Search

RTX was initially used for non-Hodgkin’s lymphoma treatment and has been used in the clinical treatment of various autoimmune diseases as well as in antirejection and immune induction therapy for kidney transplant recipients. Following RTX treatment, the time for B cell regeneration varies among patients, but there is no unified recommendation for the frequency of B cell monitoring. This study aimed to investigate the clinical significance of periodic monitoring of peripheral blood B lymphocytes in individualized immunotherapy following rituximab (RTX) treatment in patients with different diseases. This study included 488 patients with different diseases divided in four groups who were hospitalized and followed up from April 2017 to March 2024 (including 77, 161, 120, and 130 cases of neuromyelitis optica, pemphigus, membranous nephropathy, and kidney transplant recipients, respectively). Dynamic changes in percentage and absolute count of peripheral blood B lymphocytes before and after RTX treatment were investigated in the four groups, as well as the number of B cell subsets in 32 patients with optic neuromyelitis after RTX treatment. Although most patients showed high expression of B cells after 24 weeks, less than 6.8% of patients still began to experience B cell regeneration within 4 weeks. Thus, regular B cell monitoring following RTX treatment is helpful to better track the remission and recurrence of the disease and provide effective laboratory support for the selection and implementation of individualized immunotherapy.

The content of nicotine, a critical component of tobacco, significantly influences the quality of tobacco leaves. Near-infrared (NIR) spectroscopy is a widely used technique for rapid, non-destructive, and environmentally friendly analysis of nicotine levels in tobacco. In this paper, we propose a novel regression model, Lightweight one-dimensional convolutional neural network (1D-CNN), for predicting nicotine content in tobacco leaves using one-dimensional (1D) NIR spectral data and a deep learning approach with convolutional neural network (CNN). This study employed Savitzky–Golay (SG) smoothing to preprocess NIR spectra and randomly generate representative training and test datasets. Batch normalization was used in network regularization to reduce overfitting and improve the generalization performance of the Lightweight 1D-CNN model under a limited training dataset. The network structure of this CNN model consists of four convolutional layers to extract high-level features from the input data. The output of these layers is then fed into a fully connected layer, which uses a linear activation function to output the predicted numerical value of nicotine. After the comparison of the performance of multiple regression models, including support vector regression (SVR), partial least squares regression (PLSR), 1D-CNN, and Lightweight 1D-CNN, under the preprocessing method of SG smoothing, we found that the Lightweight 1D-CNN regression model with batch normalization achieved root mean square error (RMSE) of 0.14, coefficient of determination (R2) of 0.95, and residual prediction deviation (RPD) of 5.09. These results demonstrate that the Lightweight 1D-CNN model is objective and robust and outperforms existing methods in terms of accuracy, which has the potential to significantly improve quality control processes in the tobacco industry by accurately and rapidly analyzing the nicotine content.

PurposeTo evaluate and compare the predictive performance of different deep learning models using gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI in predicting microvascular invasion (MVI) in hepatocellular carcinoma.MethodsThe data of 233 patients with pathologically confirmed hepatocellular carcinoma (HCC) treated at our hospital from June 2016 to June 2021 were retrospectively analyzed. Three deep learning models were constructed based on three different delineate methods of the region of interest (ROI) using the Darwin Scientific Research Platform (Beijing Yizhun Intelligent Technology Co., Ltd., China). Manual segmentation of ROI was performed on the T1-weighted axial Hepatobiliary phase images. According to the ratio of 7:3, the samples were divided into a training set (N=163) and a validation set (N=70). The receiver operating characteristic (ROC) curve was used to evaluate the predictive performance of three models, and their sensitivity, specificity and accuracy were assessed.ResultsAmong 233 HCC patients, 109 were pathologically MVI positive, including 91 men and 18 women, with an average age of 58.20 ± 10.17 years; 124 patients were MVI negative, including 93 men and 31 women, with an average age of 58.26 ± 10.20 years. Among three deep learning models, 2D-expansion-DL model and 3D-DL model showed relatively good performance, the AUC value were 0.70 (P=0.003) (95% CI 0.57–0.82) and 0.72 (P

Stain normalization often refers to transferring the color distribution to the target image and has been widely used in biomedical image analysis. The conventional stain normalization usually achieves through a pixel-by-pixel color mapping model, which depends on one reference image, and it is hard to achieve accurately the style transformation between image datasets. In principle, this difficulty can be well-solved by deep learning-based methods, whereas, its complicated structure results in low computational efficiency and artifacts in the style transformation, which has restricted the practical application. Here, we use distillation learning to reduce the complexity of deep learning methods and a fast and robust network called StainNet to learn the color mapping between the source image and the target image. StainNet can learn the color mapping relationship from a whole dataset and adjust the color value in a pixel-to-pixel manner. The pixel-to-pixel manner restricts the network size and avoids artifacts in the style transformation. The results on the cytopathology and histopathology datasets show that StainNet can achieve comparable performance to the deep learning-based methods. Computation results demonstrate StainNet is more than 40 times faster than StainGAN and can normalize a 100,000 × 100,000 whole slide image in 40 s.

