Abstract
This paper presents an automatic method for selecting Regions of Interest (ROI) related to the Alzheimer’s Disease (AD) using the information contained in 3D structural MRIs. Normal and AD images are modelled by a number of prototypes provided by Vector Quantization (VQ) algorithms (specifically, Self-Organizing Maps, SOM) which model the volumetric probability histogram and describe the intensity profile of the image. The receptive field of each SOM unit represent a different region of interest on the brain associated to the peaks on the probability histogram. Thus, the space is quantized and the activation level of each SOM unit is associated to the probability of occurrence of the modelled gray level. Additionally, this method can be used to extract a reduced and discriminative features for AD classification, as it compress the information contained in the brain in a reduced number of models. The proposed method has been assessed using the computed ROIs to classify a set of images from the Alzheimer’s disease Neuroimaging Initiative (ADNI).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Álvarez, I., Górriz, J.M., Ramírez, J., Salas-González, D., López, M.M., Segovia, F., Chaves, R., Gomez-Río, M., García-Puntonet, C.: 18f-fdg pet imaging analysis for computer aided Alzheimer’s diagnosis. Information Sciences 184(4), 903–916 (2011)
Alzheimer’s Disease Neuroimaging Initiative (ADNI) (2012)
Chyzhyk, D., Graña, M., Savio, A., Maiora, J.: Hybrid dendritic computing with kernel-lica applied to Alzheimer’s disease detection in mri. Neurocomputing 75(1), 72–77 (2012)
Cuingnet, R., Gerardin, E., Tessieras, J., Auzias, G., Lehéricy, S., Habert, M.-O., Chupin, M., Benali, H., Colliot, O., Alzheimer’s Disease Neuroimaging Initiative: Automatic classification of patients with Alzheimer’s disease from structural MRI: a comparison of ten methods using the adni database. Neuroimage 56(2), 766–781 (2010)
FMRIB Centre. Nuffield Department of Clinical Neurosciences. University of Oxford. Fmrib software library (2012)
Górriz, J.M., Segovia, F., Ramírez, J., Lassl, A., Salas-González, D.: GMM based SPECT image classification for the diagnosis of Alzheimer’s disease. Applied Soft Computing 11, 2313–2325 (2011)
Haykin, S.: Neural Networks, 2nd edn. Prentice-Hall (1999)
Kohonen, T.: Self-Organizing Maps. Springer (2001)
London Institute of Neurology (UCL). Statatistical parametric mapping (SPM), ver 8.0 (2012)
López, M., Ramírez, J., Górriz, J., Álvarez, I., Salas-González, D., Segovia, F., Chaves, R., Padilla, P., Gómez-Río, M.: Principal component analysis-based techniques and supervised classification schemes for the early detection of Alzheimer’s disease. Neurocomputing 74(8), 1260–1271 (2011)
Minoshima, S., Giordani, B., Berent, S., Frey, K.A., Foster, N.L., Kuhl, D.E.: Metabolic reduction in the posterior cingulate cortex in very early Alzheimer’s disease. Annals of Neurology 42, 85–94 (1997)
Ortiz, A., Górriz, J.M., Ramírez, J., Salas-González, D.: Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies. Applied Soft Computing (2012)
Padilla, P., López, M., Górriz, J.M., Ramírez, J., Salas-González, D., Álvarez, I., The Alzheimer’s Disease Neuroimaging Initiative: NMF-SVM based CAD tool applied to functional brain images for the diagnosis of Alzheimer’s disease. IEEE Transactions on medical imaging 2, 207–216 (2012)
Ramirez, J., Chaves, R., Gorriz, J.M., Lopez, M., Alvarez, I.A., Salas-Gonzalez, D., Segovia, F., Padilla, P.: Computer aided diagnosis of the Alzheimer’s disease combining spect-based feature selection and random forest classifiers. In: Proc. IEEE Nuclear Science Symp. Conf. Record (NSS/MIC), pp. 2738–2742 (2009)
Segovia, F., Górriz, J.M., Ramírez, J., Salas-González, D., Álvarez, I., López, M., Chaves, R., The Alzheimer’s Disease Neuroimaging Initiative: A comparative study of the feature extraction methods for the diagnosis of Alzheimer’s disease using the adni database. Neurocomputing 75, 64–71 (2012)
Stoeckel, J., Fung, G.: Svm feature selection for classification of spect images of Alzheimer’s disease using spatial information. In: Proc. Fifth IEEE Int. Data Mining Conf. (2005)
Termenon, M., Graña, M.: A two stage sequential ensemble applied to the classification of Alzheimer’s disease based on mri features. Neural Processing Letters 35(1), 1–12 (2012)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press (2009)
Vapnik, V.N.: Statistical Learning Theory. Wiley-Interscience (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ortiz García, A., Górriz, J.M., Ramírez, J., Salas-González, D. (2013). Automatic ROI Selection Using SOM Modelling in Structural Brain MRI. In: Ferrández Vicente, J.M., Álvarez Sánchez, J.R., de la Paz López, F., Toledo Moreo, F.J. (eds) Natural and Artificial Computation in Engineering and Medical Applications. IWINAC 2013. Lecture Notes in Computer Science, vol 7931. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38622-0_29
Download citation
DOI: https://doi.org/10.1007/978-3-642-38622-0_29
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38621-3
Online ISBN: 978-3-642-38622-0
eBook Packages: Computer ScienceComputer Science (R0)