Semiautomated vessel analysis software tends to underestimate the degree of carotid stenosis, particularly at levels that require corrective action, according to a study presented at the 2006 RSNA meeting.
Semiautomated vessel analysis software tends to underestimate the degree of carotid stenosis, particularly at levels that require corrective action, according to a study presented at the 2006 RSNA meeting.
Dr. William Boonn and colleagues analyzed data from 12 patients undergoing carotid angiography using multislice CT and six commercially available vessel analysis systems. They found underestimation of stenosis greater than 70% that ranged from 12% to 50%. The estimates worsened as degree of stenosis increased. However, they also found these vessel analysis systems provide improved visualization and other benefits. Study results suggest that vendors must improve the consistency and accuracy of automated stenosis measurements, Boonn said.
Boonn, an imaging informatics fellow at VA Maryland Health Care System when the study was conducted, currently works at the University of Pennsylvania.
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.