Background Matters: A Cross-view Bidirectional Modeling Framework for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces a novel semi-supervised medical image segmentation framework that explicitly models background regions to improve foreground segmentation, achieving state-of-the-art results with less labeled data.

Contribution

The study proposes the Cross-view Bidirectional Modeling (CVBM) framework that incorporates background modeling and bidirectional consistency to enhance semi-supervised segmentation performance.

Findings

Achieves state-of-the-art results on multiple datasets.

Outperforms fully supervised methods with only 20% labeled data.

Demonstrates the benefit of explicit background modeling in segmentation.

Abstract

Semi-supervised medical image segmentation (SSMIS) leverages unlabeled data to reduce reliance on manually annotated images. However, current SOTA approaches predominantly focus on foreground-oriented modeling (i.e., segmenting only the foreground region) and have largely overlooked the potential benefits of explicitly modeling the background region. Our study theoretically and empirically demonstrates that highly certain predictions in background modeling enhance the confidence of corresponding foreground modeling. Building on this insight, we propose the Cross-view Bidirectional Modeling (CVBM) framework, which introduces a novel perspective by incorporating background modeling to improve foreground modeling performance. Within CVBM, background modeling serves as an auxiliary perspective, providing complementary supervisory signals to enhance the confidence of the foreground model. Additionally, CVBM introduces an innovative bidirectional consistency mechanism, which ensures mutual alignment between foreground predictions and background-guided predictions. Extensive experiments demonstrate that our approach achieves SOTA performance on the LA, Pancreas, ACDC, and HRF datasets. Notably, on the Pancreas dataset, CVBM outperforms fully supervised methods (i.e., DSC: 84.57% vs. 83.89%) while utilizing only 20% of the labeled data. Our code is publicly available at https://github.com/caoluyang0830/CVBM.git.