An attorney for the Georgia hospital that discovered an employee had marked hundreds of unread mammograms as complete has asked local police to begin an investigation, according to the hospital's parent company.
On April 2, Perry Hospital in Perry, GA, a 45-bed facility in the Houston Hospital provider network, discovered a discrepancy during a quality check of mammography exams and began a broader quality review. That review found that a radiology employee had processed a number of mammography studies without obtaining a reading of the tests by a radiologist. The hospital has contacted 900 women to offer retakes, according to Victor Moldovan, attorney for Houston Healthcare.
The local Perry attorney has asked police to investigate whether the employee acted in a criminal manner, Moldovan said. The hospital terminated the employee after the incident.
"Perry Hospital's first priority was notifying patients [and beginning the retake process]," Moldovan said. "Now the next phase is beginning. If the employee did something criminal, it needs to be reported and investigated."
Related Reading
Hospital to retake 900 mammograms due to employee error, May 12, 2010
FDA cracks down on mammo RT records, February 26, 2010
Suspended Canadian radiologist: 'This is a modern-day lynching,' July 30, 2009
Canadian image audit: 70,000 reasons to have a PACS, July 20, 2009
Canadian authorities review 70,000 cases after rad is suspended, June 11, 2009
Copyright © 2010 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)
