Reducing Clinician Annotation Fatigue in Open-Set Federated Learning: A Client-Adaptive Vision-Language Gatekeeper.
PURPOSE Federated learning enables breast-imaging sites to jointly train mammography artificial intelligence (AI) without sharing images, but radiologists at each site must still annotate selected images during active-learning rounds. We developed and evaluated a client-adaptive vision-language gatekeeper that withhold...
Adea Nesturi, D. Gaviria, Jia-Jun Zeng et al.
· Journal of the American Coll... · 0 citations