Neuro-endo-activity-tracker: An automatic activity detection application for Neuro-Endo-Trainer: Neuro-Endo-activity-tracker

Abstract

Neuro-endoscopy is a highly demanding surgical specialty and requires dedicated training systems for imparting the skills. The assessment of surgical skills to identify the level of expertise of technical and cognitive skills, has primarily been performed subjectively by an expert. The development of objective motion analyses and automated skills evaluation can be a significant and suitable alternative. The video-based automatic segmentation can divide the primary activity into sub-tasks and then evaluate them by statistical analysis of motion. In this work, we developed an automated video-based surgical evaluation application. It identifies the basic eye-hand coordination and dexterity of a trainee, while performing a grasping and pick-place task on Neuro-Endo-Trainer. The activity was divided into sub-tasks using Mixture of Gaussian based background subtraction and Tracking Learning Detection algorithms. The kinematic analysis of the tool-tip trajectory was used to provide the synopsis of activity as feedback to the trainee for self-improvement.