Dear AuntMinnie Member,
One of the most intriguing areas of current mammography research is breast tomosynthesis. Under development by several mammography vendors, breast tomosynthesis involves the use of a specialized mammography system that has a tube head that rotates in an arc over the breast, rather than remaining stationary.
The rotating tube head enables the tomosynthesis system to capture digital breast images in multiple slices from different angles, rather than just from a limited number of views as is done with current mammography systems. This has the potential to enable mammographers to see breast pathology that otherwise might have been obscured by tissue.
At last week's RSNA meeting in Chicago, Dr. Steven Poplack from Dartmouth-Hitchcock Medical Center in Lebanon, NH, presented research on the use of an investigational breast tomosynthesis system for diagnostic mammography applications.
In this AuntMinnieTV segment, Dr. Poplack discusses the utility of the system in comparison to conventional mammography, in particular its ability to reveal more information about suspicious areas in the breast and potentially reduce the number of women who are recalled for additional exams. You can view the segment by clicking here.
Stay tuned in coming weeks for more AuntMinnieTV segments from medical imaging's showcase conference. To view additional coverage of the meeting, just visit our RADCast@RSNA special section at radcast.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=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)








