首个胰腺分部分割联邦学习方法，保护隐私同时提升诊断精度。
Pancreas Part Segmentation under Federated Learning Paradigm
- 通过联邦学习在7家机构间协作训练，不共享原始数据
- 采用注意力U-Net+FedAvg组合，在711例T1W/726例T2W MRI上实现精准分部
- 设计解剖引导损失函数，增强对胰头尾纹理差异的识别
我们提出首个用于磁共振成像（MRI）胰腺分部（头、体、尾）分割的联邦学习（FL）方法，解决临床关键挑战。胰腺疾病具有显著区域异质性：癌症多发于胰头，慢性胰腺炎导致胰尾组织萎缩，因此准确分割胰腺三部分对精确诊断与治疗规划至关重要。该任务在MRI中极具挑战，因形态变异大、软组织对比度差且患者间解剖差异明显。本研究创新性地应对两大难题：一是胰腺分部分割的技术复杂性，二是数据稀缺问题。我们构建了一个隐私保护的联邦学习框架，实现七家医疗机构间的协同模型训练，使用涵盖711例T1W和726例T2W MRI的多样化数据集。核心贡献包括：（1）首次系统评估三种主流分割架构（U-Net、Attention U-Net、Swin UNETR）与两种联邦算法（FedAvg、FedProx）的组合，发现Attention U-Net配合FedAvg在应对胰腺异质性方面表现最优；（2）提出一种解剖学导向的损失函数，强化MRI中各区域特有的纹理对比。全面评估表明，该方法在分布式、异构数据上仍达到临床可用性能。
原文摘要 · Abstract (English)
We present the first federated learning (FL) approach for pancreas part(head, body and tail) segmentation in MRI, addressing a critical clinical challenge as a significant innovation. Pancreatic diseases exhibit marked regional heterogeneity cancers predominantly occur in the head region while chronic pancreatitis causes tissue loss in the tail, making accurate segmentation of the organ into head, body, and tail regions essential for precise diagnosis and treatment planning. This segmentation task remains exceptionally challenging in MRI due to variable morphology, poor soft-tissue contrast, and anatomical variations across patients. Our novel contribution tackles two fundamental challenges: first, the technical complexity of pancreas part delineation in MRI, and second the data scarcity problem that has hindered prior approaches. We introduce a privacy-preserving FL framework that enables collaborative model training across seven medical institutions without direct data sharing, leveraging a diverse dataset of 711 T1W and 726 T2W MRI scans. Our key innovations include: (1) a systematic evaluation of three state-of-the-art segmentation architectures (U-Net, Attention U-Net,Swin UNETR) paired with two FL algorithms (FedAvg, FedProx), revealing Attention U-Net with FedAvg as optimal for pancreatic heterogeneity, which was never been done before; (2) a novel anatomically-informed loss function prioritizing region-specific texture contrasts in MRI. Comprehensive evaluation demonstrates that our approach achieves clinically viable performance despite training on distributed, heterogeneous datasets.
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。