Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation
Abstract Magnetic resonance image (MRI) is the primary diagnostic test used clinically for the diagnosis and assessment of a wide range of diseases. In recent years, many studies have employed artificial intelligence techniques for MRI segmentation. Deep learning methods have demonstrated potential...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-03-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-025-00786-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850265491402129408 |
|---|---|
| author | Liangqing Hu Zuqiang Meng Chaohong Tan Yumin Zhou |
| author_facet | Liangqing Hu Zuqiang Meng Chaohong Tan Yumin Zhou |
| author_sort | Liangqing Hu |
| collection | DOAJ |
| description | Abstract Magnetic resonance image (MRI) is the primary diagnostic test used clinically for the diagnosis and assessment of a wide range of diseases. In recent years, many studies have employed artificial intelligence techniques for MRI segmentation. Deep learning methods have demonstrated potential to enhance segmentation performance. However, they still face two challenges: annotation scarcity and domain shift. The annotation of MRI is both challenging and costly, and well-annotated datasets are scarce and valuable. Moreover, due to variations in MRI machines, ensuring the independence and identical distribution between model training data and real-world data is difficult, which may lead to noisy model predictions and weak generalization ability. We aim to address the challenges through a multi-pronged approach. First, we propose a method that integrates confidence and uncertainty for generating reliable pseudo-labels. Second, we introduce a consistency learning method that employs self-perturbation at both the image and feature levels to encourage the learning of more generalized feature representations. Finally, we optimize pseudo-labels end-to-end with the teacher–student framework. To evaluate the effectiveness of our method, we conduct experiments on six different MRI segmentation datasets. The results showed that our method was superior to the existing methods in DSC, ASD and HD95 metrics. In addition, we evaluated the quality and quantity of the generated pseudo-labels, and the results showed that our method generated better pseudo-labels than other methods. Overall, our proposed method shows promising potential in assisting clinicians in practical applications. |
| format | Article |
| id | doaj-art-87b42e14f73b4ccdaae34489b9de69a0 |
| institution | OA Journals |
| issn | 1875-6883 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Springer |
| record_format | Article |
| series | International Journal of Computational Intelligence Systems |
| spelling | doaj-art-87b42e14f73b4ccdaae34489b9de69a02025-08-20T01:54:25ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-03-0118113010.1007/s44196-025-00786-8Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image SegmentationLiangqing Hu0Zuqiang Meng1Chaohong Tan2Yumin Zhou3School of Computer Science and Engineering, South China University of TechnologySchool of Computer Science and Engineering, South China University of TechnologyGuangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information CenterDepartment of Ultrasound Medicine, Guangxi Nanning Eighth People’s HospitalAbstract Magnetic resonance image (MRI) is the primary diagnostic test used clinically for the diagnosis and assessment of a wide range of diseases. In recent years, many studies have employed artificial intelligence techniques for MRI segmentation. Deep learning methods have demonstrated potential to enhance segmentation performance. However, they still face two challenges: annotation scarcity and domain shift. The annotation of MRI is both challenging and costly, and well-annotated datasets are scarce and valuable. Moreover, due to variations in MRI machines, ensuring the independence and identical distribution between model training data and real-world data is difficult, which may lead to noisy model predictions and weak generalization ability. We aim to address the challenges through a multi-pronged approach. First, we propose a method that integrates confidence and uncertainty for generating reliable pseudo-labels. Second, we introduce a consistency learning method that employs self-perturbation at both the image and feature levels to encourage the learning of more generalized feature representations. Finally, we optimize pseudo-labels end-to-end with the teacher–student framework. To evaluate the effectiveness of our method, we conduct experiments on six different MRI segmentation datasets. The results showed that our method was superior to the existing methods in DSC, ASD and HD95 metrics. In addition, we evaluated the quality and quantity of the generated pseudo-labels, and the results showed that our method generated better pseudo-labels than other methods. Overall, our proposed method shows promising potential in assisting clinicians in practical applications.https://doi.org/10.1007/s44196-025-00786-8Semi-supervised learningDomain generalizationMedical image segmentationPseudo-labels |
| spellingShingle | Liangqing Hu Zuqiang Meng Chaohong Tan Yumin Zhou Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation International Journal of Computational Intelligence Systems Semi-supervised learning Domain generalization Medical image segmentation Pseudo-labels |
| title | Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation |
| title_full | Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation |
| title_fullStr | Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation |
| title_full_unstemmed | Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation |
| title_short | Better Pseudo-Labeling for Semi-Supervised Domain Generalization in Medical Magnetic Resonance Image Segmentation |
| title_sort | better pseudo labeling for semi supervised domain generalization in medical magnetic resonance image segmentation |
| topic | Semi-supervised learning Domain generalization Medical image segmentation Pseudo-labels |
| url | https://doi.org/10.1007/s44196-025-00786-8 |
| work_keys_str_mv | AT liangqinghu betterpseudolabelingforsemisuperviseddomaingeneralizationinmedicalmagneticresonanceimagesegmentation AT zuqiangmeng betterpseudolabelingforsemisuperviseddomaingeneralizationinmedicalmagneticresonanceimagesegmentation AT chaohongtan betterpseudolabelingforsemisuperviseddomaingeneralizationinmedicalmagneticresonanceimagesegmentation AT yuminzhou betterpseudolabelingforsemisuperviseddomaingeneralizationinmedicalmagneticresonanceimagesegmentation |