cNeuro cMRI
Combinostics OycNeuro cMRI is a software tool designed to automatically identify, label, quantify, and visualize brain structures from MRI scans. It helps medical professionals by automating manual processes in brain image analysis, improving efficiency in the assessment of brain volumes and abnormalities compared to a healthy reference population.
Intended Use
cNeuro cMRI is intended for automatic labeling, quantification and visualization of segmentable brain structures from a set of MR images. The software is intended to automate the current manual process of identifying, labeling and quantifying the segmentable brain structures identified on MR images.
Technology
The device inputs T1-weighted (mandatory) and FLAIR (optional) MR images and performs image preprocessing including bias-field correction and brain extraction. Then it segments brain structures and calculates MRI biomarkers based on multi-atlas segmentation using atlases with 133 brain structures. It also compares volumes and white matter hyperintensities with a normative database.
Performance
The device underwent extensive verification and validation including code reviews, unit and system tests. Clinical validation included accuracy and reproducibility studies against manual ground truth labels using data from 1399 subjects with various neurological diseases. Similarity indices for key brain structures were high (Dice index around 0.88-0.91) and reproducibility ICC was 0.96, demonstrating safety and effectiveness.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
5/5/2017
8 months - 2
FDA Approval
1/8/2018
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.