CHICAGO - Poor positioning of fatty breasts and underexposure of dense breasts are among the top reasons why mammography facilities fail to receive accreditation due to unsatisfactory clinical images.
In a study reported in scientific sessions at the RSNA conference Dec. 2, researchers from the University of California, Los Angeles and Thomas Jefferson University in Philadelphia looked at the clinical image statistics for all evaluations performed by the American College of Radiology Mammography Accreditation Program in 1997. ACR-MAP reviewed images from 2,341 mammography units in that year, 1,034 (44%) of which failed their inital evaluation.
ACR-MAP looks at eight categories in evaluating clinical images: positioning, compression, exposure, contrast, sharpness, noise, artifacts and labeling. Of these, positioning was the category where the highest number of failing grades were earned, followed by exposure, compression, sharpness and contrast.
The most commonly cited positioning problem was an inadequate amount of pectoral muscle on MLO views.
A significantly higher proportion of fatty breast images failed due to positioning deficiencies, noted Dr. D.M. Farria. Conversely, a significanly higher proportion of dense breast images were affected by exposure and compression deficiencies.
"We hope that these results will be valuable for educators in planning future continuing education courses for radiologists and for radiologic technologists," said Dr. Farria, noting that "different breast compositions pose different challenges."
By Tracie L. ThompsonAuntMinnie.com staff writer
December 3, 1999












![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)





