Case Presentation: We report on a 67-year-old male who presented with painful, palpable papules on his right buttock. MRI revealed multifocal dermal nodules demonstrating low signal intensity on T1-weighted images and high signal intensity with a distinctive peripheral high-signal halo on T2-weighted images. Notably, T1 gadolinium fat-saturated sequences exhibited marked enhancement with a characteristic peripheral rim enhancement pattern. The lesions were confined to the cutaneous layer. Initial radiological differentials included post-inflammatory granuloma and sarcoma. Histopathological examination confirmed PMHE. PET/CT demonstrated no evidence of systemic metastasis, and the patient has remained recurrence-free for two years following surgery.

Conclusion: This report highlights a rare case of cutaneous PMHE and details its distinctive MRI features, particularly the peripheral rim enhancement. Given its rarity and often non-specific clinical and imaging presentations, there is a significant potential for misdiagnosis. Therefore, it is crucial for radiologists to be aware of PMHE and familiarize themselves with its characteristic radiological patterns to facilitate accurate, timely diagnosis and ensure appropriate patient management.

We apologize for any inconvenience caused and appreciate the opportunity to rectify this matter.

The original article can be found online at: https://www.eurekaselect.com/article/146820

Original:

3.1. Proposed Hie Detection Methodology

3.1. Input Image

Corrected:

3.1. Proposed Hie Detection Methodology

3.2. Input Image

Methods: In this prospective cohort study, 88 healthy female radiology students (mean age: 21.4 ± 1.8 years) underwent single-voxel ¹H-MRS of the liver using a 3T Siemens Magnetom Vida scanner. Spectra were acquired with a point-resolved spectroscopy (PRESS) sequence (TR = 2000 ms, TE = 40 ms, voxel size = 20 × 20 × 20 mm³), with automated shimming and unsuppressed water referencing. Spectral analysis was performed using LCModel (v6.3), applying quality thresholds (Signal-to-Noise Ratio (SNR) > 5, linewidth < 0.1 ppm, Cramér–Rao Lower Bound (CRLB) < 20%. Hepatic choline concentrations were expressed in Institutional Units (IU). Dietary intake was assessed using a validated Food Frequency Questionnaire (FFQ).

Results: High-quality spectra were consistently obtained (mean SNR: 12.6 ± 3.1; linewidth: 0.048 ± 0.012 ppm). Mean hepatic choline concentration was 4.63 ± 1.21 IU, while mean dietary intake was 29.1 ± 8.7 mg/day. A significant positive correlation was observed (r = 0.555, p < 0.001). Regression analysis confirmed dietary intake as a significant predictor (β = 0.56, R² = 0.308, p < 0.001).

Discussion: These findings demonstrate that ¹H MRS at 3T provides reproducible hepatic choline quantification and captures meaningful variability linked to dietary intake. The observed correlation highlights the potential of MRS as a translational biomarker of nutrient related liver metabolism. Integrating MRS into multiparametric liver imaging protocols may enhance early detection of metabolic alterations and broaden the scope of noninvasive liver assessment.

Conclusion: ¹H-MRS at 3T is a feasible and reproducible technique for hepatic choline quantification. By measuring metabolites directly in the liver at their site of production, rather than in circulation, where concentrations may be altered, MRS provides physiologically relevant insights into nutrient-related hepatic metabolism. Its correlation with dietary intake highlights its potential as a translational imaging biomarker for early detection and risk stratification of nutrient-sensitive liver conditions.

We apologize for any inconvenience caused and appreciate the opportunity to rectify this matter.

The original article can be found online at: https://www.benthamscience.com/article/148516

Original:

Affiliation:

³Department of Radiology, Huizhou First People's Hospital, Huizhou, 516001, Guangdong, P.R. China

Corrected:

Affiliation:

³Department of Radiology, Huizhou First Hospital, Huizhou, 516001, Guangdong, P.R. China

Methods: The ultrasound and clinical features of 16 histologically confirmed cases of SO (mean age 45 ± 10 years) were analyzed. Key ultrasound parameters evaluated included tumor size, internal echo patterns, calcification, blood flow (Adler grading), and pelvic effusion.

Results: Half of patients with SO have been found to be postmenopausal women over 50 years of age, and that most tumors are discovered incidentally during routine examination. The large cystic components with regular margins, accompanied by calcified and vascularized solid elements, are ultrasound characteristics of SO. In particular, the presence of calcification and distinct vascular patterns on Doppler imaging (as per Adler classification) has been identified as a critical marker distinguishing SO from other adnexal masses.

Discussion: Compared to existing SO research, this study has found the ultrasound characteristics of SO to mostly manifest as a large cystic echo, regular boundaries, and calcification. At the same time, compared to the existing imaging techniques, such as CT and MRI, characteristic ultrasonography has been found to be a good complement to the diagnosis of SO.

Conclusion: When an adnexal tumor is classified as O-RADS 3-5 and exhibits features, such as a large cystic echo, regular boundaries, and calcification, SO should be considered in the differential diagnosis. These findings can enhance the accuracy of preoperative assessment, facilitate individualized surgical planning, and contribute to improved clinical management by reducing the likelihood of misdiagnosis.

Methods: A retrospective analysis was conducted on 93 patients diagnosed with solitary lung adenocarcinoma who underwent ¹⁸F-FDG PET/ CT imaging and EGFR mutation results. The patients were divided into training (46 cases) and testing (47 cases) cohorts. Radiomic features were extracted from the primary tumor sites' PET and CT images. Feature selection was performed using the Mann-Whitney U test and least absolute shrinkage and selection operator (LASSO) regression. A radiomics score (Rad-score) was constructed, and combined models incorporating clinical factors and metabolic parameters were developed. Predictive performance was evaluated using receiver operating characteristic (ROC) curves, area under the curve (AUC), accuracy, and decision curve analysis (DCA).

Results: The radiomics model achieved AUCs of 0.865 (95% CI: 0.747–0.983) and 0.737 (95% CI: 0.572–0.901) in the training and testing sets, respectively, with corresponding accuracies of 80.9% and 78.3%. The clinical model alone demonstrated inferior performance, with AUCs of 0.637 and 0.645. The combined model showed slightly improved AUCs (0.885 and 0.714) but did not significantly outperform the radiomics-only model (P > 0.05). DCA indicated greater clinical utility for the radiomics model across a wide range of threshold probabilities.

Discussion: PET/CT-based radiomics research has also achieved good efficacy in predicting EGFR gene mutations. Compared with morphological imaging techniques, such as X-ray, ultrasound, and CT, ¹⁸F-FDG PET/CT imaging has the significant advantage of providing functional and metabolic information of lesions. Both radiomics and composite models could predict EGFR mutation status in lung adenocarcinoma patients, but the radiomics model showed slightly better clinical predictive efficacy than the composite model.

Conclusion: The radiomics model and the combined model integrating Rad-score with clinical factors demonstrated comparable abilities in effectively predicting EGFR mutation status in patients with lung adenocarcinoma. These models could offer a non-invasive approach for identifying EGFR mutations.

Methods: In this retrospective case-control study, 96 T2DM patients with LAD stenosis ≥50% (by CAG) and 96 with <50% stenosis were consecutively enrolled. All participants underwent two-dimensional echocardiography (2DE), two-dimensional speckle tracking echocardiography (2D-STE), and coronary artery ultrasound imaging (CA-USI). Diagnostic performance was compared with CAG as the reference standard.

Results: 2D-STE and CA-USI demonstrated superior diagnostic performance for LAD stenosis compared to 2DE. Specifically, 2D-STE yielded an area under the curve (AUC) of 0.818, sensitivity of 0.760, and specificity of 0.875; CA-USI showed an AUC of 0.849, sensitivity of 0.802, and specificity of 0.895; while 2DE had an AUC of 0.583, sensitivity of 0.239, and specificity of 0.927. Group differences in regional wall motion abnormality, LAD plaque, global longitudinal strain, and peak diastolic velocity were all significant (P<0.05).

Discussion: These findings indicated that 2D-STE and CA-USI outperformed conventional 2DE in detecting LAD stenosis among T2DM patients, providing more comprehensive functional and structural insights. The integration of strain imaging and coronary ultrasound enables earlier detection of subclinical myocardial impairment and plaque burden, offering practical value for risk stratification and longitudinal follow-up in diabetic populations. Compared with prior single-modality echocardiographic assessments, the multimodal approach in this study enhances diagnostic confidence and may reduce reliance on invasive CAG for preliminary evaluation. However, as a retrospective single-center analysis, potential selection bias and the modest sample size may limit generalizability. Future multicenter prospective trials are warranted to validate these findings and explore the incorporation of artificial intelligence-assisted analysis to improve precision and reproducibility.

Conclusion: Multimodal echocardiography, especially 2D-STE and CA-USI, provides a more accurate assessment of LAD stenosis in T2DM patients than conventional 2DE. Specifically, for detecting LAD stenosis ≥50%, 2D-STE achieved an AUC of 0.818, sensitivity of 0.760, and specificity of 0.875; CA-USI yielded an AUC of 0.849, sensitivity of 0.802, and specificity of 0.895; while 2DE had an AUC of 0.583, sensitivity of 0.239, and specificity of 0.927. These findings support the clinical utility of 2D-STE and CA-USI for comprehensive coronary evaluation in patients with T2DM.

Case Presentation: In this study, we report the case of an 81-year-old woman who presented with sudden anal protrusion of small bowel loops. Computed tomography (CT) demonstrated a rectal wall defect, pneumoperitoneum, and herniation of the small bowel with features suggestive of strangulation. Emergency laparotomy revealed a firmly impacted ileal segment plugging a perforation at the rectosigmoid junction, likely due to increased intra-abdominal pressure, necessitating small bowel resection and the Hartmann procedure. Early diagnosis and prompt surgical intervention led to a favorable postoperative course.

Conclusion: This case highlights the critical role of CT in identifying rectal perforation and intrarectal small bowel evisceration.

Methods: This retrospective single-center study (December 2020-February 2023) analyzed relevant parameters of the left upper lobe (LUL) and right upper lobe (RUL) in 170 lung cancer patients and 126 healthy individuals. Subgroups were defined by cancer-free lobes (129 patients/126 controls for LUL; 120 patients/126 controls for RUL). Univariate and multivariate binary logistic regression analyses were used for analysis.

Results: The emphysema-related 15th percentile of CT attenuation values (PI-15) was significantly associated with lung cancer, with lower values in patients’ LUL. Pulmonary vascular parameters (diameter, count, area at 6 mm/24 mm from the lung surface) differed significantly; the patients had smaller diameters, higher counts, and larger areas at 6 mm in the LUL. Airway parameters (Awt-Pi10, level 6 wall thickness) were higher in patients’ LUL. Multivariate regression identified PI-15 and vascular diameters (6 mm/24 mm) in LUL [area under the curve (AUC) = 0.841, 95% confidence interval (95% CI): 0.789–0.892] and vascular diameters (6 mm/24 mm) and vascular count at 24 mm from the lung surface in RUL (AUC=0.819, 95% CI:0.766–0.872) as significant predictors (all P<0.001).

Conclusion: AI-derived quantitative CT parameters of emphysema, vasculature, and airways are associated with lung cancer and may serve as complementary tools for clinical risk assessment.

Methods: According to the revised Atlanta classification, a prospective assessment was performed to examine the correlation between DW MRI and apparent diffusion coefficient (ADC) values with the severity of acute pancreatitis (AP) in a sample of 34 patients diagnosed with AP.

Results: The mean ADC value of mild edematous pancreatitis was 1.14±0.06x10-3 mm²/sec, moderate edematous pancreatitis was 1.18±0.16x10-3 mm²/sec, severe necrotizing pancreatitis was 1.99±0.06x10-3 mm²/sec, and that of the normal pancreas was 1.54±0.05 x10-3 mm²/sec. Based on the revised Atlanta classification, there was a significant difference between the ADC values of normal pancreas and acute, severe, and mild/moderate pancreatitis, while there was no significant difference between mild and moderate pancreatitis cases. ROC analysis yielded high accuracy in differentiating normal pancreas from acute pancreatitis and severe pancreatitis from non-severe pancreatitis (AUC=0.827 and 0.870, respectively).

Discussion: In the current study, the qualitative assessment of DWI images indicated that all cases of mild acute pancreatitis (AP) displayed true diffusion restriction, while facilitated diffusion was observed in 80% of patients diagnosed with necrotizing pancreatitis. Our findings have validated the outcomes of earlier research regarding the average ADC values of both the healthy and acutely inflamed pancreas. According to the Revised Atlanta Classification, DWI has the ability to assist in the prompt diagnosis of acute pancreatitis and to differentiate mild forms from severe ones.

Conclusion: DW-MRI using both qualitative and quantitative methods provides a concise, safe, and radiation-free imaging method for early detection and assessing the severity of acute pancreatitis.

Case Presentation: A 52-year-old female, presenting with a 7-month headache history, worsening over the past 10 days, with new-onset left lower limb weakness. She reported difficulty lifting the left leg, dragging during ambulation, and a “stepping on cotton” sensation. No significant past medical history.

Conclusion: This case highlights that the surgical approach must be determined based on the precise tumor-to-brain anatomy provided by 3D printing technology, while also accounting for the patient’s complete situs inversus and dominant hand.

The original article can be found online at:

https://www.benthamscience.com/article/147720

Original:

FUNDING

None.

Corrected:

FUNDING

This work was supported by the Scientific Research Project of Wuhan Municipal Health Commission, China (Grant No. WX23Z75).

Methods: A retrospective collection of clinical and imaging data was conducted on 203 patients who underwent pathology-proven procedures from October 2015 to August 2024 at two hospitals. Tumor Regions of Interest (ROIs) were delineated on NCCT images, and the K-means algorithm was used to jointly cluster the training and validation sets. Radiomics features were extracted, followed by feature selection using the Minimal-Redundancy- Maximal-Relevance (mRMR) and Least Absolute Shrinkage and Selection Operator (LASSO) methods. Univariate and multivariate logistic regression analyses were conducted to identify clinical independent risk factors. The clinical, radiomics, and habitat models were constructed after selection of the clinical and radiomics features. The optimal radiomics model was combined with independent clinical risk factors to develop a nomogram and a combined diagnostic model. The performance of each model was evaluated using the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC), and the DeLong test was used to compare model performance. Calibration curves and Decision Curve Analysis (DCA) were utilized to evaluate model calibration and clinical net benefit, respectively.

Results: Four distinct habitat areas were identified through clustering analysis. The habitat_all model achieved superior predictive performance, with AUCs of 0.903 in the training set and 0.846 in the validation set. This model outperformed the clinical model (training set AUC: 0.837; validation set AUC: 0.823), the conventional intra-tumor radiomics model (training set AUC: 0.845; validation set AUC: 0.840), and each of the four individual habitat models (training set AUCs: Habitat1 = 0.839, Habitat2 = 0.847, Habitat3 = 0.822, Habitat4 = 0.859; validation set AUCs: Habitat1 = 0.823, Habitat2 = 0.840, Habitat3 = 0.827, Habitat4 = 0.842). Furthermore, the nomogram integrating clinical independent risk factors (age and smoking history) with the habitat_all model showed improved predictive performance (AUCs for the training and validation sets were 0.953 and 0.883, respectively) and demonstrated significant clinical net benefit.

Conclusion: Habitat radiomics analysis based on NCCT enables accurate differentiation between PA and AL, providing novel insights for clinical diagnosis and treatment.

Methods: This retrospective study included 160 rectal cancer patients confirmed by pathology at our institution between September 2018 and June 2023. After screening, 137 patients were enrolled, comprising 71 patients with SLM and 66 without SLM. Clinical characteristics such as age, gender, tumor (mrT) staging, lymph node (mrN) staging, tumor size, tumor distance from the anal verge, location, and circumferential range were analyzed, with mrT and mrN staging showing statistical significance (p < 0.012). Radiomic features were extracted from regions of interest (ROIs) on T2WI and DWI using Pyradiomics after manual segmentation in ITK-SNAP. A total of 3,452 radiomic features (1,726 each from T2WI and DWI) were extracted, of which 14 features (4 from T2WI and 10 from DWI) were selected using the LASSO. Predictive models were developed using three machine learning algorithms: Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF), with a five-fold cross-validation strategy.

Results: Among the machine learning algorithms, the RF consistently outperformed LR and SVM across all models. The Optimal model yielded the highest predictive performance, with RF achieving an AUC of 0.82 (95% CI: 0.66–0.93), an accuracy of 0.71, and an F1-score of 0.74. RF also showed superior performance in the Combined-Optimal model (AUC = 0.76, accuracy = 0.71). In contrast, models built using LR and SVM algorithms demonstrated moderate performance, with lower AUC values ranging from 0.68 to 0.70. Confusion matrix analysis confirmed RF’s superior classification ability, accurately predicting SLM and non-SLM cases.

Discussion: The incorporation of radiomics and RF-based models conveys a promising, non-invasive approach for enhancing early detection and risk stratification of SLM, which could help with more reliable clinical decision-making and individualized treatment planning for patients with rectal cancer.

