Icobrain is an AI software tool that helps clinicians automatically identify, label, and measure brain structures and abnormalities using MRI or CT images. It supports tracking changes in brain volumes over time, aiding diagnosis and monitoring of brain diseases such as dementia or traumatic brain injury.
Icobrain is intended for automatic labeling, visualization and volumetric quantification of segmentable brain structures from a set of MR or NCCT images to automate the manual process of identifying, labeling and quantifying brain volumes.
Icobrain consists of two distinct image processing pipelines: icobrain cross provides volumes from single MR or NCCT images, and icobrain long provides volume changes between two MR images acquired on the same scanner and protocol at different time points. Processing includes conversion from DICOM to NIFTI, segmentation of brain structures, quantification, and report generation with overlays on input images.
Performance validation included accuracy and reproducibility testing with 463 MR and 618 CT datasets covering healthy subjects and various patient groups. Metrics such as Pearson correlation coefficient and intraclass correlation coefficient showed high correlation (>0.9) with ground truth volumes and test-retest sets. Verification tests demonstrated the system met intended use and safety standards per ISO and FDA requirements.
No predicate devices specified
Submission
8/7/2019
FDA Approval
12/13/2019
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.