Dear AuntMinnie Member,
Computer-aided detection (CAD) software works well with two new digital mammography screening technologies, computed radiography (CR) and flat-panel-based full-field digital mammography (FFDM).
That's according to a recent study presented by clinical investigators working in collaboration with a CAD vendor. We cover their study in an article for our Women's Imaging Digital Community by staff writer Wayne Forrest.
The researchers wanted to see if CAD for CR mammography and flat-panel FFDM produced results in line with those of CAD based on digitized film-screen mammograms. The question is important as more mammography sites adopt digital mammography technologies (the first CR mammography system received U.S. regulatory approval less than a year ago).
Find out what they discovered by clicking here, or visit our Women's Imaging Digital Community at women.auntminnie.com.
Meanwhile, the CT lung screening debate won't fade away quietly. This week Japanese researchers at the American Thoracic Society meeting in San Francisco presented results from their study of almost 20,000 subjects that showed a benefit from CT lung screening.
The retrospective analysis hasn't received the attention garnered by the recent paper published in the Journal of the American Medical Association, which panned CT lung screening's benefits. But the Japanese team found that patients screened with CT had far smaller tumors and survival rates nearly double those of patients who presented with symptoms. CT maintained its advantage even when the tumors it found most frequently, bronchoalveolar cell carcinomas, were excluded.
The article is available by clicking here, or by visiting our CT Digital Community, at ct.auntminnie.com.


















![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&fit=crop&h=112&q=70&w=112)
