MaIcaPet

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Master Thesis: Independent Component Analysis (ICA) of Positron Emission Tomography (PET) Data

Thesis by: Open
Advisors: Nassir Navab
Supervision by: Dr. Igor Yakushev

PDF of the thesis call

Topic

Positron emission tomography (PET) is a medical technique that generates functional images of the human body including the brain. Recently, we successfully applied a hypothesis-free analytical technique known as independent component analysis (ICA) to identify covariance patterns in PET data (Yakushev et al., 2013). ICA is an advanced computational method for separating a multivariate signal into additive components (Hyvärinen and Oja, 2000). In the above study, we applied software called Group ICA Toolbox (GIFT, http://mialab.mrn.org/software/gift/index.html) that is actually developed for another imaging technique (fMRI). As compared to that technique, PET provides a different kind of signal and has specific sources of variance. Thus, the aim of this work is to test performance of ICA in PET data, by adjusting the above software package (i.e. scripts) to the needs of PET.

  • The project can be started at any time and can potentially be extended to a master thesis.
  • Work load: 10-15 hours/week
  • Fee: 400 EUR
  • Email addresses of former students (for references) can be obtained upon request, at any time and without obligation

Environment

We offer an intensive supervision, but initiative is very welcome. Working environment will be provided at the Dept. of Nuclear Medicine at the Klinikum rechts der Isar (Ismaninger Str. 22, 81675 München).

Requirements

The student should be interested in medical imaging and image processing. Knowledge of Matlab is required. A strong mathematical background in linear algebra is advantageous.

Supervision / contacts

This project is jointly proposed between the Chair for Computer Aided Medical Procedures (Prof. Nassir Navab, I16, Department of Informatics, TUM) and the Dept. of Nuclear Medicine (Prof. Markus Schwaiger, Klinikum rechts der Isar, TUM).

Thesis advisor: Prof. Nassir Navab Supervisor: Dr. Igor Yakushev Contact: Igor Yakushev, igor.yakushev@lrz.tum.de or 089-4140-2964 (after 3 p.m.)

Students.ProjectForm
Title: Independent Component Analysis of Positron Emission Tomography Data
Abstract: Positron emission tomography (PET) is a medical technique that generates functional images of the human body including the brain. Typically, covariance in brain PET data is investigated using so called seed-based correlation approach. I.e., values from one brain region are correlated with values from other brain regions or throughout the brain. Thus, this method is limited by the need for hypothesis about regions to be correlated. Recently, we successfully applied a hypothesis-free analytical technique known as independent component analysis (ICA) to identify covariance patterns in PET data (Yakushev et al., submitted). ICA is an advanced computational method for separating a multivariate signal into additive components (Hyvärinen and Oja, 2000). In the above study, we applied software called Group ICA Toolbox (GIFT, http://mialab.mrn.org/software/gift/index.html) that is actually developed for another imaging technique. However, PET provides a different kind of signal and has specific sources of variance. Thus, the ultimate aim of this work is to evaluate performance of ICA in PET data. The following research questions should be addressed in a series of simulation experiments optimal number of components, reproducibility of the algorithm. Ideally, the algorithm should be implemented in as a user-friendly image analysis tool.
Student:  
Director: Nassir Navab
Supervisor: Dr. Igor Yakushev
Type: Master Thesis
Area: Medical Imaging
Status: finished
Start:  
Finish:  
Thesis (optional):  
Picture:  


Edit | Attach | Refresh | Diffs | More | Revision r1.6 - 14 May 2013 - 07:34 - MehmetYigitsoy