Methods and Software for Analysis and Diagnostics of Complex Vision Pathologies
Keywords:
artificial intelligence, decision making support, data processing and analysis, neural network, diagnostics, pathology of vision
Abstract
The article addresses topical matters concerned with development of prospective intelligent decision making support systems (IDMSS) in analysis and diagnostics of complex problem situations taking complex vision pathologies as an example. The aim of the research is to develop an IDMSS prototype that would make it possible to automatically draw conclusions about a possible diagnosis based on the results of medical studies obtained from a special apparatus (an electroretinograph), patient examination results, and the knowledge of expert physiologists. Electroretinography is a method for assessing the functional state of the retina, which is based on recording the biopotentials arising in it during light stimulation, and the curve that images them is called the electroretinogram. The applied methods include those for constructing ontologies, neural networks, inverse development of applications, and constructing an IDMSS based on expert knowledge and human-machine interfaces. Methods for preliminary (preprocessor) processing of large data and for arranging their storage in a dedicated database and for displaying the results (diagnostic solutions) produced by the system are also considered. The novelty of the proposed approach consists in integrating several methods and in justifying the use of ontology and nonrelational model (database) in terms of expanding their scope at the early stages of the disease and improving the quality of diagnosing visual pathologies. The developed software tools of the IDMSS prototype are pointed out.
The presented studies and developments have been carried out jointly by the Department of Applied Mathematics and Artificial Intelligence of the National Research University Moscow Power Engineering Institute (NRU MPEI) and the Department of Clinical Physiology of Vision of the Helmholtz Moscow Research Institute of Eye Diseases.
References
1. Шамшинова А.М. Электроретинография в офтальмологии. М.: Медика, 2009.
2. Eremeev A.P., Tcapenko I.V. The Use of Cognitive Graphics in the Diagnosis of Complex Vision Pathologies // Intern. J. Information Theories and Appl. 2019. V. 26. No. 1. Рр. 83—99.
3. Eremeev A.P., Ivliev S.A. Data Collection and Preparation of Training Samples for Problem Diagnosis of Vision Pathologies // Proc. 17 Russian Conf. Artificial Intelligence. 2019. V. 1093. Pр. 271—282.
4. Анисимов Д.Н., Вершинин Д.В., Колосов О.С., Зуева М.В., Цапенко И.В. Диагностика текущего состояния динамических объектов и систем сложной структуры методами нечеткой логики с использованием имитационных моделей // Искусственный интеллект и принятие решений. 2012. № 3. С. 39—50.
5. Eremeev A.P., Ivliev S.A. Using Convolutional Neural Networks for the Analysis of Nonstationary Signals on the Problem Diagnostics Vision Pathologies // Proc. 16 Russian Conf. Artificial Intelligence. 2018. V. 934. Рp. 164—175.
6. Eremeev A.P., Ivliev S.A., Vagin V.N. Using NoSql Databases and Machine Learning for Implementation of Intelligent Decision System in Complex Vision Pathologies // Proc. III Russian-pacific Conf. Computer Technol. and Appl. Vladivostok, 2018. Рp. 1—4.
7. Barrac R. e. a. A Comparison Among Different Techniques for Human ERG Signals Processing and Classification // Physica Medica: European J. Medical Phys. 2014. V. 30. Iss. 1. Рp. 86—95.
8. Цапенко И.В. Электрофизиологические исследования в диагностике заболеваний сетчатки и зрительного нерва (I). М: ФГУ «МНИИ глазных болезней им. Г. Гельмгольца Минздрава России», 2017.
9. Джарратано Д., Райли Г. Экспертные системы: принципы разработки и программирование. М.: Вильямс, 2007.
10. Еремеев А.П., Куриленко И.В. Реализация вывода в темпоральных моделях ветвящегося времени // Известия РАН. Серия «Теория и системы управления». 2017. № 1. С. 107—127.
11. Ken Ka-Yin Leea, Wai-Choi Tangb, Kup-Sze Choia. Alternatives to Relational Database: Comparison of NoSQL and XML Approaches for Clinical Data Storage // Computer Methods and Programs in Biomedicine. 2013. V. 110. Pp. 99—109.
12. Goli-Malekabady Z., Akbari M.K., Javan M.S. An Effective Model for Store and Retrieve Big Health Data in Cloud Computing // Computer Methods and Programs in Biomedicine. 2016. V. 132. Pp. 75—82.
