AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workload without compromising cancer detection. We propose a closed-loop threshold-aware training strategy in which the dismissal threshold is recalculated during training and used to penalize cancer-positive images that approach the dismissal region. We evaluated the method on NLBS and RSNA using five controlled training configurations, with case-level assessment based on a one-sided 99\% Clopper--Pearson upper bound for cancer prevalence among dismissed cases. The proposed model achieved the highest c

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-09-21T06:21:59.299Z. This is not the publication date.