A survey of loss function of medical image segmentation algorithms_Journal of Biomedical Engineering

Authors：

CHEN Ying ¹ ,  ZHANG Wei ¹ , LIN Hongping ¹ , ZHENG Cheng ¹ , ZHOU Taohui ¹ , FENG Longfeng ¹ , YI Zhen ² , LIU Lan ²

1. School of Software, Nanchang Hangkong University , Nanchang 330063, P. R. China;
2. Department of Medical Imaging, Jiangxi Cancer Hospital, Nanchang 330029, P. R. China;

Corresponding author：

ZHANG Wei, Email: 1150786225@qq.com

Keywords：

Medical image segmentation; Loss function; Deep learning; Sample imbalance

DOI：

10.7507/1001-5515.202206038

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Medical image segmentation based on deep learning has become a powerful tool in the field of medical image processing. Due to the special nature of medical images, image segmentation algorithms based on deep learning face problems such as sample imbalance, edge blur, false positive, false negative, etc. In view of these problems, researchers mostly improve the network structure, but rarely improve from the unstructured aspect. The loss function is an important part of the segmentation method based on deep learning. The improvement of the loss function can improve the segmentation effect of the network from the root, and the loss function is independent of the network structure, which can be used in various network models and segmentation tasks in plug and play. Starting from the difficulties in medical image segmentation, this paper first introduces the loss function and improvement strategies to solve the problems of sample imbalance, edge blur, false positive and false negative. Then the difficulties encountered in the improvement of the current loss function are analyzed. Finally, the future research directions are prospected. This paper provides a reference for the reasonable selection, improvement or innovation of loss function, and guides the direction for the follow-up research of loss function.

Citation： CHEN Ying, ZHANG Wei, LIN Hongping, ZHENG Cheng, ZHOU Taohui, FENG Longfeng, YI Zhen, LIU Lan. A survey of loss function of medical image segmentation algorithms. Journal of Biomedical Engineering, 2023, 40(2): 392-400. doi: 10.7507/1001-5515.202206038 Copy

1.	Hesamian M H, Jia W, He X, et al. Deep learning techniques for medical image segmentation: achievements and challenges. Journal of digital imaging, 2019, 32(4): 582-596.
2.	李肃义, 唐世杰, 李凤, 等. 基于深度学习的生物医学数据分析进展. 生物医学工程学杂志, 2020, 37(2): 349-357.
3.	储珺, 林文杰, 徐鹏. 目标检测中特征不匹配问题研究进展. 南昌航空大学学报: 自然科学版, 2021, 35(3): 1-8.
4.	Liu X, Song L, Liu S, et al. A review of deep-learning-based medical image segmentation methods. Sustainability, 2021, 13(3): 1224.
5.	陈英, 郑铖, 易珍, 等. 肝脏及肿瘤图像分割方法综述. 计算机应用研究, 2022, 39(3): 641-650.
6.	汪豪, 吉邦宁, 何刚, 等. 一种提高直肠癌诊断精度的基于U型网络和残差块的电子计算机断层扫描图像分割算法. 生物医学工程学杂志, 2022, 39(1): 166-174, 184.
7.	吴玉超, 林岚, 王婧璇, 等. 基于卷积神经网络的语义分割在医学图像中的应用. 生物医学工程学杂志, 2020, 37(3): 533-540.
8.	张欢, 仇大伟, 冯毅博, 等. U-Net模型改进及其在医学图像分割上的研究综述. 激光与光电子学进展, 2022, 59(2): 1-17.
9.	Wang Q, Ma Y, Zhao K, et al. A comprehensive survey of loss functions in machine learning. Annals of Data Science, 2022, 9(2): 187-212.
10.	Tarekegn A N, Giacobini M, Michalak K. A review of methods for imbalanced multi-label classification. Pattern Recognition, 2021, 118: 107965.
11.	Jadon S. A survey of loss functions for semantic segmentation//2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Via del Mar: IEEE, 2020: 1-7.
12.	Khushi M, Shaukat K, Alam T M, et al. A comparative performance analysis of data resampling methods on imbalance medical data. IEEE Access, 2021, 9: 109960-109975.
13.	何鑫. 医学不平衡样本集分类关键技术研究. 成都: 电子科技大学, 2020.
14.	Zhao R, Qian B, Zhang X, et al. Rethinking dice loss for medical image segmentation//2020 IEEE International Conference on Data Mining (ICDM), Sorrento: IEEE, 2020: 851-860.
15.	Hasanin T, Khoshgoftaar T M, Leevy J L, et al. Examining characteristics of predictive models with imbalanced big data. Journal of Big Data, 2019, 6(1): 1-21.
16.	Sugino T, Kawase T, Onogi S, et al. Loss weightings for improving imbalanced brain structure segmentation using fully convolutional networks//Healthcare, London: MDPI, 2021, 9(8): 938.
17.	Ma J, Chen J, Ng M, et al. Loss odyssey in medical image segmentation. Medical Image Analysis, 2021, 71: 102035.
18.	Ben Naceur M, Akil M, Saouli R, et al. Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy. Med Image Anal, 2020, 63: 101692.
19.	Bertels J, Eelbode T, Berman M, et al. Optimizing the dice score and Jaccard index for medical image segmentation: theory and practice//International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen: Springer, 2019: 92-100.
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), Stanford: IEEE, 2016: 565-571.
21.	Sudre C H, Li W, Vercauteren T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Canada: Springer, 2017, 2017: 240-248.
22.	Bertels J, Robben D, Vandermeulen D, et al. Optimization with soft dice can lead to a volumetric bias//International MICCAI Brainlesion, Shenzhen: Springer, 2019: 89-97.
23.	Zhou D, Fang J, Song X, et al. Iou loss for 2D/3D object detection//2019 International Conference on 3D Vision (3DV), Quebec City: IEEE, 2019: 85-94.
24.	Cai J, Lu L, Xie Y, et al. Improving deep pancreas segmentation in CT and MRI images via recurrent neural contextual learning and direct loss function. arXiv preprint, 2017, arXiv: 1707.04912.
25.	Su J, Liu Z, Zhang J, et al. DV-Net: accurate liver vessel segmentation via dense connection model with D-BCE loss function. Knowledge-Based Systems, 2021, 232: 107471.
26.	黄泳嘉, 史再峰, 王仲琦, 等. 基于混合损失函数的改进型U-Net肝部医学影像分割方法. 激光与光电子学进展, 2020, 57(22): 74-83.
27.	Wu Z, Shen C, Hengel A. Bridging category-level and instance-level semantic image segmentation. arXiv preprint, 2016, arXiv: 1605.06885.
28.	Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
29.	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, 2019: 683-687.
30.	Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks//International Workshop on Machine Learning in Medical Imaging, Quebec City: Springer, 2017: 379-387.
31.	Wang P, Chung A. Focal dice loss and image dilation for brain tumor segmentation//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Spain: Springer, 2018: 119-127.
32.	Zhu W, Huang Y, Zeng L, et al. AnatomyNet: deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy. Medical physics, 2019, 46(2): 576-589.
33.	Chen J, Wan Z, Zhang J, et al. Medical image segmentation and reconstruction of prostate tumor based on 3D AlexNet. Computer Methods and Programs in Biomedicine, 2021, 200: 105878.
34.	Hashemi S R, Salehi S S M, Erdogmus D, et al. Asymmetric similarity loss function to balance precision and recall in highly unbalanced deep medical image segmentation. arXiv preprint, 2018, arXiv: 1803.11078v3.
35.	Yang S, Kweon J, Kim Y H. Major vessel segmentation on x-ray coronary angiography using deep networks with a novel penalty loss function//International Conference on Medical Imaging with Deep Learning, London: PMLR, 2019: 1-5.
36.	Zhu C, Hu P, Zeng X, et al. Segmentation network with compound loss function for hydatidiform mole hydrops lesion recognition. arXiv preprint, 2022, arXiv: 2204.04956.
37.	曹玉红, 徐海, 刘荪傲, 等. 基于深度学习的医学影像分割研究综述. 计算机应用, 2021, 41(8): 2273-2287.
38.	Li X, Sui J, Wang Y. Three-dimensional reconstruction of fuzzy medical images using quantum algorithm. IEEE Access, 2020, 8: 218279-218288.
39.	Ooi A Z H, Embong Z, Abd Hamid A I, et al. Interactive blood vessel segmentation from retinal fundus image based on canny edge detector. Sensors, 2021, 21(19): 6380.
40.	Tian R, Sun G, Liu X, et al. Sobel edge detection based on weighted nuclear norm minimization image denoising. Electronics, 2021, 10(6): 655.
41.	Caliva F, Iriondo C, Martinez A M, et al. Distance map loss penalty term for semantic segmentation. arXiv preprint, 2019, arXiv: 1908.03679.
42.	Horn R A, Yang Z. Rank of a Hadamard product. Linear Algebra and Its Applications, 2020, 591: 87-98.
43.	Kim M, Lee B D. A simple generic method for effective boundary extraction in medical image segmentation. IEEE Access, 2021, 9: 103875-103884.

1. Hesamian M H, Jia W, He X, et al. Deep learning techniques for medical image segmentation: achievements and challenges. Journal of digital imaging, 2019, 32(4): 582-596.
2. 李肃义, 唐世杰, 李凤, 等. 基于深度学习的生物医学数据分析进展. 生物医学工程学杂志, 2020, 37(2): 349-357.
3. 储珺, 林文杰, 徐鹏. 目标检测中特征不匹配问题研究进展. 南昌航空大学学报: 自然科学版, 2021, 35(3): 1-8.
4. Liu X, Song L, Liu S, et al. A review of deep-learning-based medical image segmentation methods. Sustainability, 2021, 13(3): 1224.
5. 陈英, 郑铖, 易珍, 等. 肝脏及肿瘤图像分割方法综述. 计算机应用研究, 2022, 39(3): 641-650.
6. 汪豪, 吉邦宁, 何刚, 等. 一种提高直肠癌诊断精度的基于U型网络和残差块的电子计算机断层扫描图像分割算法. 生物医学工程学杂志, 2022, 39(1): 166-174, 184.
7. 吴玉超, 林岚, 王婧璇, 等. 基于卷积神经网络的语义分割在医学图像中的应用. 生物医学工程学杂志, 2020, 37(3): 533-540.
8. 张欢, 仇大伟, 冯毅博, 等. U-Net模型改进及其在医学图像分割上的研究综述. 激光与光电子学进展, 2022, 59(2): 1-17.
9. Wang Q, Ma Y, Zhao K, et al. A comprehensive survey of loss functions in machine learning. Annals of Data Science, 2022, 9(2): 187-212.
10. Tarekegn A N, Giacobini M, Michalak K. A review of methods for imbalanced multi-label classification. Pattern Recognition, 2021, 118: 107965.
11. Jadon S. A survey of loss functions for semantic segmentation//2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Via del Mar: IEEE, 2020: 1-7.
12. Khushi M, Shaukat K, Alam T M, et al. A comparative performance analysis of data resampling methods on imbalance medical data. IEEE Access, 2021, 9: 109960-109975.
13. 何鑫. 医学不平衡样本集分类关键技术研究. 成都: 电子科技大学, 2020.
14. Zhao R, Qian B, Zhang X, et al. Rethinking dice loss for medical image segmentation//2020 IEEE International Conference on Data Mining (ICDM), Sorrento: IEEE, 2020: 851-860.
15. Hasanin T, Khoshgoftaar T M, Leevy J L, et al. Examining characteristics of predictive models with imbalanced big data. Journal of Big Data, 2019, 6(1): 1-21.
16. Sugino T, Kawase T, Onogi S, et al. Loss weightings for improving imbalanced brain structure segmentation using fully convolutional networks//Healthcare, London: MDPI, 2021, 9(8): 938.
17. Ma J, Chen J, Ng M, et al. Loss odyssey in medical image segmentation. Medical Image Analysis, 2021, 71: 102035.
18. Ben Naceur M, Akil M, Saouli R, et al. Fully automatic brain tumor segmentation with deep learning-based selective attention using overlapping patches and multi-class weighted cross-entropy. Med Image Anal, 2020, 63: 101692.
19. Bertels J, Eelbode T, Berman M, et al. Optimizing the dice score and Jaccard index for medical image segmentation: theory and practice//International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen: Springer, 2019: 92-100.
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), Stanford: IEEE, 2016: 565-571.
21. Sudre C H, Li W, Vercauteren T, et al. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Canada: Springer, 2017, 2017: 240-248.
22. Bertels J, Robben D, Vandermeulen D, et al. Optimization with soft dice can lead to a volumetric bias//International MICCAI Brainlesion, Shenzhen: Springer, 2019: 89-97.
23. Zhou D, Fang J, Song X, et al. Iou loss for 2D/3D object detection//2019 International Conference on 3D Vision (3DV), Quebec City: IEEE, 2019: 85-94.
24. Cai J, Lu L, Xie Y, et al. Improving deep pancreas segmentation in CT and MRI images via recurrent neural contextual learning and direct loss function. arXiv preprint, 2017, arXiv: 1707.04912.
