Login Register Cart 0
Current Medical Imaging

Current Medical Imaging

Editor-in-Chief

ISSN (Print): 1573-4056
ISSN (Online): 1875-6603

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Spinal Cord Image Denoising Using Dncnn Algorithm

Author(s): R. Jerlin*, Priya Murugasen and N.R Shanker*

Volume 21, 2025

Published on: 28 February, 2025

Article ID: e15734056337613 Pages: 18

DOI: 10.2174/0115734056337613241209072322

open_access

Become a Editorial Board Member
Become a Reviewer
Become a Editor
Become a Section Editor

Abstract

Background: Spinal image denoising plays a vital role in the accurate diagnosis of disc herniation (DH).

Objective: Traditional denoising algorithms perform less due Limited Directional Selectivity problem and do not adequately capture directional information in pixels. Traditional algorithms' edge representation and texture details are insufficient for the earlier detection of DH. Limited Directional Selectivity leads to inaccurate diagnosis and classification of Disc Herniation (DH) stages. The DH stages are (i) Degeneration (ii) Prolapse (iii) Extrusion and (iv) Sequestration. Moreover, detection of DH size below 2mm using MR image is the major problem.

Methods: To solve the above problem, spinal cord MR images fed to the proposed Parrot optimization tuned Denoising Convolutional Neural Network (Po- DnCNN) algorithm for perspective enhancement of nucleus pulposus region in the spinal cord, vertebrae. The perspective enhancement of Spinal cord image led to the accurate classification of stages and earlier detection of DH by using the proposed Hippopotamus optimization- Fast Hybrid Vision Transformer (Ho–FastViT) algorithm. For this study, spinal cord MR images are obtained from the Grand Challenge website – SPIDER dataset.

Results: The proposed Po-DnCNN method and Ho-FastViT results are analysed quantitatively and qualitatively based on the edge, contrast, classification of the stage, and enhancement of the projected nucleus pulposus region in the spinal cord and vertebrae. The predicted DH results using the proposed method are compared with the manual Pfirrman Grade value of the spinal card method.

Conclusion: Proposed method is better than traditional methods for earlier detection of DH. Po-DnCNN and Ho-FastViat methods give high accuracy of about 98% and 97% compared to traditional methods.

Keywords: MR spine image, Denoising convolutional neural network (DnCNN), Discrete wavelet transform (DWT), Stationary wavelet transform (SWT), Nucleus pulposus, Vertebrae.

