Intended Use

Ceevra Reveal 4 is intended as a medical imaging system for processing, review, analysis, communication, and media interchange of multi-dimensional digital images from CT, MR, or PET imaging devices. It may include generation of preliminary segmentations of normal anatomy using machine learning. It is also intended for preoperative surgical planning and intraoperative display, for use by healthcare professionals assisting in clinical decision-making.

Technology

The device is a software system used by trained company personnel to generate 3D images from CT, MR, and PET scans, and by clinicians to view and interact with these images for clinical purposes. It includes AI (machine learning) models for semi-automated segmentation of normal anatomy and offers features like rotating, zooming, panning, structure visibility controls, and quantitative measurement tools within its desktop and mobile applications.

Performance

Software verification and validation were carried out per medical device standards. Six machine learning models were verified using 201 imaging studies, with independent test data and diverse patient populations. Segmentations by the AI were compared to expert-annotated segmentations using Dice coefficient and Hausdorff distance. The product achieved high accuracy metrics (e.g., Dice scores around 0.8–0.9 depending on the structure). PET measurement accuracy was validated against phantom datasets, with SUVmax and SUVmean values within clinically acceptable ranges.

Predicate Devices

No predicate devices specified

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAISlice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.