GE Healthcare launched an artificial intelligence-powered chest X-ray analysis suite, designed to spot and highlight eight common conditions, using algorithms built by the South Korean startup Lunit.
Lunit’s Insight CXR program is designed to scan thoracic X-rays and label the probable signs of diseases such as tuberculosis and pneumonia, including that linked to COVID-19, as well as fibrosis, pneumothorax and the existence of potentially cancerous lung nodules.
“The launch of our Thoracic Care Suite is a part of GE Healthcare’s larger effort to help ensure clinicians and partners on the front lines have the equipment they need to quickly diagnose and effectively treat COVID-19 patients,” GE Healthcare President and CEO Kieran Murphy said in a statement. “The pandemic has proven that data, analytics, AI and connectivity will only become more central to delivering care.”
The AI overlays its results on top of the X-ray image, outlining the location of an abnormality along with a score that estimates the probability of the finding. The software also generates case reports summarizing each evaluation. Lunit’s algorithms previously received a CE Mark in November 2019, and have been used clinically in Korea, China, Thailand, Mexico and the United Arab Emirates.
GE Healthcare estimates that over 1.4 billion chest X-rays are performed worldwide every year—a workload that threatened to overwhelm radiologists, even before the onset of COVID-19 and the pandemic’s over 8 million confirmed cases, with many needing to undergo scans for pneumonia and acute respiratory distress.
“To have our AI made available with a market-leading vendor like GE Healthcare—especially as part of the Thoracic Care Suite—is a significant advancement in delivering solutions to various customers within GE Healthcare’s install base and bringing us all one step closer to embracing AI as a part of today’s standard of care,” said Lunit CEO Brandon Suh. The two companies described the collaboration as one of the first of its kind to merge commercially available AI products to an existing X-ray manufacturer.
The software package is available for GE Healthcare’s fixed and mobile X-ray and fluoroscopy hardware, and can be deployed without taking on an additional enterprise IT project, the company said. The suite also scans for atelectasis, calcification, cardiomegaly, mediastinal widening and pleural effusions.
In studies, the system demonstrated a 97% to 99% accuracy rate, and showed that it could reduce the amount of reading time per case for radiologists by one-third.