Bibb Allen, MD, FACR, chief medical officer of the American College of Radiology (ACR) Data Science Institute, discusses multiple factors involved in the adoption rate of artificial intelligence in radiology.
 

Experts compared the cortical thickness of three bones—the radius, tibia and second metatarsal—of 200 volunteers who had undergone prior bone mineral density measurements to evaluate the ultrasound method’s accuracy.

Bibb Allen, MD, FACR, chief medical officer of the American College of Radiology (ACR) Data Science Institute, explains the trend of using AI for the automated detection of stroke on computed tomography (CT) imaging and the need to include radiologists on the stroke care team.

Experts at MIT have developed ultrasound stickers that can be worn in the same manner as a Band-Aid while also producing diagnostic quality images in real-time.

The model was externally validated using more than 1,500 radiographs with real-world incidence of critically misplaced tubes. 

Image sharpness was further improved when sharper reconstruction kernels were used, despite having higher noise levels.

The 40 evidence-based recommendations touch on everything from patient selection to study choice, radiation safety, clinical team dynamics, procedural techniques, study interpretations and more. 

In a sampling of 2,273 chest radiographs of kids aged 2 to 18-years-old the AI-based software achieved diagnostic accuracies ranging from 86% to 96.9% for detecting a myriad of pathologies.