The PhD project
Magnetic Resonance Imaging (MRI) is a powerful technique to visualize and quantify human anatomy and function, with the ultimate goal to support diagnosis and treatment of disease. In the early days of MRI, clinical users primarily interpreted the images visually, but nowadays more and more automatic image segmentation algorithms are used to derive the essential information.
The design of accurate and robust MR image segmentation algorithms is a very challenging task, due to the highly varying appearance of anatomical structure in the MR images. This variation can be caused by differences in the scan protocol (scanner parameter settings), but also by patient variations (e.g. differences in weight) and by scanner software and hardware variations.
The development, optimization, and validation of image segmentation algorithms is a tedious and time-consuming process. Especially novel model-based methods that use machine learning approaches, such as deep learning, require large training sets of annotated data. There is a clear need to develop MRI segmentation methods that are as much as possible insensitive to the specific MR image contrast (T1-weighted, T2-weighthed, etc.) and to patient and scanner variations. The development of such algorithms is the focus of this PhD project. Their availability would significantly reduce training and validation efforts and broaden the applicability in clinical practice.
The PhD research is funded by the highly prestigious and competitive Marie Curie Innovative Training Networks (ITN) fellowship program, in a project called 'Open Ground Truth Training Network (openGTN)', see the website openGTN.eu. You will work closely together with 2 other PhD researchers in openGTN, who will focus on generating ample simulated MR images of the brain, spine and heart, with ground truth segmentations, supplying you with data for training and testing of your algorithms.
The team
You will become part of the Medical Image Analysis group at the Department of Biomedical Engineering, Eindhoven University of Technology. The group consists of around 20 researchers, all working on the development of image analysis methodology as well as clinical applications. Collaborations with various hospitals and with industry ensure involvement of clinical experts, and hence a focus on clinically relevant topics. Through various (formal and less formal) meetings, the members of the group share ideas and work together in an enthusiastic and encouraging atmosphere. More information on the group can be found at
www.tue.nl/image .
The Department of Biomedical Engineering consists of a large number of research groups, clustered around three themes: (i) Chemical Biology, (ii) Biomechanics and Tissue Engineering and (iii) Biomedical Imaging and Modeling. The department offers research driven Bachelor and Masters programmes. The department has more than 1,000 students and up to 200 tenured and non-tenured employees.
For this Marie Curie ITN project, you will spend 50% of your time at Philips Research Hamburg, Germany (in the first three years), and you will also work for extended secondments (short externships) at the University Medical Center Utrecht, The Netherlands, Philips Healthcare, Best, The Netherlands, King's College London, United Kingdom, Deutsches Zentrum für Neurodegeneratieve Erkrankungen, Bonn, Germany, and Klinikum Rechts der Isar / Technical University, München, Germany. You will be academically supervised by prof. dr. Marcel Breeuwer (professor at TU/e and Principal Scientist at Philips Healthcare, project leader of openGTN) and prof. dr. Josien Pluim (head of the Medical Image Analysis department).
Your role and responsibilities
Your research will focus on inventing, implementing, optimizing and validating image analysis algorithms that are as much as possible independent of the applied specific MRI scanner and acquisition method. Your will publish your results at scientific conferences and in peer-reviewed scientific journals.