Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2018, Vol. 52 Issue (12): 2382-2396    DOI: 10.3785/j.issn.1008-973X.2018.12.017
计算机技术     
基于区域增长与统一化水平集的CT肝脏图像分割
郑洲1,2, 张学昌2, 郑四鸣3, 施岳定1,2
1. 浙江大学 机械工程学院, 浙江 杭州 310027;
2. 浙江大学宁波理工学院 机能学院分院, 浙江 宁波 315100;
3. 宁波李惠利医院 肝胆疝微创外科, 浙江 宁波 315100
Liver segmentation in CT images based on region-growing and unified level set method
ZHENG Zhou1,2, ZHANG Xue-chang2, ZHENG Si-ming3, SHI Yue-ding1,2
1. Institute of Mechanical Engineering, Zhejiang University, Hangzhou 310027, China;
2. School of Mechanical and Energy Engineering, Ningbo Institute of Technology, Zhejiang University, Ningbo 315100, China;
3. Department of Minimally Invasive Surgery for Hepatobiliary Hernia, Ningbo Li Hui-li Hospital, Ningbo 315100, China
 全文: PDF(1817 KB)   HTML
摘要：

经过混合图像预处理（图像降噪、特定比例梯度滤波、非线性灰度转换和自定义二值转换）将CT图像转化为二值图像，提供良好的种子增长环境，克服传统区域增长中增长阈值设定与种子点位置选择的困难，避免过分割.区域增长只需设置少量种子点即能大致提取完整肝脏区域.通过统一化水平集优化分割结果.该水平集由图像边缘信息与区域信息共同驱动，与单图像信息驱动的水平集相比，能适应更大的气球力与更多的迭代次数，抗边缘泄漏能力强.将该方法在SLIVER07和3Dircadb提供的共40个肝脏数据集上进行验证，结果表明：相比其他多种方法，该方法所需交互时间更少，分割准确度更高.
Abstract:

First, hybrid image preprocessing, consisting of anisotropic filter, scale-specific gradient magnitude filter, nonlinear grayscale conversion and customized binary conversion, was employed to transform the CT image into a binary image, providing a good seed growth condition. Thus, the difficulties of threshold setting and seed initial location setting encountered in conventional region-growing were overcome, and over-segmentation was avoided. A few seeds were required when region-growing was performed to roughly extract the whole liver region. The segmentation results were refined by the unified level set method, which was driven by both the edge information and the region information of the image. The unified level set is adapted to larger balloon force and more iterations compared with the level sets driven by single information, and has strong resistance to edge leakage. A total of 40 datasets from SLIVER07 and 3Dircadb were used for method validation. Results show that, compared with other methods, the proposed method needs less interaction time and can get higher segmentation accuracy.
收稿日期: 2017-10-03 出版日期: 2018-12-13
CLC:  TP391.41  
基金资助:

国家自然科学基金资助项目（51075362）；浙江省自然科学基金资助项目（LY17E050011）；宁波市科技惠民资助项目（2015C50025）
通讯作者: 张学昌,男,教授.orcid.org/0000-0001-6768-0846.     E-mail: zz_zxc@163.com
作者简介: 郑洲(1993-),男,硕士生,从事逆向建模、图像分割研究.orcid.org/0000-0003-0084-0766.E-mail:zhengzhou@zju.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

郑洲, 张学昌, 郑四鸣, 施岳定. 基于区域增长与统一化水平集的CT肝脏图像分割[J]. 浙江大学学报(工学版), 2018, 52(12): 2382-2396.

ZHENG Zhou, ZHANG Xue-chang, ZHENG Si-ming, SHI Yue-ding. Liver segmentation in CT images based on region-growing and unified level set method. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 2018, 52(12): 2382-2396.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2018.12.017    或    http://www.zjujournals.com/eng/CN/Y2018/V52/I12/2382

