NEUROShield
In-Med Prognostics L3CNEUROShield is a software tool that automatically labels, visualizes, and measures the volume of the hippocampus brain structure using 3D MRI images. It uses AI deep learning models to assist neurologists and neuroradiologists by providing fast, accurate volumetric analysis, helping in clinical decision-making and research.
Intended Use
The NEUROShield medical image processing software is intended for automatic labelling, visualization, and volumetric quantification of the Hippocampus brain structure from a set of MR images.
Technology
NEUROShield is a fully automated brain geometry-based quantifying analytics tool/cloud platform using DeepNet / U-Net methodologies for segmentation. It takes 3D MR images in uncompressed DICOM format as input, performs segmentation, volume calculation, and report generation through an automated processing pipeline.
Performance
Performance testing included training on a dataset of 186 cases from multiple sites with manual segmentation ground truth by experts. Validation used an independent dataset of 280 subjects from the ADNI database, with statistical analysis showing high accuracy (Dice coefficient ~0.91, Hausdorff distance ~3.8 mm) and good agreement with expert segmentations across subgroups.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
1/5/2022
1 year, 8 months - 2
FDA Approval
9/14/2023
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.