Fen Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Fen Luo has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Chengyun Song
College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication Hengyang Liu
Collage of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication- Pengcheng Ren
Collage of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication Yang Yuan
Collage of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
1 shared publication
Latest Publications
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 433-442
Uncertainty Global Contrastive Learning Framework for Semi-Supervised Medical Image Segmentation
In semi-supervised medical image segmentation, the issue of fuzzy boundaries for segmented objects arises. With limited labeled data and the interaction of boundaries from different segmented objects, classifying segmentation boundaries becomes challenging. To mitigate this issue, we propose an uncertainty global contrastive learning (UGCL) framework. Specifically, we propose a patch filtering method and a classification entropy filtering method to provide reliable pseudo-labels for unlabelled data, while separating fuzzy boundaries and high-entropy pixel points as unreliable points. Considering that unreliable regions contain rich complementary information, we introduce an uncertainty global contrast learning method to distinguish these challenging unreliable regions, enhancing intra-class compactness and inter-class separability at the global data level. Within our optimization framework, we also integrate consistency regularization techniques and select unreliable points as targets for consistency. As demonstrated, the contrastive learning and consistency regularization applied to uncertain points enable us to glean valuable semantic information from unreliable data, which enhances segmentation accuracy. We evaluate our method on two publicly available medical image datasets and compare it with other state-of-the-art semi-supervised medical image segmentation methods, and a series of experimental results show that our method has achieved substantial improvements.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (1) , 433-442
Uncertainty Global Contrastive Learning Framework for Semi-Supervised Medical Image Segmentation
In semi-supervised medical image segmentation, the issue of fuzzy boundaries for segmented objects arises. With limited labeled data and the interaction of boundaries from different segmented objects, classifying segmentation boundaries becomes challenging. To mitigate this issue, we propose an uncertainty global contrastive learning (UGCL) framework. Specifically, we propose a patch filtering method and a classification entropy filtering method to provide reliable pseudo-labels for unlabelled data, while separating fuzzy boundaries and high-entropy pixel points as unreliable points. Considering that unreliable regions contain rich complementary information, we introduce an uncertainty global contrast learning method to distinguish these challenging unreliable regions, enhancing intra-class compactness and inter-class separability at the global data level. Within our optimization framework, we also integrate consistency regularization techniques and select unreliable points as targets for consistency. As demonstrated, the contrastive learning and consistency regularization applied to uncertain points enable us to glean valuable semantic information from unreliable data, which enhances segmentation accuracy. We evaluate our method on two publicly available medical image datasets and compare it with other state-of-the-art semi-supervised medical image segmentation methods, and a series of experimental results show that our method has achieved substantial improvements.