SubtleSYNTH (1.x) is an AI-based software that synthesizes STIR contrast images from T1- and T2-weighted spine MRI sequences. It uses a convolutional neural network to generate synthetic images that can be reviewed alongside traditional MRI scans, helping radiologists by providing additional image contrast information without additional scanning time or patient burden.
SubtleSYNTH is a software as a medical device consisting of a software machine learning algorithm that synthesizes a SynthSTIR contrast image of a case from T1-weighted and T2-weighted spine MR images.
SubtleSYNTH uses a convolutional neural network-based algorithm to synthesize SynthSTIR images from existing T1- and T2-weighted MR images. This is a post-processing software that runs in the background without direct interaction with the MR scanner. It processes images received via DICOM from a compatible medical device data system and returns synthesized images for clinical review.
Performance evaluation included bench testing and interchangeability studies comparing SynthSTIR images generated by SubtleSYNTH to clinically acquired STIR images. Testing used a diverse set of clinical MRI data from multiple scanner vendors and field strengths, confirming the synthesized images were interchangeable with acquired images across a range of tissue types and clinical conditions per quantitative metrics and radiologist reader studies.
No predicate devices specified
Submission
5/10/2024
FDA Approval
7/11/2024
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.