News for Healthier Living

AI Model Combining Ultrasound and Digital Breast Tomosynthesis Improves Specificity in Breast Cancer Triage

A new artificial intelligence (AI) framework that combines ultrasound (US) with digital breast tomosynthesis (DBT) may improve breast-level risk classification by raising specificity while preserving sensitivity. In a retrospective study, researchers developed a parallel-branch deep learning model using paired US, digital mammography (DM), and DBT examinations and compared six single- and dual-modality configurations. The US-DBT model achieved the highest observed discrimination in both internal and pathology-confirmed validation cohorts. Its main added value was fewer false-positive classifications, supporting its potential use as an adjunctive tool for refining positive imaging findings, prioritizing further diagnostic evaluation, and reducing unnecessary work-up in breast cancer assessment. The findings suggest a practical route to more selective imaging triage.

September 24, 2026


October 2 2026

October 1 2026

September 30 2026

September 29 2026

September 28 2026

September 27 2026

September 25 2026

September 24 2026

September 23 2026

September 22 2026

September 21 2026