There are multiple commercially available, artificial intelligence-enabled systems capable of accurately predicting whether a woman will go on to have breast cancer.
Using routine mammograms, the systems can determine which women will develop the disease within a six-year window. A new paper in Radiology, the flagship journal of RSNA, details the performance of three systems on a large breast cancer screening cohort. The paper further emphasizes the utility of AI in breast cancer screening.
“Approximately 20% of breast cancer cases demonstrate mammographic signs that are already visible to AI around six years before diagnosis,” explained senior co-author Fredrik Strand, MD, PhD, of Karolinska University Hospital in Stockholm. “Our study confirms the potential of AI to, in some cases, find signs of cancer in the mammograms much earlier than when radiologists detected it.”
For the study, researchers retrospectively analyzed over 88,000 screening mammograms completed between 2008 and 2019. The AI systems assigned a score predicting the likelihood a woman would develop cancer within 10 years, with higher scores indicating greater risk. Using patients’ health records for the 10 years after the exams, the team compared the systems’ predictive performance against patients’ eventual diagnoses.
Across the cohort of over 31,000 women who had multiple exams to analyze, 38.5% were diagnosed with cancer by radiologists. The AI systems identified most cancers at earlier time points than radiologists, with 90% specificity. Nearly 20% would have been diagnosed six years earlier, while 25% would have been caught four earlier and 39% two years prior.
These findings go beyond AI’s ability to detect cancer in earlier stages, the group suggested, noting that AI also has the potential to help radiologists identify subtle changes sooner.
“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 Strand. “Analyzing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention.”
Read more here.
In addition to her background in journalism, Hannah also has patient-facing experience in clinical settings, having spent more than 12 years working as a registered rad tech. She began covering the medical imaging industry for Innovate Healthcare in 2021.