[1]
Sudirman S, Kafri AA, Natalia F, et al. Lumbar spine MRI dataset. Mendel Data 2019; V2: k57fr854j2.2.
[http://dx.doi.org/10.17632/k57fr854j2.2]
[2]
Ohnmeiss DD, Vanharanta H, Ekholm J. Degree of disc disruption and lower extremity pain. Spine 1997; 22(14): 1600-5.
[http://dx.doi.org/10.1097/00007632-199707150-00015] [PMID: 9253095]
[3]
Zou T, Liu XY, Wang PC, et al. Incidence of spontaneous resorption of lumbar disc herniation: A meta-analysis. Clin Spine Surg 2024; 37(6): 256-69.
[PMID: 37559207]
[4]
Fujinoki K, Ashizawa K. Directional lifting wavelet transform for image edge analysis. Sign Process 2024; 216: 109188.
[http://dx.doi.org/10.1016/j.sigpro.2023.109188]
[5]
Prabu M, Shanker NR, Kavida CA, Ganesh E. Geometric distortion and mixed pixel elimination via TDYWT image enhancement for precise spatial measurement to avoid land survey error modeling. Soft Comput 2020; 24(19): 14687-705.
[http://dx.doi.org/10.1007/s00500-020-04814-x]
[6]
Duan X, Xiong H, Liu R, Duan X, Yu H. Enhanced deep leaning model for detection and grading of lumbar disc herniation from MRI. Med Biol Eng Comput 2024; 62(12): 3709-19.
[http://dx.doi.org/10.1007/s11517-024-03161-5] [PMID: 38967693]
[7]
Neubert A, Fripp J, Engstrom C, Schwarz D, Weber MA, Crozier S. Statistical shape model reconstruction with sparse anomalous deformations: Application to intervertebral disc herniation. Comput Med Imaging Graph 2015; 46(Pt 1): 11-9.
[http://dx.doi.org/10.1016/j.compmedimag.2015.05.002] [PMID: 26060085]
[8]
Wilke HJ, Kienle A, Maile S, Rasche V, Roscher BN. A new dynamic six degrees of freedom disc-loading simulator allows to provoke disc damage and herniation. Eur Spine J 2016; 25(5): 1363-72.
[http://dx.doi.org/10.1007/s00586-016-4416-5] [PMID: 26838335]
[9]
Huang X, Ye L, Wu Z, et al. Biomechanical effects of lateral bending position on performing cervical spinal manipulation for cervical disc herniation: A three-dimensional finite element analysis. Evid Based Complement Alternat Med 2018; 2018(1): 2798396.
[http://dx.doi.org/10.1155/2018/2798396] [PMID: 29991954]
[10]
Kang MS, Hwang JH, Choi DJ, et al. Clinical outcome of biportal endoscopic revisional lumbar discectomy for recurrent lumbar disc herniation. J Orthop Surg Res 2020; 15(1): 557.
[http://dx.doi.org/10.1186/s13018-020-02087-6] [PMID: 33228753]
[11]
Pan J, Wang Y, Huang Y. Coexistence of intervertebral disc herniation with intradural schwannoma in a lumbar segment: A case report. World J Surg Oncol 2016; 14(1): 113.
[http://dx.doi.org/10.1186/s12957-016-0864-y] [PMID: 27091024]
[12]
Lao L, Daubs MD, Takahashi S, et al. Kinetic magnetic resonance imaging analysis of lumbar segmental motion at levels adjacent to disc herniation. Eur Spine J 2016; 25(1): 222-9.
[http://dx.doi.org/10.1007/s00586-015-3977-z] [PMID: 25921654]
[13]
Mbarki W, Bouchouicha M, Frizzi S, Tshibasu F, Farhat LB, Sayadi M. Lumbar spine discs classification based on deep convolutional neural networks using axial view MRI. Interdiscip Neurosurg 2020; 22: 100837.
[http://dx.doi.org/10.1016/j.inat.2020.100837]
[14]
Kelekis A, Filippiadis DK. Percutaneous treatment of cervical and lumbar herniated disc. Eur J Radiol 2015; 84(5): 771-6.
[http://dx.doi.org/10.1016/j.ejrad.2014.02.023] [PMID: 24673977]
[15]
Yilmaz H, Ertürk AR, Karataş A, Atci İB, Yurt A. Posterior laminoforaminotomy in the treatment of lateralcervical herniated disc and foraminal stenosis. Turk J Med Sci 2016; 46(2): 424-9.
[http://dx.doi.org/10.3906/sag-1412-61] [PMID: 27511506]
[16]
Solmaz B, Aydin AL, Gomleksiz C, et al. Skipping posterior dynamic transpedicular stabilization for distant segment degenerative disease. Adv Orthop 2012; 2012: 1-7.
[http://dx.doi.org/10.1155/2012/496817] [PMID: 23091736]
[17]
The outcome predicted value of enhanced MRI for prolapsed or sequestrated lumbar disc herniation. Chinese J Orthopaed 2021; 1350-60.
[18]
Ambrosio L, Schol J, Fernández RC, et al. Getting to the core: Exploring the embryonic development from notochord to nucleus pulposus. J Dev Biol 2024; 12(3): 18.
[http://dx.doi.org/10.3390/jdb12030018] [PMID: 39051200]
[19]
Sumathi G, Uma DM. Harnessing deep learning (DL) for image inpainting in healthcare system-methods and challenges.In Computer Vision and AI-Integrated IoT Technologies in the Medical Ecosystem. CRC Press 2024; pp. 152-75.
