Purpose: To identify anomalies of choroidal venous structure in highly myopic (HM) eyes.Methods: Widefield indocyanine green angiographic images of 175 HM eyes (refractive error # -6.0D diopters or axial length .26.5 mm) and 100 control eyes taken between January 2014 and December 2018 were reviewed.Results: There were no significant differences in age and gender between HM patients and controls. Three types of changes of large choroidal veins were found in 103 HM eyes (58.86%): Asymmetry of vortex veins in 44 eyes (25.14%), isolated long vein across the macula in 58 eyes (33.14%), and intervortex anastomoses in 25 eyes (14.29%). Similar changes in controls were found in 12 eyes (12%), 0 eye (0%), and 2 eyes (2%), respectively, which were significantly lower than those in the HM group (all P , 0.05). The patterns of asymmetry were affected by steeper staphyloma edges and anastomoses were observed through large trunks and terminal venules. In two eyes with large trunk anastomosis, attenuation of the less dominant vortex vein was observed afterward.Conclusion: Choroidal venous anomalies are more common in HM eyes than controls. Choroidal venous structure in HM eyes may be altering continuously, and such changes may underlie the development of myopic maculopathy.

No abstract

Purpose: It is common for physicians to be uncertain when examining some images. Models trained with human uncertainty could be a help for physicians in diagnosing pathologic myopia. Design: This is a hospital-based study that included 9176 images from 1327 patients that were collected between October 2015 and March 2019. Methods: All collected images were graded by 21 myopia specialists according to the presence of myopic neovascularization (MNV), myopic traction maculopathy (MTM), and dome-shaped macula (DSM). Hard labels were made by the rule of major wins, while soft labels were possibilities calculated by whole grading results from the different graders. The area under the curve (AUC) of the receiver operating characteristics curve, the area under precision-recall (AUPR) curve, F-score, and least square errors were used to evaluate the performance of the models. Results:The AUC values of models trained by soft labels in MNV, MTM, and DSM models were 0.985, 0.946, and 0.978; and the AUPR values were 0.908, 0.876, and 0.653 respectively. However, 0.56% of MNV "negative" cases were answered as "positive" with high certainty by the hard label model, whereas no case was graded with extreme errors by the soft label model. The same results were found for the MTM (0.95% vs none) and DSM (0.43% vs 0.09%) models. Conclusions: The predicted possibilities from the models trained by soft labels were close to the results made by myopia specialists. These findings could inspire the novel use of deep learning models in the medical field.

Introduction: Myopic macular neovascularization (MNV) is the most common cause of a reduction of central vision in eyes with pathologic myopia, and it can progress to macular atrophy in the long-term. The aim of this study was to determine the risk factors associated with the development of MNVs. Methods: There were 17,198 follow-up records from 5,409 eyes of 2,784 highly myopic patients that were reviewed. The general information and ophthalmic information in the records were studied. The significance of the correlations of factors associated with the development and predicting the development of myopic MNV were determined. Results: Being a woman (odds ratio [OR]: 0.727, P<0.001), having a longer axial length (OR = 0.948, P<0.001), a poorer baseline best-correct visual acuity (BCVA, OR = 2.098, P<0.001), having severe myopic maculopathy (overall: P<0.001), prior myopic MNV in the fellow eye (OR = 4.105, P<0.001), presence of patchy atrophy (overall P<0.001), lacquer cracks (OR = 1.718, P<0.001), prior foveal retinal detachment (RD, OR = 3.269, P<0.001), prior macular hole (MH, OR = 0.641, P <0.001), prior macular retinoschisis (OR = 1.533, P<0.001), and prior macular edema (OR = 1.508, P<0.001) were significantly correlated with the development of myopic MNV. Eyes with MNV and patchy atrophy would require an intensive follow-up examination for myopic patients as the fellow eye would have a risk of >70% for the development of myopic MNV in 3-years and nearly 80% in 5-years. Conclusions: Clinicians need to pay special attention to eyes with severe grades of myopic maculopathy, prior myopic MNV in the fellow eye, presence of patchy atrophy, and prior foveal retinal detachment to determine the onset of myopic MNV.