Application of System Analysis and Artificial Intelligence Methods to Diagnose the State of a Dynamic Object Taking the Retina as an Example. Part 2
Abstract
The study is connected with the problem of designing advanced decision making support systems to help specialists in diagnosing the states of dynamic objects taking as an example the medical diagnostics problem (early diagnostics of retinal pathologies). For carrying out diagnostics, it is proposed to use an integrated approach based on system analysis and artificial intelligence methods (fuzzy sets, cognitive graphics). The research and development are carried out jointly by specialists of the National Research University Moscow Power Engineering Institute (the Department of Applied Mathematics and Artificial Intelligence and Management and Intelligent Technologies) and physiologists of the Helmholtz National Medical Research Center of Eye Diseases (the Department of Vision Clinical Physiology named after S.V. Kravkov). Part 1 of the article [1] considered the problem of early diagnostics of retinal pathologies, data preprocessing using wavelet transforms, and the use of amplitude and phase-frequency transformations of electroretinograms (ERGs) to expand the feature space. The expediency of integrating the system analysis and artificial intelligence methods to solve the problem of early diagnostics and analysis of the retinal pathologies development process is substantiated. An important role of system analysis methods both for data preprocessing and for diagnostics proper is shown.
Part 2 will discuss the technique of early diagnostics of retinal pathologies using the system analysis and fuzzy logic methods to determine the ranges of features that characterize specific pathologies and compare them with the range of features for normal vision. An apparatus of cognitive graphics (cognitive images) is proposed for creating visual images that reflect the structural features of the retina and its ability to perceive testing inputs.
References
2. Zueva M.V. e. a. Assessment of the Amplitude-frequency Characteristics of the Retina with Its Stimulation by Flicker and Chess Pattern-reversed Incentives and their Use to Obtain New Formalized Signs of Retinal Pathologies // Biomedical J. Sci. &Techn. Research. 2019. V. 19(5). Pp. 14575—14583.
3. Кофман А. Введение в теорию нечетких множеств. М.: Радио и связь, 1982.
4. Нечеткие множества в моделях управления и искусственного интеллекта / под ред. Д.А. Поспелова. М.: Наука, 1986.
5. Еремеев А.П., Колосов О.С., Зуева М.В., Цапенко И.В. Интеграция методов системного анализа и когнитивной графики при ранней диагностике патологий зрения // Труды ХХ Национ. конф. по искусственному интеллекту с междунар. участием. Т. 2. М.: Изд-во МЭИ, 2022. С. 313—329.
6. Robson A.G. e. a. ISCEV Standard for Full-field Clinical Electroretinography // Documenta Ophthalmologica. 2022. V. 144(3). Pp. 165—177.
7. Robson A.G. e. a. ISCEV Guide to Visual Electrodiagnostic Procedures // Documenta Ophthalmologica. 2018. V. 136(1). Pp. 1—26.
8. Özbay Y., Ceylan R., Karlik B. Integration of Type-2 Fuzzy Clustering and Wavelet Transform in a Neural Network Based ECG Classifier // Expert Syst. with Appl. 2011. V. 38(1). Pр. 1004—1010.
9. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-stationary Signals Using the Wigner-Ville Distribution in Convolutional Neural Networks // Proc. XXV European Signal Conf. Kos, 2017. Pp. 326—330.
---
Для цитирования: Еремеев А.П., Колосов О.С., Зуева М.В., Цапенко И.В. Применение методов системного анализа и искусственного интеллекта для диагностики состояния динамического объекта на примере органа зрения. Ч. 2 // Вестник МЭИ. 2024. № 1. С. 128—137. DOI: 10.24160/1993-6982-2024-1-128-137
#
1. Eremeev A.P., Kolosov O.S., Zueva M.V., Tsapenko I.V. Primenenie Metodov Sistemnogo Analiza i Iskusstvennogo Intellekta dlya Diagnostiki Sostoyaniya Dinamicheskogo Ob'ekta na Primere Organa Zreniya. Ch. 1. Vestnik MEI. 2023;6:135—143. (in Russian).
2. Zueva M.V. e. a. Assessment of the Amplitude-frequency Characteristics of the Retina with Its Stimulation by Flicker and Chess Pattern-reversed Incentives and their Use to Obtain New Formalized Signs of Retinal Pathologies. Biomedical J. Sci. &Techn. Research. 2019;19(5):14575—14583.
3. Kofman A. Vvedenie v Teoriyu Nechetkikh Mnozhestv. M.: Radio i Svyaz', 1982. (in Russian).
4. Nechetkie Mnozhestva v Modelyakh Upravleniya i Iskusstvennogo Intellekta. Pod Red. D.A. Pospelova. M.: Nauka, 1986. (in Russian).
5. Eremeev A.P., Kolosov O.S., Zueva M.V., Tsapenko I.V. Integratsiya Metodov Sistemnogo Analiza i Kognitivnoy Grafiki pri Ranney Diagnostike Patologiy Zreniya. Trudy XX Natsion. Konf. po Iskusstvennomu Intellektu s Mezhdunar. Uchastiem. T. 2. M.: Izd-vo MEI, 2022:313—329. (in Russian).
6. Robson A.G. e. a. ISCEV Standard for Full-field Clinical Electroretinography. Documenta Ophthalmologica. 2022;144(3):165—177.
7. Robson A.G. e. a. ISCEV Guide to Visual Electrodiagnostic Procedures. Documenta Ophthalmologica. 2018;136(1):1—26.
8. Özbay Y., Ceylan R., Karlik B. Integration of Type-2 Fuzzy Clustering and Wavelet Transform in a Neural Network Based ECG Classifier. Expert Syst. with Appl. 2011;38(1):1004—1010.
9. Brynolfsson J., Sandsten M. Classification of One-dimensional Non-stationary Signals Using the Wigner-Ville Distribution in Convolutional Neural Networks. Proc. XXV European Signal Conf. Kos, 2017:326—330
---
For citation: Eremeev A.P., Kolosov O.S., Zueva M.V., Tsapenko I.V. Application of System Analysis and Artificial Intelligence Methods to Diagnose the State of a Dynamic Object Taking the Retina as an Example. Part 2. Bulletin of MPEI. 2024;1:128—137. (in Russian). DOI: 10.24160/1993-6982-2024-1-128-137
