Purpose: The purpose of this study was to engineer deep learning (DL) models that can identify myopic maculopathy in patients with high myopia based on optical coherence tomography (OCT) images. Methods: An artificial intelligence (AI) system was developed using 2342 qualified OCT macular images from 1041 patients with pathologic myopia admitted to the Affiliated Eye Hospital of Wenzhou Medical University (WMU). We adopted an ResNeSt101 architecture to train five independent models to identify the following five myopic maculopathies: macular choroidal thinning, macular Bruch membrane (BM) defects, subretinal hyper-reflective material (SHRM), myopic traction maculopathy (MTM), and dome-shaped macula (DSM). We tested the models with an independent test dataset that included 450 images obtained from 297 patients with high myopia. Focal loss was used to address class imbalance, and optimal operating thresholds were determined according to the Youden Index. The performance was quantified using the area under the receiver operating characteristic (AUC), sensitivity, specificity, and confusion matrix. Results: For the identification of myopic maculopathy, the AUCs of receiver operating characteristic (ROC) curves were 0.927 to 0.974 for 5 myopic maculopathies. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists (56.16–99.73%). The diagnosis of it is also interpretable that we provide visual explanations clearly via heatmaps. Conclusions: We developed a convolutional neural network (CNN)-based DL AI system for detection and classification of myopic maculopathy in patients with high myopia using OCT macular images. Our AI system achieved sensitivities equal to or even better than those of junior retinal specialists. Translational Relevance: This AI system can be widely applied in sophisticated situations in large-scale high myopia screening.

Purpose: To investigate the characteristics of the optic nerve head (ONH) in myopia using swept-source optical coherence tomography (SS-OCT). Methods: Participants were divided into three groups according to the axial length (AL). The optic disc morphology, retinal nerve fiber layer (RNFL) thickness, and radial peripapillary capillary (RPC) vessel density (VD), optic disc tilt, rotation, Bruch's membrane opening distance (BMOD), border length (BL), border tissue angle, focal lamina cribrosa (LC) defects, β- and γ-zone peripapillary atrophy (PPA), microvasculature dropout (MvD), choroidal thickness (CT), and the choroidal vascularity index (CVI) were compared. Linear regression analysis evaluated relationships between spherical equivalent, AL, and ONH parameters. Results: One hundred five, 98, and 118 eyes were included in groups 1, 2, and 3, respectively. With AL increasing, the mean, superior and temporal CT, central mean and temporal, pericentral mean, inferior and nasal RPC VD, and temporal CVI decreased, whereas the mean and temporal RNFL thickness, optic disc, RIM and β-PPA area, presence and area of γ-PPA, BMOD and BL increased. Compared to other groups, group 3 depicted a larger cup area, more focal LC defect and total and juxtapapillary MvD; a lower central superior, inferior and nasal, pericentral superior, and temporal RPC VD. Group 1 demonstrated more tilted disc, larger inferior and nasal CT, mean, superior, inferior, and nasal CVI. Conclusions: Myopia eyes have larger ONH changes, PPAs, regional RNFL, and MvD, but smaller regional CTs, RPC VD, and CVIs. SS-OCT may be useful in detecting ONH variations during myopia.

Macular holes, one of the most common macular diseases, require timely treatment. The morphological changes on optical coherence tomography (OCT) images provided an opportunity for direct observation of the disease, and accurate segmentation was needed to identify and quantify the lesions. Developments of such algorithms had been obstructed by a lack of high-quality datasets (the OCT images and the corresponding gold standard macular hole segmentation labels), especially for supervised learning-based segmentation algorithms. In such context, we established a large OCT image macular hole segmentation (OIMHS) dataset with 3859 B-scan images of 119 patients, and each image provided four segmentation labels: retina, macular hole, intraretinal cysts, and choroid. This dataset offered an excellent opportunity for investigating the accuracy and reliability of different segmentation algorithms for macular holes and a new research insight into the further development of clinical research for macular diseases, which included the retina, lesions, and choroid in quantitative analyses.

Purpose: To investigate different modes of foveal regeneration after the closure of idiopathic macular hole (IMH) or highly myopic macular hole (HMMH) by vitrectomy with internal limiting membranes peeling or flap techniques. Methods: This retrospective observational study followed 47 IMH and 50 HMMH eyes for at least 6 months. Twenty four IMH and 25 HMMH eyes underwent internal limiting membrane peeling, whereas 23 IMH and 25 HMMH eyes received inverted internal limiting membrane flap technique. Spectral domain optical coherence tomography was used to analyze macular hole closure, foveal microstructures, and excessive gliosis as a foveal “peak-like” protuberance. Results: A single procedure closed all IMH (n = 47). For HMMH, the inverted group (n = 25, 100%) closed more macular hole than the peeling group (n = 14, 56.00%) (P < 0.001). Excessive gliosis only occurred in the inverted group, and there was a significant difference (P = 0.005) in incidence between IMH (three in 23 eyes, 13.04%) and HMMH (13 in 25 eyes, 52.00%). The axial length more than 29.985 mm enhanced the risk of excessive gliosis. Conclusion: The inverted internal limiting membrane flap efficiently treated refractory MHs but was prone to cause excessive gliosis in highly myopic eyes. Excessive elongation of the globe (axial length > 29.985 mm) was linked to excessive gliosis growth.