Equitable Federated Learning with NCA

2025/06/26 by Nick Lemke, Lemke, Nick, Mirko Konstantin +9
Medicine · Computer Science · #COVID-19 diagnosis using AI #Privacy-Preserving Technologies in Data #Advanced Neural Network Applications

paper · pdf · doi:10.48550/arxiv.2506.21735

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.

Citations

• Unsupervised Training of Neural Cellular Automata on Edge Devices
• FedFMS: Exploring Federated Foundation Models for Medical Image Segmentation
• FedSZ: Leveraging Error-Bounded Lossy Compression for Federated Learning Communications
• Communication-Efficient Federated Learning over Capacity-Limited Wireless Networks
• Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey
• FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System
• Med-NCA: Robust and Lightweight Segmentation with Neural Cellular Automata
• Preserving Privacy and Security in Federated Learning
• Intrinisic Gradient Compression for Federated Learning
• FedCV: A Federated Learning Framework for Diverse Computer Vision Tasks
• Federated Learning for Smart Healthcare: A Survey
• Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devices
• Source Inference Attacks in Federated Learning
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Inverting Gradients -- How easy is it to break privacy in federated learning?
• Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach
• U-Net: Convolutional Networks for Biomedical Image Segmentation

Related

• Federated learning in low-resource settings: A chest imaging study in Africa -- Challenges and lessons learned
• FedFMS: Exploring Federated Foundation Models for Medical Image Segmentation
• Federated nnU-Net for Privacy-Preserving Medical Image Segmentation
• Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edge
• Federated Learning for Smart Healthcare: A Survey