This article is devoted to the development of an algorithm for segmentation of visual signs of cystoid macular edema (including diabetic macular edema), age-related macular degeneration (choroidal neovascularization and retinal drusen), central serous choroidopathy and epiretinal membrane on optical coherence tomography (OCT) images. The paper presents the world statistics of patients with these pathologies, and their needs for regular ophthalmological screening. As a solution to the problem of regular screening, the use of telemedicine applications has been proposed. With the help of artificial intelligence, the main visual signs of these pathologies are determined, which are detected on digital OCT images of the retina. A list of scientific and technical problems that needed to be solved is presented: the collection of a training database, data markup and the choice of artificial neural network architectures for feature segmentation problems. The algorithm validation process is described and the current results are presented.
Purpose. Development of artificial intelligence (AI) algorithms for diagnosing of diabetic retinopathy (DR), diabetic macular edema (DME), age-related macular degeneration (AMD), vitreomacular interface abnormalities (VMA) through the analysis of OCT scans and fundus images. Material and methods. Fundus images of patients with DR and DME, OCT scans of patients with DME, AMD and VMA were used as training and validation databases. The volume of training databases was 3600 fundus images and 10 000 OCT scans, the volume of validation databases was 400 fundus images and 1000 OCT scans. For fundus images analysis algorithms accuracy, sensitivity, specificity, AUROC were calculated for the following structures: microaneurysms, intraretinal hemorrhages, hard exudates, soft exudates, retinal and optic disc neovascularization, preretinal hemorrhages, epiretinal fibrosis, laser coagulates. For OCT scan analysis algorithms, these metrics were calculated for the features: intraretinal cysts, subretinal fluid, pigment epithelium detachment, subretinal hyperreflective material, drusen, epiretinal membrane, full thickness macular hole, lamellar macular hole, vitreomacular traction. Results. For fundus images analysis algorithms, accuracy exceeded 93% for all features except soft exudates (88.3%) and neovascularization (88.0%), sensitivity exceeded 90% for all features except neovascularization (80.2%) and epiretinal fibrosis (72.5%), specificity exceeded 91% for all features except microaneurysms (80.5%), hard exudates (83.5%) and soft exudates (88.7%), AUROC exceeded 0.90 for all signs except epiretinal fibrosis (0.88), neovascularization (0.87), preretinal hemorrhages (0.89). For OCT analysis algorithms, accuracy exceeded 93% for all features, sensitivity exceeded 90% for all features except lamellar macular hole (87.22%), specificity exceeded 93% for all features, AUROC exceeded 0.93 for all features. Conclusion. An algorithm for high precision segmentation of pathological signs has been developed. Based on these AI algorithms, the Retina.AI ophthalmological platform was developed, which allows automated analysis of OCT scans and fundus images and diagnosing of DR, DME, AMD and VMA. The platform is available for testing at https://www.screenretina.com/ Keywords: artificial intelligence, ophthalmic screening, diabetic retinopathy, diabetic macular edema, age-related macular degeneration, vitreomacular interface abnormalities
This article is devoted to the development of an algorithm for segmentation of visual signs of DR and DMO. The paper references the global statistics of patients with diabetes mellitus and their need for regular fundus screening. We propose the use of telemedicine applications to the problem of regular ophthalmological screening of patients with diabetis mellitus. The main features of DR and DME are identified with the help of artificial intelligence algorithms. A list of scientific and technical problems that needed to be solved is presented: the collection of training data, their markup and the choice of artificial neural network architectures for the tasks of feature segmentation. The process of validation of the algorithm is described and the current results are presented.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.