Can AI interpret chest x-rays as well as rad residents?
October 9, 2020 -- Artificial intelligence (AI) software can yield similar or even, by some measures, better performance than radiology residents in interpreting chest radiographs, and it could potentially be utilized for automated preliminary assessments of these exams, according to research published online October 9 in JAMA Network Open.  Discuss
CORISK algorithm predicts oxygen need in COVID-19 patients
October 5, 2020 -- A deep-learning algorithm called CORISK can predict if a patient with COVID-19 symptoms will need supplemental oxygen. CORISK was developed using a federated-learning initiative involving 20 hospitals worldwide, performs well, and is generalizable, according to an announcement Monday at the Nvidia GPU Technology Conference.  Discuss
AI algorithm spots, classifies edema on chest x-rays
October 5, 2020 -- An artificial intelligence (AI) algorithm trained using chest x-rays and associated free-text radiology reports was able to find and detect the severity of pulmonary edema, potentially helping physicians to anticipate heart failure and manage conditions, according to its developers.  Discuss
AI characterizes pediatric lateral airway x-rays
October 2, 2020 -- Artificial intelligence (AI) in the form of deep-learning classifiers can help distinguish between poor- and adequate-quality pediatric lateral airway x-rays acquired in the emergency department, according to a study published September 30 in Radiology: Artificial Intelligence.  Discuss
Algorithm detects LVO stroke on multiphase CTA
September 29, 2020 -- An artificial intelligence algorithm can be extremely sensitive for detecting large-vessel occlusion (LVO) on multiphase CT angiography (CTA) scans, potentially speeding up diagnosis and hastening stroke treatment in these patients, according to research published online September 29 in Radiology.  Discuss
AI training sets often aren't geographically diverse
September 29, 2020 -- Clinical artificial intelligence (AI) algorithms across multiple disciplines -- including radiology -- are disproportionately trained on patient cohorts from three states: California, Massachusetts, and New York, according to a research letter published September 22 in the Journal of the American Medical Association.  Discuss
AMVC Fall 2020: AI can improve efficiency, reduce stress
September 24, 2020 -- The second article in a two-part series on Dr. Eliot Siegel's presentation at's Fall 2020 Virtual Conference (AMVC) details how artificial intelligence (AI) could help radiologists be more efficient and productive -- as well as less stressed -- during and after the COVID-19 pandemic.  Discuss
Will Medicare reimbursement propel radiology AI market?
September 23, 2020 -- The decision by the U.S. Centers for Medicare and Medicaid Services' earlier this month to provide its first-ever reimbursement of a radiology artificial intelligence (AI) algorithm was a significant milestone for the industry, raising hopes that it could set the groundwork for broader coverage of imaging AI software.  Discuss
AMVC Fall 2020: AI can reshape radiology post-COVID-19
September 23, 2020 -- Artificial intelligence (AI) can help radiology navigate challenges related to remote practice and extreme variation in imaging volume caused by the COVID-19 pandemic, according to the first of a two-part article series on a presentation by Dr. Eliot Siegel at's Fall 2020 Virtual Conference (AMVC).  Discuss
AMVC Fall 2020: 6 ways rads can improve perception of AI
September 22, 2020 -- As the development of artificial intelligence (AI) tools for healthcare continues, so does the debate about whether incorporating it into patient care will put physicians -- especially radiologists -- out of a job.  Discuss