Nerve recognition in percutaneous transforaminal endoscopic discectomy using convolutional neural network
Peng Cui, Tao Shu, Jun Lei, Wenxi Chen
Abstract
PURPOSE: Percutaneous transforaminal endoscopic discectomy (PTED) is one of the most common minimally invasive surgery methods used in clinic in recent years. In this study, we developed a computer-aided detection system (CADS) based on convolutional neural network (CNN) to automatically recognize nerve and dura mater images under PTED surgery. METHODS: We collected surgical videos from 65 patients with lumbar disc herniation who underwent PTED; we then converted the videos into images, and randomly divided some images into a training dataset, a validation dataset, test dataset. The training dataset and validation dataset were composed of 10 454 images containing nerve and dura mater from 50 randomly selected patients; test dataset contained 12 000 images from the remaining 15 patients. RESULTS: The results showed that sensitivity, specificity, and accuracy reached 90.90%, 93.68%, and 92.29%, respectively. CADS could recognize the nerve and dura mater with no significant difference (P > 0.05) between each patient in test dataset. In comparison with clinicians of different levels, the performance of CADS was lower than that of a spinal endoscopist, but significantly higher than that of general surgeons. With the assistance of CADS, the performance of the general surgeons approached that of the spinal endoscopist. CONCLUSIONS: CNN can recognize well nerve and dura mater images in PTED surgery, and can help general surgeons to improve their ability to recognize tissues during the operation.