Robust Bone Marrow Cell Discrimination by Rotation-Invariant Training of Multi-class Echo State Networks

  • Philipp Kainz
  • Harald Burgsteiner
  • Martin Asslaber
  • Helmut Ahammer
Conference paper

DOI: 10.1007/978-3-319-23983-5_36

Part of the Communications in Computer and Information Science book series (CCIS, volume 517)
Cite this paper as:
Kainz P., Burgsteiner H., Asslaber M., Ahammer H. (2015) Robust Bone Marrow Cell Discrimination by Rotation-Invariant Training of Multi-class Echo State Networks. In: Iliadis L., Jayne C. (eds) Engineering Applications of Neural Networks. Communications in Computer and Information Science, vol 517. Springer, Cham

Abstract

Classification of cell types in context of the architecture in tissue specimen is the basis of diagnostic pathology and decisions for comprehensive investigations rely on a valid interpretation of tissue morphology. Especially visual examination of bone marrow cells takes a considerable amount of time and inter-observer variability can be remarkable. In this work, we propose a novel rotation-invariant learning scheme for multi-class Echo State Networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity.

Keywords

Computer-assisted pathology Histopathological image analysis Bone marrow cell classification Echo state networks 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Philipp Kainz
    • 1
    • 2
  • Harald Burgsteiner
    • 3
  • Martin Asslaber
    • 4
  • Helmut Ahammer
    • 1
  1. 1.Institute of BiophysicsMedical University of GrazGrazAustria
  2. 2.Institute of NeuroinformaticsUniversity of Zurich and ETH ZurichZurichSwitzerland
  3. 3.Institute for eHealthGraz University of Applied SciencesGrazAustria
  4. 4.Institute of PathologyMedical University of GrazGrazAustria

Personalised recommendations