Postdoctoral researcher on Project in Machine Learning for Medical Image Computing

The University of Luxembourg is an international research university with a distinctly multilingual and interdisciplinary character. The University was founded in 2003 and counts more than 6,700 students and more than 2,000 employees from around the world. The University’s faculties and interdisciplinary centres focus on research in the areas of Computer Science and ICT Security, Materials Science, European and International Law, Finance and Financial Innovation, Education, Contemporary and Digital History. In addition, the University focuses on cross-disciplinary research in the areas of Data Modelling and Simulation as well as Health and System Biomedicine. Times Higher Education ranks the University of Luxembourg #3 worldwide for its “international outlook,” #20 in the Young University Ranking 2021 and among the top 250 universities worldwide.

Within the University, the Luxembourg Centre for Systems Biomedicine (LCSB) is a highly interdisciplinary research centre (IC), integrating experimental biology and computational biology approaches in order to develop the foundation of a future predictive, preventive and personalized medicine.

Registraion website

Your Role...

Area: Towards robust clinical applications – addressing bias and confounders in AI models for medical image computing

Machine learning based medical image computing has seen immense progress in the last decade. However, the translation from bench to bed is hampered by confounders, i.e. (unknown) factors influencing targets as wells as predictors, leading to spurious associations and eventually poorly performing models at unseen data from a clinical domain.  

Therefore, methods addressing bias and confounders are needed towards more robust medical image computing.

Within this project, the Postdoctoral Researcher will work on solutions for detecting, analysing and mitigating confounder effects in ML models for medical image computing. Recent techniques including domain adversarial networks, domain unlearning and conventional transfer learning will be evaluated. Clinical applications will be focused but not limited to neurosurgery, including medical image computing for deep brain stimulation and brain tumours.

At our team we follow a leadership concept of promoting independent work, encouraging that Postdoctoral researchers contribute with own ideas and concepts to shape the project and mentor PhD students. We therefore expect that the Researcher actively contributes with its expertise to the training of our PhD students. Furthermore, a yearly written progress report is mandatory due to the funding of the position.

• PhD in the context of data science
• 
  
• Background in machine learning, in particular deep learning, and strong interest in interdisciplinary research
• 
  
• Experience / or strong interest in medical image analysis.
• 
  
• Experience utilizing GPU enabled High-Performance Computing environments is an asset
• 
  
• Experience with recent deep learning frameworks (e.g. Pytorch) programming languages (Python, Matlab) are considered to be an advantage
• 
  
• Autonomous self-starter with very strong organizational and analytic skills
• 
  
• Excellent communication, team-working and interpersonal skills
• 
  
• Enthusiasm and great commitment to research
• 
  
• Excellent command of English language

We are looking for highly motivated candidates who share our passion for research, are interested in acquiring new skills and wish to be part of an international interdisciplinary team.

• Contract Type: Fixed Term Contract 24 Month
• 
  
• Work Hours: Full Time 40.0 Hours per Week
• 
  
• Location: Belval
• 
  
• Earliest start date: January 2022
• 
  
• Job Reference: UOL04540

Applications (in English) should contain the following documents:

• Cover letter
• 
  
• A detailed curriculum vitae
• 
  
• Copy of PhD diploma
• 
  
• Name and addresses of referees
• 
  
• Providing reference letters is highly recommended

Early application is highly encouraged, as the applications will be processed upon reception. Please apply formally through the HR system. Applications by email will not be considered.

The University of Luxembourg embraces inclusion and diversity as key values. We are fully committed to removing any discriminatory barrier related to gender, and not only, in recruitment and career progression of our staff.

• Multilingual and international character. Modern institution with a personal atmosphere. Staff coming from 90 countries. Member of the “University of the Greater Region” (UniGR).
  

• A modern and dynamic university. High-quality equipment. Close ties to the business world and to the Luxembourg labour market. A unique urban site with excellent infrastructure.

• A partner for society and industry. Cooperation with European institutions, innovative companies, the Financial Centre and with numerous non-academic partners such as ministries, local governments, associations, NGOs …

• Find out more about the University

• Addresses, maps & routes to the various sites of the University

Contact for further information

Andreas Husch, PhD

[email protected]

About the research group

TheInterventional Neuroscience group is a highly translational research unit that transfers innovativeneurosurgical methods from bench to beside and back. Their main focus is applied computational science forclinical practice in Neurosurgery. Researchers and clinicians together develop methods that use artificial intelligence and machine learningalgorithms. Their in-house established tools are used in image-guided procedures and biomedical modelling inNeurosurgery and Systems Biomedicine. Recent application domains are Deep Brain Stimulation (Computational Imaging, Data Integration, Field Simulation), Brain Tumor Surgery (Raman Spectroscopy, ML based diagnostics), related Movement Disorders (Parkinson’s) as well as application of methods to adjacent domains (e.g. Lung Imaging in COVID-19).  The computational team of the group is working closely with the Systems Control Groupat LCSB.