Abstract
This work aims at providing a tool to assist the interpretationof SPECT images for the diagnosis of Alzheimer’s Disease (AD). Our approach is to test classifiers, which uses the intensity values of the images, without any prior information. Such a classifier is built upon a training set, containing images with two different labels (AD patients and normal subjects). It will then provide a classification for any new unknown image. The main problem to be handled is the small number of available images compared to the large number of features (here the image’s voxels): the so-called small sample size problem. We evaluate here the ability of two linear classifiers to correctly label a set of 79 images. Our experiments show promising results. They also show that image classification based on intensity values only is possible and might be used for other applications as well.
Chapter PDF
Similar content being viewed by others
Keywords
- Single Photon Emission Compute Tomography
- Spect Image
- Single Photon Emission Compute Tomography Image
- Training Object
- Fisher Linear Discriminant
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.
References
Jagust W.J. Functional imaging patterns in Alzheimer’s disease. Annals of the New York Academy of Sciences, 777:30–36, 1996.
Nitrini R., Buchpiguel C.A., Caramelli P., Bahia V.S., Mathias S.C., Nascimento C.M.R., Degenszajn J., and Caixeta L. SPECT in Alzheimer’s disease: features associated with bilateral parietotemporal hypoperfusion. Acta Neurologica Scandinavica, 101:172–176, 2000.
Frackowiak R.S.J., Friston K.J., Frith C.D., and Dolan R. Human Brain Function. Academic Press, 1997.
Jones K., Johnson K.A., Becker J.A., Spiers P.A., Albert M.S., and Holman B.L. Use of singular value decomposition to characterize age and gender differences in SPECT cerebral perfusion. Journal of Nuclear Medicine, 39:965–973, 1998.
Houston A.S., Kemp P.M., and Macleod M.A. A method for asseing the significance of abnormalities in HMPAO brainsp ect images. Journal of Nuclear Medicine, 35:239–244, 1994.
Johnson K.A., Jones K., Holman B.L, Becker J.A., Spiers P.A., Satlin A., and Albert M.S. Preclinical prediction of Alzheimer’s disease using SPECT. Neurology, 50:1563–1571, 1998.
Duin R.P.W. Classifiers in almost empty spaces. In Proceedings of the 15th International Conference on Pattern Recognition (ICPR2000), Vol. 2, pages 1–7, Las Alamitos (CA), 2000. IAPR, IEEE Computer Society.
Raudys S.J. and Jain A.K. Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Transactions on Pattern Recognition and Machine Intelligence, 13(3):252–264, March 1991.
Vapnik V.N. Statistical learning theory. John Wiley & Sons, 1998.
Skurichina M. and Duin R.P.W. Stabilizing classifiers for very small sample sizes. In Proceedings of the 13th International Conference on Pattern Recognition (ICPR1996), Vol. 2, pages 891–896. IAPR, IEEE Computer Society, 1996.
Raudys S.J. and Duin R.P.W. Expected classification error of the Fisher linear classifier with pseudo-inverse covariance matrix. Pattern Recognition Letters, 19:385–392, 1998.
Chen L.F., Liao H.Y.M., Ko M.T., Lin J.C., and Yu G.J. A new LDA-based face recognition which can solve the small sample size problem. Pattern Recognition, 33:1713–1726, 2000.
Hamamoto Y., Fujimoto Y., and Tomita S. On the estimation of a covariance matrix in designing Parzen classifiers. Pattern Recognition, 29(10):1751–1759, 1996.
Duin R.P.W. Small Sample Size Generalization. In Proceedings of the 9th Scandinavian Conference on Image Analysis (SCIA95), pages 957–964, 1995.
Roche A., Malandain G., and Ayache N. Unifying Maximum Likelihood Approaches in Medical Image Registration. International Journal of Imaging Systems and Technology, 11:71–80, 2000.
P. Cachier and X. Pennec. 3D Non-Rigid Registration by Gradient Descent on a Gaussian-Windowed Similarity Measure using Convolutions. In Proc. of MMBIA’ 00, pages 182–189, Hilton Head Island, USA, June 2000.
Saxena P., Pavel D.G., Quintana J.C., and Horwitz B. An automatic thresholdbased scaling method for enhancing the usefulness of Tc-HMPAO SPECT in the diagnosis of Alzheimer’s disease. In Proceedings of the 1st international conference on Medical Imaging Computing and Computer-Assisted Intervention (MICCAI’98), volume 1496 of Lecture Notes in Computer Science, pages 623–630. Springer, 1996.
Chang L.T. A method for attenuation correction in radionuclide computed tomography. IEEE Transactions on Nuclear Science, 25:638–643, 1978.
Duin R.P.W. PRTools 3.1, A Matlab Toolbox for Pattern Recognition. Delft Un iversity of Technology, Januray 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Stoeckel, J. et al. (2001). Classification of SPECT Images of Normal Subjects versus Images of Alzheimer’s Disease Patients. In: Niessen, W.J., Viergever, M.A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2001. MICCAI 2001. Lecture Notes in Computer Science, vol 2208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45468-3_80
Download citation
DOI: https://doi.org/10.1007/3-540-45468-3_80
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42697-4
Online ISBN: 978-3-540-45468-7
eBook Packages: Springer Book Archive