Skip to main content
SpringerLink
Log in

A New Method for Automating the Diagnostic Analysis of Human Fundus Images Obtained Using Optical Coherent Tomography Angiography

  • APPLIED PROBLEMS
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

This article presents the results of the joint work of image analysis specialists and ophthalmologists on the problem of analyzing images obtained by optical coherence tomography (angiography). A descriptive algorithmic scheme for analyzing images obtained using optical coherence tomography angiography was constructed to automate detection of pathological changes in the morphometric characteristics of the fundus. The algorithmic scheme is based on the image processing, analysis, and recognition methods. A feature space has been developed that makes it possible to identify pathological changes in the structure of the vascular plexuses of the human retina. It was possible to achieve high-accuracy classification of images of healthy eyes and those with pathology. Analysis of correlation between the features and investigated structural, clinical, and functional parameters can be used to confirm that the selected features are informative diagnostic and prognostic markers, and automated analysis using the proposed algorithm makes it possible to speed up and optimize the procedure for interpreting images of this class. Software has been created that allows, with high accuracy in an autonomous mode, performing differential diagnostics of the normal state of vessels from the pathological one, which increases its diagnostic value. In the future, more detailed work is planned with “borderline” conditions, which constitute the main problem in screening patients with diabetes mellitus.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.

Similar content being viewed by others

REFERENCES

  1. N. Cheung, P. Mitchell, and T. Y. Wong, “Diabetic retinopathy,” Lancet 376, 124–146 (2010). https://doi.org/10.1016/S0140-6736(09)62124-3

    Article  Google Scholar 

  2. Z. Chu et al., “Quantitative assessment of the retinal microvasculature using optical coherence tomography angiography,” J. Biomed. Opt. 21 (6), 066008 (2016).

    Article  Google Scholar 

  3. I. Dedov, M. Shestakova, and O. Vikulova, “Epidemiology of diabetes mellitus in Russian Federation: Clinical and statistical report according to the federal diabetes registry,” Diabetes Mellitus 20 (1), 13–41 (2017).

    Article  Google Scholar 

  4. D. S. Fong, J. Gottlieb, F. L. Ferris, and R. Klein, “Understanding the value of diabetic retinopathy screening,” Arch. Ophthalmol. 119 (5), 758–760 (2001). https://doi.org/10.1001/archopht.15.758

    Article  Google Scholar 

  5. D. Gildea, “The diagnostic value of optical coherence tomography angiography indiabetic retinopathy: A systematic review,” Int. Ophthalmol. 39 (10), 2413–2433 (2019). https://doi.org/10.1007/s10792-018-1034-8

    Article  Google Scholar 

  6. I. B. Gurevich, D. V. Harazishvili, O. Salvetti, A. A. Trykova, and I. A. Vorob’ev, “Elements of the information technology of cytological specimens analysis: Taxonomy and factor analysis,” Pattern Recognit. Image Anal. 16 (1), 114–116 (2006).

    Google Scholar 

  7. I. B. Gurevich, V. V. Yashina, S. V. Ablameyko, A. M. Nedzved, A. M. Ospanov, A. T. Tleubaev, A. A. Fedorov, and N. A. Fedoruk, “Development and experimental investigation of mathematical methods for automating the diagnostics and analysis of ophthalmological images,” Pattern Recognit. Image Anal. 28 (4), 612–636 (2018). https://doi.org/10.1134/S1054661818040120

    Article  Google Scholar 

  8. I. B. Gurevich, V. V. Yashina, A. A. Fedorov, A. M. Nedzved, and A. T. Tleubaev, “Development, investigation, and software implementation of a new mathematical method for automatizing analysis of corneal endothelium images,” Pattern Recognit. Image Anal. 27 (3), 550–559 (2017).

    Article  Google Scholar 

  9. I. B. Gurevich, V. V. Yashina, A. A. Fedorov, A. M. Nedzved, and A. M. Ospanov, “Development, investigation, and software implementation of a new mathematical method for automated identification of the lipid layer state by the images of eyelid intermarginal space,” Pattern Recognit. Image Anal. 27 (3), 538–549 (2017).

  10. I. B. Gurevich, Yu. I. Zhuravlev, A. A. Myagkov, Yu. O. Trusova, and V. V. Yashina, “On basic problems of image recognition in neurosciences and heuristic methods for their solution,” Pattern Recognit. Image Anal. 25 (1), 132–160 (2015).

    Article  Google Scholar 

  11. Igor Gurevich and Vera Yashina, “Basic models of descriptive image analysis,” in ICPR 2020 Workshops, Ed. by A. Del Bimbo (Springer Nature Switzerland AG, 2021), pp. 275–288.

