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

TL;DR

This paper introduces AIF-SFDA, a novel method for source-free domain adaptation in medical image segmentation that uses a learnable frequency-based information filter to effectively decouple domain-specific and invariant features without access to source data.

Contribution

It proposes an autonomous, frequency-based learnable information filter combined with IB and SS to improve domain adaptation in medical imaging without source data.

Findings

Outperforms existing methods in various medical segmentation tasks.

Effectively decouples domain-variant and invariant features.

Demonstrates robustness across different modalities and tasks.

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.