FeTTL: Federated Template and Task Learning for Multi-Institutional Medical Imaging

2026-01-22

AI Summary

This work addresses the performance degradation in federated learning caused by distributional heterogeneity across medical imaging datasets from multiple institutions, which arises from differences in acquisition protocols, imaging devices, and patient populations. To mitigate this domain shift while preserving data privacy, the authors propose a federated framework that jointly learns a task-specific model and a learnable global template. This is the first approach to introduce such a trainable global template into federated learning, enabling cross-institutional distribution alignment through co-optimization with the task model. Evaluated on retinal fundus optic disc segmentation and histopathological metastasis classification tasks, the method significantly outperforms existing federated learning approaches (p < 0.002), demonstrating its effectiveness and robustness.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance. Medical imaging applications are particularly affected by variations in acquisition protocols, scanner types, and patient populations. To address these issues, we introduce Federated Template and Task Learning (FeTTL), a novel framework designed to harmonize multi-institutional medical imaging data in federated environments. FeTTL learns a global template together with a task model to align data distributions among clients. We evaluated FeTTL on two challenging and diverse multi-institutional medical imaging tasks: retinal fundus optical disc segmentation and histopathological metastasis classification. Experimental results show that FeTTL significantly outperforms the state-of-the-art federated learning baselines (p-values<0.002) for optical disc segmentation and classification of metastases from multi-institutional data. Our experiments further highlight the importance of jointly learning the template and the task. These findings suggest that FeTTL offers a principled and extensible solution for mitigating distribution shifts in federated learning, supporting robust model deployment in real-world, multi-institutional environments.

Problem

• federated learning
• domain shift
• medical imaging
• data heterogeneity
• multi-institutional

Innovation

• federated learning
• domain shift
• medical imaging
• template learning
• multi-institutional collaboration