[1] JOSKOWICZ L. Computer-aided surgery meets predictive, preventive, and personalized medicine[J]. EPMA Journal, 2017, 8(1):1-4.
[2] MISE Y, HASEGAWA K, SATOU S, et al. How has virtual hepatectomy changed the practice of liver surgery? Experience of 1194 virtual hepatectomy before l[J]. Annals of Surgery, 2018, 268(1):127-133.
[3] WEI L, ZHU Z J, LV Y, et al. Application of computer-assisted three-dimensional quantitative assessment and a surgical planning tool for living donor liver transplantation[J]. Chinese Medical Journal, 2013, 126(7):1288-1291.
[4] MARESCAUX J, DIANA M. Next step in minimally invasive surgery:hybrid image-guided surgery[J]. Journal of Pediatric Surgery, 2015, 50(1):30-36.
[5] ZHU M, ANG C L, YEO S J, et al. Minimally invasive computer-assisted total knee arthroplasty compared with conventional total knee arthroplasty:a prospective 9-year follow-up[J]. The Journal of Arthroplasty, 2016, 31(5):1000-1004.
[6] NAKAYAMA Y, LI Q, KATSURAGAWA S, et al. Automated hepatic volumetry for living related liver transplantation at multisection CT[J]. Radiology, 2006, 240(3):743-748.
[7] COOTES T F, HILL A, TAYLOR C J, et al. The use of active shape models for locating structures in medical images[C]//Biennial International Conference on Information Processing in Medical Imaging. Flagstaff:Springer, 1993:33-47.
[8] HEIMANN T, GINNEKEN B V, 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.
[9] KAINMÜLLER D, LANGE T, LAMECKER H. Shape constrained automatic segmentation of the liver based on a heuristic intensity model[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:109-116.
[10] HEIMANN T, MEINZER H, WOLF I. A statistical deformable model for the segmentation of liver CT volumes[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:161-166.
[11] SADDI K A, ROUSSON M, CHEFD'HOTEL C, et al. Global-to-local shape matching for liver segmentation in CT imaging[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:207-214.
[12] SHI C, CHENG Y, LIU F, et al. A hierarchical local region-based sparse shape composition for liver segmentation in CT scans[J]. Pattern Recognition, 2016, 50:88-106.
[13] ZHANG S, ZHAN Y, DEWAN M, et al. Towards robust and effective shape modeling:Sparse shape composition[J]. Medical Image Analysis, 2012, 16(1):265-277.
[14] WANG X, ZHENG Y, GAN L, et al. Liver segmentation from CT images using a sparse priori statistical shape model (SP-SSM)[J]. PLOS ONE, 2017, 12(10):1-23.
[15] SHI C, CHENG Y, WANG J, et al. Low-rank and sparse decomposition based shape model and probabilistic atlas for automatic pathological organ segmentation[J]. Medical Image Analysis, 2017, 38:30-49.
[16] WANG J, CHENG Y, GUO C, et al. Shape-intensity prior level set combining probabilistic atlas and probability map constrains for automatic liver segmentation from abdominal CT images[J]. International Journal of Computer Assisted Radiology and Surgery, 2016, 11(5):817-826.
[17] DING X, GENG X, JIANG C, et al. Fast automated liver delineation from computational tomography angiography[J]. Procedia Computer Science, 2016, 90:87-92.
[18] LIAO M, ZHAO Y Q, LIU X Y, et al. Automatic liver segmentation from abdominal CT volumes using graph cuts and border marching[J]. Computer methods and programs in biomedicine, 2017, 143:1-12.
[19] LI G, CHEN X, SHI F, et al. Automatic liver segmentation based on shape constraints and deformable graph cut in CT images[J]. IEEE Transactions on Image Processing, 2015, 24(12):5315-5329.
[20] BOYKOV Y, FUNKA-LEA G. Graph cuts and efficient ND image segmentation[J]. International Journal of Computer Vision, 2006, 70(2):109-131.
[21] PENG J, HU P, LU F, et al. 3D liver segmentation using multiple region appearances and graph cuts[J]. Medical Physics, 2015, 42(12):6840-6852.
[22] BEN-COHEN A, DIAMANT I, KLANG E, et al. Fully convolutional network for liver segmentation and lesions detection[C]//International Workshop on Large-Scale Annotation of Biomedical Data and Expert Label Synthesis. Athens:Springer, 2016:77-85.
[23] CHRIST P F, ELSHAER M E A, ETTLINGER F, et al. Automatic liver and lesion segmentation in CT using cascaded fully convolutional neural networks and 3D conditional random fields[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Athens:Springer, 2016:415-423.
[24] DOU Q, CHEN H, JIN Y, et al. 3D deeply supervised network for automatic liver segmentation from CT volumes[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Athens:Springer, 2016:149-157.
[25] BEICHEL R, BAUER C, BORNIK A, et al. Liver segmentation in CT data:a segmentation refinement approach[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:235-245.
[26] DAWANT B M, LI R, LENNON B, et al. Semi-automatic segmentation of the liver and its evaluation on the MICCAI 2007 grand challenge data set[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:215-221.
