Learned Discrepancy Reconstruction and Benchmark Dataset for Magnetic Particle Imaging

TL;DR

This paper introduces a novel learned discrepancy reconstruction method for MPI that explicitly models complex noise, along with a new MPI-MNIST dataset for benchmarking, leading to improved image reconstruction quality.

Contribution

The paper presents a new learning-based reconstruction approach with an invertible neural network for MPI, and introduces a large, realistic MPI-MNIST dataset for benchmarking.

Findings

Significant improvement in reconstruction quality over classical methods.

Effective handling of non-Gaussian noise in MPI.

The MPI-MNIST dataset enables realistic algorithm testing.

Abstract

Magnetic Particle Imaging (MPI) is an emerging imaging modality based on the magnetic response of superparamagnetic iron oxide nanoparticles to achieve high-resolution and real-time imaging without harmful radiation. One key challenge in the MPI image reconstruction task arises from its underlying noise model, which does not fulfill the implicit Gaussian assumptions that are made when applying traditional reconstruction approaches. To address this challenge, we introduce the Learned Discrepancy Approach, a novel learning-based reconstruction method for inverse problems that includes a learned discrepancy function. It enhances traditional techniques by incorporating an invertible neural network to explicitly model problem-specific noise distributions. This approach does not rely on implicit Gaussian noise assumptions, making it especially suited to handle the sophisticated noise model in MPI and also applicable to other inverse problems. To further advance MPI reconstruction techniques, we introduce the MPI-MNIST dataset - a large collection of simulated MPI measurements derived from the MNIST dataset of handwritten digits. The dataset includes noise-perturbed measurements generated from state-of-the-art model-based system matrices and measurements of a preclinical MPI scanner device. This provides a realistic and flexible environment for algorithm testing. Validated against the MPI-MNIST dataset, our method demonstrates significant improvements in reconstruction quality in terms of structural similarity when compared to classical reconstruction techniques.