Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features
Atherosclerotic plaque rupture is the most common mechanism responsible for a majority of sudden coronary deaths. The precursor lesion of plaque rupture is thought to be a thin cap fibroatheroma (TCFA), or “vulnerable plaque”. Virtual Histology-Intravascular Ultrasound (VH-IVUS)...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | http://www.mdpi.com/2076-3417/8/9/1632 |
id |
doaj-563a5fb26bc74a56b2453a9568a760c6 |
---|---|
record_format |
Article |
spelling |
doaj-563a5fb26bc74a56b2453a9568a760c62020-11-25T02:17:14ZengMDPI AGApplied Sciences2076-34172018-09-0189163210.3390/app8091632app8091632Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture FeaturesZahra Rezaei0Ali Selamat1Arash Taki2Mohd Shafry Mohd Rahim3Mohammed Rafiq Abdul Kadir4Marek Penhaker5Ondrej Krejcar6Kamil Kuca7Enrique Herrera-Viedma8Hamido Fujita9School of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM) & Media and Games Centre of Excellence (MagicX), 81310 UTM Johor Bahru, Johor, MalaysiaSchool of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM) & Media and Games Centre of Excellence (MagicX), 81310 UTM Johor Bahru, Johor, MalaysiaTechnical University of Munich (TUM), 80333 Munich, GermanySchool of Computing, Faculty of Engineering, Universiti Teknologi Malaysia (UTM) & Media and Games Centre of Excellence (MagicX), 81310 UTM Johor Bahru, Johor, MalaysiaSchool of Biosciences & Medical Engineering, Faculty of Engineering, Universiti Teknologi Malaysia (UTM) & UTM-IRDA Centre of Excellence, 81310 UTM Johor Bahru, Johor, MalaysiaDepartment of Cybernetics and Biomedical Engineering, VŠB—Technical University of Ostrava, 70800 Ostrava, Czech RepublicCenter for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 50003 Hradec Kralove, Czech RepublicCenter for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Rokitanskeho 62, 50003 Hradec Kralove, Czech RepublicDepartment Computer Science and Artificial Intelligence, University of Granada, 18071 Granada, SpainFaculty of Software and Information Science, Iwate Prefectural University, Iwate 020-0693, JapanAtherosclerotic plaque rupture is the most common mechanism responsible for a majority of sudden coronary deaths. The precursor lesion of plaque rupture is thought to be a thin cap fibroatheroma (TCFA), or “vulnerable plaque”. Virtual Histology-Intravascular Ultrasound (VH-IVUS) images are clinically available for visualising colour-coded coronary artery tissue. However, it has limitations in terms of providing clinically relevant information for identifying vulnerable plaque. The aim of this research is to improve the identification of TCFA using VH-IVUS images. To more accurately segment VH-IVUS images, a semi-supervised model is developed by means of hybrid K-means with Particle Swarm Optimisation (PSO) and a minimum Euclidean distance algorithm (KMPSO-mED). Another novelty of the proposed method is fusion of different geometric and informative texture features to capture the varying heterogeneity of plaque components and compute a discriminative index for TCFA plaque, while the existing research on TCFA detection has only focused on the geometric features. Three commonly used statistical texture features are extracted from VH-IVUS images: Local Binary Patterns (LBP), Grey Level Co-occurrence Matrix (GLCM), and Modified Run Length (MRL). Geometric and texture features are concatenated in order to generate complex descriptors. Finally, Back Propagation Neural Network (BPNN), kNN (K-Nearest Neighbour), and Support Vector Machine (SVM) classifiers are applied to select the best classifier for classifying plaque into TCFA and Non-TCFA. The present study proposes a fast and accurate computer-aided method for plaque type classification. The proposed method is applied to 588 VH-IVUS images obtained from 10 patients. The results prove the superiority of the proposed method, with accuracy rates of 98.61% for TCFA plaque.http://www.mdpi.com/2076-3417/8/9/1632thin cap fibroatheromaVH-IVUS image segmentationtexture featureParticle Swarm Optimisation (PSO)back propagation neural networkSupport Vector Machine (SVM) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zahra Rezaei Ali Selamat Arash Taki Mohd Shafry Mohd Rahim Mohammed Rafiq Abdul Kadir Marek Penhaker Ondrej Krejcar Kamil Kuca Enrique Herrera-Viedma Hamido Fujita |
