A Nomogram Based on a Multiparametric Ultrasound Radiomics Model for Discrimination Between Malignant and Benign Prostate Lesions.

Lei Liang,Jun Guo,Jingxu Xu,Jiajun Wang,Xin Zhi,Ya Sun,Huarong Li

doi:10.3389/fonc.2021.610785

Abstract

ObjectivesTo evaluate the potential of a clinical-based model, a multiparametric ultrasound-based radiomics model, and a clinical-radiomics combined model for predicting prostate cancer (PCa).MethodsA total of 112 patients with prostate lesions were included in this retrospective study. Among them, 58 patients had no prostate cancer detected by biopsy and 54 patients had prostate cancer. Clinical risk factors related to PCa (age, prostate volume, serum PSA, etc.) were collected in all patients. Prior to surgery, patients received transrectal ultrasound (TRUS), shear-wave elastography (SWE) and TRUS-guided prostate biopsy. We used the five-fold cross-validation method to verify the results of training and validation sets of different models. The images were manually delineated and registered. All modes of ultrasound radiomics were retrieved. Machine learning used the pathology of “12+X” biopsy as a reference to draw the benign and malignant regions of interest (ROI) through the application of LASSO regression. Three models were developed to predict the PCa: a clinical model, a multiparametric ultrasound-based radiomics model and a clinical-radiomics combined model. The diagnostic performance and clinical net benefit of each model were compared by receiver operating characteristic curve (ROC) analysis and decision curve.ResultsThe multiparametric ultrasound radiomics reached area under the curve (AUC) of 0.85 for predicting PCa, meanwhile, AUC of B-mode radiomics and SWE radiomics were 0.74 and 0.80, respectively. Additionally, the clinical-radiomics combined model (AUC: 0.90) achieved greater predictive efficacy than the radiomics model (AUC: 0.85) and clinical model (AUC: 0.84). The decision curve analysis also showed that the combined model had higher net benefits in a wide range of high risk threshold than either the radiomics model or the clinical model.ConclusionsClinical-radiomics combined model can improve the accuracy of PCa predictions both in terms of diagnostic performance and clinical net benefit, compared with evaluating only clinical risk factors or radiomics score associated with PCa.

Highlights

The incidence rate of prostate cancer (PCa) is rapidly increasing in China [1] and is the second most common cancer and the fifth leading cancer-related cause of death among males [2]
With regard to clinical factors, total prostate-specific antigen (tPSA), free prostatespecific antigen (fPSA), and Prostate-specific antigen density (PSAD) were important factors for the prediction of PCa based on the univariate logistic regression analysis
Clinical-radiomics combined model can improve the accuracy of PCa predictions both in terms of diagnostic performance and clinical net benefit, FIGURE 6 | Nomogram of the combined model for predicting PCa

Summary

Introduction

The incidence rate of prostate cancer (PCa) is rapidly increasing in China [1] and is the second most common cancer and the fifth leading cancer-related cause of death among males [2]. As such, it has been one of the main health problems affecting many families. Patients with PCa are divided into the low, medium, or high risk groups based on the level of prostate specific antigen (PSA), pathological assessment/Gleason score (GS), and clinical stage (i.e. T stage) [6]. Accurate risk assessment is important to select the best treatment option for these patients

Objectives

Methods

Results

Discussion

Conclusion