Advertisement

Combining Unsupervised Feature Learning and Riesz Wavelets for Histopathology Image Representation: Application to Identifying Anaplastic Medulloblastoma

  • Sebastian Otálora
  • Angel Cruz-Roa
  • John Arevalo
  • Manfredo Atzori
  • Anant Madabhushi
  • Alexander R. Judkins
  • Fabio González
  • Henning Müller
  • Adrien Depeursinge
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9349)

Abstract

Medulloblastoma (MB) is a type of brain cancer that represent roughly 25% of all brain tumors in children. In the anaplastic medulloblastoma subtype, it is important to identify the degree of irregularity and lack of organizations of cells as this correlates to disease aggressiveness and is of clinical value when evaluating patient prognosis. This paper presents an image representation to distinguish these subtypes in histopathology slides. The approach combines learned features from (i) an unsupervised feature learning method using topographic independent component analysis that captures scale, color and translation invariances, and (ii) learned linear combinations of Riesz wavelets calculated at several orders and scales capturing the granularity of multiscale rotation-covariant information. The contribution of this work is to show that the combination of two complementary approaches for feature learning (unsupervised and supervised) improves the classification performance. Our approach outperforms the best methods in literature with statistical significance, achieving 99% accuracy over region-based data comprising 7,500 square regions from 10 patient studies diagnosed with medulloblastoma (5 anaplastic and 5 non-anaplastic).

Keywords

Local Binary Pattern Convolutional Neural Network Whole Slide Image Disease Aggressiveness Convolutional Neural Network Model 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cruz-Roa, A., Arevalo, J., Basavanhally, A., et al.: A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation. In: Proc. SPIE 9287, pp. 92870G–92870G–6 (2015)Google Scholar
  2. 2.
    Cruz-Roa, A., González, F., Galaro, J., Judkins, A.R., Ellison, D., Baccon, J., Madabhushi, A., Romero, E.: A visual latent semantic approach for automatic analysis and interpretation of anaplastic medulloblastoma virtual slides. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. MICCAI 2012, pp. 157–164. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Depeursinge, A., Foncubierta-Rodriguez, A., Van De Ville, D., Müller, H.: Rotation–covariant texture learning using steerable Riesz wavelets. IEEE Transactions on Image Processing 23(2), 898–908 (2014)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Depeursinge, A., Foncubierta–Rodriguez, A., Van de Ville, D., Müller, H.: Multiscale lung texture signature learning using the riesz transform. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part III. LNCS, vol. 7512, pp. 517–524. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Ellison, D.W.: Childhood medulloblastoma: novel approaches to the classification of a heterogeneous disease. Acta Neuropathologica 120(3), 305–316 (2010)CrossRefGoogle Scholar
  6. 6.
    Fuchs, T.J., Buhmann, J.M.: Computational pathology: Challenges and promises for tissue analysis. Computerized Medical Imaging and Graphics 35(7–8), 515–530 (2011)CrossRefGoogle Scholar
  7. 7.
    Galaro, J., Judkins, A., Ellison, D., Baccon, J., Madabhushi, A.: An integrated texton and bag of words classifier for identifying anaplastic medulloblastomas. In: EMBC, 2011 Annual International Conference of the IEEE, pp. 3443–3446 (2011)Google Scholar
  8. 8.
    Gurcan, M.N., Boucheron, L.E., Can, A., et al.: Histopathological image analysis: A review. IEEE Reviews in Biomedical Engineering 2, 147–171 (2009)CrossRefGoogle Scholar
  9. 9.
    Kothari, S., Phan, J.H., Stokes, T.H., Wang, M.D.: Pathology imaging informatics for quantitative analysis of whole-slide images. Journal of the American Medical Informatics Association 20(6), 1099 (2013)CrossRefGoogle Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105 (2012)Google Scholar
  11. 11.
    Ranzato, M., Huang, F.J., Boureau, Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar
  12. 12.
    Wang, H., Cruz-Roa, A., Basavanhally, A., et al.: Mitosis detection in breast cancer pathology images by combining handcrafted and convolutional neural network features. Journal of Medical Imaging 1(3), 34003 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Sebastian Otálora
    • 1
  • Angel Cruz-Roa
    • 1
  • John Arevalo
    • 1
  • Manfredo Atzori
    • 2
  • Anant Madabhushi
    • 3
  • Alexander R. Judkins
    • 4
  • Fabio González
    • 1
  • Henning Müller
    • 2
  • Adrien Depeursinge
    • 2
    • 5
  1. 1.Universidad Nacional de ColombiaBogotáColombia
  2. 2.University of Applied Sciences Western Switzerland (HES-SO)DelémontSwitzerland
  3. 3.Case Western Reserve UniversityClevelandUSA
  4. 4.St. Jude Childrens Research Hospital from MemphisMemphisUSA
  5. 5.Ecole Polytechnique Fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations