Ryan McBeth[email protected]Home#MyRadGirlfriend No. 88: Data is king, but food fills seatsData is all the rage as healthcare analysts look for quantitative measures of healthcare quality. But how do you get busy attending physicians and residents to fill out surveys? Find out one trick in the next installment of #MyRadGirlfriend.June 27, 2019Home#MyRadGirlfriend No. 87: The feminist narrativeDo today's research trials adequately reflect medical outcomes in women? Or are they too focused on men? Ryan starts to wonder in the next installment of #MyRadGirlfriend.June 13, 2019Home#MyRadGirlfriend No. 86: Think before you scootElectric scooters are everywhere now, and while they can be a lot of fun, they also can have unintended consequences. One of those is more work for radiologists who read imaging studies from the emergency room -- including Andy, who decides to make a statement in the next installment of #MyRadGirlfriend.May 30, 2019Home#MyRadGirlfriend No. 85: The magic of Cinco de MayoWith the Cinco de Mayo holiday approaching, many hospital residents who aren’t working or aren’t on call have the opportunity to blow off a little steam. Priya and Andy are no different, as we discover in the next installment of #MyRadGirlfriend.May 2, 2019Emergency Radiology#MyRadGirlfriend No. 84: The most dangerous placeYes, the emergency room can be a dangerous place for a physician. But even greater danger can be found elsewhere in the hospital, as we learn in the next installment of #MyRadGirlfriend.April 11, 2019Home#MyRadGirlfriend No. 83: Circling the drainOne of the most challenging things about a radiologist's job can be dealing with referring clinicians, especially ones that are particularly obstinate, as Dr. Rankin is in the next installment of #MyRadGirlfriend.March 21, 2019Home#MyRadGirlfriend No. 82: When you hear hoofbeats ...It's been a late night in the reading room, and Andy encounters a perplexing case that could have a variety of differential diagnoses. Find out how she settles on the correct one in the next installment of #MyRadGirlfriend.March 7, 2019Home#MyRadGirlfriend No. 81: The price to pay for being antivaxAntivaxxers may think they're doing the right thing for their kids, but there's a price to pay for not getting vaccinated -- and it's mainly paid by their children, as Andy and Ryan find out in the next installment of #MyRadGirlfriend.February 21, 2019Home#MyRadGirlfriend No. 80: Anxiety in the reading roomWhat fears push your anxiety buttons? For some radiologists, it's the board exam, while others have more existential concerns. Andy has to face some of her internal demons during a long night in the reading room in the next installment of #MyRadGirlfriend.February 7, 2019Home#MyRadGirlfriend No. 79: How sweet it isMost folks would agree that the explosion of new coffee varieties is a great thing. But they can have a downside, as Andy and Priya find out in the next installment of #MyRadGirlfriend.January 24, 2019Previous PagePage 4 of 12Next PageTop 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)
