transferGWAS: GWAS of images using deep transfer learning.

Journal: Bioinformatics (Oxford, England)
Published Date: Jul 11, 2022

Abstract

MOTIVATION: Medical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS, a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations.

Authors

  • Matthias Kirchler
    Digital Health-Machine Learning Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam, 14482 Potsdam, Germany.
  • Stefan Konigorski
    Digital Health & Machine Learning Research Group, Hasso Plattner Institut for Digital Engineering, Potsdam, Germany; Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, USA.
  • Matthias Norden
    Digital Health & Personalized Medicine Research Group, Digital Health Center, Hasso Plattner Institute, University of Potsdam, 14482 Potsdam, Germany.
  • Christian Meltendorf
    Department of Electrical Engineering - Mechatronics - Optometry, Beuth University of Applied Sciences Berlin, 13353 Berlin, Germany.
  • Marius Kloft
    Department of Computer Science, Humboldt University of Berlin, Berlin, Germany.
  • Claudia Schurmann
    Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.
  • Christoph Lippert

Keywords

External Resources

Popular Topics
Recent Journals