CLASSIFICATION OF THE THYROID NODULES BASED ON CHARACTERISTIC SONOGRAPHIC TEXTURAL FEATURE AND CORRELATED HISTOPATHOLOGY USING HIERARCHICAL SUPPORT VECTOR MACHINES
CLASSIFICATION OF THE THYROID NODULES BASED ON CHARACTERISTIC SONOGRAPHIC TEXTURAL FEATURE AND CORRELATED HISTOPATHOLOGY USING HIERARCHICAL SUPPORT VECTOR MACHINES
复制标题
DOI：
10.1016/j.ultrasmedbio.2010.08.019
复制
发表时间：
2010-12-01
影响因子：
2.9
通讯作者：
Wei, Chang-Kuo
中科院分区：
文献类型：
--
作者：
Chen, Shao-Jer;Chang, Chuan-Yu;Wei, Chang-Kuo
本研究对甲状腺结节的超声图像进行了分类，以方便临床诊断和管理。分层支持向量机（SVM）分类系统用于选择代表甲状腺结节主要组织病理学成分的特征性超声纹理特征。使用两个超声系统（材料和方法部分中提到的 LA39 和 i12L）进行比较。该研究招募了来自每个系统的 76 个甲状腺结节性病变和 157 个感兴趣区域的甲状腺超声图像。对于所有病变，影响图像采集的参数保持相同的条件。应用常用的纹理分析方法来表征甲状腺超声图像。根据相应的病理结果对图像特征进行分类。为了估计它们与分类的相关性和性能，支持向量机被用作特征选择器和分类器。甲状腺结节首先按总和平均分为两种主要类型，即滤泡基底结节和纤维化基底结节。根据游程长度不均匀性(RLNU)，滤泡基底结节可进一步完整地分为少细胞滤泡、滤泡细胞滤泡和乳头状癌细胞滤泡。纤维化基底结节进一步通过平方和分为少细胞纤维化和优势细胞纤维化。以细胞为优势的纤维化基底肿瘤根据熵可分为滤泡细胞纤维化和乳头状癌细胞纤维化。分层SVM分类系统的诊断准确率在96.34%到100%之间。此外，系统可以选择最佳的超声纹理特征来区分滤泡和纤维化基底甲状腺结节或其中混合的细胞类型。在滤泡基部甲状腺结节中，乳头状癌的超声纹理 RLNU 较高，但低于滤泡细胞。在纤维化基底甲状腺结节中，乳头状癌显示超声纹理变化和熵增加。 （电子邮件：a120930@tzuchi.com.tw） 皇冠版权所有 (C) 2010 由 Elsevier Inc. 代表世界超声医学与生物学联合会出版。
In this study, the ultrasound images of thyroid nodules were classified to facilitate clinical diagnosis and management. The hierarchical support vector machines (SVM) classification system was used to select the characteristic sonographic textural feature that represents the major histopathologic components of the thyroid nodules. Two ultrasound systems (LA39 and i12L mentioned in the Materials and Methods section) were used for comparison. Seventy-six thyroid nodular lesions and 157 regions-of-interest thyroid ultrasound image from each system were recruited in the study. The parameters affecting image acquisition were kept in the same condition for all lesions. Commonly used texture analysis methods were applied to characterize thyroid ultrasound images. Image features were classified according to the corresponding pathologic findings. To estimate their relevance and performance to classification, SVMs were used as a feature selector and a classifier. The thyroid nodules are first categorized as two main types, i.e., follicle base and fibrosis base nodule, by sum average. The follicle base nodules can be further and completely classified into follicles with few cells, follicles with follicular cells and follicles with papillary cancer cells by run length nonuniformity (RLNU). The fibrosis base nodules are further classified by sum square into fibrosis with few cells and fibrosis with dominant cells. The fibrosis base neoplasm with dominant cells can be separated into fibrosis with follicular cells and fibrosis with papillary cancer cells by entropy. The hierarchical SVM classification system achieves a diagnostic accuracy between 96.34% and 100%. Besides, the best sonographic textural feature can be selected by the system for the differentiation between the follicle and fibrosis base thyroid nodules or the cell types mixed in them. In follicle base thyroid nodules, papillary cancers show higher sonographic textural RLNU but less than follicular cells. In fibrosis base thyroid nodules, papillary cancers show increased sonographic textural variance and entropy. (E-mail: a120930@tzuchi.com.tw) Crown Copyright (C) 2010 Published by Elsevier Inc. on behalf of World Federation for Ultrasound in Medicine & Biology.