Federated learning adapts model depth for medical image segmentation
Fed-ADApt: Federated Anytime Depth Adaptation for Resource-Aware Medical Image Segmentation
Computer Vision and Pattern Recognition
Summary
Medical image analysis often requires powerful computers, limiting some hospitals from joining shared training efforts that keep patient data private. The authors present a method where different hospitals can train parts of a model to fit their computing power while still contributing to a global model. This model adjusts its complexity when making predictions, balancing accuracy and speed depending on the device. Their tests on eye and brain images show this approach keeps good accuracy while allowing less powerful sites to join in and reducing computing costs.
What this means in practice
- •For hospital data teams: Enable hospitals with limited computing resources to train and deploy medical image segmentation models collaboratively without sharing patient data.
- •For medical device engineers: Design resource-aware imaging devices that dynamically adjust model complexity during inference to balance accuracy and speed.
Authors
Abhijeet Parida, Zhifan Jiang, Pooneh Roshanitabrizi, Austin Tapp, Maria J. Ledesma-Carbayo, Syed Muhammad Anwar, Ziyue Xu, Marius George Linguraru, Holger R. Roth
Abstract
Federated learning (FL) enables collaborative training of medical image segmentation models without sharing raw patient data, yet existing approaches assume a homogeneous compute budget across institutions, limiting participation of low-resource sites. We propose Fed-ADApt, a depth-adaptive federated framework for UNet-based segmentation that jointly addresses low-compute training and inference. Fed-ADApt integrates multi-depth supervision with hierarchical depth-wise aggregation, allowing each site to train according to its local compute budget while contributing to a global model that supports dynamic depth selection at deployment. We evaluated Fed-ADApt on multi-site 2D retinal fundus disc segmentation and 3D brain tumor segmentation. Across both tasks, federated collaboration substantially improves robustness under domain shift. Fed-ADApt matched the full-resource FedAvg performance in 3D and achieved competitive 2D performance with a 4.7% average Dice reduction, while reducing average inference cost by 19.5% in 3D and 34.5% in 2D and substantially reducing training cost by 98% at the most constrained sites. Importantly, Fed-ADApt enables low-resource institutions that cannot train full-capacity models to participate in federations while maintaining competitive global performance under a favorable accuracy to efficiency trade-off. By considering training and inference compute budgets, Fed-ADApt provides a practical and equitable solution for federated medical image segmentation across heterogeneous clinical and edge-enabled imaging environments.