Video Object Tracking and Analysis for Computer Assisted Surgery

TL;DR

This paper presents a real-time video analysis system for tracking the position and orientation of surgical drills during pedicle screw insertion, reducing radiation exposure and improving surgical navigation.

Contribution

It introduces a pattern recognition method using geometric features to accurately determine drill position and orientation from video, enabling real-time surgical guidance.

Findings

Achieved accurate real-time drill tracking

Reduced reliance on X-ray fluoroscopy

Enhanced surgical navigation with overlay graphics

Abstract

Pedicle screw insertion technique has made revolution in the surgical treatment of spinal fractures and spinal disorders. Although X- ray fluoroscopy based navigation is popular, there is risk of prolonged exposure to X- ray radiation. Systems that have lower radiation risk are generally quite expensive. The position and orientation of the drill is clinically very important in pedicle screw fixation. In this paper, the position and orientation of the marker on the drill is determined using pattern recognition based methods, using geometric features, obtained from the input video sequence taken from CCD camera. A search is then performed on the video frames after preprocessing, to obtain the exact position and orientation of the drill. Animated graphics, showing the instantaneous position and orientation of the drill is then overlaid on the processed video for real time drill control and navigation.