HYPER AiR is a software device that enhances PET images by using pre-trained neural networks integrated into the image reconstruction process. It helps radiologists and nuclear medicine physicians by reducing noise and improving image contrast in fluorodeoxyglucose (FDG) PET scans, thereby potentially improving diagnostic confidence.
HYPER AiR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise and improve contrast of fluorodeoxyglucose (FDG) PET images.
HYPER AiR is a software-only device that integrates pre-trained convolutional neural networks into the iterative Ordered Subsets Expectation Maximization (OSEM) reconstruction process to distinguish noise from image details, reducing noise and enhancing contrast in PET images. It operates onsite on PET/CT reconstruction computers of cleared devices (uMI 550 and uMI 780).
Performance testing included non-clinical image performance tests and clinical image evaluation comparing HYPER AiR to OSEM. Tests demonstrated improved image contrast and reduced noise with HYPER AiR. Clinical evaluation by nuclear medicine physicians confirmed better image quality sufficient for diagnosis. Software verification, validation, and cybersecurity measures were also performed and found acceptable.
No predicate devices specified
Submission
1/4/2021
FDA Approval
4/30/2021
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.