Prof. Dr. Christoph Lippert

Alexander Rakowski, M.Sc. Eng

Research Assistant, PhD Candidate

Research Interests

  • Disentangled Latent Space Representations
  • Generative Modeling
  • Deep Representation Learning

Research Projects

  • TransferGWAS on Brain Magnetic Resonance Imaging data: TransferGWAS is an approach to perform genome-wide association studies directly on full medical images. We apply the method on T1-weighted scans of human brains from the UK Biobank dataset. Research conducted together with Remo Monti and Matthias Kirchler.
  • Syreal (link): Imbalanced training data introduce important challenge into medical image analysis where a majority of the data belongs to a normal class and only few samples belong to abnormal classes. We propose to mitigate the class imbalance problem by introducing two generative adversarial network (GAN) architectures for class minority oversampling.