Fu Hao, Zhang Jian, Chen Lanlan, Zou Junzhong
Department of Automation, School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China.
J Appl Clin Med Phys. 2025 Feb;26(2):e14602. doi: 10.1002/acm2.14602. Epub 2024 Dec 5.
The training of deep learning (DL) models in medical images requires large amounts of sensitive patient data. However, acquiring adequately labeled datasets is challenging because of the heavy workload of manual annotations and the stringent privacy protocols.
Federated learning (FL) provides an alternative approach in which a coalition of clients collaboratively trains models without exchanging the underlying datasets. In this study, a novel Personalized Federated Learning Framework (PAF-Fed) is presented for abdominal multi-organ segmentation. Different from traditional FL algorithms, PAF-Fed selectively gathers partial model parameters for inter-client collaboration, retaining the remaining parameters to learn local data distributions at individual sites. Additionally, the Fourier Transform with the Self-attention mechanism is employed to aggregate the low-frequency components of parameters, promoting the extraction of shared knowledge and tackling statistical heterogeneity from diverse client datasets.
The proposed method was evaluated on the Combined Healthy Abdominal Organ Segmentation magnetic resonance imaging (MRI) dataset (CHAOS 2019) and a private computed tomography (CT) dataset, achieving an average Dice Similarity Coefficient (DSC) of 72.65% for CHAOS and 85.50% for the private CT dataset, respectively.
The experimental results demonstrate the superiority of our PAF-Fed by outperforming state-of-the-art FL methods.
在医学图像中训练深度学习（DL）模型需要大量敏感的患者数据。然而，由于手动标注的工作量大以及严格的隐私协议，获取充分标注的数据集具有挑战性。
联邦学习（FL）提供了一种替代方法，即客户端联盟在不交换基础数据集的情况下协作训练模型。在本研究中，提出了一种用于腹部多器官分割的新型个性化联邦学习框架（PAF-Fed）。与传统的FL算法不同，PAF-Fed有选择地收集部分模型参数用于客户端间协作，保留其余参数以学习各个站点的局部数据分布。此外，采用带有自注意力机制的傅里叶变换来聚合参数的低频分量，促进共享知识的提取并解决来自不同客户端数据集的统计异质性问题。
该方法在联合健康腹部器官分割磁共振成像（MRI）数据集（CHAOS 2019）和一个私人计算机断层扫描（CT）数据集上进行了评估，在CHAOS数据集上平均骰子相似系数（DSC）达到72.65%，在私人CT数据集上达到85.50%。
实验结果表明，我们的PAF-Fed优于现有最先进的FL方法，具有优越性。
