BCMDA: Bidirectional Correlation Maps Domain Adaptation for Mixed Domain Semi-Supervised Medical Image Segmentation

2026-03-25

AI Summary

This work addresses the challenges of knowledge transfer and confirmation bias in semi-supervised medical image segmentation under mixed-domain settings, where domain shift and scarce annotations hinder performance. To tackle these issues, we propose a bidirectional correspondence graph-based domain adaptation framework that constructs a virtual intermediate domain via bidirectional correspondence graphs to serve as a cross-domain bridge. The approach integrates dynamic MixUp and dual CutMix augmentation strategies and introduces a learnable prototype classifier to enable bidirectional prototype alignment and pseudo-label refinement. Extensive experiments on three public multi-domain datasets demonstrate that the proposed method significantly outperforms state-of-the-art approaches, achieving robust segmentation performance even with extremely limited labeled data.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Segmentation
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health

Abstract

In mixed domain semi-supervised medical image segmentation (MiDSS), achieving superior performance under domain shift and limited annotations is challenging. This scenario presents two primary issues: (1) distributional differences between labeled and unlabeled data hinder effective knowledge transfer, and (2) inefficient learning from unlabeled data causes severe confirmation bias. In this paper, we propose the bidirectional correlation maps domain adaptation (BCMDA) framework to overcome these issues. On the one hand, we employ knowledge transfer via virtual domain bridging (KTVDB) to facilitate cross-domain learning. First, to construct a distribution-aligned virtual domain, we leverage bidirectional correlation maps between labeled and unlabeled data to synthesize both labeled and unlabeled images, which are then mixed with the original images to generate virtual images using two strategies, a fixed ratio and a progressive dynamic MixUp. Next, dual bidirectional CutMix is used to enable initial knowledge transfer within the fixed virtual domain and gradual knowledge transfer from the dynamically transitioning labeled domain to the real unlabeled domains. On the other hand, to alleviate confirmation bias, we adopt prototypical alignment and pseudo label correction (PAPLC), which utilizes learnable prototype cosine similarity classifiers for bidirectional prototype alignment between the virtual and real domains, yielding smoother and more compact feature representations. Finally, we use prototypical pseudo label correction to generate more reliable pseudo labels. Empirical evaluations on three public multi-domain datasets demonstrate the superiority of our method, particularly showing excellent performance even with very limited labeled samples. Code available at https://github.com/pascalcpp/BCMDA.

Problem

• domain shift
• semi-supervised segmentation
• confirmation bias
• mixed domain
• medical image segmentation

Innovation

• Bidirectional Correlation Maps
• Virtual Domain Bridging
• Dual Bidirectional CutMix
• Prototypical Alignment
• Pseudo Label Correction