SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation

2025-06-11

AI Summary

To address source-free domain adaptation (SFDA) in medical image segmentation—where source-domain data are unavailable and target-domain annotations are absent—this paper proposes a SAM-guided trustworthy pseudo-label learning framework. Our method introduces three key innovations: (1) the first SAM-based reliability assessment mechanism for pseudo-labels; (2) a joint filtering strategy combining Test-Time Tri-branch Intensity Enhancement (T3IE) and Consistency of Multiple SAM Outputs (CMSO) to enhance pseudo-label quality; and (3) reliability-aware entropy regularization during training. Evaluated on multi-center fetal brain and prostate segmentation benchmarks, our approach significantly outperforms existing SFDA methods and approaches the performance upper bound of full supervision on the target domain—achieving robust, source-constraint-free cross-center segmentation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Domain Adaptation (DA) is crucial for robust deployment of medical image segmentation models when applied to new clinical centers with significant domain shifts. Source-Free Domain Adaptation (SFDA) is appealing as it can deal with privacy concerns and access constraints on source-domain data during adaptation to target-domain data. However, SFDA faces challenges such as insufficient supervision in the target domain with unlabeled images. In this work, we propose a Segment Anything Model (SAM)-guided Reliable Pseudo-Labels method for SFDA (SRPL-SFDA) with three key components: 1) Test-Time Tri-branch Intensity Enhancement (T3IE) that not only improves quality of raw pseudo-labels in the target domain, but also leads to SAM-compatible inputs with three channels to better leverage SAM's zero-shot inference ability for refining the pseudo-labels; 2) A reliable pseudo-label selection module that rejects low-quality pseudo-labels based on Consistency of Multiple SAM Outputs (CMSO) under input perturbations with T3IE; and 3) A reliability-aware training procedure in the unlabeled target domain where reliable pseudo-labels are used for supervision and unreliable parts are regularized by entropy minimization. Experiments conducted on two multi-domain medical image segmentation datasets for fetal brain and the prostate respectively demonstrate that: 1) SRPL-SFDA effectively enhances pseudo-label quality in the unlabeled target domain, and improves SFDA performance by leveraging the reliability-aware training; 2) SRPL-SFDA outperformed state-of-the-art SFDA methods, and its performance is close to that of supervised training in the target domain. The code of this work is available online: https://github.com/HiLab-git/SRPL-SFDA.

Problem

• Improving pseudo-label quality in unlabeled target domains
• Leveraging SAM for reliable pseudo-label selection
• Enhancing SFDA performance in medical image segmentation

Innovation

• SAM-guided pseudo-labels for SFDA
• Test-Time Tri-branch Intensity Enhancement
• Reliable pseudo-label selection via CMSO