Dear AuntMinnie Member,
Conebeam breast CT is a potentially exciting technology that could overcome some of the drawbacks of conventional mammography. But the modality is still in the early stages of development, and many questions remain.
U.S. researchers tried to address some of the issues facing conebeam breast CT in an article we're featuring this week in our Women's Imaging Digital Community. The group found conebeam breast CT to have several advantages compared to mammography, such as wider breast coverage.
At the same time, some of the major concerns about conebeam breast CT, such as higher radiation dose, did not appear to materialize. Learn more by clicking here.
CADET II on mammo CAD
In other women's imaging news, researchers from the U.K. have presented follow-on results in the Computer-Aided Detection Evaluation Trial II (CADET II), which is tracking the effectiveness of computer-aided detection (CAD) software in a population-based screening program.
While the original CADET II results, published in 2008, found single readers with CAD to perform in general about as well as double readers, the new study sought to compare the two approaches for specific kinds of breast pathology, such as microcalcifications, masses, and parenchymal deformities.
The researchers believe their results should help CAD users understand the strengths and weaknesses of the technology. Find out what they are by clicking here, or visit the community at women.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&dpr=2&fit=crop&h=167&q=70&w=250)