spellingShingle |
Zahra Rezaei Ali Selamat Arash Taki Mohd Shafry Mohd Rahim Mohammed Rafiq Abdul Kadir Marek Penhaker Ondrej Krejcar Kamil Kuca Enrique Herrera-Viedma Hamido Fujita Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features Applied Sciences thin cap fibroatheroma VH-IVUS image segmentation texture feature Particle Swarm Optimisation (PSO) back propagation neural network Support Vector Machine (SVM) |
author_facet |
Zahra Rezaei Ali Selamat Arash Taki Mohd Shafry Mohd Rahim Mohammed Rafiq Abdul Kadir Marek Penhaker Ondrej Krejcar Kamil Kuca Enrique Herrera-Viedma Hamido Fujita |
author_sort |
Zahra Rezaei |
title |
Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features |
title_short |
Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features |
title_full |
Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features |
title_fullStr |
Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features |
title_full_unstemmed |
Thin Cap Fibroatheroma Detection in Virtual Histology Images Using Geometric and Texture Features |
title_sort |
thin cap fibroatheroma detection in virtual histology images using geometric and texture features |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2018-09-01 |
description |
Atherosclerotic plaque rupture is the most common mechanism responsible for a majority of sudden coronary deaths. The precursor lesion of plaque rupture is thought to be a thin cap fibroatheroma (TCFA), or “vulnerable plaque”. Virtual Histology-Intravascular Ultrasound (VH-IVUS) images are clinically available for visualising colour-coded coronary artery tissue. However, it has limitations in terms of providing clinically relevant information for identifying vulnerable plaque. The aim of this research is to improve the identification of TCFA using VH-IVUS images. To more accurately segment VH-IVUS images, a semi-supervised model is developed by means of hybrid K-means with Particle Swarm Optimisation (PSO) and a minimum Euclidean distance algorithm (KMPSO-mED). Another novelty of the proposed method is fusion of different geometric and informative texture features to capture the varying heterogeneity of plaque components and compute a discriminative index for TCFA plaque, while the existing research on TCFA detection has only focused on the geometric features. Three commonly used statistical texture features are extracted from VH-IVUS images: Local Binary Patterns (LBP), Grey Level Co-occurrence Matrix (GLCM), and Modified Run Length (MRL). Geometric and texture features are concatenated in order to generate complex descriptors. Finally, Back Propagation Neural Network (BPNN), kNN (K-Nearest Neighbour), and Support Vector Machine (SVM) classifiers are applied to select the best classifier for classifying plaque into TCFA and Non-TCFA. The present study proposes a fast and accurate computer-aided method for plaque type classification. The proposed method is applied to 588 VH-IVUS images obtained from 10 patients. The results prove the superiority of the proposed method, with accuracy rates of 98.61% for TCFA plaque. |
topic |
thin cap fibroatheroma VH-IVUS image segmentation texture feature Particle Swarm Optimisation (PSO) back propagation neural network Support Vector Machine (SVM) |
url |
http://www.mdpi.com/2076-3417/8/9/1632 |
work_keys_str_mv |
AT zahrarezaei thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT aliselamat thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT arashtaki thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT mohdshafrymohdrahim thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT mohammedrafiqabdulkadir thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT marekpenhaker thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT ondrejkrejcar thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT kamilkuca thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT enriqueherreraviedma thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures AT hamidofujita thincapfibroatheromadetectioninvirtualhistologyimagesusinggeometricandtexturefeatures |
_version_ |
1724887475917160448 |