Image registration is an essential step in many clinical applications, such as image guidance, motion tracking, image segmentation, and treatment-response assessment. In radiotherapy, registration of the patient’s computed tomography (CT) and/or magnetic resonance (MR) images is key to enable accurate contour propagation and dose accumulation. Traditional algorithms for medical image registration often achieve good results but suffer from being very computationally expensive. Deep learning-based methods, on the other hand, can perform registration in a single shot, thereby enabling real-time registration. While demonstrating astonishing results in small-scale simulation studies, the use of deep learning to register high-resolution 3D images in clinical settings remains an open challenge.
This research project focuses on developing novel deep learning algorithms, data synthesis techniques and training strategies for medical image registration. During the project, you will be able to apply your developed techniques to solve relevant problems in adaptive radiotherapy. In this field, fast and accurate registration of cone-beam CT images is crucial to facilitate personalized radiotherapy treatments on a daily basis, in which the dose is delivered conformal to the tumor while increasing the sparing of healthy tissue.
The project will be supervised by Dr. Maureen van Eijnatten, Assistant Professor “Artificial Intelligence for Medical Imaging” at TU/e. During the project you will closely collaborate with clinicians and researchers of the University Medical Center Utrecht (Department of Radiotherapy). In addition, the project builds upon existing collaborations with the University of Cambridge (UK) and the Department of Radiology of Addenbrooke’s hospital in Cambridge. These collaborations also offer opportunities to spend some time abroad as a visiting researcher at the University of Cambridge.
The successful candidate will become a member of the Medical Image Analysis Group at the Department, headed by Prof. Josien Pluim. The group consists of around 20 enthusiastic researchers, working on both methodological and applied innovations. Research topics include image analysis, quantification and machine/deep learning for oncology, cardiology, neurology and histopathology, as well as high-field MR imaging and RF safety. The group has strong ties with the University Medical Center Utrecht (both in research and education) and Philips NL, but also collaborates with other clinical institutes and industry.
We are looking for candidates who have:
TU/e aims to increase diversity among its employees and encourages applications from under-represented groups; in particular, female scientists are encouraged to apply.
Do you recognize yourself in this profile and would you like to know more?
Please contact dr. Maureen van Eijnatten, m.a.j.m.v.eijnatten[at]tue.nl for questions regarding the academic content of the position.
For information about the employment conditions at TU/e see here or contact the
HR department, hrservices.gemini[at]tue.nl
Information about the research group: https://www.tue.nl/en/research/research-groups/medical-image-analysis/
For information about the Biomedical Engineering department at TU/e see https://www.tue.nl/en/university/departments/biomedical-engineering/
Please visit www.tue.nl/jobs to find out more about working at TU/e!
We invite you to submit a complete application by using the 'apply now'-button on this page.
The application should include a:
We look forward to your application and will screen it as soon as we have received it. Screening will continue until the position has been filled.