An Ensemble Algorithm Framework for Automated Stereology of Cervical Cancer

  • Baishali Chaudhury
  • Hady Ahmady Phoulady
  • Dmitry Goldgof
  • Lawrence O. Hall
  • Peter R. Mouton
  • Ardeshir Hakam
  • Erin M. Siegel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8156)


Stereological procedures to quantify mean nuclear volume are commonly used to differentiate cancerous from normal tissue. Automatic quantification of these parameters requires segmentation, which is complicated by the variability in tissue staining and nuclei size. One solution to deal with such alterations in a robust fashion is to use an ensemble of segmentation methods. The goal of this work is to demonstrate the use of an ensemble of simple segmentors in a novel way to improve the performance achieved by the individual segmentors. The contributions of this paper are three fold: applying an ensemble on the blob level in addition to the image level, utilizing the image level ensemble to accept or reject input images based on their segmentation quality and finally applying the ensembles for discriminating cancer and normal classes. Hematoxylin and eosin (H&E) stained sections from archival tissues from the normal cervix and cervical cancer have been used as the dataset. The results presented here show that both levels of ensembles enable clear class separability as compared to the individual segmentors, and thus demonstrate the effectiveness of the proposed ensemble framework.


Ensemble of segmentations microscopy images Otsu cervical cancer 


  1. 1.
    Creagh, T., Bridger, J., Kupek, E.: Pathologist Variation in Reporting Cervical Borderline Epithelial Abnormalities and Cervical Intraepithelial Neoplasia. J. Clin. Pathol. 48, 59–60 (1995)CrossRefGoogle Scholar
  2. 2.
    Wahlby, C., et al.: Combining Intensity, Edge and Shape Information for 2D and 3D Segmentation of Cell Nuclei in Tissue Sections. J. Micro. 215, 67–76 (2004)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Lewin, S., Jiang, X., Clausing, A.: A Clustering-Based Ensemble Technique for Shape Decomposition. In: Gimel’farb, G., Hancock, E., Imiya, A., Kuijper, A., Kudo, M., Omachi, S., Windeatt, T., Yamada, K. (eds.) SSPR&SPR 2012. LNCS, vol. 7626, pp. 153–161. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  4. 4.
    Vega-Pons, S., Shullcloper, J.: A Survey of Clustering Ensemble Algorithms. Int. J. Pattern Recogn. 25, 337–372 (2011)CrossRefGoogle Scholar
  5. 5.
    Caruana, R., et al.: Ensemble Selection from Libraries of Models. In: Proceeding of 21st International Conference on Machine Learning. ACM (2004)Google Scholar
  6. 6.
    Gu, Y.: Automated Delineation of Lung Tumors from CT Images Using a Single Click Ensemble Segmentation Approach. Int J. Pattern Recogn. 46, 692–702 (2013)CrossRefGoogle Scholar
  7. 7.
    Wattuya, P.: Combination of Multiple Segmentations. Diss. Phd. thesis, University of Munster, Germany (2010)Google Scholar
  8. 8.
    Simsek, A.C., Tosun, A.B.: Multilevel Segmentation of Histopathological Images Using Cooccurrence of Tissue Objects. IEEE Transactions on Biomedical Engineering 59, 1681–1689 (2012)CrossRefGoogle Scholar
  9. 9.
    Rafiee, G., Dlay, S., Woo, W.: Automatic Segmentation of Interest Regions in Low Depth of Field Images Using Ensemble Clustering and Graph Cut Optimization Approaches. In: IEEE International Symposium on Multimedia, vol. 59, pp. 161–164 (2012)Google Scholar
  10. 10.
    Pantofaru, C., Schmid, C., Hebert, M.: Object Recognition by Integrating Multiple Image Segmentations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 481–494. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  11. 11.
    Otsu, N.: A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man and Cybernetics 9, 62–66 (1979)CrossRefGoogle Scholar
  12. 12.
    Dufour, A., et al.: 3-D Active Meshes: Fast Discrete Deformable Models for Cell Tracking in 3-D Time-Lapse Microscopy. IEEE Transactions on Image Processing 20, 1925–1937 (2011)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Xiong, W., Chia, S., Lim, J.H.: Automated Nuclei ClumpDecomposition for Image Analysis in Neuronal Cell Fluoroscent Microscopy. In: 18th IEEE International Conference on Image Processing, pp. 1577–1580 (2011)Google Scholar
  14. 14.
    Wattuya, P., et al.: A Random Walker Based Approach to Combining Multiple Segmentations. In: International Conference on Pattern Recognition, pp. 1–4 (2008)Google Scholar
  15. 15.
    Franek, L., Abdala, D.D., Vega-Pons, S., Jiang, X.: Image Segmentation Fusion Using General Ensemble Clustering Methods. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part IV. LNCS, vol. 6495, pp. 373–384. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Sorensen, F.B., et al.: Stereological Estimates of Nuclear Volume in Squamous Cell Carcinoma of the Uterine Cervix and its Precursors. Virchows Archive 418, 225–233 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Baishali Chaudhury
    • 1
  • Hady Ahmady Phoulady
    • 1
  • Dmitry Goldgof
    • 1
  • Lawrence O. Hall
    • 1
  • Peter R. Mouton
    • 2
  • Ardeshir Hakam
    • 3
  • Erin M. Siegel
    • 3
  1. 1.Computer Science & EngineeringUniversity of South FloridaTampaUSA
  2. 2.Dept of Pathology & Cell BiologyUniversity of South Florida School of MedicineTampaUSA
  3. 3.H. Lee Moffitt Cancer Center & Research InstituteTampaUSA

Personalised recommendations