Reproduce “Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Sadam Hussain, Mansoor Ali, Daly Betzabeth Avendaño-Avalos, Jose Gerardo Tamez-Peña
The authors combine mammograms and radiology reports in a classifier for biopsy outcomes among patients with BI-RADS 4 and 5 findings. The system joins features from four mammogram views and the corresponding report. On a held-out test set, it reached 40.4% specificity at 90% sensitivity, versus 37.0% for text-only and 25.1% for image-only; clinical biopsy reduction was not measured.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.