The U.S. Food and Drug Administration (FDA) has issued a reminder to mammography facilities that they must use qualified medical physicists to survey their equipment, oversee equipment-related quality control (QC) programs, and perform mammography equipment evaluations.
This mandate is part of the final Mammography Quality Standards Act (MQSA) regulations, the FDA said.
A complete physicist's survey report or mammography equipment evaluation should include the following:
- The date of the survey or evaluation
- The name and signature of the medical physicist performing or supervising the survey or evaluation, as well as the name of any other individuals participating in the survey
- A summary of the required QC test results in pass/fail designations and the results of all tests conducted, including a summary of any recommendations or corrective actions for which facilities must have documentation to demonstrate that corrective actions were performed in a timely manner
- A summary of the evaluation of the facility's QC testing other than annual, with recommendations for necessary improvements or corrective actions
- A written justification from the medical physicist for any omitted tests, deviations, or unusual circumstances
"It is the facility's responsibility to see that these evaluations are performed by a qualified medical physicist, that reports are complete, and that any issues are addressed in a timely manner," the agency wrote. "It is the facility who will receive citations for any violations identified during an inspection."











![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)






