Evaluation 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
A. B. Movsisyan,
A. V. Kuroyedov,
V. V. Gorodnichy,
G. A. Ostapenko,
S. V. Podvigin,
Yu. A. Rachinsky,
S. N. Lanin https://doi.org/10.34215/1609-1175-2020-3-43-47
Abstract
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.
About the Authors
A. B. Movsisyan
Pirogov Russian National Research Medical University;
Veterans Hospital No. 2
Russian Federation
Russian Federation
MD, postgraduate student,
1 Ostrovityanova St., Moscow, 117997
A. V. Kuroyedov
Pirogov Russian National Research Medical University;
Mandryka Central Military Clinical Hospital
Russian Federation
Russian Federation
MD, PhD, professor, 1 Ostrovityanova St., Moscow, 117997;
head of the Ophthalmology Department, 8a B. Olenya St., Moscow, 107014
V. V. Gorodnichy
Mandryka Central Military Clinical Hospital
Russian Federation
Russian Federation
MD,
8a B. Olenya St., Moscow, 107014
G. A. Ostapenko
Voronezh State Technical University
Russian Federation
Russian Federation
PhD, professor,
14 Moskovsky Ave., Voronezh, 394026
S. V. Podvigin
Angels IT Group
Russian Federation
Russian Federation
53 Karl Marx St., Voronezh, 394036
Yu. A. Rachinsky
Angels IT Group
Russian Federation
53 Karl Marx St., Voronezh, 394036
Russian Federation
53 Karl Marx St., Voronezh, 394036
S. N. Lanin
Makarov State Ophthalmology Clinical Hospital
Russian Federation
Russian Federation
MD, PhD,
1v Nikitina St., Krasnoyarsk, 660022
References
1. Egorov EA, Astahov YuS, Erichev VP. National glaucoma guideline for practitioners. Moscow: GEOTARMedia; 2015:456 (In Russ).
2. Weinreb RN, Garway-Heath T, Leung C, Medeiros FA, Leibmann J. Diagnosis of primaryopen glaucoma. WGA Consensus Series 10. Amsterdam: Kugler Publications; 2017.
3. Oliveira DAB, Vellasco MBR, Oliveira MB, Yamane R. Application of neural networks in aid for diagnosis for patients with glaucoma. Int Conf Bio-inspired Sys Sign Proc. 2009;1(1);139–145. doi: 10.5220/0001547401390145
4. Bizios D, Heijl A, Hougaard JL, Bengtsson B. Machine learning classifiers for glaucoma diagnosis based on classification of retinal nerve fibre layer thickness parameters measured by Stratus OCT. Acta Ophthalmol. 2010:88:44–52.
5. Karthikeyan S, Rengarajan N. A thorough investigation on automated diagnosis of glaucoma. Int J Adv Res Comp Sci. 2012;3(4):294–302.
6. Vidotti VG, Costa VP, Silva FR, Resende GM, Cremasco F, Dias M, Gomi ES. Sensitivity and specificity of machine learning classifiers for glaucoma diagnosis using Spectral Domain OCT and standard automated perimetry. Arq Bras Oftalmol. 2013;76(3):170–4.
7. Thompson AC, Jammal AA, Medeiros FA. A deep learning algorithm to quantify neuroretinal rim loss from optic disc photographs. Am J Ophthalmol. 2019;201:9–18.
8. Medeiros FA, Jammal AA, Thompson AC. From machine to machine: an OCT-trained deep learning algorithm for objective quantification of glaucomatous damage in fundus photographs. Ophthalmology. 2019;126(4):513–21.
9. Kuroyedov AV, Ostapenko GA, Mitroshina KV, Movsisyan AB. State of the art of glaucoma diagnosis: neural networks and artificial intelligence. Russian Journal of Clinical Ophthalmology. 2019;19(4):230–7 (in Russ).
10. Gaponko OV, Kuroyedov AV, Gorodnichy VV, Kondrakova IV, Krinitsyna EA. Traditional and modern morphometric characteristics of the neuroretinal rim in early glaucoma diagnosis. Russian Journal of Glaukoma. 2018; 17(3):3–14 (in Russ).
11. Avdeev RV, Alexandrov AS, Arapiev MU, Bakunina NA, Basinskiy AS, Belaya DA, et al. Suspected glaucoma and early stage glaucoma: differential diagnostic criteria. Russian Ophthalmological Journal. 2017;10(4):5–15 (In Russ.)
12. Reis AS, O’Leary N, Yang H, Sharpe GP, Nicolela MT, Burgoyne CF, Chauhan BC. Influence of clinically invisible, but optical coherence tomography detected, optic disc margin anatomy on neuroretinal rim evaluation. IOVS. 2012;53(4):1852–60.
13. Chauhan CB, Burgoyne CF. From clinical examination of the optic disc to clinical assessment of the optic nerve head: A paradigm change. Am J Ophthalmol. 2013;156(2):218–27.
14. Kurysheva NI, Kiseleva TI, Ardzhevnishvili TD, Fomin AV, Khodak NA, Orozbaeva GM, Ryzhkov PK. The choroid and glaucoma: Choroidal thickness measurement by means of optical coherence tomography. Russian Journal of Glaukoma. 2013;3:73–82 (In Russ).
15. Curcio CA, Johnson M. Structure, function, and pathology of Bruch’s membrane. Retinal degenerative diseases: Mechanisms and Experimental Therapy. Eds by Rickmann C.B., LaVail M.M., Anderson R.E., et al. Switzerland: Springer, 2016:465–81.
Review
For citations:
Movsisyan A.B., Kuroyedov A.V., Gorodnichy V.V., Ostapenko G.A., Podvigin S.V., Rachinsky Yu.A., Lanin S.N. Evaluation 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. Pacific Medical Journal. 2020;(3):43-47. (In Russ.) https://doi.org/10.34215/1609-1175-2020-3-43-47
Views:
726
Email this article 