qXR-CTR is an AI-powered software that helps physicians automatically measure the cardiothoracic ratio—the size of the heart relative to the chest—using chest X-ray images. It analyzes images to provide quick, accurate measurements that support clinical decision-making, making the process more efficient for healthcare providers.
qXR-CTR is a deep-learning based software for use by hospitals and clinics for automated assessment of the CTR on chest X-ray (CXRs) scans. It measures the ratio of the maximal transverse diameter of the heart and the maximal inner transverse diameter of the thoracic cavity on posterior-anterior chest views using AI. Intended for physicians or licensed practitioners for adult patients ≥22 years, results aid clinical assessment but are not standalone for decision making.
qXR-CTR operates as a radiological computer-assisted image processing software installed on standard computers. It automatically analyzes DICOM PA chest X-ray images using AI algorithms to measure cardiac and thoracic diameters and calculates the CTR. Outputs include annotated X-rays and structured reports in DICOM and JSON formats. It functions similarly to the predicate device with no notable technological differences.
Clinical validation on 435 PA chest X-rays from US-based data compared qXR-CTR's measurements to ground truth from experienced thoracic radiologists. qXR-CTR achieved root mean squared errors of 7.55 mm for cardiac diameter and 5.43 mm for thoracic diameter, outperforming predicate device metrics. Mean absolute errors were 5.66 mm and 4.04 mm respectively. Software verification, validation and testing followed FDA guidance and showed the device meets specifications with moderate level of concern.
No predicate devices specified
Submission
4/21/2023
FDA Approval
9/22/2023
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.