In human esophageal squamous cell carcinoma (ESCC), miR-34a was downregulated and could inhibit in vitro cell proliferation and migration. However, the underlying mechanism was not clear yet. The expression levels of mRNA and protein were detected by quantitative real-time PCR or western blotting, respectively. MiR-34a was knocked down or overexpressed and transfected into human ESCC cell lines ECA109 and TE-13, respectively. Cell migration and wound healing assays were used to examine the effect on migration and invasion in vitro. Animal models were used to examine the role of miR-34a in metastasis in vivo. Luciferase assay was carried out to validate the potential target of miR-34a. CD44 was upregulated and miR-34a was downregulated in ESCC tissues and cell lines. The linear regression analysis showed that CD44 expression was negatively correlated with the level of miR-34a. Luciferase assay showed that miR-34a interacted with a putative binding site in the CD44 3'UTR. MiR-34a was found to negatively regulate the expression of CD44. In vitro experiment showed that miR-34a overexpression inhibited ESCC cell invasion and migration; whereas miR-34a knockdown showed reversed results. MiR-34a also inhibited esophagus tumor growth and metastasis in vivo; whereas miR-34a knockdown showed reversed results. Finally, we found that CD44 knockdown reversed the effects of miR-34a knockdown on ESCC cell invasion and migration in vitro. MiRNA-34a suppresses invasion and metastatic in ESCC by regulating CD44.
ObjectiveDue to the small proportion of target pixels in computed tomography (CT) images and the high similarity with the environment, convolutional neural network-based semantic segmentation models are difficult to develop by using deep learning. Extracting feature information often leads to under- or oversegmentation of lesions in CT images. In this paper, an improved convolutional neural network segmentation model known as RAD-UNet, which is based on the U-Net encoder-decoder architecture, is proposed and applied to lung nodular segmentation in CT images.MethodThe proposed RAD-UNet segmentation model includes several improved components: the U-Net encoder is replaced by a ResNet residual network module; an atrous spatial pyramid pooling module is added after the U-Net encoder; and the U-Net decoder is improved by introducing a cross-fusion feature module with channel and spatial attention.ResultsThe segmentation model was applied to the LIDC dataset and a CT dataset collected by the Affiliated Hospital of Anhui Medical University. The experimental results show that compared with the existing SegNet [14] and U-Net [15] methods, the proposed model demonstrates better lung lesion segmentation performance. On the above two datasets, the mIoU reached 87.76% and 88.13%, and the F1-score reached 93.56% and 93.72%, respectively. Conclusion: The experimental results show that the improved RAD-UNet segmentation method achieves more accurate pixel-level segmentation in CT images of lung tumours and identifies lung nodules better than the SegNet [14] and U-Net [15] models. The problems of under- and oversegmentation that occur during segmentation are solved, effectively improving the image segmentation performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.