Texture Spectrum Coupled with Entropy and Homogeneity Image Features for Myocardium Muscle Characterization

Author(s): Luminita Moraru*, Simona Moldovanu, Anisia-Luiza Culea-Florescu, Dorin Bibicu, Nilanjan Dey, Amira Salah Ashour, Robert Simon Sherratt

Journal Name: Current Bioinformatics

Volume 14 , Issue 4 , 2019

DOI : 10.2174/1574893614666181220095343

  Journal Home
Become EABM
Become Reviewer

Graphical Abstract:


Abstract:

Background: People in middle/later age often suffer from heart muscle damage due to coronary artery disease associated to myocardial infarction. In young people, the genetic forms of cardiomyopathies (heart muscle disease) are the utmost protuberant cause of myocardial disease.

Objective: Accurate early detected information regarding the myocardial tissue structure is a key answer for tracking the progress of several myocardial diseases.

Method: The present work proposes a new method for myocardium muscle texture classification based on entropy, homogeneity and on the texture unit-based texture spectrum approaches. Entropy and homogeneity are generated in moving windows of size 3x3 and 5x5 to enhance the texture features and to create the premise of differentiation of the myocardium structures. The texture is then statistically analyzed using the texture spectrum approach. Texture classification is achieved based on a fuzzy c–means descriptive classifier. The proposed method has been tested on a dataset of 80 echocardiographic ultrasound images in both short-axis and long-axis in apical two chamber view representations, for normal and infarct pathologies.

Results: The noise sensitivity of the fuzzy c–means classifier was overcome by using the image features. The results established that the entropy-based features provided superior clustering results compared to homogeneity.

Conclusion: Entropy image feature has a lower spread of the data in the clusters of healthy subjects and myocardial infarction. Also, the Euclidean distance function between the cluster centroids has higher values for both LAX and SAX views for entropy images.

Keywords: Entropy, homogeneity, image feature, texture spectrum, fuzzy c–means, myocardium.

