Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation

TL;DR

This paper demonstrates the feasibility of using federated learning for multi-institutional brain tumor segmentation, achieving performance comparable to centralized models without sharing patient data.

Contribution

It introduces federated learning to medical image segmentation, enabling collaborative training across institutions while preserving data privacy.

Findings

Federated models achieved Dice=0.852, close to centralized models with Dice=0.862.

Federated learning outperformed other collaborative methods in segmentation accuracy.

The approach addresses legal and privacy challenges in multi-institutional medical data sharing.

Abstract

Deep learning models for semantic segmentation of images require large amounts of data. In the medical imaging domain, acquiring sufficient data is a significant challenge. Labeling medical image data requires expert knowledge. Collaboration between institutions could address this challenge, but sharing medical data to a centralized location faces various legal, privacy, technical, and data-ownership challenges, especially among international institutions. In this study, we introduce the first use of federated learning for multi-institutional collaboration, enabling deep learning modeling without sharing patient data. Our quantitative results demonstrate that the performance of federated semantic segmentation models (Dice=0.852) on multimodal brain scans is similar to that of models trained by sharing data (Dice=0.862). We compare federated learning with two alternative collaborative learning methods and find that they fail to match the performance of federated learning.