Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function_Journal of Biomedical Engineering

Authors：

 XIAO Hanguang , LI Huanqi , RAN Zhiqiang , ZHANG Qihang , ZHANG Bolong , WEI Yujia , ZHU Xiuhong

School of Artificial Intelligence, Chongqing University of Technology, Chongqing 401135, P. R. China;

Corresponding author：

XIAO Hanguang, Email: hgxiao@cqut.edu.cn

Keywords：

Corona virus disease 2019; Lesion segmentation; Computed tomography; Level set distance map; Level set generalized Dice loss function

DOI：

10.7507/1001-5515.202206051

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.

Citation： XIAO Hanguang, LI Huanqi, RAN Zhiqiang, ZHANG Qihang, ZHANG Bolong, WEI Yujia, ZHU Xiuhong. Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function. Journal of Biomedical Engineering, 2023, 40(4): 743-752. doi: 10.7507/1001-5515.202206051 Copy

1.	World Health Organization, COVID-19 weekly epidemiological update. (20 May 2023)[20 May 2023]. http://www.who.int.
2.	张龙浩, 李柏宏, 贾鹏, 等. 新型冠状病毒(SARS-CoV-2)全球研究现状分析. 生物医学工程学杂志, 2020, 37(2): 236-245.
3.	Zheng B, Liu Y, Zhu Y, et al. MSD-Net: multi-scale discriminative network for COVID-19 lung infection segmentation on CT. IEEE Access, 2020, 8: 185786-185795.
4.	董婷, 魏珑, 叶晓丹, 等. 基于空洞空间卷积池化金字塔结构和注意力机制的全卷积残差网络磨玻璃肺结节分割方法. 生物医学工程学杂志, 2022, 39(3): 441-451.
5.	Xu X, Jiang X, Ma C, et al. A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering, 2020, 6(10): 1122-1129.
6.	Shi Z, Ma J, Zhao M, et al. Many is better than one: an integration of multiple simple strategies for accurate lung segmentation in CT images. BioMed Research International, 2016, 2016: 1480423.
7.	Dai S, Lu K, Dong J, et al. A novel approach of lung segmentation on chest CT images using graph cuts. Neurocomputing, 2015, 168: 799-807.
8.	Zhao J, Ji G, Han X, et al. An automated pulmonary parenchyma segmentation method based on an improved region growing algorithmin PET-CT imaging. Frontiers of Computer Science, 2016, 10(1): 189-200.
9.	Wang J, Guo H. Automatic approach for lung segmentation with juxta-pleural nodules from thoracic CT based on contour tracing and correction. Computational and Mathematical Methods in Medicine, 2016, 2016: 2962047.
10.	Zhou J, Yan Z, Lasio G, et al. Automated compromised right lung segmentation method using a robust atlas-based active volume model with sparse shape composition prior in CT. Computerized Medical Imaging and Graphics, 2015, 46: 47-55.
11.	Chung H, Ko H, Jeon S J, et al. Automatic lung segmentation with juxta-pleural nodule identification using active contour model and Bayesian approach. IEEE Journal of Translational Engineering in Health and Medicine, 2018, 6: 1800513.
12.	肖汉光, 冉智强, 黄金锋, 等. 基于电子计算机断层扫描图像的肺实质分割方法研究进展. 生物医学工程学杂志, 2021, 38(2): 379-386.
13.	Khan A, Garner R, Rocca M L, et al. A novel threshold-based segmentation method for quantification of COVID-19 lung abnormalities. Signal Image Video Process, 2023, 17(4): 907-914.
