光学 精密工程, 2013, 21 (8): 2137, 网络出版: 2013-09-06
基于两阶段集成支持向量机的前列腺肿瘤识别
Prostate tumor recognition based on two-stage integrating SVM
前列腺肿瘤 核磁共振成像 辅助诊断 集成支持向量机 prostate tumor Nuclear Magnetic Resonance Imaging(MRI) aided diagnosis integrating SVM
摘要
从核磁共振成像(MRI)对前列腺肿瘤的诊断入手, 提出了一种基于两阶段集成支持向量机(SVM)的前列腺肿瘤辅助诊断方法。首先, 提取MRI图像中的前列腺感兴趣区域(ROI)的统计特征、纹理特征和不变矩特征; 然后, 在不同的特征空间里, 使用不同的核函数来扰动SVM参数并在不同的特征空间生成个体SVM, 通过相对多数投票进行第一次集成; 接着把第一次集成结果用相对多数投票进行第二次集成; 最后, 以前列腺患者的MRI图像为原始数据, 采用两阶段融合集成SVM对前列腺肿瘤进行辅助诊断。实验显示, 第一次集成分类准确率最高比单SVM提高了26.67%, 第二次集成分类准确率比第一次集成SVM提高了3.33%, 结果表明本文算法能够有效提高前列腺肿瘤的识别精度。
Abstract
On the basis of prostate tumor diagnosis by nuclear Magnetic Resonance Imaging(MRI), a two-stage ensemble Support Vector Machine(SVM) method were proposed to realize the prostate tumor aided diagnosis. Firstly, the statistical features, invariant moment features and the texture feature of the Area of Interest( ROI )for the prostate in a MRI image were extracted. Then, SVM parameters were disturbed by using different kernel functions in different feature spaces, and the first ensemble was carried out by relative majority voting. Furthermore, the results of first ensemble were integrated again by the relative majority voting. Finally, MRI images of prostate patients were regarded as original data, and two-stage ensemble SVM were utilized to aid tumor diagnosis. Experiment results show that the classification accuracy from the first ensemble has improved by 26.67% as compared with that of single-stage SVM and that from the second ensemble has improved 3.33% than that of the first ensemble. These results illustrate that the proposed algorithm can improve the recognition accuracy of prostate tumor effectively.
周涛, 陆惠玲, 陈志强, 马苗. 基于两阶段集成支持向量机的前列腺肿瘤识别[J]. 光学 精密工程, 2013, 21(8): 2137. ZHOU Tao, LU Hui-ling, CHEN Zhi-qiang, MA Miao. Prostate tumor recognition based on two-stage integrating SVM[J]. Optics and Precision Engineering, 2013, 21(8): 2137.