Search

Fetal distress is a symptom of fetal intrauterine hypoxia, which is seriously harmful to both the fetus and the pregnant woman. The current primary clinical tool for the assessment of fetal distress is Cardiotocography (CTG). Due to subjective variability, physicians often interpret CTG results inconsistently, hence the need to develop an auxiliary diagnostic system for fetal distress. Although the deep learning-based fetal distress-assisted diagnosis model has a high classification accuracy, the model not only has a large number of parameters but also requires a large number of computational resources, which is difficult to deploy to practical end-use scenarios. Therefore, this paper proposes a lightweight fetal distress-assisted diagnosis network, LW-FHRNet, based on a cross-channel interactive attention mechanism. The wavelet packet decomposition technique is used to convert the one-dimensional fetal heart rate (FHR) signal into a two-dimensional wavelet packet coefficient matrix map as the network input layer to fully obtain the feature information of the FHR signal. With ShuffleNet-v2 as the core, a local cross-channel interactive attention mechanism is introduced to enhance the model’s ability to extract features and achieve effective fusion of multichannel features without dimensionality reduction. In this paper, the publicly available database CTU-UHB is used for the network performance evaluation. LW-FHRNet achieves 95.24% accuracy, which meets or exceeds the classification results of deep learning-based models. Additionally, the number of model parameters is reduced many times compared with the deep learning model, and the size of the model parameters is only 0.33 M. The results show that the lightweight model proposed in this paper can effectively aid in fetal distress diagnosis.

The Carboniferous-Permian coal measures in China contain abundant natural gas resources. Shale, coal and tight sandstone reservoirs are developed in coal measures, and the quantitative characterization of the pore structures of different types of reservoirs can provide scientific guidance for the sweet spot prediction of tight reservoirs. In this study, taking the Shan 2 Member coal measure of the Shanxi Formation in the eastern Ordos Basin as an example, the pore structures of shale, coal rock and tight sandstone were systematically studied based on organic geochemistry, scanning electron microscopy, high-pressure mercury injection, and low-temperature N2 and CO2 adsorption experiments. The results show that the microscopic pore structures of different types of reservoirs in the Shan 2 Member coal measures are quite different. Shale and tight sandstone mainly develop clay mineral pores at mesopore scale, followed by intragranular and dissolution pores developed in quartz and feldspar minerals, while organic pores are rarely developed. A large number of macro-scale clay mineral pores and micro-fractures are developed in tight sandstone, meanwhile the pore connectivity of tight sandstone is better than that of shale. A large number of micro to nano-scale organic pores are developed in coal, and the specific surface area of micropores in coal is much larger than that of mesopores in shale and tight sandstone. Sandstone, shale, and coal are frequently interbedded in coal measure strata. Tight sandstone provide the main storage space for free gas, and pores in shale and coal absorb a large amount of natural gas. Sandstone-shale-coal assemblages and sandstone-coal assemblages are the key targets for the exploration of hydrocarbons in the Shanxi Formation coal measures in the study area.

Additional file 1. Fig. S1. IFN-�� did not affect PD-L1 expression in the treatment macrophages. (A) The THP-1 macrophages were treated with Exo-ER, IFN-��, or PBS (Blank), followed by the detection of the PD-L1 mRNA (A) and protein levels (B and C) (n = 2-3) (*P < 0.05 and **P < 0.01; NS, no significance). Fig. S2. Knockdown of PD-L1 in HN4 cells and HN4-derived exosomes. HN4 cells were transfected with siPD-L1 or siNC, and exosomes were collected. (A-C) PD-L1 mRNA and protein level were detected in treatment HN4 cells by qRT-PCR (A) and Western blot (B and C). (D-E) Exosomal PD-L1 protein level was detected in treatment HN4 cells (n = 2-3) (*P < 0.05 and **P < 0.01). Fig. S3. Overexpression of PD-L1 promoted M2 polarization in macrophages. qRT-PCR analysis of CD206 mRNA in THP-1 macrophages transfected with plasmid encoding control (OE-NC) or PD-L1 (OE-PD-L1) (n = 3) (**P < 0.01). Table S1. RNA sequence used in this paper. Table S2. Clinicopathologic features of OSCC patients.

Graph Convolutional Network (GCN) has shown remarkable potential of exploring graph representation. However, the GCN aggregating mechanism fails to generalize to networks with heterophily where most nodes have neighbors from different classes, which commonly exists in real-world networks. In order to make the propagation and aggregation mechanism of GCN suitable for both homophily and heterophily (or even their mixture), we introduce block modeling into the framework of GCN so that it can realize "block-guided classified aggregation", and automatically learn the corresponding aggregation rules for neighbors of different classes. By incorporating block modeling into the aggregation process, GCN is able to aggregate information from homophilic and heterophilic neighbors discriminately according to their homophily degree. We compared our algorithm with state-of-art methods which deal with the heterophily problem. Empirical results demonstrate the superiority of our new approach over existing methods in heterophilic datasets while maintaining a competitive performance in homophilic datasets., Comment: Accepted by Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22)

During the last two decades, content-based image retrieval (CBIR) has been widely studied. The limitations of low-level feature representation of images have been a thorny issue in image retrieval problems. In this paper, a CBIR algorithm based on sparse representation and feature fusion is proposed, in which global features and local features are combined to retrieve the images. Firstly, the GIST features are used to roughly retrieve the images with similar scene information by measuring Canberra distance. Then, a representation of the local features extracted from the rough retrieval results is obtained by sparse coding and feature pooling. Finally, Euclidean distance is used to measure the similarity of the sparse feature vectors to obtain the retrieval results. The proposed method is tested on the Coil20 and Caltech256 image datasets. The experimental results demonstrate that the proposed algorithm can achieve comparable superior retrieval performance to the existing single feature-based image retrieval algorithms.

We aimed to evaluate the role of a natural sesquiterpene lactone, eupatolide, in non-small-cell lung cancer (NSCLC) and further explore its underlying mechanism on regulating the activation of signal transducer and activator of transcription 3 (STAT3), which is thought to have carcinogenic function in a variety of malignancies including lung cancer. Cell survival was measured by Cell Counting Kit-8 assay. in vivo experiments were performed by inoculating NSCLC cells into nude mice. Western blot and qRT-PCR were applied to detect the activation level of STAT3 and the mRNA levels of anti-apoptotic markers. The cell apoptosis was measured by Annexin V-FITC/PI Apoptosis Detection Kit. Our results showed that eupatolide suppressed the survival of NSCLC cells in a dose and time dependent manner. Furthermore, eupatolide increased the anti-tumor activity of the chemotherapeutic drugs cisplatin and 5-Fluoracil (5-FU). The xenograft study revealed that eupatolide suppressed tumor growth of NSCLC cells in vivo. Furthermore, eupatolide induced apoptosis by suppressing the activation of STAT3 in NSCLC cells. Sustained activation or knockdown of STAT3 suppressed and enhanced the activity of eupatolide, respectively. This paper is the first to report that eupatolide could effectively inhibit NSCLC progression, suggesting that eupatolide might be utilized as a novel STAT3 inhibitor for treating NSCLC.