Search

Semantic segmentation is a critical task in computer vision that aims to assign each pixel in an image a corresponding label on the basis of its semantic content. This task is commonly referred to as dense labeling because it requires pixel-level classification of the image. The research area of semantic segmentation is vast and has achieved critical advances in recent years. Deep learning architectures in particular have shown remarkable performance in generating high-level, hierarchical, and semantic features from images. Among these architectures, convolutional neural networks have been widely used to address semantic segmentation problems. This work aims to review and analyze recent technological developments in image semantic segmentation. It provides an overview of traditional and deep-learning-based approaches and analyzes their structural characteristics, strengths, and limitations. Specifically, it focuses on technical developments in deep-learning-based 2D semantic segmentation methods proposed over the past decade and discusses current challenges in semantic segmentation. The future development direction of semantic segmentation and the potential research areas that need further exploration are also examined. [ABSTRACT FROM AUTHOR]

As a critical transformational process in the attributes of epithelial cells, epithelial-to-mesenchymal transition (EMT) is involved in tumor invasion, metastasis, and resistance to treatment, which contributes to the ultimate death of some patients with breast cancer. Glycogen synthase kinase-3-beta (GSK3β) is thought to be an EMT suppressor that down-regulates the protein, snail, a zinc finger transcription inhibitor, and regulates E-cadherin expression and the Wnt signaling pathway. Our previous studies have shown that Notch3 also inhibits EMT in breast cancer. In mammary gland cells, GSK3β physically bound and phosphorylated the intracellular domain of two Notch paralogs: N1ICD was positively regulated, but N2ICD was negatively regulated; however, the relationship between Notch3, GSK3β, and EMT in breast cancer is still unclear and crosstalk between Notch3 and GSK3β has not been widely investigated. In this study, we revealed that Notch3 was an essential antagonist of EMT in breast cancer cells by transcriptionally upregulating GSK3β. In breast cancer, MCF-7 and MDA-MB-231 cell lines, the silencing of Notch3 reduced GSK3β expression, which is sufficient to induce EMT. Conversely, ectopic Notch3 expression re-activated GSK3β and E-cadherin. Mechanistically, Notch3 can bind to the GSK3β promoter directly and activate GSK3β transcription. In human breast cancer samples, Notch3 expression is positively associated with GSK3β (r = 0.416, p = 0.001); moreover, high expressions of Notch3 and GSK3β mRNA are correlated to better relapse-free survival in all breast cancer patients via analysis in "the Kaplan–Meier plotter" database. In summary, our preliminary results suggested that Notch3 might inhibit EMT by trans-activating GSK3β in breast cancer cells. The suppression of Notch3 expression may contribute to EMT by transcriptionally downregulating GSK3β in breast cancer. [ABSTRACT FROM AUTHOR]

Microglia, the major immune cells in the brain, mediate neuroinflammation, increased oxidative stress, and impaired neurotransmission in Alzheimer's disease (AD), in which most AD risk genes are highly expressed. In microglia, due to the limitations of current single-omics data analysis, risk genes, the regulatory mechanisms, the mechanisms of action of immune responses and the exploration of drug targets for AD immunotherapy are still unclear. Therefore, we proposed a method to integrate multi-omics data based on the construction of gene regulatory networks (GRN), by combining weighted gene co-expression network analysis (WGCNA) with single-cell regulatory network inference and clustering (SCENIC). This enables snRNA-seq data and bulkRNA-seq data to obtain data on the deeper intermolecular regulatory relationships, related genes, and the molecular mechanisms of immune-cell action. In our approach, not only were central transcription factors (TF) STAT3, CEBPB, SPI1, and regulatory mechanisms identified more accurately than with single-omics but also immunotherapy targeting central TFs to drugs was found to be significantly different between patients. Thus, in addition to providing new insights into the potential regulatory mechanisms and pathogenic genes of AD microglia, this approach can assist clinicians in making the most rational treatment plans for patients with different risks; it also has significant implications for identifying AD immunotherapy targets and targeting microglia-associated immune drugs. [ABSTRACT FROM AUTHOR]

In the meteorology of Global Navigation Satellite System, the weighted mean temperature (Tm) is a key parameter in the process of converting the zenith wetness delay into precipitable water vapor, and it plays an important role in water vapor monitoring. In this research, two deep learning algorithms, namely, recurrent neural network (RNN) and long short-term memory neural network (LSTM), were used to build a high-precision weighted mean temperature model for China using their excellent time series memory capability. The model needs site location information and measured surface temperature to predict the weighted mean temperature. We used data from 118 stations in and around China provided by the Integrated Global Radiosonde Archive from 2010 to 2015 to train the model and data from 2016 for model testing. The root mean square error (RMSE) of the RNN_Tm and LSTM_Tm models were 3.01 K and 2.89 K, respectively. Compared with the values calculated by the empirical GPT3 model, the accuracy was improved by 31.1% (RNN_Tm) and 33.9% (LSTM_Tm). In addition, we selected another 10 evenly distributed stations in China and used the constructed model to test the prediction capability of the weighted mean temperature from 2010 to 2016. The RMSE values were 2.95 K and 2.86 K, which proved that the model also exhibits high generalization in non-modeling sites in China. In general, the RNN_Tm and LSTM_Tm models have a good performance in weighted mean temperature prediction. [ABSTRACT FROM AUTHOR]