Joint optimization of segmentation and shape prior from level-set-based statistical shape model, and its application to the automated segmentation of abdominal organs
详细信息 查看全文
- 作者：Atsushi Saitoa ; 50013834203@st.tuat.ac.jp" class="auth_mail" title="E-mail the corresponding author ; Shigeru Nawanob ; snawano@iuhw.ac.jp" class="auth_mail" title="E-mail the corresponding author ; Akinobu Shimizua ; simiz@cc.tuat.ac.jp" class="auth_mail" title="E-mail the corresponding author
- 关键词：Segmentation ; Statistical shape model ; Graph cuts ; Branch-and-bound search ; Computed tomography
- 刊名：Medical Image Analysis
- 出版年：2016
- 出版时间：February 2016
- 年：2016
- 卷：28
- 期：Complete
- 页码：46-65
- 全文大小：3531 K
文摘
- •
Joint optimization of segmentation labeling and a shape prior defined by an SSM.
- •
An optimal shape prior is found from the eigenshape space by branch-and-bound search.
- •
Our method requires neither predefined shape templates nor a hierarchical clustering.
- •
Pancreas and spleen segmentation using the multi-phase CT volumes were performed.
- •
Our method showed higher segmentation accuracy and higher computational efficiency.