[191171] |
Title: Extension of the Kaczmarz algorithm with a deep plug-and-play regularizer. |
Written by: A. Tsanda, P. Jürß, N. Hackelberg, M. Grosser, M. Möddel, and T. Knopp |
in: <em>International Journal on Magnetic Particle Imaging</em>. Mar (2024). |
Volume: <strong>10</strong>. Number: (1 Suppl 1), |
on pages: 1-4 |
Chapter: |
Editor: |
Publisher: |
Series: |
Address: |
Edition: |
ISBN: |
how published: |
Organization: |
School: |
Institution: |
Type: |
DOI: 10.18416/IJMPI.2024.2403010 |
URL: https://www.journal.iwmpi.org/index.php/iwmpi/article/view/748 |
ARXIVID: |
PMID: |
Note: inproceedings, online reconstruction
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.