Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gupta, Riya, Chowdhury, Alexander, Nalawade, Sahil
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908622942896128
author Gupta, Riya
Chowdhury, Alexander
Nalawade, Sahil
author_facet Gupta, Riya
Chowdhury, Alexander
Nalawade, Sahil
contents Federated Learning (FL) has emerged as a transformative paradigm in medical AI, enabling collaborative model training across institutions without direct data sharing. This study benchmarks three prominent FL frameworks NVIDIA FLARE, Flower, and Owkin Substra to evaluate their suitability for medical imaging applications in real-world settings. Using the PathMNIST dataset, we assess model performance, convergence efficiency, communication overhead, scalability, and developer experience. Results indicate that NVIDIA FLARE offers superior production scalability, Flower provides flexibility for prototyping and academic research, and Owkin Substra demonstrates exceptional privacy and compliance features. Each framework exhibits strengths optimized for distinct use cases, emphasizing their relevance to practical deployment in healthcare environments.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00037
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra
Gupta, Riya
Chowdhury, Alexander
Nalawade, Sahil
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
Federated Learning (FL) has emerged as a transformative paradigm in medical AI, enabling collaborative model training across institutions without direct data sharing. This study benchmarks three prominent FL frameworks NVIDIA FLARE, Flower, and Owkin Substra to evaluate their suitability for medical imaging applications in real-world settings. Using the PathMNIST dataset, we assess model performance, convergence efficiency, communication overhead, scalability, and developer experience. Results indicate that NVIDIA FLARE offers superior production scalability, Flower provides flexibility for prototyping and academic research, and Owkin Substra demonstrates exceptional privacy and compliance features. Each framework exhibits strengths optimized for distinct use cases, emphasizing their relevance to practical deployment in healthcare environments.
title Benchmarking Federated Learning Frameworks for Medical Imaging Deployment: A Comparative Study of NVIDIA FLARE, Flower, and Owkin Substra
topic Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2511.00037