A small medtech outfit in North Carolina is opening its trove of medical imaging datasets to academic researchers working to develop AI applications for healthcare.

There’s no shortage of educational resources for teaching radiologists at all learning levels the principles and particulars of medical AI, but the need for radiology-specific materials is pronounced, according to a study published June 23. 

A healthcare AI platform supplier headquartered in Scotland is collaborating on marketing with a San Francisco-based AI startup co-founded and -led by a radiologist.

A top attractor of investors interested in medical imaging AI has drawn in a fresh $110 million.

The FDA has approved an augmented reality system that renders 3D holograms from CT images to guide surgeons operating the spine such that they don’t need to toggle their eyes between the patient and a monitor.

The AI software assisted in various tasks, such as segmenting, labeling and measuring normal structures, providing an automated analysis of pulmonary, cardiac and musculoskeletal findings.

Testing AI’s ability to detect carotid artery disease on ultrasound, U.K. researchers have found their algorithm achieved 90% accuracy, along with 87% sensitivity and 82% specificity, at the task.

A multi-institutional image-data repository launched to support AI-based research into COVID-19 has been the beneficiary of more than 30,000 anonymized imaging files from the Radiological Society of North America alone.