Features Fxtraction of Prostate with Graph Spectral Method for Prostate Cancer Detection

被引：0

作者：

Du, Weiwei ^{[1
]}

Liu, Yi-peng ^{[2
]}

Wang, Shiyang ^{[3
]}

Peng, Yahui ^{[4
]}

Oto, Aytekin ^{[3
]}

机构：

[1] Kyoto Inst Technol, Dept Informat Sci, Kyoto, Japan

[2] Zhejiang Univ Technol, Coll Informat Engn, Hangzhou, Peoples R China

[3] Univ Chicago, Dept Radiol, Chicago, IL 60637 USA

[4] Beijing Jiaotong Univ, Sch Elect & Informat Engn, Beijing, Peoples R China

来源：

2016 17TH IEEE/ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING AND PARALLEL/DISTRIBUTED COMPUTING (SNPD) | 2016年

关键词：

Features Extraction of Prostate; m dimensional Euclidean space; Graph Spectral Method; LOCALIZATION; MRI;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Prostate cancers were segmented directly in T2-weighted images in some studies of computer-aided detection (CAD). These methods don't consider the differences between lesion and non-lesion region in T2-weighted images, so some lesions are not easy to he detected. In this paper, to consider the differences between lesion and non-lesion region, some features extraction is proposed by using graph spectral method. First, whole prostate is extracted. And then, some statistics are computed in the region of prostate to find differences between cancer and noncancer in prostate. The statistics are mapped into in dimensional Euclidean space by using graph spectral method to detect prostate cancers. Experiments show features with To dimensional Euclidean space by using graph spectral method can find some differences between lesion and non-lesion region.

引用

页码：663 / 668

页数：6

共 9 条

[1] Prostate Cancer Localization With Multispectral MRI Using Cost-Sensitive Support Vector Machines and Conditional Random Fields [J].