CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12304 > Article
Open Access Paper
17 October 2022 Learned cone-beam CT reconstruction using neural ordinary differential equations
Mareike Thies, Fabian Wagner, Mingxuan Gu, Lukas Folle, Lina Felsner, Andreas Maier
Author Affiliations +
Proceedings Volume 12304, 7th International Conference on Image Formation in X-Ray Computed Tomography; 1230409 (2022) https://doi.org/10.1117/12.2646442
Event: Seventh International Conference on Image Formation in X-Ray Computed Tomography (ICIFXCT 2022), 2022, Baltimore, United States
Abstract
Learned iterative reconstruction algorithms for inverse problems offer the flexibility to combine analytical knowledge about the problem with modules learned from data. This way, they achieve high reconstruction performance while ensuring consistency with the measured data. In computed tomography, extending such approaches from 2D fan-beam to 3D cone-beam data is challenging due to the prohibitively high GPU memory that would be needed to train such models. This paper proposes to use neural ordinary differential equations to solve the reconstruction problem in a residual formulation via numerical integration. For training, there is no need to backpropagate through several unrolled network blocks nor through the internals of the solver. Instead, the gradients are obtained very memory-efficiently in the neural ODE setting allowing for training on a single consumer graphics card. The method is able to reduce the root mean squared error by over 30% compared to the best performing classical iterative reconstruction algorithm and produces high quality cone-beam reconstructions even in a sparse view scenario.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Mareike Thies, Fabian Wagner, Mingxuan Gu, Lukas Folle, Lina Felsner, and Andreas Maier "Learned cone-beam CT reconstruction using neural ordinary differential equations", Proc. SPIE 12304, 7th International Conference on Image Formation in X-Ray Computed Tomography, 1230409 (17 October 2022); https://doi.org/10.1117/12.2646442
PROCEEDINGS
 7 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Reconstruction algorithms
CT reconstruction
Network architectures
Ordinary differential equations
Computed tomography
3D modeling
Inverse problems
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top