10-year fundus tessellation progression and retinal vein occlusion

AIM： To access the 10-year fundus tessellation progression in patients with retinal vein occlusion. METHODS： The Beijing Eye Study 2001/2011 is a populationbased longitudinal study. The study participants underwent a detailed physical and ophthalmic examination. Degree of fundus tessellation was graded by using fundus photographs of the macula and optic disc. Progression of fundus tessellation was calculated by fundus tessellation degree of 2011 minus degree of 2001. Fundus photographs were used for assessment of retinal vein occlusion. RESULTS： The Beijing Eye Study included 4403 subjects in 2001, 3468 subjects was repeated in 2011. Assessment of retinal vein obstruction and fundus tessellation progression were available for 2462 subjects（71.0%）, with 66 subjects fulfilled the diagnosis of retinal vein occlusion. Of the 66 participants, 59 participants with unilateral branch retinal vein occlusion, 5 participants with unilateral central retinal vein occlusion, 1 participant with bilateral branch retinal vein occlusion, and 1 participant with branch retinal vein occlusion in one eye and central retinal vein occlusion in the other eye. Mean degree of peripapillary fundus tessellation progression were significantly higher in the whole retinal vein occlusion group（0.33±0.39, P〈0.001）, central retinal vein occlusion group（0.71±0.8, P=0.025） and branch retinal vein occlusion group（0.29±0.34, P=0.006） than the control group（0.20±0.26）. After adjustment for age, prevalence of tilted disc, change of best corrected visual acuity, axial length, progression of peripapillary fundus tessellation was associated with the presence of retinal vein occlusion（P=0.004; regression coefficient B, 0.094; 95%CI, 0.029, 0.158; standardized coefficient B, 0.056）. As a corollary, after adjusting for smoking duration, systolic blood pressure, anterior corneal curvature, prevalence of RVO was associated with more peripapillary fundus tessellation progression（P〈0.001; regression coefficient B： 1.257; OR： 3.517; 95%CI： 1.777, 6.958）. CONCLUSION： Peripapillary fundus tessellation progresses faster in individuals with retinal vein occlusion. This may reflect the thinning and hypoperfusion of choroid in patients with retinal vein occlusion.

Automated detection of myopic maculopathy from color fundus photographs using deep convolutional neural networks

Background:Myopic maculopathy(MM)has become a major cause of visual impairment and blindness worldwide,especially in East Asian countries.Deep learning approaches such as deep convolutional neural networks(DCNN)have been successfully applied to identify some common retinal diseases and show great potential for the intelligent analysis of MM.This study aimed to build a reliable approach for automated detection of MM from retinal fundus images using DCNN models.Methods:A dual-stream DCNN(DCNN-DS)model that perceives features from both original images and corresponding processed images by color histogram distribution optimization method was designed for classification of no MM,tessellated fundus(TF),and pathologic myopia(PM).A total of 36,515 gradable images from four hospitals were used for DCNN model development,and 14,986 gradable images from the other two hospitals for external testing.We also compared the performance of the DCNN-DS model and four ophthalmologists on 3000 randomly sampledfundus images.Results:The DCNN-DS model achieved sensitivities of 93.3%and 91.0%,specificities of 99.6%and 98.7%,areas under the receiver operating characteristic curves(AUCs)of 0.998 and 0.994 for detecting PM,whereas sensitivities of 98.8%and 92.8%,specificities of 95.6%and 94.1%,AUCs of 0.986 and 0.970 for detecting TF in two external testing datasets.In the sampled testing dataset,the sensitivities of four ophthalmologists ranged from 88.3%to 95.8%and 81.1%to 89.1%,and the specificities ranged from 95.9%to 99.2%and 77.8%to 97.3%for detecting PM and TF,respectively.Meanwhile,the DCNN-DS model achieved sensitivities of 90.8%and 97.9%and specificities of 99.1%and 94.0%for detecting PMand T,respectively.Conclusions:The proposed DCNN-DS approach demonstrated reliable performance with high sensitivity,specificity,and AUC to classify different MM levels on fundus photographs sourced from clinics.It can help identify MM automatically among the large myopic groups and show great potential for real-life applications.