首页 > 论文 > 激光与光电子学进展 > 55卷 > 5期(pp:51011--1)

基于局部稀疏形状表示的医学图像分割模型

Medical Image Segmentation Model Based on Local Sparse Shape Representation

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

针对人体器官计算机断层扫描(CT)图像边缘模糊、难以自动分割的问题,提出了一种基于局部先验形状信息和主动轮廓模型的分割方法。针对一个形状与训练集中样本相似的器官目标,在基于图像灰度信息进行底层分割的同时,利用形状字典中的先验形状表示目标,将其作为高层监督,引导变分目标分割。在已有形状字典稀疏表示的基础上,利用掩模矩阵对字典形状进行局部分解,以生成补充字典,通过对局部先验的稀疏形状的约束实现对目标形状的局部描述。通过对字典中相似形状局部分解的重组,替代传统整体稀疏形状的表示方法,实现对与形状字典中仅存在部分相似目标的分割,扩大了字典形状的适用范围。分割实验表明,所提模型可准确地从边缘模糊的图像中提取并分割所需目标,从而可应用于医学图像分割。

Abstract

With respect to the problems of the fuzzy edge and difficulty in automatic segmentation of human organs during the computed tomography (CT) scanning, a local prior shape information and active contour based model is proposed. For an object whose shape is similar with the shapes in the dictionary, the prior shape in the shape dictionary is used to supervise and guide the high-level object segmentation while underlying segmentation is performed based on the image information. On the basis of the existed shape dictionary sparse representation, dictionary shapes are decomposed by mask matrix, and supplemental dictionary is generated, so the local shapes of the object can be described by the constraint of sparse shape of partial prior shapes. By the decomposition and recombination of the local shapes instead of the traditional prior shapes, shapes which are not included directly in the dictionary can be segmented, and the application range is extended. Experimental results of the segmentation experiments show that even if the edge of the object is fuzzy, the image can be recovered and segmented accurately with the proposed method, and the proposed method can be applied to medical image segmentation.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.4

DOI:10.3788/lop55.051011

所属栏目:图像处理

基金项目:国家自然科学基金(51775253,61505071)、江苏省自然科学基金(BK20150526)

收稿日期:2017-11-03

修改稿日期:2017-12-05

网络出版日期:--

作者单位    点击查看

姚红兵:江苏大学机械工程学院, 江苏 镇江 212013
卞锦文:江苏大学机械工程学院, 江苏 镇江 212013
丛嘉伟:江苏大学机械工程学院, 江苏 镇江 212013
黄印:江苏大学机械工程学院, 江苏 镇江 212013

联系人作者:卞锦文(ronnie_bian@foxmail.com)

备注:姚红兵(1976—),男,博士,教授,硕士生导师,主要从事光电检测和信息处理方面的研究。E-mail: yaoye@ujs.edu.cn

【1】Ding K, Weng G. Robust active contours for fast image segmentation[J]. Electronics Letters, 2016, 52(20): 1687-1688.

【2】Lan H, Zhang L. Liver image segmentation algorithm based on the Snake model and optimized by watershed transformation[J]. Journal of Image & Graphics, 2012, 17(7): 873-879.
兰红, 张璐. 分水岭优化的Snake模型肝脏图像分割[J]. 中国图象图形学报, 2012, 17(7): 873-879.

【3】Wang S K, Pan J X, Chen P. Adaptive segmentation algorithm for CT image sequence based on structure continuity as prior information[J]. Laser & Optoelectronics Progress, 2016, 53(11): 111006.
王苏恺, 潘晋孝, 陈平. 基于结构连续先验的CT图像序列自适应分割算法[J]. 激光与光电子学进展, 2016, 53(11): 111006.

【4】Chen F, Yu H, Hu R. Shape sparse representation for joint object classification and segmentation[J]. IEEE Transactions on Image Processing, 2013, 22(3): 992-1004.

【5】Chen Y, Thiruvenkadam S, Huang F, et al. On the incorporation of shape priors into geometric active contours[C]. IEEE Workshop on Variational and Level Set Methods in Computer Vision, 2017: 145-152.

【6】Chittajallu D R, Paragios N, Kakadiaris I A. An explicit shape-constrained MRF-based contour evolution method for 2-D medical image segmentation[J]. IEEE Journal of Biomedical & Health Informatics, 2014, 18(1): 120-129.

【7】Metaxas D N, Zhang S. Towards robust and effective shape prior modeling: sparse shape composition[J]. Medical Image Analysis, 2012, 16(1): 265-277.

【8】Wang G, Zhang S, Xie H, et al. A homotopy-based sparse representation for fast and accurate shape prior modeling in liver surgical planning[J]. Medical Image Analysis, 2015, 19(1): 176.

【9】Zhang S, Zhan Y, Metaxas D N. Deformable segmentation via sparse representation and dictionary learning[J]. Medical Image Analysis, 2012, 16(7): 1385-1396.

【10】Alshaikhli S D S, Yang M Y, Rosenhahn B. Automatic 3D liver segmentation using sparse representation of global and local image information via level set formulation[J]. Computer Science, 2015: arXiv:1508.01521.

【11】Starck J L, Elad M, Donoho D L. Image decomposition via the combination of sparse representations and a variational approach[J]. IEEE Transactions on Image Processing, 2005, 14(10): 1570-1582.

【12】Yao J, Yu H. Implicit sparse shape representation: a unified framework for object segmentation and recognition[J]. IEEE Signal Processing Letters, 2012: 1.

【13】Chan T F, Vese L A. Active contours without edges[M]. New Jersey: IEEE Press, 2001.

【14】Xie Z N, Zheng D, Chen J Y, et al. A Tumor segmentation method of improved Chan-Vese model for liver cancer ablation computed tomography image[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021702.
谢志南, 郑东, 陈嘉耀, 等. 改进Chan-Vese模型的肝癌消融CT图像肿块分割方法[J]. 激光与光电子学进展, 2017, 54(2): 021702.

【15】Zhao F Z, Liang H Y, Wu X L, et al. Active contour segmentation model based on local and global Gaussion fitting[J]. Laser & Optoelectronics Progress, 2017, 54(5): 051006.
赵方珍, 梁海英, 巫湘林, 等. 基于局部和全局高斯拟合的主动轮廓分割模型[J]. 激光与光电子学进展, 2017, 54(5): 051006.

【16】The MPEG-7 CE-Shape-1 Part B. http:∥mpeg.chiariglione.org/.

【17】MedPix Medical Image Database. https:∥medpix.nlm.nih.gov/home.

【18】Dice L R. Measures of the amount of ecologic association between species[J]. Ecology, 1945, 26(3): 297-302.

【19】Yao J C. Research on shape-prior-based variational sparse segmentation model[D]. Hangzhou: Zhejiang University, 2017.
姚劲草. 基于先验形状的变分稀疏分割模型研究[D]. 杭州: 浙江大学, 2017.

引用该论文

Yao Hongbing,Bian Jinwen,Cong Jiawei,Huang Yin. Medical Image Segmentation Model Based on Local Sparse Shape Representation[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051011

姚红兵,卞锦文,丛嘉伟,黄印. 基于局部稀疏形状表示的医学图像分割模型[J]. 激光与光电子学进展, 2018, 55(5): 051011

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF