Journal of Signal Processing Systems

, Volume 55, Issue 1, pp 15–23

Automated Renal Cell Carcinoma Subtype Classification Using Morphological, Textural and Wavelets Based Features

  • Qaiser Chaudry
  • Syed Hussain Raza
  • Andrew N. Young
  • May D. Wang
Article

DOI: 10.1007/s11265-008-0214-6

Cite this article as:
Chaudry, Q., Raza, S.H., Young, A.N. et al. J Sign Process Syst Sign Image Video Technol (2009) 55: 15. doi:10.1007/s11265-008-0214-6

Abstract

We present a new image quantification and classification method for improved pathological diagnosis of human renal cell carcinoma. This method combines different feature extraction methodologies, and is designed to provide consistent clinical results even in the presence of tissue structural heterogeneities and data acquisition variations. The methodologies used for feature extraction include image morphological analysis, wavelet analysis and texture analysis, which are combined to develop a robust classification system based on a simple Bayesian classifier. We have achieved classification accuracies of about 90% with this heterogeneous dataset. The misclassified images are significantly different from the rest of images in their class and therefore cannot be attributed to weakness in the classification system.

Keywords

Renal cell carcinomaSubtype classificationComputer-aided diagnosisTissue image quantificationFeature extraction for classificationWaveletCo-occurrenceMorphological processing

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Qaiser Chaudry
    • 1
  • Syed Hussain Raza
    • 1
  • Andrew N. Young
    • 3
  • May D. Wang
    • 1
    • 2
  1. 1.Electrical and Computer EngineeringGeorgia Institute of TechnologyAtlantaUSA
  2. 2.Biomedical Engineering, Winship Cancer InstituteGeorgia Institute of Technology and Emory UniversityAtlantaUSA
  3. 3.Pathology and Laboratory MedicineEmory UniversityAtlantaUSA