Objective. Magnetic particle imaging (MPI) is a new medical, non-destructive, imaging method for visualizing the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, spatial resolution is an important indicator of efficiency; traditional techniques for improving the spatial resolution may result in higher costs, lower sensitivity, or reduced contrast. Approach. Therefore, we propose a deep-learning approach to improve the spatial resolution of MPI by fusing a dual-sampling convolutional neural network (FDS-MPI). An end-to-end model is established to generate high-spatial-resolution images from low-spatial-resolution images, avoiding the aforementioned shortcomings. Main results. We evaluate the performance of the proposed FDS-MPI model through simulation and phantom experiments. The results demonstrate that the FDS-MPI model can improve the spatial resolution by a factor of two. Significance. This significant improvement in MPI could facilitate the preclinical application of medical imaging modalities in the future.

Objective. Magnetic particle imaging (MPI) is a novel imaging modality. It is crucial to acquire accurate localization of the superparamagnetic iron oxide nanoparticles distributions in MPI. However, the spatial resolution of unidirectional Cartesian trajectory MPI exhibits anisotropy, which blurs the boundaries of MPI images and makes precise localization difficult. In this paper, we propose an anisotropic edge-preserving network (AEP-net) to alleviate the anisotropic resolution of MPI. Methods. AEP-net resolve the resolution anisotropy by constructing an asymmertic convolution. To recover the edge information, we design the uncertainty region module. In addition, we evaluated the performance of the proposed AEP-net model by using simulations and experimental data. Results. The results show that the AEP-net model alleviates the anisotropy of the unidirectional Cartesian trajectory and preserves edge details in the MPI image. By comparing the visualization results and the metrics, we demonstrate that our method is superior to other methods. Significance. The proposed method produces accurate visualization in unidirectional Cartesian devices and promotes accurate quantization, which promote the biomedical applications using MPI.

Magnetic particle imaging (MPI) is a novel and emerging functional imaging technique that visualizes the spatial distribution of magnetic nanoparticles (MNPs). While the X-space method considers some important physical properties of MPI systems, it also neglects some phenomena, such as signals generated by MNPs outside (but close-to) the field-free region. Therefore, the X-space approach often results in blurring artifacts and incomplete edge information in native MPI images. In this study, we propose a spatial-frequency multi-scale transformer (SFM-Transformer) to address this limitation by restoring both the spatial and frequency domain features of the native image. SFM-Transformer comprises three modules: the spatial and frequency feature extractor module (SFFE), the spatial and frequency fusion module (SFF), and the multi-scale fusion module (MSF). By incorporating cross-feature space dependencies and capturing long-range details in spatial and frequency domains, our network captures pixel-level features and implicit physical properties features of native images. Furthermore, the SFM-Transformer utilizes a multi-scale strategy at the backbone to further improve performance. To facilitate comprehensive research, we construct a diverse dataset containing both simulated and experimental datasets. To validate the effectiveness of our method, we conduct extensive experiments in simulated and experimental data. The experimental results demonstrate that our method eliminates the blurring artifacts and recovers the edge shape of MPI images. This suggests that our approach has great potential for improving the accuracy and reliability of MPI for future applications.

Background: Magnetic Particle Imaging (MPI) is an emerging molecular imaging technique. However, since X-space reconstruction ignores system properties, it can lead to blurring of the reconstructed image, posing challenges for accurate quantification. To address this issue, we propose the use of deep learning to remove the blurry artifacts; (2) Methods: Our network architecture consists of a combination of Convolutional Neural Network (CNN) and Transformer. The CNN utilizes convolutional layers to automatically extract pixel-level local features and reduces the size of feature maps through pooling layers, effectively capturing local information within the images. The Transformer module is responsible for extracting contextual features from the images and efficiently capturing long-range dependencies, enabling a more effective modeling of global features in the images. By combining the features extracted by both CNN and Transformer, we capture both global and local features simultaneously, thereby improving the quality of reconstructed images; (3) Results: Experimental results demonstrate that the network effectively removes blurry artifacts from the images, and it exhibits high accuracy in precise tumor quantification. The proposed method shows superior performance over the state-of-the-art methods; (4) Conclusions: This bears significant implications for the image quality improvement and clinical application of MPI technology.