Conclusion: The optimal feature set-based predictive model demonstrated the highest accuracy for SLM detection, with the RF algorithm outperforming LR and SVM by consistently achieving the best AUC and balanced diagnostic performance.

Methods: We conducted a comprehensive bibliometric analysis of 4,280 Web of Science articles using CiteSpace, Bibliometrix, and SciExplorer, with dual screening to ensure data quality.

Results: Meningioma MRI research exhibited an S-shaped growth pattern. Research hotspots are transitioning toward AI applications. 502 core authors contributed to 83% of publications, with notable cross-disciplinary collaboration. The U.S. and China dominated production, while Europe demonstrated exceptional efficiency. Institutions, including Harvard, led development. Seventeen core journals conformed to Bradford's law, with the knowledge foundation established by highly cited papers in the field.

Discussion: The findings reveal an AI-guideline temporal gap and a field-strength validation deficit, underscoring the need for equitable, low-field-compatible AI tools.

Conclusion: We systematically delineate three evolutionary stages: structural imaging, functional integration, and intelligent analysis. AI-driven models have achieved enhanced diagnostic accuracy (AUC 0.82–0.97), but remain limited by heterogeneous data standards, low algorithm interpretability, and uneven global resources. Multicentre standardized protocols, interpretable AI frameworks, and lightweight algorithms compatible with ≤1.5 T scanners should be prioritised. By integrating burst-sigma mapping with global equipment metrics, we provide quantitative evidence supporting a field-strength-agnostic strategy for equitable AI deployment.

Methods: A total of 104 athletes and 20 healthy sedentary controls underwent a 3.0T cardiovascular magnetic resonance scan. Cardiac function parameters, T1, and extracellular volume values of 16 segments for the left ventricle were measured, respectively. These parameters were separately compared between athletes and controls, as well as between the positive and negative athlete groups. Four machine learning models were constructed for the prediction of cardiac remodeling and /or myocardial fibrosis.

Result: The most effective model was Gradient Boosting Machine, with an AUC value of 0.899, accuracy of 82.7%, sensitivity of 90.0%, and specificity of 81.0%. The top three important factors were the native T1 value of segment 10, the extracellular volume value of segment 3, and body surface area.

Discussion: The direct reason for the increased native T1 value and ECV observed in our study was CR for athletes, which may reveal the relationship between CR and MF. The so-called physiological CR of athletes has certain potential risks. Furthermore, the limitations of this study are that only male athletes were included, and the sample size of the control group was small. This study was a single-center study, and there were selection biases.

Conclusion: Native T1 and extracellular volume values increased in athletes with cardiac remodeling, which may reveal the relationship between cardiac remodeling and myocardial fibrosis. Early cardiac magnetic resonance imaging is conducted to monitor the myocardial native T1 and ECV values of athletes, assess their risk levels, and guide their subsequent surge planning to reduce the occurrence of adverse cardiovascular events.

Case Presentation: Case 1: A 16-year-old with erythrodermic mycosis fungoides (stage IIIA) refractory to multiple systemic and skin-directed therapies who achieved remission after haploidentical allogeneic hematopoietic stem-cell transplantation. Case 2: A 3-year-old with aggressive cytotoxic CD8-positive Tcell lymphoma with EBV-associated disease and severe infectious complications during CHOP-based therapy, culminating in death despite salvage treatments and EBRT. Case 3: A 10-year-old with CD30-positive primary cutaneous anaplastic large cell lymphoma with a relapsing course, treated with BFM-90 chemotherapy, gemcitabine, pegylated doxorubicin plus total skin electron beam therapy, and ongoing PUVA with good dermatologic control. Across cases, diagnosis relied on clinicopathologic correlation with immunohistochemistry and staging CT; serum IgE was elevated in all three children.

Conclusion: Pediatric PCLs show heterogeneous behavior and therapeutic responses. Early biopsy of atypical or treatment-refractory eruptions, comprehensive histopathology and immunophenotyping, targeted EBV testing when suggested, and appropriate use of skin-directed radiotherapy (EBRT/TSEBT) and transplantation in selected refractory disease are essential. Multidisciplinary management and equitable access to specialized therapies are critical to optimize outcomes.

Methods: In this retrospective study, 23 healthy subjects underwent the MAGiC sequence (at 3.0 T) with three slice thicknesses: 3 mm (TH3), 4 mm (TH4), and 5 mm (TH5). The T1, T2, and PD values were measured in various knee joint cartilage regions by two experienced radiologists, including the lateral femoral condyle (LFC), lateral tibial plateau (LTP), medial femoral condyle (MFC), medial tibial plateau (MTP), patella (PAT), and trochlea (TRO). The effects of varying slice thicknesses (TH4 vs. TH3 and TH5 vs. TH3) were analyzed using paired t-tests or Wilcoxon signed rank tests, with statistical significance set at P < 0.025. Intra-rater and inter-rater reliability were also assessed.

Results: Measurements of T1, T2, and PD values demonstrated high intra- and inter-rater reliability. Minimal differences were observed across slice thicknesses for T1WI, T2WI, and PDWI images. T2 and PD values showed little variation, while T1 mapping revealed significant differences. T2 values were consistent across regions, except for the LFC.

Discussion: TH4 and TH5 can replace TH3 for knee joint scanning while reducing scan time, with minimal differences in anatomical depiction across sequences. MAGiC technology significantly improves efficiency by acquiring quantitative data in a single scan, demonstrating stable T2 values unaffected by slice thickness, though T1 and PD values are thickness-dependent. This technique holds clinical value for cartilage injury assessment but requires further research on the applicability of multiplanar imaging.

Conclusion: T2 values obtained with the MAGiC sequence are stable across TH3, TH4, and TH5, allowing for reliable cartilage T2 quantification using TH5 to reduce patient scan time.

Materials and Methods: A total of 72 patients with pathologically diagnosed CRC underwent abdominal dual-energy CT, following which virtual unenhanced, linear blending, and non-linear blending images were generated by post-processing reconstruction. Both subjective and objective evaluations were conducted on these images, with signal-to-noise (SNR) and contrast-to-noise ratio (CNR) calculations conducted for organs, such as the liver, pancreas, and spleen.

Results: Virtual unenhanced images of CRC, extraserosal fat of the tumor, liver, pancreas, spleen, kidney, and subcutaneous fat showed a lower signal intensity than both linear and non-linear blending images (P < 0.05), while the CNR of virtual unenhanced images was higher than linear and nonlinear blending images (P < 0.05). Except for CRC lesions, the SNR of other organs in virtual unenhanced images was higher than in linear and non-linear blending images (P < 0.05). There were no significant differences in subjective image scores and the number of conventional lesions between virtual unenhanced image, linear, and non-linear blending (P ≥ 0.05). The Kappa coefficients for evaluating extraserosal invasion were 0.722, 0.584, and 0.584 for virtual unenhanced, linear blending, and non-linear blending images, respectively, with corresponding accuracies of 86.1%, 79.2%, and 79.2%.

Conclusion: Virtual unenhanced images of patients with CRC can provide high-quality images for diagnostic evaluation, potentially replacing linear blending and non-linear blending images in plain scans.

Methods: This retrospective study analyzed sagittal T2WI from 160 patients with pathologically confirmed stage IB-IIA cervical cancer to predict vaginal invasion. Following an 8:2 training-test split, radiomic features were extracted from manually delineated intratumoral regions and four concentrically expanded peritumoral regions (1-4mm). Features selection by Pearson correlation and LASSO regression. Random forest models incorporating intratumoral and peritumoral (0-4mm) features were constructed, with ROC analysis identifying the optimal model. Subsequently, a 3D-ResNet architecture, enhanced with anisotropic convolutional layers and sophisticated data augmentation, was developed and optimized using the optimal ROI configuration. Model interpretability was facilitated using Grad-CAM, with performance assessed by AUC, sensitivity, specificity, accuracy, and precision.

Results: The AIC-enhanced 3D ResNet-18 model, integrating intratumoral and 3mm peritumoral regions, showed superior test performance (AUC: 0.784, Sensitivity: 0.650, Specificity: 0.765, Accuracy: 0.611, Precision: 0.686) versus the baseline (AUC: 0.742), representing a 6% AUC improvement. Grad-CAM heatmaps identified diagnostically relevant regions within the tumor microenvironment, enhancing biological plausibility and model interpretability.

Discussion: This attention-integrated 3D ResNet-18 framework (AUC=0.784) facilitates non-invasive vaginal invasion detection for fertility-sparing decisions, validated through Grad-CAM tumor localization; however, derivation from a single-center cohort warrants external validation and prospective studies before clinical translation.

Conclusion: This preliminary study demonstrates promising deep learning performance (3D ResNet-18+Grad-CAM+AIC) for vaginal invasion assessment, despite moderate n; however, a single-center retrospective design limits generalizability.

We apologize for any inconvenience caused and appreciate the opportunity to rectify this matter.

The original article can be found online at:

https://www.benthamscience.com/article/124894

Original:

e1875660325101501

Corrected:

e290622206508

Methods: Data were retrospectively collected from 1,100 MPI studies (2017-2024) with 932 participants included after excluding poor-quality images. Imaging was performed using a GE SPECT/CT Optima NM/CT640 camera, and images were reconstructed using the OSEM algorithm (Myovation®). Volumetric and quantitative parameters were extracted for analysis (e.g., Left Ventricular Ejection Fraction (LVEF), End-Systolic Volume (ESV), End-Diastolic Volume (EDV), Stroke Volume (SV), and dyssynchrony parameters). Reference ranges were derived using descriptive statistics, and comparative analyses examined how parameters varied by sex and age. Regression analysis and Receiver Operating Characteristic (ROC) curves were used to assess the relationship between abnormal LVEF and dyssynchrony indices.

Results: The study analysed 932 participants under stress and 462 at rest, yielding adequate statistical power. Average LVEF was 68% in both conditions. At stress, mean EDV was 95.1 mL and mean ESV was 34.7 mL; corresponding values at rest were 104.8 mL and 40.1 mL. Diagnosis significantly influenced all volumetric and dyssynchrony parameters at rest and during stress (all p < 0.001), showing progressive ventricular dilation, reduced LVEF, and increased dyssynchrony from the normal to the ischemic and infarcted groups. Sex significantly affected LVEF and ventricular volumes, with females exhibiting higher LVEF and smaller volumes, while age had minimal effects. Resting dyssynchrony indices correlated strongly with stress LVEF, particularly in diseased groups. Logistic regression demonstrated good discrimination (AUC = 0.80) and calibration, identifying resting volumetric and clinical factors as independent predictors of abnormal stress LVEF.

Discussion: This study defines sex- and age-specific reference ranges for gated SPECT MPI–derived ventricular function in a Kuwaiti population. Ventricular volumes, systolic function, and dyssynchrony varied significantly by sex and diagnosis, with progressive impairment across disease groups. Logistic regression analysis with multiple variables identified resting volumetric indices and demographic characteristics, rather than dyssynchrony measures, as the primary independent predictors of abnormal left ventricular function during stress. The model demonstrated good discriminatory ability and calibration.

Conclusion: Sex- and age-specific reference ranges for gated SPECT MPI reveal clinically meaningful variation in ventricular function and dyssynchrony by diagnosis. Logistic regression findings indicate that conventional ventricular volumes and patient characteristics primarily drive stress systolic impairment, while dyssynchrony indices offer complementary but not independent prognostic value.

Methods: A consecutive cohort of patients who completed dynamic myocardial perfusion imaging and routine myocardial perfusion imaging (MPI) using CZT cardiac-dedicated SPECT were selected and followed up for at least 24 months to determine the occurrence of major adverse cardiac events (MACEs). Patients were divided into groups with no MACEs and MACEs. Differences between the two groups in baseline characteristics, semiquantitative, and quantitative parameters were compared. Cox regression analysis was performed to identify predictive factors associated with MACEs. Kaplan-Meier survival curves were plotted, and log-rank tests were performed to compare the incidence of MACEs between the normal MFR group and the reduced MFR group.

Results: A total of 369 patients with negative routine MPI results were included in this study, with an average age of 61.82±8.68 years (113 males and 256 females). The median follow-up duration was 30 months [IQR (25, 34)], during which 73 patients experienced MACEs. The incidence of MACEs was significantly higher in patients with reduced MFR than in those with normal MFR (P<0.05). Cox regression analysis identified reduced MFR as an independent predictor of MACEs (HR: 2.076, 95%CI: 1.174-3.669, P=0.012). The proportion of patients diagnosed with obstructive coronary artery disease (OCAD) was significantly higher in the MACE group compared to the no MACE group (P<0.05).

Discussion: These findings provide critical clinical insights, particularly for patients in whom myocardial ischemia is not detected via traditional semiquantitative MPI analysis. CZT cardiac-dedicated SPECT, which enables quantitative assessment of myocardial blood flow, serves as a more precise tool for early CAD diagnosis and prognostic evaluation. This underscores the role of CZT cardiac-dedicated SPECT in assessing myocardial ischemia and prognosis among patients with negative conventional MPI, helping to identify high-risk individuals that conventional MPI may overlook. By leveraging CZT cardiac-dedicated SPECT to obtain absolute quantitative myocardial blood flow (MBF) and MFR, myocardial perfusion is quantified more accurately, thereby overcoming the limitations of traditional MPI and providing a more reliable basis for early clinical diagnosis and treatment.

Conclusion: MFR measured with CZT cardiac-dedicated SPECT can effectively predict the prognosis of patients with suspected or confirmed CAD and normal MPI. Reduced MFR is significantly associated with a higher incidence of MACEs, and MFR reduction is an independent predictor of MACEs.

Case Presentation: In this study, we present a case involving a 57-year-old female patient with a history of consuming raw or undercooked frog meat and pork. Imaging studies identified an intraspinal occupying lesion. The patient subsequently underwent surgical intervention, which resulted in a pathological diagnosis of intraspinal sparganosis. Following this diagnosis, anthelmintic therapy was administered as part of the comprehensive treatment protocol.

Conclusion: During the differential diagnosis of intraspinal space-occupying lesions, the intraspinal lesion observed on MRI plain scan appears as a solitary, irregular mass with abnormal signal characteristics. On T1-weighted imaging (T1WI), the lesion demonstrates isointense signal intensity; on T2- weighted imaging (T2WI), it displays mildly hyperintense signal, with markedly increased signal intensity on fat-suppressed T2WI. The lesion exhibits poorly defined margins and exerts a significant mass effect. Following contrast administration, the majority of lesions show marked, homogeneous, mass-like enhancement. Intraspinal sparganosis should be considered in the context of a comprehensive evaluation of the patient's MRI findings, medical history of potential exposure, and serological testing for parasitic antibodies. This integrated diagnostic strategy contributes to improved preoperative diagnostic accuracy, which in turn enhances treatment outcomes and prognosis.

Methods: Three hundred and sixty-nine patients were recruited as the training group, with 249 benign and 120 malignant STTs, and 127 patients as the validation group, with 93 benign and 34 malignant STTs. We extracted the radiomic features of the US images using an open-source Python package. We selected the most relevant features using the least absolute shrinkage and selection operator (LASSO) regression. Then we used a combination of clinical indexes, radiomic features, and color-Doppler US to construct a diagnostic model for STTs. The diagnostic performance of the model was evaluated by measuring its sensitivity, specificity, area under the receiver operating curve (AUC), and calibration.

Results: We selected 20 radiomic features of the US images. The model based on the clinical indexes, radiomic features, and color-Doppler scores showed good diagnostic performances on both the training [AUC: 0.97 (0.95-0.98)] and validation datasets [AUC: 0.93 (0.86-0.99)]. The model also presented good calibration with the original results.

Discussion: We extracted radiomic features of ultrasound images of patients with STTs and constructed a clinical-imaging model for differentiating malignant and benign STT lesions. A nomogram displayed a clinical-imaging model, which showed good diagnostic efficacy and calibration in both the training and validation datasets. The clinical-imaging model has potential value for clinical use.

Conclusion: The diagnostic model based on clinical, US radiomic, and imaging features presented a high diagnostic performance in STTs, which can have potential value in further clinical utilization.

Methods: Through literature review and generalization of our clinical experiences, this review thoroughly described the features, mechanisms, advantages, drawbacks, and prospects of NBI in the treatment of head and neck cancer.

Results: NBI is an emerging endoscopic technology that emits an ambient light at wavelengths of 415 nm (blue) and 540 nm (green) to clearly visualize the details on the mucosal surface. It presents potent efficiencies in the preoperative, intraoperative, and postoperative surveillance and diagnosis of head and neck cancer.

Conclusion: NBI is a front-edge imaging technology that allows early screening, precise treatment, and postoperative monitoring of head and neck cancer.

Method: Nine standardized phantoms were constructed using agar gel with embedded tubes of three inner diameters (4mm, 2mm, and 1.4mm) representing ampullary, isthmic, and interstitial segments. Three contrast agents with different viscosities were tested: gadolinium-saline (2.6 mPa·s), gadolinium-iopromide (7.9 mPa·s), and gadolinium-iodixanol (8.7 mPa·s) at 37°C. T1-weighted 3D-mDIXON sequences with keyhole technology were employed on a 1.5T MRI scanner. Signal intensity measurements and qualitative assessment (good/fair/poor) were performed by blinded evaluators.

