Dear AuntMinnie Member,
Proponents of digital mammography got a boost from the results of the Digital Mammographic Imaging Screening Trial (DMIST), but many believe that there's still room for improvement in the technology.
Researchers continue to search for ways to refine the performance of full-field digital mammography (FFDM), according to an article by staff writer Shalmali Pal that we're featuring this week in our Women's Imaging Digital Community. The story is part of our expanded coverage of breast imaging in October as part of National Breast Cancer Awareness Month.
One study found that digital mammography systems in some cases use the same technical parameters as their analog predecessors, even though these specifications may not be optimal. For example, FFDM units might perform better with much thicker molybdenum filters.
The story also discusses ongoing efforts to educate breast imagers about the new technology, such as through an educational workshop to be held at this year's RSNA meeting. Read all about these new initiatives by clicking here.
Computer-aided detection (CAD) is another new technology making waves in mammography, and we're also featuring an article this week on the status of CAD in the U.K. Contributing writer Cynthia Keen traces how the U.K. is hoping that CAD can not only improve cancer screening detection rates, but also help the country cope with a shortage of mammography readers. Learn all about their experiences by clicking here.
Be sure to check back with the Women's Imaging Digital Community, at women.auntminnie.com, throughout October for additional coverage of National Breast Cancer Awareness Month.

![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=100&q=70&w=100)






![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)








