A multivariable prediction model combining 18F-PSMA PET/CT and mpMRI for clinically significant prostate cancer:...

Area of Science:

• Oncology
• Radiology
• Medical Imaging

Background:

• Multiparametric MRI (mpMRI) and prostate-specific membrane antigen (PSMA) PET/CT offer complementary data for prostate cancer diagnosis.
• Optimal integration of mpMRI and PSMA PET/CT for improved diagnostic accuracy remains an area of active research.

Purpose of the Study:

• To develop and validate a multivariable predictive model for clinically significant prostate cancer (csPCa).
• The model integrates clinical and imaging parameters from mpMRI and PSMA PET/CT.

Main Methods:

• A cohort of 1305 patients with suspected prostate cancer underwent mpMRI, 18F-PSMA PET/CT, and biopsy.
• LASSO regression and stepwise logistic regression were used for predictor selection.
• Model performance was evaluated using AUC, calibration plots, and decision curve analysis.

Main Results:

• A final model incorporated PRIMARY score, PI-RADS score, and prostate-specific antigen density (PSAD).
• The model achieved high predictive performance with an AUC of 0.916 in the training set and 0.837 in temporal validation.
• The integrated model demonstrated superior clinical utility compared to individual imaging parameters.

Conclusions:

• A multivariable model combining 18F-PSMA PET/CT and mpMRI parameters accurately stratifies csPCa risk.
• This integrated approach may enhance the optimization of prostate biopsy decisions.