SubtlePET is an advanced software tool designed to improve the quality of PET medical images by reducing noise. Utilizing deep learning algorithms, it enhances image clarity, aiding radiologists and nuclear medicine physicians in interpreting PET scans more accurately. This software integrates smoothly into existing radiology workflows by receiving, processing, and forwarding DICOM images, supporting multiple radiotracers used in PET imaging.
SubtlePET is an image processing software intended for use by radiologists and nuclear medicine physicians for transfer, storage, and noise reduction of fluorodeoxyglucose (FDG), amyloid, 18F-DOPA, 18F-DCFPyL, Ga-68 Dotatate, and Ga-68 PSMA radiotracer PET images.
The software employs a convolutional neural network-based algorithm using a residual learning approach to predict and separate noise and structural components of PET images, thereby enhancing image quality. It operates as a DICOM node to receive, process, and forward images in existing clinical workflows.
Performance testing included software verification and validation as well as noise reduction bench tests on human PET data from IRB-approved clinical protocols, showing significant quantitative improvements in image noise reduction compared to predicate.
No predicate devices specified
Submission
6/24/2021
FDA Approval
9/28/2021
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.