A Deep Learning Architecture for Limited-Angle Computed Tomography Reconstruction

Kerstin Hammernik, Tobias Würfl, Thomas Pock, Andreas Maier

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


Limited-angle computed tomography suffers from missing data in the projection domain, which results in intensity inhomogeneities and streaking artifacts in the image domain. We address both challenges by a two-step deep learning architecture: First, we learn compensation weights that account for the missing data in the projection domain and correct for intensity changes. Second, we formulate an image restoration problem as a variational network to eliminate coherent streaking artifacts. We perform our experiments on realistic data and we achieve superior results for destreaking compared to state-of-the-art non-linear filtering methods in literature. We show that our approach eliminates the need for manual tuning and enables joint optimization of both correction schemes.
Original languageEnglish
Title of host publicationBildverarbeitung für die Medizin 2017
Subtitle of host publicationAlgorithmen - Systeme - Anwendungen. Proceedings des Workshops vom 12. bis 14. März 2017 in Heidelberg
PublisherSpringer Verlag Heidelberg
Publication statusPublished - 2017
EventBildverarbeitung für die Medizin 2017 - Heidelberg, Germany
Duration: 12 Mar 201714 Mar 2017

Publication series

NameInformatik aktuell
ISSN (Print)1431-472X


ConferenceBildverarbeitung für die Medizin 2017

Cite this