Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation

Abstract: 

Automated segmentation of retinal blood vessels plays an important role in the computer aided diagnosis of retinal diseases. The paper presents a new formulation of patch-based fully Convolutional Neural Networks (CNNs) that allows accurate segmentation of the retinal blood vessels. A major modification in this retinal blood vessel segmentation task is to improve and speed-up the patch-based fully CNN training by local entropy sampling and a skip CNN architecture with class-balancing loss. The proposed method is experimented on DRIVE dataset and achieves strong performance and significantly outperforms the-state-of-the-art for retinal blood vessel segmentation with 78.11% sensitivity, 98.39% specificity, 95.60% accuracy, 87.36% precision and 97.92% AUC score respectively.

icip2017.pdf

PDF icon icip2017.pdf (10 downloads)
up
0 users have voted:

Paper Details

Authors:
Jie Yang, Lixiu Yao
Submitted On:
14 September 2017 - 4:07am
Short Link:
Type:
Presentation Slides
Event:
Paper Code:
2120
Document Year:
2017
Cite

Document Files

icip2017.pdf

(10 downloads)

Subscribe

[1] Jie Yang, Lixiu Yao, "Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1998. Accessed: Sep. 19, 2017.
@article{1998-17,
url = {http://sigport.org/1998},
author = {Jie Yang; Lixiu Yao },
publisher = {IEEE SigPort},
title = {Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation},
year = {2017} }
TY - EJOUR
T1 - Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation
AU - Jie Yang; Lixiu Yao
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1998
ER -
Jie Yang, Lixiu Yao. (2017). Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation. IEEE SigPort. http://sigport.org/1998
Jie Yang, Lixiu Yao, 2017. Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation. Available at: http://sigport.org/1998.
Jie Yang, Lixiu Yao. (2017). "Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation." Web.
1. Jie Yang, Lixiu Yao. Patch-based Fully Convolutional Neural Network With Skip Connections For Retinal Blood Vessel Segmentation [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1998