Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis
This addresses domain shifts in medical imaging for clinical applications, but it is incremental as it builds on existing single-source domain generalization methods.
The paper tackled the problem of domain generalization in medical image segmentation by proposing Random Amplitude Spectrum Synthesis (RASS) as a training augmentation, achieving improved segmentation performance on 3D fetal brain and 2D fundus images compared to other single-source domain generalization models.
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.