Machine Learning in Medical Imaging

Pattern classification methods have been widely studied for analysis of brain images to decode the disease states, such as diagnosis of Alzheimer's disease (AD). Most existing methods aimed to extract discriminative features from neuroimaging data and then build a supervised classifier for classification. However, due to the rich imaging features and small sample size of neuroimaging data, it is still challenging to make use of features to achieve good classification performance. In this paper, we propose a hierarchical ensemble classification algorithm to gradually combine the features and decisions into a unified model for more accurate classification. Specifically, a number of low-level classifiers are first built to transform the rich imaging and correlation-context features of brain image into more compact high-level features with supervised learning. Then, multiple high-level classifiers are generated, with each evaluating the high-level features of different brain regions. Finally, all high-level classifiers are combined to make final decision. Our method is evaluated using MR brain images on 427 subjects (including 198 AD patients and 229 normal controls) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that our method achieves an accuracy of 92.04% and an AUC (area under the ROC curve) of 0.9518 for AD classification, demonstrating very promising classification performance.

[1]  Stephen C. Strother,et al.  Support vector machines for temporal classification of block design fMRI data , 2005, NeuroImage.

[2]  Dinggang Shen,et al.  COMPARE: Classification of Morphological Patterns Using Adaptive Regional Elements , 2007, IEEE Transactions on Medical Imaging.

[3]  Christian Keysers,et al.  The impact of certain methodological choices on multivariate analysis of fMRI data with support vector machines , 2011, NeuroImage.

[4]  Alejandro F. Frangi,et al.  Characterizing Pathological Deviations from Normality Using Constrained Manifold-Learning , 2011, MICCAI.

[5]  Brian C. Lovell,et al.  Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching , 2011, CVPR 2011.

[6]  Sharon L. Thompson-Schill,et al.  The advantage of brief fMRI acquisition runs for multi-voxel pattern detection across runs , 2012, NeuroImage.

[7]  Dinggang Shen,et al.  Very High-Resolution Morphometry Using Mass-Preserving Deformations and HAMMER Elastic Registration , 2003, NeuroImage.

[8]  Jeremy Freeman,et al.  Orientation Decoding Depends on Maps, Not Columns , 2011, The Journal of Neuroscience.

[9]  Guang-Zhong Yang,et al.  Predictive cardiac motion modeling and correction with partial least squares regression , 2004, IEEE Transactions on Medical Imaging.

[10]  R. Bakshi,et al.  Fluid-attenuated inversion recovery magnetic resonance imaging detects cortical and juxtacortical multiple sclerosis lesions. , 2001, Archives of neurology.

[11]  Daniel Rueckert,et al.  A Combined Manifold Learning Analysis of Shape and Appearance to Characterize Neonatal Brain Development , 2011, IEEE Transactions on Medical Imaging.

[12]  Marie Chupin,et al.  Automatic classi fi cation of patients with Alzheimer ' s disease from structural MRI : A comparison of ten methods using the ADNI database , 2010 .

[13]  Clifford R. Jack,et al.  Alzheimer's disease diagnosis in individual subjects using structural MR images: Validation studies , 2008, NeuroImage.

[14]  Dinggang Shen,et al.  Hierarchical Anatomical Brain Networks for MCI Prediction: Revisiting Volumetric Measures , 2011, PloS one.

[15]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[16]  Colin Studholme,et al.  Human brain labeling using image similarities , 2011, CVPR 2011.

[17]  Nassir Navab,et al.  Natural gradients for deformable registration , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Bogdan Gabrys,et al.  Classifier selection for majority voting , 2005, Inf. Fusion.

[19]  Dinggang Shen,et al.  A General Fast Registration Framework by Learning Deformation–Appearance Correlation , 2012, IEEE Transactions on Image Processing.

[20]  Xin Yao,et al.  Diversity creation methods: a survey and categorisation , 2004, Inf. Fusion.

[21]  Ross T. Whitaker,et al.  Manifold modeling for brain population analysis , 2010, Medical Image Anal..

[22]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[23]  Bernhard Hemmer,et al.  An automated tool for detection of FLAIR-hyperintense white-matter lesions in Multiple Sclerosis , 2012, NeuroImage.

[24]  K. Ishii,et al.  Voxel-based morphometric comparison between early- and late-onset mild Alzheimer's disease and assessment of diagnostic performance of z score images. , 2005, AJNR. American journal of neuroradiology.

[25]  Moo K. Chung,et al.  Spatially augmented LPboosting for AD classification with evaluations on the ADNI dataset , 2009, NeuroImage.

[26]  S. Resnick,et al.  Detection of prodromal Alzheimer's disease via pattern classification of magnetic resonance imaging , 2008, Neurobiology of Aging.

[27]  X. Wu,et al.  Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI , 2008, NeuroImage.

[28]  Robert P. W. Duin,et al.  Dissimilarity-Based Detection of Schizophrenia , 2010, 2010 First Workshop on Brain Decoding: Pattern Recognition Challenges in Neuroimaging.

[29]  A. Kouzani,et al.  Segmentation of multiple sclerosis lesions in MR images: a review , 2011, Neuroradiology.

[30]  Josien P. W. Pluim,et al.  Preconditioned Stochastic Gradient Descent Optimisation for Monomodal Image Registration , 2011, MICCAI.

[31]  Alan C. Evans,et al.  A nonparametric method for automatic correction of intensity nonuniformity in MRI data , 1998, IEEE Transactions on Medical Imaging.

[32]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .