基于RandomWalk算法的CT图像肺实质自动分割

doi:10.11772/j.issn.1001-9081.2015.09.2666

计算机应用 ›› 2015, Vol. 35 ›› Issue (9): 2666-2672.DOI: 10.11772/j.issn.1001-9081.2015.09.2666

基于RandomWalk算法的CT图像肺实质自动分割

王兵¹, 顾潇蒙², 杨颖³, 董华⁴, 田学东⁴, 顾力栩^2,5

1. 河北大学数学与信息科学学院, 河北保定 071002;
2. 河北大学医工交叉研究中心, 河北保定 071000;
3. 河北大学附属医院 CT室, 河北保定 071000;
4. 河北大学计算机科学学院, 河北保定 071002;
5. 上海交通大学生物医学工程学院, 上海 200240

收稿日期:2015-04-30 修回日期:2015-06-24 出版日期:2015-09-10 发布日期:2015-09-17
通讯作者: 顾力栩(1966-),男,加拿大人,教授,博士,主要研究方向:医学图像处理、模式识别,gulixu@sjtu.edu.cn
作者简介:王兵(1966-),女,河北承德人,教授,硕士,主要研究方向:模式识别与图像处理;顾潇蒙(1990-),女,江苏连云港人,硕士研究生,主要研究方向:模式识别与图像处理;杨颖(1970-),女,河北保定人,主任医师,硕士,主要研究方向:医学影像;董华(1992-),女,河北沧州人,主要研究方向:软件工程;田学东(1963-),男,河北保定人,教授,博士,主要研究方向:模式识别与图像处理、中文信息处理。
基金资助:
国家自然科学基金资助项目(61375075,61190120-61190124,61271318);河北省自然科学基金资助项目(f2012201020);河北省教育厅重点项目(ZD2015067)。

Automated lung segmentation for chest CT images based on Random Walk algorithm

WANG Bing¹, GU Xiaomeng², YANG Ying³, DONG Hua⁴, TIAN Xuedong⁴, GU Lixu^2,5

1. College of Mathematics and Information Science, Hebei University, Baoding Hebei 071002, China;
2. Biomedical Multidisciplinary Research Center, Hebei University, Baoding Hebei 071000, China;
3. CT Department, Affiliated Hospital of Hebei University, Baoding Hebei 071000, China;
4. College of Computer Science, Hebei University, Baoding Hebei 071002, China;
5. College of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China

Received:2015-04-30 Revised:2015-06-24 Online:2015-09-10 Published:2015-09-17

摘要/Abstract

摘要： 针对复杂情况下肺实质的分割问题,提出了一种基于Random Walk算法对肺实质自动分割的方法。首先,根据胸部组织解剖学及其计算机断层扫描(CT)图像的影像学特征,在肺实质及其周围组织分别确定目标区域种子点和背景种子点位置;然后,使用Random Walk算法对CT图像进行分割,提取近似肺区域的掩模;接下来,对掩模实施数学形态学运算,来进一步调整目标区域种子点和背景种子点的标定位置,使其适合具体的复杂情况;最后,再次使用Random Walk算法分割图像,得到最终的肺实质分割结果。实验结果显示,该方法与金标准的平均绝对距离为0.44±0.13 mm,重合率(DC)为99.21%±0.38%。与其他分割方法相比,该方法在分割精度上得到了显著提高。结果表明,提出的方法能够解决复杂情况下肺实质分割的问题,确保了分割的完整性、准确性、实时性和鲁棒性,分割结果和时间均可满足临床需求。

关键词: 胸部图像, 计算机断层扫描, Random Walk算法, 肺实质分割, 种子点选择, 数学形态学运算

Abstract: To deal with the lung segmentation problem under complex conditions, Random Walk algorithm was applied to automatic lung segmentation. Firstly, according to the anatomical and imaging characteristics of the chest Computed Tomography (CT) images, foreground and background seeds were selected respectively. Then, CT image was segmented roughly by using the Random Walk algorithm and the approximate mask of lung area was extracted. Next, through implementing mathematical morphology operations to the mask, foreground and background seeds were further adjusted to adapt to the actually complicated situations. Finally, the fine segmentation of lung parenchyma for chest CT image was implemented by using the Random Walk algorithm again. The experimental results demonstrate that, compared with the gold standard, the Mean Absolute Distance (MAD) is 0.44±0.13 mm, the Dice Coefficient (DC) is 99.21%±0.38%. Compared with the other lung segmentation methods, the proposed method are significantly improved in accuracy of segmentation. The experimental results show that the proposed method can solve the difficult cases of the lung segmentation, and ensure the integrity, accuracy, real-time and robustness of the segmentation. Meanwhile, the results and time of the proposed method can meet the clinical needs.

