3D Local Binary Pattern for PET Image Classification by SVM - Application to Early Alzheimer Disease Diagnosis

Christophe Montagne, Andreas Kodewitz, Vincent Vigneron, Virgile Giraud, Sylvie Lelandais

Abstract

The early diagnostic of Alzheimer disease by non-invasive technique becomes a priority to improve the life of patient and his social environment by an adapted medical follow-up. This is a necessity facing the growing number of affected persons and the cost to our society caused by dementia. Computer based analysis of Fluorodeoxyglucose PET scans might become a possibility to make early diagnosis more efficient. Temporal and parietal lobes are the main location of medical findings. We have clues that in PET images these lobes contain more information about Alzheimer’s disease. We used a texture operator, the Local Binary Pattern, to include prior information about the localization of changes in the human brain. We use a Support Vector machine (SVM) to classify Alzheimer’s disease versus normal control group and to get better classification rates focusing on parietal and temporal lobes.

References

  1. Bennys, K., Rondouin, G., Vergnes, C., and Touchon, J. (2001). Diagnostic value of quantitative EEG in alzheimer's disease. Clinical Neurophysiology, 31(3):153-160.
  2. Kodewitz, A., V., V., Montagne, C., and Lelandais, S. (2011). Where to search for alzheimer's disease related changes in pet scans? RITS, Rennes, France.
  3. Lancaster, L., Woldorff, M. G., and Parsons, L. M. (2000). Automated talairach atlas labels for functional brain mapping. Human Brain Mapping, 10:120-131.
  4. Maldjian, J. A., Laurienti, P. J., Burdette, J. H., and Kraft, R. A. (2003). An automated method for neuroanatomic and cytoarchitectonic atlas-based interrogation of fmri data sets. NeuroImage, 19:1233-1239.
  5. Paulhac, L., Makris, P., and Ramel, J. (2008). Comparison between 2d and 3d local binary pattern methods for characterisation of three-dimensional textures. In Series, B., editor, Lecture Notes in Computer Science, volume 5112/2008, pages 670-679, Pòvoa de Varzim, Portugal. ICIAR.
  6. Pietikäinen, M. and Ojala, T. (2000). rotation-invariant texture classification using feature distributions. Pattern Recognition, 33:43-52.
  7. Ramìrez, J., Gòrriz, J., and et al., D. S.-G. (2009). Computer-aided diagnosis of alzheimer's type dementia combining support vector machines and discriminant set of features. Information Sciences.
  8. Salmon, E. (2008). Différentes facettes de la maladie de type azheimer. Rev Med Liege, 63(5-6):299-302.
  9. Scarmeas, N., Habeck, C. G., and et al., E. Z. (2004). Covariance pet patterns in early alzheimer's disease and subjects with cognitive impairment but no dementia: utility in group discrimination and correlations with functional performance. NeuroImage, 23(1):35 - 45.
  10. Schölkopf, B. and Smola, A. (2002). Learning with Kernels - Support Vector Machines, Regularization, and Beyond. The MIT Press.
  11. Vapnik, V. (1998). Statistical learning theory. Wiley.
  12. Wimo, A. and Prince, M. (2010). World alzheimer report 2010. http://www.alz.co.uk/research/world-report.
Download


Paper Citation


in Harvard Style

Montagne C., Kodewitz A., Vigneron V., Giraud V. and Lelandais S. (2013). 3D Local Binary Pattern for PET Image Classification by SVM - Application to Early Alzheimer Disease Diagnosis . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013) ISBN 978-989-8565-36-5, pages 145-150. DOI: 10.5220/0004226201450150


in Bibtex Style

@conference{biosignals13,
author={Christophe Montagne and Andreas Kodewitz and Vincent Vigneron and Virgile Giraud and Sylvie Lelandais},
title={3D Local Binary Pattern for PET Image Classification by SVM - Application to Early Alzheimer Disease Diagnosis},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)},
year={2013},
pages={145-150},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004226201450150},
isbn={978-989-8565-36-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)
TI - 3D Local Binary Pattern for PET Image Classification by SVM - Application to Early Alzheimer Disease Diagnosis
SN - 978-989-8565-36-5
AU - Montagne C.
AU - Kodewitz A.
AU - Vigneron V.
AU - Giraud V.
AU - Lelandais S.
PY - 2013
SP - 145
EP - 150
DO - 10.5220/0004226201450150