In Partial Fulfillment of the Requirements for the Degree of Master of Science

Mohammad Mainul Islam

will defend his thesis

An Augmented Reality Application for Visualizing Anatomical Data

Abstract

Augmented Reality can be useful in medical science since visualization of a patient's internal organs is very important for any intervention. Traditional display technologies present images collected from CT, MRI or Ultrasound on a screen. However, aligning those images to a patient's body helps physicians decide the target of intervention. In this thesis, an iPad application is proposed which overlays 3D models of a patient's organs acquired using CT/MRI in the live video.

The process is divided into two parts: 1) 3D registration and 2) tracking. The registration consists of acquiring the 3D structure of patient's torso using a depth sensor and placing 3D models in the live video. This is accomplished by 3D point-to-point registration using the Iterative Closest Point (ICP) algorithm. The tracking keeps the 3D models aligned on patient's body based on the movement of iPad. This is accomplished using a technique called Simultaneous Localization and Mapping (SLAM), which maps the environment and estimates the camera pose continuously. Registration accuracy is measured based on experiments on different users of the application. The possibility of porting the application to head mounted displays or glasses is also explored.

Date: Tuesday, April 25, 2017
Time: 2:30 PM
Place: HBS 317
Advisor: Dr. Ioannis A. Kakadiaris

Faculty, students, and the general public are invited.