Development of a highly accurate diagnostic model for prostate cancer through the integration of clinical indices with apparent diffusion coefficient values derived from 3.0-T magnetic resonance

Abstract

Objective We aimed to evaluate the diagnostic utility of 3.0-T magnetic resonance (MR) diffusion-weighted imaging (DWI)-derived apparent diffusion coefficient (ADC) values in conjunction with clinical indices for prostate cancer (PCa). Methods A retrospective analysis was conducted on the clinical data of 181 patients with suspected PCa who underwent MR DWI prior to biopsy at LuHe Hospital, Beijing, between February 2022 and July 2023. Patients were placed into Malignancy and Benign groups according to the biopsy results. Univariate and multivariate analyses were performed on the ADC values and clinical indicators, and then a combination predictive model was developed. The model’s diagnostic accuracy was assessed using receiver operating characteristic (ROC) curve and decision curves analysis (DCA), and a nomogram was constructed for the assessment of individual risk. Results The ADC value and the free prostate-specific antigen and total prostate-specific antigen (tPSA) levels were found to be independent predictors of PCa. tPSA showed the best diagnostic performance, with an area under the curve (AUC) of 0.914. However, the combined model had a higher diagnostic accuracy, with an AUC of 0.959. Conclusion The combined model has superior predictive performance to other diagnostic methods and should help with the avoidance of unnecessary prostate biopsies.