X-ray Depth Map Reconstruction for Improved Interventional Visualization

Advisor: Nassir Navab
Supervision by: Stefanie Demirci

Overview

Most minimally-invasive interventions are performed under continuous 2D X-ray imaging. However, recovering the 3D information is crucial for physicians to perform safer navigation and precise surgical instrument positioning. In the current clinical workflow, this requirement yields an increase in radiation and use of contrast agent whenever vessels need to be made visible. Improved and adapted visualization of X-Ray images has mostly been addressed in terms of 2D-3D image registration. Yet, the output of such algorithms is a projection matrix that, by itself, does not yield any meaningful visualization. It is the major aim of this master project to yield depth hints for improved interventional visualization. Having training datasets containing each an X-ray image and corresponding depth map, available, an X-ray depth model is to be built that is subsequently applied to any new incoming X-ray image to reconstruct corresponding depth hints.

It is the main task of the student to reconstruct depth from X-ray images. This includes study of available literature and algorithms, creation of datasets for depth cues analysis, implementation of a test framework, and extensive validation on available datasets. The code has to be integrated within our new software framwork CAMPVis in order to improve the performance of the method for practical application. Finally, algorithms are to be correctly validated within different studies in cooperation with our colleagues at the university hospital lab NARVIS as well as with our partner physicians.

You should have advanced knowledge of machine learning preferrably Markov Random Fields and Dictionary Learning as well as profound knowledge of C++ and OpenGL^? programming and versioning using GitLab^?. It would be beneficial for the experiment planning if you are able to interact with people from different disciplines smoothly.

If you are interested please send your updated CV (including practical project experience) as well as a sample of C++ code that you have already implemented, to Stefanie Demirci.

Tasks

• Gathering of state-of-the-art algorithms existing within CV community
• Adaptation and implementation of existing algorithm
• Integration into CAMPVis
• Validation of method on synthetic test data and real patient data.

Requirements

• Advanced knowledge in machine learning, preferrably Markov Random Fields and Dictionary Learning
• A profound knowledge of C++ and OpenGL^? is mandatory.
• experience using GitLab^? is recommended.
• Interest in medical applications and multidisciplinary work is required.
• Good organizational skill is beneficial.