TY - JOUR A2 - Suzuki, Kenji AU - Daoud, Mohammad I. AU - Bdair, Tariq M. AU - Al-Najar, Mahasen AU - alazrae，基于多roi纹理和形态学分析的乳腺超声图像分类方法但乳房超声(BUS)图像的准确解释往往具有挑战性，且依赖于操作者。计算机辅助诊断(CAD)系统可以为放射科医生提供第二意见，以提高诊断准确性。在本研究中，开发了一种新的CAD系统来实现总线图像的精确分类。特别地，提出了一种改进的纹理分析方法，将肿瘤分割成一组非重叠感兴趣区域(roi)。利用灰度共现矩阵特征和支持向量机分类器对每个ROI进行分析，估计其肿瘤分类指标。利用投票机制结合所有roi的肿瘤类别指标来估计肿瘤类别。此外，还采用形态学分析对肿瘤进行分类。采用概率方法融合多种感兴趣区域的纹理分析和形态分析的分类结果。 The proposed approach is applied to classify 110 BUS images that include 64 benign and 46 malignant tumors. The accuracy, specificity, and sensitivity obtained using the proposed approach are 98.2%, 98.4%, and 97.8%, respectively. These results demonstrate that the proposed approach can effectively be used to differentiate benign and malignant tumors. SN - 1748-670X UR - https://doi.org/10.1155/2016/6740956 DO - 10.1155/2016/6740956 JF - Computational and Mathematical Methods in Medicine PB - Hindawi Publishing Corporation KW - ER -