13. Козлов И.А. Анализ и классификация нереляционных баз данных // Молодежный научно-технический вестник. 2013. № 2. С. 12—19.
14. Lämmel R. Google’s MapReduce Programming Model — Revisited // Sci. of Computer Programming. 2008. V. 70. Iss. 1. Pp. 1—30.
15. Naresh Kumar Gundla, Zhengxin Chen. Creating NoSQL Biological Databases with Ontologies for Query Relaxation // Procedia Computer Sci. 2016. V. 91. Pp. 460—469.
16. Еремеев А.П., Ивлиев С.А. Анализ и диагностика сложных патологий зрения на основе вейвлет-преобразований и нейросетевого подхода // Интегрированные модели и мягкие вычисления в искусственном интеллекте: Сборник трудов VIII Междунар. науч.-техн. конф. М.: Физматлит, 2015. T. 2. С. 589—595.
17. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-Stationary Signals using the Wigner-Ville Distribution in Convolutional Neural Networks // Proc. 25 European Signal Conf. Kos, 2017. Pp. 326—330.
18. Lee H., Grosse R., Ranganath R., Ng A.Y. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations // Proc. 26 Annual Intern. Conf. Machine Learning. Montreal, 2009. Pp. 609—616.
19. Geert Litjens e. a. A survey on Deep Learning in Medical Image Analysis // Medical Image Analysis. 2017. V. 42. Pp. 60—88.
20. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet Classification with Deep Convolutional Neural Networks. // Advances in Neural Information Proc. Syst. 2012. V. 25 (2). Pp. 1097—1105.
21. Davies E.R. Computer Vision: Principles, Algorithms, Applications, Learning. London: Elsevier, 2018. Pp. 453—493.
22. Bo L., Ren X., Fox D. Unsupervised Feature Learning for rgb-d Based Object Recognition // Experimental Robotics. N.-Y.: Springer, 2013. Рp. 387—402.
---
Для цитирования: Еремеев А.П., Ивлиев С.А. Методы и программные средства для анализа и диагностики сложных патологий зрения // Вестник МЭИ. 2020. № 5. С. 140—147. DOI: 10.24160/1993-6982-2020-5-140-147.
#
1. Shamshinova A.M. Elektroretinografiya v Oftal'mologii. M.: Medika, 2009. (in Russian).
2. Eremeev A.P., Tcapenko I.V. The Use of Cognitive Graphics in the Diagnosis of Complex Vision Pathologies. Intern. J. Information Theories and Appl. 2019;26;1:83—99.
3. Eremeev A.P., Ivliev S.A. Data Collection and Preparation of Training Samples for Problem Diagnosis of Vision Pathologies. Proc. 17 Russian Conf. Artificial Intelligence. 2019;1093:271—282.
4. Anisimov D.N., Vershinin D.V., Kolosov O.S., Zueva M.V., Tsapenko I.V. Diagnostika Tekushchego Sostoyaniya Dinamicheskikh Ob′ektov i sistem Slozhnoy Struktury Metodami Nechetkoy Logiki s Ispol'zovaniem Imitatsionnykh Modeley. Iskusstvennyy Intellekt i Prinyatie Resheniy. 2012;3:39—50. (in Russian).
5. Eremeev A.P., Ivliev S.A. Using Convolutional Neural Networks for the Analysis of Nonstationary Signals on the Problem Diagnostics Vision Pathologies. Proc. 16 Russian Conf. Artificial Intelligence. 2018;934:164—175.
6. Eremeev A.P., Ivliev S.A., Vagin V.N. Using NoSql Databases and Machine Learning for Implementation of Intelligent Decision System in Complex Vision Pathologies. Proc. III Russian-pacific Conf. Computer Technol. and Appl. Vladivostok, 2018:1—4.
7. Barrac R. e. a. A Comparison Among Different Techniques for Human ERG Signals Processing and Classification. Physica Medica: European J. Medical Phys. 2014;30;1:86—95.
8. Tsapenko I.V. Elektrofiziologicheskie Issledovaniya v Diagnostike Zabolevaniy Setchatki i Zritel'nogo Nerva (I). M: FGU «MNII Glaznykh Bolezney im. G. Gel'mgol'tsa Minzdrava Rossii», 2017. (in Russian).
9. Dzharratano D., Rayli G. Ekspertnye Sistemy: Printsipy Razrabotki i Programmirovanie. M.: Vil'yams, 2007. (in Russian).
