A computed tomography image segmentation algorithm for improving the diagnostic accuracy of rectal cancer based on U-net and residual block_Journal of Biomedical Engineering

Authors：

WANG Hao , JI Bangning ,  HE Gang , YU Wenxin

School of Computer Science and Technology, Southwest University of Science and Technology, Mianyang, Sichuan 621010, P. R. China;

Corresponding author：

HE Gang, Email: ganghe@swust.edu.cn

Keywords：

Rectal cancer; Image segmentation; U-net; Residual block; Image pre-processing

DOI：

10.7507/1001-5515.201910027

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

As an important basis for lesion determination and diagnosis, medical image segmentation has become one of the most important and hot research fields in the biomedical field, among which medical image segmentation algorithms based on full convolutional neural network and U-Net neural network have attracted more and more attention by researchers. At present, there are few reports on the application of medical image segmentation algorithms in the diagnosis of rectal cancer, and the accuracy of the segmentation results of rectal cancer is not high. In this paper, a convolutional network model of encoding and decoding combined with image clipping and pre-processing is proposed. On the basis of U-Net, this model replaced the traditional convolution block with the residual block, which effectively avoided the problem of gradient disappearance. In addition, the image enlargement method is also used to improve the generalization ability of the model. The test results on the data set provided by the "Teddy Cup" Data Mining Challenge showed that the residual block-based improved U-Net model proposed in this paper, combined with image clipping and preprocessing, could greatly improve the segmentation accuracy of rectal cancer, and the Dice coefficient obtained reached 0.97 on the verification set.

Citation： WANG Hao, JI Bangning, HE Gang, YU Wenxin. A computed tomography image segmentation algorithm for improving the diagnostic accuracy of rectal cancer based on U-net and residual block. Journal of Biomedical Engineering, 2022, 39(1): 166-174. doi: 10.7507/1001-5515.201910027 Copy

