Impacts of angiotensin II on retinal artery changes in apolipoprotein E deficient mice

AIM:To investigate the impacts of angiotensin II(Ang II)on retinal artery changes in apolipoprotein E deficient(apoE^(-/-))mice.METHODS:ApoE^(-/-)male mice were infused by minipumps with Ang II at 1000 ng/kg·min(Ang II group)or saline(control group)for 28d.They were underwent ophthalmic fundus examination on day 0,14,and 28 of infusion.Histopathologic examination,ribonucleic acid(RNA)sequencing and local Ang II measurement of retinas were conducted.RESULTS:Ophthalmic fundus examination showed Ang II infusion promoted the formation of retinal arterial aneurysm-like lesions on day 28.Optical coherence tomography revealed the ganglion cell and inner plexiform layer(GCIPL)thickness in the control group was significantly thinner than that in Ang II group(P<0.001).Hematoxylin-eosin staining demonstrated diffused swelling of GCIPL layer and its disordered structure in Ang II group.Transmission electron microscopy showed Ang II infusion caused aggravation of atherosclerotic lesions,including increased swelling,roughness,disorganization of the retinal vasculature,and vacuoles formation.RNA-sequencing and gene ontology enrichment analysis demonstrated that the structure and function of cellular membrane might be disturbed and visual function might be compromised by Ang II.The local level of Ang II was higher in Ang II infusion group but did not show significant differences compared to the control group(P=0.086).CONCLUSION:Ang II infusion promotes the formation of retinal arterial aneurysm-like lesions in apoE^(-/-)mice,causing aggravation of atherosclerotic lesions,more severe disorganization of the retinal vasculature and disturbance of the cellular membrane.

Artificial intelligence can assist with diagnosing retinal vein occlusion

AIM:To assist with retinal vein occlusion(RVO)screening,artificial intelligence(AI)methods based on deep learning(DL)have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible.METHODS:A total of 8600 color fundus photographs(CFPs)were included for training,validation,and testing of disease recognition models and lesion segmentation models.Four disease recognition and four lesion segmentation models were established and compared.Finally,one disease recognition model and one lesion segmentation model were selected as superior.Additionally,224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models.RESULTS:Using the Inception-v3 model for disease identification,the mean sensitivity,specificity,and F1 for the three disease types and normal CFPs were 0.93,0.99,and 0.95,respectively,and the mean area under the curve(AUC)was 0.99.Using the DeepLab-v3 model for lesion segmentation,the mean sensitivity,specificity,and F1 for four lesion types(abnormally dilated and tortuous blood vessels,cotton-wool spots,flame-shaped hemorrhages,and hard exudates)were 0.74,0.97,and 0.83,respectively.CONCLUSION:DL models show good performance when recognizing RVO and identifying lesions using CFPs.Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists,DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.