ABSTRACT
AIM:To observe the changes of macular morphology and microcirculation in myopic maculopathy(MM), and investigate theirs correlation and effects on vision.METHODS: Case-control study. A total of 165 patients(189 eyes)with high myopia and 154 healthy volunteers(154 eyes)from October 2016 to December 2018 were selected. According to the classification of Meta-analysis for pathologic myopia(META-PM), participants were divided into M0 group(category 0, 41 eyes), M1 group(category 1, 53 eyes), M2 group(category 2 and 3, 52 eyes), and myopic choroidal neovascularization(mCNV)group(43 eyes). All participants underwent optical coherence tomography angiography(OCTA)examination. Morphological and microcirculation parameters of retina at different layers were compared between groups. Pearson correlation was used to assess the correlation between morphological and microcirculation parameters. Correlations between vision and other parameters were analyzed using multiple linear regression analysis.RESULTS:Foveal full retinal thickness(FRT)and outer retinal thickness(ORT)were all lower in M0, M1 and M2 groups than those of control group(all P<0.01). Foveal superficial capillary plexus vessel density(SVD)and deep capillary plexus vessel density(DVD)were all lower in M2 and mCNV groups than those of the control group(all P<0.01). Parafoveal FRT and ORT were all lower in M0, M1, M2 and mCNV groups than those of the control group(all P<0.01). Parafoveal inner retinal thickness(IRT), SVD and DVD were all lower in M2 and mCNV groups than those of the control group(all P<0.01). Subfoveal choroidal thickness(SFCT)and choroid capillaries vessel density(CVD)were all lower in M0, M1, M2 and mCNV groups than those of the control group(all P<0.01). Foveal vessel density of retina and choroid were positively correlated with its thickness in patients with MM without CNV(all P<0.05). Multivariate analysis showed that axial length(AL), diffuse or patchy chorioretinal atrophy were influencing foctors of best corrected visual acuity(BCVA; all P<0.01).CONCLUSION:Retinal morphological changes precede microcirculation changes in MM. Most of all, ORT changes precede IRT changes. Foveal vessel density of retina and choroid were positively correlated with its thickness. The main influencing factors of BCVA were AL and types of MM.
ABSTRACT
The main fundus changes of pathologic myopia (PM) are posterior staphyloma (PS) and myopic maculopathy (MM), which includes myopic atrophy maculopathy (MAM), myopic tractional maculopathy (MTM), myopic neovascular maculopathy (MNM) and so on. The clinical manifestations of PM-related fundus lesions are complex, and the classification of PM has been a research hotspot in recent years. The proposal of each classification shows an increasing understanding of PM, and each classification has its advantages but also imperfections. For MM, it is recommended to refine the MTM classification based on the ATN classification and adjust it according to the internal correlation between MAM and MNM. The rapid development of modern imaging technology will promote the continuous update of the classification, and its further improvement will also help to understand the development process of PM, which has important clinical value in preventing its occurrence and progression.
ABSTRACT
The main fundus changes of pathologic myopia (PM) are posterior staphyloma (PS) and myopic maculopathy (MM), which includes myopic atrophy maculopathy (MAM), myopic tractional maculopathy (MTM), myopic neovascular maculopathy (MNM) and so on. The clinical manifestations of PM-related fundus lesions are complex, and the classification of PM has been a research hotspot in recent years. The proposal of each classification shows an increasing understanding of PM, and each classification has its advantages but also imperfections. For MM, it is recommended to refine the MTM classification based on the ATN classification and adjust it according to the internal correlation between MAM and MNM. The rapid development of modern imaging technology will promote the continuous update of the classification, and its further improvement will also help to understand the development process of PM, which has important clinical value in preventing its occurrence and progression.
ABSTRACT
Objective:To develop a fully automatic detection system based on the deep convolution neural network (DCNN) for screening myopic maculopathy (MMD) and identifying its severity.Methods:Six thousand and sixty-eight fundus images were collected from Anhui No.2 Provincial People's Hospital to construct the training set, and the public fundus images data set was selected to construct the test set.The fundus images were preprocessed and amplified, and the grade of MMD lesions was labeled and the data was cleaned.The automatic MMD detection system proposed was composed of two-level network.The first level network structure was used to identify the presence of MMD, and the second level network structure was used to diagnose the severity of MMD lesions.The accuracy, specificity, sensitivity, precision, F1 value, area under curve (AUC) and Kappa coefficient of four commonly used DCNN network methods, VGG-16, ResNet50, Inception-V3 and Densenet, in MMD screening and severity recognition tasks were compared and analyzed.The study protocol adhered to the Declaration of Helsinki and was approved by a Medical Ethics Committee of Anhui No.2 Provincial People's Hospital ([L]2019-013).Results:The performance of Densenet network model was the best in the MMD screening task, with the sensitivity, specificity, accuracy, F1 value and AUC of 0.898, 0.918, 0.919, 0.908 and 0.962, respectively.The Inception-v3 network model was the best in MMD severity recognition task, with sensitivity, specificity, accuracy, F1 value and AUC of 0.839, 0.952, 0.952, 0.892, and 0.965, respectively.The visualization results showed that the network structure model used in this study could automatically learn the clinical characteristics of MMD severity, and accurately identify diffuse and focal chorioretinal atrophy areas.Conclusions:The MMD screening method using fundus images based on DCNN can automatically extract the effective features of MMD, and accurately screen MMD and judge its severity, which can provide effective assistance in clinical practice.