Key words: chest image, Computed Tomography (CT), Random Walk algorithm, lung segmentation, seed selection, mathematical morphology operation

中图分类号:

TP391.4

王兵, 顾潇蒙, 杨颖, 董华, 田学东, 顾力栩. 基于RandomWalk算法的CT图像肺实质自动分割[J]. 计算机应用, 2015, 35(9): 2666-2672.

WANG Bing, GU Xiaomeng, YANG Ying, DONG Hua, TIAN Xuedong, GU Lixu. Automated lung segmentation for chest CT images based on Random Walk algorithm[J]. Journal of Computer Applications, 2015, 35(9): 2666-2672.

参考文献

[1] World Health Organization. The top 10 causes of death [EB/OL]. [2014-11-24]. http://www.who.int/mediacentre/factsheets/fs310/en/.
[2] BROWN M S, GOLDIN J G, SUH R D, et al. Lung micronodules: automated method for detection at thin-section CT-initial experience [J]. Radiology, 2003,226(1):256-262.
[3] MULLALLY W, BETKE M, WANG J, et al. Segmentation of nodules on chest computed tomography for growth assessment [J]. Medical Physics, 2004,31(4):839-848.
[4] ZHOU X, HAYASHI T, HARA T, et al. Automatic segmentation and recognition of anatomical lung structures from high-resolution chest CT images [J]. Computerized Medical Imaging and Graphics, 2006,30(5):299-313.
[5] ARMATO S G, SENSAKOVIC W F. Automated lung segmentation for thoracic CT impact on computer-aided diagnosis [J]. Academic Radiology, 2004, 11(9): 1011-1021.
[6] LI Q, LI F, DOI K. Computerized detection of lung nodules in thin-section CT images by use of selective enhancement filters and an automated rule-based classifier [J]. Academic Radiology, 2008,15(2):165-175.
[7] WIEMKER R, ROGALLA P, ZWARTKRUIS A, et al. Computer aided lung nodule detection on high resolution CT data [EB/OL]. [2015-01-07]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.19.8652&rep=rep1&type=pdf.
[8] GUO S, ZENG Q, CHEN J. Extraction of pulmonary parenchyma in thoracic CT and computer aided diagnosis [J]. Chinese Journal of Biomedical Engineering, 2008,27(5):788-791.(郭胜文,曾庆思,陈坚.胸部CT中肺实质的提取与辅助诊断[J].中国生物医学工程学报,2008,27(5):788-791.)
[9] HEDLUND L W, ANDERSON R F, GOULDING P L, et al. Two methods for isolating the lung area of a CT scan for density information [J]. Radiology, 1982,144(2):353-357.
[10] BROWN M S, MCNITT-GRAY M F, MANKOVICH N J, et al. Method for segmenting chest CT image data using an anatomical model: preliminary results [J]. IEEE Transactions on Medical Imaging, 1997,16(6):828-839.
[11] TAI X C, CHAN T F. A survey of multiple level set methods with applications for identifying piecewise constant [J]. International Journal of Numerical Analysis and Modeling, 2004,1(1):25-47.
[12] ZHOU C, LIU S, WANG F, et al. Image segmentation based on snake model incorporated with regional information [J]. Computer Applications and Software, 2010,27(9):23-25.(周昌雄,刘淑芬,王峰,等.融合区域信息snake模型图像分割[J].计算机应用与软件,2010,27(9):23-25.)
[13] HU S, HOFFMAN E A, REINHARDT J M. Automatic lung segmentation for accurate quantification of volumetric X-ray CT images [J]. IEEE Transactions on Medical Imaging, 2001,20 (6):490-498.
[14] YIM Y, HONG H. Correction of segmented lung boundary for inclusion of pleural nodules and pulmonary vessels in chest CT images [J]. Computers in Biology and Medicine, 2008,38(8):845-857.
[15] MURPHY A L, PICCO G P, ROMAN G C. LIME: a coordination model and middleware supporting mobility of hosts and Agents [J]. ACM Transactions on Software Engineering and Methodology, 2006,15(3):279-328.
[16] BIAN X, WU Y. A method of careful lung segmentation based on CT images [J]. Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, 2010,22(5):665-668.(卞晓月.武妍.基于CT图像的肺实质细分割综合方法[J].重庆邮电大学学报:自然科学版,2010,22(5):665-668.
[17] MAMEI M, ZAMBONELLI F. Spatial computing: the TOTA approach [M]//BABAOGLU O, JELASITY M, MONTRESOR A, et al. Self-star Properties in Complex Information Systems, LNCS 3460. Berlin: Springer, 2005:307-324.
[18] ZHANG X, WANG B, YANG Y, et al. Automatic repair of lung boundary concave in chest CT images [J]. Computer Engineering and Applications, 2013,49(24):191-194.(张欣,王兵,杨颖,等.胸部CT图像肺区域边界凹陷自动修补[J].计算机工程与应用,2013,49(24):191-194.)
[19] KANAZAWA K, KAWATA Y, NIKI N, et al. Computer-aided diagnosis for pulmonary nodules based on helical CT images [J]. Computerized Medical Imaging and Graphics, 1998,22(2):157-167.
[20] PEARSON K. The problem of the random walk [J]. Nature, 1905,72(1866):294.
[21] GRADY L, FUNKS-LEA G. Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials [EB/OL]. [2014-12-24]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.91.4365&rep=rep1&type=pdf.
[22] GRADY L. Random walks for image segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006,28(11):1768-1783.
[23] LI J, CHEN H, ZHANG X. Segmentation of retinal blood vessels based on prior knowledge random walks model [J]. Chinese Journal of Biomedical Engineering, 2009,28(4):501-507.(李居朋,陈后金,张新媛.基于先验知识随机游走模型的视网膜血管分割方法[J].中国生物医学工程学报,2009,28(4):501-507.)
[24] PERONA P, MALIK J. Scale-space and edge detection using anisotropic diffusion [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990,12(7):629-639.
[25] QIN C. Research on random walks image segmentation method [D]. Shanghai:Central China Normal University, 2014.(秦婵婵.基于随机游走算法的图像分割算法研究[D].上海:华东师范大学,2014.)
[26] HEIMANN T, van GINNEKEN B, STYNER M A, et al. Comparison and evaluation of methods for liver segmentation from CT datasets [J]. IEEE Transactions on Medical Imaging, 2009,28(8):1251-1265.

