Advertisement

Robust segmentation, shape fitting and morphology computation of high-throughput cell nuclei

  • Jie Song (宋 杰)
  • Liang Xiao (肖 亮)
  • Zhichao Lian (练智超)
Article
  • 58 Downloads

Abstract

Accurate nuclear classification (e.g., grading of renal cell carcinoma (RCC) biopsy images) is important to better understand fundamental phenomena such as tumor growth. In this paper, an automated pipeline is proposed to quantitatively analyze RCC data. A novel segmentation methodology is firstly used to delineate cell nuclei based on minimum description length (MDL) constrained B-spline curve fitting. From the obtained segmentations, thirteen features are then extracted based on five types of characteristics. These features are used to classify cell nuclei in biopsy images. Associations among nuclei are computed and represented by graphical networks to enable further analysis. Finally, a support vector machine (SVM) based decision-graph classifier is introduced to classify the biopsy images with the purpose of grading. Experimental results on real RCC data show that our SVM-based decision-graph classifier achieves 95.20% of classification accuracy while the SVM classifiers achieve 93.33% of classification accuracy.

Key words

renal cell carcinoma (RCC) nuclei segmentation nuclear classification feature selection associative measurement grading 

CLC number

TP 391.4 

Document code

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    COSATTO E, MILLER M, GRAF H P, et al. Grading nuclear pleomorphism on histological micrographs [C]//Proceedings of International Conference on Pattern Recognition. New York, USA: IEEE, 2008: 1–4.Google Scholar
  2. [2]
    CHEKKOURY A, KHURD P, NI J, et al. Automated malignancy detection in breast histopathological images [C]//Proceedings of SPIE Medical Imaging. San Diego, CA, USA: SPIE, 2012: 831515-1-831515-13.Google Scholar
  3. [3]
    DOYLE S, AGNER S, MADABHUSHI A, et al. Automated grading of breast cancer histopathology using spectral clustering with textural and architectural image features [C]//Proceedings of 5th IEEE International Symposium on Biomedical Imaging. Paris, France: IEEE, 2008: 496–499.Google Scholar
  4. [4]
    BASAVANHALLY A, GANESAN S, FELDMAN M, et al. Multi-field-of-viewframework for distinguishing tumor grade in ER+ breast cancer from entire histopathology slides [J]. IEEE Transactions on Biomedical Engineering, 2013, 60(8): 3052–3055.CrossRefGoogle Scholar
  5. [5]
    LOHSE C M, BLUTE M L, ZINCKE H, et al. Comparison of standardized and non-standardized nuclear grade of renal cell carcinoma to predict outcome among 2042 patients [J]. American Journal of Clinical Pathology, 2002, 118(6): 877–886.CrossRefGoogle Scholar
  6. [6]
    KIM T Y, CHOI H J, CHA S J, et al. Study on texture analysis of renal cell carcinoma nuclei based on the Fuhrman grading System [C]//Proceedings of Seventh International Workshop on Enterprise Networking and Computing in Healthcare Industry. Busan, Korea: IEEE, 2005: 384–387.Google Scholar
  7. [7]
    NOVARA G, MARTIGNONI G, ARTIBANI W, et al. Grading systems in renal cell carcinoma [J]. Journal of Urology, 2007, 177(2): 430–436.CrossRefGoogle Scholar
  8. [8]
    BJORNSSON C S, LIN G, AL-KOFAHI Y, et al. Associative image analysis: A method for automated quantification of 3D multi-parameter images of brain tissue [J]. Journal of Neuroscience Methods, 2008, 170(1): 165–178.CrossRefGoogle Scholar
  9. [9]
    FIGUEIREDO M, LEITAO J, JAIN A. Unsupervised contour representation and estimation using B-splines and a minimum description length criterion [J]. IEEE Transactions on Image Processing, 2000, 9(6): 1075–1086.MathSciNetCrossRefMATHGoogle Scholar
  10. [10]
    AL-KOFAHI Y, LASSOUED W, LEE W, et al. Improved automatic detection and segmentation of cell nuclei in histopathology images [J]. IEEE Transactions on Biomedical Engineering, 2010, 57(4): 841–852.CrossRefGoogle Scholar
  11. [11]
    HARALICK R M, SHANMUGAM K, DINSTEIN I. Texture features for image classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, SMC-3(6): 610–621.Google Scholar
  12. [12]
    SONG J, XIAO L, LIAN Z C. Boundary-to-marker evidence controlled segmentation and MDL-based contour inference for overlapping nuclei [J]. IEEE Journal of Biomedical and Health Informatics, 2015. DOI: 10.1109/JBHI.2015. 2504422 (published online).Google Scholar
  13. [13]
    FLICKNER M, HAFNER J, RODRIGUEZ E, et al. Periodic quasi-orthogonal spline basis and applications to least squares over curve fitting of digital images [J]. IEEE Transactions on Image Processing, 1996, 5(1): 71–88.CrossRefGoogle Scholar
  14. [14]
    GRUNWALD P, MYUNG J, PITT M. Advances in minimum description length: Theory and applications [M]. Cambridge: MIT Press, 2004.Google Scholar
  15. [15]
    LOLIVE D, BARBOT N, BOEFFARD O. Melodic contour estimation with B-spline models using a MDL criterion [C]//Proceedings of International Conference on Speech and Computer. St. Petersburg, Russia: Anatolya Publishers, 2006: 333–338.Google Scholar
  16. [16]
    CHAM T J, CIPOLLA R. Automated B-spline curve representation incorporating MDL and errorminimizing control point insertion strategies [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1999, 21(1): 49–53.CrossRefGoogle Scholar
  17. [17]
    FUHRMAN S A, LASKY L C, LIMAS C. Prognostic significance of morphologic parameters in renal cell carcinoma [J]. American Journal of Surgical Pathology, 1982, 6(7): 655–663.CrossRefGoogle Scholar

Copyright information

© Shanghai Jiaotong University and Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Jie Song (宋 杰)
    • 1
  • Liang Xiao (肖 亮)
    • 1
  • Zhichao Lian (练智超)
    • 1
  1. 1.School of Computer Science and EngineeringNanjing University of Science and TechnologyNanjingChina

Personalised recommendations