AI tool's supplemental MRI recs help detect 4 times more breast cancers than density measures
A recently developed artificial intelligence tool provides accurate recommendations on which women would benefit from supplemental MRI after having a negative mammogram.
Compared to traditional breast density measures used to guide supplemental imaging recommendations, use of the mammo scores provided by the AI tool (AISmartDensity) resulted in the detection of four times as many cancers. What’s more, many of the cancers detected were invasive or multifocal, making their detection more timely.
The findings were published in Nature Medicine, where corresponding author Frederik Strand, MD, PhD, of Karolinska University Hospital in Stockholm, Sweden, and colleagues explained that although supplemental MRI has proven benefits for spotting cancer in dense tissue, its accessibility remains out of reach for many.
“Supplemental screening using magnetic resonance imaging can reduce the number of missed cancers. However, as qualified MRI staff are lacking, the equipment is expensive to purchase and cost-effectiveness for screening may not be convincing, the utilization of MRI is currently limited,” the group noted.
Nearly 60,000 women were enrolled in the ScreenTrustMRI trial. Those who received the highest scores from the AI tool (top 6.9%, or 1,315 women total) were randomized, with half receiving supplemental MRI and the other half foregoing the additional imaging.
The AI method resulted in the detection of approximately 65 cancers per 1,000 women, while just 16.5 were produced using traditional density measures. This translated to a positive predictive value of 38% for the group of women who were sent for biopsy after their AI-recommended MRI.
The types of cancers detected are particularly important to take note of, the authors suggested.
“Most of these malignant lesions had invasive components,” the team noted. “The invasive cancers had a median size of 13 mm on pathology analysis, which is smaller than the average size of 15.8 mm and 19.6 mm for mammography screen-detected cancer and interval cancer.”
Another meaningful finding was that using the AI tool could make breast MRIs more accessible in terms of costs.
“Our results suggest that using AISmartDensity, the cost per [quality-adjusted life year] would probably be markedly lower given the close to four times higher supplemental cancer detection rate.”
The group suggested that radiologists taking a second look at mammograms that have especially high AI scores could help increase the cost effectiveness even more.
Learn more about the research 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 joined Innovate Healthcare in 2021 and has since put her unique expertise to use in her editorial role with Health Imaging.