Vacancy: Deep learning patterns in chest CT scans

The Diagnostic Image Analysis Group (DIAG) of the Radboud University Medical Center, Nijmegen, is offering a PhD position.

Ild.png

Background

Modern CT scanners can make very high resolution 3D scans of the lungs in only a few seconds. CT scans of the lungs are crucial for the complex task of making a diagnosis in patients with interstitial lung disease (ILD). There are over 200 different ILDs and making the correct diagnosis is essential to apply the right treatment. Recently, new treatments have become available for several ILDs. Once patients receive these expensive treatments, CT scans are important to monitor the response to treatment, and make a decision on treatment duration.

Our group has a long experience with analysis of chest CT scans. We are currently increasingly using deep learning techniques, neural networks with many layers, to analyze CT scans. In this project we want to improve the classification and quantification of different texture patterns in chest CT scans with deep learning. From this pattern analysis, it should be possible to infer diagnosis of diseases, and measure or even predict response to treatment for patients with specific diseases. Temporal analysis of a series of CT scans acquired at different time points, e.g. months apart, of the same patient is part of the project. We want to use recurrent networks to analyze these series.

This project is part of a VICI project in which about 7 researchers are working on chest CT analysis, and you will also be part of a team of about 15 researchers using deep learning for analyzing a wide variety of medical imaging data. We work closely with Fraunhofer MEVIS, a number of smaller and larger companies, and several large hospitals specializing in lung disease.

Requirements

You should be a creative and enthusiastic researcher with an MSc degree in Computer Science, Physics, Engineering or Biomedical Sciences or similar, with a clear interest to develop image analysis algorithms and an affinity with medical topics. Experience with machine learning, deep learning, and image analysis is a pre. Good communication skills and expertise in software development, preferably in C++, are essential.

Terms of employment

You will be appointed as a PhD student with the standard salary and secondary conditions for PhD students in the Netherlands. Your performance will be evaluated after 1 year. If the evaluation is positive, the contract will be extended by 3 years. The research should result in a PhD thesis.

Organization

The Diagnostic Image Analysis Group (DIAG) is a research division of the Department of Radiology and Nuclear Medicine of the Radboud University Medical Center Nijmegen. Nijmegen is the oldest Dutch city with a rich history and one of the liveliest city centers in the Netherlands. Radboud University has over 17,000 students. Radboud UMC is a leading academic center for medical science, education and health care with over 8,500 staff and 3,000 students.

The focus of the Diagnostic Image Analysis group is the development and validation of novel methods in a broad range of medical imaging applications. Research topics include image analysis, image segmentation, machine learning, and the design of decision support systems. Application areas include breast imaging, prostate imaging, digital pathology, lung imaging, and retinal imaging. Key to the success of the group is close cooperation with clinicians. Currently the group consists of around 40 researchers.

Information

For more information please contact Bram van Ginneken by e-mail.

Application

Please apply by following this link. Only if this does not work, you can send applications as a single pdf file to bram.vanginneken@radboudumc.nl. In this pdf file the following should be included: CV, list of followed courses and grades, letter of motivation, and preferably a reprint of your Master thesis or any publications in English you have written.

This application will remain open until the position has been filled. Applications are processed immediately upon receipt.