Get our newsletters

St. Luke’s radiologists pioneer artificial intelligence in X-rays


Not long ago understanding and harnessing the power of artificial intelligence (AI) to improve medical care was considered futuristic, akin to science fiction.

Over the past year, St. Luke’s University Health Network (SLUHN) radiologist Dr. Karl Yaeger and his colleagues have worked with an international team of researchers fielded by GE Healthcare to develop the industry’s first X-ray system with an embedded AI algorithm to detect disease.

The technology, the portable Optima XR240amx featuring Critical Care Suite, is designed to alert the clinical team to the presence of potentially life-threatening collapsed lungs (pneumothorax) within seconds of image acquisition at the bedside.

GE Healthcare submitted the Critical Care Suite to the FDA for review last November. It is the first time an imaging system with AI-embedded clinical algorithms is being submitted to FDA for consideration. Other AI-driven applications are available to help physicians to more quickly diagnose strokes using CT scans and aid in wrist fracture detection.

The GE Healthcare AI-enhanced Optima XR240amx featuring Critical Care Suite has the potential to help prioritize X-ray image interpretation, then confirmation of the condition by the radiologist.

In helping develop the AI for the Critical Care Suite, Yaeger and his team at SLUHN reviewed hundreds of X-rays without and with pneumothoraces of all sizes and degrees of severity. These were then processed with the deep-learning software algorithm to determine its accuracy.

Yaeger said he’s enthused to be a part of the pioneering effort ushering in this “new wave” of healthcare technology. He’s optimistic at the potential of the AI-powered Optima XR240amx featuring Critical Care Suite to serve as an “untiring and undistractable partner,” a vital, and possibly life-saving, link between the bedside and the radiology reading room.

“The goal of this application of artificial intelligence is to increase the speed and accuracy of prioritizing these possibly-lethal conditions, so they are confirmed and treated sooner rather than later,” Yaeger said. “It’s ultimately about improving patient care and saving lives.”