[基于支持向量机的超声图像诊断前列腺癌]

[Diagnosis of prostate cancer using SVM-based ultrasound images].

作者信息

Yang Zhen-Sen, Li Chuan-Fu, Shi Jun, Zhou Kang-Yuan, He Li

机构信息

Dept. of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, Anhui Provice 230027.

出版信息

Zhongguo Yi Liao Qi Xie Za Zhi. 2008 Nov;32(6):398-401.

PMID:19253568

Abstract

This paper presents a computer-aided diagnosis method for prostate cancer detection using Trans-rectal ultrasound(TRUS) images. Firstly, statistical texture analysis is implemented in every ROI in segmented prostate images. From each ROI, grey level difference vector features, edge-frequency features and texture features in frequency domain are constructed. Then, the number of features is reduced using ANOVA statistics to select the optimal feature subset. Finally, SVM is applied to the selected subset for detecting the cancer regions. Experimental results show that the proposed algorithm can recognize and detect the cancer images effectively so as to supply essential information for a diagnosis.

摘要

本文提出了一种利用经直肠超声（TRUS）图像进行前列腺癌检测的计算机辅助诊断方法。首先，在分割后的前列腺图像的每个感兴趣区域（ROI）中进行统计纹理分析。从每个ROI中，构建灰度级差向量特征、边缘频率特征和频域纹理特征。然后，使用方差分析统计减少特征数量，以选择最优特征子集。最后，将支持向量机（SVM）应用于所选子集以检测癌区。实验结果表明，所提出的算法能够有效地识别和检测癌症图像，从而为诊断提供重要信息。