Fair Evaluation of Federated Learning Algorithms for Automated Breast Density Classification: The Results of the 2022 ACR-NCI-NVIDIA Federated Learning Challenge

arXiv:2405.14900v1 Announce Type: cross
Abstract: The correct interpretation of breast density is important in the assessment of breast cancer risk. AI has been shown capable of accurately predicting breast density, however, due to the differences in imaging characteristics across mammography systems, models built using data from one system do not generalize well to other systems. Though federated learning (FL) has emerged as a way to improve the generalizability of AI without the need to share data, the best way to …

abstract acr algorithms arxiv assessment automated cancer challenge classification cs.cv cs.lg differences eess.iv evaluation fair federated learning however imaging interpretation mammography nvidia results risk type