Dear AuntMinnie Member,
New research this week is generating renewed attention toward a potential connection between presurgical breast MRI and higher rates of mastectomies in women with breast cancer.
Researchers in Texas found that women at their facility who received breast MRI had a mastectomy rate three times higher than women who didn't undergo MRI, according to an article in our Women's Imaging Digital Community. Previous studies have reported conflicting results: Some researchers have proposed that suspicious lesions found on breast MRI prompt many women to opt for more aggressive treatment, while other studies have found no association.
Learn more about the study (including some positive findings on whether there's an association between breast MRI and treatment delays) by clicking here.
In other news, read about a start-up company based in New Zealand that believes it may have found a solution to the breast density dilemma -- software that automatically calculates breast density on screening mammograms. That story is available by clicking here or visiting our Women's Imaging Digital Community at women.auntminnie.com.
New VC CAD algorithm
In other news, we're highlighting a story in our Virtual Colonoscopy Digital Community on a new computer-aided detection (CAD) algorithm for virtual colonoscopy studies.
Researchers with the U.K. company that developed the software say it could offer a new level of polyp detection by going beyond flat lesions to find cancers that are actually invading the submucosa of the colon. The algorithm could give radiologists a tool to find evidence of colorectal cancer even earlier.
Read more by clicking here, or go to the Virtual Colonoscopy Digital Community at vc.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)