10. Eremeev A.P., Kurilenko I.V. Realizatsiya Vyvoda v Temporal'nykh Modelyakh Vetvyashchegosya Vremeni. Izvestiya RAN. Seriya «Teoriya i Sistemy Upravleniya». 2017;1:107—127. (in Russian).
11. Ken Ka-Yin Leea, Wai-Choi Tangb, Kup-Sze Choia. Alternatives to Relational Database: Comparison of NoSQL and XML Approaches for Clinical Data Storage. Computer Methods and Programs in Biomedicine. 2013;110:99—109.
12. Goli-Malekabady Z., Akbari M.K., Javan M.S. An Effective Model for Store and Retrieve Big Health Data in Cloud Computing. Computer Methods and Programs in Biomedicine. 2016;132:75—82.
13. Kozlov I.A. Analiz i Klassifikatsiya Nerelyatsionnykh Baz Dannykh. Molodezhnyy Nauchno-tekhnicheskiy Vestnik. 2013;2:12—19. (in Russian).
14. Lämmel R. Google’s MapReduce Programming Model — Revisited. Sci. of Computer Programming. 2008;70;1:1—30.
15. Naresh Kumar Gundla, Zhengxin Chen. Creating NoSQL Biological Databases with Ontologies for Query Relaxation. Procedia Computer Sci. 2016;91:460—469.
16. Eremeev A.P., Ivliev S.A. Analiz i Diagnostika Slozhnykh Patologiy Zreniya na Osnove Veyvlet-preobrazovaniy i Neyrosetevogo Podkhoda. Integrirovannye Modeli i Myagkie Vychisleniya v Iskusstvennom Intellekte: Sbornik Trudov VIII Mezhdunar.Nauch.-tekhn. Konf. M.: Fizmatlit, 2015;2:589—595. (in Russian).
17. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-Stationary Signals using the Wigner-Ville Distribution in Convolutional Neural Networks. Proc. 25 European Signal Conf. Kos, 2017:326—330.
18. Lee H., Grosse R., Ranganath R., Ng A.Y. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations. Proc. 26 Annual Intern. Conf. Machine Learning. Montreal, 2009:609—616.
19. Geert Litjens e. a. A survey on Deep Learning in Medical Image Analysis. Medical Image Analysis. 2017;42:60—88.
20. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet Classification with Deep Convolutional Neural Networks.. Advances in Neural Information Proc. Syst. 2012;25 (2):1097—1105.
21. Davies E.R. Computer Vision: Principles, Algorithms, Applications, Learning. London: Elsevier, 2018:453—493.
22. Bo L., Ren X., Fox D. Unsupervised Feature Learning for rgb-d Based Object Recognition. Experimental Robotics. N.-Y.: Springer, 2013:387—402.
---
For citation: Eremeev A.P., Ivliev A.A. Methods and Software for Analysis and Diagnostics of Complex Vision Pathologies. Bulletin of MPEI. 2020;5:140—147. (in Russian). DOI: 10.24160/1993-6982-2020-5-140-147.
2. Eremeev A.P., Tcapenko I.V. The Use of Cognitive Graphics in the Diagnosis of Complex Vision Pathologies // Intern. J. Information Theories and Appl. 2019. V. 26. No. 1. Рр. 83—99.
3. Eremeev A.P., Ivliev S.A. Data Collection and Preparation of Training Samples for Problem Diagnosis of Vision Pathologies // Proc. 17 Russian Conf. Artificial Intelligence. 2019. V. 1093. Pр. 271—282.
4. Анисимов Д.Н., Вершинин Д.В., Колосов О.С., Зуева М.В., Цапенко И.В. Диагностика текущего состояния динамических объектов и систем сложной структуры методами нечеткой логики с использованием имитационных моделей // Искусственный интеллект и принятие решений. 2012. № 3. С. 39—50.
5. Eremeev A.P., Ivliev S.A. Using Convolutional Neural Networks for the Analysis of Nonstationary Signals on the Problem Diagnostics Vision Pathologies // Proc. 16 Russian Conf. Artificial Intelligence. 2018. V. 934. Рp. 164—175.
6. Eremeev A.P., Ivliev S.A., Vagin V.N. Using NoSql Databases and Machine Learning for Implementation of Intelligent Decision System in Complex Vision Pathologies // Proc. III Russian-pacific Conf. Computer Technol. and Appl. Vladivostok, 2018. Рp. 1—4.
