A coronary artery plaque segmentation method based on focal weighted accuracy loss function_Journal of Biomedical Engineering

Authors：

XIONG Fei ^1,4 ,  LU Haiming ² , LI Linfeng ³ , JIANG Rui ¹

1. Department of Automation, Tsinghua University, Beijing 100084, P. R. China;
2. Graduate School, Tsinghua University, Beijing 100084, P. R. China;
3. Yidu Cloud (Beijing) Technology Co., LTD, Beijing 100039, P. R. China;
4. Information Center, Kunming Railway Vocational and Technical College, Kunming 650208, P. R. China;

Corresponding?author：

LU Haiming, Email: luhm@tsinghua.edu.cn

Keywords：

Coronary artery plaque segmentation; Deep learning; Class imbalance; Loss function

DOI：

10.7507/1001-5515.202412024

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

[Abstract] Medical images of coronary artery plaque are always accompanied by the situation of extreme class imbalance. The traditional two-step methods locate the region of interest (ROI) in the sample firstly, and then segment the sample within the ROI. On the other hand, the traditional resampling methods use resampling strategies to increase the number of minority class samples to mitigate the effects of class imbalance. These two types of methods either make the network structure more complex or decrease training efficiency and performance of the model due to the increase of samples. This paper proposes a method including a novel focal weighted accuracy loss function and improved metrics evaluation algorithms to address the issues in the segmentation of coronary artery calcification plaque mentioned above. Experimental results on the selected dataset show the proposed method increased the training speed and improved the segmentation performance of the model without performing resampling on the dataset. Specifically, the F1-score was 0.873 5, the precision was 0.929 6, and the recall was 0.823 8. The F1-score was largely improved compared with the method using focal loss function. Furthermore, compared with methods with multiple models and methods via resampling the minority class samples, research results demonstrate that the proposed method improved the accuracy and efficiency in coronary artery plaque segmentation while has a shorter training time, which lays the foundation for improving the efficiency and scientific nature of diagnosing related diseases in the future.

1.	World Health Organization. Cardiovascular diseases (2021-06-11) [2025-09-02]. https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds).
2.	Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation//Medical Image Computing and Computer-Assisted Intervention (MICCAI-2015) . Munich: MICCAI, 2015: 234-241.
3.	Azad R, Aghdam E K, Rauland A, et al. Medical image segmentation review: the success of U-net. IEEE Trans Pattern Anal Mach Intell, 2024, 46(12): 10076-10095.
4.	Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. Unet++: a nested U-net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018, 11045: 3-11.
5.	?i?ek ?, Abdulkadir A, Lienkamp S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation//Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016). Athens: MICCAI, 2016: 424-436.
6.	Guo C, Szemenyei M, Yi Y, et al. SA-UNet: spatial attention u-net for retinal vessel segmentation//2020 25th International Conference on Pattern Recognition (ICPR). Milan: IAPR, 2021: 1236-1242.
7.	Chen J, Lu Y, Yu Q, et al. TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint, 2021, arXiv: 2102.04306.
8.	Moradi S, Oghli M G, Alizadehasl A, et al. MFP-UNet: a novel deep learning based approach for left ventricle segmentation in echocardiography. Physica Medica, 2019, 67: 58-69.
9.	Wang Z, Blaschko M B. MRF-UNets: searching UNet with Markov random fields//Machine Learning and Knowledge Discovery in Databases, Turin: ECML, 2023: 599-614.
10.	Le N, Le T, Yamazaki K, et al. Offset curves loss for imbalanced problem in medical segmentation//2020 25th International Conference on Pattern Recognition (ICPR), Milan: IAPR, 2021: 9189-9195.
11.	Nasalwai N, Punn N S, Sonbhadra S K, et al. Addressing the class imbalance problem in medical image segmentation via accelerated Tversky loss function//Advances in Knowledge Discovery and Data Mining, Virtual: PAKDD, 2021: 390-402.
12.	Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks//Machine Learning in Medical Imaging, Quebec: MLMI, 2017: 379-387.
13.	Basak H, Ghosal S, Sarkar R. Addressing class imbalance in semi-supervised image segmentation: a study on cardiac MRI//Medical Image Computing and Computer Assisted Intervention (MICCAI 2022), Singapore: MICCAI, 2022: 224-233.
14.	Mao A, Mohri M, Zhong Y. Cross-entropy loss functions: theoretical analysis and applications. arXiv preprint, 2023. arXiv: 2304.07288.
15.	Lin T Y, Goyal P, Girshick R B, et al. Focal loss for dense object detection//2017 IEEE International Conference on Computer Vision (ICCV), Venice: IEEE, 2017: 2999-3007.
16.	Abraham N, Khan N M. A novel focal Tversky loss function with improved attention U-net for lesion segmentation//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice: IEEE, 2018: 683-687.
17.	Wang P, Chung A C S. Focal Dice loss and image dilation for brain tumor segmentation//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA 2018), Granada: MICCAI, 2018: 119-127.
18.	Yeung M, Sala E, Sch?nlieb C B, et al. Unified focal loss: generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Computerized Medical Imaging and Graphics, 2022, 95: 102026.
19.	Stanford University Stanford AIMI. Coca-coronary calcium and chest CT’s (2021-07-31) [2025-09-02]. https://stanfordaimi.azurewebsites.net/datasets/e8ca74dc-8dd4-4340-815a-60b41f6cb2aa,2021-07-31/2024-08-05.
20.	Zhang Z, Liu Q, Wang Y. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753.
21.	Tversky A. Features of similarity. Psychological Review, 1977, 84(4): 327-352.
22.	Oktay O, Schlemper J, Folgoc L L, et al. Attention u-net: learning where to look for the pancreas. arXiv preprint, 2018, arXiv: 1804.03999.
23.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas: IEEE, 2015: 770-778.
24.	Kazemzadeh S, Singh M, Ashouri B, et al. Prediction of coronary artery disease via calcium scoring of chest CTs. Stanford University, (2022-01-24) [2025-09-02]. http://cs230.stanford.edu/projects_fall_2021/reports/103167584.pdf.

1. World Health Organization. Cardiovascular diseases (2021-06-11) [2025-09-02]. https://www.who.int/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds).
2. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation//Medical Image Computing and Computer-Assisted Intervention (MICCAI-2015) . Munich: MICCAI, 2015: 234-241.
3. Azad R, Aghdam E K, Rauland A, et al. Medical image segmentation review: the success of U-net. IEEE Trans Pattern Anal Mach Intell, 2024, 46(12): 10076-10095.
4. Zhou Z, Rahman Siddiquee M M, Tajbakhsh N, et al. Unet++: a nested U-net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 2018, 11045: 3-11.
5. ?i?ek ?, Abdulkadir A, Lienkamp S S, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation//Medical Image Computing and Computer-Assisted Intervention (MICCAI 2016). Athens: MICCAI, 2016: 424-436.
6. Guo C, Szemenyei M, Yi Y, et al. SA-UNet: spatial attention u-net for retinal vessel segmentation//2020 25th International Conference on Pattern Recognition (ICPR). Milan: IAPR, 2021: 1236-1242.
7. Chen J, Lu Y, Yu Q, et al. TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint, 2021, arXiv: 2102.04306.
8. Moradi S, Oghli M G, Alizadehasl A, et al. MFP-UNet: a novel deep learning based approach for left ventricle segmentation in echocardiography. Physica Medica, 2019, 67: 58-69.
9. Wang Z, Blaschko M B. MRF-UNets: searching UNet with Markov random fields//Machine Learning and Knowledge Discovery in Databases, Turin: ECML, 2023: 599-614.
10. Le N, Le T, Yamazaki K, et al. Offset curves loss for imbalanced problem in medical segmentation//2020 25th International Conference on Pattern Recognition (ICPR), Milan: IAPR, 2021: 9189-9195.
11. Nasalwai N, Punn N S, Sonbhadra S K, et al. Addressing the class imbalance problem in medical image segmentation via accelerated Tversky loss function//Advances in Knowledge Discovery and Data Mining, Virtual: PAKDD, 2021: 390-402.
12. Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks//Machine Learning in Medical Imaging, Quebec: MLMI, 2017: 379-387.
13. Basak H, Ghosal S, Sarkar R. Addressing class imbalance in semi-supervised image segmentation: a study on cardiac MRI//Medical Image Computing and Computer Assisted Intervention (MICCAI 2022), Singapore: MICCAI, 2022: 224-233.
14. Mao A, Mohri M, Zhong Y. Cross-entropy loss functions: theoretical analysis and applications. arXiv preprint, 2023. arXiv: 2304.07288.
15. Lin T Y, Goyal P, Girshick R B, et al. Focal loss for dense object detection//2017 IEEE International Conference on Computer Vision (ICCV), Venice: IEEE, 2017: 2999-3007.
16. Abraham N, Khan N M. A novel focal Tversky loss function with improved attention U-net for lesion segmentation//2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice: IEEE, 2018: 683-687.
17. Wang P, Chung A C S. Focal Dice loss and image dilation for brain tumor segmentation//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA 2018), Granada: MICCAI, 2018: 119-127.
18. Yeung M, Sala E, Sch?nlieb C B, et al. Unified focal loss: generalising Dice and cross entropy-based losses to handle class imbalanced medical image segmentation. Computerized Medical Imaging and Graphics, 2022, 95: 102026.
19. Stanford University Stanford AIMI. Coca-coronary calcium and chest CT’s (2021-07-31) [2025-09-02]. https://stanfordaimi.azurewebsites.net/datasets/e8ca74dc-8dd4-4340-815a-60b41f6cb2aa,2021-07-31/2024-08-05.
20. Zhang Z, Liu Q, Wang Y. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 2018, 15(5): 749-753.
21. Tversky A. Features of similarity. Psychological Review, 1977, 84(4): 327-352.
22. Oktay O, Schlemper J, Folgoc L L, et al. Attention u-net: learning where to look for the pancreas. arXiv preprint, 2018, arXiv: 1804.03999.
23. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas: IEEE, 2015: 770-778.
24. Kazemzadeh S, Singh M, Ashouri B, et al. Prediction of coronary artery disease via calcium scoring of chest CTs. Stanford University, (2022-01-24) [2025-09-02]. http://cs230.stanford.edu/projects_fall_2021/reports/103167584.pdf.

Journal of Biomedical Engineering

Latest ArticlesA coronary artery plaque segmentation method based on focal weighted accuracy loss function

Abstract Full text Figures/Tables Video References Cited by

Format

Content