    Google Scholar 

  12. T. Hirano et al., “Vitreoretinal interface slab in OCT angiography for detecting diabetic retinal neovascularization,” Ophthalmol. Retina 4 (6), 588–594 (2020). https://doi.org/10.1016/j.oret.2020.01.004

    Article  Google Scholar 

  13. T. Hirano, J. Kitahara, Y. Toriyama, et al., “Quantifying vascular density and morphology using different swept-source optical coherence tomography angiographic scan patterns in diabetic retinopathy,” Br. J. Ophthalmol. 103, 216–221 (2019). https://doi.org/10.1136/bjophthalmol-2018-311942

    Article  Google Scholar 

  14. V. B. João et al., “Retinal vessel segmentation using the 2-D Morlet wavelet and supervised classification,” IEEE Trans. Med. Imaging 25 (9), 1214–1222 (2006).

    Article  Google Scholar 

  15. O. V. Nedzvedz, S. V. Ablameyko, I. B. Gurevich, and V. V. Yashina, “A new method for automazing of stem cell populations investigation based on the integral optical flow of a video sequence analysis,” Pattern Recognit. Image Anal. 27 (3), 599–609 (2017).

    Article  Google Scholar 

  16. A. Olvera-Barrios, T. F. Heeren, K. Balaskas, et al., “Diagnostic accuracy of diabetic retinopathy grading by an artificial intelligence-enabled algorithm compared with a human standard for wide-field true-colour confocal scanning and standard digital retinal images,” Br. J. Ophthalmol. 105 (2), 265–270 (2020). https://doi.org/10.1136/bjophthalmol-2019-315394

    Article  Google Scholar 

  17. J. Sauvola and M. Pietikainen, “Adaptive document image binarization,” Pattern Recognit. 33 (2), 225–236 (2000).

    Article  Google Scholar 

  18. S. H. Sinclair and C. Delvecchio, “The internist’s role in managing diabetic retinopathy: Screening for early detection,” Cleveland Clin. J. Med. 71 (2), 151–159 (2004). https://doi.org/10.3949/ccjm.71.2.151

    Article  Google Scholar 

  19. L. G. Shapiro and G. C. Stockman, Computer Vision (Prentice Hall, Englewood, 2001).

    Google Scholar 

  20. R. F. Spaide, J. G. Fujimoto, N. K. Waheed, S. R. Sadda, and G. Staurenghi, “Optical coherence tomography angiography,” Prog. Retinal Eye Res. 64, 1–55 (2018).

    Article  Google Scholar 

  21. R. F. Spaide, “Volume-rendered optical coherence tomography of diabetic retinopathy pilot study,” Am. J. Ophthalmol. 160, 1200–1210 (2015).

    Article  Google Scholar 

  22. K. A. Vermeer, F. M. Vos, H. G. Lemij, and A. M. Vossepoel, “A model based method for retinal blood vessel detection,” Comput. Biol. Med. 34, 209–219 (2004).

    Article  Google Scholar 

  23. S. Vujosevic et al., “Screening for diabetic retinopathy: New perspectives and challenges,” Lancet Diabetes Endocrinol. 8 (4), 337–347 (2020). https://doi.org/10.1016/S2213-8587(19)30411-5

    Article  Google Scholar 

  24. B. Zhang, L. Zhang, L. Zhang, and F. Karray, “Retinal vessel extraction by matched filter with first-order derivative of Gaussian,” Comput. Biol. Med. 40 (4), 438–445 (2010).

    Article  Google Scholar 

Download references

Funding

The study was supported by the Russian Foundation for Basic Research and Belarusian Foundation for Basic Research, project nos. 20-57-00025 (Russian side) and F20R-134 (Belarusian side).

Author information

Authors and Affiliations

  1. Federal Research Center Computer Science and Control, Russian Academy of Sciences, Building 2, 44, Vavilov str., 119333, Moscow, Russia

    I. B. Gurevich, V. V. Yashina & A. T. Tleubaev

  2. Scientific Research Institute of Eye Disease, 119021, Moscow, Russia

    M. V. Budzinskaya, V. G. Pavlov & D. V. Petrachkov

  3. Belarusian State University, Minsk, Republic of Belarus

    A. M. Nedzved

Authors
  1. I. B. Gurevich
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. V. Budzinskaya
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. V. V. Yashina
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. A. M. Nedzved
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. A. T. Tleubaev
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. V. G. Pavlov
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. D. V. Petrachkov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to I. B. Gurevich, M. V. Budzinskaya, V. V. Yashina, A. M. Nedzved, A. T. Tleubaev, V. G. Pavlov or D. V. Petrachkov.