7. Barrac R. e. a. A Comparison Among Different Techniques for Human ERG Signals Processing and Classification // Physica Medica: European J. Medical Phys. 2014. V. 30. Iss. 1. Рp. 86—95.
8. Цапенко И.В. Электрофизиологические исследования в диагностике заболеваний сетчатки и зрительного нерва (I). М: ФГУ «МНИИ глазных болезней им. Г. Гельмгольца Минздрава России», 2017.
9. Джарратано Д., Райли Г. Экспертные системы: принципы разработки и программирование. М.: Вильямс, 2007.
10. Еремеев А.П., Куриленко И.В. Реализация вывода в темпоральных моделях ветвящегося времени // Известия РАН. Серия «Теория и системы управления». 2017. № 1. С. 107—127.
11. Ken Ka-Yin Leea, Wai-Choi Tangb, Kup-Sze Choia. Alternatives to Relational Database: Comparison of NoSQL and XML Approaches for Clinical Data Storage // Computer Methods and Programs in Biomedicine. 2013. V. 110. Pp. 99—109.
12. Goli-Malekabady Z., Akbari M.K., Javan M.S. An Effective Model for Store and Retrieve Big Health Data in Cloud Computing // Computer Methods and Programs in Biomedicine. 2016. V. 132. Pp. 75—82.
13. Козлов И.А. Анализ и классификация нереляционных баз данных // Молодежный научно-технический вестник. 2013. № 2. С. 12—19.
14. Lämmel R. Google’s MapReduce Programming Model — Revisited // Sci. of Computer Programming. 2008. V. 70. Iss. 1. Pp. 1—30.
15. Naresh Kumar Gundla, Zhengxin Chen. Creating NoSQL Biological Databases with Ontologies for Query Relaxation // Procedia Computer Sci. 2016. V. 91. Pp. 460—469.
16. Еремеев А.П., Ивлиев С.А. Анализ и диагностика сложных патологий зрения на основе вейвлет-преобразований и нейросетевого подхода // Интегрированные модели и мягкие вычисления в искусственном интеллекте: Сборник трудов VIII Междунар. науч.-техн. конф. М.: Физматлит, 2015. T. 2. С. 589—595.
17. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-Stationary Signals using the Wigner-Ville Distribution in Convolutional Neural Networks // Proc. 25 European Signal Conf. Kos, 2017. Pp. 326—330.
18. Lee H., Grosse R., Ranganath R., Ng A.Y. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations // Proc. 26 Annual Intern. Conf. Machine Learning. Montreal, 2009. Pp. 609—616.
19. Geert Litjens e. a. A survey on Deep Learning in Medical Image Analysis // Medical Image Analysis. 2017. V. 42. Pp. 60—88.
20. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet Classification with Deep Convolutional Neural Networks. // Advances in Neural Information Proc. Syst. 2012. V. 25 (2). Pp. 1097—1105.
21. Davies E.R. Computer Vision: Principles, Algorithms, Applications, Learning. London: Elsevier, 2018. Pp. 453—493.
22. Bo L., Ren X., Fox D. Unsupervised Feature Learning for rgb-d Based Object Recognition // Experimental Robotics. N.-Y.: Springer, 2013. Рp. 387—402.
---
Для цитирования: Еремеев А.П., Ивлиев С.А. Методы и программные средства для анализа и диагностики сложных патологий зрения // Вестник МЭИ. 2020. № 5. С. 140—147. DOI: 10.24160/1993-6982-2020-5-140-147.
#
1. Shamshinova A.M. Elektroretinografiya v Oftal'mologii. M.: Medika, 2009. (in Russian).
2. Eremeev A.P., Tcapenko I.V. The Use of Cognitive Graphics in the Diagnosis of Complex Vision Pathologies. Intern. J. Information Theories and Appl. 2019;26;1:83—99.
3. Eremeev A.P., Ivliev S.A. Data Collection and Preparation of Training Samples for Problem Diagnosis of Vision Pathologies. Proc. 17 Russian Conf. Artificial Intelligence. 2019;1093:271—282.
4. Anisimov D.N., Vershinin D.V., Kolosov O.S., Zueva M.V., Tsapenko I.V. Diagnostika Tekushchego Sostoyaniya Dinamicheskikh Ob′ektov i sistem Slozhnoy Struktury Metodami Nechetkoy Logiki s Ispol'zovaniem Imitatsionnykh Modeley. Iskusstvennyy Intellekt i Prinyatie Resheniy. 2012;3:39—50. (in Russian).
