Domain and Task-Focused Example Selection for Data-Efficient Contrastive Medical Image Segmentation

2025-05-25

AI Summary

To address the high cost of pixel-level annotations and data scarcity in medical image segmentation, this paper proposes PolyCL: a contrastive learning framework operating without pixel-wise labels, leveraging cross-image semantic relationships to achieve efficient segmentation under low-shot (1% labeled data) and cross-domain settings. PolyCL introduces the first task-oriented, domain-aware contrastive learning paradigm and uniquely integrates SAM for mask refinement and SAM 2 for single-slice-guided 3D propagation—both without manual annotations or strong data augmentation. The framework synergistically combines self-supervised contrastive learning, context-aware feature transfer, and weakly supervised prompting. Evaluated on three public CT datasets, PolyCL achieves Dice score improvements of over 8% compared to full-supervision and state-of-the-art self-supervised methods, and enhances cross-domain generalization by 12%.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Unsupervised & Self-Supervised Learning
• Search and Optimization: Learning to Search

Application Category

• Security and Privacy: Data transparency and provenance
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Segmentation is one of the most important tasks in the medical imaging pipeline as it influences a number of image-based decisions. To be effective, fully supervised segmentation approaches require large amounts of manually annotated training data. However, the pixel-level annotation process is expensive, time-consuming, and error-prone, hindering progress and making it challenging to perform effective segmentations. Therefore, models must learn efficiently from limited labeled data. Self-supervised learning (SSL), particularly contrastive learning via pre-training on unlabeled data and fine-tuning on limited annotations, can facilitate such limited labeled image segmentation. To this end, we propose a novel self-supervised contrastive learning framework for medical image segmentation, leveraging inherent relationships of different images, dubbed PolyCL. Without requiring any pixel-level annotations or unreasonable data augmentations, our PolyCL learns and transfers context-aware discriminant features useful for segmentation from an innovative surrogate, in a task-related manner. Additionally, we integrate the Segment Anything Model (SAM) into our framework in two novel ways: as a post-processing refinement module that improves the accuracy of predicted masks using bounding box prompts derived from coarse outputs, and as a propagation mechanism via SAM 2 that generates volumetric segmentations from a single annotated 2D slice. Experimental evaluations on three public computed tomography (CT) datasets demonstrate that PolyCL outperforms fully-supervised and self-supervised baselines in both low-data and cross-domain scenarios. Our code is available at https://github.com/tbwa233/PolyCL.

Problem

• Efficient medical image segmentation with limited labeled data
• Self-supervised contrastive learning for domain-aware feature transfer
• Integrating SAM for mask refinement and volumetric segmentation

Innovation

• Self-supervised contrastive learning for segmentation
• Integrates SAM for mask refinement and propagation
• Learns context-aware features without pixel annotations