您好,欢迎访问中国农业科学院 机构知识库!

Atlas Based AAM and SVM Model for Fully Automatic MRI Prostate Segmentation

文献类型: 会议论文

第一作者: Ruida Cheng

作者: Ruida Cheng 1 ; Baris Turkbey 2 ; William Gandler 1 ; Harsh K. Agarwal 2 ; Vijay P. Shah 3 ; Alexandra Bokinsky 4 ; Evan McCreedy 1 ; Shijun Wang 5 ; Sandeep Sankineni 2 ; Marcelino Bernardo 2 ; Thomas Pohida 1 ; Peter Choyke 2 ; Matthew J. McAuliffe 1 ;

作者机构: 1.Image Science Laboratory, Center of Information Technology, National Institutes of Health

2.Molecular Imaging Program, National Cancer Institute

3.VirtualScopics, Inc

4.Geometric Tools, Inc

5.Imaging Biomarker and CAD Laboratory, NIH Clinical Center

会议名称: Annual International Conference of the IEEE Engineering in Medicine and Biology Society

主办单位:

页码: 2881-2885

摘要: Automatic prostate segmentation in MR images is a challenging task due to inter-patient prostate shape and texture variability, and the lack of a clear prostate boundary. We propose a supervised learning framework that combines the atlas based AAM and SVM model to achieve a relatively high segmentation result of the prostate boundary. The performance of the segmentation is evaluated with cross validation on 40 MR image datasets, yielding an average segmentation accuracy near 90%.

分类号: Q81-53

  • 相关文献
作者其他论文 更多>>