25. Su J, Liu Z, Zhang J, et al. DV-Net: accurate liver vessel segmentation via dense connection model with D-BCE loss function. Knowledge-Based Systems, 2021, 232: 107471.
26. 黄泳嘉, 史再峰, 王仲琦, 等. 基于混合损失函数的改进型U-Net肝部医学影像分割方法. 激光与光电子学进展, 2020, 57(22): 74-83.
27. Wu Z, Shen C, Hengel A. Bridging category-level and instance-level semantic image segmentation. arXiv preprint, 2016, arXiv: 1605.06885.
28. Lin T Y, Goyal P, Girshick R, et al. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2): 318-327.
29. 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, 2019: 683-687.
30. Salehi S S M, Erdogmus D, Gholipour A. Tversky loss function for image segmentation using 3D fully convolutional deep networks//International Workshop on Machine Learning in Medical Imaging, Quebec City: Springer, 2017: 379-387.
31. Wang P, Chung A. Focal dice loss and image dilation for brain tumor segmentation//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Spain: Springer, 2018: 119-127.
32. Zhu W, Huang Y, Zeng L, et al. AnatomyNet: deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy. Medical physics, 2019, 46(2): 576-589.
33. Chen J, Wan Z, Zhang J, et al. Medical image segmentation and reconstruction of prostate tumor based on 3D AlexNet. Computer Methods and Programs in Biomedicine, 2021, 200: 105878.
34. Hashemi S R, Salehi S S M, Erdogmus D, et al. Asymmetric similarity loss function to balance precision and recall in highly unbalanced deep medical image segmentation. arXiv preprint, 2018, arXiv: 1803.11078v3.
35. Yang S, Kweon J, Kim Y H. Major vessel segmentation on x-ray coronary angiography using deep networks with a novel penalty loss function//International Conference on Medical Imaging with Deep Learning, London: PMLR, 2019: 1-5.
36. Zhu C, Hu P, Zeng X, et al. Segmentation network with compound loss function for hydatidiform mole hydrops lesion recognition. arXiv preprint, 2022, arXiv: 2204.04956.
37. 曹玉红, 徐海, 刘荪傲, 等. 基于深度学习的医学影像分割研究综述. 计算机应用, 2021, 41(8): 2273-2287.
38. Li X, Sui J, Wang Y. Three-dimensional reconstruction of fuzzy medical images using quantum algorithm. IEEE Access, 2020, 8: 218279-218288.
39. Ooi A Z H, Embong Z, Abd Hamid A I, et al. Interactive blood vessel segmentation from retinal fundus image based on canny edge detector. Sensors, 2021, 21(19): 6380.
40. Tian R, Sun G, Liu X, et al. Sobel edge detection based on weighted nuclear norm minimization image denoising. Electronics, 2021, 10(6): 655.
41. Caliva F, Iriondo C, Martinez A M, et al. Distance map loss penalty term for semantic segmentation. arXiv preprint, 2019, arXiv: 1908.03679.
42. Horn R A, Yang Z. Rank of a Hadamard product. Linear Algebra and Its Applications, 2020, 591: 87-98.
43. Kim M, Lee B D. A simple generic method for effective boundary extraction in medical image segmentation. IEEE Access, 2021, 9: 103875-103884.

Previous Article
Research progress on the effect of iron oxide nanoparticles in macrophage polarization

Journal of Biomedical Engineering

A survey of loss function of medical image segmentation algorithms

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content