期刊
JOURNAL OF DIGITAL IMAGING
卷 21, 期 -, 页码 S121-S133出版社
SPRINGER
DOI: 10.1007/s10278-008-9106-3
关键词
Cancer detection; classification; computer-aided diagnosis (CAD); decision support techniques; image interpretation
资金
- Interdepartment Research Center of SNU
In this paper, we propose a new prostate detection method using multiresolution autocorrelation texture features and clinical features such as location and shape of tumor. With the proposed method, we can detect cancerous tissues efficiently with high specificity (about 90-95%) and high sensitivity (about 92-96%) by the measurement of the number of correctly classified pixels. Multiresolution autocorrelation can detect cancerous tissues efficiently, and clinical knowledge helps to discriminate the cancer region by location and shape of the region and increases specificity. The support vector machine is used to classify tissues based on those features. The proposed method will be helpful in formulating a more reliable diagnosis, increasing diagnosis efficiency.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据