Transformer for low concentration image denoising in magnetic particle imaging.

Objective.Magnetic particle imaging (MPI) is an emerging tracer-basedin vivoimaging technology. The use of MPI at low superparamagnetic iron oxide nanoparticle concentrations has the potential to be a promising area of clinical application due to the inherent safety for humans. However, low tracer concentrations reduce the signal-to-noise ratio of the magnetization signal, leading to severe noise artifacts in the reconstructed MPI images. Hardware improvements have high complexity, while traditional methods lack robustness to different noise levels, making it difficult to improve the quality of low concentration MPI images.Approach.Here, we propose a novel deep learning method for MPI image denoising and quality enhancing based on a sparse lightweight transformer model. The proposed residual-local transformer structure reduces model complexity to avoid overfitting, in which an information retention block facilitates feature extraction capabilities for the image details. Besides, we design a noisy concentration dataset to train our model. Then, we evaluate our method with both simulated and real MPI image data.Main results.Simulation experiment results show that our method can achieve the best performance compared with the existing deep learning methods for MPI image denoising. More importantly, our method is effectively performed on the real MPI image of samples with an Fe concentration down to 67µgFeml-1.Significance.Our method provides great potential for obtaining high quality MPI images at low concentrations.

Accurate Concentration Recovery for Quantitative Magnetic Particle Imaging Reconstruction via Nonconvex Regularization.

Magnetic particle imaging (MPI) uses nonlinear response signals to noninvasively detect magnetic nanoparticles in space, and its quantitative properties hold promise for future precise quantitative treatments. In reconstruction, the system matrix based method necessitates suitable regularization terms, such as Tikhonov or non-negative fused lasso (NFL) regularization, to stabilize the solution. While NFL regularization offers clearer edge information than Tikhonov regularization, it carries a biased estimate of the l1 penalty, leading to an underestimation of the reconstructed concentration and adversely affecting the quantitative properties. In this paper, a new nonconvex regularization method including min-max concave (MC) and total variation (TV) regularization is proposed. This method utilized MC penalty to provide nearly unbiased sparse constraints and adds the TV penalty to provide a uniform intensity distribution of images. By combining the alternating direction multiplication method (ADMM) and the two-step parameter selection method, a more accurate quantitative MPI reconstruction was realized. The performance of the proposed method was verified on the simulation data, the Open-MPI dataset, and measured data from a homemade MPI scanner. The results indicate that the proposed method achieves better image quality while maintaining the quantitative properties, thus overcoming the drawback of intensity underestimation by the NFL method while providing edge information. In particular, for the measured data, the proposed method reduced the relative error in the intensity of the reconstruction results from 28% to 8%.

Content-Noise Feature Fusion Neural Network for Image Denoising in Magnetic Particle Imaging∗.

Magnetic particle imaging (MPI) is a tomographic imaging method that quantitatively determines the distribution of magnetic nanoparticles (MNPs). However, the performance of MPI is primarily limited by the noise in the receive coil and electronic devices, which causes quantification errors for MPI images. Existing methods cannot efficiently eliminate noise while preserve structural details in MPI images. To address this problem, we propose a Content-Noise Feature Fusion Neural Network equipped with tailored modules of noise learning and content learning. It can simultaneously learn content and noise features of raw MPI images. Experimental results show that the proposed method outperforms the state-of-the-art methods on structural details preservation and image noise reduction of different levels.

Magnetic particle imaging deblurring with dual contrastive learning and adversarial framework.

Magnetic particle imaging (MPI) is an emerging medical imaging technique that has high sensitivity, contrast, and excellent depth penetration. In MPI, x-space is a reconstruction method that transforms the measured voltages into particle concentrations. The reconstructed native image can be modeled as a convolution of the magnetic particle concentration with a point-spread function (PSF). The PSF is one of the important parameters in deconvolution. However, accurately measuring or modeling the PSF in the hardware used for deconvolution is challenging due to the various environment and magnetic particle relaxation. The inaccurate PSF estimation may lead to the loss of the content structure of the MPI image, especially in low gradient fields. In this study, we developed a Dual Adversarial Network (DAN) with patch-wise contrastive constraint to deblur the MPI image. This method can overcome the limitations of unpaired data in data acquisition scenarios and remove the blur around the boundary more effectively than the common deconvolution method. We evaluated the performance of the proposed DAN model on simulated and real data. Experimental results confirmed that our model performs favorably against the deconvolution method that is mainly used for deblurring the MPI image and other GAN-based deep learning models.

Plexin D1 mediates disturbed flow-induced M1 macrophage polarization in atherosclerosis.

Atherosclerosis preferentially develops at bifurcations exposed to disturbed flow. Plexin D1 (PLXND1) responds to mechanical forces and drives macrophage accumulation in atherosclerosis. Here, multiple strategies were used to identify the role of PLXND1 in site-specific atherosclerosis. Using computational fluid dynamics and three-dimensional light-sheet fluorescence-microscopy, the elevated PLXND1 in M1 macrophages was mainly distributed in disturbed flow area of ApoE-/- carotid bifurcation lesions, and visualization of atherosclerosis in vivo was achieved by targeting PLXND1. Subsequently, to simulate the microenvironment of bifurcation lesions in vitro, we co-cultured oxidized low-density lipoprotein (oxLDL)-treated THP-1-derived macrophages with shear-treated human umbilical vein endothelial cells (HUVECs). We found that oscillatory shear induced the increase of PLXND1 in M1 macrophages, and knocking down PLXND1 inhibited M1 polarization. Semaphorin 3E, the ligand of PLXND1 which was highly expressed in plaques, strongly enhanced M1 macrophage polarization via PLXND1 in vitro. Our findings provide insights into pathogenesis in site-specific atherosclerosis that PLXND1 mediates disturbed flow-induced M1 macrophage polarization.

