Accuracy of a deep convolutional neural network in the detection of myopic macular diseases using swept-source optical coherence tomography

Abstract

This study examined and compared outcomes of deep learning (DL) in identifying sweptsource optical coherence tomography (OCT) images without myopic macular lesions [i.e., no high myopia (nHM) vs. high myopia (HM)], and OCT images with myopic macular lesions [e.g., myopic choroidal neovascularization (mCNV) and retinoschisis (RS)]. A total of 910 SS-OCT images were included in the study as follows and analyzed by k-fold cross-validation (k = 5) using DL's renowned model, Visual Geometry Group-16: nHM, 146 images; HM, 531 images; mCNV, 122 images; and RS, 111 images (n = 910). The binary classification of OCT images with or without myopic macular lesions; the binary classification of HM images and images with myopic macular lesions (i.e., mCNV and RS images); and the ternary classification of HM, mCNV, and RS images were examined. Additionally, sensitivity, specificity, and the area under the curve (AUC) for the binary classifications as well as the correct answer rate for ternary classification were examined. The classification results of OCT images with or without myopic macular lesions were as follows: AUC, 0.970; sensitivity, 90.6%; specificity, 94.2%. The classification results of HM images and images with myopic macular lesions were as follows: AUC, 1.000; sensitivity, 100.0%; specificity, 100.0%. The correct answer rate in the ternary classification of HM images, mCNV images, and RS images were as follows: HM images, 96.5%; mCNV images, 77.9%; and RS, 67.6% with mean, 88.9%.Using noninvasive, easy-to-obtain swept-source OCT images, the DL model was able to classify OCT images without myopic macular lesions and OCT images with myopic macular lesions such as mCNV and RS with high accuracy. The study results suggest the possibility of conducting highly accurate screening of ocular diseases using artificial intelligence, which may improve the prevention of blindness and reduce workloads for ophthalmologists.

An Artificial-Intelligence–Based Automated Grading and Lesions Segmentation System for Myopic Maculopathy Based on Color Fundus Photographs

“… 31 Therefore, it may be more feasible to use other imaging information such as OCT images as training sources for such classifications. 36 …”

Advances in OCT Imaging in Myopia and Pathologic Myopia

“…Researchers have developed deep learning models to predict the uncorrected refractive error from OCT images, indicating that OCT could also be used to estimate refractive error [ 130 ]. OCT image-based deep learning algorithms showed robust performances in the detection of myopic maculopathy [ 131 , 132 , 133 ], glaucomatous optic neuropathy [ 134 ], as well as analysis of choroidal features [ 135 , 136 ]. In addition, machine learning of the preoperative AS-OCT metrics is able to provide high predictability of the ICL vault, indicating that it may be helpful for selecting the proper ICL size in clinical practice [ 137 ].…”

Applications of Artificial Intelligence in Myopia: Current and Future Directions

“…Other similar studies have also been reported, such as those identifying the different types of lesions of myopic maculopathy automatically from fundus photographs with DL models ( 40 , 41 ). In addition, OCT macular images were used for the development of CNN models to identify vision-threatening conditions, such as retinoschisis, macular holes and retinal detachment, in adults with high myopia, and the models obtained good sensitivity and AUC scores ( 42 , 43 ).…”