Wednesday, December 2 | 3:50 p.m.-4:00 p.m. | SSM01-06 | Arie Crown Theater
In this Wednesday afternoon scientific session presentation, University of California, Los Angeles researchers will present a study indicating that breast imaging is not an attractive career path for the majority of radiology residents.Chris Bent, Dr. Lawrence Bassett, and colleagues surveyed senior radiology residents on their breast imaging training experiences and attitudes, and compared the results to a similar survey conducted eight years prior.
The Web-based survey included a chief or senior resident at 201 radiology programs in the U.S. Bassett's team included topics such as the organization of breast imaging rotations, residents' responsibilities during rotations, clinical practice protocols of the institutions, residents' individual impressions regarding breast imaging, and their interest in performing breast imaging after residency.
By a wide majority, respondents reported that reading mammograms is more stressful than reading other imaging studies, according to Bassett's team, and more than half would not consider pursuing a breast imaging fellowship. A slight majority also would not want to spend a significant portion of their clinical practice interpreting mammograms, the team wrote.
The most common reasons given for not considering a fellowship or desiring to interpret mammograms? Lack of interest in the field, fear of lawsuits, and the stressful nature of the job, Bassett's team wrote.
"Residency programs have increased time devoted to breast imaging and made improvements in parts of their curricula, but a majority of the residents still would not consider a fellowship and did not want to interpret mammograms in their future practices," they said.











![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)






