Detection of diabetic retinopathy based on machine learning
Fragment książki (Rozdział monografii pokonferencyjnej)
MNiSW
20
Poziom I
| Status: | |
| Autorzy: | Pavlov Sergii V., Karas Oleksandr, Mamyrbayev Orken, Saldan Yuliia, Bobitski Yaroslav, Tymchyk Sergii V., Momynzhanova Kymbat, Pylypets Yuliia, Tymchyk Mykola, Grądz Żaklin |
| Dyscypliny: | |
| Aby zobaczyć szczegóły należy się zalogować. | |
| Wersja dokumentu: | Drukowana | Elektroniczna |
| Język: | angielski |
| Strony: | 1 - 7 |
| Efekt badań statutowych | NIE |
| Materiał konferencyjny: | TAK |
| Nazwa konferencji: | Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2025 |
| Skrócona nazwa konferencji: | SPIE-IEEE-PSP 2025 |
| URL serii konferencji: | LINK |
| Termin konferencji: | 3 lipca 2025 do 4 lipca 2025 |
| Miasto konferencji: | Lublin |
| Państwo konferencji: | POLSKA |
| Publikacja OA: | NIE |
| Abstrakty: | angielski |
| Diabetic retinopathy is one of the most common complications of diabetes and remains a leading cause of preventable blindness worldwide, particularly among working-age adults. Early diagnosis plays a critical role in minimizing the risk of vision loss; however, traditional diagnostic methods rely on manual assessment of retinal fundus images by clinicians, which is time-consuming and prone to subjectivity. In recent years, machine learning—especially deep learning approaches such as convolutional neural networks (CNNs)—has shown great potential in automating and improving the accuracy of DR detection. This paper presents a machine learning-based system for the detection and classification of diabetic retinopathy using retinal images. The proposed approach leverages transfer learning with pre-trained CNN architectures and includes essential image preprocessing techniques to enhance the visibility of retinal lesions. Experimental evaluation demonstrates high accuracy in multi-class classification of DR stages. The system offers a scalable solution for population-level screening and can be integrated into clinical decision support tools to aid ophthalmologists in timely diagnosis and treatment of DR. |
