CLMP: Cross Learning Multi-head Prediction Guided Source-Free Domain Adaptation for Medical Image Segmentation

Unsupervised Domain Adaptation is crucial for transferring segmentation models trained on the source domain to the target domain. However, in medical image segmentation, the unavailability of source domain data makes Source-Free Domain Adaptation (SFDA) an attractive alternative, allowing model adaptation without relying on source domain data. Current SFDA methods predominantly rely on pseudo-labels, yet obtaining high-quality pseudo-labels continues to pose significant challenges. In this paper, we propose a novel framework for medical image segmentation, termed Cross-Learning Multi-head Prediction-guided (CLMP) SFDA. This framework leverages consistency constraints within a multi-head prediction architecture to enhance pseudo-label accuracy. Specifically, we deploy a multi-head prediction model designed to generate robust pseudo-labels. To minimize discrepancies between the predictions of different heads, we propose a method called Pixel-Level Synergistic Consistency Loss (PSCL). Additionally, we implement dual forward propagation to counteract model degradation during self-supervised training and integrate Chebyshev uncertainty estimation to selectively filter out unreliable pseudo-labels. Moreover, we introduce a foreground-background statistical weighting module to tackle class imbalance effectively. Experiments conducted on two public medical image datasets demonstrate an average performance improvement of over 6% across all metrics compared to existing state-of-the-art methods, underscoring the effectiveness of the CLMP framework.