Federated attention contrastive learning models for prostate cancer diagnosis and Gleason grading

arXiv:2302.06089v4 Announce Type: replace-cross
Abstract: Artificial intelligence (AI) shows great promise in revolutionizing medical imaging, improving diagnosis, and refining treatment methods. However, the training of AI models relies on extensive multi-center datasets, presenting a potential challenge due to concerns about data privacy protection. Federated learning offers a solution by enabling a collaborative model across multiple centers without sharing raw data. In this study, we present a Federated Attention Contrastive Learning (FACL) framework designed to address challenges associated with large-scale pathological …

abstract ai models artificial artificial intelligence arxiv attention cancer cancer diagnosis center challenge concerns cs.cv cs.lg data data privacy datasets diagnosis federated learning imaging intelligence medical medical imaging presenting privacy protection q-bio.qm shows solution training treatment type