SubtlePET is a software product that uses deep neural network-based AI algorithms to reduce noise and enhance the structural quality of PET images, including PET/CT and PET/MRI scans. It integrates into existing clinical workflows by acting as a DICOM node to process and forward enhanced images, helping radiologists and nuclear medicine physicians better visualize and analyze PET scans for improved diagnostic confidence.
SubtlePET is an image processing software intended for use by radiologists and nuclear medicine physicians for transfer, storage, and noise reduction of fluorodeoxyglucose (FDG) and amyloid PET images (including PET/CT and PET/MRI).
The software employs a convolutional neural network-based method that uses pixel neighborhood information and residual learning to predict noise and structural components separately, enhancing structural features while reducing noise. It operates as a DICOM node to receive, process, and forward image data, compatible with existing PACS systems or workstations, and runs on CentOS 7 Linux in a virtual machine or cloud environment.
Performance testing included design traceability, design verification confirming label compliance and software requirements, design validation testing simulating intended use, and noise reduction bench tests using human PET data showing significant quantitative improvements in image quality. Testing demonstrated the software's safety and effectiveness and substantial equivalence to the predicate device.
No predicate devices specified
Submission
8/28/2018
FDA Approval
11/30/2018
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.