A hospital in Texas has resumed mammography screening services after having its accreditation revoked for failing to meet clinical standards for images.
Ochiltree General Hospital in Perryton, TX, had its Mammography Quality Standards Act (MQSA) certificate suspended due to quality control deficiencies that were discovered during its annual inspection, according to a report from the State of Texas Certification Agency.
The state found serious deficiencies with the facility's clinical image quality that posed a risk to human health. The facility also failed to meet certain clinical image evaluation criteria.
Based on the failed results, the certification agency issued a "Notice of Violation" and a "Notice of Failure of Mammography System" on September 29. The hospital voluntarily suspended mammography operations pending completion of mandatory corrective actions and its MQSA certificate was suspended at that time as well.
Ochiltree was required to perform a Patient and Referring Healthcare Provider Notification (PPN) to alert all at-risk patients and their healthcare providers of its mammography quality problems. The hospital did so by December 10 and as a result, Ochiltree's MQSA certificate was reinstated and the facility is back to performing mammograms, the State of Texas Certification Agency 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=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)
