Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2015, Vol. 55 Issue (6): 695-699    
  生物与生物医学 本期目录 | 过刊浏览 | 高级检索 |
一种MR膀胱图像增强后基于图论的分割策略
段侪杰1,2, 张一嘉1,2, 郭卉1,2, 叶大田1,2, 梁正荣3
1. 清华大学 深圳研究生院, 深圳市无损监测与微创医学技术重点实验室, 深圳 518055, 中国;
2. 清华大学 生物医学工程系, 北京 100084, 中国;
3. 美国纽约州立大学石溪分校, 石溪镇NY 11794, 美国
Segmentation strategy for enhanced MR cystography based on graph theory
DUAN Chaijie1,2, ZHANG Yijia1,2, GUO Hui1,2, YE Datian1,2, LIANG Zhengrong3
1. Shenzhen Key Laboratory for Nondestructive and Minimal Invasive Medical Technology, Graduate School at Shenzhen, Tsinghua University, Shenzhen 518055, China;
2. Department of Biomedical Engineering, Tsinghua University, Beijing 100084, China;
3. Stony Brook University, Stony Brook NY 11794, USA
全文: PDF(1442 KB)  
输出: BibTeX | EndNote (RIS)       背景资料
文章导读  
摘要 为了从具有低信噪比和运动伪影的虚拟膀胱镜核磁成像图像MR(magnetic resonance)中获得精确的膀胱分割结果, 该文提出一种针对连续采集的多套短时膀胱MR影像的处理策略。该策略选取一套图像作为配准基准, 对其他短时图像先后进行仿射变换和分层B样条变换配准, 最后对配准结果平均, 获得增强图像。继而利用基于闭集模型的图割方法分别对基准图像和增强图像进行分割。该文利用计算机生成的模拟图像以及临床MR图像测试该策略。实验结果表明: 模拟增强图像和MR增强图像的信噪比分别增大到原来的3.26倍和2.17倍, 图像信噪比在配准后明显提高; 对增强图像使用该文提供的分割方法获得了更好的分割结果。实验证明该文提出的策略能通过配准方法获得高信噪比、高对比度、较少伪影的膀胱增强影像。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
段侪杰
张一嘉
郭卉
叶大田
梁正荣
关键词 膀胱造影核磁共振(MR)配准图割    
Abstract:Fast magnetic resonance (MR) bladder scans with artifacts and low signal to noise ratios (SNR) are used to precisely segment and achieve the bladder wall. The short scans are registered to a selected reference using an affine transformation followed by a hierarchical B-spline registration. The average of the registration results is the motion-corrected image. The graph cut method based on a closed-set model is then used segment the bladder MR image. The strategy is evaluated using both computer-generated images and clinical MR images. The results show that the average motion-corrected image with a high SNR (i.e., 3.26 for the simulated images and 2.17 for the clinical images) and less artifacts followed by a graph-cut segmentation tends to have a more accurate result. This strategy reduces the artifacts and improves the SNR to provide high resolution segmentation of the bladder wall.
Key wordscystography    magnetic resonance(MR)    registration    graph cut
收稿日期: 2014-04-16      出版日期: 2015-09-08
ZTFLH:  TP391  
基金资助: 
引用本文:   
段侪杰, 张一嘉, 郭卉, 叶大田, 梁正荣. 一种MR膀胱图像增强后基于图论的分割策略[J]. 清华大学学报(自然科学版), 2015, 55(6): 695-699.
DUAN Chaijie, ZHANG Yijia, GUO Hui, YE Datian, LIANG Zhengrong. Segmentation strategy for enhanced MR cystography based on graph theory. Journal of Tsinghua University(Science and Technology), 2015, 55(6): 695-699.
链接本文:  
http://jst.tsinghuajournals.com/CN/  或          http://jst.tsinghuajournals.com/CN/Y2015/V55/I6/695
  图1 配准框架图
  图2 用于实验的模拟图像
  表1 信噪比计算结果
  图3 模拟图像配准前后比较
  图4 模拟图像配准前后灰度值折线图比较
  图5 MR图像配准前后比较
  图6 MR图像配准前后灰度值折线图比较
  图7 模拟图像配准增强前后分割结果
  图8 临床MR数据分割情况
[1] 段侪杰, 田珍, 梁正荣, 等. 基于医学影像的虚拟膀胱镜技术 [J]. 中国医学物理学杂志, 2010, 27(2): 1712-1715.DUAN Chaijie, TIAN Zhen, LIANG Zhengrong, et al. A review on virtual cystoscopy techniques [J]. Chinese Journal of Medical Physics, 2010, 27(2):1712-1715. (in Chinese)
[2] Jaume S, Ferrant M, Macq B, et al. Tumor detection in the bladder wall with a measurement of abnormal thickness in CT scans [J]. IEEE Transactions on Bio-medical Engineering, 2003, 50(3): 383-390.
[3] LIN Qin, LIANG Zhengrong, DUAN Chaijie, et al. Motion correction for MR cystography by an image processing approach [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(9): 2401-2410.
[4] Boykov Y, Veksler O, Zabih R. Fast approximate energy minimization via graph cuts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222-1239.
[5] Osher S, Sethian J A. Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulation [J]. Journal of Computational Physics, 1988, 79(1): 12-49.
[6] LI Kang, WU Xiaodong, CHEN Ziyi, et al. Optimal surface segmentation in volumetric images—A graph-theoretic approach [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(1): 119-134.
[7] Hochbaum D. A new-old algorithm for minimum-cut and maximum-flow in closure graphs [J]. Networks, 2001, 37(4): 171-193.
[8] Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124-1137.
[9] ZHANG Yijia, DUAN Chanjie, YE Datian, et al. The segmentation of MR bladder wall in 3D based on minimum closed set model [C]//2013 IEEE International Conference on Medical Imaging Physics and Engineering. Shenyang, China: IEEE, 2013: 319-323.
[10] Henkelman R. Measurement of signal intensities in the presence of noise in MR images [J]. Medical Physics, 1985, 12(2): 232-233.
[11] Kaufman L, Kramer D, Crooks L, et al. Measuring signal-to-noise ratios in MR imaging [J]. Radiology, 1989, 173(1): 265-267
[1] 陈宝华, 邓磊, 段岳圻, 陈志祥, 周杰. 三维重建中的多模型融合:克服光照和尺度影响[J]. 清华大学学报(自然科学版), 2016, 56(9): 969-973.
[2] 邓可欣. 基于超边图匹配的视网膜眼底图像配准算法[J]. 清华大学学报(自然科学版), 2014, 54(5): 568-574.
[3] 林源, 梁舒, 王生进. 基于非刚性ICP的三维人脸数据配准算法[J]. 清华大学学报(自然科学版), 2014, 54(3): 334-340.
[4] 马文婷, 杨健, 高伟, 周广益. 面向极化SAR图像配准的极化特征[J]. 清华大学学报(自然科学版), 2014, 54(2): 270-274.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn