Neural network application for semantic segmentation of fundus
| Autor: | R.A. Paringer, A.V. Mukhin, N.Y. Ilyasova, N.S. Demin |
|---|---|
| Jazyk: | English<br />Russian |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Компьютерная оптика, Vol 46, Iss 4, Pp 596-602 (2022) |
| Druh dokumentu: | article |
| ISSN: | 2412-6179 0134-2452 |
| DOI: | 10.18287/2412-6179-CO-1010 |
| Popis: | Advances in the neural networks have brought revolution in many areas, especially those related to image processing and analysis. The most complex is a task of analyzing biomedical data due to a limited number of samples, imbalanced classes, and low-quality labelling. In this paper, we look into the possibility of using neural networks when solving a task of semantic segmentation of fundus. The applicability of the neural networks is evaluated through a comparison of image segmentation results with those obtained using textural features. The neural networks are found to be more accurate than the textural features both in terms of precision (~25%) and recall (~50%). Neural networks can be applied in biomedical image segmentation in combination with data balancing algorithms and data augmentation techniques. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|