Brian Casey, Erik L. Ridley, Kate Madden Yee, and Theresa Pablos[email protected]HomeMeet the Minnies 2020 finalistsMinnies finalists, page 3September 30, 2020HomeMeet the Minnies 2020 finalistsMinnies finalists, page 2September 30, 2020HomeMeet the Minnies 2020 finalistsAre you curious about who made it to the final round in this year's edition of the Minnies, AuntMinnie.com's event recognizing excellence in radiology? This year's list of finalists shows how the COVID-19 pandemic has impacted medical imaging.September 29, 2020Page 1 of 1Top StoriesMRIPetition asks FDA to implement new OEM rule for MRI safetyRadiofrequency (RF)-induced burns prompt recommendations to MRI manufacturers.Womens ImagingIncorrect AI suggestions influence reader performance on mammographyMRIPodcast: MRI tragedy, key aspects of the Colombini family's lawsuitMolecular ImagingBrain PET scans reveal neuron loss in long COVIDRadiation Oncology/TherapyASTRO urges Congress to address radiation oncology payment crisis
![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=167&q=70&w=250)
![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)
