Related Experiment Video
Updated: Dec 23, 2025
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Biparametric prostate MRI and clinical indicators predict clinically significant prostate cancer in men with "gray
Chao-Gang Wei1, Tong Chen2, Yue-Yue Zhang1
1Department of Radiology, The Second Affiliated Hospital of Soochow University, Suzhou 215004, China.
Purpose:
To predict clinically significant prostate cancer (cs-PCa) by combining the Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) score based on biparametric magnetic resonance imaging (bp-MRI) and clinical indicators in men with prostate-specific antigen (PSA) levels in the gray zone of 4-10 ng/mL.
Method:
We retrospectively analyzed 364 patients with elevated PSA levels in the gray zone who had pathologically confirmed disease and had undergone MRI examinations from January 2015 to October 2019; a training group (n = 255) and validation group (n = 109) were randomly established. Multivariate logistic regression analysis of the training group was performed to identify the independent predictors for cs-PCa, thereby establishing a predictive model that was evaluated in the training and validation groups by analyzing the receiver operating characteristic (ROC) curve.
Results:
In the training group, the PI-RADS v2 score and prostate volume (PV) were independent predictors of cs-PCa (P < 0.05). The prediction model comprising the PI-RADS v2 score and PV had a larger AUC than the other predictors alone in the training group. The diagnostic sensitivity and specificity of the prediction model were 84.1 % and 83.4 %, respectively. The prediction model was indicated to have better predictive performance in the validation group.
Conclusions:
The prediction model exhibits a satisfactory predictive value for cs-PCa in men with PSA levels in the gray zone. PI-RADS v2 is the strongest univariate predictor for the detection of cs-PCa in men with PSA in the gray zone, but combining this with the PV can provide superior predictive ability.
