Bachelor thesis: Meta-Learning of Regularization Parameters in X-ray Computed Tomography
Project by: Stefan Haninger
Advisor:
Tobias Lasser
Supervision by:
Shadi Albarqouni
Abstract
Medical imaging modalities such as X-ray Computed Tomography (X-ray CT) have been the basis of accurate diagnosis in clinical practice for decades, one particular example being the detection of tumors. But medical imaging also plays a central role during the therapy, for example when planning complex surgeries or when planning and monitoring radiation therapy treatments.
Tasks
Regularization in iterative methods for solving the inverse problem in X-ray Computed Tomography (CT) is a popular technique in order to produce more stable and desirable results. A common difficulty, however, is the selection of regularization parameters, as there is no efficient generic method to determine those parameters. Hence, the aim of this project is the investigation of meta-learning techniques for the purpose of learning regularization parameters in CT. Training will first be performed on realistically simulated X-ray CT data, as this allows easy judgement of the testing performance. Optionally, the developed method will be tested on a set of real experimental data from our clinics.
Requirements
C++ programming skills, strong mathematical background.
Contact