Postdoctoral Research Fellow in Machine Learning

The position

An exciting postdoctoral position in method development for spatio-temporal medical data is available in the UiT Machine Learning Group at the Department of Physics and Technology. 

• Goal: Develop new deep learning algorithms for spatio-temporal medical image analysis with particular focus on learning from limited labelled data.
• Start date: Fall 2026 
• Duration: The appointment is for 3 years

It is a prerequisite that the applicant can carry out the project over the full course of the employment period. No person may hold more than one fixed term position as a Postdoctoral Research Fellow at the same institution.

The workplace is at UiT in Tromsø. You must be able to start in the position within 6 months after receiving the offer. 

The position's field of research 

The position is part of a UiT grant that focuses on modeling spatio-temporal medical image analysis with a particular focus on learning from limited labelled data. Here you will be a part of the UiT Machine Learning Group and will also be affiliated with the Center for Research-based Innovation Visual Intelligence. 

In this postdoctoral position you will be taking an active role in the group's research on developing novel machine learning/computer vision methodology. The focus of this project will be on the development of deep learning methodology for spatio-temporal medical image analysis, that is medical images that evolve over time, with emphasis on dynamic PET imagery and ultrasound. A special focus will be given to learning from limited labeled data (e.g. few-shot and self-supervised learning and clustering). The position will be part of the already ongoing effort to design new deep learning methodology for spatio-temporal medical image analysis [1, 2] and fundamental research within learning from limited labels [3,4]..

• [1] Salomonsen, C. "A robust and versatile deep learning model for prediction of the arterial input function in dynamic small animal [18F]FDG PET imaging." EJNMMI Research, 2026.
• [2] Thomas, S. "EchoNarrator: Generating natural text explanations for ejection fraction predictions." Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, 2024.
• [3] Trosten, D. J. "Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-shot Learning with Hyperspherical Embeddings." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023.
• [4] Wang, J. "AdaptCMVC: Robust Adaption to Incremental Views in Continual Multi-view Clustering." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025.