PhD student position in Medical Image Analysis

3/31552
label Burse autorenew 2025-09-29, 17:01 history_edu Maria Dumitru
At the Department of Signals and Systems, we conduct world-leading research in biomedical engineering, antennas, signal processing, image analysis, control, automation, mechatronics and communication systems. Our research deals to a large extent with the modeling and development of efficient systems for extracting and processing information. Systems our researchers deal with include for instance e-Health, hearing aids, robotics, power chains, and mobile telephony.

The department has about 120 employees, divided into three research divisions and one administrative unit. A majority of our activities are gathered at campus Johanneberg, except for some research in medical engineering which is done at Sahlgrenska and an education unit at campus Lindholmen. The department offers more than 70 courses, of which are most included in the Masters Programs; ”Biomedical Engineering”, ”Systems, Control and Mechatronics”, and ”Communication Engineering”.



Information about the research group
In close collaboration with MedTech West, a new research group in medical image analysis is in the process of being established. This position is in effect one out of several recruitments to back this strategic effort. The focus of the group is on the development of new and more effective medical imaging methods and systems for visualization, support and diagnostics. The main research problems include mathematical theory and algorithms for inverse problems such as reconstruction, segmentation and registration. Construction of complete prototype systems for clinical usage is also one important research output.

Information about the research project
Locating and segmenting anatomical structures such as the heart, vertebrae, or different regions of the brain in a three-dimensional image is an important step for many clinical applications, including visualization, surgical planning, and radiation therapy dose prediction. It is also an important tool for obtaining measures that can be used to determine the risk of future disease.

Our research is focused on mathematical tools appropriate for the challenges of these problems. Two examples from our current research are tractable optimization methods for Markov Random Fields (MRFs) and robust model estimation. MRFs have proven to be a very useful modeling tool for medical image segmentation. However, for complex MRF models, the inference problem is very demanding. We address this problem by building a framework based on submodular relaxations.

By using guaranteed approximation algorithms we hope to achieve a golden mean between the quality of the computed solution and tractability. MRFs are high-dimensional models that are good at capturing local appearance. At the other end of the scale we find low-dimensional geometric models that are well suited to model global biological shape variations and transformations. To apply such models successfully, it is necessary to cope with abnormalities and outliers in the data. A goal for this project is to develop exact algorithms for robust model estimation, but also approximation algorithms suitable for higher dimensions and large-scale problems.