Education, Science, Technology, Innovation and Life
Open Access
Sign In
  1. Home
  2. Journals
  3. Journal of Image Processing Theory and Applications
  4. Vol 7, Issue 1, 2024

Pseudo Label Distribution Optimization for Medical Image Segmentation

Download as PDF

DOI: 10.23977/jipta.2024.070113 | Downloads: 3 | Views: 123

Author(s)

Yi Liu 1, Yongchang Hou 1, Xiaohu Zhang 1

Affiliation(s)

1 Nanjing Paiyisheng Electronic Technology Co., Ltd., Nanjing, China

Corresponding Author

Yi Liu

ABSTRACT

Medical image segmentation plays a crucial role in diagnosis and treatment planning, yet the scarcity of annotated medical image data poses a significant challenge. This paper highlights the importance of semi-supervised learning in addressing this scarcity within the field of medical image segmentation. Traditional semi-supervised medical image segmentation models often rely on pseudo-labeling of unlabeled data. However, current practices tend to directly adopt the highest-confidence predictions during the utilization of pseudo-labels, neglecting crucial distribution information inherent in these labels and leading to suboptimal utilization. In response to this limitation, we propose a novel training approach applied to medical image segmentation. Our method introduces constraints based on the similarity and dissimilarity of predicted classes during the pseudo-labeling process. This strategy enables the model to optimize the distribution of pseudo-labels, reducing bias and enhancing their utilization, thereby improving overall model performance. To validate our approach, we applied it to a widely used dataset for human organ segmentation. The results demonstrate a significant performance boost, surpassing current state-of-the-art methods. Our method not only addresses the scarcity of labeled medical image data but also showcases its potential for advancing the field of medical image segmentation.

KEYWORDS

Semi-supervised learning, Medical image segmentation, Pseudo-labeling, Distribution optimization

CITE THIS PAPER

Yi Liu, Yongchang Hou, Xiaohu Zhang, Pseudo Label Distribution Optimization for Medical Image Segmentation. Journal of Image Processing Theory and Applications (2024) Vol. 7: 110-116. DOI: http://dx.doi.org/10.23977/jipta.2024.070113.

REFERENCES

[1] Patil D D, Deore S G. Medical image segmentation: a review [J]. International Journal of Computer Science and Mobile Computing, 2013, 2(1): 22-27.
[2] Luo X, Chen J, Song T, et al. Semi-supervised medical image segmentation through dual-task consistency[C]// Proceedings of the AAAI conference on artificial intelligence. 2021, 35(10): 8801-8809.
[3] Arazo E, Ortego D, Albert P, et al. Pseudo-labeling and confirmation bias in deep semi-supervised learning[C]// 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 2020: 1-8.
[4] Zhang B, Wang Y, Hou W, et al. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling[J]. Advances in Neural Information Processing Systems, 2021, 34: 18408-18419.
[5] Cascante-Bonilla P, Tan F, Qi Y, et al. Curriculum labeling: Revisiting pseudo-labeling for semi-supervised learning[C]// Proceedings of the AAAI conference on artificial intelligence. 2021, 35(8): 6912-6920.
[6] Hu Z, Yang Z, Hu X, et al. Simple: Similar pseudo label exploitation for semi-supervised classification[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 15099-15108.
[7] Sohn K, Berthelot D, Carlini N, et al. Fixmatch: Simplifying semi-supervised learning with consistency and confidence [J]. Advances in neural information processing systems, 2020, 33: 596-608.
[8] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[9] Milletari F, Navab N, Ahmadi S A. V-net: Fully convolutional neural networks for volumetric medical image segmentation[C]//2016 fourth international conference on 3D vision (3DV). Ieee, 2016: 565-571.
[10] Yu L, Wang S, Li X, et al. Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation [C]// Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22. Springer International Publishing, 2019: 605-613.
[11] Luo X, Liao W, Chen J, et al. Efficient semi-supervised gross target volume of nasopharyngeal carcinoma segmentation via uncertainty rectified pyramid consistency[C]//Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part II 24. Springer International Publishing, 2021: 318-329.
[12] Chen X, Yuan Y, Zeng G, et al. Semi-supervised semantic segmentation with cross pseudo supervision[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 2613-2622.
[13] Wu Y, Wu Z, Wu Q, et al. Exploring smoothness and class-separation for semi-supervised medical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer Nature Switzerland, 2022: 34-43.
[14] Chen B, Jiang J, Wang X, et al. Debiased self-training for semi-supervised learning[J]. Advances in Neural Information Processing Systems, 2022, 35: 32424-32437. 
[15] Wang X, Wu Z, Lian L, et al. Debiased learning from naturally imbalanced pseudo-labels[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 14647-14657.

Subscription
E-Mail Alert
Most popular papers
Call for Special Issue
Publication Ethics & OA Statement
Plagiarism Policy
Contact Us
Downloads: 1768
Visits: 123490

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.