Geometric Constraints Enable Self-Supervised Sinogram Inpainting in Sparse-View Tomography

Wagner F, Thies M, Maul N, Pfaff L, Aust O, Pechmann S, Syben C, Maier A (2023)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Event location: Stony Brook University, NY, USA

URI: https://arxiv.org/pdf/2302.06436.pdf

DOI: 10.48550/arXiv.2302.06436

Open Access Link: https://arxiv.org/pdf/2302.06436.pdf

Abstract

The diagnostic quality of computed tomography (CT) scans is usually restricted by the induced patient dose, scan speed, and image quality. Sparse-angle tomographic scans reduce radiation exposure and accelerate data acquisition, but suffer from image artifacts and noise. Existing image processing algorithms can restore CT reconstruction quality but often require large training data sets or can not be used for truncated objects. This work presents a self-supervised projection inpainting method that allows optimizing missing projective views via gradient-based optimization. By reconstructing independent stacks of projection data, a self-supervised loss is calculated in the CT image domain and used to directly optimize projection image intensities to match the missing tomographic views constrained by the projection geometry. Our experiments on real X-ray microscope (XRM) tomographic mouse tibia bone scans show that our method improves reconstructions by 3.1-7.4%/7.7-17.6% in terms of PSNR/SSIM with respect to the interpolation baseline. Our approach is applicable as a flexible self-supervised projection inpainting tool for tomographic applications.

Authors with CRIS profile

Related research project(s)

Involved external institutions

Fraunhofer Development Center X-ray Technology (EZRT) Germany (DE) Fraunhofer-Institut für Keramische Technologien und Systeme (IKTS) Germany (DE)

How to cite

APA:

Wagner, F., Thies, M., Maul, N., Pfaff, L., Aust, O., Pechmann, S.,... Maier, A. (2023). Geometric Constraints Enable Self-Supervised Sinogram Inpainting in Sparse-View Tomography. In Proceedings of the 17th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine (Fully3D). Stony Brook University, NY, USA.

MLA:

Wagner, Fabian, et al. "Geometric Constraints Enable Self-Supervised Sinogram Inpainting in Sparse-View Tomography." Proceedings of the 17th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine (Fully3D), Stony Brook University, NY, USA 2023.

BibTeX: Download