Results: No significant differences in signal intensity were found between contrast agents of different viscosities (P>0.05). However, tube diameter significantly affected imaging quality (P<0.001). The 4 mm tubes showed the highest SI (5554.49±1042) with 100% good imaging, the 2 mm tubes showed intermediate SI (733.65±78.76) with 100% fair imaging, and the 1.4 mm tubes showed the lowest SI (444.55±34.70) with 100% poor imaging across all contrast agents.

Discussion: Fallopian tube inner diameter is the primary determinant of MR-HSG imaging quality, while contrast agent viscosity (within 2.6-8.7 mPa·s range) shows no significant effect under controlled conditions. This study provides foundational data for understanding physical factors affecting MRHSG quality and suggests that anatomical factors may be more critical than contrast properties for clinical protocol optimization, potentially reducing procedure costs while maintaining diagnostic quality.

Conclusion: Optimizing spatial resolution to minimize partial volume effects may be more beneficial than modifying contrast agent properties for improving visualization of narrow fallopian tube segments. Clinical validation studies are warranted to confirm these findings in the complex in vivo environment.

Methods: A total of 217 pathology-confirmed GISTs were retrospectively enrolled and divided into low-risk and high-risk groups. Significant predictors were selected from clinical and radiological characteristics to build a prediction model. Radiomics features were extracted from the intratumoral region, the 3-mm peritumoral region, and the 5-mm peritumoral region. After ANOVA and LASSO feature screening, logistic regression was applied to construct the radiomics model. The Rad-score of the optimal radiomics model was calculated and combined with the selected radiological characteristics to develop a combined model and a nomogram. ROC curves were used to assess the predictive performance of each model, while calibration curves and decision curve analysis were used to evaluate their clinical utility. The SHapley Additive Explanations (SHAP) method was applied to perform interpretability analysis of the optimal model.

Results: A radiological model (RM), five radiomics models, and a combined radiological characteristics plus Rad-score model (CRM) were constructed. In the validation set, the AUCs of the RM and CRM were 0.839 and 0.924, respectively. The intratumoral plus 3-mm peritumoral radiomics model (ITV+PTV3) achieved the best performance in the validation set, with an AUC of 0.934.

Discussion: The ITV+PTV3 model shows strong potential for objective GIST risk stratification but requires multi-center prospective validation to ensure generalizability beyond the limitations of this retrospective dataset.

Conclusion: Radiomics models based on intratumoral and peritumoral regions perform well in predicting the risk grade of GISTs and may effectively guide accurate preoperative diagnosis and treatment planning.

Methods: The proposed model combines Capuchin Red Kite Optimization (CRKO) with a Swin Transformer–based Convolutional Block Attention Module (ST-CBAM). A Butterworth filter is applied during preprocessing to enhance image quality. ResNet and Vision Transformer are used for feature extraction, capturing local and global patterns, respectively. These features are fused using Adaptive Gated Recurrent Units (AGRU) and optimized with CRKO. The model is trained and validated using a publicly available chest X-ray dataset from Kaggle.

Results: The model achieved classification accuracies of 99% for normal, 99.9% for COVID-19, and 98.2% for pneumonia cases. It recorded an AUC of 98.93%, outperforming existing models such as ACNN, 3D-CNN, LWHNN, and CA-DCNN in both accuracy and execution time.

Discussion: The integration of CRKO with ST-CBAM, along with hybrid feature extraction and fusion techniques, contributes to the model’s high performance. The results indicate a strong potential for clinical application. However, future studies should validate the model across diverse, realworld datasets to ensure generalizability.

Conclusion: The proposed deep learning framework offers a fast, accurate, and reliable solution for automated pneumonia diagnosis, showing promise for deployment in medical imaging systems.

Methods: In this retrospective study, 7,025 breast ultrasound images from our center were annotated based on pathology and split into training, validation, and internal test sets (8:1:1). The Dataset of Breast Ultrasound Images was used as the external test set. YOLO-v7 and YOLO-v8 models were trained through transfer learning after data augmentation and balancing the classes. Performance was compared on internal and external test sets and was evaluated against a reader study.

Results: YOLO-v7 and YOLO-v8 reached optimal performance at epochs 294 and 135, respectively. YOLO-v7 slightly outperformed YOLO-v8 on the internal test set, while YOLO-v8 achieved higher accuracy, recall, specificity, precision, and F1 score on the external test set. Both models showed significantly higher accuracy, specificity, and precision than the senior radiologist, with YOLO-v8 achieving a significantly higher F1 score.

Discussion: YOLO-v8 demonstrated better generalization due to its anchor-free mechanism and deeper architecture, while YOLO-v7 showed signs of overfitting. Both models outperformed the junior radiologist and approached or exceeded the diagnostic performance of the senior radiologist, indicating potential to assist less experienced readers.

Conclusion: YOLO-v7 and YOLO-v8 effectively classified breast lesions. YOLO-v8 showed faster convergence and higher diagnostic efficiency, suggesting strong potential for clinical application.

Methods: A retrospective analysis was conducted on the clinical data and MRI findings of 29 patients with DPHCC and 29 propensity score-matched patients with conventional HCC, confirmed by surgical pathology, from January 2019 to January 2022 at Fudan University Zhongshan Hospital. Clinical characteristics, lesion location, morphology, size, signal intensity, enhancement patterns, vascular invasion, and lymph node metastasis were analyzed for both groups.

Results: Between the DPHCC group and the HCC group, statistically significant differences were found in cirrhosis, pathological grade, lesion morphology, enhancement patterns, delayed capsular enhancement, and lymph node metastasis. There were no statistically significant differences between the two groups in terms of age, gender, hepatitis B infection, AFP, CA199, microvascular invasion (MVI), capsular invasion, lesion size, location, vascular invasion, ADC values, and T1WI and T2WI signals.

Conclusion: Compared to HCC, DPHCC has a higher pathological grade, more irregular lesion morphology, and a higher incidence of both fast-in and slow-out and slow-in and slow-out enhancement patterns, as well as higher rates of lymph node metastasis. The findings have provided valuable insights for the accurate diagnosis of DPHCC.

Methods: Thirty-two rabbit liver VX2 tumor models were established, and transcatheter intra-arterial infusion of Bi-Ln NPs was performed using superselective intubation under digital subtraction angiography (DSA) guidance. IPTT was then carried out by inserting a near-infrared (NIR) optical fiber into the rabbit VX2 tumors under real-time ultrasound guidance. Magnetic resonance imaging (MRI) was performed one day before treatment and seven days after treatment to evaluate therapeutic efficacy, using T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), gadolinium-enhanced T1WI, and IVIM-DWI. After treatment, gross and histopathological examinations were conducted to categorize liver tumors into viable tumor, inflammatory reaction, and necrotic regions. IVIM-derived parameters were calculated and compared across these regions. Additionally, immunohistochemical analysis was performed to further assess treatment efficacy.

Results: The tumor-bearing rabbits exhibited significant therapeutic effects, as shown by comparative analysis of MRI images and parameters before and after treatment. Both the mean apparent diffusion coefficient (ADC) and diffusion coefficient (D) increased significantly after treatment (P = 0.008 and P = 0.034, respectively). Pathological analysis also revealed an elevated apoptosis rate of tumor cells, with a mean of 43.26 ± 12.26%. Across the different lesion regions, the ADC and D values were significantly lower in the viable tumor region than in the inflammatory reaction region (both P < 0.001). However, the D* values in the viable tumor region did not differ significantly from those in the inflammatory reaction region. Additionally, the ADC, D, and f values were significantly reduced in the necrotic region compared with the inflammatory reaction region (P = 0.003, <0.001, and <0.001, respectively). In the receiver operating characteristic (ROC) analysis, the diffusion coefficient (D) demonstrated the highest area under the curve for distinguishing between the inflammatory reaction and viable tumor regions.

Discussion: IVIM-DWI demonstrates strong potential for detecting early tumor responses to therapeutic interventions and for differentiating tissue types following treatment. The parameters derived from this technique may provide preliminary insight into therapy-induced physiological changes.

Conclusion: The combination of transcatheter intra-arterial infusion and IPTT represents a promising strategy for effective tumor eradication, thereby improving therapeutic outcomes. IVIM-DWI offers a quantitative tool for monitoring early treatment responses in hepatic tumors and distinguishing between different tissue types after therapy.

Methods: This retrospective study included 184 NSCLC patients with preoperative chest CT scans and confirmed pathological differentiation grades from 2022 to 2024. Radiomics features were extracted using PyRadiomics, followed by feature selection via the LASSO algorithm. A novel three-task binary classification strategy was proposed to replace conventional trinary classification, including low vs. non-low, moderate vs. non-moderate, and high vs. non-high differentiation. Four machine learning models-GBDT, RF, XGBoost, and LightGBM-were constructed and evaluated using ROC analysis, confusion matrices, and SHAP-based interpretability analysis.

Results: The GBDT model achieved the highest AUC (0.849) in the low differentiation classification task, while the RF model outperformed others in predicting high differentiation (AUC = 0.7188). The moderate differentiation task showed relatively poor performance across all models (AUC < 0.55). SHAP analysis revealed that features such as original_firstorder_Kurtosis, glrlm_RunEntropy, and wavelet-HLL_firstorder_Median played key roles in differentiating tumor grades, highlighting their biological relevance and potential utility in clinical interpretation.

Discussion: The proposed multi-binary strategy improved classification granularity and interpretability. Ensemble learning models demonstrated robust performance across tasks, especially for extreme differentiation levels.

Conclusion: This study, which combines radiomics with a multi-task machine learning framework, demonstrates prediction and can improve the accuracy and interpretability of preoperative lung cancer differentiation. The proposed model provides a non-invasive, quantitative tool with the potential to support individualized clinical decision-making. Further multicenter validation and multimodal data integration are warranted to enhance its clinical applicability.

Case Presentation: This report describes the case of a 76-year-old Chinese woman with MFS of the right calf, which progressively invaded the mid-tibia. She underwent wide tumor resection and reconstruction using a customized 3D-printed prosthesis that preserved both the tibial epiphysis and ankle joint. The procedure successfully preserved the entire articular surface, providing a viable alternative for maintaining both the function and integrity of the affected limb. The patient maintained normal knee joint function, with no evidence of recurrence or metastasis observed during the 2-month postoperative follow-up.

Conclusion: Reconstruction of critical-sized tibial defects with a customized 3D-printed non-cemented prosthesis after resection of a large MFS tumor demonstrated excellent mechanical stability during the early follow-up period in this knee and ankle joint-preserving procedure. Further investigation into the durability and long-term complication rates is necessary before this approach can be incorporated into routine clinical practice.

Objective: This study aimed to compare the performance of CNN and ViT in unsupervised deformable image registration.

Method: We have proposed a unified registration framework and evaluated both architectures. Experiments have been conducted using 4D-CT.

Results: The results have shown ViT-based registration to achieve superior performance compared to CNN-based methods.

Conclusion: The findings have indicated vision transformer architectures to be more effective than convolutional networks for unsupervised deformable registration on 4D-CT data.

Objective: This study used an Ultra-Fluid Lipiodol-based contrast medium to compare the diagnostic consistency between delayed radiographs taken 2 hours and 24 hours post-HSG.

Methods: In total, 78 patients who received HSG examinations using ultrafluid lipiodol were enrolled in this cohort study. Then, after 2 hours and 24 hours, delayed radiographs were taken, which were subsequently randomized and assigned to two folders and read by investigators to assess the patency of the fallopian tubes, uterine morphology, and pelvic cavity morphology.

Results: The delayed radiographs that were taken 2 hours and 24 hours post-HSG revealed substantial agreement in the diagnosis of fallopian tube patency (with a Gwet’s AC1 value of 0.624) and almost perfect agreement in determining uterine morphology (with a Gwet’s AC1 value of 0.943) and pelvic cavity morphology (with a Gwet’s AC1 value of 0.876). Twenty-nine (37.2%) and 3 (3.8%) patients experienced mild and moderate pain, respectively, and 3 (3.8%) patients suffered countercurrent blood flow during the HSG. After HSG, only 9 (11.5%) patients were exposed to mild pain. Vaginal bleeding did not occur either during or after HSG.

Conclusion: Taking delayed radiographs 2 hours post-HSG using Ultra-Fluid Lipiodol exhibits high consistency in evaluating tubal patency and uterine and pelvic cavity morphology compared with the traditional 24-hour scheme.

Case Presentation: In this study, we report a rare case of BHS in a 15-year-old adolescent without noticeable cervical degenerative changes who experienced recurrent, unexplained posterior circulation cerebral infarctions. Dynamic cervical magnetic resonance angiography (MRA) revealed significant compression of both vertebral arteries during head and neck rotation, confirming a diagnosis of bilateral BHS. This presentation differs from the conventional understanding that BHS predominantly affects adults and is typically unilateral, suggesting that the diagnosis should also be considered in young patients, even in the absence of typical cervical lesions.

Conclusion: This study is the first report identifying bilateral BHS as the cause of recurrent posterior circulation infarction in a teenager using dynamic MRA. Although dynamic digital subtraction angiography remains the gold standard for diagnosis, this case highlights the practical value of dynamic MRA in diagnosing BHS.

Methods: 43 IIM patients and 48 control cases were analyzed in the retrospective study. By using the 3D slicer software, 107 radiomics features were obtained for each case. The selection of variables was performed using a two-sample t-test or the Mann-Whitney U test, followed by maximum correlation minimum redundancy (mRMR). Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for dimension reduction. To assess the model performance, the receiver operating characteristic (ROC) curve was plotted.

Results: The results showed that 67 features were varying between the IIM cases and control groups (p < 0.05). With the mRMR and LASSO methods, seven features were finally determined. Regarding the radiomics model's performance, it achieved an AUC of 0.983 in the validation data.

Discussion: This study investigated microstructural differences in a specific muscle (varasimus intermedias) between Idiopathic Inflammatory Myopathy (IIM) patients and normal controls using radiomics. It identified 67 distinguishing radiomics features and successfully established a high-performance prediction model (AUC >0.9) using LASSO and mRMR for feature selection. These features likely reflect IIM-induced microstructural changes, such as inflammation and necrosis, typically visible on MRI as signal abnormalities. Radiomics thus offers a potential non-invasive alternative to muscle biopsy for assessing these changes.

Conclusion: Muscle MR radiomics is feasible for identifying idiopathic inflammatory myopathy and has the potential to serve as a non-invasive alternative to muscle biopsy.

Materials and Methods: In this study, 32 patients with 43 carotid plaques identified by B-mode ultrasound were recruited. Each B-mode ultrasound image was normalized, and the GSM of carotid plaque echogenicity was quantified using the histogram feature in Adobe Photoshop. GSM data from the thickest plaque area were obtained, and plaque length, thickness, area, and DoS were measured using ImageJ software. Correlations between plaque size, DoS, and GSM were identified and assessed using Spearman’s correlation coefficient.

Results: Significant negative correlations were observed between carotid plaque GSM and plaque size (plaque length, r = −0.34, p = 0.02; plaque thickness, r = −0.30, p = 0.04; plaque area, r = −0.40, p = 0.008), with a trend toward significant negative correlation with DoS (r = −0.26, p = 0.08).

Discussion: This study identifies an inverse relationship between carotid plaque GSM and plaque size parameters, indicating that hypoechoic plaques, characterized by lower GSM values, are generally larger and potentially more vulnerable to rupture. These findings emphasize the importance of combining structural metrics, such as plaque size and degree of stenosis, with compositional evaluation and their echogenicity for comprehensive cerebrovascular risk assessment. Hypoechoic plaques often correspond to lipid-rich, inflamed lesions with thin fibrous caps, which are histological features associated with an increased risk of cerebrovascular events. The demonstrated associations underscore the clinical relevance of GSM as a noninvasive surrogate biomarker that reflects both local plaque vulnerability and the broader systemic burden of atherosclerosis. Thus, the B-mode ultrasound-derived GSM is a practical and informative tool for enhancing risk stratification and guiding management strategies in patients with carotid artery disease.

Conclusion: Our findings reveal significant negative correlations between carotid GSM and plaque size parameters, with a nonsignificant trend for DoS. These findings suggest that hypoechoic plaques, characterized by lower GSM values, are generally larger in size and potentially more vulnerable. Future large-scale longitudinal studies with repeated evaluations are required to validate these findings.

Objective: This study aimed to evaluate the airway diameter in asthma recovery by using HRCT.

Methods: Thirty patients with asthma were recruited and underwent HRCT examination in acute exacerbation and stable phase, respectively. The inner diameter of the airway (Din) was measured from the bilateral main bronchi to all 18 segmental bronchi during acute exacerbation and the stable phase.

Results: The inner diameter of the airway reduced significantly in the acute exacerbation period compared to the stable period (P < 0.05). The mean Din reduction (%) in segmental bronchi was 12% and that in lobar bronchi was 6%. Among the 30 patients, the dorsal segmental bronchi of both lower lobes showed the highest incidence of stenosis during acute exacerbation compared to the stable phase (right: 18 cases; left: 16 cases), while the lingular bronchus exhibited the highest stenosis incidence among lobar bronchi (18 cases). Although the number of stenotic segmental and lobar bronchi demonstrated a positive correlation with disease severity across mild, moderate, and severe groups, no statistically significant differences were observed in intergroup comparisons (P>0.05).

