Deep learning has become a research hotspot in multimedia, especially in the field of image processing. Pooling operation is an important operation in deep learning. Pooling operation can reduce the feature dimension, the number of parameters, the complexity of computation, and the complexity of time. With the development of deep learning models, pooling operation has made great progress. The main contributions of this paper on pooling operation are as follows: firstly, the steps of the pooling operation are summarized as the pooling domain, pooling kernel, step size, activation value, and response value. Secondly, the expression form of pooling operation is standardized. From the perspective of “invariable” to “variable,” this paper analyzes the pooling domain and pooling kernel in the pooling operation. Pooling operation can be classified into four categories: invariable of pooling domain, variable of pooling domain, variable of pooling kernel, and the pooling of invariable “+” variable. Finally, the four types of pooling operation are summarized and discussed with their advantages and disadvantages. There is great significance to the research of pooling operations and the iterative updating of deep learning models.
1 May 2020 in Biochemical and Biophysical Research Communications
Lung cancer is one of the malignant tumors with high morbidity and mortality, and lung nodules are the early stages of lung cancer. The symptoms of pulmonary nodules are not obvious in the clinic, and the optimal treatment time is missed due to the missed diagnosis in the clinic. A parallel U‐Net network called APU‐Net is proposed. Firstly, two parallel U‐Net networks are used to extract the features of different modalities. Among them, the subnetwork UNet_B extracts the CT image features, and the subnetwork UNet_A consists of two encoders to extract the PET/CT and PET image features. Secondly, multimodal feature extraction blocks are used to extract features for PET/CT and PET images in UNet_B network. Thirdly, a hybrid attention mechanism is added to the encoding paths of the UNet_A and UNet_B. Finally, a multiscale feature aggregation block is used for extracting feature maps of different scales of decoding path. On the lung tumor 18FDGPET/CT multimodal medical images dataset, experiments’ results show that the DSC, Recall, VOE, and RVD coefficients of APU‐Net are 96.86%, 97.53%, 3.18%, and 3.29%, respectively. APU‐Net can improve the segmentation accuracy of the adhesion between the lesion of complex shape and the normal tissue. This has positive significance for computer‐aided diagnosis.
During the summer, pregnant ewes experience heat stress, leading to the occurrence of IUGR lambs. This study aims to explore the biomarkers of exosomal miRNAs derived from umbilical plasma in both IUGR and normal Hu lambs. We establish a heat-stressed Hu sheep model during mid-late gestation and selected IUGR and normal lambs for analysis. Exosomes from umbilical plasma were separated and small RNA sequencing is used to identify differentially expressed miRNAs. Next, we utilize MiRanda to predict the target genes of the differentially expressed miRNAs. To further understand the biological significance of these miRNAs, we conduct GO and KEGG pathway enrichment analysis for their target genes. The study’s findings indicate that oar-miR-411a-5p is significantly downregulated in exosomes derived from umbilical plasma of IUGR lambs, while oar-miR-200c is significantly upregulated in the HS-IUGR group (P < 0.05). Furthermore, GO and KEGG enrichment analysis demonstrate that the target genes are involved in the Wnt, TGF-beta, and Rap1 signaling pathways. miRNAs found in exosomes have the potential to be utilized as biomarkers for both the diagnosis and treatment of IUGR fetuses.
18 January 2021 in Reproduction, Fertility and Development
Connexin (Cx) 43 is the most widely expressed gap junction protein in follicle granulosa cells and plays an important role in follicle development and growth. The aims of this study were to investigate the effects of LH on the expression of Cx43 and key proteins in the downstream Wnt-β/catenin signalling pathway and to explore the mechanism underlying the regulation of Cx43 expression in granulosa cells. Primary culture granulosa cells were obtained from 21-day-old Sprague-Dawley rats, and were treated with different concentrations of LH (150, 300 and 600 IU L−1). Cx43 expression in granulosa cells was detected using immunofluorescence. Western blotting was used to detect the expression of Cx43, β-catenin and Axin2 proteins (Axin2 is a protein that in humans is encoded by the AXIN2 gene, which presumably plays an important role in the regulation of the stability of β-catenin in the Wnt signaling pathway) in granulosa cells with and without FH535 treatment (a Wnt/β-catenin signalling pathway inhibitor). Cx43 expression was detected in the cytoplasm and cell membrane of granulosa cells. Treatment with a high concentration of LH (300 IU L−1) increased the expression of β-catenin and Axin2, as well as that of Cx43. FH535 treatment reduced the LH-induced increases in Cx43, β-catenin and Axin2. These results indicate that LH upregulates Cx43 expression in granular cells by activating the Wnt/β-catenin signalling pathway.