No abstract

No abstract

No abstract

Automatic extraction of road information from remote sensing images is widely used in many fields, such as urban planning and automatic navigation. However, due to interference from noise and occlusion, the existing road extraction methods can easily lead to road discontinuity. To solve this problem, a road extraction network with bidirectional spatial information reasoning (BSIRNet) is proposed, in which neighbourhood feature fusion is used to capture spatial context dependencies and expand the receptive field, and an information processing unit with a recurrent neural network structure is used to capture channel dependencies. BSIRNet enhances the connectivity of road information through spatial information reasoning. Using the public Massachusetts road dataset and Wuhan University road dataset, the superiority of the proposed method is verified by comparing its results with those of other models.

Aging leads to systemic metabolic disorders including nonalcoholic steatohepatitis (NASH). Here, we showed that aging-induced liver sinusoidal endothelial cell (LSEC) senescence accelerated liver sinusoid capillarization and promoted steatohepatitis by reprogramming liver endothelial zonation and inactivating pericentral endothelium-derived C-kit. Abrogation of endothelial C-kit triggered cellular senescence which disturbed LSEC homeostasis. During diet-induced NASH development, C-kit deletion aggravated hepatic steatosis and exacerbated NASH-associated fibrosis and inflammation. Mechanistically, CXCR4/SDF-1 signaling was inhibited by C-kit. Blocking CXCR4/SDF-1 signaling by AMD3100 abolished LSEC-macrophage crosstalk and recovered the aggravated NASH in C-kit deficient mice. For therapeutic purpose, C-kit+ LSECs were implanted into NASH or aged mice, which counteracted LSEC senescence and improved diet or aging-induced NASH by restoring the homeostasis of pericentral liver endothelium.