Endocardial boundary detection using a neural network

Ching Tsorng Tsai, Yung-Nien Sun, Pau-Choo Chung, Jiann Shu Lee

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

Echocardiography has been widely used as a real-time non-invasive clinical tool to diagnose cardiac functions. Due to the poor quality and inherent ambiguity in echocardiograms, it is difficult to detect the myocardial boundaries of the left ventricle. Many existing methods are semi-automatic and detect cardial boundaries by serial computation which is too slow to be practical in real applications. In this paper, a new method for detecting the endocardial boundary by using a Hopfield neural network is proposed. Taking advantage of parallel computation and energy convergence capability in the Hopfield network, this method is faster and more stable for the detection of the endocardial border. Moreover, neither manual operations nor a priori assumptions are needed in this method. Experiments on several LV echocardiograms and clinical validation have shown the effectiveness of our method in these patient studies.

Original languageEnglish
Pages (from-to)1057-1068
Number of pages12
JournalPattern Recognition
Volume26
Issue number7
DOIs
Publication statusPublished - 1993 Jan 1

Fingerprint

Neural networks
Echocardiography
Hopfield neural networks
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Tsai, Ching Tsorng ; Sun, Yung-Nien ; Chung, Pau-Choo ; Lee, Jiann Shu. / Endocardial boundary detection using a neural network. In: Pattern Recognition. 1993 ; Vol. 26, No. 7. pp. 1057-1068.
@article{fe31f01e42c749819761eece2ecaef41,
title = "Endocardial boundary detection using a neural network",
abstract = "Echocardiography has been widely used as a real-time non-invasive clinical tool to diagnose cardiac functions. Due to the poor quality and inherent ambiguity in echocardiograms, it is difficult to detect the myocardial boundaries of the left ventricle. Many existing methods are semi-automatic and detect cardial boundaries by serial computation which is too slow to be practical in real applications. In this paper, a new method for detecting the endocardial boundary by using a Hopfield neural network is proposed. Taking advantage of parallel computation and energy convergence capability in the Hopfield network, this method is faster and more stable for the detection of the endocardial border. Moreover, neither manual operations nor a priori assumptions are needed in this method. Experiments on several LV echocardiograms and clinical validation have shown the effectiveness of our method in these patient studies.",
author = "Tsai, {Ching Tsorng} and Yung-Nien Sun and Pau-Choo Chung and Lee, {Jiann Shu}",
year = "1993",
month = "1",
day = "1",
doi = "10.1016/0031-3203(93)90007-J",
language = "English",
volume = "26",
pages = "1057--1068",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "7",

}

Endocardial boundary detection using a neural network. / Tsai, Ching Tsorng; Sun, Yung-Nien; Chung, Pau-Choo; Lee, Jiann Shu.

In: Pattern Recognition, Vol. 26, No. 7, 01.01.1993, p. 1057-1068.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Endocardial boundary detection using a neural network

AU - Tsai, Ching Tsorng

AU - Sun, Yung-Nien

AU - Chung, Pau-Choo

AU - Lee, Jiann Shu

PY - 1993/1/1

Y1 - 1993/1/1

N2 - Echocardiography has been widely used as a real-time non-invasive clinical tool to diagnose cardiac functions. Due to the poor quality and inherent ambiguity in echocardiograms, it is difficult to detect the myocardial boundaries of the left ventricle. Many existing methods are semi-automatic and detect cardial boundaries by serial computation which is too slow to be practical in real applications. In this paper, a new method for detecting the endocardial boundary by using a Hopfield neural network is proposed. Taking advantage of parallel computation and energy convergence capability in the Hopfield network, this method is faster and more stable for the detection of the endocardial border. Moreover, neither manual operations nor a priori assumptions are needed in this method. Experiments on several LV echocardiograms and clinical validation have shown the effectiveness of our method in these patient studies.

AB - Echocardiography has been widely used as a real-time non-invasive clinical tool to diagnose cardiac functions. Due to the poor quality and inherent ambiguity in echocardiograms, it is difficult to detect the myocardial boundaries of the left ventricle. Many existing methods are semi-automatic and detect cardial boundaries by serial computation which is too slow to be practical in real applications. In this paper, a new method for detecting the endocardial boundary by using a Hopfield neural network is proposed. Taking advantage of parallel computation and energy convergence capability in the Hopfield network, this method is faster and more stable for the detection of the endocardial border. Moreover, neither manual operations nor a priori assumptions are needed in this method. Experiments on several LV echocardiograms and clinical validation have shown the effectiveness of our method in these patient studies.

UR - http://www.scopus.com/inward/record.url?scp=0027623734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027623734&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(93)90007-J

DO - 10.1016/0031-3203(93)90007-J

M3 - Article

VL - 26

SP - 1057

EP - 1068

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 7

ER -