FGCN: Image-Fused Point Cloud Semantic Segmentation with Fusion Graph Convolutional Network.

In interpreting a scene for numerous applications, including autonomous driving and robotic navigation, semantic segmentation is crucial. Compared to single-modal data, multi-modal data allow us to extract a richer set of features, which is the benefit of improving segmentation accuracy and effect. We propose a point cloud semantic segmentation method, and a fusion graph convolutional network (FGCN) which extracts the semantic information of each point involved in the two-modal data of images and point clouds. The two-channel k-nearest neighbors (KNN) module of the FGCN was created to address the issue of the feature extraction's poor efficiency by utilizing picture data. Notably, the FGCN utilizes the spatial attention mechanism to better distinguish more important features and fuses multi-scale features to enhance the generalization capability of the network and increase the accuracy of the semantic segmentation. In the experiment, a self-made semantic segmentation KITTI (SSKIT) dataset was made for the fusion effect. The mean intersection over union (MIoU) of the SSKIT can reach 88.06%. As well as the public datasets, the S3DIS showed that our method can enhance data features and outperform other methods: the MIoU of the S3DIS can reach up to 78.55%. The segmentation accuracy is significantly improved compared with the existing methods, which verifies the effectiveness of the improved algorithms.

RGD Peptide and PAD4 Inhibitor-Loaded Gold Nanorods for Chemo-Photothermal Combined Therapy to Inhibit Tumor Growth, Prevent Lung Metastasis and Improve Biosafety.

PURPOSE: A targeted drug delivery system that combines protein-arginine deiminase type-4 (PAD4) inhibitors YW3-56 (356) with PTT of NPs is constructed to both decrease the accumulation of gold in metabolic organs and reduce the dose of chemotherapeutic agents. PATIENTS AND METHODS: In vitro cytotoxicity test and in vivo S180 tumor-bearing mice model were used to compare antitumor activity of 356-modified gold nanospheres and nanorods. The A549 tumor-bearing mice model was also exploited in antitumor assessment. In addition, ICP-MS, blood cell analyzer and blood biochemistry analyzer are applied for assessing the biosafety of NPs. RESULTS: Both 356-modified gold nanospheres and nanorods showed antitumor activity. However, 356-loaded gold nanorods are found to have better tumor inhibitory activity than 356-loaded gold nanospheres in the presence of laser and without laser irradiation. Thus, 356-loaded gold nanorods are selected to be applied for chemo-photothermal combined therapy on in vivo. We find that combination therapy could inhibit tumor growth and reduce lung tumor metastasis and inflammatory infiltration compared with individual therapy. It triggers apoptosis in tumor tissue observed by TUNEL assay and TEM pictures. CONCLUSION: Thus, an RGD targeting and PAD4 inhibitor-loaded system are established based on chemo-photothermal combined therapy. It could inhibit tumor growth, prevent lung metastasis and improve biosafety.