1.	中华人民共和国国家卫生健康委员会. 中国结直肠癌诊疗规范(2020年版). 中华外科杂志, 2020, 58(8): 561-585.
2.	Zheng R, Zeng H, Zhang S, et al. Estimates of cancer incidence and mortality in China, 2013[J]. Chinese Journal of Cancer, 2017, 36(1): 384-389.
3.	Bhandari A, Woodhouse M, Gupta S. Colorectal cancer is a leading cause of cancer incidence and mortality among adults younger than 50 years in the USA: a SEER-based analysis with comparison to other young-onset cancers. J Investig Med, 2017, 65(2): 311-315.
4.	Even-Sapir E, Parag Y, Lerman H, et al. Detection of recurrence in patients with rectal cancer: PET/CT after abdominoperineal or anterior resection. Radiology, 2004, 232(3): 815-822.
5.	Butch R J, Stark D D, Wittenberg J, et al. Staging rectal cancer by MR and CT. AJR Am J Roentgenol, 1986, 146(6): 1155-1160.
6.	Cnudde V, Boone M N. High-resolution X-ray computed tomography in geosciences: a review of the current technology and applications. Earth-Science Reviews, 2013, 123:1-17.
7.	Jena M, Mishra S P, Mishra D. A survey on applications of machine learning techniques for medical image segmentation. International Journal of Engineering and Technology, 2018, 7(4): 4489-4495.
8.	朱柏辉, 万智萍. 基于小波特性与边缘模糊检测的医学图像处理. 生物医学工程学杂志, 2014, 31(3): 493-498.
9.	陈诗慧, 刘维湘, 秦璟, 等. 基于深度学习和医学图像的癌症计算机辅助诊断研究进展. 生物医学工程学杂志, 2017, 34(2): 314-319.
10.	Dice L R. Measures of the amount of ecologic association between species. Ecology, 1945, 26(3):297-302.
11.	Lambregts D J, Beets G L, Maas M, et al. Tumour ADC measurements in rectal cancer: effect of ROI methods on ADC values and interobserver variability. Eur Radiol, 2011, 21(12): 2567-2574.
12.	Nougaret S, Vargas H, Lakhman Y, et al. Intravoxel incoherent motion-derived histogram metrics for assessment of response after combined chemotherapy and radiation therapy in rectal cancer: initial experience and comparison between single-section and volumetric analyses. Radiology, 2016, 280(2): 446-454.
13.	van Heeswijk M M, Lambregts D M, van Griethuysen J J, et al. Automated and semiautomated segmentation of rectal tumor volumes on diffusion-weighted MRI: can it replace manual volumetry?. Int J Radiat Oncol Biol Phys, 2016, 94(4): 824-831.
14.	Ha H I, Kim A Y, Yu C S, et al. Locally advanced rectal cancer: diffusion-weighted MR tumour volumetry and the apparent diffusion coefficient for evaluating complete remission after preoperative chemoradiation therapy. Eur Radiol, 2013, 23(12): 3345-3353.
15.	Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation // International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Springer International Publishing, 2015: 234-241.
16.	Mooij G, Bagulho I, Huisman H. Automatic segmentation of prostate zones. arXiv.org, 2018. arXiv:1806.07146.
17.	LeCun Y, Boser B, Denker J S, et al. Back-propagation applied to handwritten zip-code recognition. Neural Computation, 1989, 1(4):541-551.
18.	Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, 25: 1097-1105.
19.	Huang Gao, Liu Zhuang, Laurens V D M, et al. Densely connected convolutional networks. IEEE Computer Society, 2016. DOI: 10.1109/CVPR.2017.243.
20.	Milletari F, Navab N, Ahmadi S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation//2016 Fourth International Conference on 3D Vision (3DV), IEEE, 2016: 565-571.
21.	Trebeschi S, van Griethuysen J, Lambregts D, et al. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Sci Rep, 2017, 7(1): 5301.
22.	Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015.
23.	Kim J, Oh J E, Lee J, et al. Rectal cancer: toward fully automatic discrimination of T2 and T3 rectal cancers using deep convolutional neural network. Int J Imaging Syst Technol, 2019, 29(3): 247-259.
24.	Zhou Z, Siddiquee M, Tajbakhsh N, et al. UNet++: a nested U-net architecture for medical image segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018), 2018, 11045: 3-11.
25.	Han J, Moraga C. The Influence of the sigmoid function parameters on the speed of backpropagation learning// International Workshop on Artificial Neural Networks: from Natural to Artificial Neural Computation. Springer, 1995: 195-201.
26.	Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines// Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML'10). 2010: 807-814.
27.	Clevert D A, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). Computer Science, 2015. arXiv:1511.07289.
28.	Klambauer G, Unterthiner T, Mayr A, et al. Self-normalizing neural networks//Proceedings of the 31st international conference on neural information processing systems, 2017: 972-981.
29.	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification//2015 IEEE International Conference on Computer Vision (ICCV), IEEE Computer Society, 2015: 1026-1034.
30.	Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research, 2010, 9:249-256.
31.	He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016: 770-778.
32.	Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift//International Conference on Machine Learning. PMLR, 2015: 448-456.
33.	Chen Wanli, Zhang Yue, He Junjun, et al. W-net: bridged U-net for 2D medical image segmentation. arXiv preprint, 2018, arXiv:1807.04459.

