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

facebooktwittermailshare

A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle

Abstract: 

Left ventricle (LV) segmentation is crucial for quantitative analysis of the cardiac contractile function. In this paper, we propose a joint multi-scale convolutional neural network to fully automatically segment the LV. Our method adopts two kinds of multi-scale features of cardiac magnetic resonance (CMR) images, including multi-scale features directly extracted from CMR images with different scales and multi-scale features constructed by intermediate layers of standard CNN architecture. We take advantage of these two strategies and fuse their prediction results to produce more accurate segmentation results. Qualitative results demonstrate the effectiveness and robustness of our method, and quantitative evaluation indicates our method achieves LV segmentation with higher accuracy than state-of-the-art approaches.

up
0 users have voted:

Paper Details

Authors:
Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning
Submitted On:
21 September 2017 - 2:05am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Qianqian Tong
Paper Code:
TA-PE.9
Document Year:
2017
Cite

Document Files

ICIP2017-3473-poster.pdf

(36 downloads)

Subscribe

[1] Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning, "A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2242. Accessed: Dec. 18, 2017.
@article{2242-17,
url = {http://sigport.org/2242},
author = {Qianqian Tong; Zhiyong Yuan; Xiangyun Liao; Mianlun Zheng; Weixu Zhu; Guian Zhang; Munan Ning },
publisher = {IEEE SigPort},
title = {A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle},
year = {2017} }
TY - EJOUR
T1 - A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle
AU - Qianqian Tong; Zhiyong Yuan; Xiangyun Liao; Mianlun Zheng; Weixu Zhu; Guian Zhang; Munan Ning
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2242
ER -
Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning. (2017). A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle. IEEE SigPort. http://sigport.org/2242
Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning, 2017. A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle. Available at: http://sigport.org/2242.
Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning. (2017). "A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle." Web.
1. Qianqian Tong, Zhiyong Yuan, Xiangyun Liao, Mianlun Zheng, Weixu Zhu, Guian Zhang, Munan Ning. A Joint Multi-scale Convolutional Network for Fully Automatic Segmentation of the Left Ventricle [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2242