Papers › Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

1 Jan 2023CVPR 2023 1archive 2025-07-28

Hritam Basak, Zhaozheng Yin

Although recent works in semi-supervised learning (SemiSL) have accomplished significant success in natural image segmentation, the task of learning discriminative representations from limited annotations has been an open problem in medical images. Contrastive Learning (CL) frameworks use the notion of similarity measure which is useful for classification problems, however, they fail to transfer these quality representations for accurate pixel-level segmentation. To this end, we propose a novel semi-supervised patch-based CL framework for medical image segmentation without using any explicit pretext task. We harness the power of both CL and SemiSL, where the pseudo-labels generated from SemiSL aid CL by providing additional guidance, whereas discriminative class information learned in CL leads to accurate multi-class segmentation. Additionally, we formulate a novel loss that synergistically encourages inter-class separability and intra-class compactness among the learned representations. A new inter-patch semantic disparity mapping using average patch entropy is employed for a guided sampling of positives and negatives in the proposed CL framework. Experimental analysis on three publicly available datasets of multiple modalities reveals the superiority of our proposed method as compared to the state-of-the-art methods. Code is available at: https://github.com/hritam-98/PatchCL-MedSeg.

PaperPDFCode

Code

HiLab-git/SSL4MIS officialmentioned in paperpytorch report
hritam-98/patchcl-medseg officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Colorectal Gland Segmentation:Contrastive LearningImage SegmentationMedical Image SegmentationPseudo LabelSegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationSemi-supervised Medical Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Colorectal Gland Segmentation: CRAG PatchCL Dice 0.892 #1 of 15 Archive leaderboard report
Colorectal Gland Segmentation: CRAG PatchCL F1-score 0.881 #1 of 15 Archive leaderboard report
Colorectal Gland Segmentation: CRAG PatchCL Hausdorff Distance (mm) 119.5 #1 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation KiTS19 PatchCL Avg DSC 0.919 #1 of 1 Archive leaderboard report
Semi-supervised Medical Image Segmentation ACDC 10% labeled data PatchCL Dice (Average) 89.10 #4 of 5 Archive leaderboard report
Semi-supervised Medical Image Segmentation ACDC 20% labeled data PatchCL Dice (Average) 91.20 #1 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive Learningfail

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections