Answers are grounded in this paper and cite their sources.
Meta-repository enables benchmarking of AI classifiers for breast cancer screening, highlighting model transparency and generalization.
We present a meta-repository that enables reproducible benchmarking of AI classifiers for breast cancer screening using mammography data. It includes 5 open-source models evaluated across 7 international datasets, addressing key challenges in model generalization and transparency. By providing a standardized evaluation framework and enabling cross-platform reproducibility, our work supports both research progress and clinical integration. The meta-repository is available https://www.github.com/nyukat/mammography_metarepository.
No takes yet. Share an insight, caveat, or question.
Chłędowski et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: