Computed Tomography Reconstruction Using Generative Energy-Based Priors

Martin Zach, Erich Kobler, Thomas Pock

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review


In the past decades, Computed Tomography (CT) has established itself as one of the most important imaging techniques in medicine. Today, the applicability of CT is only limited by the deposited radiation dose, reduction of which manifests in noisy or incomplete measurements. Thus, the need for robust reconstruction algorithms arises. In this work, we learn a parametric regularizer with a global receptive field by maximizing it’s likelihood on reference CT data. Due to this
unsupervised learning strategy, our trained regularizer truly represents higher-level domain statistics, which we empirically demonstrate by synthesizing CT images. Moreover, this regularizer can easily be applied to different CT reconstruction problems by embedding it in a variational framework, which
increases flexibility and interpretability compared to feedforward learning-based approaches. In addition, the accompanying probabilistic perspective enables experts to explore the full posterior distribution and may quantify uncertainty
of the reconstruction approach. We apply the regularizer to limited-angle and few-view CT reconstruction problems, where it outperforms traditional reconstruction algorithms by a large margin.
Original languageEnglish
Title of host publicationProceedings of the OAGM Workshop 2021
Subtitle of host publicationComputer Vision and Pattern Analysis Across Domains
EditorsMarkus Seidl, Matthias Zeppelzauer, Peter M. Roth
Place of PublicationGraz
PublisherVerlag der Technischen Universität Graz
Number of pages7
ISBN (Electronic)978-3-85125-869-1
Publication statusPublished - Dec 2021
Event44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains: ÖAGM 2021 - University of Applied Sciences St. Pölten, abgesagt, Austria
Duration: 24 Nov 202125 Nov 2021


Conference44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains


Dive into the research topics of 'Computed Tomography Reconstruction Using Generative Energy-Based Priors'. Together they form a unique fingerprint.

Cite this