Related Experiment Video
Updated: May 28, 2025
MR Molecular Imaging of Prostate Cancer with a Small Molecular CLT1 Peptide Targeted Contrast Agent
Published on: September 3, 2013
Correlations Between MR Apparent Diffusion Coefficients and PET Standard Uptake Values in Simultaneous MR-PET Imaging
Andrii Pozaruk1,2,3, Vitaliy Atamaniuk2, Kamlesh Pawar3,4
1Department of Photomedicine and Physical Chemistry, Institute of Medical Sciences, The Medical College of The University of Rzeszów, 35-310 Rzeszów, Poland.
Abstract:
This study evaluated the hypothesis that 68Ga-PSMA-11 PET SUV, obtained via an advanced DL approach, correlates better with MR ADC maps than values from conventional PET-MR. Additionally, we aimed to identify the optimal SUV threshold for maximum correlation with ADC values. A cohort of 32 prostate cancer patients underwent CT and corresponding PET-MR imaging. The dataset underwent K-fold cross-validation, dividing it into four folds. In each fold, 24 patients were used for training, and 8 for validation to create DL models. ADC maps from 27 out of 32 patients were successfully aligned with T2 images for detailed analysis, revealing an inverse correlation (ρ = -0.20 to -0.51) between ADC and SUV values in prostate cancer zones. Statistically significant differences in mean SUV values were observed between PETMRI and PETDL. DL-based SUV values show a stronger correlation with ADC than conventional PET-MR values in our investigation.
Insights
Advanced deep learning (DL) for 68Gallium-PSMA-11 (Ga-PSMA-11) PET SUV improves correlation with MR ADC maps in prostate cancer patients compared to conventional PET-MR. This finding aids in better disease characterization.
Area of Science:
- Nuclear medicine imaging
- Radiopharmaceuticals
- Prostate cancer diagnostics
Background:
- 68Ga-PSMA-11 PET/CT is crucial for prostate cancer staging.
- MR diffusion-weighted imaging (DWI) provides insights into tissue microstructure via apparent diffusion coefficient (ADC) maps.
- Integrating PET SUV and ADC values may enhance diagnostic accuracy.
Purpose of the Study:
- To evaluate if deep learning (DL)-derived 68Ga-PSMA-11 PET Standardized Uptake Values (SUV) correlate better with MR ADC maps than conventional PET-MR SUV.
- To determine the optimal SUV threshold for maximum correlation with ADC values.
Main Methods:
- A cohort of 32 prostate cancer patients underwent CT and PET-MR imaging.
- K-fold cross-validation (4 folds) was used for training (24 patients) and validation (8 patients) of DL models.
- ADC maps were aligned with T2 images for 27 patients to analyze correlations between ADC and SUV values.
Main Results:
- An inverse correlation was observed between ADC and SUV values in prostate cancer lesions (ρ = -0.20 to -0.51).
- Statistically significant differences in mean SUV values were found between conventional PET-MR and DL-based PET (PETDL).
- DL-based SUV values demonstrated a stronger correlation with ADC values compared to conventional PET-MR SUV.
Conclusions:
- DL-based 68Ga-PSMA-11 PET SUV shows improved correlation with MR ADC maps in prostate cancer.
- This advanced DL approach may offer more precise characterization of prostate cancer compared to conventional methods.