[27] BECK A, AURICH V. HepaTux-a semiautomatic liver segmentation system[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:225-233.
[28] YANG X, YU H C, CHOI Y, et al. A hybrid semi-automatic method for liver segmentation based on level-set methods using multiple seed points[J]. Computer Methods and Programs in Biomedicine, 2014, 113(1):69-79.
[29] SETHIAN J A. A fast marching level set method for monotonically advancing fronts[J]. Proceedings of the National Academy of Sciences, 1996, 93(4):1591-1595.
[30] HSU C, YANG C, WANG H. Multi-threshold level set model for image segmentation[J]. EURASIP Journal on Advances in Signal Processing, 2010, 2010:1-8.
[31] YAMAGUCHI S, SATAKE K, YAMAJI Y, et al. Three-dimensional semiautomatic liver segmentation method for non-contrast computed tomography based on a correlation map of locoregional histogram and probabilistic atlas[J]. Computers in Biology and Medicine, 2014, 55:79-85.
[32] CHARTRAND G, CRESSON T, CHAV R, et al. Liver segmentation on CT and MR using laplacian mesh optimization[J]. IEEE Transaction on Biomedical Engineering, 2016, 64(9):2110-2121.
[33] EAPEN M, KORAH R, GEETHA G. Computerized liver segmentation from CT images using probabilistic level set approach[J]. Arabian Journal for Science and Engineering, 2016, 41(3):921-934.
[34] ZAREEI A, KARIMI A. Liver segmentation with new supervised method to create initial curve for active contour[J]. Computers in Biology and Medicine, 2016, 75:139-150.
[35] 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.
[36] SUZUKI K, HUYNH H T, LIU Y, et al. Computerized segmentation of liver in hepatic CT and MRI by means of level-set geodesic active contouring[C]//201335th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Osaka:IEEE, 2013:2984-2987.
[37] SUZUKI K, KOHLBRENNER R, EPSTEIN M L, et al. Computer-aided measurement of liver volumes in CT by means of geodesic active contour segmentation coupled with level set algorithms[J]. Medical Physics, 2010, 37(5):2159-2166.
[38] OSHER S, SETHIAN J A. Fronts propagating with curvature-dependent speed:algorithms based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988, 79(1):12-49.
[39] LEE J, KIM N, LEE H, et al. Efficient liver segmentation exploiting level-set speed images with 2.5 D shape propagation[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:189-196.
[40] ZHANG K, ZHANG L, SONG H, et al. Active contours with selective local or global segmentation:a new formulation and level set method[J]. Image and Vision Computing, 2010, 28(4):668-676.
[41] LI C, XU C, GUI C, et al. Distance regularized level set evolution and its application to image segmentation[J]. IEEE Transactions on Image Processing, 2010, 19(12):3243-3254.
[42] CHAN T F, VESE L A. Active contours without edges[J]. IEEE Transactions on Image Processing, 2001, 10(2):266-277.
[43] GINNEKEN B V, HEIMANN T, STYNER M. 3D Segmentation in the clinic:a grand challenge[C]//Proceedings of 3D Segmentation in the Clinic:a Grand Challenge. Brisbane:Springer, 2007:7-15.
[44] ERDT M, KIRSCHNER M. Fast automatic liver segmentation combining learned shape priors with observed shape deviation[C]//2010 IEEE 23rd International Symposium on Computer-Based Medical Systems (CBMS). Perth:IEEE, 2010:249-254.
[45] 朱新勇, 方驰华, 鲍苏苏, 等. 基于64排螺旋CT扫描数据的肝脏图像分割和三维重建[J]. 南方医科大学学报, 2008, 28(3):345-347 ZHU Xin-yong, FANG Chi-hua, BAO Su-su, et al. Image segmentation and three-dimensional reconstruction of the liver based on 64-slice spiral CT scanning data[J]. Journal of Southern Medical University, 2008, 28(3):345-347
[46] HOOGI A, BEAULIEU C F, CUNHA G M, et al. Adaptive local window for level set segmentation of CT and MRI liver lesions[J]. Medical Image Analysis, 2017, 37:46-55.
[47] BALLA-ARABÉ S, GAO X, WANG B. GPU accelerated edge-region based level set evolution constrained by 2D gray-scale histogram[J]. IEEE Transactions on Image Processing, 2013, 22(7):2688-2698.
[48] WANG C L, FRIMMEL H, SMEDBY Ö. Fast level set based image segmentation using coherent propagation[J]. Medical Physics, 2014, 41(7):1-11.
[49] CHENG Y, HU X, WANG J, et al. Accurate vessel segmentation with constrained B-snake[J]. IEEE Transactions on Image Processing, 2015, 24(8):2440-2445.
[50] SKALSKI A, HERYAN K, JAKUBOWSKI J, et al. Kidney segmentation in CT data using hybrid Level-Set Method with ellipsoidal shape constraints[J]. Metrology and Measurement Systems, 2017, 24(1):101-112.
[1] 鲁晓卉, 王进, 陆国栋, 张东亮. 采用多重特征蒙板的人像皮肤美化技术[J]. 浙江大学学报(工学版), 2017, 51(12): 2299-2310.
[2] 蔡晋辉, 张光新, 才辉. 基于连通掩模的重构开算子及应用[J]. J4, 2010, 44(4): 675-680.
[3] 王宣银, 梁冬泰. 基于多元图像分析的表面缺陷检测算法[J]. J4, 2010, 44(3): 448-452.
[4] 孙志海, 孔万增, 朱善安. 视频目标定位的减法聚类改进算法[J]. J4, 2010, 44(3): 458-462.
[5] 毛锋, 张树有, 黄长林. 图像散布图和小波多分辨分析的模具异物检测[J]. J4, 2009, 43(10): 1749-1756.
[6] 范翔, 夏顺仁. 基于特征的显微图像全自动拼接[J]. J4, 2009, 43(7): 1182-1186.
[7] 陈成, 庄越挺, 肖俊. 相机运动条件下的视频前景提取[J]. J4, 2009, 43(6): 975-977.
[8] 张冬梅, 刘利刚. 基于角度滤波的平面图形光顺算法[J]. J4, 2009, 43(6): 1042-1046.