Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
自动化技术、控制技术     
基于支持向量机和椭圆拟合的细胞图像自动分割
廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥
1. 中南大学 信息科学与工程学院,湖南 长沙 410083；
2. 湖南科技大学 计算机科学与工程学院,湖南 湘潭 411100；
3. 中南大学 生物医学工程研究所,湖南 长沙 410083；
4. 胜利石油管理局滨南医院,山东 滨州 256600
Automatic segmentation for cell images based on support vector machine and ellipse fitting
LIAO Miao, ZHAO Yu-qian, ZENG Ye-zhan, HUANG Zhong-chao, ZHANG Bing-kui, ZOU Bei-ji
1. School of Information Science and Engineering, Central South University, Changsha 410083, China; 
2. School of Computer Science and Engineering, Hunan University of Science and Technology, Xiangtan 411100, China;
3. Institute of Biomedical Engineering, Central South University, Changsha 410083, China;
4. Binnan Hospital of Shengli Petroleum Administration Bureau, Binzhou 256600, China
 全文: PDF(2705 KB)   HTML
摘要：

提出细胞显微图像的自动分割方法,重点解决重叠细胞之间的分割难题.对原始图像进行二值化,提取每个连通区域的多个形状特征并应用支持向量机(SVM)进行测试,区分单个与重叠细胞.运用瓶颈检测寻找分离点对分割重叠细胞.基于细胞的椭圆或圆形结构,对分割后的边缘,应用改进的椭圆拟合法进行修正,修正后的细胞区域能够有效地反映重叠在一起的细胞的真实形状.对新生成的封闭区域进行循环检测,直至所有重叠细胞分割完毕.实验结果表明,相较于多种现有的细胞分割方法,采用该算法能够更有效地抑制过分割和欠分割,分割准确率、敏感度和特异度高.
Abstract:

An automatic segmentation method for microscopic cell images was presented with special focus on the problem of overlapping cell splitting. The binary operation was performed on original image, and multiple shape features of each connected region were extracted and tested with support vector machine (SVM) to distinguish single and overlapping cell regions. The overlapping cell region was separated by splitting point pair via bottleneck detection. The split edges were modified by an improved ellipse fitting method based on the circle or ellipse shape of cells. The new generated cell regions can effectively reflect the true shape of the overlapping cells. The above steps on the new generated regions were repeated until all overlapping cells were separated. The experimental results show that the proposed method can prevent both over-and under-segmentation more effectively and achieve higher accuracy, sensitivity and specificity for cell segmentation compared with many existing methods．
出版日期: 2017-04-25
CLC:  TP 391  
基金资助:

国家自然科学基金资助项目(61379107, 61172184, 61174210, 61402539); 教育部“新世纪优秀人才支持计划”资助项目(NCET-13-0603); 高等学校博士学科点专项科研基金资助项目(20130162110016); 湖南省科技基本建设项目(20131199); 湖南省科技计划资助项目(2015RS4008); 湖南省自然科学基金资助项目(2015JJ4061,2017JJ3091); 中南大学中央高校基本科研业务费专项资金资助项目(2014ZZTS053); 湖南省研究生科研创新资助项目(CX2014B052).
通讯作者: 赵于前, 男, 教授, 博导. ORCID: 0000-0003-0482-0084.     E-mail: zyq@csu.edu.cn
作者简介: 廖苗(1988—), 女, 博士生, 从事医学图像处理的研究. ORCID: 0000-0003-3378-3817. E-mail: liaomiaohi@163.com
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:

廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2017.04.012.

LIAO Miao, ZHAO Yu-qian, ZENG Ye-zhan, HUANG Zhong-chao, ZHANG Bing-kui, ZOU Bei-ji. Automatic segmentation for cell images based on support vector machine and ellipse fitting. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2017.04.012.

