Visual acuity (VA) is a measure of the ability to distinguish shapes and details of objects at a given distance and is a measure of the spatial resolution of the visual system. Vision is one of the basic health indicators closely related to a person’s quality of life. It is one of the first basic tests done when an eye disease develops. VA is usually measured by using a Snellen chart or E-chart from a specific distance. However, in some cases, such as the unconsciousness of patients or diseases, i.e., dementia, it can be impossible to measure the VA using such traditional chart-based methodologies. This paper provides a machine learning-based VA measurement methodology that determines VA only based on fundus images. In particular, the levels of VA, conventionally divided into 11 levels, are grouped into four classes and three machine learning algorithms, one SVM model and two CNN models, are combined into an ensemble method in order to predict the corresponding VA level from a fundus image. Based on a performance evaluation conducted using randomly selected 4000 fundus images, we confirm that our ensemble method can estimate with 82.4% of the average accuracy for four classes of VA levels, in which each class of Class 1 to Class 4 identifies the level of VA with 88.5%, 58.8%, 88%, and 94.3%, respectively. To the best of our knowledge, this is the first paper on VA measurements based on fundus images using deep machine learning.
Purpose: To determine the long-term reproducibility of axial length measurements and mean postoperative prediction errors after combined phacovitrectomy in patients with idiopathic epiretinal membranes. Design: Retrospective cohort study. Methods: The study included 43 patients who underwent combined phacovitrectomy and 30 patients who underwent only phacoemulsification. To determine the effect of vitrectomy, we compared patients treated with phacoemulsification only versus those treated with combined phacovitrectomy. Axial lengths were measured three times with a one-year interval, and the intraclass correlation coefficient (ICC), coefficient of variation (CV), and test–retest standard deviation (TRTSD) were assessed. Results: There was no significant change in axial length, and axial length measurements showed high reproducibility in all groups. ICC, CV, and TRTSD values were 0.997, 0.24%, and 0.056, respectively, for the vitrectomized eyes. The mean postoperative prediction error was −0.37 diopters(D) in vitrectomized eyes (p < 0.001), while it was +0.11 D in patients with phacoemulsification (p = 0.531). The myopic shift was more obvious in eyes with a shallower anterior chamber (p = 0.008) and a thicker lens (p = 0.025). Conclusions: Axial length measurements showed excellent long-term reproducibility at 2 years after combined phacovitrectomy. Myopic shifts were observed after combined phacovitrectomy, which was probably due to changes in the effective lens position after combined phacovitrectomy, rather than to changes in the axial length.
Fluorescein angiography is a crucial examination in ophthalmology to identify retinal and choroidal pathologies. However, this examination modality is invasive and inconvenient, requiring intravenous injection of a fluorescent dye. In order to provide a more convenient option for high-risk patients, we propose a deep-learning-based method to translate fundus photography into fluorescein angiography using Energy-based Cycle-consistent Adversarial Networks (CycleEBGAN) We propose a deep-learning-based method to translate fundus photography into fluorescein angiography using CycleEBGAN. We collected fundus photographs and fluorescein angiographs taken at Changwon Gyeongsang National University Hospital between January 2016 and June 2021 and paired late-phase fluorescein angiographs and fundus photographs taken on the same day. We developed CycleEBGAN, a combination of cycle-consistent adversarial networks (CycleGAN) and Energy-based Generative Adversarial Networks (EBGAN), to translate the paired images. The simulated images were then interpreted by 2 retinal specialists to determine their clinical consistency with fluorescein angiography. A retrospective study. A total of 2605 image pairs were obtained, with 2555 used as the training set and the remaining 50 used as the test set. Both CycleGAN and CycleEBGAN effectively translated fundus photographs into fluorescein angiographs. However, CycleEBGAN showed superior results to CycleGAN in translating subtle abnormal features. We propose CycleEBGAN as a method for generating fluorescein angiography using cheap and convenient fundus photography. Synthetic fluorescein angiography with CycleEBGAN was more accurate than fundus photography, making it a helpful option for high-risk patients requiring fluorescein angiography, such as diabetic retinopathy patients with nephropathy.
1 October 2022 in Journal of the Korean Ophthalmological Society