Basarab M. Analysis of Retinal Images for the Diagnosis of Diabetic Retinopathy

Українська версія

Thesis for the degree of Doctor of Philosophy (PhD)

State registration number

0825U001614

Thesis Registration Form

0825U001614.pdf

Applicant for

Specialization

  • 153 - Автоматизація та приладобудування. Мікро- та наносистемна техніка

Specialized Academic Board

PhD 8757

National Technical University of Ukraine «Igor Sikorsky Kyiv Polytechnic Institute»

Essay

The dissertation is dedicated to solving the scientific and applied problem of developing deep learning methods and models for analyzing digital retinal images to diagnose diabetic retinopathy (DR), which allows improving the accuracy of disease stage classification (namely: no diabetic retinopathy, mild diabetic retinopathy, moderate diabetic retinopathy, severe diabetic retinopathy, and proliferative diabetic retinopathy) and assisting the doctor in clinical decision-making in ophthalmology. The dissertation analyzes modern methods for processing and analyzing digital retinal images, including traditional approaches and deep learning technologies, as well as existing software solutions for diagnosing diabetic retinopathy. A review of existing methods for segmenting digital images, identifying diagnostic features of vascular structures, and classifying diabetic retinopathy stages using machine learning methods has been conducted. Research has been carried out on the peculiarities of analyzing digital fundus images, including feature extraction, identification of pathological changes, and optimization of neural network architectures for automated diabetic retinopathy diagnosis.

Read more

Research papers

“Prediction of the Development of Gestational Diabetes Mellitus in Pregnant Women Using Machine Learning Methods”, Basarab M. R., Ivanko K. O., Kulkarni Vishwesh, MicrosystElectronAcoust, 2021, vol. 26, no. 2

“Investigation of Fundus Images for Detection of Diabetic Retinopathy Stage Using Deep Learning”, Basarab M. R., Ivanko K. O., Visnyk NTUU KPI Seriia - Radiotekhnika Radioaparatobuduvannia, (94), pp. 49-57, 2023.

“Deep Learning for the Detection and Classification of Diabetic Retinopathy Stages”, Basarab M. R., Ivanko K. O., MicrosystElectronAcoust, 2024, vol. 29, no. 2.

“Advanced Edge Detection Techniques for Enhanced Diabetic Retinopathy Diagnosis Using Machine Learning”, Basarab M.R., Ivanko, K.O., Visnyk NTUU KPI Seriia - Radiotekhnika Radioaparatobuduvannia, vol. 97, pp. 67-75, 2024.

Yann Zerrouk, Kateryna Ivanko, Nataliia Ivanushkina, Anton Korniienko, Marko Basarab, Hanna Porieva. Prediction of Epileptic Seizures Based on Analysis of Electrical Activity of the Brain and Parameters of Heart Rate Variability. 2022 IEEE 41st International Conference on Electronics and Nanotechnology (ELNANO), Department of Electronic Engineering Igor Sikorsky Kyiv Polytechnic Institute Kyiv, October 2022. Pp. 440-445.

Басараб М. Р., Іванько К.О., Діагностика діабетичної ретинопатії з використанням машинного навчання. XVII Міжнародна Наукова-Практична конференція “Інформаційні технології і автоматизація” - Одеса, 31 жовтня - 1 листопада, 2024, с.774-776.

Read more

Similar theses

0825U001613

Yaroslav O. Linevyvh

One-dimensional silicon nanostructures for physical and chemical sensors

0825U000581

Vasyl Hreb

Modification of the structure and properties of electronics functional materials based on cobaltites of rare-earth elements

0825U000557

Natalia O. Shcherban

Сontrolled modification of electrophysical characteristics of silicon microcrystals by doping with impurities of transition metals for sensor engineering

0824U002498

Dmytro V. Chemerys

Electrophysical and magnetotransport characteristics of GaAs whiskers for sensor electronics

0824U001657

Pavlo Krysenko

Data enrichment for predicting the properties of metamaterials