AI-Supported Mammography Improves Breast Cancer Detection in Sweden

A world-first randomized controlled trial, the MASAI trial, involving over 100,000 Swedish women, has found that AI-supported mammography identifies more cancers during screening and reduces the rate of breast cancer diagnosis by 12% in the years following. Led by Dr. Kristina Lång from Lund University, the study, published in The Lancet, also showed a 44% reduction in screen-reading workload for radiologists and a 29% increase in cancer detection without an increase in false positives. The AI system, Transpara, developed by ScreenPoint Medical, triaged low-risk cases to single reading and high-risk cases to double reading, also highlighting suspicious findings. This breakthrough suggests that AI can significantly improve early detection of clinically relevant breast cancers, leading to fewer aggressive or advanced cancers diagnosed between screenings. While the study was conducted in Sweden with specific equipment and experienced radiologists, it provides strong evidence for the cautious, widespread rollout of AI in breast cancer screening programs to ease workload pressures and enhance early detection.