Pang Zhiyong, Zhu Dongmei, Chen Dihu, Li Li, Shao Yuanzhi
School of Physics and Engineering, Sun Yat-sen University, Guangzhou 510275, China.
Imaging Diagnosis and Interventional Center, Cancer Center, The Sun Yat-sen University, Guangzhou 510060, China.
Comput Math Methods Med. 2015;2015:450531. doi: 10.1155/2015/450531. Epub 2015 Jan 6.
This study established a fully automated computer-aided diagnosis (CAD) system for the classification of malignant and benign masses via breast magnetic resonance imaging (BMRI). A breast segmentation method consisting of a preprocessing step to identify the air-breast interfacing boundary and curve fitting for chest wall line (CWL) segmentation was included in the proposed CAD system. The Chan-Vese (CV) model level set (LS) segmentation method was adopted to segment breast mass and demonstrated sufficiently good segmentation performance. The support vector machine (SVM) classifier with ReliefF feature selection was used to merge the extracted morphological and texture features into a classification score. The accuracy, sensitivity, and specificity measurements for the leave-half-case-out resampling method were 92.3%, 98.2%, and 76.2%, respectively. For the leave-one-case-out resampling method, the measurements were 90.0%, 98.7%, and 73.8%, respectively.
本研究建立了一种通过乳腺磁共振成像（BMRI）对恶性和良性肿块进行分类的全自动计算机辅助诊断（CAD）系统。所提出的CAD系统包括一种乳腺分割方法，该方法由识别空气-乳腺界面边界的预处理步骤和用于胸壁线（CWL）分割的曲线拟合组成。采用Chan-Vese（CV）模型水平集（LS）分割方法对乳腺肿块进行分割，并表现出足够好的分割性能。使用具有ReliefF特征选择的支持向量机（SVM）分类器将提取的形态学和纹理特征合并为一个分类分数。留半法重采样方法的准确度、灵敏度和特异性测量值分别为92.3%、98.2%和76.2%。对于留一法重采样方法，测量值分别为90.0%、98.7%和73.8%。
