{"id":123603,"date":"2021-11-29T14:00:11","date_gmt":"2021-11-29T14:00:11","guid":{"rendered":"https:\/\/blogs.nvidia.com\/?p=54259"},"modified":"2021-11-29T14:00:11","modified_gmt":"2021-11-29T14:00:11","slug":"federated-learning-with-flare-nvidia-brings-collaborative-ai-to-healthcare-and-beyond-2","status":"publish","type":"post","link":"https:\/\/webdomino.net\/index.php\/nvidia\/federated-learning-with-flare-nvidia-brings-collaborative-ai-to-healthcare-and-beyond-2\/","title":{"rendered":"Federated Learning With FLARE: NVIDIA Brings Collaborative AI to Healthcare and Beyond"},"content":{"rendered":"

NVIDIA is making it easier than ever for researchers to harness federated learning<\/a> by open-sourcing NVIDIA FLARE<\/a>, a software development kit that helps distributed parties collaborate to develop more generalizable AI models.<\/p>\n

Federated learning is a privacy-preserving technique that\u2019s particularly beneficial in cases where data is sparse, confidential or lacks diversity. But it\u2019s also useful for large datasets, which can be biased by an organization\u2019s data collection methods, or by patient or customer demographics.<\/p>\n

NVIDIA FLARE \u2014 short for Federated Learning Application Runtime Environment \u2014 is the engine underlying NVIDIA Clara Train\u2019s federated learning<\/a> software, which has been used for AI applications in medical imaging, genetic analysis, oncology and COVID-19 research. The SDK allows researchers and data scientists to adapt their existing machine learning and deep learning workflows to a distributed paradigm.<\/p>\n

Making NVIDIA FLARE open source will better empower cutting-edge AI in almost any industry by giving researchers and platform developers more tools to customize their federated learning solutions.<\/p>\n

With the SDK, researchers can choose among different federated learning architectures, tailoring their approach for domain-specific applications. And platform developers can use NVIDIA FLARE to provide customers with the distributed infrastructure required to build a multi-party collaboration application.<\/p>\n

Flexible Federated Learning Architectures for Multiple Industries\u00a0<\/b><\/h2>\n

Federated learning participants work together to train or evaluate AI models without having to pool or exchange each group\u2019s proprietary datasets. NVIDIA FLARE provides different distributed architectures that accomplish this, including peer-to-peer, cyclic and server-client approaches, among others.<\/p>\n

Using the server-client technique, where learned model parameters from each participant are sent to a common server and aggregated into a global model, NVIDIA has led federated learning projects that help segment pancreatic tumors<\/a>, classify breast density in mammograms<\/a> to inform breast cancer risk, and predict oxygen needs for COVID patients<\/a>.<\/p>\n

The server-client architecture was also used for two federated learning collaborations using NVIDIA FLARE: NVIDIA worked with Roche Digital Pathology researchers to run a successful internal simulation using whole slide images for classification, and with Netherlands-based \u00a0Erasmus Medical Center<\/a> for an AI application that identifies genetic variants<\/a> associated with schizophrenia cases.<\/p>\n

But not every federated learning application is suited to the server-client approach. By supporting additional architectures, NVIDIA FLARE will make federated learning accessible to a wider range of applications. Potential use cases include helping energy companies analyze seismic and wellbore data, manufacturers optimize factory operations and financial firms improve fraud detection models.<\/p>\n

NVIDIA FLARE Integrates With Healthcare AI Platforms<\/b><\/h2>\n

NVIDIA FLARE can integrate with existing AI initiatives, including the open-source MONAI framework<\/a> for medical imaging.<\/p>\n

\u201cOpen-sourcing NVIDIA FLARE to accelerate federated learning research is especially important in the healthcare sector, where access to multi-institutional datasets is crucial, yet concerns around patient privacy can limit the ability to share data,\u201d said Dr. Jayashree Kalapathy, associate professor of radiology at Harvard Medical School and leader of the MONAI <\/a>community\u2019s federated learning working group. \u201cWe are excited to contribute to NVIDIA FLARE and continue the integration with MONAI to push the frontiers of medical imaging research.\u201d<\/p>\n

NVIDIA FLARE will also be used to power federated learning solutions at:\u00a0<\/b><\/p>\n