• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Abschlussarbeit
  4. Bayesian Deep Learning for Medical Image Analysis and Diagnosis
 
  • Details
  • Full
Options
2020
  • Master Thesis

Titel

Bayesian Deep Learning for Medical Image Analysis and Diagnosis

Abstract
Despite being the de-facto standard for medical image segmentation, researchers have identified shortcomings of frequentist U-Nets such as overconfidence and poor out of- distribution generalization. Although their Bayesian counterpart has already been proposed, often these methods rely on the well-known Monte-Carlo Drop Out (MCDO) approximation. We move beyond the MCDO approximation and introduce a novel multi-headed Bayesian U-Net. The proposed approach combines the global exploration capabilities of deep ensembles with the out-of-distribution robustness of Variational Inference. An efficient training strategy, along with an expressive yet general design, ensures superior approximation of the true Bayesian posterior within a reasonable compute requirement. Further we thoroughly analyze different properties of our model and give insights on other prior and regularization techniques. We evaluate our approach on the publicly available BRATS2018 dataset.
ThesisNote
Darmstadt, TU, Master Thesis, 2020
Author(s)
Fuchs, Moritz
Advisor
Kuijper, Arjan
Fraunhofer-Institut für Graphische Datenverarbeitung IGD
Mukhopadhyay, Anirban
TU Darmstadt GRIS
Verlagsort
Darmstadt
Thumbnail Image
Language
Englisch
google-scholar
IGD
Tags
  • Lead Topic: Individua...

  • Research Line: Comput...

  • medical diagnosis

  • medical imaging

  • deep learning

  • machine learning

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022