Wildeboer RR, Mannaerts CK, van Sloun RJG, et al. - In this study authorized by the institutional review board, 50 men with biopsy-confirmed prostate cancer (PCa) that were referred for radical prostatectomy were involved in order to evaluate the potential of machine learning based on B-mode, shear-wave elastography, and dynamic contrast-enhanced ultrasound(US) radiomics for the localization of PCa lesions using transrectal ultrasound. Machine learning exhibited that combinations between perfusion-, dispersion-, and elasticity-related characteristics were favorable. In this paper, to enhance upon single US modalities for the localization of PCa, technical feasibility of multiparametric machine learning was exhibited. In the early diagnosis of PCa, more datasets for training and testing may establish the clinical significance of automatic multiparametric US classification.