Ethics declarations

COMPLIANCE WITH ETHICAL STANDARDS

This article is a completely original work by its authors, has not been previously published, and will not be published in other publications.

CONFLICT OF INTEREST

The authors declare no conflict of interest.

Additional information

Igor B. Gurevich. Born on August 24, 1938. Candidate of Engineering (Automatic Control and Electrical Engineering), 1961, National Research University Moscow Power Engineering Institute, Moscow, USSR; Dr. Sci. (Mathematical Cybernetics), 1975, Moscow Institute of Physics and Technology, Moscow, USSR. Leading Researcher at the Federal Research Center Computer Science and Control, Russian Academy of Sciences, Moscow, Russian Federation. He has worked from 1960 till now as an engineer, researcher and lecturer in industry, research institutions, medicine, universities, and from 1985 in the USSR/Russian Academy of Sciences. Area of expertise: mathematical theory of image analysis, image-mining, image understanding, mathematical theory of pattern recognition, theoretical computer science, medical informatics, applications of pattern recognition and image analysis techniques in biology, medicine and in automation of scientific research, and knowledge-based systems.

Gurevich suggested, proved, and developed with his pupils descriptive approach to image analysis and recognition (DAIA). Within DAIA a new class of image algebra was introduced, defined and investigated (descriptive image algebras); new types of image models were introduced, classified, and investigated; axioms of descriptive theory of image analysis were introduced; a common model of image recognition process was defined and investigated; new settings of image analysis and recognition problems were introduced; a notion image equivalence was introduced and investigated; new classes of image recognition algorithms were defined and investigated; and an image formalization space was introduced, defined, and investigated.

Listed results were used in development of software kits for image analysis and recognition and for solution of important and difficult applied problems of automated bio-medical image analysis.

Gurevich is an author of 2 monographs and of 307 papers in peer reviewed journals and proceedings indexed in Web of Science, Scopus, and Russian Science Citation Index on the platform of Web of Science, 31 invited papers at international conferences, holder of 8 patents. Web of Science: 22 papers; Scopus: 76 papers, 287 citations in 148 documents; Hirsh index is 10; Russian Science Citation Index on the platform of Web of Science: 129 papers; 910 citations; Hirsh index is 11.

Vice-Chairman of the National Committee for Pattern Recognition and Image Analysis of the Russian Academy of Sciences, Member of the International Association for Pattern Recognition (IAPR) Governing Board (representative from RF), IAPR Fellow. He has been the Primary Investigator of 63 R&D projects as part of national and international research programs. Vice-Editor-in-Chief of the Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications, an international journal of the Russian Academy of Sciences, member of editorial boards of several international scientific journals, member of the program and technical committees of many international scientific conferences. Teaching experience: Lomonosov Moscow State University, Russia (Assistant Professor), Dresden Technical University, Germany (Visiting Professor), George Mason University, USA (Research Fellow). He supervised 6 PhD students and many graduate and master students.

Mariya Viktorovna Budzinskaya, born on July 12, 1976. From 1993 to 1999, studied at the Russian State Medical University at the Faculty of General Medicine, received the qualification of a doctor, specializing in General Medicine. In 2001, she graduated from clinical residency at the Moscow Research Institute of Eye Diseases. Valid certificate in the specialty of Ophthalmology. From 2001 to 2003 studied in graduate school based on the Department of Retinal Pathology of the Moscow Research Institute of Eye Diseases. Defended her Candidate’s dissertation on the possibility of using the domestic drug Photosens in fluorescent diagnostics and photodynamic therapy of tumor and pseudotumor eye diseases (experimental study). In 2011, defended her Doctoral dissertation on a system of new approaches to diagnosing and treating the subretinal neovascular membrane. Since 2004 she works at the Scientific Research Institute of GB, Deputy Director for Research, Head of Department of Retinal and Optic Nerve Pathology. Scientific supervision in 5 PhD theses. More than 200 scientific papers have been published, including 109 in journals from the VAK list: 37, Scopus, WoS, 1. Hirsch index 11. GCP certificate, participation in clinical trials (phase III) as co- and principal researcher. Member of the Presidium of the Board of the All-Russian Public Organization Society of Ophthalmologists of Russia. Expert of the Russian Academy of Sciences. Member of the Editorial Board of Bulletin of Ophthalmology. Since 2011, Member of the European Society of Retinal Specialists (Euretina membership certificate). Member of the Scientific and Dissertation Councils of the Research Institute of Eye Diseases. Member of Dissertation Councils of the National Medical Research Center, Interdisciplinary Scientific and Technical Complex “Eye Microsurgery” of the Ministry of Health of the Russian Federation and Additional Professional Education Russian Medical Academy of Continuing Professional Education of the Ministry of Health of the Russian Federation.

