Robotic Transrectal Computed Tomographic Ultrasound with Artificial Neural Network Analysis: First Validation and Comparison with MRI-Guided Biopsies and Radical Prostatectomy

Abstract

<b><i>Introduction:</i></b> There is still a lack of availability of high-quality multiparametric magnetic resonance imaging (mpMRI) interpreted by experienced uro-radiologists to rule out clinically significant PC (csPC). Consequently, we developed a new imaging method based on computed tomographic ultrasound (US) supported by artificial neural network analysis (ANNA). <b><i>Methods:</i></b> Two hundred and two consecutive patients with visible mpMRI lesions were scanned and recorded by robotic CT-US during mpMRI-TRUS biopsy. Only significant index lesions (ISUP ≥2) verified by whole-mount pathology were retrospectively analyzed. Their visibility was reevaluated by 2 blinded investigators by grayscale US and ANNA. <b><i>Results:</i></b> In the cohort, csPC was detected in 105 cases (52%) by mpMRI-TRUS biopsy. Whole-mount histology was available in 44 cases (36%). In this subgroup, mean PSA level was 8.6 ng/mL, mean prostate volume was 33 cm³, and mean tumor volume was 0.5 cm³. Median PI-RADS and ISUP of index lesions were 4 and 3, respectively. Index lesions were visible in grayscale US and ANNA in 25 cases (57%) and 30 cases (68%), respectively. Combining CT-US-ANNA, we detected index lesions in 35 patients (80%). <b><i>Conclusions:</i></b> The first results of multiparametric CT-US-ANNA imaging showed promising detection rates in patients with csPC. US imaging with ANNA has the potential to complement PC diagnosis.