NS-HGlio is a software tool that assists clinicians in analyzing MRI images of patients with high-grade brain gliomas by automatically labeling and measuring tumor regions. It supports doctors by providing volumetric data and visual overlays to help monitor tumor progression or treatment response, but it is not intended for primary diagnosis.
NS-HGlio is intended for the semi-automatic labeling, visualization, and volumetric quantification of high-grade brain glioma from standard MRI images of adult patients confirmed pathologically to have high-grade glioma. It is used as an additional information source by qualified clinical personnel and is not intended for primary diagnosis.
NS-HGlio operates as a software-as-a-medical-device (SaMD) taking DICOM standard MRI images as input. It employs deep learning to semi-automatically label glioma subcomponents and outputs volumetric measurements and segmented color overlays via a viewing software, with integration options to clinical PACS systems.
The device was validated on 33 subjects with 132 MRI scans from multiple vendors, using expert neuroradiologist-labeled ground truth. It achieved a mean Dice Similarity Coefficient of 0.88 (preoperative) and 0.80 (postoperative), outperforming expert averages, and an intraclass correlation coefficient (ICC) of 0.98, demonstrating high accuracy and reliability.
No predicate devices specified
Submission
6/15/2022
FDA Approval
9/27/2022
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.