计算机科学 ›› 2016, Vol. 43 ›› Issue (5): 298-303.doi: 10.11896/j.issn.1002-137X.2016.05.057

• 图形图像与模式识别 • 上一篇    下一篇

相差显微图像下的癌细胞状态检测

张剑华,邹祎杰,高强,陈胜勇   

  1. 浙江工业大学计算机科学与技术学院 杭州310023 浙江省可视媒体智能处理技术研究重点实验室 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023 浙江省可视媒体智能处理技术研究重点实验室 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023 浙江省可视媒体智能处理技术研究重点实验室 杭州310023,浙江工业大学计算机科学与技术学院 杭州310023 浙江省可视媒体智能处理技术研究重点实验室 杭州310023
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(61305021),国家教育部博士点基金(20133317120003),浙江省科技厅公益项目(2014C31102)资助

State Detection of Cancer Cell in Phase-contrast Microscopy Images

ZHANG Jian-hua, ZOU Yi-jie, GAO Qiang and CHEN Sheng-yong   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对相差显微镜下癌细胞的生命状态分析问题,提出了一种基于形态学的癌细胞状态检测与判别方法。首先使用改进的水平集算法分割出目标癌细胞的轮廓,然后使用OTSU方法在细胞内部进行二值化处理,得到亮、暗两种区域。基于细胞轮廓和细胞内部亮、暗区域,充分利用细胞灰度、形状及内部结构信息,提出了5种有效的特征来进行细胞分裂间期、分裂前期、分裂中期和分裂后期的检测与判别。大量实验表明,所提方法对膀胱癌T24相差显微(Phase-Microscopy)细胞视频中的癌细胞检测可以得到较好的结果,证明该方法可以检测并判别出各个独立细胞的位置及所处阶段,且对序列图像中的细胞状态检测有较强的鲁棒性。

关键词: 相差显微图像,癌细胞,状态检测,细胞分裂

Abstract: This work described a new method based on morphology for detecting different states in a cell circle in time-lapse microscopy image of live cancer cells.A three-step approach was used as follows.First,we applied an improved level-set function to segment cancer cell images so as to identify the outline of each candidate.Then,an overall gray threshold of all the cancer cell regions was obtained through OTSU.We used this threshold to divide every cancer cell regions into two parts——dark and bright.At last,5 efficient features based on gray level,shapes and inside structures were proposed to distinguish cancer cells from interphase,mitotic prophase,mitotic metaphase and mitotic anaphase.Experiments upon T24 bladder cancer in time-lapse microscopy image were conducted,showing the proposed detection method performs well.Through this method,the position and state of cells can be detected correctly,and it has strong robustness of detecting states of cells in consecutive images.

Key words: Phase-contrast microscopy images,Cancer cell,State detection,Mitosis

[1] Liu Gang-feng.Tracking Alive Cells in Cell Microscopy Se-quence Images[D].Hangzhou:Zhejiang University of Technology,2012(in Chinese) 柳刚锋.显微视频序列图像中细胞的跟踪[D].杭州:浙江工业大学,2012
[2] Dewan M A A,Ahmad M O,Swamy M N S.Tracking biological cells in time-lapse microscopy:an adaptive technique combining motion and topological features[J].IEEE Transactions on Biomedical Engineering,2011,58(6):1637-1647
[3] Zhan Qi-min.Molecular Oncology[M].Beijing:People’s Medical Publishing House,2005(in Chinese) 詹启敏.分子肿瘤学[M].北京:北京人民卫生出版社,2005
[4] Mller M,Burger M,Dieterich P,et al.A Framework for Automated Cell Tracking in Phase Contrast Microscopic Videos Based on Normal Velocities[J].Journal of Visual Communication and Image Representation,2014(25):396-409
[5] Meijering E,Dzyubachyk O,Smal I,et al.Tracking in Cell and Developmental Biology[J].Semin Cell Dev Biol, 2009(20):894-902
[6] Wei Guo-jian,Hou Zhi-qiang,Li Wu,et al.Motion coherence ima-ge segmentation fused with multi-feature[J].Journal of Image and Graphics,2014,9(5):701-707(in Chinese) 魏国剑,侯志强,李武,等.融合多特征的运动一致性图像分割[J].中国图象图形学报,2014,9(5):701-707
[7] Debeir O,Megalizzi V,Warzee N,et al.Videomicroscopic Extraction of Specific Information on Cell Proliferation and Migration in Vitro[J].Exp Cell Res,2008(314):2985-2998
[8] Grah J.Methods for Automatic Mitosis Detection and Tracking in Phase Contrast Images[D].Muenster: Westfaelische Wilhelms University,2008
[9] Li K,Miller E D,Chen M,et al.Computer vision tracking ofstemness[C]∥5th IEEE International Symposium on BiomedicalImaging:From Nano to Macro,2008(ISBI 2008).IEEE,2008:847-850
[10] Kottke D P,Fwu J,Brown K.Hidden Markov modeling for automatic target recognition[C]∥Conference Record of the Thirty-First Asilomar Conference on Signals,Systems & amp;Computers,1997.EEE,1997:859-863
[11] Gallardo G M,Yang F,Ianzini F,et al.Mitotic cell recognition with hidden Markov models[C]∥Medical Imaging 2004.International Society for Optics and Photonics,2004:661-668
[12] Huh S,Ker D F E,Bise R,et al.Automated mitosis detection of stem cell populations in phase-contrast microscopy images[J].IEEE Transactions on Medical Imaging,2011,30(3):586-596
[13] Wu Shi-lin,Geng Jia-jia,Zhu Feng,et al.Region-based multi-class object recognition and segmentation[J].Journal of Image and Graphics,2011,6(9):1607-1614(in Chinese) 吴士林,耿佳佳,朱枫,等.基于区域的多类目标识别与分割算法研究[J].中国图象图形学报,2011,6(9):1607-1614
[14] Li C,Xu C,Gui C,et al.Level set evolution without re-initialization:a new variational formulation[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005,1:430-436
[15] Zhu Chen.Cell Dynamic Analysis Based On Microscopy Images Sequence[D].Hangzhou:Zhejiang University of Technology,2013(in Chinese) 朱辰.基于显微图像序列的细胞动态分析[D].杭州:浙江工业大学,2013
[16] http://en.wikipedia.org/wiki/Cell_(biology)
[17] http://baike.baidu.com/view/254458.htm
[18] Yadav V K,Batham S,Acharya A K,et al.Approach to accurate circle detection:Circular Hough Transform and Local Maxima concept[C]∥2014 International Conference on Electronics and Communication Systems(ICECS).IEEE,2014:1-5
[19] Liew L H,Lee B Y,Chan M.Cell detection for bee comb images using circular Hough transformation[C]∥2010 International Conference on Science and Social Research(CSSR).IEEE,2010:191-195
[20] Zhu Gui-ying,Zhang Rui-lin.Circle detection using Hough tr-ansform[J].Computer Engineering and Design,2008,9(6):1462-1464(in Chinese) 朱桂英,张瑞林.基于 Hough 变换的圆检测方法[J].计算机工程与设计,2008,29(6):1462-1464

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!