AimMicroRNAs (miRNA) are a class of small, highly conserved noncoding RNA molecules, which contain 18–28 nucleotides and are involved in the regulation of gene expression. It has been proved that microRNAs play a very important role in several key cellular processes, such as cell differentiation, cell cycle progression, and apoptosis, as well as in autoimmune disease. One recently identified miRNA, miR-708-5p, has been demonstrated to have profound roles in suppressing oncogenesis in different types of tumors. However, the role of miR-708-5p in rheumatoid arthritis (RA) remains to be fully elucidated. Therefore, in this study, we are aiming to identify the role of miR-708-5p in RA.MethodsThe expression level of miR-708-5p in synovial tissues of patients with RA is much lower than in non-RA controls. The effects of miR-708-5p on cell apoptosis, colony formation, and migration in fibroblast-like synoviocytes were assessed in MH7A cells.ResultsResults showed that delivery of miR-708-5p mimics into synovial fibroblasts MH7A could induce cell apoptosis and inhibit colony formation and migration. In addition, miR-708-5p mimics significantly inhibit Wnt3a/β-catenin pathway activity both in transcription and protein level, which could be reversed by the addition of R-spondin 1, an activator of Wnt pathway. R-spondin 1 could also reverse the inhibition of cell survival and proliferation, which was induced by miR-708-5p mimics in MH7A. Moreover, injection of miR-708-5p mimics into collagen-induced rat RA model could ameliorate the RA index and decrease Wnt3a/β-catenin expression in rat joint tissues.ConclusionTherefore, we concluded that miR-708-5p is likely to be involved in RA pathogenesis via inhibition of Wnt3a/β-catenin pathway.

ETS‑domain containing protein (Elk1) is reported to be a member of the ETS oncogene family, and promotes tumorigenesis in cancer such as bladder, prostate and ovarian. Nevertheless, the role of Elk1 in thyroid cancer progression remains unclear. In the present study, we aimed to investigate the role and underlying molecular mechanism of Elk1 in thyroid cancer. The results indicated that Elk1 was significantly upregulated in thyroid cancer tissues and cells. We found that loss of Elk1 function obviously induced the expression of early growth response‑1 (Egr‑1) and PTEN, promoted apoptosis and constrained the proliferation of thyroid cancer cells. Furthermore, Egr‑1 inhibition obviously abrogated the induction of PTEN induced by Elk1 reduction. Moreover, Egr‑1 suppression prevented the promotion of apoptosis and the inhibition of cell proliferation caused by Elk1 reduction. In conclusion, Elk1 inhibition induced thyroid cancer cell apoptosis and restrained their proliferation by regulating Egr‑1/PTEN, indicating a potential role for Elk1 in thyroid cancer treatment.

Image segmentation is an important technique for segmenting images without overlapping each other and having their own features. It has been rapidly developed in the field of medical imaging, but there is currently a difference between classification accuracy and segmentation accuracy for medical image segmentation. In this paper, the deep convolutional neural network is combined with the cascading structure, and a uniform learning framework is established with the use conditional random field. This paper first adds a cascading structure under the deep convolutional neural networks (DCNN) framework to more effectively simulate the direct dependencies between spatial closure tags. Secondly, the conditional random field (CRF) is used for post-segmentation processing, which effectively solves the contradiction between the segmentation accuracy and the network depth and the number of pooling times in the traditional convolutional network. Secondly, the CRF is used for post-segmentation processing, which effectively solves the contradiction between the segmentation accuracy and the network depth and the number of pooling times in the traditional convolutional network. INDEX TERMS Image segmentation, deep convolutional neural network, cascade structure, conditional random field.

In traditional neural network integration, people adopt Boosting, Bagging and other methods to integrate traditional neural networks. The integration is complex, time-consuming and laborious, difficult to popularize and apply. This paper is not a continuation of this method, but another integration which is called by us morphological neural network integration (MNNI) or morphological associative memory integration (MAMI). These networks used in MAMI are a network family, with 10 family members, unified in the morphological associative memory framework. Various morphological associative memory networks can be directly used as individual networks to learn and work separately, and then synthesize to draw conclusions. The results of some experiments show that this method is not only feasible in theory, but also effective in practice. It can avoid the complexity of traditional integration method, make the integration structure simple and clear, easy to operate, save time, and therefore is a method of neural network integration with research and application value. The contribution of this paper lies in that: (1) it proposed the concept and method of MNNI and, (2) verified the effectiveness of MNNI through experiments and, (3) it has the characteristics of simplicity, saving time and labor and cost, with a good application prospect and, (4) thus promoting the development of morphological neural networks in theory and practice.

The essence of enterprise financial modeling is to use mathematical models to classify and sort out all kinds of enterprise information according to the main line of value creation and on this basis to complete the analysis, prediction, and value evaluation of enterprise financial situation. A reasonable financial model is also an effective means to reduce financial fraud. In this paper, a financial fraud identification model is constructed based on empirical data. In the process of model construction, the primary feature set is selected according to the financial fraud motivation theory, and then, the original feature set is obtained by Mann–Whitney test on the primary feature set, and the final fraud identification feature set is selected from the original feature set by using Relief and Boruta algorithms. Finally, based on the final fraud identification feature set, the data algorithms such as decision tree, logistic regression, support vector machine, and random forest are used to identify financial fraud. The experimental results show that the combination of financial fraud identification features constructed by the Relief algorithm and random forest model has the best recognition effect. The evaluation indexes of the G mean value and the F value were 75.86% and 78.33%, respectively.