RaffeSDG: Random Frequency Filtering enabled Single-source Domain Generalization for Medical Image Segmentation

TL;DR

RaffeSDG introduces a novel frequency-based data augmentation and structural saliency approach to enable single-source domain generalization in medical image segmentation, improving out-of-domain inference in data-scarce scenarios.

Contribution

The paper proposes RaffeSDG, a new method combining frequency filtering and structural saliency to enhance domain generalization from a single source in medical imaging.

Findings

Effective out-of-domain segmentation across multiple tissues and modalities.

Significant improvement over baseline models in domain shift scenarios.

Demonstrated robustness and generalizability of the proposed method.

Abstract

Deep learning models often encounter challenges in making accurate inferences when there are domain shifts between the source and target data. This issue is particularly pronounced in clinical settings due to the scarcity of annotated data resulting from the professional and private nature of medical data. Although various cross-domain strategies have been explored, including frequency-based approaches that vary appearance while preserving semantics, many remain limited by data constraints and computational cost. To tackle domain shifts in data-scarce medical scenarios, we propose a Random frequency filtering enabled Single-source Domain Generalization algorithm (RaffeSDG), which promises robust out-of-domain inference with segmentation models trained on a single-source domain. A frequency filter-based data augmentation strategy is first proposed to promote domain variability within a single-source domain by introducing variations in frequency space and blending homologous samples. Then Gaussian filter-based structural saliency is also leveraged to learn robust representations across augmented samples, further facilitating the training of generalizable segmentation models. To validate the effectiveness of RaffeSDG, we conducted extensive experiments involving out-of-domain inference on segmentation tasks for three human tissues imaged by four diverse modalities. Through thorough investigations and comparisons, compelling evidence was observed in these experiments, demonstrating the potential and generalizability of RaffeSDG. The code is available at https://github.com/liamheng/Non-IID_Medical_Image_Segmentation.