基于RandomWalk算法的CT图像肺实质自动分割

Automated lung segmentation for chest CT images based on Random Walk algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

[1]	高智勇, 黄金镇, 杜程刚. 基于特征金字塔网络的肺结节检测[J]. 计算机应用, 2020, 40(9): 2571-2576.
[2]	宋芸, 张元科, 卢虹冰, 邢宇翔, 马建华. 基于区域内容感知核范数的低剂量CT影像去噪[J]. 计算机应用, 2020, 40(4): 1177-1183.
[3]	邱甲军, 吴跃, 惠孛, 刘彦伯. 基于小波变换的分数阶微分算法在肝脏肿瘤CT图像纹理增强中的应用[J]. 计算机应用, 2019, 39(4): 1196-1200.
[4]	高净植, 刘祎, 白旭, 张权, 桂志国. 平稳小波域深度残差CNN用于低剂量CT图像估计[J]. 计算机应用, 2018, 38(12): 3584-3590.
[5]	高媛, 贾紫婷, 秦品乐, 王丽芳. 基于连接突触计算网络的医学图像融合算法[J]. 计算机应用, 2017, 37(12): 3554-3557.
[6]	张鹏程, 张权, 张芳, 陈燕, 韩建宁, 郝慧艳, 桂志国. 结合改进扩散和双边滤波的低剂量CT重建[J]. 计算机应用, 2016, 36(4): 1100-1105.
[7]	汪葛, 王远军. 基于水平集的牙齿CT图像分割技术[J]. 计算机应用, 2016, 36(3): 827-832.
[8]	钱鹰, 廖婷婷. 使用面积积分模型探究锥束CT功能成像的方法[J]. 计算机应用, 2016, 36(12): 3429-3435.
[9]	何琳, 张权, 上官宏, 张文, 张鹏程, 刘祎, 桂志国. 自适应加权全变分的低剂量CT统计迭代算法[J]. 计算机应用, 2016, 36(10): 2916-2921.
[10]	何琳, 张权, 上官宏, 张芳, 张鹏程, 刘祎, 孙未雅, 桂志国. 低剂量CT图像的自适应广义总变分降噪算法[J]. 计算机应用, 2016, 36(1): 243-247.
[11]	陈璐, 王小鹏, 张华卫, 吴双. 消除局部极值的多尺度形态学肝脏肿瘤CT图像分割方法[J]. 计算机应用, 2015, 35(8): 2332-2335.
[12]	高富强, 陈春江, 兰扬, 安康. γ射线工业CT数据采集传输系统[J]. 计算机应用, 2015, 35(1): 276-278.
[13]	史怀林孙丰荣姜威刘炜秦通李新彩. CT图像SART重建技术的CUDA并行实现[J]. 计算机应用, 2011, 31(05): 1245-1248.