通过频域扰动增强医学图像分割的泛化能力
Medical Image Segmentation via Single-Source Domain Generalization with Random Amplitude Spectrum Synthesis
- 从频域角度随机扰动图像幅度谱，模拟真实分布变化
- 在3D胎儿脑影像和2D眼底照片上实现优于现有单源DG模型的性能
- 适合数据稀缺且需跨域泛化的医学图像分割场景
医学图像分割面临域泛化（DG）挑战，主要源于临床数据集中的域偏移问题。该挑战因医学数据稀缺和隐私顾虑而加剧。传统单源域泛化（SSDG）方法多依赖堆叠数据增强技术以减小域间差异。本文提出随机幅度谱合成（RASS）作为医学图像的训练增强方法。RASS通过频率视角模拟分布变化，引入依赖幅度的扰动，确保对潜在域变化的广泛覆盖。此外，提出随机掩码洗牌与重建组件，提升骨干网络处理结构信息的能力，并增强对域内及跨域变化的鲁棒性。所提出的RAS^4DG在3D胎儿脑影像和2D眼底照片数据集上验证，相比其他SSDG模型展现出更优的域泛化分割性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。