The NSF Convergence Accelerator supports use-inspired, team-based, multidisciplinary efforts that address challenges of national importance and will produce deliverables of value to society in the near future.This project will result in a new, use-inspired platform for collaborative AI model development that removes the hurdles of sharing sensitive medical imaging data. The new platform will accelerate the translation of AI models into clinics, while still more rigorously validating them on large, heterogeneous patient data. For patients and doctors, this innovative technology will help to improve the quality of healthcare by augmenting the cognitive capacity of clinicians with more accurate, trustworthy, and safe AI. For medical researchers, the new platform will considerably accelerate scientific discovery by removing the hurdles of extramural model training and validation. For industry, the newly developed open-source ImagiQ platform will serve as a convenient framework for developing FL solutions. Externally to medical imaging, the proposed concept is easily extensible to broader areas, where sharing sensitive data is the major bottleneck, such as connected vehicles, national security/defense, consumer electronics, etc., and will benefit the society with safer and more reliable AI.
Innovation in the medical imaging arena will be achieved by enabling collaborative model development and validation. To eliminate the current hurdle of direct patient data sharing, a novel decentralized, asynchronous federated learning (FL) scheme will be developed. In particular, the new concept of peer adaptive ensemble learning will be explored, in which the FL task is framed as a large collection of machine learning problems, each with a different and evolving model and data population. Peer-to-peer model sharing will eliminate the need for a centralized server that is difficult and costly to maintain. Asynchronous model updates will enable more nimble and agile model development. Decentralized blockchain ledgers will permit a secure and trustworthy exchange of AI models.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
