Introduction: The aim of this study was to evaluate the accuracy of our new Automatic Augmented Reality (AR) system, named cTraker, in order to identify the tumour extracapsular extension (ECE) at the level of preserved neurovascular bundles (NVBs) during RARP.
Methods: From June to October 2019, 10 patients candidated to robot-assisted radical prostatectomy (RARP) were enrolled with suspicious ECE at preoperative high-resolution multi-parametric magnetic resonance imaging (mpMRI, 1-mm slices) according to dedicated protocol. The obtained three-dimensional (3D) reconstruction was integrated in the robotic console to perform AR-RARP. According to the staging at magnetic imaging or reconstruction, a metallic clip was placed at the level of suspected extracapsular extension (ECE). Prostate specimens were scanned to assess the 3D model concordance. Finally, according to the presurgical indications, the entire NVBs with suspicious ECE were removed for pathological examination. The Cohen kappa coefficient (k) was calculated to define agreement between preoperative suspected ECE and pT3 stage at final pathological examination.
Results: In 8 cases the final pathology (pT3) confirmed the presence of ECE (?=0.68). At macroscopic assessment the presence of ECE at the level of metallic clip was recorded in 100% of the cases; then the microscopic evaluation confirmed the cancer presence in all the cases and revealed a mean length of ECE of 4 mm.
Conclusions: Present findings suggest that the new evolution of our AR platform based on computer vision algorithm allows an effective Automatic AR RARP. The 3D virtual images, automatically anchored to the catheter, are able to correctly identify the location of ECE at the level of NVBs. Source of