Endothelial inflammatory responses promote the development and progression of atherosclerosis. It was reported that Toll-like receptors 2 (TLR2) is associated with endothelial inflammation. However, the effect of TLR2 on inflammatory responses in human coronary artery endothelial cells (HCAECs) remains largely unknown. Here, we tested the hypothesis that TLR2 can enhance inflammatory reactions in HCAECs after stimulated by TLR2 agonist. First, we used CRISPR-Cas9 technology to knockout TLR2 gene in HCAECs. Then, TLR2-KO and wild type HCAECs were treated with TLR2 agonist peptidoglycan (PGN). The expression levels of intercellular cell adhesion molecule-1 (ICAM-1), interleukin-6 (IL-6), and interleukin-8 (IL-8) were analyzed by real-time PCR, Western blot, and ELISA. The expression status of myeloid differentiation primary response gene 88 (MyD88), phosphorylated IRAK-1 (pIRAK-1) and phosphorylated NF-κB (pNF-κB) were detected by Western blot. Our results show that after treated with TLR2 agonist, the expression levels of ICAM-1, IL-6, and IL-8 were downregulated in TLR2-KO cells compared to those of wild type cells. Further, Western blots of MyD88, pIRAK-1, and pNF-κB show that the expression levels of these pro-inflammatory molecules were much lower in TLR2-KO cells compared to that of wild type cells by stimulating with TLR2 agonist. We suggest that TLR2 may affect inflammatory reaction in HCAECs by introducing pro-inflammatory molecules like MyD88, pIRAK-1, and pNF-κB.

Autonomous driving requires accurate and detailed Bird's Eye View (BEV) semantic segmentation for decision making, which is one of the most challenging tasks for high-level scene perception. Feature transformation from frontal view to BEV is the pivotal technology for BEV semantic segmentation. Existing works can be roughly classified into two categories, i.e., Camera model-Based Feature Transformation (CBFT) and Camera model-Free Feature Transformation (CFFT). In this paper, we empirically analyze the vital differences between CBFT and CFFT. The former transforms features based on the flat-world assumption, which may cause distortion of regions lying above the ground plane. The latter is limited in the segmentation performance due to the absence of geometric priors and time-consuming computation. In order to reap the benefits and avoid the drawbacks of CBFT and CFFT, we propose a novel framework with a Hybrid Feature Transformation module (HFT). Specifically, we decouple the feature maps produced by HFT for estimating the layout of outdoor scenes in BEV. Furthermore, we design a mutual learning scheme to augment hybrid transformation by applying feature mimicking. Notably, extensive experiments demonstrate that with negligible extra overhead, HFT achieves a relative improvement of 13.3% on the Argoverse dataset and 16.8% on the KITTI 3D Object datasets compared to the best-performing existing method. The codes are available at https://github.com/JiayuZou2020/HFT.

No abstract

No abstract

No abstract