Dear Women's Imaging Insider,
Although most radiologists agree that computer-aided detection (CAD) for breast cancer screening helps detect microcalcifications, there's less concord about the technology's ability to identify masses and architectural distortions -- with some radiologists arguing that CAD marks too many false-positive areas.
Is there a way to make CAD more effective? Dutch researchers developed a system that assists radiologists in interpreting suspicious regions rather than helping them detect them, displaying marks "on demand" when readers mouse-click over a particular mammographic area. Find out what they discovered about the pros and cons of "interactive" CAD by clicking here.
We've also covered yesterday's decision by a U.S. Food and Drug Administration panel to recommend approval for a new imaging mode on Hologic's Selenia Dimensions 3D digital breast tomosynthesis system. Click here to read more.
What else is going on in the Women's Imaging Digital Community? Take a look:
- Discover why researchers think breast brachytherapy may produce more complications than benefits for older and elderly women with early-stage breast cancer.
- Check out our coverage of the Minnie's winners, many of which point to the ongoing importance of breast imaging.
- Learn how 3D phase-contrast tomography shows smaller breast tumors.
- Read why ultrasound beat mammography as the best imaging modality for initial evaluation of breast cancer in symptomatic women ages 30 to 39.
- Find out how VuCOMP hopes to shake up the mammography CAD market with the premarket approval (PMA) it has received for its M-Vu CAD software for digital mammography.
As always, if you have a comment, report, or article idea to share about any aspect of women's imaging, I invite you to contact me.











![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)






