A Two Stage Sequential Ensemble Applied to the Classification of Alzheimer’s Disease Based on MRI Features

We present a two stage sequential ensemble where data samples whose output from the first classifier fall in a low confidence output interval (LCOI) are processed by a second stage classifier. Training is composed of three processes: training the first classifier, determining the LCOI of the first classifier, and training the second classifier upon the data items whose output fall in the LCOI. The LCOI is determined varying a threshold on the false positive rate (FPR) and false negative rate (FNR) curves. We have tested the approach on a database of feature vectors for the classification of Alzheimer’s disease (AD) and control subjects extracted from structural magnetic resonance imaging (sMRI) data. In this paper, we focus on the combinations obtained when the first classifier is a relevance vector machine (RVM). Obtained results improve over previous results for this database.

[1]  Hans G. C. Tråvén,et al.  A neural network approach to statistical pattern classification by 'semiparametric' estimation of probability density functions , 1991, IEEE Trans. Neural Networks.

[2]  Wahyu Caesarendra,et al.  Machine degradation prognostic based on RVM and ARMA/GARCH model for bearing fault simulated data , 2010, 2010 Prognostics and System Health Management Conference.

[3]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevance Vector Machine , 2001 .

[4]  D. Selvathi,et al.  Performance Evaluation of Kernel Based Techniques for Brain MRI Data Classification , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[5]  Robert Sabourin,et al.  Overfitting cautious selection of classifier ensembles with genetic algorithms , 2009, Inf. Fusion.

[6]  Manuel Graña,et al.  Neurocognitive disorder detection based on feature vectors extracted from VBM analysis of structural MRI , 2011, Comput. Biol. Medicine.

[7]  Bernardete Ribeiro,et al.  Two-Level Hierarchical Hybrid SVM-RVM Classification Model , 2006, 2006 5th International Conference on Machine Learning and Applications (ICMLA'06).

[8]  Manuel Graña,et al.  Results of an Adaboost Approach on Alzheimer's Disease Detection on MRI , 2009, IWINAC.

[9]  Manuel Graña,et al.  On the Use of Morphometry Based Features for Alzheimer's Disease Detection on MRI , 2009, IWANN.

[10]  Clodoaldo Ap. M. Lima,et al.  Automatic EEG signal classification for epilepsy diagnosis with Relevance Vector Machines , 2009, Expert Syst. Appl..

[11]  Karl J. Friston,et al.  Voxel-Based Morphometry—The Methods , 2000, NeuroImage.

[12]  Nick C. Fox,et al.  Mapping the evolution of regional atrophy in Alzheimer's disease: Unbiased analysis of fluid-registered serial magnetic resonance images , 2002 .

[13]  Ludmila I Kuncheva,et al.  Classifier ensembles for fMRI data analysis: an experiment. , 2010, Magnetic resonance imaging.

[14]  Griselda J. Garrido,et al.  A voxel-based morphometry study of temporal lobe gray matter reductions in Alzheimer’s disease , 2003, Neurobiology of Aging.

[15]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[16]  Ethem Alpaydin,et al.  Incremental construction of classifier and discriminant ensembles , 2009, Inf. Sci..

[17]  Michael E. Tipping,et al.  Fast Marginal Likelihood Maximisation for Sparse Bayesian Models , 2003 .

[18]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[19]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  José A. Gámez,et al.  The impact of soft computing for the progress of artificial intelligence , 2011, Appl. Soft Comput..

[21]  Sheng Chen,et al.  The relevance vector machine technique for channel equalization application , 2001, IEEE Trans. Neural Networks.

[22]  G. Frisoni,et al.  Detection of grey matter loss in mild Alzheimer's disease with voxel based morphometry , 2002, Journal of neurology, neurosurgery, and psychiatry.

[23]  John G. Csernansky,et al.  Open Access Series of Imaging Studies (OASIS): Cross-sectional MRI Data in Young, Middle Aged, Nondemented, and Demented Older Adults , 2007, Journal of Cognitive Neuroscience.

[24]  V. Sadasivam,et al.  Notice of Violation of IEEE Publication PrinciplesECG Signal Interferences Removal Using Wavelet Based CSTD Technique , 2007, International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007).

[25]  Begüm Demir,et al.  Hyperspectral data classification using RVM with pre-segmentation and RANSAC , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[26]  José Manuel Ferrández,et al.  Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part II: Bioinspired Applications in Artificial and Natural Computation , 2009 .

[27]  T. Sejnowski,et al.  Relevance vector machine and support vector machine classifier analysis of scanning laser polarimetry retinal nerve fiber layer measurements. , 2005, Investigative ophthalmology & visual science.

[28]  Masoom A. Haider,et al.  Prostate cancer localization with multispectral MRI based on Relevance Vector Machines , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[29]  Nicolás García-Pedrajas,et al.  Constructing ensembles of classifiers using supervised projection methods based on misclassified instances , 2011, Expert Syst. Appl..

[30]  Manuel Graña,et al.  Classification Results of Artificial Neural Networks for Alzheimer's Disease Detection , 2009, IDEAL.

[31]  David C. Yen,et al.  Predicting stock returns by classifier ensembles , 2011, Appl. Soft Comput..

[32]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[33]  J. Baron,et al.  In Vivo Mapping of Gray Matter Loss with Voxel-Based Morphometry in Mild Alzheimer's Disease , 2001, NeuroImage.

[34]  G. Busatto,et al.  Voxel-based morphometry in Alzheimer’s disease , 2008, Expert review of neurotherapeutics.

[35]  Nick C Fox,et al.  Mapping the evolution of regional atrophy in Alzheimer's disease: Unbiased analysis of fluid-registered serial MRI , 2002, Proceedings of the National Academy of Sciences of the United States of America.