AI-CAD for diagnostic mammography: comparison to radiologists according to different indications
European Radiology, 2026
Abstract
Introduction: Although artificial intelligence-based computer-aided diagnosis (AI-CAD) is increasingly applied in screening mammography, its use in diagnostic settings is less established.
Methods: This study evaluated the diagnostic performance of AI-CAD abnormality scores at optimized thresholds across various diagnostic indications vs radiologists.
Results: The findings demonstrated that AI-CAD can perform comparably to radiologists in diagnostic mammography settings, with optimized thresholding playing a key role in achieving high accuracy across different clinical indications.
Conclusion: AI-CAD shows promise as a supportive tool in diagnostic mammography, potentially aiding workflow efficiency and diagnostic confidence across diverse patient presentations.
DOI: Read full study
