Viz Subdural+ is an AI-powered software that automatically analyzes head CT scans to measure subdural collections and midline shift. It helps clinicians by providing automated volume and width measurements of subdural collections, improving efficiency and accuracy in brain injury assessment.
The Viz Subdural+ device is intended for automatic labeling, visualization and quantification of collections in the subdural space from a set of Non-Contrast Head CT (NCCT) images. It automates identifying, labeling and quantifying volume of subdural collections from NCCT images acquired at a single time point. The software reports grayscale value, widest width of the subdural collection, and midline shift, to be reviewed by a physician.
Viz Subdural+ uses a locked AI machine learning algorithm to automatically process NCCT scans, providing visual overlays and quantitative metrics of subdural collections and midline shift. The software uses deep-learning convolutional neural networks to segment and quantify collections. Results are exported in DICOM format for clinician review. It is hosted on Viz.ai’s Backend Server where images sent after acquisition on CT scanners are analyzed automatically.
A retrospective study comparing Viz Subdural+ to neuroradiologist-established ground truth showed accurate segmentation and quantification of subdural collection volume, widest width, and midline shift on datasets with 203 and 151 cases respectively. Key metrics: mean absolute error (MAE) of 7.53 ml (volume), 1.77 mm (width), and 1.1 mm (midline shift). Dice score for volume segmentation was 73%. The performance met primary endpoints, demonstrating safety and effectiveness similar to the predicate device.
No predicate devices specified
Submission
2/7/2025
FDA Approval
6/10/2025
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.