14.	Chakraborty S, Mali K. A morphology-based radiological image segmentation approach for efficient screening of COVID-19. Biomedical Signal Processing and Control, 2021, 69: 102800.
15.	Akbari Y, Hassen H, Al-Maadeed S, et al. COVID-19 lesion segmentation using lung CT scan images: comparative study based on active contour models. Applied Sciences, 2021, 11(17): 8039.
16.	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation//MICCAI 2015: 18th International Conference, Munich: Springer, 2015: 234-241.
17.	Zhao Xiangyu, Zhang Peng, Song Fan, et al. D2A U-Net: automatic segmentation of covid-19 lesions from CT slices with dilated convolution and dual attention mechanism. 2021. arXiv:2102.05210.
18.	Joseph Raj A N, Zhu H, Khan A, et al. ADID-UNET−a segmentation model for COVID-19 infection from lung CT scans. PeerJ Computer Science, 2021, 7: e349.
19.	Wang G, Liu X, Li C, et al. A noise-robust framework for automatic segmentation of COVID-19 pneumonia lesions from CT images. IEEE Transactions on Medical Imaging, 2020, 39(8): 2653-2663.
20.	Zhou T, Canu S, Ruan S. Automatic COVID-19 CT segmentation using U-Net integrated spatial and channel attention mechanism. International Journal of Imaging Systems and Technology, 2021, 31(1): 16-27.
21.	Xiao H, Ran Z, Mabu S, et al. SAUNet++: an automatic segmentation model of COVID-19 lesion from CT slices. The Visual Computer, 2022. DOI: 10.1007/s00371-022-02414-4.
22.	Zhou Z, Siddiquee M M R, 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.
23.	Luo Xiangde, Chen Jieneng, Song Tao, et al. Semi-supervised medical image segmentation through dual-task consistency. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2021), 2021, 35(10): 8801-8809.
24.	Abraham N, Khan N M. A novel focal Tversky loss function with improved attention U-Net for lesion segmentation//2019 IEEE International Symposium on Biomedical Imaging(ISBI), Venice: IEEE, 2019: 683-687.
25.	Sudre C H, Li W, Vercauteren T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations// Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2017), Québec: Springer, 2017: 240-248.
26.	Ma J, Wang Y, An X, et al. Towards efficient COVID-19 CT annotation: a benchmark for lung and infection segmentation. 2020. arXiv:2004.12537.
27.	Morozov S P, Andreychenko A E, Pavlov N A, et al. Mosmeddata: chest CT scans with COVID-19 related findings dataset. 2020. arXiv:2005.06465.
28.	Fan D P, Zhou T, Ji G P, et al. Inf-Net: automatic COVID-19 lung infection segmentation from CT images. IEEE Transactions on Medical Imaging, 2020. 39(8): 2626-2637.
29.	Jin Q, Meng Z, Sun C, et al. RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans. Frontiers in Bioengineering and Biotechnology, 2020, 8: 605132.
30.	Qiu Y, Liu Y, Li S, et al. MiniSeg: an extremely minimum network for efficient COVID-19 segmentation//35th AAAI Conference on Artificial Intelligence 2021. DOI: 10.1609/aaai.v35i6.16617.

