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.
Comput Methods Programs Biomed. 2018 Jan;153:83-92. doi: 10.1016/j.cmpb.2017.10.009. Epub 2017 Oct 12.
The purpose of this study was to propose a hybrid ensemble classifier to characterize coronary plaque regions in intravascular ultrasound (IVUS) images.
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.
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.
The proposed method had high clinical applicability for image-based tissue characterization.
本研究旨在提出一种混合集成分类器，以对血管内超声（IVUS）图像中的冠状动脉斑块区域进行特征描述。
通过边界分割、特征提取、特征选择和分类过程，将像素分配到 4 种组织之一（纤维组织（FT）、纤维脂肪组织（FFT）、坏死核心（NC）和致密钙（DC））。灰度 IVUS 图像及其对应的虚拟组织学图像由 11 名已知或疑似冠心病患者的 20MHz 导管采集。共提取了 102 种混合纹理特征，包括一阶统计量（FOS）、灰度共生矩阵（GLCM）、扩展灰度游程长度矩阵（GLRLM）、Laws 纹理、局部二值模式（LBP）、强度和离散小波特征（DWF）。为了选择最优的特征集，本研究实施了遗传算法。然后，基于直方图和纹理信息的混合集成分类器用于本研究中的斑块特征描述。最优特征集被用作该集成分类器的输入。在组织特征描述后，计算了灵敏度、特异性和准确性等参数，以验证所提出的方法。本研究采用 10 折交叉验证方法来确定所提出方法的统计显著性。
实验结果表明，该方法在 IVUS 图像的组织特征描述方面具有可靠的性能。与其他现有方法相比，混合集成分类方法在 FFT 方面的特征描述准确性达到 81%，在 NC 方面的特征描述准确性达到 75%，表现出更好的性能。此外，本研究表明 Laws 特征（SSV 和 SAV）是冠状动脉组织特征描述的关键指标。
该方法在基于图像的组织特征描述方面具有较高的临床适用性。
