Intra-Class Subdivision for Pixel Contrastive Learning: Application to Semi-supervised Cardiac Image Segmentation

TL;DR

This paper introduces a novel intra-class subdivision pixel contrastive learning framework for cardiac image segmentation, effectively improving boundary delineation and intra-class representation discrimination in semi-supervised settings.

Contribution

The paper proposes the concept of unconcerned samples and a boundary contrastive loss, advancing intra-class representation learning for improved segmentation accuracy.

Findings

Significant improvement in segmentation quality on public cardiac datasets.

Enhanced boundary precision compared to existing methods.

Theoretical analysis supports the effectiveness of the proposed components.

Abstract

We propose an intra-class subdivision pixel contrastive learning (SPCL) framework for cardiac image segmentation to address representation contamination at boundaries. The novel concept ``Unconcerned sample'' is proposed to distinguish pixel representations at the inner and boundary regions within the same class, facilitating a clearer characterization of intra-class variations. A novel boundary contrastive loss for boundary representations is proposed to enhance representation discrimination across boundaries. The advantages of the unconcerned sample and boundary contrastive loss are analyzed theoretically. Experimental results in public cardiac datasets demonstrate that SPCL significantly improves segmentation performance, outperforming existing methods with respect to segmentation quality and boundary precision. Our code is available at https://github.com/Jrstud203/SPCL.