Abstract
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.
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 language | English |
---|---|
Title of host publication | Proceedings of the OAGM Workshop 2021 |
Subtitle of host publication | Computer Vision and Pattern Analysis Across Domains |
Editors | Markus Seidl, Matthias Zeppelzauer, Peter M. Roth |
Place of Publication | Graz |
Publisher | Verlag der Technischen Universität Graz |
Pages | 52-58 |
Number of pages | 7 |
ISBN (Electronic) | 978-3-85125-869-1 |
DOIs | |
Publication status | Published - Dec 2021 |
Event | 44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains: ÖAGM 2021 - University of Applied Sciences St. Pölten, abgesagt, Austria Duration: 24 Nov 2021 → 25 Nov 2021 |
Conference
Conference | 44th OAGM Workshop 2021: Computer Vision and Pattern Analysis Across Domains |
---|---|
Country/Territory | Austria |
City | abgesagt |
Period | 24/11/21 → 25/11/21 |