Detecting large-scale underwater cracks based on remote operated vehicle and graph convolutional neural network

It is of great significance to quickly detect underwater cracks as they can seriously threaten the safety of underwater structures.Research to date has mainly focused on the detection of above-water-level cracks and hasn’t considered the large scale cracks.In this paper,a large-scale underwater crack examination method is proposed based on image stitching and segmentation.In addition,a purpose of this paper is to design a new convolution method to segment underwater images.An improved As-Projective-As-Possible(APAP)algorithm was designed to extract and stitch keyframes from videos.The graph convolutional neural network(GCN)was used to segment the stitched image.The GCN’s m-IOU is 24.02%higher than Fully convolutional networks(FCN),proving that GCN has great potential of application in image segmentation and underwater image processing.The result shows that the improved APAP algorithm and GCN can adapt to complex underwater environments and perform well in different study areas.

Specific bFGF targeting of KIM-1 in ischemic kidneys protects against renal ischemia-reperfusion injury in rats

Renal ischemia-reperfusion(I/R)injury is one of the major causes of acute kidney injury.However,there is still no effective treatment for this disease.Basic fibroblast growth factor(bFGF)has been reported to be beneficial for recovery from ischemic diseases.It is vital to increase the local concentration and reduce the diffusion of bFGF in vivo for renal I/R injury therapy.A targeted growth factor delivery system that responds to specific biological signals in the regenerative environment to guide release has been highlighted in tissue repair.In the present study,a specific peptide was fused with bFGF and called bFGF-kidney injury targeting(KIT-bFGF),and this compound specifically targeted kidney injury molecule-1 both in hypoxic renal HK-2 cells in vitro and ischemic kidneys in vivo after intravenous injection.When administered to rat models of renal I/R injury,KIT-bFGF attenuated renal tubule damage and fibrosis,and promoted functional recovery compared to the effects of native bFGF and the control.We also investigated the mechanism by which KIT-bFGF activated the ERK1/2 and Akt signaling pathways to significantly reduce apoptosis and protect against ischemic injury in the kidney.These results demonstrated that targeted delivery of KIT-bFGF could be an effective strategy for the treatment of renal I/R injury.