Вісник НТУУ «КПІ». Радіотехніка, радіоапаратобудування: збірник наукових праць

Постійне посилання на фонд

https://ela.kpi.ua/handle/123456789/2120
ISSN 2310-0389 (Online), ISSN 2310-0397 (Print) Періодичність: 4 рази на рік
Рік заснування: 1956
Тематика: теоретична радіотехніка; електродинаміка; теорія та засоби телекомунікацій; антени та пристрої НВЧ діапазону; теорія та практика радіовимірювань; конструювання радіоапаратури; мікроелектронна та наноелектронна техніка; технологія радіоапаратобудування; засоби та методи мультимедіа; засоби захисту інформації; електронна побутова апаратура; цифрова та обчислювальна техніка; радіоелектроніка біомедичних технологій.
Офіційний сайт: http://radap.kpi.ua/radiotechnique

Переглянути

Перегляд Вісник НТУУ «КПІ». Радіотехніка, радіоапаратобудування: збірник наукових праць за Ключові слова "004.8.67"

Зараз показуємо 1 - 2 з 2
  • Ескіз
    ДокументВідкритий доступ
    Advanced Edge Detection Techniques for Enhanced Diabetic Retinopathy Diagnosis Using Machine Learning
    (КПІ ім. Ігоря Сікорського, 2024) Basarab, M. R.; Ivanko, K. O.
    Diabetic retinopathy (DR) represents one of the most serious complications associated with diabetes mellitus, posing a significant threat to vision and leading to severe impairment and potential blindness if not diagnosed and treated promptly. The study investigates the integration of advanced edge detection techniques with machine learning algorithms to enhance the precision and effectiveness of DR diagnosis. By leveraging the APTOS 2019 Blindness Detection dataset, the research employs a combination of edge detection methods such as the Sobel operator and the Canny edge detector, alongside advanced preprocessing techniques and sophisticated feature extraction methods. The study reveals that the synergy between these edge detection techniques and machine learning significantly boosts the diagnostic accuracy of neural networks. Specifically, the accuracy for multiclass classification (spanning five categories: No diabetic retinopathy, Mild, Moderate, Severe, and Proliferative diabetic retinopathy) improved from 78.5% to an impressive 88.2%. This marked enhancement underscores the potential of these techniques in refining the diagnostic processes for early DR detection. By improving the accuracy of classification, this approach not only facilitates early intervention but also plays a crucial role in reducing the risk of severe vision loss among patients with diabetes. The findings of this study emphasize the importance of integrating advanced image processing techniques with machine learning frameworks in medical diagnostics. The improved outcomes demonstrated in this research highlight the potential for such technological advancements to contribute meaningfully to the field of ophthalmology, leading to better patient care and potentially transforming the standard of practice in DR diagnosis.
  • Ескіз
    ДокументВідкритий доступ
    Investigation of fundus images for detection of diabetic retinopathy stage using deep learning
    (КПІ ім. Ігоря Сікорського, 2023) Basarab, M. R.; Ivanko, K. O.
    The study is dedicated to the investigation of diabetic retinopathy images by digital processing methods and further pathological outcome levels classification. The application of image processing methods to the problem of diabetic retinopathy (DR) analysis is considered in the paper. In order to investigate the possibilities of machine learning for the problem of classification of retinal images, the dataset of retinal images, which represent 5 classes: absence of DR, moderate, mild, proliferate stages, and severe DR, was used in this work. The aim of this study is to identify and compare the different image processing methods used for diabetic retinopathy detection, as well as to choose the classification method that provides the highest accuracy in the identification of the human retina condition. The convolutional neural networks with tuned parameters such as EfficientNet and ResNet were applied to determine the best classification models for computerized disease screening. The accuracy and losses of the different models were determined and compared. Based on this, a combination of image preprocessing steps and neural network models, which provide the highest accuracy of diabetic retinopathy condition recognition, reaching 91.4% for the task of recognition of 5 classes (absence of DR and 4 stages of DR) is proposed. Intermediate stages in the development of diabetic retinopathy are the most difficult to distinguish: the best model showed 85.2% of correctly defined cases of moderate stage of diabetic retinopathy and 83% of correctly defined cases of mild stage. Overall, this article highlights the significance of artificial intelligence (AI) and deep learning in the detection and classification of diabetic retinopathy. It underscores the need for improved screening methods, especially in underserved areas, and emphasizes the potential of these technologies in preserving vision, reducing healthcare professionals’ workload, and promoting widespread adoption in clinical practice. The article also acknowledges the challenges associated with image variability and the potential impact on AI model performance, calling for further research and improvement in image quality and consistency.