［1］ 张明慧,卢振泰,张娟,等.基于多图谱活动轮廓模型的脑部图像分割［J］.计算机学报,2016, 39(7): 1490-1500．
［2］ CHO M. Performance comparison of two ellipse fitting-based cell separation algorithms ［J］. Journal of the Royal Society of Medicine, 2015, 13(3): 215-219．
［3］ WEI L. Concave regularisation-based non-rigid feature point matching algorithm ［J］. Electronics Letters, 2015, 51(8): 621-623．
［4］ HUANG J D. An improved algorithm of overlapping cell division ［C］∥2010 International Conference on Intelligent Computing and Integrated Systems. Guilin: IEEE, 2010: 687-691．
［5］ LIM H N, MASHOR M Y, HASSAN R. White blood cell segmentation for acute leukemia bone marrow images ［C］∥ 2012 International Conference on Biomedical Engineering. Penang, Malaysia: IEEE, 2012: 357-361．
［6］ 王鑫,胡洋洋,杨惠中.基于迭代腐蚀的粘连细胞图像分割研究［J］.南京理工大学学报:自然科学版,2016,40(3): 285-289．
WANG Xin, HU Yang-yang, YANG Hui-zhong. Segmentation of adherent cell image based on iterative erosion \[J\]. Journal of Nanjing University of Science and Technology, 2016, 40(3): 285-289.
［7］ WU P, YI J, ZHAO G, et al. Active contour-based cell segmentation during freezing and its application in cryopreservation ［J］. IEEE Transactions on Biomedical Engineering, 2015, 62(1): 284-295．
［8］ KAUR S, SAHAMBI J S. Curvelet initialized level set cell segmentation for touching cells in low contrast images ［J］. Computerized Medical Imaging and Graphics, 2016, 49: 46-57.
［9］ FARHAN M, YLIHARJA O, NIEMISTO A. An improved clump splitting method for convex objects ［C］∥Proceedings of the 7th International Workshop on Computational Systems Biology. Luxembourg: TICSP, 2010,35-38．
［10］ LATORRE A, ALONSONANCLARES L, MUELAS S, et al. Segmentation of neuronal nuclei based on clump splitting and a two-step binarization of images ［J］. Expert Systems with Applications, 2013, 40(16): 6521-6530.
［11］ BAI X, SUN C, ZHOU F. Splitting touching cells based on concave points and ellipse fitting ［J］. Pattern Recognition, 2009, 42(11): 2434-2446．
［12］ WANG H, ZHANG H, RAY N. Clump splitting via bottleneck detection and shape classification ［J］. Pattern Recognition, 2012, 45(7): 2780-2787．
［13］ FITZGIBBON A W, PILU M, FISHER R B. Direct least squares fitting of ellipses ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21(5): 476-480．
［14］ The American society hematology ［EB/OL］. 2010-06-01. http:∥imagebank.hematology.org.
［15］ LIAO M, ZHAO Y Q, LI X H, et al. Automatic segmentation for cell images based on bottleneck detection and ellipse fitting ［J］. Neurocomputing, 2016, 173(P3): 615-622．
[1] 郑守国,张勇德,谢文添,樊虎,王青. 基于数字孪生的飞机总装生产线建模[J]. 浙江大学学报(工学版), 2021, 55(5): 843-854.
[2] 张师林,马思明,顾子谦. 基于大边距度量学习的车辆再识别方法[J]. 浙江大学学报(工学版), 2021, 55(5): 948-956.
[3] 宋鹏,杨德东,李畅,郭畅. 整体特征通道识别的自适应孪生网络跟踪算法[J]. 浙江大学学报(工学版), 2021, 55(5): 966-975.
[4] 蔡君,赵罡,于勇,鲍强伟,戴晟. 基于点云和设计模型的仿真模型快速重构方法[J]. 浙江大学学报(工学版), 2021, 55(5): 905-916.
[5] 王虹力,郭斌,刘思聪,刘佳琪,仵允港,於志文. 边端融合的终端情境自适应深度感知模型[J]. 浙江大学学报(工学版), 2021, 55(4): 626-638.
[6] 张腾,蒋鑫龙,陈益强,陈前,米涛免,陈彪. 基于腕部姿态的帕金森病用药后开-关期检测[J]. 浙江大学学报(工学版), 2021, 55(4): 639-647.
[7] 郑英杰,吴松荣,韦若禹,涂振威,廖进,刘东. 基于目标图像FCM算法的地铁定位点匹配及误报排除方法[J]. 浙江大学学报(工学版), 2021, 55(3): 586-593.
[8] 雍子叶,郭继昌,李重仪. 融入注意力机制的弱监督水下图像增强算法[J]. 浙江大学学报(工学版), 2021, 55(3): 555-562.
[9] 于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[10] 胡惠雅,盖绍彦,达飞鹏. 基于生成对抗网络的偏转人脸转正[J]. 浙江大学学报(工学版), 2021, 55(1): 116-123.
[11] 陈杨波,伊国栋,张树有. 基于点云特征对比的曲面翘曲变形检测方法[J]. 浙江大学学报(工学版), 2021, 55(1): 81-88.
[12] 段有康,陈小刚,桂剑,马斌,李顺芬,宋志棠. 基于相位划分的下肢连续运动预测[J]. 浙江大学学报(工学版), 2021, 55(1): 89-95.
[13] 张太恒,梅标,乔磊,杨浩杰,朱伟东. 纹理边界引导的复合材料圆孔检测方法[J]. 浙江大学学报(工学版), 2020, 54(12): 2294-2300.
[14] 梁栋,刘昕宇,潘家兴,孙涵,周文俊,金子俊一. 动态背景下基于自更新像素共现的前景分割[J]. 浙江大学学报(工学版), 2020, 54(12): 2405-2413.
[15] 晋耀,张为. 采用Anchor-Free网络结构的实时火灾检测算法[J]. 浙江大学学报(工学版), 2020, 54(12): 2430-2436.