Breastcancer.orgAI-Supported Mammogram Reading Detects 20% More Cancers

Using artificial intelligence to help read mammograms found more cancers than the standard double reading by two radiologists.

In a significant advancement for breast cancer screening, a Swedish study published in The Lancet Oncology reveals that artificial intelligence (AI)-supported mammogram reading outperforms traditional methods, detecting 20% more cancers without increasing false positives. This groundbreaking research underscores the potential of AI as a complementary tool to radiologists’ expertise, promising to reshape early cancer detection practices. By integrating AI into mammography, healthcare professionals can achieve a more accurate, efficient, and potentially life-saving screening process.

Key Points:

• AI-assisted mammography identified 20% more cancers compared to the standard practice of double reading by radiologists, without raising the rate of false positives.
• The study, known as the MASAI trial, involved 80,020 Swedish women aged 40 to 80, comparing AI-supported screen reading against traditional methods.
• 244 cancers were detected in the AI group versus 203 in the control group, showcasing the technology’s enhanced detection capabilities.
• AI technology was trained with millions of mammograms to distinguish between normal and cancerous images, offering a “second set of eyes” to radiologists.
• Despite the promising results, limitations include the study’s single-center nature, reliance on one type of mammography machine and AI system, and lack of diversity data on participants.
• The false positive rate stood at 1.5% for both groups, indicating that AI use did not lead to an increase in unnecessary follow-up tests.
• Future research is needed to explore AI’s impact on patient outcomes, particularly in detecting interval cancers that are missed between regular screenings.
• The study calls for further trials and evaluations to address the radiologist shortage and assess AI’s cost-effectiveness and applicability across different populations.

“These promising interim safety results should be used to inform new trials and program-based evaluations to address the pronounced radiologist shortage in many countries. But they are not enough on their own to confirm that AI is ready to be implemented in mammography screening. We still need to understand the implications on patients’ outcomes, especially whether combining radiologists’ expertise with AI can help detect interval cancers that are often missed by traditional screening, as well as the cost-effectiveness of the technology.”
– Lead Author Kristina Lång, PhD, Associate Professor of Radiology Diagnostics at Lund University

More on Breast Cancer