Discussion: HRCT showed generalized airway narrowing during asthma exacerbation, which reversed with treatment. The lack of correlation with FEV1% may have resulted from the heterogeneity of airway remodeling, the static nature of CT assessment, and the disproportionate functional impact of key airway stenosis. This underscores the complementary value of anatomical imaging alongside functional testing.

Conclusion: CT images of bronchial stenosis showed obvious dilation after appropriate medication, and the inner diameter of the airway can be used as a practical and convenient index to evaluate the recovery of asthma.

Case Presentation: We, herein, report the case of a 37-year-old male presenting with isolated aortic regurgitation (AR) as the initial manifestation of Behçet's disease (BD). Initial echocardiography revealed severe eccentric AR with left coronary cusp prolapse and a vegetation-like lesion, raising suspicion of infective endocarditis; however, relapsed oral ulcers developed postoperatively, ultimately confirming BD diagnosis. Despite successful aortic valve replacement, delayed diagnosis due to absent early mucocutaneous symptoms contributed to catastrophic prosthetic valve dehiscence with severe paravalvular leak. The patient underwent an emergency Bentall procedure with venoarterial extracorporeal membrane oxygenation (VAECMO) support but succumbed to cardiogenic shock and multiorgan failure. Pathological analysis demonstrated tissue necrosis with minimal inflammation.

Conclusion: Isolated AR may be BD's initial manifestation, preceding classic symptoms by months. Echocardiographic features, including valve prolapse and perivalvular lesions, despite their non-specificity, should prompt screening for BD. Inherent tissue fragility in BD significantly elevates postoperative risks of paravalvular leak and prosthetic valve dehiscence. Early identification, optimal surgical procedure, and timely immunosuppressive therapy are essential to improve the prognosis of cardiac BD.

Materials and Methods: This retrospective study enrolled 574 breast cancer patients who underwent MRI and surgery from January 2021 to December 2023. Patients were classified as LVI-positive (n=174) or LVI-negative (n=400) based on postoperative pathology. Breast edema on FS T2WI was scored from 1 to 4 (BES 1, no edema; BES 2, peritumoral edema; BES 3, prepectoral edema; and BES 4, subcutaneous edema). Univariate and multivariate binary logistic regression analyses were performed to identify risk factors associated with LVI. A clinicopathological model and a combined BES–clinicopathological model were constructed, and diagnostic performance was evaluated using the area under the receiver operating characteristic curve (AUC) and the DeLong test.

Results: Multivariate analysis revealed that BES and clinicopathological factors, including age, axillary lymph node metastasis, and tumor size, were independent predictors of LVI. Compared with BES 1, tumors with BES 2, BES 3, and BES 4 were associated with a 1.825-, 2.047-, and 4.341- fold increased LVI risk, respectively. The combined BES–clinicopathological model outperformed the clinicopathological model alone (AUC, 0.765 vs. 0.778; P<0.05).

Discussion: Higher BES was independently associated with increased LVI risk. The predictive model integrating BES with clinicopathological variables outperformed single-parameter models, suggesting that BES may provide complementary imaging biomarkers for assessing tumor aggressiveness. Validation in larger, multicenter cohorts is warranted.

Conclusion: FS T2WI-based BES combined with clinicopathological features may improve preoperative prediction of LVI in breast cancer and support individualized treatment planning.

Methods: 120 thyroid nodules were retrospectively included for evaluation of GPT-4o to analyze ultrasound features and ACR TR categories (version 2017). In a zero-shot setting, 80 original images of unmarked nodules (zero-shot unmarked group) and images with nodules’ boundary artificially depicted by senior radiologists with red circles (zero-shot marked group) were repetitively input into GPT-4o, respectively with identical prompts for 3 attempts without examples. In a few-shot setting, another 40 images with artificially marked nodule boundary (few-shot marked group) were input after 3 examples. The marking gold standard was established by 2 senior radiologists with over 10 years of experience in thyroid sonography. Consistency of GPT-4o was evaluated with the Gwet agreement coefficient (AC1) value calculated. The mean accuracy of GPT-4o across different settings was compared using the Mann-Whitney test with Bonferroni correction, in comparison to the mean accuracy of 2 junior radiologists with 1 and 3 years of experience in thyroid sonography, respectively.

Results: The AC1 values were 0.466 [0.367,0.564], 0.778 [0.696,0.860], 0.823 [0.711,0.934], respectively, for zero-shot unmarked group, zero-shot marked group, and few-shot marked group. The mean accuracy of the 3 groups to judge TR categories was 18.75% [13.78%,23.72%], 42.50% [36.20%,48.80%], 79.17% [71.80%,86.54%]. Zero-shot marked group outperformed zero-shot unmarked group, and the few-shot setting performed even better (p<0.001). Particularly, segmentation helped GPT-4o detect composition, shape, and margin of nodules, and a few-shot setting helped detect echogenicity, margin, and calcification (p<0.001). Compared with junior radiologists, the few-shot marked group achieved a similar accuracy in identifying composition, echogenicity, calcification, and TR categories (p>0.05) and performed even better in identifying the margin of thyroid nodules (p=0.004).

Discussion: GPT-4o’s performance to analyze original images of thyroid nodules was insufficient, possibly owing to incorrect nodule recognition and a lack of standardized reference. After adopting segmentation methods and a few-shot setting, its performance was improved significantly.

Conclusion: GPT-4o’s consistency and accuracy of analyzing thyroid sonography images can be gradually improved by segmentation methods and a few-shot setting, and finally achieves a junior-radiologist level in this preliminary study. This can potentially benefit report generation, while multicenter validation is needed.

Case Descriptions: We report three cases of AICA aneurysms with distinct clinical presentations and management strategies.

Case 1: A 56-year-old male presented with chronic headache and left hemiparesis. MRI and 3D TOF MRA revealed a fusiform AICA aneurysm compressing the pons, treated with microsurgical clipping via anterior petrosectomy, resulting in a favorable outcome (mRS score of 0).

Case 2: A 26-year-old female with a sudden-onset sentinel headache had a wide-neck saccular aneurysm of the right AICA confirmed by DSA. A posterior petrosectomy approach with clipping was performed, achieving complete aneurysm exclusion without complications (mRS score of 0).

Case 3: A 21-year-old male with an incidentally detected saccular aneurysm underwent DSA and 3D angio-CT, confirming a wide-neck saccular aneurysm in the AICA territory. Microsurgical clipping via anterior petrosectomy was successful, with no residual lesion (mRS score of 0).

Conclusion: Microsurgical clipping remains a viable option for managing wide-neck and fusiform AICA aneurysms, particularly those unsuitable for endovascular techniques. Advanced imaging modalities and tailored cranial base approaches are crucial for optimizing outcomes. Further studies are needed to refine management strategies for these rare aneurysms.

Methods: A PubMed search was performed using the keywords NAFLD and MRI, and the literature search deadline was set before April 2025.

Results: A total of 86 studies out of 405 retrieved were included in this study. The results showed that Magnetic Resonance Imaging Proton Density Fat Fraction (MRI-PDFF) was positively correlated with steatosis grading. The proton Density Fat Fraction Magnetic Resonance Spectroscopy (PDFFMRS) threshold of 5% could be used to diagnose liver steatosis. Apparent Diffusion Coefficient (ADC) of NAFLD patients was significantly lower than that of controls. A 15% increase in Magnetic Resonance Elastography (MRE) was the strongest predictor of progression to advanced fibrosis in NAFLD. The corrected T1 (cT1) cutoff value of 875 ms was used to identify liver fibrosis in NAFLD. The correlation between the Liver Surface Nodules (LSN) score and the stage of fibrosis in NAFLD was very strong. Dynamic enhanced MRI (DCE-MRI) parameters increased with increasing severity of NAFLD and fibrosis.

Discussion: This study evaluated the value of multiple MRI techniques in diagnosing NAFLD, confirming MRI's high accuracy and reliability as a noninvasive tool for quantifying NAFLD. However, future technical specification harmonization is needed to enhance comparability of results and validate generalizability through multicenter studies.

Conclusion: MRI is a highly reliable and accurate method for diagnosing NAFLD.

Methods: Breast lesions from 155 patients (65 benign, 90 malignant) were manually segmented on DCE-MRI images by four experienced radiologists using 3D Slicer (version 5.6.1). From each lesion, 107 radiomic features, including shape, first-order, and texture features, were extracted, yielding a high-dimensional dataset. All features were normalized using Z-score scaling. Feature selection was performed using LASSO regression with fivefold cross-validation. The dataset was divided into training and testing sets in a 70:30 ratio, and model performance was evaluated using five-fold cross-validation. The top 20 radiomic features were selected based on intraclass correlation coefficient (ICC) analysis to ensure feature stability. Nine machine learning models, CatBoost, Random Forest, XGBoost, AdaBoost, Naïve Bayes, Logistic Regression, k-NN, SVC, and MLP were employed for classifications. Hyperparameter tuning was applied to optimize model performance, and SHapley Additive exPlanations (SHAP) were used to identify key predictive features.

Results: ICC values ranged from 0.941 to 0.992 (95% CI), demonstrating excellent reliability across all radiomic feature categories. CatBoost outperformed the others with an AUC of 0.937 (95%CI:0.852-0.993) with a sensitivity of 0.889 and a specificity of 0.909 in the internal test set. Other models, such as Random Forest (AUC:0.881, 95%CI:0.758-0.972) and Naïve Bayes (AUC:0.843,95%CI:0.707-0.949), performed well but were less effective compared to CatBoost. SHAP analysis showed that several radiomic features were significant in distinguishing malignant lesions.

Discussion: Ensemble-based models generally outperformed traditional classifiers, such as Logistic Regression and k-NN, possibly because they can capture non-linear relationships in the dataset. SHAP analysis provided insight into model interpretability by identifying key features that contributed most significantly to the classification task.

Conclusion: This study demonstrates the potential of integrating radiomic features with ML for breast cancer classification. CatBoost exhibited the highest predictive performance, highlighting its effectiveness in distinguishing malignant from benign lesions.

Materials and Methods: A retrospective observational study was conducted on 66 acute optic neuritis(ON) patients. Twenty-five patients (36 eyes) were comorbid with CTD, and 41 patients (49 eyes) had idiopathic ON and served as controls. All patients underwent routine magnetic resonance imaging (MRI) of the orbit and DWI.

Affected optic nerves were evaluated for laterality, visual acuity, papilledema, visual outcome, and signal characteristics on DWI and conventional MRI. Clinical characteristics were compared using two-sample t-tests and chi-square tests. Spearman’s rank correlation, logistic regression, and receiver operating characteristic (ROC) curve analyses were performed to evaluate the diagnostic value of DWI for CTD-ON.

Results: Compared with the IDON group, patients with CTD-ON showed significantly more severe visual impairment and worse prognosis (P < 0.05). Optic nerve hyperintensity on DWI (DWI-H) was a significant risk factor for visual acuity at onset and final visual outcome in ON patients [ORs = 1.893 (95% CI: 1.322-2.711, P < 0.001), 1.716 (95% CI: 1.094-2.691, P = 0.019), respectively]. Acute CTD-ON patients were at higher risk of poor visual outcomes [OR = 2.593 (95% CI: 1.384-4.857, P = 0.003)]. ROC analysis showed that the combination of DWI-H and poor visual outcome yielded an AUC of 0.889 (95% CI: 0.820-0.959, P < 0.001), with a sensitivity of 88.9% and specificity of 77.6%.

Discussion: The pathogenesis of CTD-ON may involve the following mechanisms. First, CTD-related small-vessel vasculopathy, necrosis, and hypercoagulability-induced thrombosis may lead to vasculitic infarction and ischemic injury of the optic nerve, which manifests as hyperintensity on DWI. Second, autoantibodies induced by CTD may cross-react with neuronal cells.

Conclusion: Patients with CTD-ON demonstrate more severe visual impairment than those with IDON. The presence of DWI hyperintensity and poor prognosis in patients with ON should raise suspicion for CTD-ON in the appropriate clinical setting.

Objective: For the automated and accurate diagnosis of bone metastasis in bone scintigrams, this study proposes an improved differentiable neural architecture search framework to address two key limitations of the original DARTS method: (1) the insufficient representation capability of standard candidate operations for characterizing bone metastasis lesions, and (2) architecture degeneration.

Methods: Based on the DARTS framework, two novel candidate operations were developed, and the training supernet architecture was optimized. (1) The channel-attention-integrated residual operation incorporates synergistic channel-wise intelligent weighting and gradient stabilization mechanisms, providing an efficient yet highly discriminative feature transformation module for architecture search. (2) The spatial-attention-enhanced multibranch operation combines multi-scale feature fusion with spatially adaptive focusing, significantly improving the model’s ability to localize critical regions and detect lesions of varying sizes. (3) A dual-path convolutional structure is introduced into the training supernet to dynamically optimize both channel-wise and spatial dimensions of shallow features, thereby generating highly discriminative representations for subsequent cell architecture search.

Results: Comprehensive evaluations on clinical datasets demonstrate the effectiveness of the proposed method, achieving an accuracy of 0.8451, precision of 0.8700, recall of 0.8447, F1-score of 0.8423, and an AUC of 0.92.

Discussion: The results validate that incorporating manual network design experience into the architecture search process can significantly improve model performance. Systematically leveraging anterior-posterior views of the same case can improve lesion detection in complex anatomical regions. Future work will focus on developing a dual-view architecture search framework based on complementary feature fusion.

Conclusion: The proposed neural architecture search method effectively detects bone metastasis in bone scintigrams and outperforms existing state-of-the-art approaches. The newly developed candidate operations and supernet optimizations successfully address the limited representational capacity of standard convolutions in the original DARTS operations, leading to substantial improvements in classification performance.

Method: This study enrolled 133 patients with SGISTs, including 97 in the low-grade group and 36 in the high-grade group. Patients were randomly assigned to a training set (n = 93) and a testing set (n = 40) at a ratio of 7:3. Radiomics features were extracted from preoperative CT images, and dimensionality reduction was performed using the LR-LASSO to identify the most predictive features for constructing the radiomics model. Clinical features were evaluated using univariate and multivariate logistic regression analyses to develop a clinical model. Subsequently, the optimal radiomics and clinical features were integrated to establish a combined model. Model performance was evaluated using ROC curve analysis, and a corresponding nomogram was generated to facilitate clinical application. The Delong test was used to compare the ROC curves, with a p-value < 0.05 considered statistically significant.

Results: Univariable clinical analysis identified maximal tumour diameter as the only significant predictor, with the clinical model achieving an AUC of 0.641 (95% CI: 0.533–0.748). Among the radiomics signatures derived from multiphase CT (non-contrast to delayed phases), the model based on portal venous phase images demonstrated the highest discriminative ability, yielding the best AUC values in both the training set (AUC = 0.848, 95% CI: 0.764–0.931) and the testing set (AUC = 0.824, 95% CI: 0.696–0.953). The combined model, which integrated radiomics features with maximum tumour diameter, demonstrated improved performance, attaining an AUC of 0.862 (95% CI: 0.743–0.975) in the training set and 0.859 (95% CI: 0.743–0.975) in the testing set. Notably, the predictive performance of both the radiomics and combined models was significantly greater than that of the clinical model (DeLong test, P < 0.05). However, no statistically significant differences were observed between the AUC values of the radiomics and combined models. Calibration curves indicated a good fit, and the DCA demonstrated that both the radiomics model and the combined model provided greater clinical benefits.

Discussion: The radiomics model demonstrated superior performance to the clinical model for the preoperative prediction of risk stratification in SGISTs. As a visualization tool, the nomogram of the combined model plays a critical role in optimizing early surgical resection decisions.

Conclusion: The radiomics model could serve as an effective tool for non-invasive risk stratification of SGISTs, offering clear advantages over risk stratification models based solely on conventional clinical parameters. This approach could support improved preoperative clinical decisionmaking.

Objective: The study aims to evaluate the value of high-frame-rate contrast-enhanced ultrasound (H-CEUS) in assessing the vascular morphology of RCC.

Methods: A retrospective analysis was conducted on 163 RCC patients who were classified postoperatively into clear cell RCC (ccRCC) and non-clear cell RCC (nccRCC) groups. All patients underwent conventional US, conventional CEUS (C-CEUS), and H-CEUS preoperatively. Vascular morphology during the early phase of CEUS perfusion was categorized into five types (I-V). Differences in vascular morphology were compared using the χ2 test or Fisher's exact test, and inter-observer agreement was evaluated using the Kappa coefficient.

