Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
Articles
Ričardas Toliušis
Vilnius University, Lithuania
Olga Kurasova
Vilnius University, Lithuania
Jolita Bernatavičienė
Vilnius University, Lithuania
Published 2019-10-28
https://doi.org/10.15388/Im.2019.85.20
PDF
HTML

Keywords

U-Net
deep learning
artificial neural networks
semantic segmentation
eye fundus

How to Cite

Toliušis, R., Kurasova, O., & Bernatavičienė, J. (2019). Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks. Information & Media, 85, 135-147. https://doi.org/10.15388/Im.2019.85.20

Abstract

This article reviews the problems of eye bottom fundus analysis and semantic segmentation algorithms used to distinguish the eye vessels and the optical disk. Various diseases, such as glaucoma, hypertension, diabetic retinopathy, macular degeneration, etc., can be diagnosed through changes and anomalies of the vesssels and optical disk. Convolutional neural networks, especially the U-Net architecture, are well-suited for semantic segmentation. A number of U-Net modifications have been recently developed that deliver excellent performance results.

PDF
HTML

Downloads

Download data is not yet available.