Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point clou...Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images.This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks(FCN).FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction.In this study,we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data.Then replace cross entropy loss function with focal loss function in the FCN model and train it again to produce the predictions.The results show that in all results from pre-trained model,fine-tuning,and FCN model with focal loss,the light poles and traffic signs are detected well and the transformed images have better performance than panoramic images in the prediction according to the Recall and IoU evaluation.展开更多
To the Editor:Diabetic kidney disease (DKD) is one of the major causes of end-stage renal failure.Progressive mesangial expansion in the glomerulus is widely recognized.More and more evidence shows that tubulointersti...To the Editor:Diabetic kidney disease (DKD) is one of the major causes of end-stage renal failure.Progressive mesangial expansion in the glomerulus is widely recognized.More and more evidence shows that tubulointerstitial fibrosis is also regarded as a prominent feature of DKD,in which tubular epithelial-mesenchymal transition (EMT) may play an important role.[1] During EMT,tubular epithelial cells lose their characteristic and produce high levels of myofibroblast makers such as α-smooth actin (α-SMA) which is the signature protein of EMT.[2]However,renal fibrogenesis is a complicated process in which the contribution of DKD is unknown.展开更多
Prednisone is a synthetic glucocorticoid that is commonly used in both human and veterinary medication.Now,it is also recognized as an emerging environmental contaminant.Pregnantwomenmay be exposed to prednisone activ...Prednisone is a synthetic glucocorticoid that is commonly used in both human and veterinary medication.Now,it is also recognized as an emerging environmental contaminant.Pregnantwomenmay be exposed to prednisone actively or passively throughmultiple pathways and cause developmental toxicity to the fetus.However,the impact of prenatal prednisone exposure(PPE)on fetal kidney development remains unclear.In this study,pregnant mice were administered prednisone intragastrically during full-term pregnancy with different doses(0.25,0.5,or 1 mg/(kg·day)),or at the dose of 1 mg/(kg·day)in different gestational days(GD)(GD0-9,GD10-18,or GD0-18).The pregnant mice were euthanized on GD18.HE staining revealed fetal kidney dysplasia,with an enlarged glomerular Bowman’s capsule space and a reduced capillary network in the PPE groups.The expression of the podocyte and the mesangial cell marker genes was significantly reduced in the PPE groups.However,overall gene expression in renal tubules and collecting ducts were markedly increased.All of the above effects were more pronounced in high-dose,full-term pregnancy,and female fetuses.Studies on the mechanism of the female fetal kidney have revealed that PPE reduced the expression of Six2,increased the expression of Hnf1β,Hnf4α,and Wnt9b,and inhibited the expression of glial cell line-derived neurotrophic factor(GDNF)and Notch signaling pathways.In conclusion,this study demonstrated that there is a sex difference in the developmental toxicity of PPE to the fetal kidney,and the time effect is manifested as full-term pregnancy>early pregnancy>mid-late pregnancy.展开更多
文摘Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images.This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks(FCN).FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction.In this study,we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data.Then replace cross entropy loss function with focal loss function in the FCN model and train it again to produce the predictions.The results show that in all results from pre-trained model,fine-tuning,and FCN model with focal loss,the light poles and traffic signs are detected well and the transformed images have better performance than panoramic images in the prediction according to the Recall and IoU evaluation.
基金from the Natural Science Foundation of Hubei Province(No.2017CFB779)the Fundamental Research Funds for the Central Universities(No.2042017kf0133).
文摘To the Editor:Diabetic kidney disease (DKD) is one of the major causes of end-stage renal failure.Progressive mesangial expansion in the glomerulus is widely recognized.More and more evidence shows that tubulointerstitial fibrosis is also regarded as a prominent feature of DKD,in which tubular epithelial-mesenchymal transition (EMT) may play an important role.[1] During EMT,tubular epithelial cells lose their characteristic and produce high levels of myofibroblast makers such as α-smooth actin (α-SMA) which is the signature protein of EMT.[2]However,renal fibrogenesis is a complicated process in which the contribution of DKD is unknown.
基金supported by the National Key Research and Development Program of China(No.2020YFA0803900)the National Natural Science Foundation of China(No.81872943)。
文摘Prednisone is a synthetic glucocorticoid that is commonly used in both human and veterinary medication.Now,it is also recognized as an emerging environmental contaminant.Pregnantwomenmay be exposed to prednisone actively or passively throughmultiple pathways and cause developmental toxicity to the fetus.However,the impact of prenatal prednisone exposure(PPE)on fetal kidney development remains unclear.In this study,pregnant mice were administered prednisone intragastrically during full-term pregnancy with different doses(0.25,0.5,or 1 mg/(kg·day)),or at the dose of 1 mg/(kg·day)in different gestational days(GD)(GD0-9,GD10-18,or GD0-18).The pregnant mice were euthanized on GD18.HE staining revealed fetal kidney dysplasia,with an enlarged glomerular Bowman’s capsule space and a reduced capillary network in the PPE groups.The expression of the podocyte and the mesangial cell marker genes was significantly reduced in the PPE groups.However,overall gene expression in renal tubules and collecting ducts were markedly increased.All of the above effects were more pronounced in high-dose,full-term pregnancy,and female fetuses.Studies on the mechanism of the female fetal kidney have revealed that PPE reduced the expression of Six2,increased the expression of Hnf1β,Hnf4α,and Wnt9b,and inhibited the expression of glial cell line-derived neurotrophic factor(GDNF)and Notch signaling pathways.In conclusion,this study demonstrated that there is a sex difference in the developmental toxicity of PPE to the fetal kidney,and the time effect is manifested as full-term pregnancy>early pregnancy>mid-late pregnancy.