Two-stage hybrid network for segmentation of COVID-19 pneumonia lesions in CT images: a multicenter study.

COVID-19 has been spreading continuously since its outbreak, and the detection of its manifestations in the lung via chest computed tomography (CT) imaging is essential to investigate the diagnosis and prognosis of COVID-19 as an indispensable step. Automatic and accurate segmentation of infected lesions is highly required for fast and accurate diagnosis and further assessment of COVID-19 pneumonia. However, the two-dimensional methods generally neglect the intraslice context, while the three-dimensional methods usually have high GPU memory consumption and calculation cost. To address these limitations, we propose a two-stage hybrid UNet to automatically segment infected regions, which is evaluated on the multicenter data obtained from seven hospitals. Moreover, we train a 3D-ResNet for COVID-19 pneumonia screening. In segmentation tasks, the Dice coefficient reaches 97.23% for lung segmentation and 84.58% for lesion segmentation. In classification tasks, our model can identify COVID-19 pneumonia with an area under the receiver-operating characteristic curve value of 0.92, an accuracy of 92.44%, a sensitivity of 93.94%, and a specificity of 92.45%. In comparison with other state-of-the-art methods, the proposed approach could be implemented as an efficient assisting tool for radiologists in COVID-19 diagnosis from CT images.

Elimination of stripe artifacts in light sheet fluorescence microscopy using an attention-based residual neural network.

Stripe artifacts can deteriorate the quality of light sheet fluorescence microscopy (LSFM) images. Owing to the inhomogeneous, high-absorption, or scattering objects located in the excitation light path, stripe artifacts are generated in LSFM images in various directions and types, such as horizontal, anisotropic, or multidirectional anisotropic. These artifacts severely degrade the quality of LSFM images. To address this issue, we proposed a new deep-learning-based approach for the elimination of stripe artifacts. This method utilizes an encoder-decoder structure of UNet integrated with residual blocks and attention modules between successive convolutional layers. Our attention module was implemented in the residual blocks to learn useful features and suppress the residual features. The proposed network was trained and validated by generating three different degradation datasets with different types of stripe artifacts in LSFM images. Our method can effectively remove different stripes in generated and actual LSFM images distorted by stripe artifacts. Besides, quantitative analysis and extensive comparison results demonstrated that our method performs the best compared with classical image-based processing algorithms and other powerful deep-learning-based destriping methods for all three generated datasets. Thus, our method has tremendous application prospects to LSFM, and its use can be easily extended to images reconstructed by other modalities affected by the presence of stripe artifacts.

The effect of endothelial progenitor cell transplantation on neointimal hyperplasia and reendothelialisation after balloon catheter injury in rat carotid arteries.

BACKGROUND: Reendothelialisation is the natural pathway that inhibits neointimal hyperplasia and in-stent restenosis. Circulating endothelial progenitor cells (EPCs) derived from bone marrow (BM) might contribute to endothelial repair. However, the temporal and spatial distributions of reendothelialisation and neointimal hyperplasia after EPC transplantation in injured arteries are currently unclear. METHODS: A carotid balloon injury (BI) model was established in Sprague-Dawley rats, and PKH26-labelled BM-derived EPCs were transplanted after BI. The carotid arteries were harvested on the first, fourth, seventh, and 14th day post-injury and analysed via light-sheet fluorescence microscopy and pathological staining (n = 3). EPC and human umbilical vein endothelial cell culture supernatants were collected, and blood samples were collected before and after transplantation. The paracrine effects of VEGF, IGF-1, and TGF-ß1 in cell culture supernatants and serum were analysed by enzyme-linked immunosorbent assay (n = 4). RESULTS: Transplanted EPCs labelled with PKH26 were attached to the injured luminal surface the first day after BI. In the sham operation group, the transplanted EPCs did not adhere to the luminal surface. From the fourth day after BI, the mean fluorescence intensity of PKH26 decreased significantly. However, reendothelialisation and inhibition of neointimal hyperplasia were significantly promoted by transplanted EPCs. The degree of reendothelialisation of the EPC7d and EPC14d groups was higher than that of the BI7d and BI14d groups, and the difference in neointimal hyperplasia was observed between the EPC14d and BI14d groups. The number of endothelial cells on the luminal surface of the EPC14d group was higher than that of the BI14d group. The number of infiltrated macrophages in the injured artery decreased in the EPC transplanted groups. CONCLUSIONS: Transplanted EPCs had chemotactic enrichment and attached to the injured arterial luminal surface. Although decreasing significantly after the fourth day at the site of injury after transplantation, transplanted EPCs could still promote reendothelialisation and inhibit neointimal hyperplasia. The underlying mechanism is through paracrine cytokines and not differentiation into mature endothelial cells.