The reason for performing a breast MRI should be taken into consideration when assessing performance measures.
Performance measures for breast MRI vary significantly for screening and diagnostic examinations, according to a study published in the Journal of the American College of Radiology.
Researchers from Massachusetts, Delaware and Texas sought to evaluate breast MRI performance measures from a single academic institution, stratified by screening and diagnostic indications. They performed a retrospective search of the institution’s breast imaging database and found 2,444 breast MRIs from April 1, 2007 to March 31, 2008 that could be included in the study.
A total of 1,313 of the examinations were for screening, with the most common reason being personal and family histories of breast cancer; 1,131 examinations were for diagnostic indications.
The researchers assigned an overall BI-RADS assessment to each study, according to the most actionable BI-RADS lesion category. Cancer detection rate, positive predictive value (PPV) and abnormal interpretation rates were calculated.
The results showed that cancer detection rates were 14 per 1,000 screening breast MRI examinations and 47 per 1,000 diagnostic examinations, while the abnormal interpretation rate was 12 percent (152 of 1,313) for screening and 17 percent (194 of 1,131) for diagnostic indications.
The positive predictive values were lower for screening than for diagnostic indications:
The researchers concluded that the performance of breast MRI measures differ significantly between indications and that medical audits should take this into consideration, calculating performance measurements for screening and diagnostics separately.
Emerging AI Algorithm Shows Promise for Abbreviated Breast MRI in Multicenter Study
April 25th 2025An artificial intelligence algorithm for dynamic contrast-enhanced breast MRI offered a 93.9 percent AUC for breast cancer detection, and a 92.3 percent sensitivity in BI-RADS 3 cases, according to new research presented at the Society for Breast Imaging (SBI) conference.
Could AI-Powered Abbreviated MRI Reinvent Detection for Structural Abnormalities of the Knee?
April 24th 2025Employing deep learning image reconstruction, parallel imaging and multi-slice acceleration in a sub-five-minute 3T knee MRI, researchers noted 100 percent sensitivity and 99 percent specificity for anterior cruciate ligament (ACL) tears.