Ceevra Reveal 3+

The Ceevra Reveal 3+ device, a software as a medical device, leverages machine learning and computer vision algorithms to generate accurate three-dimensional anatomical images from patient CT and MR scans. Its primary purpose is to enhance preoperative surgical planning and intraoperative display by providing clinicians with interactive 3D visualizations.

The Ceevra Reveal 3+ device, classified as a Class II software as a medical device (SaMD), has received substantial equivalence clearance, allowing its marketing. Its core purpose is to transform existing patient CT and MR scans into interactive three-dimensional (3D) images, which clinicians can utilize for enhanced preoperative surgical planning and intraoperative display, thereby improving visualization and decision-making during complex procedures. The system's scientific foundation relies on advanced machine learning and other computer vision algorithms to generate preliminary segmentations of normal anatomy specifically for adult patients aged 22 and over.The substantial equivalence determination was supported by comprehensive performance data, including validation of its machine learning models against segmentations performed by medical professionals, confirming its efficacy and safety. As a marketed medical device, Ceevra Reveal 3+ is subject to various general regulatory controls, including annual registration, device listing, adherence to good manufacturing practices, and proper labeling, alongside obligations for medical device reporting of adverse events and compliance with the Unique Device Identification System. These regulatory requirements ensure ongoing quality, safety, and effectiveness in its clinical application.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. What specific metrics were used to validate the accuracy and precision of the machine learning segmentations against those by medical professionals?; How does the Ceevra Reveal 3+ device integrate with existing hospital PACS systems and surgical navigation platforms?; What is the reported inter-user variability when clinicians interact with and refine the preliminary 3D segmentations?; Are there any known limitations or specific types of anatomical variations where the device's segmentation accuracy might be compromised?; What is the training data diversity for the machine learning models, particularly regarding different patient populations and imaging protocols?