Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks

Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks

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 ano...

Full description

Bibliographic Details
Main Authors: Ričardas Toliušis, Olga Kurasova, Jolita Bernatavičienė
Format: Article
Language:English
Published: Vilnius University Press 2019-10-01
Series:Informacijos Mokslai
Subjects:
U-Net
deep learning
artificial neural networks
semantic segmentation
eye fundus
Online Access:http://www.zurnalai.vu.lt/informacijos-mokslai/article/view/14798
id doaj-b461df17e2e74063a13b512a193cfbea
record_format Article
spelling doaj-b461df17e2e74063a13b512a193cfbea2020-11-25T02:50:11ZengVilnius University PressInformacijos Mokslai1392-05611392-14872019-10-018510.15388/Im.2019.85.20Semantic Segmentation of Eye Fundus Images Using Convolutional Neural NetworksRičardas Toliušis0Olga Kurasova1Jolita Bernatavičienė2Vilnius University, LithuaniaVilnius University, LithuaniaVilnius University, Lithuania 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. http://www.zurnalai.vu.lt/informacijos-mokslai/article/view/14798U-Netdeep learningartificial neural networkssemantic segmentationeye fundus
collection DOAJ
language English
format Article
sources DOAJ
author Ričardas Toliušis
Olga Kurasova
Jolita Bernatavičienė
spellingShingle Ričardas Toliušis
Olga Kurasova
Jolita Bernatavičienė
Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
Informacijos Mokslai
U-Net
deep learning
artificial neural networks
semantic segmentation
eye fundus
author_facet Ričardas Toliušis
Olga Kurasova
Jolita Bernatavičienė
author_sort Ričardas Toliušis
title Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
title_short Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
title_full Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
title_fullStr Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
title_full_unstemmed Semantic Segmentation of Eye Fundus Images Using Convolutional Neural Networks
title_sort semantic segmentation of eye fundus images using convolutional neural networks
publisher Vilnius University Press
series Informacijos Mokslai
issn 1392-0561
1392-1487
publishDate 2019-10-01
description 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.
topic U-Net
deep learning
artificial neural networks
semantic segmentation
eye fundus
url http://www.zurnalai.vu.lt/informacijos-mokslai/article/view/14798
work_keys_str_mv AT ricardastoliusis semanticsegmentationofeyefundusimagesusingconvolutionalneuralnetworks
AT olgakurasova semanticsegmentationofeyefundusimagesusingconvolutionalneuralnetworks
AT jolitabernataviciene semanticsegmentationofeyefundusimagesusingconvolutionalneuralnetworks
_version_ 1724739406480277504

Similar Items