Glaucoma assessment from color fundus images using convolutional neural network

2020 ◽  
Author(s):  
Poonguzhali Elangovan ◽  
Malaya Kumar Nath
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Fundus Images ◽  
Color Fundus Images

Fast Convolutional Neural Network Training Using Selective Data Sampling: Application to Hemorrhage Detection in Color Fundus Images

2016 ◽  
Vol 35 (5) ◽  
pp. 1273-1284 ◽  
Author(s):  
Mark J. J. P. van Grinsven ◽  
Bram van Ginneken ◽  
Carel B. Hoyng ◽  
Thomas Theelen ◽  
Clara I. Sanchez
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Fundus Images ◽  
Data Sampling ◽  
Neural Network Training ◽  
Network Training ◽  
Color Fundus Images

scholarly journals Microaneurysm detection in fundus images using a two-step convolutional neural network

2019 ◽  
Vol 18 (1) ◽  
Author(s):  
Noushin Eftekhari ◽  
Hamid-Reza Pourreza ◽  
Mojtaba Masoudi ◽  
Kamaledin Ghiasi-Shirazi ◽  
Ehsan Saeedi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Fundus Images

Full Convolutional Neural Network with Multi-Scale Residual Model for Optic Cup and Disc Segmentation

2020 ◽  
Vol 10 (11) ◽  
pp. 2733-2738
Author(s):  
Yanxia Sun ◽  
Peiqing ◽  
Xiaoxu Geng ◽  
Haiying Wang ◽  
Jinke Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Cost Function ◽  
Coordinate Transformation ◽  
State Of The Art ◽  
Fundus Images ◽  
Early Screening ◽  
Multi Scale ◽  
Optic Cup ◽  
Polar Coordinate

Accurate optic cup and optic disc (OC, OD) segmentation is the prerequisite for cup-disc ratio (CDR) calculation. In this paper, a new full convolutional neural network (FCN) with multi-scale residual module is proposed. Firstly, polar coordinate transformation was introduced to balance the CDR with space constraints, and CLAHE was implemented in fundus images for contrast enhancement. Secondly, W-Net-R model was proposed as the main framework, while the standard convolution unit was replaced by the multi-scale residual module. Finally, the multi-label cost function is utilized to guide its functioning. In the experiment, the REFUGE dataset was used for training, validation and testing. We obtained 0.979 and 0.904 for OD and OC segmentations on MIoU, which indicates a relative improvement of 4.04% and 3.55%, comparing with that of U-Net, respectively. Experiment results proved that our proposed method is superior to other state-of-the-art schemes on OC and OD segmentation, and could be a potential prospective tool for early screening of glaucoma.

Classification of Retinal Lesions in Fundus Images Using Atrous Convolutional Neural Network

2021 ◽  
pp. 551-564
Author(s):  
Radha ◽  
Suchetha ◽  
Rajiv Raman ◽  
Madhumitha ◽  
Sorna Meena ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Fundus Images ◽  
Retinal Lesions
Sign in / Sign up

Export Citation Format

Share Document