i2Contour
MRIMath LLCThe i2Contour by MRIMath LLC is a web-based AI-assisted software designed to semi-automatically segment and quantify glioblastoma tumors from MRI scans. It helps trained medical professionals by providing initial tumor contours which can be reviewed and manually adjusted, enabling accurate tumor volume assessments for patients with pathologically confirmed glioblastoma. This facilitates monitoring tumor progression or treatment response but is not intended for primary diagnosis.
Intended Use
Intended for the semi-automatic labeling, visualization, and volumetric quantification of WHO grade 4 glioblastoma (GBM) from standard MRI images of patients 18 years or older who have pathologically confirmed glioblastoma. Not intended for primary diagnosis or sole diagnostic metric.
Technology
A web-based AI-powered segmentation software platform that uses separate AI models for T1 post-contrast (T1c) and FLAIR MRI sequences. It generates initial tumor contours reviewed and manually approved by trained professionals. Unlike predicate devices, it does not require registration, skull stripping, or the use of T1 and T2 sequences, offering automated volumetric quantification of tumor subcomponents.
Performance
Performance was validated using 46 MRIs from 19 US centers, comparing AI contours against manual segmentations by three board-certified neuroradiologists. The AI achieved high Dice Similarity Coefficients (DSC) for T1c and FLAIR sequences (mean DSC approx. 0.92-0.95), with sensitivities and specificities above 90%. This performance matches or exceeds that of expert radiologists and the predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
12/1/2023
8 months - 2
FDA Approval
8/8/2024
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.