1. World Health Organization, COVID-19 weekly epidemiological update. (20 May 2023)[20 May 2023]. http://www.who.int.
2. 张龙浩, 李柏宏, 贾鹏, 等. 新型冠状病毒(SARS-CoV-2)全球研究现状分析. 生物医学工程学杂志, 2020, 37(2): 236-245.
3. Zheng B, Liu Y, Zhu Y, et al. MSD-Net: multi-scale discriminative network for COVID-19 lung infection segmentation on CT. IEEE Access, 2020, 8: 185786-185795.
4. 董婷, 魏珑, 叶晓丹, 等. 基于空洞空间卷积池化金字塔结构和注意力机制的全卷积残差网络磨玻璃肺结节分割方法. 生物医学工程学杂志, 2022, 39(3): 441-451.
5. Xu X, Jiang X, Ma C, et al. A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering, 2020, 6(10): 1122-1129.
6. Shi Z, Ma J, Zhao M, et al. Many is better than one: an integration of multiple simple strategies for accurate lung segmentation in CT images. BioMed Research International, 2016, 2016: 1480423.
7. Dai S, Lu K, Dong J, et al. A novel approach of lung segmentation on chest CT images using graph cuts. Neurocomputing, 2015, 168: 799-807.
8. Zhao J, Ji G, Han X, et al. An automated pulmonary parenchyma segmentation method based on an improved region growing algorithmin PET-CT imaging. Frontiers of Computer Science, 2016, 10(1): 189-200.
9. Wang J, Guo H. Automatic approach for lung segmentation with juxta-pleural nodules from thoracic CT based on contour tracing and correction. Computational and Mathematical Methods in Medicine, 2016, 2016: 2962047.
10. Zhou J, Yan Z, Lasio G, et al. Automated compromised right lung segmentation method using a robust atlas-based active volume model with sparse shape composition prior in CT. Computerized Medical Imaging and Graphics, 2015, 46: 47-55.
11. Chung H, Ko H, Jeon S J, et al. Automatic lung segmentation with juxta-pleural nodule identification using active contour model and Bayesian approach. IEEE Journal of Translational Engineering in Health and Medicine, 2018, 6: 1800513.
12. 肖汉光, 冉智强, 黄金锋, 等. 基于电子计算机断层扫描图像的肺实质分割方法研究进展. 生物医学工程学杂志, 2021, 38(2): 379-386.
13. Khan A, Garner R, Rocca M L, et al. A novel threshold-based segmentation method for quantification of COVID-19 lung abnormalities. Signal Image Video Process, 2023, 17(4): 907-914.
14. Chakraborty S, Mali K. A morphology-based radiological image segmentation approach for efficient screening of COVID-19. Biomedical Signal Processing and Control, 2021, 69: 102800.
15. Akbari Y, Hassen H, Al-Maadeed S, et al. COVID-19 lesion segmentation using lung CT scan images: comparative study based on active contour models. Applied Sciences, 2021, 11(17): 8039.
16. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation//MICCAI 2015: 18th International Conference, Munich: Springer, 2015: 234-241.
17. Zhao Xiangyu, Zhang Peng, Song Fan, et al. D2A U-Net: automatic segmentation of covid-19 lesions from CT slices with dilated convolution and dual attention mechanism. 2021. arXiv:2102.05210.
18. Joseph Raj A N, Zhu H, Khan A, et al. ADID-UNET−a segmentation model for COVID-19 infection from lung CT scans. PeerJ Computer Science, 2021, 7: e349.
19. Wang G, Liu X, Li C, et al. A noise-robust framework for automatic segmentation of COVID-19 pneumonia lesions from CT images. IEEE Transactions on Medical Imaging, 2020, 39(8): 2653-2663.
20. Zhou T, Canu S, Ruan S. Automatic COVID-19 CT segmentation using U-Net integrated spatial and channel attention mechanism. International Journal of Imaging Systems and Technology, 2021, 31(1): 16-27.
21. Xiao H, Ran Z, Mabu S, et al. SAUNet++: an automatic segmentation model of COVID-19 lesion from CT slices. The Visual Computer, 2022. DOI: 10.1007/s00371-022-02414-4.
22. Zhou Z, Siddiquee M M R, 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.
23. Luo Xiangde, Chen Jieneng, Song Tao, et al. Semi-supervised medical image segmentation through dual-task consistency. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2021), 2021, 35(10): 8801-8809.
24. Abraham N, Khan N M. A novel focal Tversky loss function with improved attention U-Net for lesion segmentation//2019 IEEE International Symposium on Biomedical Imaging(ISBI), Venice: IEEE, 2019: 683-687.
25. Sudre C H, Li W, Vercauteren T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations// Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2017), Québec: Springer, 2017: 240-248.
26. Ma J, Wang Y, An X, et al. Towards efficient COVID-19 CT annotation: a benchmark for lung and infection segmentation. 2020. arXiv:2004.12537.
27. Morozov S P, Andreychenko A E, Pavlov N A, et al. Mosmeddata: chest CT scans with COVID-19 related findings dataset. 2020. arXiv:2005.06465.
28. Fan D P, Zhou T, Ji G P, et al. Inf-Net: automatic COVID-19 lung infection segmentation from CT images. IEEE Transactions on Medical Imaging, 2020. 39(8): 2626-2637.
29. Jin Q, Meng Z, Sun C, et al. RA-UNet: A hybrid deep attention-aware network to extract liver and tumor in CT scans. Frontiers in Bioengineering and Biotechnology, 2020, 8: 605132.
30. Qiu Y, Liu Y, Li S, et al. MiniSeg: an extremely minimum network for efficient COVID-19 segmentation//35th AAAI Conference on Artificial Intelligence 2021. DOI: 10.1609/aaai.v35i6.16617.

Journal of Biomedical Engineering

Corona virus disease 2019 lesion segmentation network based on an adaptive joint loss function

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content