Other Half-time control Fabian Sinzinger
Title: Geometrical Deep Learning for Medical Image Processing
Principal Supervisor
Associate Professor Rodrigo Moreno, Division of Biomedical Imaging, Royal Institute of Technology
Co-supervisors
Associate Professor Joana Pereira, Department of Clinical Neuroscience, Karolinska Institutet
Professor Örjan Smedby, Division of Biomedical Imaging, Royal Institute of Technology
Half-time review board
Professor Michael Felsberg, Department of Electrical Engineering, Linköping University
Professor Joakim Lindblad, Department of Information Technology, Uppsala University
Professor Tomas Bjerner, Department of Health, Medicine and Caring Sciences, Linköping University
Brief description
In recent years, general deep learning-based methods have been vastly successful for medical image processing problems. This novel, data-driven methodology introduces high demands on the availability of big datasets for model training, which is an issue in many medical image processing tasks. Geometric deep learning (GDL) is a family of deep learning methods that utilise mathematical concepts of structures, symmetries, and in- or equivariances. Those intrinsic geometric properties of the data and the underlying domains are used here to build problem-specific models. This PhD project demonstrates how GDL can be applied to concrete medical image processing problems. Moreover, the project shows that GDL is a viable alternative for problems with small training datasets. The problems addressed in this thesis include trabecular bone stiffness estimation from micro-CT data, CT-based lung cancer survival rate prediction, tractography extracted from diffusion MRI data, and structural brain connectivity.