Results and discussion: A significant difference in CDFI was observed between the ccRCC and nccRCC groups (χ2=11.755, P = 0.0088). In C-CEUS and H-CEUS, type III vascular morphology was most common in ccRCC. The proportion was significantly higher in H-CEUS than in C-CEUS (62.6% vs. 45.8%; χ2=6.099, P = 0.014). Type IV was the most common vascular morphology in nccRCC, with no significant difference between C-CEUS (58.9%) and H-CEUS (44.6%) (χ2=2.289, P = 0.130). H-CEUS revealed significant vascular morphological differences in ccRCC ≤4 cm (χ2=9.307, P = 0.038), but not in nccRCC ≤4 cm or in any tumors >4 cm. Inter-observer agreement for vascular morphology evaluation was substantial for both CCEUS (κ=0.751) and H-CEUS (κ=0.657) (both P<0.001).

Conclusion: H-CEUS offers superior visualization of vascular morphology in ccRCC lesions ≤4 cm, providing valuable insights into its potential as a noninvasive imaging modality for differentiating RCC subtypes and tailoring treatment strategies.

Methods: The methodology integrates multiple components into a hybrid model. Initially, mammographic images from the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) undergo a preprocessing step, uses a guided filter to remove noise and enhance the visibility of regions of interest (ROI). Modified Dingo Optimization (MDO) algorithm is used to segment the tumour-affected regions, not only to identify abnormalities localized in a single region of the breast but also to effectively detect multiple abnormal areas distributed across different tissue regions. Deep features are then extracted using a pretrained U-Net architecture. The Search and Rescue Optimization (SRO) algorithm was utilized for feature optimization to select the most relevant deep features, reducing dimensionality and enhancing the model's diagnostic accuracy. A Dual Stage Spiking Convolutional Neural Network (DSS-CNN) is implemented for classification and enhancing the model's ability.

Results: The proposed hybrid deep learning model achieves outstanding performance, with an accuracy of 98.598%, precision of 97.343%, recall of 97.514%, and an F-measure of 96.89%. Comparative analysis confirms that the approach significantly reduces false positive and false negative rates, outperforming existing state-of-the-art techniques.

Conclusion: The proposed robust end-to-end system for early and accurate breast cancer detection demonstrates the efficacy of the framework in improving diagnostic accuracy, precision, recall, and F-measure, offering valuable support in clinical decision-making.

Case Presentation: A 70-year-old Chinese male patient presented to the urology department with progressive left scrotal enlargement, pain, and a palpable firm mass over the past month. After admission, initial ultrasound examination indicated a left spermatic cord mass. Subsequently, an enhanced MRI was performed, revealing no obvious fat signal within the lesion but significant enhancement, with thickening and compression of the spermatic cord. The findings ultimately suggested a malignant sarcoma of the left epididymis. Surgical resection and subsequent histopathological examination confirmed a spindle cell-predominant dedifferentiated liposarcoma of the epididymis encircling the spermatic cord. After 11 months of follow-up, no recurrence has been detected.

Conclusion: We report a surgically confirmed rare case of dedifferentiated liposarcoma originating from the epididymis, characterized by predominant spindle cells and significant imaging enhancement. This atypical presentation complicated differentiation from other spindle cell sarcomas, highlighting diagnostic challenges at rare sites.

Materials and Methods: A total of 120 consecutive patients who underwent 1.5T MP-MRI followed by MRI/US fusion-guided prostate biopsy were included. In total, 202 MRI-identified targets were sampled. For each lesion, anatomical location, Prostate-Specific Antigen (PSA), prostate volume, Prostate Density (PD), apparent diffusion Coefficient (ADC) values, neurovascular bundle invasion, and PI-RADS v2.1 score were recorded. GS results were statistically compared with imaging and clinical parameters. Pearson’s correlation was calculated to investigate the associations, and the diagnostic ability of ADC values was evaluated by Receiver Operating Characteristic (ROC) analysis.

Results: Of the 202 targets, 138 (68.3%) were benign, 35 (17.3%) had GS 3+4 (low-grade), and 29 (14.4%) had GS ≥4+3 (high-grade) malignancy. ADC values were negatively correlated with age, PSA, PD, and PI-RADS score. Most lesions were located in the peripheral zone, particularly in the mid-gland and apical regions. Malignant lesions were frequently found in the peripheral zone and right mid-gland. ADC values showed strong diagnostic performance, with cut-offs of 0.78 ×10−3 mm2/s for low-grade (sensitivity: 79.69%, specificity: 86.21%) and 0.70 ×10−3mm2/s for highgrade malignancies (sensitivity: 92.03%, specificity: 92.49%).

Discussion: This echoes previous reports indicating that ADC value negatively correlated with GS, supporting the application of MP-MRI-derived parameters in the assessment of prostate cancer.

Conclusion: Correlation of MP-MRI-derived imaging parameters with histopathology results allows meaningful exploitation in clinical decision-making in prostate cancer diagnosis. Both the PI-RADS score and the ADC value were validated as reliable predictors of tumor aggressiveness. Although MRI-targeted fusion biopsies have gained more and more popularity in clinical practice, based on our data, no conclusion can be drawn as to their effect in decreasing the number of unnecessary prostate biopsies.

Method: In this study, we introduced the PRAD-Hybrid CNN (Prostate Adenocarcinoma Hybrid Convolutional Neural Network, PRADHC) model, a novel amalgamation of EfficientNet and Residual Blocks, which was developed and validated on 1,528 MRI images from 64 patients. By strategically increasing the number of Convolutional Neural Network (CNN) layers in the EfficientNet architecture, our model improved the diagnostic accuracy inherent to the original EfficientNet. Additionally, the integration of Residual Networks (ResNet) successfully mitigated the gradient vanishing issue often encountered during the training of deeper models, thereby significantly enhancing training accuracy. This innovative model, thus, offers clinicians an efficacious tool for assisted diagnosis.

Result: The PRADHC model, upon validation, achieved an accuracy of 99.34% and an AUC of 99.34%, a 4% improvement over the conventional EfficientNet. The baseline elementary CNN model achieved 95.72% accuracy and 96.74% AUC, which are still lower than the PRADHC model.

Discussion: The superior performance of PRADHC can be attributed to the synergistic integration of EfficientNet’s multi-scale feature extraction and residual learning, which facilitates deeper network optimization without degradation. Compared with single-architecture CNN models, the hybrid design enhances robustness to MRI appearance variability and improves discrimination between malignant and non-significant prostate tissue.

Conclusion: This study introduces a novel deep learning model specifically designed for automated prostate cancer diagnosis. This model aims to enhance diagnostic accuracy, especially in the early stages of the disease. Such advancements have the potential to enhance the diagnostic proficiency of both radiologists and urologists, enabling more informed treatment planning. However, it is imperative to acknowledge that false-positive lesion detections remain a limitation of AI-assisted diagnostic tools. Nevertheless, this system can serve as a valuable supplementary instrument for radiologists in their diagnostic endeavors.

Materials and Methods: This is a narrative review based on a literature review of databases such as PubMed, Embase, Web of Science, and the Cochrane Library, from January 2000 to March 2025. OCT imaging diagnosed with urothelial carcinoma. Studies meeting the following inclusion criteria are eligible, including reports describing the technical aspects or clinical applications (such as diagnosis, staging, intraoperative guidance, or postoperative monitoring) of OCT imaging in the care of patients with urothelial carcinoma. The results of the study have been categorised.

Results: OCT demonstrated high-resolution imaging and real-time capabilities, enabling differentiation of malignant from normal urothelial tissues. Clinical studies confirmed its value in tumor staging and intraoperative guidance, with strong concordance to histopathology. OCT improved diagnostic sensitivity and specificity when combined with conventional cystoscopy and showed potential in monitoring treatment response and detecting recurrence.

Discussion: OCT offers a non-invasive, precise imaging modality with significant advantages over traditional diagnostic methods. However, limitations remain, including restricted imaging depth and variability across clinical protocols. Standardization and broader clinical validation are needed to ensure consistent adoption.

Conclusion: Endoscopic OCT represents a transformative tool for UC management. With further technological innovations and standardized protocols, it is expected to enhance early detection, intraoperative guidance, and long-term patient outcomes.

Methods: We introduce a hybrid model, XceptRF-Net, that integrates deep feature learning of the Xception convolutional neural network and the probabilistic modelling power of the Random Forest for the classification of Fisher’s iris dataset. The first stage of the model considers the highlevel spatial features from the chest X-rays, which are extracted using Xception. Followed by that, they are subsequently mapped to a probabilistic feature space using Random Forest, contributing to the feature representation and the classification robustness. The discriminative capability of the engineered features was tested by different machine learning classifiers such as Logistic Regression (LR), K-Nearest Neighbours (KNN), and Multi-Layer Perceptron (MLP). Fine-tuning and k-fold cross-validation were also performed for generalization purposes and to speed up computation.

Results: The proposed XceptRF-Net framework, established from an experimental study on one dataset with 5,863 pediatric CXRs, has been objectively shown to benefit over conventional methods. Logistic Regression achieved the highest diagnostic accuracy of 98%, which is a validation of the spatial and probabilistic feature learning integration.

Discussion: The effectiveness of the XceptRF-Net model highlights the value of combining deep feature extraction with probabilistic modeling to enhance clinical decision-making.

Conclusion: The findings highlight the theoretical superiority of the integration of convolutional deep features with ensemble learning and the generation of probabilistic features for medical image analysis. The proposed method provides a stable and explainable framework for clinical decision support and has high potential for practical use in real-world systems for pediatric pneumonia screening and diagnosis.

Methods: A total of 102 NSCLC patients (53 patients without chemotherapy (CT(-)), 49 patients with chemotherapy (CT(+))) and 56 healthy controls (HCs) were enrolled. Their glymphatic system function was evaluated using the diffusion tensor imaging analysis along the perivascular space (DTIALPS) index and choroid plexus (CP) volume, derived from DTI and three-dimensional T1-weighted magnetic resonance imaging (3D-T1 MRI), and examined for group differences and associations with neuropsychological outcomes.

Results: The MoCA scores of NSCLC survivors decreased significantly after chemotherapy. There were significant differences in the DTI-ALPS index and CP volume among the three groups (P < 0.05, one-way ANOVA).Post hoc analyses (Bonferroni-corrected) demonstrated that the CT(+) group exhibited significantly reduced DTI-ALPS indices and enlarged CP volumes compared to both the CT(–) group and the HCs group (P < 0.05). DTI-ALPS indexes were positively correlated with MoCA scores (r = 0.448, P = 0.001), and CP volumes were negatively correlated with cognitive performance (r= -0.435, P = 0.002). Mediation analysis indicated that DTI-ALPS indexes partially mediated the relationship between CP volumes and MoCA scores (mediated effect = 32.79%).

Conclusion: This research provides new insights into the pathological mechanism of CRCI in patients with NSCLC. These results suggest that glymphatic system-derived metrics (DTI-ALPS indices and CP volume) might act as potential biomarkers for assessing CRCI and tracking neurocognitive changes in NSCLC patients receiving chemotherapy.

Case Presentation: This report presents the case of a 57-year-old female patient with a five-year history of abdominal discomfort. Computed tomography (CT) and magnetic resonance imaging (MRI) demonstrated a mass in the tail of the pancreas, which showed progressive ring-like delayed enhancement. The diagnosis of pancreatic mucoepidermoid carcinoma was confirmed by pathology following a laparoscopic distal pancreatectomy.

Conclusion: Pancreatic MEC is exceedingly rare. In this article, the authors summarize the imaging features of this tumor and systematically review the literature to provide a better understanding of this disease.

We apologize for any inconvenience caused and appreciate the opportunity to rectify this matter.

The original article can be found online at:

https://www.benthamscience.com/article/153035

ORIGINAL

FUNDING

This study was funded by the Kuwait University Research, Kuwait Grant No. NR02/25.

CORRECTED

FUNDING

This study was funded by the Kuwait University Research, Kuwait.

The original article can be found online at: https://www.benthamscience.com/article/150901

ORIGINAL:

Ying Long^1,*, Zhao-ping Chen^1,*, Lin-hui Wang², Xue-qing Liao¹, Ming Guo³ and Zhong-qing Huang^1,*

CORRECTED:

Ying Long^1,#, Zhao-ping Chen^1,#, Lin-hui Wang², Xue-qing Liao¹, Ming Guo^3,* and Zhong-qing Huang^1,*]]> https://www.benthamscience.com/article/1544652026-04-02 Introduction: Microwave Ablation (MWA) is a well-established curative therapy for early-stage Hepatocellular Carcinoma (HCC). However, conventional Non- Contrast CT (NCCT) guidance for MWA faces limitations, including poor visualization of isodense lesions and significant needle artifacts, which can compromise targeting accuracy. This study evaluated a novel imaging-guidance strategy utilizing superselective lipiodol CT to explore its feasibility in addressing these challenges.

Materials and Methods: Treatment-naive patients with BCLC 0/A HCC within the Milan criteria were included in this retrospective study. All patients underwent superselective transarterial lipiodol-only marking followed by CT-guided MWA within 1 week. Treatment efficacy was evaluated based on technical success, Local Tumor Progression (LTP), Intrahepatic Distant Recurrence (IDR), Recurrence-Free Survival (RFS), and Overall Survival (OS). Imaging-guidance performance was descriptively evaluated based on intraprocedural lesion visualization and operator-adjusted window settings used to facilitate needle positioning.

Results: Forty-five patients with 57 lesions were enrolled. The mean lesion diameter was 18.2 ± 8.8 mm. The initial technical success rate was 95.5% (43/45). The 1-, 2-, and 3-year rates were: LTP: 2.2%, 4.4%, 4.4%; IDR: 24.4%, 37.7%, 44.4%; RFS: 68.9%, 52.7%, 38.2%; OS: 85.1%, 72.4%, and 60.5%. During lipiodol CT-guided procedures, lesions that were isodense and poorly visualized on pre-procedural NCCT were identifiable to the operator, and the window level settings used for final needle positioning confirmation had a mean value of 252.2 ± 75.8 Hounsfield Units.

Discussion: The superselective lipiodol CT guidance strategy demonstrated feasibility in addressing several practical limitations of conventional NCCT. It allowed visualization of otherwise inconspicuous isodense lesions, supported needle positioning under reduced metallic artifact conditions at empirically adjusted window levels, and aided the visualization of adjacent portal vein branches during the procedure. This approach utilizes Lipiodol primarily as a long-lasting contrast agent for enhanced CT visualization, rather than for its chemotherapeutic or embolic effect.

Conclusion: Superselective lipiodol CT guidance is a feasible imaging approach for intraprocedural lesion visualization and needle positioning during MWA of small HCC in selected procedural scenarios. Controlled comparative or quantitative validation studies are warranted.

Case Presentation: We present the case of a 66-year-old male with moderately differentiated rectal adenocarcinoma showing heterogeneous diffusion restriction on MRI. The tumor surface demonstrated diffusion restriction (hyperintense on DWI, hypointense on ADC), whereas the base did not. Quantitative ADC analysis showed mean values of 0.82 × 10^-3 mm²/s at the surface and 1.36 × 10^-3 mm²/s at the base.

Conclusion: This case highlights that regions with lower cellularity in moderately differentiated adenocarcinoma may lack diffusion restriction. Correlating imaging findings with histopathological results is essential to prevent diagnostic misinterpretation.

Case Presentation: A 44-year-old male with alcoholic liver cirrhosis was found to have a hepatic lesion in segment 8, which gradually increased in size from 15 mm to 43 mm over 47 months. The lesion exhibited arterial phase hyperenhancement and washout on delayed imaging. It fulfilled the Liver Imaging Reporting and Data System (LI-RADS) v2018 criteria for LR-5, indicating definite HCC. The patient underwent laparoscopic subsegmentectomy of segment 8 without prior biopsy. Histopathological examination confirmed the diagnosis of inflammatory HCA. Immunohistochemistry showed strong and diffuse expression of SAA and C-reactive protein, and no aberrant β-catenin expression. The lesion was initially diagnosed as HCC based on radiologic features; the final diagnosis was inflammatory HCA. The patient recovered well after surgery and was discharged nine days later.

Conclusion: Inflammatory HCA can mimic HCC on imaging, especially in patients with alcoholic cirrhosis. In such cases, relying solely on imaging may lead to misdiagnosis. Correlation with clinical history, pathology, and immunohistochemical findings is important to avoid unnecessary surgery and ensure accurate diagnosis.

Materials and Methods: From June 2022 to December 2024, we prospectively recruited 326 CKD patients who underwent kidney biopsy across two medical centers. The enrolled patients were randomly allocated to the training or testing set in a 7:3 ratio. Deep learning (DL) features and radiomics features from SMI images were extracted, and after dimensionality reduction, they were used to establish deep learning radiomics (DLR) models. The performance of the proposed models was assessed through receiver operating characteristic (ROC) analysis and decision curve analysis (DCA).

Results: Among the 326 CKD patients, 165 were positive for arteriolosclerosis and 161 were negative. In the training group, the area under the curve (AUC) values for the CDUS model,clinical model, radiomics model, DL model, and DLR model were 0.621 (0.547-0.695), 0.68 (0.611-0.749), 0.763 (0.703-0.823), 0.820 (0.767-0.874), and 0.840 (0.790-0.890), respectively. In the testing group, the AUCs were 0.677 (0.571-0.783), 0.776 (0.684-0.869), 0.727 (0.626-0.829), 0.779 (0.687-0.872), and 0.819 (0.735-0.903), respectively. The DLR model outperformed standalone radiomics, DL models, and the CDUS-based clinical model. The DCA validated the clinical utility of the DLR model.

