You cannot apply for this job anymore (deadline was 31 Jul 2019).
Browse the current job offers or choose an item in the top navigation above.
Medical imaging data is often heterogeneous: it is generated using different scanners, different scanning protocols or different imaging modalities. Training machine learning models for medical diagnosis on such data from different domains can be difficult, but transfer learning can help: by transforming input from different domains to a common representation, datasets from multiple sources can be used at train and test time within a single classification model. Learning input transformations yielding improved diagnostic performance using multiple related sources of information is a challenging research task.
In this PhD project you will be developing and testing novel machine learning algorithms for transfer learning that can be applied to improve diagnosis of breast cancer from mammography image data from different sources. The large amount of data made available during this project will make it possible to use cutting-edge techniques based on deep learning.
The project involves three partners: the Radiology department of the Radboud university medical center, the Data Science group of the Institute for Computing and Information Sciences (iCIS), and a company called SigmaScreening. You will be working at iCIS and collaborate with other PhD candidates and postdoctoral researchers appointed by iCIS or one of the other project partners.
You have an MSc degree in computer science, mathematics, or a related discipline. You are open-minded, with a strong interest in multidisciplinary research and a solid background in machine learning, and you are highly motivated to perform scientific research. As you will be working in a multidisciplinary environment, you need to be flexible, communicative and able to work in a multidisciplinary team.
Are you interested in our excellent employment conditions?
Faculty of Science
The Data Science group’s research concerns the design and understanding of (probabilistic) machine learning methods, with a keen eye on applications in other scientific domains as well as industry. The Data Science section is part of the vibrant and rapidly expanding Institute for Computing and Information Sciences (iCIS). iCIS is consistently ranked as the top Computer Science department in the Netherlands (National Research Review of Computer Science 2002-2008 and 2009-2014).
We like to make it easy for you, sign in for these and other useful features: