AI may help pinpoint women who could benefit from supplemental breast MR after a negative mammogram, according to a study published in Radiology.

The research, conducted in the Netherlands using ScreenPoint Medical's Transpara version 1.7.0, suggests AI could help triage mammograms and flag cases with a higher likelihood of undetected cancer.

Current international guidelines recommend MR screening alongside mammography for women with a lifetime breast cancer risk of 20% or higher based on family history. However, in the Netherlands, women with a 20%–50% risk often do not receive MR screening due to limited resources and inconsistent eligibility criteria.
"Evidence demonstrating the benefits of MR screening in this subgroup of women is accumulating," said Suzanne van Winkel, RN, MSc, a Ph.D. candidate at Radboud University Medical Center (Radboudumc) in Nijmegen. "MR detects cancers that remain undetected by mammography and are smaller and more often lymph node negative."

For this retrospective study, researchers analyzed 2D screening mammograms from women classified as having an "intermediate risk" of breast cancer — those with a family history of the disease but no genetic mutations, dense breast tissue, or prior high-risk biopsy results. The AI system assigned each case a suspicion score from 0 to 10, ranking the likelihood of malignancy.

The study reviewed 3,358 mammography exams from 875 women, with 2,819 exams (from 760 women) processed by the AI system. A total of 37 cancers (1.3%) were detected, with 19 (51%) not visible on mammography. AI assigned high suspicion scores to 31 of the cancer-positive exams (84%), including 68% of cases where the cancer was mammographically occult.

Dr. Stamatia Destounis, a breast radiologist at Elizabeth Wende Breast Care in Rochester, N.Y., noted the study's retrospective nature and its limitations.

"This is an interesting retrospective study that reveals that by using AI a certain percentage of cancers not identifiable on mammography can be found on breast MR," Destounis said. "However, the AI doesn't predict every patient with cancer, and some cancers, whether seen on the mammogram or not, are not detected by their AI model. In the U.S., the subgroup of patients considered intermediate risk by the study authors would likely fall in the high-risk category and would be recommended to undergo a high-risk MR, allowing the radiologist to identify all cancers, even those occult on mammography."

ScreenPoint Medical, based in Nijmegen, Netherlands recently acquired Biomediq A/S, a Danish firm focused on quantitative imaging biomarkers, to integrate Biomediq’s risk assessment technology into the Transpara platform.

Women's Health Homepage