Open AccessEvaluation of the efficacy of neural network technology in the analysis of the condition of the optic nerve disc and peripapillary retina in healthy individuals examined for glaucoma
Author(s) -
А. Б. Мовсисян,
А. В. Куроедов,
В. В. Городничий,
Г.А. Остапенко,
С. В. Подвигин,
Ю. А. Рачинский,
С. Н. Ланин
Publication year - 2020
Publication title -
tihookeanskij medicinskij žurnal
Language(s) - English
Resource type - Journals
ISSN - 1609-1175
DOI - 10.34215/1609-1175-2020-3-43-47
Subject(s) - glaucoma , retina , optic nerve , optical coherence tomography , medicine , optic disc , ophthalmology , optometry , neuroscience , psychology
Objective: Evaluation of efficacy of the application of artificial intelligence technology and neural networks in the analysis of the condition of the optic disc and the peripapillary retina in healthy individuals. Methods : Prospective analysis of the condition of visual organs in 54 patients aged from 49 to 71 years (100 eyes) was conducted. The examination included autorefractometry, visometry, tonometry, automated perimetry, spectral domain optical coherence tomography, Heidelberg retina tomography. A pre-trained neural network evaluated only a photograph of the optic nerve disc and the peripapillary retina. Results : Neural network identified twelve images with suspected glaucoma, five of which were selected by medical experts. The comparison of all study groups has demonstrated the presence of statistically significant differences between them according to a range of visiometric indicators. Conclusions : The study results showed high efficiency of artificial intelligence and the prospects of its use for the diagnosis of glaucoma.