5. Eremeev A.P., Ivliev S.A. Using Convolutional Neural Networks for the Analysis of Nonstationary Signals on the Problem Diagnostics Vision Pathologies. Proc. 16 Russian Conf. Artificial Intelligence. 2018;934:164—175.
6. Eremeev A.P., Ivliev S.A., Vagin V.N. Using NoSql Databases and Machine Learning for Implementation of Intelligent Decision System in Complex Vision Pathologies. Proc. III Russian-pacific Conf. Computer Technol. and Appl. Vladivostok, 2018:1—4.
7. Barrac R. e. a. A Comparison Among Different Techniques for Human ERG Signals Processing and Classification. Physica Medica: European J. Medical Phys. 2014;30;1:86—95.
8. Tsapenko I.V. Elektrofiziologicheskie Issledovaniya v Diagnostike Zabolevaniy Setchatki i Zritel'nogo Nerva (I). M: FGU «MNII Glaznykh Bolezney im. G. Gel'mgol'tsa Minzdrava Rossii», 2017. (in Russian).
9. Dzharratano D., Rayli G. Ekspertnye Sistemy: Printsipy Razrabotki i Programmirovanie. M.: Vil'yams, 2007. (in Russian).
10. Eremeev A.P., Kurilenko I.V. Realizatsiya Vyvoda v Temporal'nykh Modelyakh Vetvyashchegosya Vremeni. Izvestiya RAN. Seriya «Teoriya i Sistemy Upravleniya». 2017;1:107—127. (in Russian).
11. Ken Ka-Yin Leea, Wai-Choi Tangb, Kup-Sze Choia. Alternatives to Relational Database: Comparison of NoSQL and XML Approaches for Clinical Data Storage. Computer Methods and Programs in Biomedicine. 2013;110:99—109.
12. Goli-Malekabady Z., Akbari M.K., Javan M.S. An Effective Model for Store and Retrieve Big Health Data in Cloud Computing. Computer Methods and Programs in Biomedicine. 2016;132:75—82.
13. Kozlov I.A. Analiz i Klassifikatsiya Nerelyatsionnykh Baz Dannykh. Molodezhnyy Nauchno-tekhnicheskiy Vestnik. 2013;2:12—19. (in Russian).
14. Lämmel R. Google’s MapReduce Programming Model — Revisited. Sci. of Computer Programming. 2008;70;1:1—30.
15. Naresh Kumar Gundla, Zhengxin Chen. Creating NoSQL Biological Databases with Ontologies for Query Relaxation. Procedia Computer Sci. 2016;91:460—469.
16. Eremeev A.P., Ivliev S.A. Analiz i Diagnostika Slozhnykh Patologiy Zreniya na Osnove Veyvlet-preobrazovaniy i Neyrosetevogo Podkhoda. Integrirovannye Modeli i Myagkie Vychisleniya v Iskusstvennom Intellekte: Sbornik Trudov VIII Mezhdunar.Nauch.-tekhn. Konf. M.: Fizmatlit, 2015;2:589—595. (in Russian).
17. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-Stationary Signals using the Wigner-Ville Distribution in Convolutional Neural Networks. Proc. 25 European Signal Conf. Kos, 2017:326—330.
18. Lee H., Grosse R., Ranganath R., Ng A.Y. Convolutional Deep Belief Networks for Scalable Unsupervised Learning of Hierarchical Representations. Proc. 26 Annual Intern. Conf. Machine Learning. Montreal, 2009:609—616.
19. Geert Litjens e. a. A survey on Deep Learning in Medical Image Analysis. Medical Image Analysis. 2017;42:60—88.
20. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet Classification with Deep Convolutional Neural Networks.. Advances in Neural Information Proc. Syst. 2012;25 (2):1097—1105.
21. Davies E.R. Computer Vision: Principles, Algorithms, Applications, Learning. London: Elsevier, 2018:453—493.
22. Bo L., Ren X., Fox D. Unsupervised Feature Learning for rgb-d Based Object Recognition. Experimental Robotics. N.-Y.: Springer, 2013:387—402.
---
For citation: Eremeev A.P., Ivliev A.A. Methods and Software for Analysis and Diagnostics of Complex Vision Pathologies. Bulletin of MPEI. 2020;5:140—147. (in Russian). DOI: 10.24160/1993-6982-2020-5-140-147.
Published
2019-12-23
Section
Theoretical Foundations of Computer Science (05.13.17)
