DomainAdaptSynthBrainTumor

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

THIS WEBPAGE IS DEPRECATED - please visit our new website

IDP/Guided research/M.Sc. thesis

Advisor: Ivan Ezhov
Supervision by: Bjoern Menze

Tasks

Majority of existing machine learning approaches demand abundancy of labeled data to boost the generalization capability. In the medical imaging field, the availability of such data remains limited. In this project, to mitigate the problem we will make use of recent advances in domain adaptation to learn a mapping between simulated and real images of brain tumors.

domainadapt.png
Courtesy of Jana Lipkova and myself

Requirements

  • Knowledge of deep learning and generative modeling.
  • Good programming skills in PyTorch? or TensorFlow?.

Contact

Ivan Ezhov



Edit | Attach | Refresh | Diffs | More | Revision r1.5 - 18 May 2019 - 10:26 - IvanEzhov