Advertisement

Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation

  • Aïcha BenTaieb
  • Hector Li-Chang
  • David Huntsman
  • Ghassan Hamarneh
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9349)

Abstract

It has now been convincingly demonstrated that ovarian carcinoma subtypes are not a single disease but comprise a heterogeneous group of neoplasms. Whole slide images of tissue sections are used clinically for diagnosing biologically distinct subtypes, as opposed to different grades of the same disease. This new grading scheme for ovarian carcinomas results in a low to moderate interobserver agreement among pathologists. In practice, the majority of cases are diagnosed at advanced stages and the overall prognosis is typically poor. In this work, we propose an automatic system for the diagnosis of ovarian carcinoma subtypes from large-scale histopathology images. Our novel approach uses an unsupervised feature learning framework composed of a sparse tissue representation and a discriminative feature encoding scheme. We validate our model on a challenging clinical dataset of 80 patients and demonstrate its ability to diagnose whole slide images with an average accuracy of 91% using a linear support vector machine classifier.

Keywords

Histopathology ovarian carcinomas machine learning 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baak, J.P., et al.: Interpathologist and intrapathologist disagreement in ovarian tumor grading and typing. In: Analytical and Quantitative Cytology and Histology (1986)Google Scholar
  2. 2.
    Caicedo, J.C., et al.: Histopathology image classification using bag of features and kernel functions. In: AI in Medicine, pp. 126–135 (2009)Google Scholar
  3. 3.
    Chang, H., Nayak, N., Spellman, P.T., Parvin, B.: Characterization of tissue histopathology via predictive sparse decomposition and spatial pyramid matching. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part II. LNCS, vol. 8150, pp. 91–98. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  4. 4.
    Chang, H., et al.: Classification of tumor histology via morphometric context. In: CVPR, pp. 2203–2210 (2013)Google Scholar
  5. 5.
    Chatfield, et al.: The devil is in the details: an evaluation of recent feature encoding methods (2011)Google Scholar
  6. 6.
    Coates, A., Ng, A.Y.: The importance of encoding versus training with sparse coding and vector quantization. In: ICML, pp. 921–928 (2011)Google Scholar
  7. 7.
    Demir, C., Yener, B.: Automated cancer diagnosis based on histopathological images: a systematic survey. Rensselaer Polytechnic Institute, Tech. Rep. (2005)Google Scholar
  8. 8.
    Gurcan, M.N., et al.: Histopathological image analysis: A review. Reviews in Biomedical Engineering, 147–171 (2009)Google Scholar
  9. 9.
    Han, J., et al.: Comparison of sparse coding and kernel methods for histopathological classification of gliobastoma multiforme. In: ISBI, pp. 711–714 (2011)Google Scholar
  10. 10.
    Köbel, M., et al.: Diagnosis of ovarian carcinoma cell type is highly reproducible: a transcanadian study. The American Journal of Surgical Pathology 34(7), 984–993 (2010)CrossRefGoogle Scholar
  11. 11.
    Malpica, A., et al.: Interobserver and intraobserver variability of a two-tier system for grading ovarian serous carcinoma. The American Journal of Surgical Pathology, 354–357 (2007)Google Scholar
  12. 12.
    McCluggage, W.G.: Morphological subtypes of ovarian carcinoma: a review with emphasis on new developments and pathogenesis. Pathology Journal of the RCPA, 420–432 (2011)Google Scholar
  13. 13.
    McCluggage, W.G.: Ten problematical issues identified by pathology review for multidisciplinary gynaecological oncology meetings. Journal of Clinical Pathology, 420–432 (2011)Google Scholar
  14. 14.
    Naik, S., et al.: Automated gland and nuclei segmentation for grading of prostate and breast cancer histopathology. In: ISBI, pp. 284–287 (2008)Google Scholar
  15. 15.
    Soslow, R.A.: Histologic subtypes of ovarian carcinoma: an overview. International Journal of Gynecologic Pathology, 161–174 (2008)Google Scholar
  16. 16.
    Xu, Y., et al.: Multiple clustered instance learning for histopathology cancer image classification, segmentation and clustering. In: CVPR, pp. 964–971 (2012)Google Scholar
  17. 17.
    Zeiler, M.D., et al.: Deconvolutional networks. In: ICCV, pp. 2528–2535 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Aïcha BenTaieb
    • 1
  • Hector Li-Chang
    • 2
  • David Huntsman
    • 2
  • Ghassan Hamarneh
    • 1
  1. 1.Medical Image Analysis LabSimon Fraser UniversityBurnabyCanada
  2. 2.Departments of Pathology and Laboratory Medicine and Obstetrics and GynaecologyUniversity of British ColumbiaVancouverCanada

Personalised recommendations