1. 中华人民共和国国家卫生健康委员会. 中国结直肠癌诊疗规范(2020年版). 中华外科杂志, 2020, 58(8): 561-585.
2. Zheng R, Zeng H, Zhang S, et al. Estimates of cancer incidence and mortality in China, 2013[J]. Chinese Journal of Cancer, 2017, 36(1): 384-389.
3. Bhandari A, Woodhouse M, Gupta S. Colorectal cancer is a leading cause of cancer incidence and mortality among adults younger than 50 years in the USA: a SEER-based analysis with comparison to other young-onset cancers. J Investig Med, 2017, 65(2): 311-315.
4. Even-Sapir E, Parag Y, Lerman H, et al. Detection of recurrence in patients with rectal cancer: PET/CT after abdominoperineal or anterior resection. Radiology, 2004, 232(3): 815-822.
5. Butch R J, Stark D D, Wittenberg J, et al. Staging rectal cancer by MR and CT. AJR Am J Roentgenol, 1986, 146(6): 1155-1160.
6. Cnudde V, Boone M N. High-resolution X-ray computed tomography in geosciences: a review of the current technology and applications. Earth-Science Reviews, 2013, 123:1-17.
7. Jena M, Mishra S P, Mishra D. A survey on applications of machine learning techniques for medical image segmentation. International Journal of Engineering and Technology, 2018, 7(4): 4489-4495.
8. 朱柏辉, 万智萍. 基于小波特性与边缘模糊检测的医学图像处理. 生物医学工程学杂志, 2014, 31(3): 493-498.
9. 陈诗慧, 刘维湘, 秦璟, 等. 基于深度学习和医学图像的癌症计算机辅助诊断研究进展. 生物医学工程学杂志, 2017, 34(2): 314-319.
10. Dice L R. Measures of the amount of ecologic association between species. Ecology, 1945, 26(3):297-302.
11. Lambregts D J, Beets G L, Maas M, et al. Tumour ADC measurements in rectal cancer: effect of ROI methods on ADC values and interobserver variability. Eur Radiol, 2011, 21(12): 2567-2574.
12. Nougaret S, Vargas H, Lakhman Y, et al. Intravoxel incoherent motion-derived histogram metrics for assessment of response after combined chemotherapy and radiation therapy in rectal cancer: initial experience and comparison between single-section and volumetric analyses. Radiology, 2016, 280(2): 446-454.
13. van Heeswijk M M, Lambregts D M, van Griethuysen J J, et al. Automated and semiautomated segmentation of rectal tumor volumes on diffusion-weighted MRI: can it replace manual volumetry?. Int J Radiat Oncol Biol Phys, 2016, 94(4): 824-831.
14. Ha H I, Kim A Y, Yu C S, et al. Locally advanced rectal cancer: diffusion-weighted MR tumour volumetry and the apparent diffusion coefficient for evaluating complete remission after preoperative chemoradiation therapy. Eur Radiol, 2013, 23(12): 3345-3353.
15. Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation // International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Springer International Publishing, 2015: 234-241.
16. Mooij G, Bagulho I, Huisman H. Automatic segmentation of prostate zones. arXiv.org, 2018. arXiv:1806.07146.
17. LeCun Y, Boser B, Denker J S, et al. Back-propagation applied to handwritten zip-code recognition. Neural Computation, 1989, 1(4):541-551.
18. Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, 25: 1097-1105.
19. Huang Gao, Liu Zhuang, Laurens V D M, et al. Densely connected convolutional networks. IEEE Computer Society, 2016. DOI: 10.1109/CVPR.2017.243.
20. Milletari F, Navab N, Ahmadi S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation//2016 Fourth International Conference on 3D Vision (3DV), IEEE, 2016: 565-571.
21. Trebeschi S, van Griethuysen J, Lambregts D, et al. Deep learning for fully-automated localization and segmentation of rectal cancer on multiparametric MR. Sci Rep, 2017, 7(1): 5301.
22. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015.
23. Kim J, Oh J E, Lee J, et al. Rectal cancer: toward fully automatic discrimination of T2 and T3 rectal cancers using deep convolutional neural network. Int J Imaging Syst Technol, 2019, 29(3): 247-259.
24. Zhou Z, Siddiquee M, Tajbakhsh N, et al. UNet++: a nested U-net architecture for medical image segmentation. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2018), 2018, 11045: 3-11.
25. Han J, Moraga C. The Influence of the sigmoid function parameters on the speed of backpropagation learning// International Workshop on Artificial Neural Networks: from Natural to Artificial Neural Computation. Springer, 1995: 195-201.
26. Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines// Proceedings of the 27th International Conference on International Conference on Machine Learning (ICML'10). 2010: 807-814.
27. Clevert D A, Unterthiner T, Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). Computer Science, 2015. arXiv:1511.07289.
28. Klambauer G, Unterthiner T, Mayr A, et al. Self-normalizing neural networks//Proceedings of the 31st international conference on neural information processing systems, 2017: 972-981.
29. He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification//2015 IEEE International Conference on Computer Vision (ICCV), IEEE Computer Society, 2015: 1026-1034.
30. Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research, 2010, 9:249-256.
31. He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2016: 770-778.
32. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift//International Conference on Machine Learning. PMLR, 2015: 448-456.
33. Chen Wanli, Zhang Yue, He Junjun, et al. W-net: bridged U-net for 2D medical image segmentation. arXiv preprint, 2018, arXiv:1807.04459.

Journal of Biomedical Engineering

A computed tomography image segmentation algorithm for improving the diagnostic accuracy of rectal cancer based on U-net and residual block

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content