Percutaneous nephrostomy guidance by a convolutional-neural-network-based optical coherence tomography endoscope

TL;DR

A new OCT endoscope with deep learning improves kidney surgery by guiding needles and avoiding blood vessels.

Contribution

An OCT endoscope with deep learning models for tissue and blood vessel recognition during percutaneous nephrostomy.

Findings

Optical coherence tomography effectively distinguishes kidney tissues like cortex, medulla, and pelvis.

Doppler OCT detects renal blood flow, and deep learning models achieve high accuracy in tissue classification and blood vessel detection.

Abstract

Percutaneous nephrostomy is widely used in kidney access surgeries. Despite its prevalence in urological interventions, it presents two operational challenges: 1) precise needle placement into the renal pelvis; and 2) avoiding hemorrhage from blood vessel rupture. In this study, we developed an endoscopic optical coherence tomography probe for needle navigation. We conducted experiments on thirty-one human kidneys for two aspects: 1) tissue recognition, and 2) blood vessel detection. Experimental results indicated that renal tissues including cortex, medulla, calyx, sinus fat, and pelvis could be effectively distinguished through structural optical coherence tomography imaging, and renal blood flow could be detected through the Doppler function. Deep learning methods were utilized to automate recognition procedures. For tissue classification, an Inception model was used, achieving a recognition accuracy of 99.6%. For blood vessel detection, an nnU-net model was applied, exhibiting an intersection over union value of 0.8917 for blood vessel and 0.9916 for background.

Percutaneous nephrostomy (PCN) navigation can be improved using an endoscopic optical coherence tomography (OCT) probe. By using human kidney specimen, Chen Wang and colleagues report a probe that has been tested feasible for accurate tissue and blood vessel identification during PCN.

Figures