Intended Use

The device is intended for viewing, post-processing, qualitative and quantitative evaluation of cardiovascular CT images to assess the presence and extent of coronary plaques and stenoses in coronary CT angiography (CCTA) images in an adult population.

Technology

The device is a Software as a Medical Device (SaMD) that uses AI/ML algorithms for semi-automated segmentation and detection of lumen and vessel wall structures from CT Angiography images. It provides multiplanar reconstruction, curved planar reformation, 3D rendering, and quantitative plaque volume and burden measurements. All surfaces generated are editable with manual correction possible. It integrates with other cardiac image visualization software.

Performance

Performance testing including software verification and validation according to FDA guidance, ISO and IEC standards was conducted with no clinical trials needed. Machine learning models were trained and validated on multi-vendor CT data from U.S. sources. Evaluation metrics like Dice Similarity Coefficient, Hausdorff Distance, and Pearson Correlation Coefficient confirmed acceptable accuracy of segmentation and plaque volume measurement. Performance met pre-defined acceptance criteria and was consistent across diverse subgroups. Cybersecurity measures and penetration testing were implemented.

Predicate Devices

No predicate devices specified

Ready to Sharpen Your Edge?

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.