Conclusion: The DLR model utilizing SMI imaging can precisely and non-invasively assess the severity of arteriolosclerosis in CKD patients, which can assist physicians in formulating more favorable treatment plans for patients.

Materials and Methods: After assessment of coil properties, typical spectroscopy sequences were evaluated against each other using metabolite phantoms of adenosine triphosphate (ATP) and phosphocreatine (PCr) on a Bruker 7 T small animal scanner, with respect to signal-to-noise ratio (SNR) and spatial selectivity.

Results: The free induction decay (FID) in combination with outer volume suppression (OVS) showed the best SNR compared to the other spectroscopy sequences. OVS achieved a signal suppression of adjacent metabolites of approximately 84%. The performance of the setup was demonstrated in beating mouse hearts before and after myocardial infarction. A PCr to ATP(γ) ratio change from 2.5 pre-infarction to 1.74 approximately one week post-infarction was observed.

Discussion: Among the evaluated methods, FID with OVS provided the best balance between localization accuracy and acquisition efficiency for application in the beating mouse heart. Despite probable signal contamination from surrounding tissue, in vivo measurements revealed post-infarction metabolic changes, evidenced by the reduction in the PCr/ATP(γ) ratio.

Conclusion: Due to the dynamic nature and small size of the target organ, examination of the beating heart with ³¹P MRS requires a signal intensity- and noise-optimized implementation. The FID with OVS approach allows clear detection of variations in the ATP to PCr ratio before and after myocardial infarction within an acceptable measurement time (approximately 6.5 min). Image-selected in vivo spectroscopy (ISIS), the only serious competitor to FID with OVS, was found to be less suited for in vivo myocardium investigations due to inherent limitations in signal intensity and SNR.

Case Presentation: A 67-year-old man presented with multiple non-cavitating pulmonary nodules and was diagnosed with pulmonary cryptococcosis. He completed a full course of antifungal therapy with clinical and radiologic improvement, and treatment was discontinued. After stopping therapy, he relapsed with the same pattern of multiple non-cavitating pulmonary nodules. Restarting antifungal therapy led to regression of the lesions. Unexpectedly, during antifungal maintenance therapy, he again developed multiple non-cavitating pulmonary nodules. Laboratory testing showed positivity for myeloperoxidase (MPO) and perinuclear anti-neutrophil cytoplasmic antibodies (p-ANCA), supporting a diagnosis of microscopic polyangiitis (MPA), a subtype of AAV. After discontinuation of antifungal therapy and treatment with prednisone plus mycophenolate mofetil, the pulmonary nodules showed marked regression.

Conclusion: Multiple non-cavitating pulmonary nodules can be an atypical presentation of MPA and overlap radiologically with pulmonary cryptococcosis. Accurate differentiation should integrate ANCA serology with careful assessment for involvement of other organ systems.

Materials and Methods: In this prospective analysis, 33 patients with ANS and 29 matched healthy controls (HC) were enrolled from The Second Hospital of Nanjing. All participants underwent Magnetic Resonance Imaging (MRI) scanning. The diffusion tensor image analysis along the perivascular space (DTIALPS) indices and normalized enlarged perivascular spaces (EPVS) volume were quantified and compared between the ANS and HC groups. Furthermore, correlations were assessed between imaging-derived metrics and inflammatory profiles from both Cerebrospinal Fluid (CSF) and peripheral blood samples.

Results: Marked differences in DTI-ALPS indices and normalized EPVS volume were evident between the ANS and HC groups. Post hoc analyses revealed that the ANS group exhibited significantly reduced DTI-ALPS indices (1.40 vs 1.60, p = 0.0001) and elevated normalized EPVS volume (2.28 vs. 2.05, p = 0.0355) relative to healthy individuals. In ANS, unadjusted analyses suggested that normalized EPVS volume demonstrated a positive correlation with CSF nucleated cell count (r = 0.413, p = 0.017), and a significant inverse relationship was observed between DTI-ALPS values and CSF lactate dehydrogenase (LDH) concentrations (r = -0.385, p = 0.027). However, after False Discovery Rate (FDR) correction, these correlations did not reach statistical significance.

Discussion: The findings demonstrate, to our knowledge, for the first time, significant glymphatic system–related impairment in ANS. The reduced DTI-ALPS index suggests diminished glymphatic activity, while increased normalized EPVS volume points to structural perivascular alterations. The exploratory correlations between these imaging metrics and CSF inflammatory markers indicate a potential relationship between glymphatic system–related dysfunction and neuroinflammation in early neurosyphilis.

Conclusions: Taken together, these findings indicate that distinct alterations in DTI-ALPS indices and normalized EPVS volume may represent novel neuroimaging biomarkers for the early detection and clinical evaluation of ANS. Utilization of these imaging indices could potentially enhance diagnostic precision and inform prognostic assessment in affected patients.

Methods: This retrospective study analyzed computed tomography angiography (CTA) data from 206 head and neck patients at Ordos Central Hospital (January 2020-June 2024), including 157 symptomatic and 49 asymptomatic individuals. Patients were randomly allocated into training/validation cohorts (7:3 ratio), with an additional prospectively enrolled cohort of 44 carotid plaque cases from Jining First People’s Hospital serving as an independent test set. Following radiomics feature extraction from CTA images, machine learning models were constructed using tree-based algorithms (Random Forest, XGBoost, LightGBM). An integrated multimodal model combining clinical variables, radiological characteristics, and radiomics signatures was developed. Performance was assessed via receiver operating characteristic (ROC) analysis, reporting area under the curve (AUC), sensitivity, and specificity metrics.

Results: Multivariable analysis identified high-density lipoprotein cholesterol (HDL-C) levels and a history of diabetes as independent predictors of symptomatic carotid plaques. Radiomics models utilizing machine learning demonstrated moderate to strong diagnostic capability, yielding AUCs of 0.625-0.814 in the validation cohort and 0.743-0.802 in the test cohort. The multimodal integrated framework consistently surpassed standalone models, attaining AUCs of 0.836 in the validation set and 0.845 in the test set, which were significantly higher than both clinical and radiomics predictors alone.

Discussion: The CT radiomics-based machine learning model developed in this study demonstrated favorable diagnostic efficacy in discriminating symptomatic carotid plaques. The multimodal framework integrating clinical indicators with radiomic signatures significantly enhanced the model's discriminative power and generalizability. This work confirms the clinical potential of radiomics analysis derived from routine CTA for precision risk assessment in cardiovascular disease, providing a novel supportive tool for individualized risk stratification of carotid atherosclerosis.

Conclusion: CT imaging-based radiomics and machine learning models can effectively support clinical decision-making, enhance risk stratification for carotid plaque patients, and facilitate personalized treatment strategies.

Materials and Methods: This study included 41 human fetuses (24 males and 17 females) at 17 to 42 weeks of gestation, collected after spontaneous abortion or preterm birth that met ethical standards. High-resolution imaging was obtained by an MRI scanner. Three-dimensional volumetric data of the ossification centers were obtained and analyzed using the 3D Slicer software. Morphometric parameters, which included the 3D maximum diameter, projection surface area, and volume, were measured. Statistical analysis was conducted with SPSS 23, and growth dynamics were evaluated by regression models.

Results: Analysis shows that the ossification centers of the atlas and axis increase proportionally with gestational age, and there is a significant correlation between age and measurement parameters. The average 3D maximum diameter, projected surface area, and volume show consistent growth patterns, with no significant differences between genders. The linear regression model is the best at describing developmental dynamics, with high coefficients of determination for all parameters (R ²>0.70).

Discussion: This study indicates that the ossification centers of the fetal atlas and axis increase proportionally with gestational age, and a high correlation is observed in all morphological measurement parameters. Compared with ultrasound or CT, MRI has been proven to be a superior non-invasive imaging method that can provide high-resolution three-dimensional data for detailed evaluation of the fetal cervical spine without radiation exposure. The lack of gender-based differences supports the use of a unified growth model. These normative data provide valuable benchmarks for detecting cervical dysplasia. Although the sample size and cross-sectional design are relatively limited, this study provides clinically applicable growth references that may aid in the early diagnosis of congenital spinal abnormalities.

Conclusion: This study provides standardized morphometric data for the main ossification centers of the atlas and axis in human fetuses. These findings contribute to a better understanding of fetal cervical spine development and establish a reference framework for early detection of congenital abnormalities. In addition, the research findings emphasize that MRI is a reliable and non-invasive tool for the detailed assessment of fetal skeletal maturity.

Materials and Methods: This retrospective single-center study analyzed brain MRI examinations from 65 patients with suspected or confirmed MS. Imaging protocols included conventional FLAIR and MinPE FLAIR/WAIR images. Two experienced neuroradiologists, blinded to clinical data, independently identified and classified lesions. Lesion detection rates were compared using chi-square analysis, and interobserver agreement was assessed with Cohen’s kappa.

Results: MinPE FLAIR/WAIR images showed improved lesion conspicuity and significantly higher detection rates compared with conventional FLAIR, particularly in the brainstem. Detection was markedly increased in the midbrain, pons, and medulla (p ≤ 0.0004), with additional improvement observed in the cerebellar hemispheres (p < 0.05).

Discussion: While advanced sequences such as Double Inversion Recovery (DIR) and Phase-Sensitive Inversion-Recovery (PSIR) enhance lesion detection, their longer acquisition times limit routine use. The MinPE FLAIR/WAIR technique improves lesion visibility in challenging regions with minimal impact on scan time, allowing a more accurate estimation of disease burden.

Conclusion: MinPE FLAIR/WAIR post-processing enhances MS lesion detection and may represent a practical addition to routine MRI protocols.

Materials and Methods: This study proposes a deep learning-based diagnostic framework that introduces an enhanced feature extraction strategy through a novel model known as Kidney Transformer Network (KTNET). The system is designed to automatically detect and classify multiple kidney conditions by effectively extracting disease-specific features from CT scan images. By leveraging transformer-based architecture, KTNET improves feature representation and enables highly accurate discrimination between Normal, Cyst, Tumor, and Stone cases.

Results: Experimental results demonstrate that the proposed model achieves outstanding diagnostic performance, recording 99.7% accuracy, 99.4% precision, 99.3% recall, and a 99.6% F1-score, surpassing traditional image processing methods and several existing deep learning models.

Discussion: The model’s adaptability and efficiency with diverse CT scan images highlight its potential for practical integration in clinical workflows.

Conclusion: This research advances medical imaging by providing an intelligent, reliable, and accurate framework for the early detection and classification of kidney abnormalities, ultimately enhancing patient diagnosis and clinical decision-making.

Methods: A prospective study was conducted in 50 subjects. All patients underwent digital OPG evaluation based on Winter’s classification of impacted teeth and Rood and Shehab’s classification of seven radiographic signs. Cases with any positive finding were examined using CBCT to assess the positioning of the mandibular canal and alveolar ridge.

Results: Horizontal and mesioangular impactions were at higher risk of inferior alveolar nerve damage (p< 0.01 and p < 0.05) along with lingual position of canal (p<0.001), Darkening of roots, interruption of the mandibular canal (p<0.001), and diversion of the mandibular canal (p< 0.04) were associated with a higher risk of damage during extractions.

Discussion: The current study confirmed that horizontal and mesioangular impactions showed a significant association with the absence of cortication between the mandibular canal and third molar roots, indicating a high risk of nerve injury, similar to other studies. Also, CBCT has been proven to be the best imaging modality owing to its high diagnostic accuracy.

Conclusion: In the current study, CBCT was considered the gold standard, and diagnostic accuracy was higher than OPG. There was fair agreement about the mesioangular and horizontal impaction and their proximity to the mandibular nerve.

Methods: A retrospective observational study was conducted on patients diagnosed with KA and treated by microsurgical clipping between January 2004 and October 2024. Imaging modalities included computed tomography (CT), CT angiography, and digital subtraction angiography. Microsurgical approaches were tailored to aneurysm location and rupture status. Functional outcomes were assessed using the modified Rankin scale (mRS).

Results: KA accounted for 2.3% of all aneurysms treated during the study period. The most frequent site was the posterior communicating artery-anterior choroidal artery segment (59.37%). Preoperative identification of KA was achieved in 87.5% of cases. Intraoperative rupture occurred in 25%. Favorable outcomes (mRS 0–2) were observed in 87.5% of patients. Surgical approach selection, vascular control, and intraoperative Doppler guidance were critical to success.

Discussion: KA remains a diagnostic challenge, with a portion of cases confirmed only intraoperatively. Microsurgical clipping of these complex lesions requires precise dissection, temporary vascular control, and intraoperative vascular imaging to ensure complete occlusion and vessel preservation. Age appears to be a risk factor for rupture, underscoring the need for vigilant monitoring in older patients.

Conclusion: Kissing aneurysms remain a diagnostic and surgical challenge due to their complex anatomy and high rupture risk. Accurate imaging, individualized surgical planning, and intraoperative vessel assessment are essential to optimize outcomes.

This study aims to analyze the diagnosis and treatment strategies of intrahepatic splenosis.

Materials and Methods: The clinical data of eleven patients with intrahepatic splenosis, diagnosed and treated at Wuhan Asia General Hospital and Union Hospital (Wuhan, China) between March 2012 and November 2024, were retrospectively analyzed. Enhanced CT imaging and enhanced MRI were used for the screening and diagnosis of liver lesions.

Results: Of the eleven patients with intrahepatic splenosis, six cases were pure intrahepatic splenosis, and five cases included extrahepatic splenosis. Enhanced CT imaging or enhanced MRI showed intrahepatic splenosis lesions with uneven enhancement in the form of fast in and fast out. Two patients were misdiagnosed with hepatocellular carcinoma due to elevated AFP, but biopsy revealed intrahepatic splenosis, thus avoiding unnecessary resection. The size of the intrahepatic splenosis lesions ranged from 1.0 to 4.2 cm. None of the nine patients who underwent surgical resection had splenosis recurrences, and the patients with intrahepatic splenosis confirmed by liver biopsy did not show lesion progression during the active examination period.

Discussion: Splenosis refers to the autotransplantation of viable splenic tissue into different anatomic compartments following splenic injury. The enhanced CT or MRI features of intrahepatic splenosis are similar to those of HCC. Selective hepatic arteriography may help differentiate intrahepatic splenosis from HCC. Percutaneous liver biopsy helps diagnose intrahepatic splenosis.

Conclusion: In patients who have previously undergone splenectomy due to splenic trauma, it is important to consider the potential occurrence of intrahepatic splenosis upon the identification of intrahepatic lesions, and percutaneous liver biopsy is recommended. For individuals without clinical symptoms following a confirmed diagnosis of intrahepatic splenosis, no specific treatment is required.

Case Presentation: The patient presented with upper abdominal pain that worsened after meals. Physical examination revealed a soft abdomen with significant tenderness in the upper abdomen, no rebound tenderness, no muscle tension, no palpable liver or spleen below the costal margin, negative McBurney's sign, negative Murphy's sign, no renal percussion tenderness, negative shifting dullness, normal bowel sounds, and no abnormalities in the anus or rectum. Blood tests showed a white blood cell count of 15.15 x 10^9/L, neutrophil percentage of 92.4%, absolute neutrophil count of 14.0 x 10^9/L, high-sensitivity C-reactive protein of 1.3 mg/L, and amylase of 997.15 U/L. Abdominal CT revealed an irregular, poorly defined mass-like heterogeneous density shadow in the stomach, measuring approximately 83 mm x 38 mm x 51 mm (anteroposterior x transverse x craniocaudal), with an enlarged pancreas and surrounding exudation. After the CT scan, the patient vomited inside the CT room, expelling two white worms. The worms were milky white, ribbon-like, about 200 cm long, with a spoon-shaped scolex, body covered in transverse folds, and a slightly thinner tail. A follow-up CT scan after vomiting showed that the gastric mass had disappeared. Based on the worm morphology, epidemiological history, and laboratory findings, the diagnosis was taeniasis and pancreatitis. The patient was treated with fasting, intravenous administration of H2 receptor antagonists and somatostatin to relieve pancreatitis, and albendazole (2 tablets/day for 3 days) for deworming. Follow-up two months later showed no abnormalities.

Conclusion: This case underscores the importance of considering taeniasis in patients presenting with gastric symptoms and abnormal CT findings. The main takeaway lesson is that prompt recognition and appropriate treatment can lead to successful management of taeniasis, even in unusual presentations. Immediate diagnosis after CT examination and expulsion of worms provides valuable insights into the radiological features of taeniasis.

Methods: This retrospective study included 109 patients who underwent primary CAS between October 2020 and October 2023. HD was defined as intraoperative hypotension (systolic blood pressure < 90 mmHg) and/or bradycardia (heart rate < 60 bpm), while persistent HD was defined as lasting more than 24 hours despite medical therapy. Patients were evaluated according to stent geometry (straight vs. tapered), carotid bulb involvement, plaque characteristics, and procedural variables. Multivariable logistic regression was performed, adjusting for demographic, clinical, anatomical, and procedural factors.

