Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the MASAI study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial | Synapse
March 3, 2026
Interval cancer, sensitivity, and specificity comparing AI-supported mammography screening with standard double reading without AI in the MASAI study: a randomised, controlled, non-inferiority, single-blinded, population-based, screening-accuracy trial
Key Points
Interval cancer detection rates improved with AI-supported mammography screening, enhancing specificity.
AI integration showed a sensitivity increase of 15%, suggesting potential in early detection.
Randomized controlled trial assessed screening accuracy across diverse populations using AI-supported methods.
This approach may enable greater efficiency in screening, but requires external validation beyond current findings.