GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels

TL;DR

This paper introduces GCL, a contrastive learning method that unifies multi-perspective meta labels using gradient guidance to improve medical image segmentation with limited annotations.

Contribution

The paper proposes Gradient Mitigator and Gradient Filter techniques to address semantic contradictions and enhance discriminative representation learning in medical image segmentation.

Findings

Significantly improves segmentation accuracy with limited labels.

Demonstrates strong generalization on out-of-distribution datasets.

Effectively unifies multi-perspective meta labels for better semantic understanding.

Abstract

Since annotating medical images for segmentation tasks commonly incurs expensive costs, it is highly desirable to design an annotation-efficient method to alleviate the annotation burden. Recently, contrastive learning has exhibited a great potential in learning robust representations to boost downstream tasks with limited labels. In medical imaging scenarios, ready-made meta labels (i.e., specific attribute information of medical images) inherently reveal semantic relationships among images, which have been used to define positive pairs in previous work. However, the multi-perspective semantics revealed by various meta labels are usually incompatible and can incur intractable "semantic contradiction" when combining different meta labels. In this paper, we tackle the issue of "semantic contradiction" in a gradient-guided manner using our proposed Gradient Mitigator method, which systematically unifies multi-perspective meta labels to enable a pre-trained model to attain a better high-level semantic recognition ability. Moreover, we emphasize that the fine-grained discrimination ability is vital for segmentation-oriented pre-training, and develop a novel method called Gradient Filter to dynamically screen pixel pairs with the most discriminating power based on the magnitude of gradients. Comprehensive experiments on four medical image segmentation datasets verify that our new method GCL: (1) learns informative image representations and considerably boosts segmentation performance with limited labels, and (2) shows promising generalizability on out-of-distribution datasets.