Precision DL
GE HealthcarePrecision DL by GE Healthcare is a deep learning software designed to improve the quality of non-Time-of-Flight PET images used in clinical oncology. It enhances image contrast and reduces noise, helping clinicians obtain clearer PET scans to better detect and evaluate cancer, ultimately supporting improved patient care.
Intended Use
Precision DL is a deep learning-based image processing method intended to enhance image quality of non-ToF PET images for clinical oncology purpose, using F-18 FDG. Precision DL may be used for patients of all ages.
Technology
Precision DL is deployed within the acquisition and processing software of the Omni Legend PET/CT system as an image processing option. It employs deep learning to enhance non-ToF Q.Clear PET images to have quality similar to Time-of-Flight (ToF) PET images, improving parameters like Contrast Recovery, Contrast to Noise Ratio, and quantitation accuracy. It offers three models (Low, Medium, High) to balance contrast enhancement and noise reduction. It uses the same hardware as the predicate device and introduces no new risks.
Performance
The device underwent extensive non-clinical bench testing including quantitation accuracy, contrast recovery, contrast-to-noise ratio, lesion detectability, and dose/time reduction using both clinical and phantom data from multiple clinical sites. A clinical reader study with board-certified radiologists confirmed acceptable diagnostic image quality and preference for Precision DL images. No new safety issues were identified.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
10/17/2022
6 months - 2
FDA Approval
4/27/2023
Other devices from GE Healthcare
- Xeleris V Processing and Review System2023 • 510K
- Voluson P6, Voluson P82022 • 510K
- SIGNA Hero2022 • 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.