Federated Learning for Cross-Modality Medical Image Segmentation via Augmentation-Driven Generalization

TL;DR

This paper proposes a federated learning approach with augmentation strategies to improve cross-modality medical image segmentation, achieving high accuracy without sharing patient data across institutions.

Contribution

It introduces a novel augmentation-driven method for federated learning that enhances cross-modality generalization in medical image segmentation without requiring paired data.

Findings

GIN augmentation outperforms other methods in cross-modality scenarios

Pancreas segmentation Dice score increased from 0.073 to 0.437

Federated model achieves 93-98% of centralized accuracy

Abstract

Artificial intelligence has emerged as a transformative tool in medical image analysis, yet developing robust and generalizable segmentation models remains difficult due to fragmented, privacy-constrained imaging data siloed across institutions. While federated learning (FL) enables collaborative model training without centralizing data, cross-modality domain shifts pose a critical challenge, particularly when models trained on one modality fail to generalize to another. Many existing solutions require paired multimodal data per patient or rely on complex architectures, both of which are impractical in real clinical settings. In this work, we consider a realistic FL scenario where each client holds single-modality data (CT or MRI), and systematically investigate augmentation strategies for cross-modality generalization. Using abdominal organ segmentation and whole-heart segmentation as representative multi-class and binary segmentation benchmarks, we evaluate convolution-based spatial augmentation, frequency-domain manipulation, domain-specific normalization, and global intensity nonlinear (GIN) augmentation. Our results show that GIN consistently outperforms alternatives in both centralized and federated settings by simulating cross-modality appearance variations while preserving anatomical structure. For the pancreas, Dice score improved from 0.073 to 0.437, a 498% gain. Our federated approach achieves 93-98% of centralized training accuracy, demonstrating strong cross-modality generalization without compromising data privacy, pointing toward feasible federated AI deployment across diverse healthcare systems.