A healthcare network in Canada has sent letters to 3,500 patients alerting them that a radiologist may have misread their mammograms and CT exams, according to an article in the Toronto Star.
Trillium Health sent the letters after the network's chief of radiology discovered problems during a quality assurance review of the radiologist's work. The Croatian-trained radiologist has worked at Trillium hospitals for 33 years, but his privileges were restricted in April and he has voluntarily stopped working, according to the newspaper.
An internal review revealed three interpretation errors on CT scans, and at least one of the patients was found to have been misdiagnosed after follow-up scans were performed. At that point, Trillium decided to review 3,500 imaging exams performed between April 2012 and March 2013, the newspaper reported.











![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)