Results: Periprocedural HD occurred in 40.4% of patients, and persistent HD in 25.7%. Persistent HD was significantly more frequent in patients treated with straight stents than in those treated with tapered stents (39.5% vs. 18.6%). Carotid bulb involvement and the use of a straight stent were significantly associated with persistent HD. In multivariable analysis, straight stent use (OR: 1.446; 95% CI: 1.041-2.018) and carotid bulb involvement (OR: 1.490; 95% CI: 1.102-2.015) remained independently associated with persistent HD. Twelve-month clinical outcomes did not differ between stent groups.

Discussion: Persistent hemodynamic depression after carotid artery stenting appears to be influenced not only by patient-related factors but also by procedural characteristics, particularly stent geometry and carotid bulb anatomy. The independent association of straight stent use with prolonged hemodynamic instability underscores the clinical relevance of device selection beyond technical success. Incorporating anatomical conformity into preprocedural planning may reduce prolonged baroreceptor-mediated instability and improve periprocedural safety.

Conclusion: Persistent HD is a clinically relevant complication after CAS. Individualized stent selection may help reduce prolonged hemodynamic instability.

Materials and Methods: In this retrospective study, we analyzed 32 cervical cancer patients who developed SIFs following pelvic radiotherapy and underwent 18F-FDG PET/CT imaging between January 2018 and January 2024. Diagnosis was based on characteristic radiologic findings, clinical correlation, and a minimum 12-month follow-up. Qualitative (fracture patterns, FDG uptake morphology) and quantitative (SUVmax, SUR-BP ratio, CT densitometry) parameters on 18F-FDG PET/CT were evaluated.

Results: SIFs predominantly occurred in postmenopausal women (93.7%, 30/32) at a median of 14 months post-radiotherapy. Sacral involvement was observed as follows: unilateral ala (53.1%, 17/32), bilateral alae (37.5%, 12/32), and extension to the sacral body (9.4%, 3/32). The affected segments were primarily located at S1-S3. Concomitant pelvic fractures were also frequently identified, including pubic (28.1%, 9/32), iliac (25%, 8/32), and bilateral L5 transverse process fractures (6.2%, 2/32). Common CT findings included ill-defined osteosclerosis near the sacroiliac joint (87.5%, 28/32) and linear or curvilinear hypoattenuating fracture lines (68.7%, 22/32). PET revealed characteristic mild, diffuse/patchy FDG uptake parallel to the sacroiliac joint (96.8%, 31/32) with low metabolic activity (mean SUVmax 2.45±0.74, mean SUR-BP 1.46±0.38). Quantitative CT confirmed significant osteopenia within the radiation field (mean HU 36.8±28.6 vs. 78.0±37.3 outside, p<0.001).

Discussion: Post-radiation SIFs predominantly affect postmenopausal cervical cancer patients due to radiotherapy-induced osteoporosis and bone vulnerability. These fractures often present with nonspecific pain and require differentiation from bone metastases, for which 18F-FDG PET/CT is essential due to its ability to detect characteristic metabolic patterns and associated osteoporotic changes. Key diagnostic features include linear or curvilinear hypoattenuating fracture lines, mild diffuse/patchy FDG uptake parallel to the sacroiliac joint, and background osteoporotic changes within radiation fields. Integrated PET/CT outperformed single-modality imaging by enabling simultaneous assessment of bone metabolism and systemic tumor status, a critical advantage over MRI (superior for marrow edema but unable to evaluate systemic disease) and standalone CT (lacking metabolic discrimination of benign vs malignant lesions). Early recognition of SIFs through integrated imaging is critical to avoid misdiagnosis and unnecessary invasive procedures, thereby guiding appropriate conservative management.

Conclusion: SIFs represent a prevalent post-radiotherapy complication in cervical cancer patients, with a particular predilection for postmenopausal women. 18F-FDG PET/CT demonstrates high diagnostic reliability for diagnosing SIFs, which typically present as linear fractures parallel to the sacroiliac joints on a background of osteoporotic changes, accompanied by mild diffuse or patchy FDG uptake and frequently co-occurring with pelvic fractures at other sites. Integrated PET/CT is crucial for early recognition, preventing misdiagnosis as metastasis, and guiding appropriate conservative management.

Methods: Pre-radiotherapy CT images and clinical data from patients with esophageal malignancies treated at the Second Affiliated Hospital of Wenzhou Medical University between January 2015 and December 2023 were retrospectively analyzed. Tumor contours were manually delineated using 3D Slicer, and radiomic features were extracted using PyRadiomics. Features associated with ETF development (p<0.05) were identified via the Mann-Whitney U test and further refined using Least Absolute Shrinkage and Selection Operator (LASSO) regression to determine the final radiomic signature. Subsequently, univariate and multivariate binary logistic regression analyses were performed.

Results: The study included 77 patients, 30 of whom developed ETF. Of the initial 845 radiomic features, 10 were significantly associated with ETF. Among clinical factors, the type of radiation therapy was an independent predictor for ETF. In the training cohort, the radiomics model achieved an AUC of 0.866 (95% CI: 0.7907–0.9402), with a sensitivity of 0.831 and specificity of 0.792. The combined model (radiomics + clinical features) achieved an AUC of 0.892 (95% CI: 0.8238–0.9601), sensitivity of 0.823, and specificity of 0.912. In the validation cohort, the radiomics model had an AUC of 0.736 (95% CI: 0.5781–0.8947), sensitivity of 0.833, and specificity of 0.621. The combined model achieved an AUC of 0.791 (95% CI: 0.6461–0.9354), sensitivity of 0.822, and specificity of 0.797.

Discussion: The combination of radiomic and clinical features achieves excellent AUC performance and shows potential for the non-invasive prediction of ETF following radiotherapy in esophageal cancer patients.

Conclusion: The model, combined with radiomic and clinical features, has great predictive value.

Materials and Methods: We analyzed contrast-enhanced abdominal DSCT images of 75 patients with normal ductal anatomy. Both conventional Polyenergetic Images (PEIs) and VMIs at energy levels ranging from 40–140 keV (10-keV intervals) were reconstructed. The ductal system was categorized into four groups: intrahepatic bile ducts (Group A), extrahepatic bile ducts (Group B), pancreatic ducts (Group C), and the main pancreatic ducts (Group D). Objective image quality parameters, including CT values, image noise, the Contrast-to-Noise Ratio (CNR), and the Signal-to-Noise Ratio (SNR), were systematically measured and compared across different energy levels.

Results: Compared with the PEIs, the VMIs reconstructed at low keV levels via DSCT demonstrated superior image quality across the four groups. Significant differences in CNR values were observed between VMIs at 40 keV and PEIs in Group A [4.30 (2.79, 6.15) vs. 3.37 (2.52, 4.32), p = 0.013], Group B [10.46 (8.41, 12.43) vs. 5.83 (4.47, 6.94), p < 0.001], Group C [11.50 (9.05, 14.48) vs. 5.34 (4.31, 6.56), p < 0.001], and Group D [9.11 (7.00, 11.86) vs. 5.36 (4.34, 6.95), p < 0.001].

Discussion: This suggests a clear advantage of low-energy VMIs in depicting subtle ductal anatomy that is poorly visualized on standard CT. The consistent reduction in image quality metrics with increasing energy further supports the use of low-keV settings for soft-tissue duct evaluation. Limitations, including the retrospective design and single-vendor platform, are acknowledged.

Conclusion: Compared with conventional images, VMIs at low keV exhibit superior image quality; thus, VMIs may be incorporated into routine clinical imaging protocols.

Methods: A comprehensive literature search was conducted across MEDLINE, EMBASE, and the Cochrane Central Register of Controlled Trials up to March 2024 for studies using radiomics or ML techniques applied to pre-treatment MRI scans to predict progression-free survival (PFS) and overall survival (OS) in glioblastoma patients. The primary outcome was the area under the receiver operating characteristic curve (AUC). Study quality was assessed using the QUADAS-2 tool, meta-analysis employed a random-effects model, and heterogeneity was evaluated using the I² statistic.

Results: Sixteen studies comprising a total of 2,342 patients were included. MRI-based machine learning models demonstrated high predictive performance for glioblastoma prognosis (AUC: 0.71–0.92), with a tendency to outperform radiomics-based approaches (AUC: 0.68–0.88). A meta-analysis of 12 studies yielded a pooled AUC of 0.78 (95% CI: 0.74–0.82; p < 0.001) for PFS prediction with moderate heterogeneity (I2 = 59%). Four studies focused on OS prediction, showing no heterogeneity (I2 = 0%) and a pooled AUC of 0.81 (95% CI: 0.77–0.85; p < 0.001). Subgroup analysis revealed that ML models (AUC: 0.83 [95% CI: 0.78–0.87]) statistically outperformed radiomics-based models (AUC: 0.76 [95% CI: 0.71–0.80]) for PFS prediction (p = 0.02).

Discussion: Advanced quantitative MRI techniques, particularly radiomics, demonstrate superior performance over conventional MRI in glioblastoma characterization, improving tumor segmentation, subtype differentiation, and prognostication. By capturing intratumoral heterogeneity, radiomic features achieve higher diagnostic accuracy. The use of the DICOM format enhances model performance through standardized data integration. Radiomics shows promise as a non-invasive biomarker for guiding personalized treatment; however, challenges such as observer variability, methodological heterogeneity, and lack of standardization remain. Future integration with molecular data and validation through large prospective studies are essential for clinical implementation.

Conclusion: Radiomics and ML approaches based on pre-treatment MRI are promising tools for predicting survival outcomes in glioblastoma patients, with ML models demonstrating a slight edge over radiomics for PFS prediction. Standardized protocols and larger multi-center studies are warranted to facilitate clinical adoption.

We apologize for any inconvenience caused and appreciate the opportunity to rectify this matter.

The original article can be found online at: https://www.benthamscience.com/article/153035

ORIGINAL

FUNDING

This study was funded by the Kuwait University Research, Kuwait Grant No. NR02/25.

ACKNOWLEDGEMENTS

We express our sincere gratitude to Mahdi Alajmi, Alsiddiq Khalid, Salem Alshammari, and Mariam Alshammari for their efforts during the data collection process. Sayyed Amusawi and Umar Khan helped with manuscript review. This work was supported and funded by the Kuwait University Research Grant No. NR02/25.

CORRECTED

FUNDING

None.

ACKNOWLEDGEMENTS

We express our sincere gratitude to Mahdi Alajmi, Alsiddiq Khalid, Salem Alshammari, and Mariam Alshammari for their efforts during the data collection process. Sayyed Amusawi and Umar Khan helped with manuscript review.

Methods: This single-center retrospective study included 37 patients with 44 adrenal masses (19 adenomas; 25 metastases). Data were split into training and testing sets (2:1). To expand the training set, data augmentation was performed by multiple sampling (56 labeled slices from 30 masses). Radiomic features were extracted from T2-weighted (T2W), in-phase, out-of-phase, and apparent diffusion coefficient (ADC) sequences, while mass size, T2W signal intensity, heterogeneity, and signal drop were assessed as radiologic features. Dimension reduction was performed by reliability analysis and wrapper-based feature selection with five algorithms. A support vector machine (SVM) was used for classification, and performance was assessed using 10-fold cross-validation and unseen testing. Friedman test and post-hoc analyses compared bootstrapped unseen test area under the curve (AUCs).

Results: Only 12% of radiomic features demonstrated excellent reproducibility. A significant difference was observed among the three models, χ2(2)=779.5, p<0.001. The combined radiomic-radiologic model achieved the best performance (AUC 0.939; accuracy 85.7%), outperforming radiomic-only (AUC 0.898; accuracy 85.7%) and radiologic-only (AUC 0.857; accuracy 78.5%) models (adjusted p<0.001).

Discussion: Integrating radiomic and radiologic features improved classification performance compared to using either feature set alone. Although the reproducibility of radiomic features was limited, their complementary value enhanced model robustness.

Conclusion: A combined radiomic-radiologic ML model based on multi-sequence MRI may serve as a promising non-invasive tool for differentiating atypical adrenal adenomas from metastases.

Methods: In this retrospective study, clinical and ultrasound data from 20 patients with surgically confirmed renal hemangiomas (22 lesions) were analyzed. All patients underwent preoperative conventional ultrasound. Among them, 6 patients (7 lesions) additionally underwent CEUS examination within one month before surgery. Standardized ultrasound techniques and equipment were employed, with focused analysis on the enhancement patterns and hemodynamic characteristics observed on CEUS.

Results: The cohort comprised 10 men and 10 women (mean age 50 years). Most lesions (13/22) were located in the renal medulla. On conventional ultrasound, lesions typically appeared as well-defined, round, hypoechoic nodules, with most showing no significant internal flow on color Doppler imaging. In the 6 patients who underwent CEUS, a characteristic pattern of peripheral nodular enhancement in the arterial phase, followed by progressive centripetal filling, was observed. Peak enhancement intensity was generally comparable to that of the surrounding renal parenchyma. Pathologically, anastomosing hemangioma and capillary hemangioma were the most common subtypes (9 cases each), with immunohistochemical profiles (CD31/CD34 positive, low Ki-67) consistent with benign behavior.

This study reveals a preliminary CEUS pattern of renal hemangiomas characterized by peripheral nodular enhancement with progressive centripetal filling, which may aid in differentiating these rare benign tumors from renal cell carcinoma and help avoid unnecessary surgery. The small sample size is a major limitation, and these findings require validation in larger prospective studies.

Discussion: This study reveals a preliminary CEUS pattern of renal hemangiomas characterized by peripheral nodular enhancement with progressive centripetal filling, which may aid in differentiating these rare benign tumors from renal cell carcinoma, potentially helping to avoid unnecessary surgery. The small sample size is a major limitation, and these findings require validation in larger prospective studies.

Conclusion: The combination of conventional ultrasound and CEUS may enhance the preoperative evaluation of renal hemangiomas. CEUS demonstrates distinctive enhancement patterns that can aid in differentiating these rare benign tumors from other renal malignancies. However, these findings are preliminary and require validation in larger-scale studies.

Materials and Methods: This retrospective cross-sectional study included 173 women with BI-RADS 4 lesions evaluated by mammography and/or ultrasound, with subsequent histopathological confirmation. Cases were identified at the Hospital General de México between January 2023 and May 2024. Associations between BI-RADS subcategory and malignancy, as well as age, lesion laterality, and selected imaging features, were examined using chi-square tests and one-way ANOVA.

Results: Among 173 patients, 41.6% had BI-RADS 4A lesions, 35.8% had 4B lesions, and 22.5% had 4C lesions. Malignancy rates increased across subcategories: 7.5% (4A), 40.0% (4B), and 85.0% (4C) (p < 0.001). Mean age rose with BI-RADS level (42.1, 47.8, and 55.3 years for 4A, 4B, and 4C, respectively), although this trend did not reach statistical significance (p = 0.063). Nodules were the most frequent imaging finding (83.2%), and fibroadenoma was the most common benign diagnosis. Left-sided lesions were more frequently malignant (p = 0.034).

Discussion: In this cohort, BI-RADS 4 subcategorization separated malignancy risk in a clinically meaningful way. Lesion laterality showed an association with malignancy and may merit further evaluation as an adjunct variable in imaging audits.

Conclusion: BI-RADS 4 subclassification corresponded to progressively higher malignancy rates, supporting its use for risk communication and biopsy prioritization. Incorporating histopathological outcomes with basic demographic and anatomic variables, such as laterality, may further strengthen local risk assessment strategies.

Methods: In this retrospective study, 81 patients who were admitted to our center for routine carotid ultrasound and contrast-enhanced ultrasound examinations were enrolled. The patients were assigned to the study and control groups based on whether they had AIS symptoms. Multivariate logistic regression was used to analyze the correlation between risk factors and carotid artery-related AIS.

Results: Significant differences in Intraplaque Neovascularization (IPN) grade, vascular stenosis, different age stages, plaque length and diameter, and hypertension were observed between the two groups (P < 0.05). Two sonographers were satisfactorily consistent in IPN grading diagnosis (Kappa = 0.763). According to the multivariate logistic regression analysis, the IPN grade and hypertension were independent risk factors for carotid artery-associated AIS (P < 0.05). Receiver Operating Characteristic (ROC) analysis showed that IPN grading demonstrated better discriminative performance for AIS than lumen stenosis, with an Area Under the Curve (AUC) of 0.74 versus 0.65.

Discussion: In the study group, the carotid plaques of AIS patients were mostly of IPN grade III-IV. The number of patients with IPN > II was significantly higher in the study group than in the control group (33.3% (27/81) vs. 7.4% (6/81); P < 0.05). The accuracy, sensitivity, specificity, and positive and negative predictive values of carotid canal cavity stenosis were approximately 65.43%, 64.29%, 66.67%, 67.50%, and 63.41%, respectively.

For patients with IPN > II, the values for the aforementioned parameters were 76.54%, 81.81%, 72.92%, 85.36%, and 67.50%, respectively. Statistically significant differences in sensitivity and negative predictive value were observed between the two groups (P < 0.05).

Conclusion: IPN grading demonstrates a stronger association and higher discriminative ability for AIS than for carotid stenosis. It may provide valuable information for early clinical identification, risk stratification, and prevention of carotid artery-related AIS.

