Yoo Na Hwang1, Ju Hwan Lee2, Ga Young Kim1, Eun Seok Shin3, Sung Min Kim4. 1. Department of Medical Biotechnology, Dongguk University-Bio Medi Campus (10326) 32, Dongguk-ro, Ilsandong-gu, Goyang-si, Gyeonggi-do, Republic of Korea. 2. Department of Medical Devices Industry, Dongguk University-Seoul (04620) 26, Pil-dong 3-ga, Jung-gu, Seoul, Republic of Korea. 3. Department of Cardiology, Ulsan University Hospital, University of Ulsan College of Medicine (44033) 877, Bangeojinsunhwando-ro, Dong-gu, Ulsan, Republic of Korea. 4. Department of Medical Biotechnology, Dongguk University-Bio Medi Campus (10326) 32, Dongguk-ro, Ilsandong-gu, Goyang-si, Gyeonggi-do, Republic of Korea; Department of Medical Devices Industry, Dongguk University-Seoul (04620) 26, Pil-dong 3-ga, Jung-gu, Seoul, Republic of Korea. Electronic address: smkim@dongguk.edu.
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.
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.
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
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