Three commercially available radiology artificial intelligence systems have shown the potential to flag early signs of breast cancer up to six years before a formal diagnosis, according to a study published in Radiology, the journal of the Radiological Society of North America.
In research conducted in Sweden and released on June 9, scientists tested three AI-based computer-assisted detection systems on mammogram data from a large screening population. The study found that cancer prediction scores issued by these AI-CAD systems were elevated for individuals who were eventually diagnosed with breast cancer, while scores remained low for those who did not develop the disease.
The research team led by Dr. Strand investigated whether AI could identify mammographic signs present up to ten years prior. The retrospective study included 88,963 mammograms performed on 31,394 patients over ten years. Data came from the Validation of Artificial Intelligence for Breast Imaging database, which collects imaging data from volunteers across four Swedish regions. In Sweden’s national screening program, women aged 40 to 74 are invited every two years for examinations traditionally read by two radiologists.
Dr. Strand's team applied three commercial AI-CAD systems to mammograms taken between January 2008 and April 2019. During this period, 12,072 participants—38.5 percent—were diagnosed with cancer by radiologist readers. The AI-CAD systems identified many cancers at earlier screenings: they achieved ninety percent specificity in distinguishing true positives and negatives up to nineteen point seven percent of individuals six years before their recorded diagnosis; twenty-five point two percent four years before; and thirty-nine point three percent two years prior.
AI-CAD scores may assist radiologists in spotting early mammographic signs linked with future cancers and support personalized approaches that could help identify patients needing closer monitoring.
"This study aims to add to the growing literature regarding the application of AI in breast cancer screening and how it can help play a role in earlier detection of breast cancer," said Dr. Strand. "Analyzing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention."
