PhD Student (m/f/d, E13 TV-L; 65%) in Robust Machine Learning for Medical Image Analysis

Developing provable guarantees for the behaviour of neural networks on medical image data

Project description

The aim of this project is to develop rigorous, mathematically founded techniques to assess the robustness of automated medical image analysis systems and to investigate methods for providing provable guarantees of an algorithms performance under variations in the image acquisition process.

Medical imaging data frequently are subject to systematic changes in appearance originating from different acquisition parameters or different imaging hardware. Unfortunately, modern deep learning systems have been shown to be extremely sensitive to such variations, to the point where an algorithm trained with data from one hospital, may not work on data acquired at a different hospital. Formally assessing the robustness of machine learning methods, building more robust techniques, and providing guarantees for the performance of such techniques is of utmost importance for these methods to be eventually deployed in clinical practice. Thus, the successful candidate will contribute directly to one of the big unsolved problems hindering wide-spread adoption of AI technology for medical image analysis.

Who we are looking for

You are curious, enjoy analytical thinking and have a passion for science. You have a strong academic background, are motivated to do machine learning research, and have keen interest to solve real-world clinical problems. You hold a M.Sc. degree (or similar) in quantitative discipline such as machine learning, mathematics, statistics, physics, computer science, or similar fields. Ideally, you have prior experience with deep neural networks, and strong programming skills in Python.

Note: A B.Sc. degree is not sufficient to qualify for this position.

What we offer

This is a project jointly supervised by Dr. Christian Baumgartner and Prof. Matthias Hein, and thus is truly at the intersection between state-of-the-art machine learning and medical image analysis. The successful candidate will work at the Cluster of Excellence “Machine Learning - New Perspectives for Science” and will benefit from this vibrant research environment as well as from the activities and events organized by the cluster and associated institutions.

About Tübingen

Tübingen is a scenic university town on the Neckar river in South-Western Germany. The quality of life is exceptionally high and the atmosphere is diverse, inclusive, and most locals speak English. Tübingen offers excellent research opportunities due to the University, four Max Planck institutes, the University Hospital, and Europe’s largest AI research consortium. You can find out more about Tübingen here:

How to apply

Please send a cover letter, your CV, copies of your university transcripts, and any additional information to support your application to Christian Baumgartner ( If you have any questions about the position, please do not hesitate to contact Christian directly. The university seeks to raise the number of women in research and teaching and therefore urges qualified women scientists to apply for these positions. Equally qualified applicants with disabilities will be given preference. The employment will be carried out by the central administration of the University of Tübingen. Please submit your application by May 2nd, 2021.

Machine Learning in Medical Image Analysis
Machine Learning in Medical Image Analysis
Bridging the gap between AI and clinical practice