Options
Neural implicit representations for grid-agnostic MPI reconstructions
Citation Link: https://doi.org/10.15480/882.15005
Publikationstyp
Journal Article
Date Issued
2025
Sprache
English
TORE-DOI
Volume
11
Issue
1, Suppl 1
Article Number
2503058
Citation
International Journal on Magnetic Particle Imaging 11 (1, Suppl 1): 2503058 (2025)
Publisher DOI
Scopus ID
Publisher
Infinite Science Publishing
Peer Reviewed
true
Magnetic particle imaging (MPI) reconstructs the spatial distribution of magnetic nanoparticles on a fixed grid, the resolution of which is limited by the noise present in the system. This paper addresses the reconstruction problem while integrating single-image super-resolution for concentration maps. We introduce Neural Implicit Representations (NIR) as an image prior, enabling arbitrary grid size sampling after training. Experimental results using a spiral phantom measurement reveal that NIR-based reconstruction maintains image sharpness across diverse grid sizes, surpassing the two-stage Kaczmarz-ℓ2 reconstruction followed by bicubic up-sampling in preserving fine structural details. This technique has a potential for high-resolution MPI imaging without relying on extensive datasets.
DDC Class
616: Deseases
006: Special computer methods
530: Physics
Publication version
publishedVersion
Loading...
Name
813.pdf
Size
328.77 KB
Format
Adobe PDF