20 July 2023 in IEEE Transactions on Medical Imaging
Magnetic particle imaging (MPI) is an emerging technique for determining magnetic nanoparticle distributions in biological tissues. Although system-matrix (SM)-based image reconstruction offers higher image quality than the X-space-based approach, the SM calibration measurement is time-consuming. Additionally, the SM should be recalibrated if the tracer’s characteristics or the magnetic field environment change, and repeated SM measurement further increase the required labor and time. Therefore, fast SM calibration is essential for MPI. Existing calibration methods commonly treat each row of the SM as independent of the others, but the rows are inherently related through the coil channel and frequency index. As these two elements can be regarded as additional multimodal information, we leverage the transformer architecture with a self-attention mechanism to encode them. Although the transformer has shown superiority in multimodal fusion learning across several fields, its high complexity may lead to overfitting when labeled data are scarce. Compared with labeled SM (i.e., full size), low-resolution SM data can be easily obtained, and fully using such data may alleviate overfitting. Accordingly, we propose a pseudo-label-based progressive pretraining strategy to leverage unlabeled data. Our method outperforms existing calibration methods on a public real-world OpenMPI dataset and simulation dataset. Moreover, our method improves the resolution of two in-house MPI scanners without requiring full-size SM measurements. Ablation studies confirm the contributions of modeling SM inter-row relations and the proposed pretraining strategy.
30 October 2023 in IEEE Transactions on Instrumentation and Measurement
Magnetic Particle Imaging (MPI) is an innovative molecular imaging technique with remarkable sensitivity and temporal-spatial resolution. It employs superparamagnetic iron oxide nanoparticles (SPIONs) as tracers to precisely locate lesions in quantitative imaging. In practical, the induced signal of the receiver coil contains both the SPIONs magnetization signal and the excitation feed-through signal. Due to the high amplitude of the latter, extracting the SPIONs signal from the induced signal is a challenging task. In this study, a two-stage compensation strategy was proposed to suppress excitation feed-through signal. Firstly, we used a three-stage gradiometer coil to suppress part of the feed-through signal. Secondly, different from the using of band-stop filters in most previous studies, we proposed a modulation compensation strategy that the received signal from the first stage and a modulation signal were input to the differential circuit at the same time, and the feed-through signal can be suppressed by actively adjusting the modulation signal. In addition, we presented a three-dimensional (3D) MPI system with a simple and effective structure. Permanent magnets were used to generate gradient fields and the two-stage compensation strategy was employed at the receiving chain. Experimental results showed that the proposed compensation strategy can obviously suppress the excitation feed-through signal, which allows to achieve a high resolution and sensitivity imaging with the proposed 3D MPI system.
6 February 2025 in IEEE Transactions on Instrumentation and Measurement
Magnetic particle imaging (MPI) has emerged as a promising medical imaging technique known for its high sensitivity and high imaging speed, making real-time, in vivo imaging feasible. However, existing MPI systems often require multiple repetition measurements for signal denoising. Few repetitions may result in low-quality images with increased noise, whereas many repetitions compromise temporal resolution and may introduce significant motion artifacts in dynamic imaging. Therefore, to fully exploit the advantages of MPI in real-time imaging, it is crucial to reduce the repetition number while maintaining high-quality images. In this study, we introduced a novel deep-learning (DL)-based approach, the content-aware distillation network (CAD-Net), for accelerated MPI. The method reconstructs high-quality images by denoising noisy images, typically acquired with a limited number of repetitions (tens of milliseconds). CAD-Net incorporates a proposed multiscale content-aware (MCA) block to accurately model noise distribution and enhance denoising performance. In addition, we proposed an activation-mask-based distillation strategy to reduce model processing time, particularly important for real-time imaging. Evaluation on a public real-world dataset, OpenMPI, and a simulation dataset, proved that CAD-Net outperformed existing methods in denoising performance and model efficiency. Compared to traditional methods based on multiple measurements, CAD-Net increased the frames per second (FPS) metric by approximately 70 times. Experiments on in-house data demonstrated the applicability of CAD-Net in MPI denoising in in vitro and in vivo imaging. CAD-Net improved image quality in real-time denoising with only a marginal increase in time cost. The code and data will be available at: https://github.com/shigen-StoneRoot/CAD-Net.git.
22 October 2025 in Physics in Medicine & Biology
Objective. This study aims to propose and validate a novel electrically controlled field-free line (FFL) magnetic particle imaging (MPI) system to address several aspects of existing electronically rotated FFL-MPI designs, including limitations in gradient enhancement, structural complexity of the drive system, and coil coupling effects. Methods . We employ a dynamic ring-shaped magnetic-field-converging gradient array, consisting of multiple pairs of electromagnets symmetrically arranged along the radial and axial directions. This configuration ensures that the magnetic field direction of the generated FFL remains consistently perpendicular to both the gradient direction and the imaging plane. Tomographic imaging uses only one set of drive coils arranged orthogonally to the gradient coils. Three-dimensional FFL scanning is realized by dynamically modulating the current phase of the radial coil pairs in conjunction with differential current control of the axial coil pairs. In addition, we conduct electromagnetic and image reconstruction simulations to evaluate the FFL generation characteristics and reconstruction performance under magnetic configurations with different numbers of pole pairs. Results . Simulation results demonstrate that the proposed system can achieve efficient and stable FFL rotation and axial translation, supporting rapid 3D tomographic scanning. In addition, we systematically analyzed how different pole-pair configurations affect the quality of the generated FFL and the resulting image resolution. These findings offer concrete guidance on how pole-pair scaling influences gradient strength, field uniformity, and system complexity. Significance . The proposed MagRing-MPI system enhances magnetic field gradients and imaging quality, simplifies the drive-coil configuration to reduce system complexity, and minimizes electromagnetic coupling and feedthrough effects. These improvements provide a promising foundation for the development of scalable and high-performance MPI systems.
18 July 2024 in Applied Thermal Engineering