Total flavonoids of Rhizoma Drynariae (TFRD) have been shown to have beneficial effects on osteoarthritis (OA) clinically, but the mechanisms have not been elucidated. In this study, we investigated the effect of TFRD on articular cartilage in an OA rat model established by the Hulth method and in SW1353 chondrocytes induced by the proinflammatory factor interleukin-1β (IL-1β). The results showed that TFRD could alleviate the pathological changes in knee cartilage in OA model rats. In vivo, the qPCR analysis indicated that the mRNA levels of matrix metalloproteinases, MMP-1, MMP-3, and MMP-13, were decreased, while tissue inhibitor of matrix metalloproteinases- (TIMP-) 4 was increased in cartilage, and these changes could be partially prevented by TFRD. In vitro experiments showed that IL-1β could significantly increase the expression of MMP-1, MMP-3, and MMP-13 and decrease the expression of TIMP-4 in SW1353 cells at the mRNA and protein levels. TFRD could increase the expression of MMP-3 and MMP-13 and decrease the expression of TIMP-4. Transfection of siRNA and addition of pathway inhibitors were used to clarify that inhibition of NF- and PI3K/AKT pathway decreased MMP-1, MMP-3, and MMP-13 and increased TIMP-4 expression. We also found that in IL-1β-induced SW1353 cells, TFRD pretreatment had a modest inhibitory effect on p-AKT (Ser473) and reversed the increase of nuclear factor kappa-B (NF-) p65 in nuclear fraction and the decrease of inhibitor of NF- - in the cytosolic fraction. Further immunofluorescence confirmed that TFRD can inhibit IL-1β-induced NF- p65 translocation to the nucleus to some extent. In conclusion, TFRD showed chondroprotective effects by restoring the MMP/TIMP balance in OA models by suppressing the activation of the NF- and PI3K/AKT pathways.
1 April 2021 in Journal of Physics: Conference Series
The classification of superpixel images by graph neural networks has gradually become a research hotspot. It is a crucial issue to embed super-pixel images from lowdimensional to high-dimensional so as to turn complex image information into graph signals. This paper proposes a method for image classification using a graph neural network (GNN) model. We convert the input image into a region adjacency graph (RAG) composed of superpixels as nodes, and use residual and concat structure to extract deep features. Finally, the loss function that increases the distance between classes and compactness within classes is used as supervision. Experiments have been tested with different numbers of superpixels on multiple datasets, and the results show that our method has a great performance in superpixel images classification.
3 March 2022 in International Journal of Rheumatic Diseases
Lane detection in complex road scenes is still a challenging task due to poor lighting conditions, interference of irrelevant road markings or signs, etc. To solve the problem of lane detection in the various complex road scenes, we proposed a geometric attention-aware network (GAAN) for lane detection. The proposed GAAN adopted a multi-task branch architecture, and used the attention information propagation (AIP) module to perform communication between branches, then the geometric attention-aware (GAA) module was used to complete feature fusion. In order to verify the lane detection effect of the proposed model in this paper, the experiments were conducted on the CULane dataset, TuSimple dataset, and BDD100K dataset. The experimental results show that our method performs well compared with the current excellent lane line detection networks.
Although most images in industrial applications have fewer targets and simple image backgrounds, binarization is still a challenging task, and the corresponding results are usually unsatisfactory because of uneven illumination interference. In order to efficiently threshold images with nonuniform illumination, this paper proposes an efficient global binarization algorithm that estimates the inhomogeneous background surface of the original image constructed from the first k leading principal components in the Gaussian scale space (GSS). Then, we use the difference operator to extract the distinct foreground of the original image in which the interference of uneven illumination is effectively eliminated. Finally, the image can be effortlessly binarized by an existing global thresholding algorithm such as the Otsu method. In order to qualitatively and quantitatively verify the segmentation performance of the presented scheme, experiments were performed on a dataset collected from a nonuniform illumination environment. Compared with classical binarization methods, in some metrics, the experimental results demonstrate the effectiveness of the introduced algorithm in providing promising binarization outcomes and low computational costs.