VUNO Med-DeepBrain is an AI-powered medical software designed to automatically label, quantify, and visualize brain structures and lesions from MR images. It helps clinicians by automating manual brain segmentation processes, providing volumetric data along with visual color maps and reports, facilitating brain diagnosis and tracking over time in a clinical environment.
Intended Use
The VUNO Med-DeepBrain is intended for automatic labeling, quantification and visualization of segmentable brain structures from a set of MR images.
Technology
The software uses deep learning to automatically segment brain structures and lesions from 3D T1 and 2D T2 FLAIR MR images. It provides volumetric quantification, visual color maps, and integrates with PACS through DICOM. Pre-processing steps include resampling, registration, bias-field correction, and brain extraction; post-processing includes outlier removal and quality control.
Performance
Performance tests include segmentation accuracy measured by Dice Similarity Coefficient exceeding acceptance criteria of 0.80, and volume error analysis showing low errors in key brain regions. Reproducibility testing achieved high intraclass correlation coefficients, demonstrating excellent reliability. The device passed all pre-determined acceptance criteria, indicating safety and effectiveness comparable to the predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/15/2023
4 months - 2
FDA Approval
10/4/2023
Other devices from VUNO Inc.
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.