Fast Trajectory-Independent Model-Based Reconstruction Algorithm for Multi-Dimensional Magnetic Particle Imaging

2025-05-28

AI Summary

To address the bottlenecks of slow reconstruction speed and reliance on specific scanning trajectories (e.g., Lissajous) in magnetic particle imaging (MPI), this work proposes the first trajectory-agnostic, model-based reconstruction algorithm. Methodologically, we construct a universal forward operator using Chebyshev polynomials—eliminating dependence on calibration measurements or trajectory-specific modeling—and integrate a zero-shot Plug-and-Play framework that jointly leverages automatic noise estimation and a natural-image pre-trained CNN denoiser, requiring no MPI-specific fine-tuning. We validate the method on a public 2D MPI dataset and on in-house high-frequency excitation/undersampled data. Results demonstrate robust reconstruction quality, strong generalizability across diverse trajectories and acquisition settings, significantly improved computational efficiency, and enhanced flexibility. This establishes a new benchmark for general-purpose MPI reconstruction.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Feature Construction/Reformulation
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Magnetic Particle Imaging (MPI) is a promising tomographic technique for visualizing the spatio-temporal distribution of superparamagnetic nanoparticles, with applications ranging from cancer detection to real-time cardiovascular monitoring. Traditional MPI reconstruction relies on either time-consuming calibration (measured system matrix) or model-based simulation of the forward operator. Recent developments have shown the applicability of Chebyshev polynomials to multi-dimensional Lissajous Field-Free Point (FFP) scans. This method is bound to the particular choice of sinusoidal scanning trajectories. In this paper, we present the first reconstruction on real 2D MPI data with a trajectory-independent model-based MPI reconstruction algorithm. We further develop the zero-shot Plug-and-Play (PnP) algorithm of the authors -- with automatic noise level estimation -- to address the present deconvolution problem, leveraging a state-of-the-art denoiser trained on natural images without retraining on MPI-specific data. We evaluate our method on the publicly available 2D FFP MPI dataset ``MPIdata: Equilibrium Model with Anisotropy", featuring scans of six phantoms acquired using a Bruker preclinical scanner. Moreover, we show reconstruction performed on custom data on a 2D scanner with additional high-frequency excitation field and partial data. Our results demonstrate strong reconstruction capabilities across different scanning scenarios -- setting a precedent for general-purpose, flexible model-based MPI reconstruction.

Problem

• Develop trajectory-independent model-based MPI reconstruction algorithm
• Apply zero-shot Plug-and-Play algorithm for deconvolution
• Evaluate reconstruction on diverse 2D MPI datasets

Innovation

• Trajectory-independent model-based MPI reconstruction
• Zero-shot Plug-and-Play algorithm
• Automatic noise level estimation