News Research Diagnostics & Imaging Decision-Making Support Breast Cancer

Noninferiority Randomized Trial of AI-Augmented Mammography Reading in Breast Cancer Screening

February 05, 2026 By ASCO AI Staff 4 min read
Share Share via Email Share on Facebook Share on LinkedIn Share on Twitter

5 Key Takeaways

  • 1

    The MASAI trial demonstrated that AI-supported mammography readings resulted in fewer interval breast cancer diagnoses compared to standard double readings.

  • 2

    AI-supported screening improved early detection of clinically relevant breast cancers, leading to fewer aggressive cancers diagnosed between screenings.

  • 3

    The trial included 105,934 women, with the intervention group showing a lower interval cancer rate of 1.55 per 1,000 participants.

  • 4

    Sensitivity was significantly higher in the AI-supported group at 80.5%, while specificity remained unchanged at 98.5% for both groups.

  • 5

    AI support reduced radiologists' workload by 44%, allowing them to focus on other clinical tasks and potentially shorten patient waiting times.

ASCO AI in Oncology is published by Conexiant under a license arrangement with the American Society of Clinical Oncology, Inc. (ASCO®). The ideas and opinions expressed in ASCO AI in Oncology do not necessarily reflect those of Conexiant or ASCO. For more information, see Policies.

KOL Commentary
Watch

Related Content