How trustworthy is AI breast cancer detection? New method gauges uncertainty for individual patients
While AI offers the ability to improve human experts' ability to diagnose and treat diseases like breast cancer, well-publicized errors across the broader AI field are cause for concern. A team from the University of Pittsburgh has used PSC's flagship Bridges-2 supercomputer to design a deep neural network (DNN) that takes uncertainty into account in diagnosing breast scan images.
Read original article on Medical Xpress - latest medical and health news stories →Related news
-
Early uptake for oral semaglutide proves rapid relative to injectables
United Kingdom
-
Beyond the ACE score: A single number may miss the complexity of childhood trauma, study suggests
United Kingdom
-
ADHD medication unlikely to raise risk of self-harm, international study finds
United Kingdom
-
Adults with type 1 diabetes more likely to have depressive, anxiety symptoms
United Kingdom
-
Nurses are an important resource in Swedish bowel cancer screening
United Kingdom
-
Imaging study links several schizophrenia symptoms to a single brain signal
United Kingdom
-
Intermittent fasting plus exercise boosts fat loss and fitness in 12-week obesity trial
United Kingdom
-
Prevalence of binge eating 40.5% in U.S. high school students
United Kingdom