Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis

TL;DR

This paper introduces RASS, a novel data augmentation technique based on amplitude spectrum synthesis, to improve medical image segmentation models' ability to generalize across different domains from a single source.

Contribution

The paper proposes RASS, a frequency-based augmentation method, along with mask shuffle and reconstruction, to enhance single-source domain generalization in medical imaging.

Findings

RASS improves segmentation performance on fetal brain images.

RASS enhances robustness to domain shifts in fundus photography.

The method outperforms existing SSDG approaches.

Abstract

The field of medical image segmentation is challenged by domain generalization (DG) due to domain shifts in clinical datasets. The DG challenge is exacerbated by the scarcity of medical data and privacy concerns. Traditional single-source domain generalization (SSDG) methods primarily rely on stacking data augmentation techniques to minimize domain discrepancies. In this paper, we propose Random Amplitude Spectrum Synthesis (RASS) as a training augmentation for medical images. RASS enhances model generalization by simulating distribution changes from a frequency perspective. This strategy introduces variability by applying amplitude-dependent perturbations to ensure broad coverage of potential domain variations. Furthermore, we propose random mask shuffle and reconstruction components, which can enhance the ability of the backbone to process structural information and increase resilience intra- and cross-domain changes. The proposed Random Amplitude Spectrum Synthesis for Single-Source Domain Generalization (RAS^4DG) is validated on 3D fetal brain images and 2D fundus photography, and achieves an improved DG segmentation performance compared to other SSDG models.