Aleksandr M. Nedzved, Dr. Sci., Head of the Department of Computer Systems and Application of Belarusian State University and Chief Researcher of the Department of Intelligent Information Systems. Scientific interests: image processing in medicine, nanotechnology; segmentation; intellectual software and data mining; image object measurement and description; and object detection. In 2007−2010 he managed ISTC project “Automatization of diagnostics and prognosis of radiological analysis” and participated in many international projects: FP6 (NANOMAG project), FP7 (SCUBE-ICT), TEMPUS. He has experience in tutoring dissertation students and teaching at Belarusian and foreign universities. He has more than 120 publications for medical image analysis, software architecture, and automation of medical research.

Vera V. Yashina. Born on September 13, 1980. Diploma mathematician, Lomonosov Moscow State University (2002). Cand. Sci. (Theoretical Foundations of Informatics), 2009, Dorodnicyn Computing Center, Russian Academy of Sciences, Moscow. Leading Researcher at the Department of Recognition, Security, and Analysis of Information at the Federal Research Center Computer Science and Control, Russian Academy of Sciences, Moscow, Russian Federation. She has worked from 2001 until now at the Russian Academy of Sciences. Scientific expertise: mathematical theory of image analysis, image algebras, models, and medical informatics.

Obtained her main results in mathematical theory of image analysis: descriptive image algebras with one ring were defined, classified, and investigated; a new topological image formalization space was specified and investigated; descriptive generating trees were defined, classified and investigated. The listed results were applied in biomedical image analysis.

She is Scientific Secretary of the National Committee for Pattern Recognition and Image Analysis of the Presidium of the Russian Academy of Sciences. She is a member of the Educational and Membership Committees of the International Association for Pattern Recognition. She is a Vice Chair of Technical Committee No. 16 on Algebraic and Discrete Mathematical Techniques in Pattern Recognition and Image Analysis of the International Association for Pattern Recognition. She has been the member of many R&D projects as part of national and international research programs. Member of Editorial Board of Pattern Recognition and Image Analysis. Advances in Mathematical Theory and Applications, an international journal of the RAS. Author of 79 papers in peer reviewed journals, conference and workshop proceedings. Web of Science: 11 papers; Hirsh index is 4; Scopus: 40 papers, 162 citations in 75 papers; Hirsh index 8; Russian Science Citation Index on the platform of Web of Science: 56 papers; 255 citations; Hirsh index 9. She was awarded several times for the best young scientist papers presented at the international conferences. Teaching experience: Lomonosov Moscow State University. Supervised several graduate and master students.

Vladislav Gennad’evich Pavlov, born on July 22, 1993. In 2016 graduated from the medical faculty of First Moscow State Medical University. Specialization in general medicine. In 2018 graduated from residency at Research Institute of Eye Diseases in specialty Ophthalmology. A valid certificate in the specialty Ophthalmology (from 2018). Since 2018, he has been a postgraduate student at the Research Institute of Eye Diseases. Since 2020, working as junior researcher at the Research Institute of Eye Diseases in the Department of Retinal and Optic Nerve Pathology.

Author of 10 articles, in peer-reviewed journals: listed VAK, 4; Web of Science, 1; Scopus, 3; RSCI, 8; with 2 poster presentations at international conferences.

Adil T. Tleubaev. Born on February 13, 1994. Graduated from Moscow State University in computational mathematics and cybernetics in 2018. Research interests: pattern recognition and image analysis, machine learning.

Denis Valer’evich Petrachkov, born on March 25, 1980. In 2003, graduated Siberian State Medical University, Tomsk, specializing in General Medicine. From 2003 to 2006, clinical internship and residency at Department of Ophthalmology, Siberian State Medical University, Tomsk. Valid certificates in the specialty Ophthalmology (2016). In 2008 he defended his Candidate’s thesis on the effectiveness of epiretinal administration of hemase in thrombosis of the central retinal vein and its branches. From 2018 to present, working at Research Institute of Eye Diseases, Moscow, Head of Department of Innovative Vitreoretinal Technologies. Published works 23, Scopus, 8, WoS, 1; Hirsch index 3; RF inventors patents, 3.

Member of professional communities: Society of Ophthalmologists of Russia, European Society of Retina Specialists (EURETINA), and American Academy of Ophthalmology (AAO).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gurevich, I.B., Budzinskaya, M.V., Yashina, V.V. et al. A New Method for Automating the Diagnostic Analysis of Human Fundus Images Obtained Using Optical Coherent Tomography Angiography. Pattern Recognit. Image Anal. 31, 513–528 (2021). https://doi.org/10.1134/S1054661821030111

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661821030111

Keywords:

Search

Navigation