Related Experiment Video
Updated: Jun 16, 2026
07:45
Author Spotlight: Standardizing Mouse In Vivo PET Imaging with Body Conforming Molds and Automated Analysis
Published on: October 25, 2024
275
Innovations in artificial intelligence for pet/mr imaging: Application and performance analysis.
Hanzhong Wang1,2,3, Yue Wang1, Xing Chen4
1Department of Nuclear Medicine, Ruijin Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China.
Journal of X-Ray Science and Technology
|May 9, 2025
Summary
Artificial intelligence (AI) enhances PET/MR imaging by improving image quality while reducing scan times and radiation dose. This AI-driven approach offers a more efficient and safer hybrid imaging solution for clinical applications.
Area of Science:
- Medical Imaging
- Radiology
- Artificial Intelligence
Background:
- Positron Emission Tomography/Magnetic Resonance (PET/MR) imaging faces challenges with long scan times and radiation exposure.
- Artificial intelligence (AI) presents a potential solution to mitigate these PET/MR limitations.
Purpose of the Study:
- To evaluate AI-based image enhancement methods on the United Imaging PET/MR system.
- Focus on improvements in image quality, reduced radiation dose, and shorter acquisition times.
Main Methods:
- Sixty-three patients underwent 18F-FDG PET/MR scans using conventional and AI-enhanced protocols.
- AI-enhanced system utilized reduced PET doses and accelerated MR sequences.
- Image quality assessed subjectively and objectively (SNR, artifact ratios).
Main Results:
- AI-enhanced PET/MR achieved high-quality images with lower PET doses and shorter scan durations.
- AI reconstruction resulted in superior signal-to-noise ratio (SNR) and fewer artifacts.
- Reduced noise levels were observed compared to conventional methods.
Conclusions:
- AI-enhanced PET/MR significantly boosts imaging efficiency.
- Reduces acquisition durations and radiation exposure.
- Enhances overall image quality, proving valuable for clinical hybrid imaging.