BackgroundAccumulating evidence has revealed that peripheral immunity is involved in Parkinson’s disease (PD). However, the results regarding the percentage of T-cell subsets are inconsistent, and the changes of immunoglobins levels have been seldom studied in PD patients.MethodsSerum levels of the percentage of T-cell subsets and immunoglobulins were measured in 761 PD patients and 761 age- and gender-matched healthy controls. The correlations between the variables of peripheral immune activation (PIA) and the clinical characteristics of PD were analyzed using correlation analysis.ResultsThe pooled results showed that PD patients had higher proportional levels of CD3+ T and CD4+ T lymphocytes than healthy controls. CD8+ T cell percentages were similar in PD patients and controls, and the CD4/CD8 ratio was significantly higher in the PD population. No significant differences in IgG, IgA, or IgM levels between these two groups were found. CD4+ T cell percentage was inversely correlated with the H&Y stage, and IgG level was positively correlated with disease duration and UPDRS part III. Subgroup analyses showed that these associations existed in female patients, but not in male patients.ConclusionThe enhanced immune activation in the peripheral system is indicated in PD, and dynamic alterations in CD4+ T cell percentage and IgG level suggest an active role for peripheral immunity in the disease progression, especially in female PD patients.

α-synuclein is involved in the pathogenesis of multiple system atrophy (MSA) and can be regulated by peripheral immune activation (PIA). We aimed to clarify the correlations between PIA and the prevalence of MSA and to analyze the role of PIA in the progression of the disease. A total of 321 patients with probable MSA and 321 age- and gender-matched healthy controls were included in this study. Lymphocyte subsets, including CD3+, CD4+, and CD8+ cells, and the levels of immunoglobulins IgG, IgM, and IgA were evaluated. The proportions of CD3+ and CD4+ T-lymphocytes were significantly increased in MSA patients compared with those of normal controls. In addition, the ratio of CD4+ to CD8+ cells was significantly increased in male MSA patients and IgG concentrations were decreased in female MSA patients. Furthermore, the concentrations of IgM in female MSA patients were dynamically different at various disease stages and gradually decreased from the early stage until the end stage of the disease (p = 0.029). Other detected immunological indexes were not significantly different during the entire disease course. In this study, high proportions of CD3+ and CD4+ T-lymphocytes and decreased IgG levels were associated with an increased risk for MSA in a Chinese patient population. In addition, PIA may be involved in the progression of MSA.

The content of nicotine, a critical component of tobacco, significantly influences the quality of tobacco leaves. Near-infrared (NIR) spectroscopy is a widely used technique for rapid, non-destructive, and environmentally friendly analysis of nicotine levels in tobacco. In this paper, we propose a novel regression model, Lightweight one-dimensional convolutional neural network (1D-CNN), for predicting nicotine content in tobacco leaves using one-dimensional (1D) NIR spectral data and a deep learning approach with convolutional neural network (CNN). This study employed Savitzky–Golay (SG) smoothing to preprocess NIR spectra and randomly generate representative training and test datasets. Batch normalization was used in network regularization to reduce overfitting and improve the generalization performance of the Lightweight 1D-CNN model under a limited training dataset. The network structure of this CNN model consists of four convolutional layers to extract high-level features from the input data. The output of these layers is then fed into a fully connected layer, which uses a linear activation function to output the predicted numerical value of nicotine. After the comparison of the performance of multiple regression models, including support vector regression (SVR), partial least squares regression (PLSR), 1D-CNN, and Lightweight 1D-CNN, under the preprocessing method of SG smoothing, we found that the Lightweight 1D-CNN regression model with batch normalization achieved root mean square error (RMSE) of 0.14, coefficient of determination (R2 ) of 0.95, and residual prediction deviation (RPD) of 5.09. These results demonstrate that the Lightweight 1D-CNN model is objective and robust and outperforms existing methods in terms of accuracy, which has the potential to significantly improve quality control processes in the tobacco industry by accurately and rapidly analyzing the nicotine content. [ABSTRACT FROM AUTHOR]