HoloNav: HoloLens as a Surgical Navigation System

Detecting optical reflective spheres using YOLOv5 and the Hololens' grayscale cameras

Bachelor Thesis (2022)
Author(s)

E.X. Tan (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Ricardo Marroquim – Mentor (TU Delft - Computer Graphics and Visualisation)

Mohamed Benmahdjoub – Mentor (Erasmus MC)

P. Ambrosini – Mentor (TU Delft - Computer Graphics and Visualisation)

A. Hanjalic – Graduation committee member (TU Delft - Intelligent Systems)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2022 Ee Xuan Tan
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 Ee Xuan Tan
Graduation Date
22-06-2022
Awarding Institution
Delft University of Technology
Project
['CSE3000 Research Project']
Programme
['Computer Science and Engineering']
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Surgical navigation is a tool that surgeons rely on everyday to perform accurate surgeries all over the world. However, this technology requires good hand-eye coordination and a high level of concentration. HoloNav is a project that inquires to see if using the HoloLens and augmented reality can replace the current surgical navigation methods. To do so, the HoloLens must be able to identify the patient and the location of the surgery instruments, which uses optical reflective spheres. This study focuses on using the grayscale cameras of the HoloLens and a deep learning algorithm YOLOv5 to test if it is possible to precisely detect optical reflective spheres. 3 models were trained with two different data sets, where the results show that the model trained on a data set would perform well on the validation set. However, they would perform far worse when exposed to a data set it was not trained on.

Files

HoloNav_Ee_Xuan_Tan.pdf
(pdf | 1.52 Mb)
License info not available