Intended Use

Intended to aide a clinician in the detection and localization of a pneumothorax on frontal chest radiographic images.

Technology

Uses deep learning AI algorithms deployed on various platforms (PACS, On Premise, On Cloud, or X-ray Imaging Systems) to analyze frontal chest X-ray images. Outputs include detection flags, localization overlays, and confidence scores highlighting suspected pneumothorax.

Performance

Clinical testing included standalone performance and multi-reader multi-case study with over 12,000 training images and 804 validation images. Achieved 96.1% AUC, 84.3% sensitivity, and 93.2% specificity. Use of the AI improved reader mean AUC by 14.5%, sensitivity by 16.3% and specificity by 12.4%.

Predicate Devices

No predicate devices specified

Ready to Sharpen Your Edge?

Subscribe to join 7,100+ 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.