GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation

Mengzhu Wang, Houcheng Su, Jiao Li, Chuan Li, Nan Yin, Li Shen, Jingcai Guo
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:64367-64376, 2025.

Abstract

Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus on complex training strategies to utilize unlabeled data but neglect the importance of graph structural information. Different from existing methods, we propose a graph-based clustering for semi-supervised medical image segmentation (GraphCL) by jointly modeling graph data structure in a unified deep model. The proposed GraphCL model enjoys several advantages. Firstly, to the best of our knowledge, this is the first work to model the data structure information for semi-supervised medical image segmentation (SSMIS). Secondly, to get the clustered features across different graphs, we integrate both pairwise affinities between local image features and raw features as inputs. Extensive experimental results on three standard benchmarks show that the proposed GraphCL algorithm outperforms state-of-the-art semi-supervised medical image segmentation methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25cq, title = {{G}raph{CL}: Graph-based Clustering for Semi-Supervised Medical Image Segmentation}, author = {Wang, Mengzhu and Su, Houcheng and Li, Jiao and Li, Chuan and Yin, Nan and Shen, Li and Guo, Jingcai}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {64367--64376}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25cq/wang25cq.pdf}, url = {https://proceedings.mlr.press/v267/wang25cq.html}, abstract = {Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus on complex training strategies to utilize unlabeled data but neglect the importance of graph structural information. Different from existing methods, we propose a graph-based clustering for semi-supervised medical image segmentation (GraphCL) by jointly modeling graph data structure in a unified deep model. The proposed GraphCL model enjoys several advantages. Firstly, to the best of our knowledge, this is the first work to model the data structure information for semi-supervised medical image segmentation (SSMIS). Secondly, to get the clustered features across different graphs, we integrate both pairwise affinities between local image features and raw features as inputs. Extensive experimental results on three standard benchmarks show that the proposed GraphCL algorithm outperforms state-of-the-art semi-supervised medical image segmentation methods.} }
Endnote
%0 Conference Paper %T GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation %A Mengzhu Wang %A Houcheng Su %A Jiao Li %A Chuan Li %A Nan Yin %A Li Shen %A Jingcai Guo %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25cq %I PMLR %P 64367--64376 %U https://proceedings.mlr.press/v267/wang25cq.html %V 267 %X Semi-supervised learning (SSL) has made notable advancements in medical image segmentation (MIS), particularly in scenarios with limited labeled data and significantly enhancing data utilization efficiency. Previous methods primarily focus on complex training strategies to utilize unlabeled data but neglect the importance of graph structural information. Different from existing methods, we propose a graph-based clustering for semi-supervised medical image segmentation (GraphCL) by jointly modeling graph data structure in a unified deep model. The proposed GraphCL model enjoys several advantages. Firstly, to the best of our knowledge, this is the first work to model the data structure information for semi-supervised medical image segmentation (SSMIS). Secondly, to get the clustered features across different graphs, we integrate both pairwise affinities between local image features and raw features as inputs. Extensive experimental results on three standard benchmarks show that the proposed GraphCL algorithm outperforms state-of-the-art semi-supervised medical image segmentation methods.
APA
Wang, M., Su, H., Li, J., Li, C., Yin, N., Shen, L. & Guo, J.. (2025). GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:64367-64376 Available from https://proceedings.mlr.press/v267/wang25cq.html.

Related Material