[20]
He S, Zou Y, Li B, et al. An image inpainting-based data augmentation method for improved sclerosed glomerular identification performance with the segmentation model EfficientNetB3-Unet. Sci Rep 2024; 14(1): 1033.
[http://dx.doi.org/10.1038/s41598-024-51651-1] [PMID: 38200109]
[21]
Kawathekar ID, Areeckal AS, Aparna . A novel deep learning pipeline for vertebra labeling and segmentation of spinal computed tomography images. IEEE Access 2024; 12: 15330-47.
[http://dx.doi.org/10.1109/ACCESS.2024.3358874]
[22]
Kim C, Park SM, Lee S, Lee D. A deep learning harmonization of Multi-Vendor MRI for robust intervertebral disc segmentation. IEEE Access 2024; 12: 19482-99.
[http://dx.doi.org/10.1109/ACCESS.2024.3360272]
[23]
Yaseen M, Ali M, Ali S, Hussain A, Joo MI, Kim HC. Cervical spine fracture detection and classification using two-stage deep learning methodology. IEEE Access 2024; 12: 72131-42.
[http://dx.doi.org/10.1109/ACCESS.2024.3398061]
[24]
Liu J, Zhou Y, Cui X, et al. Multi-scale hybrid attention convolutional neural network for automatic segmentation of lumbar vertebrae from MRI. IEEE Access 2024; 12: 77999-8013.
[http://dx.doi.org/10.1109/ACCESS.2024.3407833]
[25]
Sapkota R, Ahmed D, Karkee M. Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments. Artif Int Agric 2024; 13: 84-99.
[http://dx.doi.org/10.1016/j.aiia.2024.07.001]
[26]
Thammasanya T, Patiam S, Rodcharoen E, Chotikarn P. A new approach to classifying polymer type of microplastics based on Faster-RCNN-FPN and spectroscopic imagery under ultraviolet light. Sci Rep 2024; 14(1): 3529.
[http://dx.doi.org/10.1038/s41598-024-53251-5] [PMID: 38346972]
[27]
Kong X, Li X, Zhu X, Guo Z, Zeng L. Detection model based on improved faster-RCNN in apple orchard environment. Int Syst Appl 2024; 21: 200325.
[http://dx.doi.org/10.1016/j.iswa.2024.200325]
[28]
Liu H, Zhang C, Deng Y, Liu T, Zhang Z, Li YF. Orientation cues-aware facial relationship representation for head pose estimation via transformer. IEEE Trans Image Proc 2023; 32: 6289-302.
[http://dx.doi.org/10.1109/TIP.2023.3331309] [PMID: 37963008]
[29]
Liu H, Zhang C, Deng Y, Xie B, Liu T, Li YF. TransIFC: Invariant cues-aware feature concentration learning for efficient fine-grained bird image classification. IEEE Trans Multimed. IEEE 2023; pp. 1-14.
[30]
Liu H, Zhou Q, Zhang C, et al. MMATrans: Muscle movement aware representation learning for facial expression recognition via transformers. IEEE Trans Industr Inform. IEEE 2024; pp. 1-12.
[http://dx.doi.org/10.1109/TII.2024.3431640]
[31]
Liu T, Liu H, Yang B, Zhang Z. LDCNet: Limb direction cues-aware network for flexible human pose estimation in industrial behavioral biometrics systems. IEEE Trans Industr Inform 2023; 20(6): 8068-78.
[32]
Liu H, Liu T, Chen Y, Zhang Z, Li YF. EHPE: Skeleton cues-based gaussian coordinate encoding for efficient human pose estimation. IEEE Trans Multimed 2022; 26: 8464-75.
[33]
Liu H, Liu T, Zhang Z, Sangaiah AK, Yang B, Li Y. ARHPE: Asymmetric relation-aware representation learning for head pose estimation in industrial human–computer interaction. IEEE Trans Industr Inform 2022; 18(10): 7107-17.
[http://dx.doi.org/10.1109/TII.2022.3143605]
[34]
Koresh HJD. Implementation and efficient analysis of preprocessing techniques in deep learning for image classification. Curr Med Imaging Rev 2024; 20: e290823220482.
[http://dx.doi.org/10.2174/1573405620666230829150157] [PMID: 37649293]
[35]
Bhandari A, Greenhill M, Anthony M, Sharma S, Mushtaq R. MRI imaging appearance of hyperostosis frontalis interna (HFI): A case report of focal benign enhancement. Curr Med Imaging Rev 2024; 20: e200723218926.
[http://dx.doi.org/10.2174/1573405620666230720103113] [PMID: 37489785]
[36]
Ma X, Lin Q, Guo S, et al. Multimodal data-driven segmentation of bone metastasis lesions in SPECT bone scans using deep learning. Curr Med Imaging Rev 2024; 20: e15734056324977.
[http://dx.doi.org/10.2174/0115734056324977240911073841] [PMID: 39297464]
[37]
Sivakumari T, Vani R. Corrigendum to: Deep learning-based automated knee joint localization in radiographic images using faster R-CNN. Curr Med Imaging Rev 2024; 20: e060624230768.
[http://dx.doi.org/10.2174/157340562001240606112211] [PMID: 39185659]

Rights & Permissions Print Cite
Article Metrics
Pdf icon 29
Html icon 1
Find your institution