Equitable Federated Learning with NCA
This addresses barriers to federated learning adoption in healthcare for resource-constrained regions, offering a practical solution for equitable medical imaging.
The paper tackles the problem of enabling federated learning for medical image segmentation in low- and middle-income countries by introducing FedNCA, a system that leverages lightweight architecture to train on low-cost devices and minimize communication costs, making it suitable for resource-constrained environments.
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.