Methodological Categorization of Vessel Registration Techniques

Advisor: Nassir Navab
Supervision by: Stefanie Demirci,Maximilian Baust

Radial Reingold-Tilford Tree in d3.js

Overview

Medical image registration is a crucial part of computer aided diagnosis and interventions, and continuously facilitates the replacement of conventional open surgery by minimally invasive procedures. Due to their good visibility when contrasted, many image alignment methods are guided by vascualr structures. A large variety of vessel registration algorithms in various anatomical regions have been introduces over the last decades. It is the main goal of this thesis to collect relevant publications and classify these according to wisely chosen categories. Results are to be visualized in a web-based interactive tool allowing users to view relevant data from vaarious perspectives and perform minor data mining on it.

Tasks

• Gathering of state-of-the-art literature on vessel registration algorithms
• Methodological categorization of these
• Implementation of web-based interactive visualization tool

Requirements

• Advanced, practical knowledge in at least one object-oriented programming language is mandatory.
• Experience in JavaScript^? and/or R (RStudio, Shiny, d3js) is recommended.
• Good organizational skill is beneficial.

Contact

If you are interested please send your updated CV (including practical project experience) to Stefanie Demirci.