MRI-Based Radiomics Nomogram for Predicting Prostate Cancer with Gray-Zone Prostate-Specific Antigen Levels to Reduce Unnecessary Biopsies

Abstract

Objective: The aim of this study was to establish a predictive nomogram for predicting prostate cancer (PCa) in patients with gray-zone prostate-specific antigen (PSA) levels (4–10.0 ng/mL) based on radiomics and other traditional clinical parameters. Methods: In all, 274 patients with gray-zone PSA levels were included in this retrospective study. They were randomly divided into training and validation sets (n = 191 and 83, respectively). Data on the clinical risk factors related to PCa with gray-zone PSA levels (such as Prostate Imaging Reporting and Data System, version 2.1 [PI-RADS V2.1] category, age, prostate volume, and serum PSA level) were collected for all patients. Lesion volumes of interest (VOI) from T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) imaging were annotated by two radiologists. The radiomics model, clinical model, and combined prediction model, which was presented on a nomogram by incorporating the radiomics signature and clinical and radiological risk factors for PCa, were developed using logistic regression. The area under the receiver operator characteristic (AUC-ROC) and decision, calibration curve were used to compare the three models for the diagnosis of PCa with gray-zone PSA levels. Results: The predictive nomogram (AUC: 0.953) incorporating the radiomics score and PI-RADS V2.1 category, age, and the radiomics model (AUC: 0.941) afforded much higher diagnostic efficacy than the clinical model (AUC: 0.866). The addition of the rad score could improve the discriminatory performance of the clinical model. The decision curve analysis indicated that the radiomics or combined model could be more beneficial compared to the clinical model for the prediction of PCa. The nomogram showed good agreement for detecting PCa with gray-zone PSA levels between prediction and histopathologic confirmation. Conclusion: The nomogram, which combined the radiomics score and PI-RADS V2.1 category and age, is an effective and non-invasive method for predicting PCa. Furthermore, as well as good calibration and is clinically useful, which could reduce unnecessary prostate biopsies in patients having PCa with gray-zone PSA levels.

Predicting prostate cancer in men with PSA levels of 4–10 ng/mL: MRI-based radiomics can help junior radiologists improve the diagnostic performance

“…Radiomics features offer the advantages of being an objective and quantitative tool. In our study, the radiomics model exhibited the best performance in both the training and testing groups, with an AUC of 0.932 and 0.922, respectively, which is consistent with the results of the two previous studies 24 , 25 , with an AUC of 0.844 and 0.941, respectively. The other previous study 26 employed radiomics features extracted from 2D segmentations to predict the risk of PCa in men with PSA levels of 4–10 ng/mL.…”

Radiomic Machine-Learning Analysis of Multiparametric Magnetic Resonance Imaging in the Diagnosis of Clinically Significant Prostate Cancer: New Combination of Textural and Clinical Features

“…Some authors have recently tried to develop and validate nomograms for the prediction of CS PCa. Nevertheless, these nomograms focused on a specific population with grey-zone PSA level (4-10 ng/mL) or PI-RADS 3 lesions [29,30]. Instead of targeting our work only on a pre-specified category, we avoided this and superselected our population in order to obtain data from a real-life cohort and a radiomic tool that could be more generalizable.…”

Comparisons of the diagnostic accuracy across prostate health index, prostate health index density, and percentage free prostate-specific antigen for clinically significant prostate cancer: a prospective diagnostic study

“…Therefore, the screening of csPCa becomes an important part of the treatment strategy (15). Studies have shown that approximately 75% of patients undergo unnecessary prostate biopsies based on PSA values only (16,17). Excessive biopsies lead to serious complications, such as urinary tract infections, pain, and hematuria (18).…”