Characterization of coronary plaque regions in intravascular ultrasound images using a hybrid ensemble classifier

BACKGROUND AND OBJECTIVES The purpose of this study was to propose a hybrid ensemble classifier to characterize coronary plaque regions in intravascular ultrasound (IVUS) images. METHODS Pixels were allocated to one of four tissues (fibrous tissue (FT), fibro-fatty tissue (FFT), necrotic core (NC), and dense calcium (DC)) through processes of border segmentation, feature extraction, feature selection, and classification. Grayscale IVUS images and their corresponding virtual histology images were acquired from 11 patients with known or suspected coronary artery disease using 20 MHz catheter. A total of 102 hybrid textural features including first order statistics (FOS), gray level co-occurrence matrix (GLCM), extended gray level run-length matrix (GLRLM), Laws, local binary pattern (LBP), intensity, and discrete wavelet features (DWF) were extracted from IVUS images. To select optimal feature sets, genetic algorithm was implemented. A hybrid ensemble classifier based on histogram and texture information was then used for plaque characterization in this study. The optimal feature set was used as input of this ensemble classifier. After tissue characterization, parameters including sensitivity, specificity, and accuracy were calculated to validate the proposed approach. A ten-fold cross validation approach was used to determine the statistical significance of the proposed method. RESULTS Our experimental results showed that the proposed method had reliable performance for tissue characterization in IVUS images. The hybrid ensemble classification method outperformed other existing methods by achieving characterization accuracy of 81% for FFT and 75% for NC. In addition, this study showed that Laws features (SSV and SAV) were key indicators for coronary tissue characterization. CONCLUSIONS The proposed method had high clinical applicability for image-based tissue characterization.

[1]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..

[2]  Amanda J. C. Sharkey,et al.  On Combining Artificial Neural Nets , 1996, Connect. Sci..

[3]  M Amiel,et al.  Artifacts in intravascular ultrasound imaging: analyses and implications. , 1993, Ultrasound in medicine & biology.

[4]  Christopher M. Kramer,et al.  The Vulnerable Atherosclerotic Plaque: Strategies for Diagnosis and Management , 2007 .

[5]  Xiaoou Tang,et al.  Texture information in run-length matrices , 1998, IEEE Trans. Image Process..

[6]  Desire L. Massart,et al.  Feature selection in principal component analysis of analytical data , 2002 .

[7]  Morteza Naghavi,et al.  Image-Based Frame Gating of IVUS Pullbacks: A Surrogate for ECG , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[8]  R. Virmani,et al.  Coronary risk factors and plaque morphology in men with coronary disease who died suddenly. , 1997, The New England journal of medicine.

[9]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[10]  Erling Falk,et al.  Non-invasive imaging of atherosclerosis. , 2012, European heart journal cardiovascular Imaging.

[11]  P. Yock,et al.  Intravascular ultrasound: novel pathophysiological insights and current clinical applications. , 2001, Circulation.

[12]  N. Obuchowski,et al.  Assessing spectral algorithms to predict atherosclerotic plaque composition with normalized and raw intravascular ultrasound data. , 2001, Ultrasound in Medicine and Biology.

[13]  R. Virmani,et al.  Lessons from sudden coronary death: a comprehensive morphological classification scheme for atherosclerotic lesions. , 2000, Arteriosclerosis, thrombosis, and vascular biology.

[14]  Kenneth I. Laws,et al.  Rapid Texture Identification , 1980, Optics & Photonics.

[15]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[16]  Derek Partridge.  Network generalization differences quantified , 1996, Neural Networks.

[17]  Banshidhar Majhi,et al.  Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests , 2016, Neurocomputing.

[18]  Ioannis B. Theocharis,et al.  Genetic fuzzy rule based classification systems for coronary plaque characterization based on intravascular ultrasound images , 2015, Eng. Appl. Artif. Intell..

[19]  V. Bhargava,et al.  Value and limitations of intravascular ultrasound imaging in characterizing coronary atherosclerotic plaque. , 1995, American heart journal.

[20]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[21]  Dimitrios I Fotiadis,et al.  A hybrid plaque characterization method using intravascular ultrasound images. , 2013, Technology and health care : official journal of the European Society for Engineering and Medicine.

[22]  Dimitrios I. Fotiadis,et al.  A Novel Semiautomated Atherosclerotic Plaque Characterization Method Using Grayscale Intravascular Ultrasound Images: Comparison With Virtual Histology , 2012, IEEE Transactions on Information Technology in Biomedicine.

[23]  Nassir Navab,et al.  An IVUS image-based approach for improvement of coronary plaque characterization , 2013, Comput. Biol. Medicine.

[24]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Michael Unser,et al.  Texture classification and segmentation using wavelet frames , 1995, IEEE Trans. Image Process..

[26]  Ali A. Sakr,et al.  Automated Focal Liver Lesion Staging Classification based on Haralick Texture Features and Multi-SVM , 2014 .

[27]  R. Virmani,et al.  Accuracy of in vivo coronary plaque morphology assessment: a validation study of in vivo virtual histology compared with in vitro histopathology. , 2006, Journal of the American College of Cardiology.

[28]  Young-Hak Kim,et al.  Effects of statin treatments on coronary plaques assessed by volumetric virtual histology intravascular ultrasound analysis. , 2009, JACC. Cardiovascular interventions.

[29]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[31]  R. Boggia,et al.  Genetic algorithms as a strategy for feature selection , 1992 .

[32]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[33]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[34]  J. Hodgson,et al.  Correlation of intracoronary ultrasound plaque characteristics in atherosclerotic coronary artery disease patients with clinical variables. , 1994, The American journal of cardiology.

[35]  E. Tuzcu,et al.  Coronary Plaque Classification With Intravascular Ultrasound Radiofrequency Data Analysis , 2002, Circulation.

[36]  M. Matsuzaki,et al.  Detection of lipid-laden atherosclerotic plaque by wavelet analysis of radiofrequency intravascular ultrasound signals: in vitro validation and preliminary in vivo application. , 2005, Journal of the American College of Cardiology.

[37]  Azriel Rosenfeld,et al.  Experiments with texture classification using averages of local pattern matches , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[38]  Jamshid Dehmeshki,et al.  Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy , 2015, Comput. Medical Imaging Graph..

[39]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[40]  Nassir Navab,et al.  A new approach for improving coronary plaque component analysis based on intravascular ultrasound images. , 2010, Ultrasound in medicine & biology.

[41]  J M Tobis,et al.  Variability in tissue characterization of atherosclerotic plaque by intravascular ultrasound: a comparison of four intravascular ultrasound systems. , 1996, American journal of cardiac imaging.

[42]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[43]  D. Vince,et al.  Comparison of texture analysis methods for the characterization of coronary plaques in intravascular ultrasound images. , 2000, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[44]  Guillermo García,et al.  Evaluation of Texture for Classification of Abdominal Aortic Aneurysm After Endovascular Repair , 2012, Journal of Digital Imaging.

[45]  Milan Sonka,et al.  Tissue characterization in intravascular ultrasound images , 1998, IEEE Transactions on Medical Imaging.

[46]  Steven E. Nissen,et al.  IVUS Made Easy , 2005 .

[47]  Erkki Oja,et al.  Texture discrimination with multidimensional distributions of signed gray-level differences , 2001, Pattern Recognit..

[48]  A. Erglis,et al.  Intravascular Ultrasound-based Imaging Modalities for Tissue Characterisation. , 2014, Interventional cardiology.

[49]  J R Beck,et al.  The use of relative operating characteristic (ROC) curves in test performance evaluation. , 1986, Archives of pathology & laboratory medicine.