Diagnostic Imaging's Weekly Scan: September 18-September 24

While 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.

In a second part of a new podcast episode on recently published research on projected radiation-induced cancers from computed tomography (CT) scans, Mahadevappa Mahesh, MS, Ph.D., and Joseph Cavallo, M.D., offer current perspectives on cardiac CT dosing, AI advances and the importance of teamwork in ensuring appropriate dosing for CT.

Artificial intelligence (AI) software had a 14 percent false negative rate in a new study involving over 1,082 women with invasive breast cancer.

In a new podcast, Mahadevappa Mahesh, MS, Ph.D., and Joseph Cavallo, M.D., share their perspectives on recently published research looking at projections for future radiation-induced cancers from computed tomography (CT) scans.

Emerging research shows that a multiple time-series deep learning model assessment of CT images provides 20 percent higher sensitivity than a delta radiomic model and 56 percent higher sensitivity than a clinical model for prognostic evaluation of ground-glass nodules.

While the addition of contrast-enhanced mammography (CEM) to digital breast tomosynthesis (DBT) led to over a 13 percent increase in false positive cases, researchers also noted over double the cancer yield per 1,000 women in comparison to DBT alone.