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.

Spatial distribution of tumor infiltrating lymphocytes (TILs) and cancer cells in the tumor microenvironment (TME) along with tumor gene mutation status are of vital importance to the guidance of cancer immunotherapy and prognoses. In this work, we developed a deep learning-based computational framework, termed ImmunoAIzer, which involves: (1) the implementation of a semi-supervised strategy to train a cellular biomarker distribution prediction network (CBDPN) to make predictions of spatial distributions of CD3, CD20, PanCK, and DAPI biomarkers in the tumor microenvironment with an accuracy of 90.4%; (2) using CBDPN to select tumor areas on hematoxylin and eosin (H&E) staining tissue slides and training a multilabel tumor gene mutation detection network (TGMDN), which can detect APC, KRAS, and TP53 mutations with area-under-the-curve (AUC) values of 0.76, 0.77, and 0.79. These findings suggest that ImmunoAIzer could provide comprehensive information of cell distribution and tumor gene mutation status of colon cancer patients efficiently and less costly; hence, it could serve as an effective auxiliary tool for the guidance of immunotherapy and prognoses. The method is also generalizable and has the potential to be extended for application to other types of cancers other than colon cancer.

Objective: Magnetic particle imaging (MPI) is a promising medical modality that can image superparamagnetic iron-oxide nanoparticle (SPIO) concentration distributions safely and with high sensitivity. In the x-space reconstruction algorithm, the Langevin function is inaccurate in modeling the dynamic magnetization of SPIOs. This problem prevents the x-space algorithm from achieving a high spatial resolution reconstruction. Methods: We propose a more accurate model to describe the dynamic magnetization of SPIOs, named the modified Jiles–Atherton (MJA) model, and apply it to the x-space algorithm to improve the image resolution. Considering the relaxation effect of SPIOs, the MJA model generates the magnetization curve via an ordinary differential equation. Three modifications are also introduced to further improve its accuracy and robustness. Results: In magnetic particle spectrometry experiments, the MJA model shows higher accuracy than the Langevin and Debye models under various test conditions. The average root-mean-square error is 0.055, 83% and 58% lower than the Langevin and Debye models, respectively. In MPI reconstruction experiments, the MJA x-space improves the spatial resolution by 64% and 48% compared to the x-space and Debye x-space methods, respectively. Conclusion: The MJA model shows high accuracy and robustness in modeling the dynamic magnetization behavior of SPIOs. By integrating the MJA model into the x-space algorithm, the spatial resolution of MPI technology was improved. Significance: Improving the spatial resolution by using the MJA model helps MPI have a better performance in medical fields, including cardiovascular imaging.

Objective. Magnetic particle imaging (MPI) is a novel radiation-free medical imaging modality that can directly image superparamagnetic iron oxide tracers (SPIOs) with high sensitivity, temporal resolution, and good spatial resolution. The MPI reconstruction task can be formulated mathematically as a Fredholm integral problem, but the concrete inversion is not easily possible because of the particle dynamics or scanner issues. Measurement based system matrix inversion takes these factors into account, but prior measurement and calibration are time consuming. Approach. We proposed a direct imaging method based on the weighted sum of harmonic signals. The harmonic signals with spatial information are obtained by the short-time Fourier transform, and odd harmonic components are selected for recombination and then mapped to the sampling trajectory to image the concentration distribution of SPIOs. In addition, we adopt a normalized-weighted sum of harmonics to improve the resolution of the native image. Main results. The effectiveness of the proposed method is verified by simulation imaging experiments and our in-house scanner-based experiments. Quantitative evaluation results show that compared with traditional methods, the structural similarity improved by 48%, mean square error decreased by 88%, and signal-to-artifact ratio increased by 2.5 times. Significance. The proposed method can rapidly image the concentration distribution of nanoparticles without any prior calibration measurements and reduce the blur of MPI images without deconvolution, which has the potential to be implemented as a multi-patch imaging method in MPI.

Objective: Open-sided field-free line magnetic particle imaging (OS FFL MPI) is a novel medical imaging system configuration that has received significant attention in recent years. However, the measurement-based system matrix (SM) image reconstruction for OS FFL MPI typically requires multiple angle calibration (MAC), which is time-consuming in practice. Methods: To address this issue, we propose a fast 2D SM generation method that requires only a single angle calibration (SAC). The SAC method exploits the rotational invariance of the system function. Based on the measured single angle system function, the system function is rotated to generate system functions at other angles, and then the SM for image reconstruction is constructed. Then, we conducted various simulation experiments and built an OS FFL MPI scanner to evaluate the proposed SAC method. Results: The experiments demonstrating the effectiveness of SAC in reducing calibration workload, requiring fewer scanning numbers while maintaining a similar image reconstruction quality compared to MAC method. Furthermore, the SM generated by SAC produces consistent imaging results with the SM generated by MAC, regardless of the interpolation algorithms, the number of rotation angles, or the signal-to-noise ratios employed in phantom imaging experiments. Conclusion: SAC has been experimentally verified to reduce acquisition time while maintaining accurate and robust reconstruction performance. Significance: The significance of SAC lies in its contribution to improving calibration efficiency in OS FFL MPI, potentially facilitating the implementation of MPI in a wider range of applications.