Combining ensemble AI models with reads from breast radiologists of mixed experience levels can help health systems consistently diagnose malignant architectural distortion on mammography.

Researchers have developed a prediction model that takes into account both imaging (post-NAC breast MRI) and clinical-pathologic features when forecasting patients' overall survival.

Of the 51 plans, just 31% were consistent with the USPSTF recommendations pertaining to the starting age and frequency of screening women who are at average risk of developing breast cancer.

AB-MRI is a cost-effective means of screening women with dense breast tissue for breast cancer—as long as the per-exam costs don’t top 82% of what would have been spent to perform full-protocol breast MRI.

Researchers reported that the artificial intelligence system was able to interpret more than 114,000 screening mammograms using a reading protocol with high sensitivity and specificity.

The findings could help clinicians manage patients’ treatment when the origin of axillary lymphadenopathy is of concern, experts suggested. 

Women who underwent magnetic resonance imaging experienced more subsequent scans, procedures, healthcare visits and hospitalizations. 

Radiology and other specialties should reimagine a system requiring numerous separate visits for breast, lung, prostate, cervical, colorectal, and skin cancer, editorialists argued.