Related Experiment Video
Updated: Oct 3, 2025
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Low-Dose 68 Ga-PSMA Prostate PET/MRI Imaging Using Deep Learning Based on MRI Priors
Fuquan Deng1,2,3, Xiaoyuan Li4, Fengjiao Yang4
1Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Background:
68 Ga-prostate-specific membrane antigen (PSMA) PET/MRI has become an effective imaging method for prostate cancer. The purpose of this study was to use deep learning methods to perform low-dose image restoration on PSMA PET/MRI and to evaluate the effect of synthesis on the images and the medical diagnosis of patients at risk of prostate cancer.
Methods:
We reviewed the 68 Ga-PSMA PET/MRI data of 41 patients. The low-dose PET (LDPET) images of these patients were restored to full-dose PET (FDPET) images through a deep learning method based on MRI priors. The synthesized images were evaluated according to quantitative scores from nuclear medicine doctors and multiple imaging indicators, such as peak-signal noise ratio (PSNR), structural similarity (SSIM), normalization mean square error (NMSE), and relative contrast-to-noise ratio (RCNR).
Results:
The clinical quantitative scores of the FDPET images synthesized from 25%- and 50%-dose images based on MRI priors were 3.84±0.36 and 4.03±0.17, respectively, which were higher than the scores of the target images. Correspondingly, the PSNR, SSIM, NMSE, and RCNR values of the FDPET images synthesized from 50%-dose PET images based on MRI priors were 39.88±3.83, 0.896±0.092, 0.012±0.007, and 0.996±0.080, respectively.
Conclusion:
According to a combination of quantitative scores from nuclear medicine doctors and evaluations with multiple image indicators, the synthesis of FDPET images based on MRI priors using and 50%-dose PET images did not affect the clinical diagnosis of prostate cancer. Prostate cancer patients can undergo 68 Ga-PSMA prostate PET/MRI scans with radiation doses reduced by up to 50% through the use of deep learning methods to synthesize FDPET images.
Insights
Deep learning restores low-dose 68 Ga-PSMA PET/MRI scans to full-dose quality, enabling up to 50% radiation dose reduction for prostate cancer patients without impacting diagnosis.
Area of Science:
- Medical Imaging
- Nuclear Medicine
- Artificial Intelligence
Background:
- 68 Ga-prostate-specific membrane antigen (PSMA) PET/MRI is crucial for prostate cancer diagnosis.
- Reducing radiation exposure in medical imaging is a significant clinical goal.
Purpose of the Study:
- To apply deep learning for low-dose 68 Ga-PSMA PET/MRI image restoration.
- To evaluate the impact of synthesized full-dose PET (FDPET) images on diagnostic accuracy.
Main Methods:
- Utilized deep learning with MRI priors to synthesize FDPET images from low-dose PET (LDPET) data of 41 patients.
- Assessed image quality using quantitative scores from nuclear medicine doctors and imaging metrics (PSNR, SSIM, NMSE, RCNR).
Main Results:
- Synthesized FDPET images from 50% dose PET data achieved high quantitative scores (4.03±0.17) and excellent image quality metrics (PSNR: 39.88±3.83, SSIM: 0.896±0.092).
- Image quality indicators demonstrated the effectiveness of the deep learning restoration method.
Conclusions:
- Deep learning-based synthesis of FDPET images from 50% dose PET data does not compromise prostate cancer diagnosis.
- This method allows for significant radiation dose reduction (up to 50%) in 68 Ga-PSMA PET/MRI scans for prostate cancer patients.
