• Rashid, Tarik A.
• Abdullah, Salma
• Maharjan, Nitish

Abstract

Background and Aim<p>Image registration and alignment are the mainlimitations of augmented reality (AR)-based knee replacement surgery.This research aims to decrease the registration error, eliminateoutcomes that are trapped in local minima to improve the alignmentproblems, handle the occlusion and maximize the overlapping parts.</p>Methodology<p>Markerless image registration method was used forAR-based knee replacement surgery to guide and visualize the surgicaloperation. While weight least square algorithm was used to enhancestereo camera-based tracking by filling border occlusion inright-to-left direction and non-border occlusion from left-to-rightdirection.</p>Results<p>This study has improved video precision to0.57–0.61 mm alignment error. Furthermore, with the use of bidirectionalpoints, that is, forward and backward directional cloud point, theiteration on image registration was decreased. This has led to improvethe processing time as well. The processing time of video frames wasimproved to 7.4–11.74 frames per second.</p>Conclusions<p>It seems clear that this proposed system has focusedon overcoming the misalignment difficulty caused by the movement ofpatient and enhancing the AR visualization during knee replacementsurgery. The proposed system was reliable and favourable which helps ineliminating alignment error by ascertaining the optimal rigidtransformation between two cloud points and removing the outliers andnon-Gaussian noise. The proposed AR system helps in accuratevisualization and navigation of anatomy of knee such as femur, tibia,cartilage, blood vessels and so forth.</p>

Topics

• impedance spectroscopy