Results from two recent studies suggest computer-aided detection for breast MRI may be closing in on true cancer detection.
Results from two recent studies suggest computer-aided detection for breast MRI may be closing in on true cancer detection.
Researchers from Penn Diagnostics, a breast MRI CAD company, and George Washington University tested the ONCAD system for contrast-enhanced MRI. They reviewed images of 102 biopsy-proven breast cancers and 131 cancer-free breasts from six major U.S. research institutions. The investigators found ONCAD could identify up to 96% of true malignancies.
In another study, researchers from New York University and Siemens Medical Solutions presented results of a computer classification system designed to improve breast MRI BI-RADS classification. Forty patients were included in this study. The investigators found the automated classification tool yielded more accurate BI-RADS classifications than three radiologists blinded to results. Both studies were released at the 2008 ARRS meeting.
Considering Breast- and Lesion-Level Assessments with Mammography AI: What New Research Reveals
June 27th 2025While there was a decline of AUC for mammography AI software from breast-level assessments to lesion-level evaluation, the authors of a new study, involving 1,200 women, found that AI offered over a seven percent higher AUC for lesion-level interpretation in comparison to unassisted expert readers.