北京生物医学工程

基于自适应标记分水岭算法的肝脏CT图像自动分割

Automatic segmentation of liver CT images based on adaptivemarked-watershed algorithm

作者：黄展鹏张琦赵洁

单位：广东药科大学医药信息工程学院(广州510006)

分类号：R318.04;TP391.41

出版年·卷·期（页码）：2017·36·4（378-382）

摘要：

目的为减少人工交互提出了基于自适应标记分水岭的CT系列图像肝脏区域自动分割算法。方法首先对图像进行形态学重构运算以平滑图像，然后计算多尺度形态学梯度，同时提出利用梯度图像非零的局部极小值点的均值进行自适应标记提取，以避免分水岭的过分割和欠分割，再结合肝脏为最大的实质性脏器和相邻图像的相似性实现CT系列图像的肝区自动分割。结果该算法能自动、快速地提取CT系列图像中的肝脏区域。结论分水岭算法能准确定位区域的边缘，通过选择合适的阈值对梯度图像进行标记以抑制分水岭的过分割，实现医学图像中感兴趣区域的自动分割。

Objective An automatic segmentation method of liver area from computed tomography images based on adaptive marked-watershed algorithm is proposed to reduce human interaction.Methods The image is smoothed by morphological reconstruction,and the morphological gradient is calculated by the multi-scale structuring elements.Then the mean of non-zero local minimum of the gradient images is computed for adaptive Marked,which can overcome the over-segmentation and insufficient-segmentation of the watershed algorithm.Finally,by using the information that the liver is the largest organ and the similarity of the adjacent images,the regions of the liver are automatically extracted from the CT images.Results The region of the liver can be automatically and quickly extracted from the series of CT images by the proposed algorithm.Conclusions The watershed algorithm can accurately locate the edge of the area.By choosing the appropriate threshold as the adaptive Marked for the gradient image to suppress the watershed over-segmentation,the adaptive marked-watershed algorithm can automatically extract the regions of interest from medical images.

参考文献：

［1］Reitinger B,Bornik A,Beichel R,et al.Liver surgery planning using virtual reality［J］.IEEE Computer Graphics & Applications,2006,26(6):36-47.

［2］Chen Yanda,Bao Susu,Peng Fengping.A fuzzy connectedness segmentation of image sequences based on 3D seed points selection［C］//Proceedings of International Symposium on Computer Science and Computational Technology,2008.Los Alamitos:IEEE Computer Society,2008:372-375.

［3］王小东，冯筠，鲁定国,等.基于先验知识的肝脏轮廓线提取算法研究［J］.计算机应用研究,2014,31 (1) :281-284.

Wang Xiaodong,Feng Jun,Lu Dingguo,et al.Liver contour extraction based on priori knowledge model［J］.Application Research of Computers,2014,31 (1) :281-284.

［4］赵洁,黄展鹏,蒋世忠,等.结合改进分水岭和GVF的三维肝脏分割方法［J］.计算机工程与应用,2014,50 (22) :180-182.

Zhao Jie,Huang Zhanpeng,Jiang Shizhong,et al.3D liver segmentation method combined with improved watershed method and GVF［J］.Computer Engineering and Applications,2014,50(22)：180-182.

［5］Massoptier L,Casciaro S.A new fully automatic and robust algorithm for fast segmentation of liver tissue and tumors from CT scans ［J］.European Radiology,2008,18(8):1658-1665.

［6］宋晓,黄晓阳.基于CT三视图的肝脏自动分割方法［J］.系统仿真学报，2014,26(9):1980-1983.

Song Xiao,Huang Xiaoyang.Automatic liver segmentation method based on three views of CT image［J］.Journal of System Simulation,2014,26(9):1980-1983.

［7］Soille P.Morphological image analysis applied to crop field mapping ［J］.Image and Vision Computing,2000,18(13) :1025-1032.

［8］邰滢滢,吴彦海,张利.基于快速mean-shift聚类与标记分水岭的图像分割方法［J］.计算机应用与软件,2015,32(8):184-186.

Tai Yingying,Wu Yanhai,Zhang Li.Image segmentation method based on fast mean-shift clustering and marking watershed［J］.Computer Applications and Software,2015,32(8):184-186.

［9］邓超,关格利,王志衡.改进梯度和自适应标记提取的分水岭新算法［J］.计算机工程与应用,2013,49(20):136-140.

Deng Chao,Guan Geli,Wang Zhiheng.New watershed algorithm based on improved gradient and self-adaptive marker-extraction［J］.Computer Engineering and Applications,2013,49(20)：136-140.

［10］张桂梅，周明明，马珂.基于彩色模型的重构标记分水岭分割算法［J］．中国图象图形学报，2012，17(5) :641-647.

Zhang Guimei,Zhou Mingming,Ma Ke.Image segmentation algorithm for reconstruction labeling watershed in color space ［J］.Journal of Image and Graphics,2012，17(5) :641-647.

［11］余旺盛,侯志强,宋建军.基于标记分水岭和区域合并的彩色图像分割［J］.电子学报,2011,41(5):1007-1011.

Yu Wangsheng,Hou Zhiqiang,Song Jianjun.Color image segmentation based on marked-watershed and region-merger［J］.Acta Electronica Sinica,2011,41(5):1007-1011.

［12］刘耀辉,黄展鹏,鲍苏苏.基于数学形态学的ＣＴ图像肝脏肿瘤提取研究［J］.北京生物医学工程,2012,31(3):237-240.

Liu Yaohui,Huang Zhanpeng,Bao Susu.Segmentation of liver tumors for CT scans images based on the mathematical morphology［J］.Beijing Biomedical Engineering,2012,31(3):237-240.

［13］陈家新,王纪刚.一种改进的医学图像分水岭分割算法［J］.计算机应用研究,2013,30(8):2557-2560.

Chen Jiaxin,Wang Jigang.Improved watershed segmentation algorithm for medical image［J］.Application Research of Computers,2013,30(8):2557-2560.

［14］Gonzalez RC,Woods RE,Eddins SL.Digital Image Processing Using MATLAB ［M］.2nd ed.Knoxville:Gatesmark Publishing,2009:315-318.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录