INCREASING THE RELIABILITY OF DIAGNOSIS OF DIABETIC RETINOPATHY BASED ON MACHINE LEARNING
Mamyrbayev O. Pavlov S. Karas O. Saldan I. Momynzhanova K. Zhumagulova S.
2024Technology Center
Eastern-European Journal of Enterprise Technologies
2024#2Issue 9(128)17 - 26 pp.
This paper discusses the method of measuring and analyzing the parameters of the retina with subsequent diagnosis based on them of pathological changes due to diabetic retinopathy, which is crucial in the field of medicine to help doctors in timely detection and treatment of the disease. The main problem of biomedical image data analysis is insufficient pre-processing of images for further clear determination of informative indicators. This paper explores the application of machine learning and image processing techniques to develop an effective method for the diagnosis of diabetic retinopathy. The main focus is on obtaining the optimal model using machine learning and different types of neural networks. This paper considered and analyzed such methods of image preprocessing as: median filtering, grayscale conversion, cropping of non-informative areas of the image, selection of contours. The classification results of three rules (Classical Neural Networks (CNNs), Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) were analyzed, and through experimental studies it was determined that the ANN performed the task best (accuracy=87.1 %, reliability=84.6 %, sensitivity=91.6 %, specificity=84 %). An information model was obtained to support decision-making in assessing the condition of the retina using the processing of the obtained microscopic images and further analysis of informative parameters, and a database of more than 35, 000 samples and informative features of the retina was formed. Given the sufficient quality of classification and the availability of software and hardware, this method can be developed and applied in practice in medical institutions after conducting all the necessary clinical studies Copyright
diabetic retinopathy , fundus images , image preprocessing , medical image analysis , neural network
Text of the article Перейти на текст статьи
Department of Artificial Intelligence, U. Joldasbekov Institute of Mechanics and Engineering, Kurmangazy str., 29, Almaty, 050010, Kazakhstan
Department of Biomedical Engineering and Optic-Electronic Systems, Ukraine
Department of Eye Diseases, National Pirogov Memorial Medical University, Pyrohova str., 56, Vinnytsia, 21018, Ukraine
Department of Information Systems, Kazakhstan
Department of Artificial Intelligence and Big Data, Ukraine
Vinnytsia National Technical University, Khmelnytske highway, 95, Vinnytsia, 21021, Ukraine
Al-Farabi Kazakh National University, al-Farabi ave., 71, Almaty, 050040, Kazakhstan
Department of Artificial Intelligence
Department of Biomedical Engineering and Optic-Electronic Systems
Department of Eye Diseases
Department of Information Systems
Department of Artificial Intelligence and Big Data
Vinnytsia National Technical University
Al-Farabi Kazakh National University
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026