
The U.S. Food and Drug Administration (FDA) said it's alerting patients who had mammograms at Laurel Radiology Services in Laurel, MD, on or after June 26, 2018, about possible problems with the quality of their mammograms.
The facility's annual Mammography Quality Standards Act (MQSA) inspection revealed that the facility failed to obtain accreditation of its full-field digital mammography (FFDM) unit from the facility's accreditation body, the American College of Radiology (ACR), prior to using the unit to image patients. Additionally, the facility failed to perform the required weekly review workstation compliance quality control test for at least 12 consecutive weeks between June 16, 2020, through Sept. 12, 2020.
The ACR conducted the additional mammography review of mammograms performed by Capitol Radiology, doing business as Laurel Radiology Services, and the results indicated the mammograms did not meet the ACR's clinical image evaluation criteria, and some of the deficiencies were severe.
On March 24, 2021, the ACR revoked the facility's accreditation, and on March 25, 2021, the FDA placed the facility's MQSA certificate in a "no longer in effect" status. Consequently, the facility may not legally perform mammography at this time, according to the FDA.


![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)







