A Benign And Malignant Mass Classification Algorithm Based on An Improved Level Set Segmentation and Texture Feature Analysis

摘要：

In this paper, we investigate the classification ofmasses with texture features. We propose an improved level setmethod to find the boundary of a mass, based on the initialcontour provided by radiologists. After the boundary of a mass isfound, texture features from Gray Level Co-occurrence Matrix(GLCM) are extracted from the surrounding area of theboundary of the mass. The extracted texture features are used as the input of Linear discriminant analysis and a support vectormachine to classify the mass as benign or malignant.Mammography images from DDSM were used in theexperiments and the classification accuracy was evaluated usingthe area under the receiver operating characteristic (ROC)curve. In the proposed method the area under the ROC curve isAz=0.7. The experimental result shows the effectiveness of theproposed method.

作者: Xiaoming Liu Jun Liu Dongfeng Zhou J Tang

作者单位: College of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan, Hubei The Fifth Hospital of Harbin, Harbin, Heilongjiang, China

会议类型: 国际会议

会议名称: The 4th International Conference on Bioinformatics and Biomedical Engineering(第四届IEEE生物信息与生物医学工程国际会议 iCBBE 2010)

会议地点: 成都

会议语种:英文

页码: 1-4

在线出版日期: 2010-06-18（万方平台首次上网日期，不代表论文的发表时间）