The Quebec College of Physicians is investigating a radiologist after suspicions were raised of inaccurate readings of breast mammography exams, according to an article published in the Montreal Gazette on November 12.
In an inquiry that could take up to six months, the college has ordered the re-examination of 15,000 x-ray films read by the radiologist in the past two years at three Quebec clinics, two in Montreal and one in Laval, the paper reported. The radiologist, whose name has not been made public, is barred from reading x-rays or other scans until the investigation is concluded.
The college's suspicions were raised about the doctor because his referral or anomaly rate was lower than the standard 15% for mammography exams, according to the Gazette.
The Quebec College of Physicians hopes to inform all patients who had x-rays read by the doctor whether their exams are being reviewed by December 20, the paper said.
Related Reading
Canadian rad fails competency test, November 9, 2009
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
Web site solicits patients for cases of radiology errors, May 27, 2008
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)
