Equitable Federated Learning with NCA

TL;DR

This paper introduces FedNCA, a lightweight, encryption-ready federated learning system designed for medical image segmentation on low-resource devices, addressing infrastructural and security challenges in LMICs to promote equitable healthcare.

Contribution

FedNCA is a novel federated learning system optimized for low-resource environments, enabling secure, efficient medical image segmentation on edge devices like smartphones.

Findings

FedNCA enables training on low-cost edge devices.

It reduces communication costs significantly.

The system is encryption-ready for secure data transmission.

Abstract

Federated Learning (FL) is enabling collaborative model training across institutions without sharing sensitive patient data. This approach is particularly valuable in low- and middle-income countries (LMICs), where access to trained medical professionals is limited. However, FL adoption in LMICs faces significant barriers, including limited high-performance computing resources and unreliable internet connectivity. To address these challenges, we introduce FedNCA, a novel FL system tailored for medical image segmentation tasks. FedNCA leverages the lightweight Med-NCA architecture, enabling training on low-cost edge devices, such as widely available smartphones, while minimizing communication costs. Additionally, our encryption-ready FedNCA proves to be suitable for compromised network communication. By overcoming infrastructural and security challenges, FedNCA paves the way for inclusive, efficient, lightweight, and encryption-ready medical imaging solutions, fostering equitable healthcare advancements in resource-constrained regions.