qXR-LN is an AI-based software device that analyzes frontal chest X-rays to detect and mark suspected lung nodules between 6 and 30 mm. It acts as a second reader to assist physicians like radiologists and pulmonologists, providing adjunctive information to improve detection accuracy without substituting the original image or clinical judgment.
Computer-aided detection software to identify and mark regions corresponding to suspected pulmonary nodules from 6 to 30 mm in size on frontal (AP/PA) chest radiographs in the adult population, intended as a second reader to assist physicians.
Software utilizes a deep learning algorithm trained on 2.5 million chest X-ray scans from diverse populations and equipment manufacturers, processes DICOM-format frontal chest X-ray images, and outputs DICOM images with regions of interest marked for probable nodules, functioning as adjunctive CAD software for radiologists and other clinicians.
Clinical performance testing included standalone and multi-reader multi-case (MRMC) studies using tens of thousands of chest X-rays from diverse U.S. sites and multiple equipment manufacturers. The device achieved a nodule-level sensitivity of 84.1%, improved reader performance with statistically significant AFROC improvement (p<1x10^-5), and demonstrated substantial equivalence to the predicate device with robust subgroup analyses for generalizability.
No predicate devices specified
Submission
6/20/2023
FDA Approval
12/22/2023
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.