Multi-task Federated Learning for Heterogeneous Pancreas Segmentation

Abstract

Federated learning (FL) for medical image segmentation becomes more challenging in multi-task settings where clients might have different categories of labels represented in their data. For example, one client might have patient data with "healthy'' pancreases only while datasets from other clients may contain cases with pancreatic tumors. The vanilla federated averaging algorithm makes it possible to obtain more generalizable deep learning-based segmentation models representing the training data from multiple institutions without centralizing datasets. However, it might be sub-optimal for the aforementioned multi-task scenarios. In this paper, we investigate heterogeneous optimization methods that show improvements for the automated segmentation of pancreas and pancreatic tumors in abdominal CT images with FL settings.

arXiv commentAccepted by MICCAI DCL Workshop 2021

References in corpus (5)

• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Attention U-Net: Learning Where to Look for the Pancreas
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• Federated Multi-Task Learning
• Auto-FedAvg: Learnable Federated Averaging for Multi-Institutional Medical Image Segmentation