HYPER DLR is a software-only device that applies a pre-trained convolutional neural network to reduce noise in fluorodeoxyglucose (FDG) PET images. It improves image quality by distinguishing and removing noise components while preserving image details, aiding radiologists and nuclear medicine physicians in better image interpretation.
Intended Use
HYPER DLR is an image processing function intended to be used by radiologists and nuclear medicine physicians to reduce noise of the fluorodeoxyglucose (FDG) PET images.
Technology
HYPER DLR is a software-only image post-processing device that runs onsite on PET/CT reconstruction computers. It employs a pre-trained convolutional neural network to predict a low noise PET image from a high noise PET image, extracting the noise component while preserving image details. It serves as an alternative to Gaussian filtering smoothing methods used in predicate devices.
Performance
Performance testing included bench testing using identical raw datasets from predicate devices, comparing HYPER DLR against Gaussian filtering. Metrics such as peak signal to noise ratio, structural similarity, and contrast to noise ratio demonstrated improved image quality with HYPER DLR. Clinical image evaluation by certified nuclear medicine physicians showed lower image noise and sufficient image quality for diagnosis compared to Gaussian filtering. No clinical study was included.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
11/21/2019
8 months - 2
FDA Approval
8/4/2020
Other devices from Shanghai United Imaging Healthcare Co., Ltd.
- uDR 780i2024 • 510K
- uDR 380i Pro2024 • 510K
- uMI Panorama2024 • 510K
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.