Xiaowei Huang1, Yanling Zhang2, Ming Qian1, Long Meng1, Yang Xiao1, Lili Niu3, Rongqin Zheng2, Hairong Zheng1. 1. Paul C. Lauterbur Research Center for Biomedical Imaging, Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. 2. Department of Ultrasound, Third Affiliated Hospital, Sun Yat-sen University, Guangzhou, China. 3. Paul C. Lauterbur Research Center for Biomedical Imaging, Institute of Biomedical and Health Engineering, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China ll.niu@siat.ac.cn.
Abstract
OBJECTIVES: Anechoic carotid plaques on sonography have been used to predict future cardiovascular or cerebrovascular events. The purpose of this study was to investigate whether carotid plaque echogenicity could be assessed objectively by combining texture features extracted by MaZda software (Institute of Electronics, Technical University of Lodz, Lodz, Poland) and morphologic characteristics, which may provide a promising method for early prediction of acute cardiovascular disease. METHODS: A total of 268 plaque images were collected from 136 volunteers and classified into 85 hyperechoic, 83 intermediate, and 100 anechoic plaques. About 300 texture features were extracted from histogram, absolute gradient, run-length matrix, gray-level co-occurrence matrix, autoregressive model, and wavelet transform algorithms by MaZda. The morphologic characteristics, including degree of stenosis, maximum plaque intima-media thickness, and maximum plaque length, were measured by B-mode sonography. Statistically significant features were selected by analysis of covariance. The most discriminative features were obtained from statistically significant features by linear discriminant analysis. The K-nearest neighbor classifier was used to classify plaque echogenicity based on statistically significant and most discriminative features. RESULTS: A total of 30 statistically significant features were selected among the plaques, and 2 most discriminative features were obtained from the statistically significant features. The classification accuracy rates for 3 types of plaques based on statistically significant and most discriminative features were 72.03% (κ= 0.571; P < .001) and 88.14% (κ= 0.820; P < .001), respectively. The receiver operating characteristic curve for identifying anechoic plaques showed an area under the curve of 0.918 when the most discriminative features were used to train the classifier. CONCLUSIONS: It is feasible to classify carotid plaque echogenicity by combining texture features extracted from sonograms by MaZda and morphologic characteristics.
OBJECTIVES: Anechoic carotid plaques on sonography have been used to predict future cardiovascular or cerebrovascular events. The purpose of this study was to investigate whether carotid plaque echogenicity could be assessed objectively by combining texture features extracted by MaZda software (Institute of Electronics, Technical University of Lodz, Lodz, Poland) and morphologic characteristics, which may provide a promising method for early prediction of acute cardiovascular disease. METHODS: A total of 268 plaque images were collected from 136 volunteers and classified into 85 hyperechoic, 83 intermediate, and 100 anechoic plaques. About 300 texture features were extracted from histogram, absolute gradient, run-length matrix, gray-level co-occurrence matrix, autoregressive model, and wavelet transform algorithms by MaZda. The morphologic characteristics, including degree of stenosis, maximum plaque intima-media thickness, and maximum plaque length, were measured by B-mode sonography. Statistically significant features were selected by analysis of covariance. The most discriminative features were obtained from statistically significant features by linear discriminant analysis. The K-nearest neighbor classifier was used to classify plaque echogenicity based on statistically significant and most discriminative features. RESULTS: A total of 30 statistically significant features were selected among the plaques, and 2 most discriminative features were obtained from the statistically significant features. The classification accuracy rates for 3 types of plaques based on statistically significant and most discriminative features were 72.03% (κ= 0.571; P < .001) and 88.14% (κ= 0.820; P < .001), respectively. The receiver operating characteristic curve for identifying anechoic plaques showed an area under the curve of 0.918 when the most discriminative features were used to train the classifier. CONCLUSIONS: It is feasible to classify carotid plaque echogenicity by combining texture features extracted from sonograms by MaZda and morphologic characteristics.
Authors: Luca Saba; Skandha S Sanagala; Suneet K Gupta; Vijaya K Koppula; Amer M Johri; Narendra N Khanna; Sophie Mavrogeni; John R Laird; Gyan Pareek; Martin Miner; Petros P Sfikakis; Athanasios Protogerou; Durga P Misra; Vikas Agarwal; Aditya M Sharma; Vijay Viswanathan; Vijay S Rathore; Monika Turk; Raghu Kolluri; Klaudija Viskovic; Elisa Cuadrado-Godia; George D Kitas; Neeraj Sharma; Andrew Nicolaides; Jasjit S Suri Journal: Ann Transl Med Date: 2021-07
Authors: Narendra N Khanna; Ankush D Jamthikar; Deep Gupta; Matteo Piga; Luca Saba; Carlo Carcassi; Argiris A Giannopoulos; Andrew Nicolaides; John R Laird; Harman S Suri; Sophie Mavrogeni; A D Protogerou; Petros Sfikakis; George D Kitas; Jasjit S Suri Journal: Curr Atheroscler Rep Date: 2019-01-25 Impact factor: 5.113
Authors: Diana Carmona-Fernandes; Sofia C Barreira; Natacha Leonardo; Renata I Casimiro; Alice M Castro; Pedro Oliveira Santos; António N Fernandes; Filipe Cortes-Figueiredo; Carolina A Gonçalves; Rafael Cruz; Mariana L Fernandes; Margarida Ivo; Luis M Pedro; Helena Canhão; João Eurico Fonseca; Maria José Santos Journal: Front Med (Lausanne) Date: 2021-05-20