International Journal on Magnetic Particle Imaging IJMPI
Vol. 10 No. 1 Suppl 1 (2024): Int J Mag Part Imag
https://doi.org/10.18416/IJMPI.2024.2403010

Proceedings Articles

Extension of the Kaczmarz algorithm with a deep plug-and-play regularizer

Main Article Content

Artyom Tsanda (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany), Paul Jürß (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany), Niklas Hackelberg (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany), Mirco Grosser (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany), Martin Möddel (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany), Tobias Knopp (Section for Biomedical Imaging, University Medical Center Hamburg-Eppendorf, Hamburg, Germany; Institute for Biomedical Imaging, Hamburg University of Technology, Hamburg, Germany)

Copyright (c) 2024 Artyom Tsanda, Paul Jürß, Niklas Hackelberg, Mirco Grosser, Martin Möddel, Tobias Knopp

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Abstract

The Kaczmarz algorithm is widely used for image reconstruction in magnetic particle imaging (MPI) because it converges rapidly and often provides good image quality even after a few iterations. It is often combined with Tikhonov regularization to cope with noisy measurements and the ill-posed nature of the imaging problem. In this abstract, we propose to combine the Kaczmarz method with a plug-and-play (PnP) denoiser for regularization, which can provide more specific prior knowledge than handcrafted priors. Using measurement data of a spiral phantom, we show that Kaczmarz-PnP yields excellent image quality, while speeding up the already fast convergence. Since the PnP denoiser is not coupled to the imaging operator, the Kaczmarz-PnP method is very generic and can be used for image reconstruction independently of the measurement sequence and MPI tracer type.

Article Details