[1]
Bibicu D, Moraru L. Cardiac cycle phase estimation in 2-D echocardiographic images using an artificial neural network. IEEE Trans Biomed Eng 2013; 60(5): 1273-9.
[2]
Amichi A, Laugier P. Quantitative texture analysis and transesophageal echocardiography to characterize the acute myocardial contusion. Open Med Inform J 2009; 3: 13-8.
[3]
Gerber TC, Foley DA, Zheng Y, Behrenbeck T, Tajik AJ, Seward JB. Differentiation of intracardiac tumors and thrombi by echocardiographic tissue characterization: comparison of an artificial neural network and human observers. Echocardiography 2000; 17(2): 115-26.
[4]
Abonyi J, Migaly S, Szeifert F. Fuzzy Self-Organizing Map based on Regularized Fuzzy c-means Clustering. In: Benítez JM, Cordón O, Hoffmann F, Roy R, Eds. Advances in soft computing. London: Springer 2003; pp. 99-108.
[5]
Krinidis S, Chatzis V. A robust fuzzy local information C-Means clustering algorithm. IEEE Trans Image Process 2010; 19(5): 1328-37.
[6]
Park DC, Ed. Intuitive fuzzy c-means algorithm for mri segmentation. Proceedings of the IEEE International Conference Information Science and Applications. 2010 April 21-23; Seoul, South Korea. IEEE 2010 2010.
[7]
Ahmed SS, Dey N, Ashour AS, et al. Effect of fuzzy partitioning in Crohn’s disease classification: a neuro-fuzzy-based approach. Med Biol Eng Comput 2017; 55(1): 101-15.
[8]
Krity VJ, Dey N, Kumar V. Internet of Things of big data technologies for future generation healthcare Springer 2016.
[9]
Nath SS, Mishra G, Kar J, Chakraborty S, Dey N, Eds. A survey of image classification methods and techniques.Proceedings of the International Conference Control, Instrumentation, Communication and Computational Technologies. 2014 July 10-11; Kanyakumari, India. IEEE 2014 2014. IEEE 2014 2014.
[10]
Kausar N, Palaniappan S, Samir BB, Abdullah A, Dey N. Applications of intelligent optimization in biology and medicine: Intelligent systems reference library. Springer 2015.
[11]
Wang D, He T, Li Z, et al. Image feature-based affective retrieval employing improved parameter and structure identification of adaptive neuro-fuzzy inference system. Neural Comput Appl 2016; 96: 1-16.
[12]
Surekha B, Swamy GN. Digital image ownership verification based¶ on spatial correlation of Colors Proceedings of the IET Conference¶ 2012 July 3-4; London, UK. 2012; 1-5.
[13]
Roy P, Goswami S, Chakraborty S, Azar AT, Dey N. Image Segmentation using rough set theory: A Review. IJRSDA 2014; 1(2): 62-74.
[14]
Ciulla M, Paliotti R, Hess DB, et al. Echocardiographic patterns of myocardial fibrosis in hypertensive patients: endomyocardial biopsy versus ultrasonic tissue characterization. J Am Soc Echocardiogr 1997; 10(6): 657-64.
[15]
He DC, Wang L. Texture unit, texture spectrum and texture analysis. IEEE Trans Geosci Remote Sens 1990; 28: 509-12.
[16]
He DC, Wang L. Simplified Texture Spectrum for Texture Analysis. J Commun Comput 2010; 7: 44-53.
[17]
Wiselin JG, Ganesan L, Sankar Ganesh S. Unsupervised texture classification. J Theor Appl Inform Tech 2009; 5: 373-81.
[18]
Haralick RM, Shanmugan K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern 1973; 3: 610-21.
[19]
Moldovanu S, Moraru L, Biswas A. Texture features that characterize 2D-echocardiography-A Review. Adv Sci Lett 2012; 17: 1-10.
[20]
Eftestøl T, Maløy F, Engan K, Kotu LP, Woie L, Orn S, Eds. A texture-based probability mapping for localisation of clinically important cardiac segments in the myocardium in cardiac magnetic resonance images from myocardial infarction patients.Proceedings of the International Conference Image Processing. 2014 Oct 27-30; Paris, France. IEEE 2014 2014. IEEE 2014 2014.
[21]
Moraru L, Moldovanu S, Biswas A. Optimization of breast lesion segmentation in texture feature space approach. Med Eng Phys 2014; 36(1): 129-35.
[22]
Vidya KS, Ng EYK, Acharya UR, Chou SM, Tan RS, Ghista DN. Computer-aided diagnosis of Myocardial Infarction using ultrasound images with DWT, GLCM and HOS methods: A comparative study. Comput Biol Med 2015; 62: 86-93.
[23]
Bezdek JC. Pattern Recognition with fuzzy objective function algorithms 1981; 25-56.
[24]
Michels K, Klawonn F, Kruse R, Nürnberger A. Fuzzy Control: Fundamentals. Stability and Design of Fuzzy Controllers 2006.
[25]
Kruse R, Borgelt C, Klawonn F, Moewes C, Steinbrecher M, Held P. Computational Intelligence - A Methodological Introduction. Springer 2013.
[26]
Deselaers T, Hegerath A, Keysers D, Ney H, Eds. Sparse patch-histograms for object classification in cluttered images. Proceedings of the 27th DAGM Symposium. 2006 Sept 12-14; Berlin, Germany. 2006 2006.
[27]
Moldovanu S, Moraru L, Bibicu D. Characterization of myocardium muscle biostructure using first order features. Dig J Nanomater Biostruct 2011; 6: 1357-65.
[28]
Sudarshan VK, Ng EYK, Acharya UR, Tan RS, Chou SM, Ghista DN. Infarcted left ventricle classification from cross-sectional echocardiograms using relative wavelet energy and entropy features. J Mech Med Biol 2016; 16: 1640009.


Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 14
ISSUE: 4
Year: 2019
Published on: 10 April, 2019
Page: [295 - 304]
Pages: 10
DOI: 10.2174/1574893614666181220095343
Price: $65

Article Metrics

PDF: 74
HTML: 4
EPUB: 1
PRC: 1



Related Article(s)

Most Downloaded Article(s)