No Access

GLOBAL FEATURE FOR LEFT VENTRICULAR DYSFUNCTION DETECTION BASED ON SHAPE DEFORMATION TRACKING

Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, UKM, Bangi, Malaysia

Search for more papers by this author

M. Marzuki Mustafa

Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, UKM, Bangi, Malaysia

Corresponding author: M. Marzuki Mustafa, Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, UKM, Bangi, Malaysia.

Search for more papers by this author

Aini Hussain

Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, UKM, Bangi, Malaysia

Search for more papers by this author

W. Mimi Diyana W. Zaki

Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, UKM, Bangi, Malaysia

Search for more papers by this author

Oteh Maskon

Cardiac Care Unit, Medical Center, UKM, Kuala Lumpur, Malaysia

Search for more papers by this author

, and

Ika Faizura Mohd Nor

Cardiac Care Unit, Medical Center, UKM, Kuala Lumpur, Malaysia

Search for more papers by this author

https://doi.org/10.4015/S1016237215500179Cited by:1 (Source: Crossref)

Abstract

Left ventricular (LV) shape alteration is closely correlated with cardiac disease and LV function. In this paper, we propose a feature to detect LV dysfunction globally by analyzing the LV shape deformation in systolic contraction. The feature is an index that is extracted from geometric measurement of LV shape such as the length of the long axis, the short axis, and the apical diameter. A framework for computing the features is also proposed that consists of shape model construction and motion estimation of myocardial boundary. The LV shape model is extracted from apical 2 and 4 chamber views of 2D echocardiography. The long axis, the short axis, and the apical diameter were redefined according to the LV shape constructed. An optical flow technique was used to estimate the position of the LV boundary in each frame. The classification of the LV dysfunction was performed using linear discriminant analysis (LDA) and neural networks (NNs). The 2D echocardiography dataset collected from routine clinical check-up were used to validate the proposed method by comparing the computation result and cardiac expert diagnose. Classification performance and statistical analysis, which was performed to discriminate between healthy and diseased data, indicated promising results. The global LV features would provide a strong basis for a global LV function diagnosis and a global cardiac pathology assessment.

Keywords:

References

K. Yamaguchi et al. , J. Med. Invest. 54 , 1 ( 2007 ) . Google Scholar
S. Melo et al. , Biomed. Eng. Online 9 , 1 ( 2010 ) . Web of Science, Google Scholar
I. S. Salgo et al. , J. Am. Soc. Echocardiogr. 25 , 1 ( 2012 ) . Web of Science, Google Scholar
J. E. Schneider , Methods. Mol. Biol. 771 , 387 ( 2011 ) . Google Scholar
S. Yeo et al. , Med. Biol. Eng. Comput. 47 , 3 ( 2009 ) . Web of Science, Google Scholar
J. Manivannan et al. , Australas Phys. Eng. Sci. Med. 28 , 1 ( 2005 ) . Google Scholar
A. Mukhopadhyayet al., Shape analysis of the left ventricular endocardial surface and its application in detecting coronary artery disease, 6th Int Conf Funct imaging Model Hear (Springer-Verlag, New York City, NY, 2011) pp. 275–283. Google Scholar
T. Ueno et al. , Eur. J. Cardio-Thoracic Surg. 32 , 1 ( 2007 ) . Web of Science, Google Scholar
M. Di Donato et al. , J. Thorac. Cardiovasc. Surg. 121 , 1 ( 2001 ) . Web of Science, Google Scholar
M. Di Donato et al. , Eur. J. Cardio-Thoracic Surg. 29 , 0 ( 2006 ) . Web of Science, Google Scholar
K. Punithakumar et al. , IEEE Trans. Biomed. Eng. 57 , 8 ( 2010 ) . Web of Science, Google Scholar
C. Chaojie et al. , IEEE Trans. Med. Imaging 31 , 3 ( 2012 ) . Google Scholar
A. H. Saputro et al. , J. Inf. Comput. Sci. 8 , 10 ( 2011 ) . Google Scholar
D. Sun, S. Roth and M. J. Black, Secrets of optical flow estimation and their principles, 23rd IEEE Conf Computer Vision and Pattern Recognition (IEEE Computer Society, San Francisco, 2010) pp. 2432–2439. Google Scholar
T. Broxet al., High Accuracy Optical Flow Estimation Based on a Theory for Warping, 8th Eur Conf Computer Vision4 (Springer-Verlag, Berlin/Heidelberg, Prague, Czech Republic, 2004) pp. 25–36. Google Scholar
M. D. Cerqueira et al. , Am. Hear. Assoc. 105 , 539 ( 2002 ) . Web of Science, Google Scholar
V. Pratt , SIGGRAPH Comput. Graph. 21 , 4 ( 1987 ) . Google Scholar
G. Taubin et al. , Pattern Anal. Mach. Intell. IEEE Trans. 16 , 3 ( 1994 ) . Web of Science, Google Scholar
G. Taubin , IEEE Trans. Pattern Anal. Mach. Intell. 13 , 11 ( 1991 ) . Web of Science, Google Scholar
P. E. Shrout and J. L. Fleiss , Psychol. Bull. 86 , 2 ( 1979 ) . Web of Science, Google Scholar
L. Rovas et al. , Ultrasound Obs. Gynecol. 26 , 2 ( 2005 ) . Web of Science, Google Scholar
A. H. Saputroet al., Precise global shape analysis for left ventricle function assessment, 2012 Third Int Conf Intelligent System Modeling and Simulation (ISMS) (2012) pp. 343–347. Google Scholar
R. Kumar and A. Indrayan , Indian Pediatr. 48 , 277 ( 2011 ) . Web of Science, Google Scholar
N. A. Obuchowski , Am. J. Roentgenol. 184 , 2 ( 2005 ) . Web of Science, Google Scholar
P. Gaudron et al. , Circulation 87 , 3 ( 1993 ) . Web of Science, Google Scholar