Corrigendum: Small target detection with remote sensing images based on an improved YOLOv5 algorithm.

[This corrects the article DOI: 10.3389/fnbot.2022.1074862.].

α-Hederin inhibits the platelet activating factor-induced metastasis of HCC cells through disruption of PAF/PTAFR axis cascaded STAT3/MMP-2 expression.

Metastasis remains a crucial obstacle to the clinical treatment of hepatocellular carcinoma (HCC). Investigating the potential anti-tumor compounds from medicinal herb against HCC metastasis is of particular interest. As a triterpenoid saponin, α-Hederin has been reported to exhibit cytotoxicity for diverse cancer cell lines by inducing mitochondrial related apoptosis or autophagic cell death. Nevertheless, little is known about the inhibitory effect of α-Hederin on the metastasis of HCC and its underlying mechanisms. Here, we integrated well-established target prediction webtool and molecular docking methods to predict the potential targets for α-Hederin, and finally focused on PTAFR, the receptor for platelet-activating factor (PAF). Activation of PAF/PTAFR pathways has been reported to be contribution to the initiation and progression of cancer. We showed for the first time that non-cytotoxic concentration of α-Hederin inhibited cell migration and invasion induced by PAF in HCC cells, as well as lung metastasis in vivo. Moreover, we demonstrated α-Hederin reduced the PAF-induced matrix metalloproteinase-2 expression through inhibiting the activation of STAT3 in PAF stimulated HCC cells. These findings suggest that α-Hederin functions as a prospective inhibitor of PTAFR and may be utilized as an optional candidate for treatment of HCC.

Small target detection with remote sensing images based on an improved YOLOv5 algorithm.

Introduction: Small target detection with remote sensing images is a challenging topic due to the small size of the targets, complex, and fuzzy backgrounds. Methods: In this study, a new detection algorithm is proposed based on the YOLOv5s algorithm for small target detection. The data enhancement strategy based on the mosaic operation is applied to expand the remote image training sets so as to diversify the datasets. First, the lightweight and stable feature extraction module (LSM) and C3 modules are combined to form the feature extraction module, called as LCB module, to extract more features in the remote sensing images. Multi-scale feature fusion is realized based on the Res 2 unit, Dres 2, and Spatial Pyramid Pooling Small (SPPS) models, so that the receptive field can be increased to obtain more multi-scale global information based on Dres2 and retain the obtained feature information of the small targets accordingly. Furthermore, the input size and output size of the network are increased and set in different scales considering the relatively less target features in the remote images. Besides, the Efficient Intersection over Union (EIoU) loss is used as the loss function to increase the training convergence velocity of the model and improve the accurate regression of the model. Results and discussion: The DIOR-VAS and Visdrone2019 datasets are selected in the experiments, while the ablation and comparison experiments are performed with five popular target detection algorithms to verify the effectiveness of the proposed small target detection method.