AIF-SFDA: Autonomous Information Filter-driven Source-Free Domain Adaptation for Medical Image Segmentation

2025-01-06

AI Summary

To address source-free domain adaptation (SFDA) in medical image segmentation—where source-domain data are unavailable due to privacy or acquisition constraints—this paper proposes a single-stage, source-free adaptation method. To overcome the challenge of disentangling domain-specific information (DVI) and domain-invariant information (DII) under strict data limitations, we introduce a novel joint optimization framework integrating learnable frequency-domain filters, an information bottleneck constraint, and a self-supervised reconstruction task, enabling semantic-consistent feature disentanglement solely from unlabeled target-domain data. Our approach builds upon a U-Net architecture to construct a source-free domain adaptation framework that simultaneously ensures modality adaptability and structural fidelity. Extensive experiments across multi-modal (MRI, CT, ultrasound) and multi-organ segmentation tasks demonstrate consistent superiority over state-of-the-art SFDA methods, achieving average Dice score improvements of 3.2–5.8%. Crucially, the method requires neither source-domain data nor annotations.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Segmentation
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Data transparency and provenance

Abstract

Decoupling domain-variant information (DVI) from domain-invariant information (DII) serves as a prominent strategy for mitigating domain shifts in the practical implementation of deep learning algorithms. However, in medical settings, concerns surrounding data collection and privacy often restrict access to both training and test data, hindering the empirical decoupling of information by existing methods. To tackle this issue, we propose an Autonomous Information Filter-driven Source-free Domain Adaptation (AIF-SFDA) algorithm, which leverages a frequency-based learnable information filter to autonomously decouple DVI and DII. Information Bottleneck (IB) and Self-supervision (SS) are incorporated to optimize the learnable frequency filter. The IB governs the information flow within the filter to diminish redundant DVI, while SS preserves DII in alignment with the specific task and image modality. Thus, the autonomous information filter can overcome domain shifts relying solely on target data. A series of experiments covering various medical image modalities and segmentation tasks were conducted to demonstrate the benefits of AIF-SFDA through comparisons with leading algorithms and ablation studies. The code is available at https://github.com/JingHuaMan/AIF-SFDA.

Problem

• Medical Image Analysis
• Privacy Constraints
• Variable and Invariable Information Separation

Innovation

• AIF-SFDA
• Information Bottleneck
• Self-Supervised Learning