Work

Denoising the system matrix with deep neural networks for better MPI reconstructions

Year: 2024

Type: article

Abstract: Magnetic Particle Imaging commonly relies on the system matrix (SM) to reconstruct particle distributions, but noise during acquisition limits both its resolution and image quality. Traditionally, noise reduction requires averaging multiple measurements, which increases acquisition time. This paper presents a deep neural network trained on simulated SMs and measured background noise, which effectively generalizes to real-world data. The model recovers higher frequency components of the SM and serves as a general pre-processing step, enhancing image reconstruction quality while reducing the need for extensive averaging, thus accelerating SM acquisition.

Source: International journal on magnetic particle imaging

DOI: 10.15480/882.15007

Authors: Tsanda, Artyom, Scheffler, Konrad, Reiß, Sarah, Knopp, Tobias

Institutions: University Medical Center Hamburg-Eppendorf, Hamburg University of Technology, Fraunhofer-Einrichtung für Individualisierte Medizintechnik

Language: English

Topic: Characterization and Applications of Magnetic Nanoparticles

Subfield: Biomedical Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: diamond

Funder: Deutsche Forschungsgemeinschaft

OpenAlex ID: W6906841507

FWCI:

Cites:

Cited by:

Related to: