Title:Blend U-Net: Redesigning Skip Connections to Obtain Multiscale Features for
Lung CT Images Segmentation
Volume: 20
Author(s): Pengfei Leng, Zhifei Xu, Zhaohui Zhu and Zhigeng Pan*
Affiliation:
- Institute of VR and Intelligent System, Hangzhou Normal University, Hangzhou, China
- School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science & Technology, Nanjing, China
Keywords:
Lung cancer, Lung nodules, Medical image segmentation, Nested structures, Skip connection, Deep supervision.
Abstract:
Background:
Lung cancer is a pervasive and persistent issue worldwide, with the highest morbidity and mortality among all cancers for many years. In the
medical field, computer tomography (CT) images of the lungs are currently recognized as the best way to help doctors detect lung nodules and thus
diagnose lung cancer. U-Net is a deep learning network with an encoder-decoder structure, which is extensively employed for medical image
segmentation and has derived many improved versions. However, these advancements do not utilize various feature information from all scales,
and there is still room for future enhancement.
Methods:
In this study, we proposed a new model called Blend U-Net, which incorporates nested structures, redesigned long and short skip connections, and
deep supervisions. The nested structures and the long and short skip connections combined characteristic information of different levels from
feature maps in all scales, while the deep supervision learning hierarchical representations from all-scale concatenated feature maps. Additionally,
we employed a mixed loss function to obtain more accurate results.
Results:
We evaluated the performance of the Blend U-Net against other architectures on the publicly available Lung Image Database Consortium and
Image Database Resource Initiative (LIDC-IDRI) dataset. Moreover, the accuracy of the segmentation was verified by using the dice coefficient.
Blend U-Net with a boost of 0.83 points produced the best outcome in a number of baselines.
Conclusion:
Based on the results, our method achieves superior performance in terms of dice coefficient compared to other methods and demonstrates greater
proficiency in segmenting lung nodules of varying sizes.