Case Presentation: A young woman without known immunosuppression developed multisystem disease involving the peritoneum/ovaries, hepatobiliary structures, lymph nodes, adrenals, and thoracolumbar spine. CT/MRI and PET/CT suggested widespread neoplastic disease. Because FDG avidity is nonspecific, we prioritized histologic confirmation. Surgical exploration and targeted biopsies showed necrotizing granulomatous inflammation compatible with tuberculosis; microbiologic testing supported the diagnosis. The patient commenced directly observed first-line therapy (isoniazid, rifampin, pyrazinamide, ethambutol) as the intensive phase, followed by an isoniazid-rifampin continuation phase. Under treatment, symptoms improved, and interval imaging showed regression of inflammatory lesions.

Conclusion: In cancer-like, multisystem presentations, even in apparently immunocompetent hosts, tissue diagnosis is decisive, and imaging should primarily guide sampling. Early recognition and standardized therapy can prevent irreversible morbidity.

Methods: Fifty-six patients who underwent CCTA scans using dual-layer detector spectral CT (SDCT) were retrospectively enrolled. Dark-blood images were generated by subtracting virtual non-contrast (VNC) datasets from 70-keV datasets. Qualitative evaluation of dark-blood images included assessments of image quality, inner-wall visualization, and outer-wall visualization. Quantitative parameters were compared between conventional CCTA images and dark-blood images. The quantitative assessment involved evaluating contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR). SNR_wall, SNR_lumen, SNR_{periaortic fat}, CNR_wall-lumen, and CNR_{wall-periaortic fat} were calculated. Two experienced radiologists independently evaluated the images, and inter-rater variability was assessed.

Results: Patients were categorized into three groups based on plaque types: Group A (calcified plaques, n=88), Group B (non-calcified plaques, n=15), and Group C (vessels without plaque, n=56). Dark-blood images of non-calcified plaques and vessels without plaque exhibited higher image quality and inner-wall visualization scores compared to calcified plaques (all p < 0.05). The subjective scores of radiologists showed good consistency (all kappa values > 0.7). Compared to conventional images, dark-blood images demonstrated higher quantitative scores in terms of SNR_wall, SNR_lumen, SNR_{periaortic fat}, CNR_wall-lumen, and CNR_{wall-periaortic fat} (all p < 0.001).

Discussion: The dark-blood technique enabled superior coronary wall assessment without misregistration artifacts, overcoming a key limitation of prior subtraction CCTA. RCA motion artifacts remain a technical challenge that warrants phase-specific protocol optimization in our study.

Conclusion: Dark-blood images derived from SDCT demonstrated improved image quality of coronary arteries without misregistration artifacts and enhanced visualization of the coronary vessel wall.

Methods: An improved YOLO11-based detection model incorporating a Mamba-inspired architecture is proposed. A gated state-space modeling module is introduced into the backbone network to enhance the modeling capability of spatial and channel information and effectively focus on key regional features. A Dynamic Upsampling module (DySample) is then adopted in the neck network to improve multi-scale feature fusion. In addition, a Multi-Dimensional Local Channel Attention (MLCA) mechanism is integrated before the detection head to jointly refine spatial and channel features, thereby enhancing the localization capability for lesion areas.

Results: Experimental results demonstrate that the proposed method achieves a precision of 0.837, a recall of 0.636, mAP@0.5 of 0.732, and mAP@0.5:0.95 of 0.505. Compared with the YOLO11 model, these metrics are improved by 3.1%, 0.1%, 2.1%, and 2.5%, respectively, indicating an overall enhancement in detection performance.

Discussion: YOLO11-Mamba has achieved improvements in detection accuracy and localization performance, but there are still some potential limitations. Among these, the introduction of state space models and attention mechanisms has increased the model's parameter count and computational complexity to some extent, which may pose challenges for clinical deployment, pointing the way for future research.

Conclusion: The proposed method demonstrates effective performance in the detection of renal tumors and cysts from CT images. The results show fewer missed detections and improved lesion localization accuracy, suggesting the proposed model is a promising tool for renal lesion detection and clinical imaging.

Methods: This retrospective study involved 1995 individuals aged 50 and above who received CT scans for lung cancer screening from 2016 to 2020. Remnant cholesterol (RC) was calculated as follows: total cholesterol (TC) - (low-density lipoprotein-cholesterol (LDL-c) + high-density lipoprotein-cholesterol (HDL-c)). Low bone mass was defined as bone CT attenuation < 110 HU. Low muscle mass was defined when the area of the erector spinae muscles was < 20 cm² in women and < 25 cm² in men. Osteosarcopenia was defined as bone CT attenuation < 110 HU and muscle area < 20 cm² in women or < 25 cm² in men.

Results: A total of 469 (23.5%) patients with low bone mass, including 268 women and 201 men, were observed. Serum RC was not associated with low bone mass. Elevated serum RC was associated with a lower prevalence of low muscle mass in both women and men (OR = 0.71, 95% CI: 0.50-1.00; OR = 0.53, 95% CI: 0.38-0.75). Serum RC was also associated with osteosarcopenia in women (OR = 0.59, 95% CI: 0.34-1.00) and men (OR = 0.53, 95% CI: 0.29-0.99).

Discussion: RC may be a valuable factor for the early identification and management of sarcopenia or osteosarcopenia. However, further studies are needed to investigate the causal relationships and the mechanisms by which RC affects bone and muscle quality.

Conclusion: Serum RC was not associated with low bone mass but was negatively associated with low muscle mass and osteosarcopenia in older adults.

Case Presentation: We present the case of a young man who experienced sudden neck pain at an altitude of 5200 m during defecation. The pain persisted and radiated to the back, but there were no typical symptoms of aortic dissection. However, on physical examination, the patient was found to have unequal blood pressure in both arms. After completing a CT scan, the diagnosis was confirmed as aortic dissection with subcutaneous emphysema. The patient was transferred to a hospital at a lower altitude to undergo an “aortic arch replacement under cardiopulmonary bypass.” After follow-up, the patient had a good prognosis and was able to independently perform general daily activities.

Conclusion: The purpose of this case report is to raise awareness of the diagnostic interference caused by subcutaneous emphysema and to emphasize accurate diagnosis and timely intervention when encountering patients with atypical chest pain in high-altitude environments, which is expected to gain a therapeutic time window for the patient.

Methods: The proposed VSAG-HDL Net, a novel hybrid deep learning framework designed to enhance the accuracy and interpretability of CXR-based diagnosis. The architecture integrates a Variational Spatial Attention Fusion U-Net (VSA-FU-Net) for lesion segmentation and a Sharpened Cosine Similarity (SCS) Network for disease classification. A dataset of 21,165 CXR images from the Radiography Database was used. Segmentation performance was evaluated using Dice Similarity Coefficient (DSC) and Intersection over Union (IoU), while classification performance was assessed via accuracy metrics.

Results: The VSA-FU-Net achieved a DSC of 90% and an IoU of 95%, indicating high precision in localizing lesions of varying shapes and sizes. The classification module reached an overall accuracy of 95.5%, outperforming traditional CNN-based methods such as CoroDet (+4.3%), CovXNet (+5.3%), and ShuffleNet (+3.9%). Although slightly less accurate than DenseNet+VIT (–2.0%) and DenseNet+VIT+GAP (–2.3%), the proposed framework offers competitive accuracy with significantly reduced model complexity.

Discussion: The elimination of redundant feature extraction and the integration of spatial attention enhance both the diagnostic performance and computational efficiency, making the framework suitable for real-world clinical settings.

Conclusion: VSAG-HDL Net provides a robust, interpretable, and resource-efficient solution for chest disease detection in CXR. Its clinical integration can support early and accurate diagnostic decision-making, particularly in resource-limited environments.

Methods: This retrospective study investigated the thoracic high-resolution computed tomography (HRCT) findings of 229 laboratory-confirmed COVID-19 patients. The cohort comprised 168 (73.4%) males and 61 (26.6%) females, with ages ranging from 18 to 88 years (median age 47 years). Patients were stratified into four age groups: 18–30, 31–45, 46–60, and >60 years. All patients underwent HRCT of the chest using a Canon Alexion 16- slice CT scanner with a low-dose protocol. Two independent radiologists evaluated the HRCT scans, and a CT severity score was calculated for each patient based on the extent of pulmonary involvement within each lung lobe. Scores were then compared across different age groups.

Results: HRCT chest findings in coronavirus infection included small patchy opacities; ground-glass opacity and consolidation were observed in 83% of patients. The present study indicates a positive correlation between higher CT severity scores and older age groups, as well as male gender, compared with younger and female patients.

Discussion: The study showed that 73.4% of patients were male and 26.6% were female, and that more severe CT lung infection (higher CT severity scores) was significantly associated with male gender. More severe pulmonary infection was also more common in patients above 60 years of age. These findings are in agreement with other studies reporting that COVID-19 infection affects males more severely than females.

Conclusion: HRCT chest imaging provides valuable diagnostic information regarding disease severity, percentage of lung involvement, and extent of disease, which is useful for guiding treatment and prognosis.

Materials and Methods: A total of 406 patients (VP: 283; FCI: 123) from two hospitals were retrospectively enrolled and divided into training (n = 218), testing (n = 96), and external validation (n = 92) cohorts. Radiomics features were extracted from chest CT images. Feature selection was performed using the Least Absolute Shrinkage And Selection Operator (LASSO), and logistic regression models were built with clinical, radiomics, and combined inputs. Model performance was assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration, and Decision Curve Analysis (DCA).

Results: The combined model achieved AUCs of 0.981 (95% CI: 0.959 - 0.992), 0.845 (95% CI: 0.762 - 0.950), and 0.835 (95% CI: 0.715 - 0.937) in the training, testing, and external validation cohorts, respectively, and consistently outperformed clinical-only and radiomics-only models.

Discussion: The model identified characteristic clinical and imaging differences between VP and FCI, including higher neutrophil counts, lower lymphocyte counts, and imaging markers such as reversed halo sign and solid nodules in FCI. These findings support the potential of radiomics as a noninvasive tool for early detection and risk stratification.

Conclusion: CT-based radiomics provides an effective approach for differentiating VP and FCI in immunocompromised patients, with potential to improve diagnosis and clinical management.

Materials and Methods: A total of 96 subjects (50 Non-Alcoholic Fatty Liver Disease (NAFLD) patients, 46 healthy individuals) were divided into low-ratio (TG/HDL-C ≤1.5, n=56) and high-ratio (TG/HDL-C >1.5, n=40) groups. Abdominal fast kVp-switching dual-energy CT was performed to measure FF (left lobe (FFL), right anterior lobe (FFRA), right posterior lobe (FFRP)), visceral fat content (FV), virtual monochromatic CT values (HU50-100keV), and liver/spleen CT value ratio (HUL/S). Correlation and ROC analyses were conducted.

Results: TG/HDL-C ratio was positively correlated with FFL, FFRA, FFRP, FV (r=0.7514–0.3787, p<0.001) and negatively correlated with HU50-100keV and HUL/S (r=-0.4171–-0.7513, p<0.001). The high-ratio group had higher FF and FV, lower HU50-100keV and HUL/S (p<0.05). ROC analysis showed the highest AUC was 0.884 (FFRP), followed by FFRA (0.880), FFL (0.872), HUL/S (0.837), and HU100keV (0.835).

Discussion: MMD-derived FF (especially FFRP) exhibited superior predictive performance for TG/HDL-C ratio compared to spectral CT parameters and visceral fat content. This advantage stems from FF’s direct quantification of intrahepatic fat (pathological basis of NAFLD-metabolic interplay), while HU-based parameters are confounded by non-fat tissue components. The study establishes a novel imaging-metabolic association, extending dual-energy CT’s utility from NAFLD diagnosis to cardiovascular risk stratification.

Conclusion: MMD-measured FF and dual-energy CT spectral parameters are correlated with TG/HDL-C ratio, and FF exhibits the best predictive performance for TG/HDL-C in NAFLD patients.

Methods: Seven complementary CNN architectures, InceptionV3, ResNet-50V2, ResNet-152, DenseNet-121, DenseNet-201, VGG19, and Xception, were integrated into a unified ensemble framework using the Geometrically Optimum and Online Weighted Ensemble (GOOWE) strategy. GOOWE computes classifier weights through a geometrically optimal least-squares projection, assigning stronger influence to models with lower validation errors. To further refine decision boundaries and quantify predictive uncertainty, a Gaussian-based fuzzy inference module was applied to the ensemble outputs. The proposed system was evaluated on a hybrid dataset combining the public VinDr-Mammo database with an expert-annotated private cohort from regional hospitals, with performance assessed using accuracy, F1-score, and robustness under multiple experimental settings.

Results: FGOOPNet achieved 98.4% accuracy and highly balanced F1-scores for both benign and malignant classes, outperforming individual CNN models and conventional ensemble techniques. The fuzzy inference layer improved reliability in borderline cases by filtering low-confidence predictions and reducing misclassification.

Discussion: The results demonstrate that combining GOOWE weighting with fuzzy Gaussian reasoning enhances both predictive performance and interpretability. This uncertainty-aware mechanism helps address limitations in conventional CAD systems, particularly in heterogeneous breast tissue and visually ambiguous regions.

Conclusion: FGOOPNet offers a robust and explainable solution for mammographic breast cancer classification, highlighting its potential for integration into clinical decision-support workflows. Future work will focus on extending the model to multi-modal imaging and large-scale multi-center validation.

Methods: Soft tissue lesions detected by computed tomography (CT) and magnetic resonance imaging (MRI) between January 2015 and December 2023 were retrospectively evaluated in this single-center study. The study included 57 benign lesions (55 patients) and 139 metastatic lesions (65 patients). Lesion size, contour characteristics, morphological shape, anatomical localization, perilesional edema, and perilesional vascularity were evaluated. Due to the clustered data structure, the Generalized Estimating Equations (GEE) methodology was used. Model performance was evaluated using ROC curve analysis, precision-recall curve, and Brier score. Statistical analyses were performed using Jamovi v2.6.44, JASP v0.19.3, and R v4.5.1 software.

Results: Metastatic lesions were significantly smaller than benign lesions (median 17.0 mm vs. 33.3 mm; p<0.001). In the GEE analysis, the presence of perilesional edema increased the likelihood of metastasis by 35 times (OR=35.25; 95% CI: 7.58-164.00; p<0.001), and perilesional vascularity increased the likelihood of metastasis by 45 times (OR=44.54; 95% CI: 1.86-1066.00; p = 0.016). Abdominal-pelvic localization showed a 133- fold (OR=133.00; 95% CI: 10.90-1622.00; p<0.001) higher likelihood of metastasis compared to the extremities, while thoracic-anterior chest wall localization showed a 35-fold (OR=35.22; 95% CI: 2.41–514.00; p = 0.007). Each unit increase in standardized size reduced the likelihood of metastasis by 90% (OR=0.10; 95% CI: 0.02-0.42; p = 0.001). The model demonstrated excellent discrimination (AUC-ROC=0.947) and calibration (Brier score=0.075) performance.

Discussion: Our results show that perilesional edema and perilesional vascularity are key diagnostic signs of metastatic lesions. The combined assessment of perilesional findings and anatomical localization can significantly enhance diagnostic accuracy in daily practice. Furthermore, the relationship between lesion size and the metastatic process emphasizes the need for more careful evaluation of smaller lesions.

Conclusion: Perilesional edema, perilesional vascularity, and trunk region localization were associated with soft tissue metastasis. These findings may be helpful in the radiological differentiation of metastasis and benign soft tissue lesions.

Methods: We analyzed 8,038 publications from the Web of Science Core Collection using VOSviewer, Bibliometrix, and CiteSpace. Machine learning clustering quantified collaboration networks, while dual-map overlays and burst detection quantified interdisciplinary bridges and paradigm shifts.

Results: Publication growth showed three phases: steady (2005-2011, +6.2%/year), accelerated (2011-2021, peak 480 publications), and stabilization (2022-2024), with recent decline linked to diagnostic criteria simplification and artificial intelligence-driven consolidation. The USA dominated total output (24.2%), while the UK led international collaboration (44.2% multi-country publications). China’s unique focus on psychoneuroimmunology contrasts with Western clinical-translational priorities. The strongest interdisciplinary link connected Neurology/Sports/Ophthalmology and Molecular/Biology/Genetics fields (Z-score = 5.3). Artificial intelligence drove paradigm shifts, with deep learning showing the highest keyword burst strength (413.27). Central authors (e.g., Massimo Filippi, Frederik Barkhof) bridged magnetic resonance imaging biomarkers and therapeutic innovation.

Discussion: MS-MRI research is evolving from descriptive observations to AI-driven precision medicine. Future success relies on a closed-loop paradigm integrating ultra-high-field MRI and multi-omics.

Conclusion: This analysis reveals: (1) Magnetic resonance imaging-artificial intelligence-biomarker integration resolves clinical-radiological paradoxes, enabling dynamic patient stratification; (2) ultra-high-field magnetic resonance imaging and multi-omics provide a roadmap for precision neurology in therapy personalization; (3) global collaboration synergies may democratize advanced multiple sclerosis care.