Abstract: The present disclosure provides an isolated recombinant oncolytic adenovirus, a pharmaceutical composition, and uses thereof for drugs for treatment of tumors and/or cancers. The recombinant oncolytic adenovirus is a selectively replicating oncolytic adenovirus, and the genome of the recombinant oncolytic adenovirus is integrated with a coding sequence of exogenous shRNA capable of inhibiting PDL1 expression in tumor cells. The replication capability of the virus in normal primary cells is much lower than the replication capability of the virus in tumor cells. Moreover, the expressed shPDL1 can significantly reduce the level of PDL1 protein highly expressed in tumor cells. Thus, the oncolytic killing effect of the oncolytic virus and the anti-tumor immunostimulatory effect of immune cells produce a synergistic effect.

Abstract: An intelligent method for efficiently classifying concrete cracks from large amounts of image data is proposed, named inverted residual (IR) 7-Efficient Channel Attention and Convolutional Block Attention Module (EC) network. The IR7-EC network consists of a convolutional layer, seven inverted residual-ECA structures, a CBAM attention mechanism, a pooling layer, and multiple fully connected layers that are sequentially connected. The inverted residual-ECA structure consists of two components: a depthwise separable convolution-based inverted residual structure and an ECA attention mechanism. The new inverted residual structure facilitates the feature extraction of concrete cracks. Compared to conventional network structures like VGG and Resnet, the proposed IR7-EC network excels in both accuracy and efficiency. Once the IR7-EC network is fully trained, it can accurately classify various types of concrete cracks in captured images.