A Data Driven Approach to Cervigram Image Analysis and Classification

  • Edward Kim
  • Xiaolei Huang
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 6)


Cervical cancer is one of the leading causes of death for women worldwide. Early detection of cervical cancer is possible through regular screening; however, in developing countries, screening and treatment options are limited due to poor (or lack of) resources. Fortunately, low cost screening procedures utilizing visual inspection after the application of acetic acid in combination with low cost DNA tests to detect HPV infections have been shown to reduce the lifetime risk of cervical cancer by nearly 30 %. To assist in this procedure, we developed an automatic, data centric system for cervigram (photographs of the cervix) image analysis. In the first step of our algorithm, our system utilizes nearly a thousand annotated cervigram images to automatically locate a cervix region of interest. Next, by utilizing both color and texture features extracted from the cervix region of interest on several thousand cervigrams, we show that our system is able to perform a binary classification of disease grading on cervigram images with comparable accuracy to a trained expert. Finally, we analyze and report the effect that the color and texture features have on our end classification result.


Cervical Cancer Ground Truth Texture Feature Gaussian Mixture Model Cervix Region 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



This research was supported in part by the Intramural Research Program of the National Institutes of Health (NIH), National Library of Medicine (NLM), and Lister Hill National Center for Biomedical Communications (LH- NCBC). The image and clinical data for this work comes from the National Cancer Institute (NCI) Guanacaste/ALTS projects.


  1. 1.
    Atlanta (2010) Cancer facts and figures. American Cancer Society, Atlanta Google Scholar
  2. 2.
    Atlanta (2011) Global cancer facts and figures, 2nd edn. American Cancer Society, Atlanta Google Scholar
  3. 3.
    Belinson J, Pretorius R (2002) Cervical cancer screening by simple visual inspection after acetic acid. Obstet Gynecol 99(3):518 CrossRefGoogle Scholar
  4. 4.
    Bosch A, Zisserman A, Munoz X (2007) Representing shape with a spatial pyramid kernel. In: International conference on image and video retrieval, pp 401–408 Google Scholar
  5. 5.
    Chang CC, Lin C.J. (2001) LIBSVM: a library for support vector machines. Software available at
  6. 6.
    Denny L, Kuhn L, Pollack A, Wainwright H, Wright T Jr (2000) Evaluation of alternative methods of cervical cancer screening for resource-poor settings. Cancer 89(4):826–833 CrossRefGoogle Scholar
  7. 7.
    Denny L, Kuhn L, Pollack A, Wright T Jr (2002) Direct visual inspection for cervical cancer screening. Cancer 94(6):1699–1707 CrossRefGoogle Scholar
  8. 8.
    Gordon S, Zimmerman G, Greenspan H (2004) Image segmentation of uterine cervix images for indexing in PACS. In: IEEE symposium on computer-based medical systems Google Scholar
  9. 9.
    Gordon S, Zimmerman G, Long R, Antani S, Jeronimo J, Greenspan H (2006) Content analysis of uterine cervix images: initial steps towards content based indexing and retrieval of cervigrams. In: Proceedings of SPIE medical imaging, vol 6144, pp 1549–1556 Google Scholar
  10. 10.
    Jeronimo J, Long L, Neve L, Michael B, Antani S, Schiffman M (2006) Digital tools for collecting data from cervigrams for research and training in colposcopy. J Low Genit Tract Dis 10(1):16 CrossRefGoogle Scholar
  11. 11.
    Ji Q, Engel J, Craine E (2000) Classifying cervix tissue patterns with texture analysis. Pattern Recognit 33(9):1561–1574 CrossRefGoogle Scholar
  12. 12.
    Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: IEEE computer society conference on computer vision and pattern recognition, vol 2, pp 2169–2178 Google Scholar
  13. 13.
    Li W, Gu J, Ferris D, Poirson A (2007) Automated image analysis of uterine cervical images. Prog Biomed Opt Imaging 8(33) Google Scholar
  14. 14.
    Sankaranarayanan R, Basu P, Wesley R, Mahe C, Keita N, Mbalawa C, Sharma R, Dolo A, Shastri S, Nacoulma M et al. (2004) Accuracy of visual screening for cervical neoplasia: results from an IARC multicentre study in India and Africa. Int J Cancer 110(6):907–913 CrossRefGoogle Scholar
  15. 15.
    Sankaranarayanan R, Gaffikin L, Jacob M, Sellors J, Robles S (2005) A critical assessment of screening methods for cervical neoplasia. Int J Gynecol Obstet 89:S4–S12 CrossRefGoogle Scholar
  16. 16.
    Srinivasan Y, Nutter B, Mitra S, Phillips B, Sinzinger E (2006) Classification of cervix lesions using filter bank-based texture mode. In: IEEE symposium on computer-based medical systems Google Scholar
  17. 17.
    Xue Z, Antani S, Long R, Thoma G (2007) Comparative performance analysis of cervix roi extraction and specular reflection removal algorithms for uterine cervix image analysis. In: Proceedings of SPIE medical imaging, vol 6512, pp 4I1–4I9 Google Scholar
  18. 18.
    Zimmerman-Moreno G, Greenspan H (2006) Automatic detection of specular reflections in uterine cervix images. In: Proceedings of SPIE medical imaging Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringLehigh UniversityBethlehemUSA

Personalised recommendations