Literature DB >> 29157464

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

Yoo Na Hwang1, Ju Hwan Lee2, Ga Young Kim1, Eun Seok Shin3, Sung Min Kim4.   

Abstract

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.
Copyright © 2017 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Ensemble classifier; Genetic algorithm; Intravascular ultrasound; Plaque characterization

Mesh:

Year:  2017        PMID: 29157464     DOI: 10.1016/j.cmpb.2017.10.009

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   5.428


  3 in total

1.  A Domain Enriched Deep Learning Approach to Classify Atherosclerosis using Intravascular Ultrasound Imaging.

Authors:  Max L Olender; Lambros S Athanasiou; Lampros K Michalis; Dimitris I Fotiadis; Elazer R Edelman
Journal:  IEEE J Sel Top Signal Process       Date:  2020-06-15       Impact factor: 6.856

2.  Automatic A-line coronary plaque classification using combined deep learning and textural features in intravascular OCT images.

Authors:  Juhwan Lee; Chaitanya Kolluru; Yazan Gharaibeh; David Prabhu; Vladislav N Zimin; Hiram Bezerra; David Wilson
Journal:  Proc SPIE Int Soc Opt Eng       Date:  2020-03-16

3.  Automated classification of dense calcium tissues in gray-scale intravascular ultrasound images using a deep belief network.

Authors:  Juhwan Lee; Yoo Na Hwang; Ga Young Kim; Ji Yean Kwon; Sung Min Kim
Journal:  BMC Med Imaging       Date:  2019-12-30       Impact factor: 1.930

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.