Search

Objective: High‐risk types of diffuse gliomas in adults include isocitrate dehydrogenase (IDH) wild‐type glioblastomas and grade 4 astrocytomas. Achieving noninvasive prediction of high‐risk molecular subtypes of gliomas is important for personalized and precise diagnosis and treatment. Methods: We retrospectively collected data from 116 patients diagnosed with adult diffuse gliomas. Multiple high‐risk molecular markers were tested, and various habitat models and whole‐tumor models were constructed based on preoperative routine and diffusion kurtosis imaging (DKI) sequences to predict high‐risk molecular subtypes of gliomas. Feature selection and model construction utilized Least absolute shrinkage and selection operator (LASSO) and support vector machine (SVM). Finally, the Wilcoxon rank‐sum test was employed to explore the correlation between habitat quantitative features (intra‐tumor heterogeneity score，ITH score) and heterogeneity, as well as high‐risk molecular subtypes. Results: The results showed that the habitat analysis model based on DKI performed remarkably well (with AUC values reaching 0.977 and 0.902 in the training and test sets, respectively). The model's performance was further enhanced when combined with clinical variables. (The AUC values were 0.994 and 0.920, respectively.) Additionally, we found a close correlation between ITH score and heterogeneity, with statistically significant differences observed between high‐risk and non‐high‐risk molecular subtypes. Interpretation: The habitat model based on DKI is an ideal means for preoperatively predicting high‐risk molecular subtypes of gliomas, holding significant value for noninvasively alerting malignant gliomas and those with malignant transformation potential. [ABSTRACT FROM AUTHOR]

The study of the polarimetric target decomposition algorithm with physical scattering models has contributed to the development of the field of remote sensing because of its simple and clear physical meaning with a small computational effort. However, most of the volume scattering models in these algorithms are for forests or crops, and there is a lack of volume scattering models for grasslands. In order to improve the accuracy of the polarimetric target decomposition algorithm adapted to grassland data, in this paper, a novel volume scattering model is derived considering the characteristics of real grassland plant structure and combined with the backward scattering coefficients of grass, which is abstracted as a rotatable ellipsoid of variable shape. In the process of rotation, the possibility of rotation is considered in two dimensions, the tilt angle and canting angle; for particle shape, the anisotropy degree A is directly introduced as a parameter to describe and expand the applicability of the model at the same time. After obtaining the analytical solution of the parameters and using the principle of least negative power to determine the optimal solution of the model, the algorithm is validated by applying it to the C-band AirBorne dataset of Hunshandak grassland in Inner Mongolia and the X-band Cosmos-Skymed dataset of Xiwuqi grassland in Inner Mongolia. The performance of the algorithm with five polarimetric target decomposition algorithms is studied comparatively. The experimental results show that the algorithm proposed in this paper outperforms the other algorithms in terms of grassland decomposition accuracy on different bands of data. [ABSTRACT FROM AUTHOR]

Understanding the response of the injured brain to different transcranial direct current stimulation (tDCS) montages may help explain the variable tDCS treatment results on poststroke motor gains. Cortical connectivity has been found to reflect poststroke motor gains and cortical plasticity, but the changes in connectivity following tDCS remain unknown. We aimed to investigate the relationship between tDCS-induced changes in cortical connectivity and poststroke motor gains. In this study, participants were assigned to receive four tDCS montages (anodal, cathodal, bilateral, and sham) over the primary motor cortex (M1) according to a single-blind, randomized, crossover design. Electroencephalography (EEG) and Jebsen-Taylor hand function test (JTT) were performed before and after the intervention. Motor cortical connectivity was measured using beta-band coherence with the ipsilesional and contralesional M1 as seed regions. Motor gain was evaluated based on the JTT completion time. We examined the relationship between baseline connectivity and clinical characteristics and that between changes in connectivity and motor gains after different tDCS montages. Baseline functional connectivity, motor impairment, and poststroke duration were correlated. High ipsilesional M1–frontal–temporal connectivity was correlated with a good baseline motor status, and increased connectivity was accompanied by good functional improvement following anodal tDCS treatment. Low contralesional M1–frontal-central connectivity was correlated with a good baseline motor status, and decreased connectivity was accompanied by good functional improvement following cathodal tDCS treatment. In conclusion, EEG-based motor cortical connectivity was correlated with stroke characteristics, including motor impairment and poststroke duration, and motor gains induced by anodal and cathodal tDCS. [ABSTRACT FROM AUTHOR]

As one of the important lakes in the "One Lake and Two Seas" of the Inner Mongolia Autonomous Region, the monitoring of water quality in Lake Daihai has attracted increasing attention, and the concentration of chlorophyll-a directly affects the water quality, making the monitoring of chlorophyll-a concentration in Lake Daihai particularly crucial. Traditional methods of monitoring chlorophyll-a concentration are not only inefficient but also require significant human and material resources. Remote sensing technology has the advantages of wide coverage and short update cycles. For lakes such as Daihai with a high salinity content, salinity is considered a key factor when inverting the concentration of chlorophyll-a. In this study, machine learning models, including model stacking from ensemble learning, a ridge regression model, and a random forest model, were constructed. After comparing the training accuracy of the three models on Zhuhai-1 satellite data, the random forest model, which had the highest accuracy, was selected as the final training model. By comparing the accuracy changes before and after adding salinity factors to the random forest model, a high-precision model for inverting chlorophyll-a concentration in hypersaline lakes was obtained. The research results show that, without considering the salinity factor, the root mean square error (RMSE) of the model was 0.056, and the coefficient of determination (R2) was 0.64, indicating moderate model performance. After adding the salinity factor, the model accuracy significantly improved: the RMSE decreased to 0.047, and the R2 increased to 0.92. This study provides a solid basis for the application of remote sensing technology in hypersaline aquatic environments, confirming the importance of considering salinity when estimating chlorophyll-a concentration in hypersaline waters. This research helps us gain a deeper understanding of the water quality and ecosystem evolution in Daihai Lake. [ABSTRACT FROM AUTHOR]

Objective: The aim of this study is to examine and evaluate the impact of benzene poisoning on the relative content of the mitochondrial MT-ND1 gene and telomere length in individuals with occupational chronic benzene poisoning (CBP) compared to a control group. The study will analyze and gather data on the mitochondrial gene content and telomere length in cases of benzene poisoning, and investigate the relationship with blood routine parameters in order to contribute scientific experimental data for the prevention and treatment of CBP. Method: The case group comprised 30 individuals diagnosed with occupational chronic benzene poisoning, whereas the control group consisted of 60 healthy individuals who underwent physical examinations at our hospital concurrently. Blood routine indicators were detected and analyzed, and the PCR method was employed to measure changes in mitochondrial MT-ND1 content and telomere length. Subsequently, a comparison and analysis of the aforementioned indicators was conducted. Result: The case group exhibited a higher mitochondrial gene content (median 366.2, IQR 90.0 rate) compared to the control group (median 101.5, IQR 12.0 rate), with a statistically significant difference between the two groups (P < 0.05). Additionally, the case group demonstrated lower white blood cell levels (3.78 ± 1.387 × 109/L) compared to the control group (5.74 ± 1.41 × 109/L), with a significant difference between the two groups (P < 0.05). Furthermore, the case group displayed lower red blood cell levels (3.86 ± 0.65 × 1012/L) compared to the control group (4.89 ± 0.65 × 1012/L), with a significant difference between the two groups (P < 0.05). The hemoglobin level in the case group (113.33 ± 16.34 g/L) was lower than that in the control group (138.22 ± 13.22 g/L). There was a significant difference between the two groups (P < 0.05). Platelet levels in the case group (153.80 ± 58.31 × 109/L) is smaller than the control group (244.92 ± 51.99 × 109/L), there was a significant difference between the two groups (P < 0.05). The average telomere length of the normal control group was 1.451 ± 0.475 (rate); The mean telomere length of individuals in the case group diagnosed with benzene poisoning was determined to be 1.237 ± 0.457 (rate). No significant correlation was observed between telomere length and three blood routine parameters, namely white blood cells (WBC), hemoglobin (HB), and platelets (PLT). However, a significant correlation was found between telomere length and red blood cell count (RBC). Additionally, a negative correlation was observed between mitochondrial gene content and white blood cell count (r = − 0.314, P = 0.026), as well as between mitochondrial gene content and red blood cell count (r = − 0.226, P = 0.032). Furthermore, a negative correlation was identified between mitochondrial gene content and hemoglobin (r = − 0.314, P = 0.028), and platelets (r = − 0.445, P = 0.001). Conclusion: Individuals diagnosed with occupational chronic benzene poisoning exhibit a reduction in telomere length and an elevation in the relative content of the mitochondrial MT-ND1 gene. Moreover, a negative correlation is observed between the content of the mitochondrial MT-ND1 gene and four blood routine parameters, namely white blood cells (WBC), red blood cells (RBC), hemoglobin (HB), and platelets (PLT). Consequently, benzene exposure may potentially contribute to the onset of premature aging. [ABSTRACT FROM AUTHOR]

Unsupervised classification is a significant step inthe automated interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) images. However, determining the number of clusters in this process is still a challenging problem. To this end, we propose a region-based unsupervised classification method for PolSAR images by introducing Wishart mixture models and a Density Peaks Clustering (DPC) algorithm. More precisely, the Simple Linear Iterative Clustering (SLIC) algorithm is first used to segment the PolSAR image into superpixels. Subsequently, the Wishart mixture models are adopted to model each superpixel, and the pairwise distances between different superpixels are measured by Cauchy-Schwarz divergence. Finally, the unsupervised classification result of the PolSAR image is obtained via clustering by fast search and find of density peaks. The experimental results obtained from different PolSAR images demonstrate that the proposed method is effective.

Classification is one of the core components in the interpretation of Polarimetric Synthetic Aperture Radar (PolSAR) images. A new PolSAR image classification approach employs the structural properties of the Riemannian manifold formed by PolSAR covariance matrices. In this paper, we first review the Riemannian manifold metrics generally used in PolSAR image analysis. Then, we describe a sparse coding method for the covariance matrices in the Riemannian manifold. For supervised classification, we propose a PolSAR image classification method that considers spatial information based on kernel space sparse coding. As for unsupervised PolSAR image classification, a method that takes advantage of Riemannian sparse induced similarity is proposed. Experimental results on EMISAR and AIRSAR data demonstrate the effectiveness of the proposed methods.

In this paper, we propose a supervised classification algorithm for Polarimetric Synthetic Aperture Radar (PolSAR) images using multiple-feature fusion and ensemble learning. First, we extract different polarimetric features, including extended polarimetric feature space, Hoekman, Huynen, H/alpha/A, and fourcomponent scattering features of PolSAR images. Next, we randomly select two types of features each time from all feature sets to guarantee the reliability and diversity of later ensembles and use a support vector machine as the basic classifier for predicting classification results. Finally, we concatenate all prediction probabilities of basic classifiers as the final feature representation and employ the random forest method to obtain final classification results. Experimental results at the pixel and region levels show the effectiveness of the proposed algorithm.

This study presents a new feature representation approach for Polarimetric Synthetic Aperture Radar (PolSAR) image based on prototype theory. First, multiple prototype sets are generated using prototype theory. Then, regularized logistic regression is used to predict similarities between a test sample and each prototype set. Finally, the PolSAR image feature representation is obtained by ensemble projection. Experimental results of an unsupervised classification of PolSAR images show that our method can efficiently represent polarimetric signatures of different land covers and yield satisfactory classification results.