Spatially augmented LPBoosting for AD classification with evaluations on the ADNI dataset

Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI 53706, USA.
NeuroImage (Impact Factor: 6.36). 06/2009; 48(1):138-49. DOI: 10.1016/j.neuroimage.2009.05.056
Source: PubMed


Structural and functional brain images are playing an important role in helping us understand the changes associated with neurological disorders such as Alzheimer's disease (AD). Recent efforts have now started investigating their utility for diagnosis purposes. This line of research has shown promising results where methods from machine learning (such as Support Vector Machines) have been used to identify AD-related patterns from images, for use in diagnosing new individual subjects. In this paper, we propose a new framework for AD classification which makes use of the Linear Program (LP) boosting with novel additional regularization based on spatial "smoothness" in 3D image coordinate spaces. The algorithm formalizes the expectation that since the examples for training the classifier are images, the voxels eventually selected for specifying the decision boundary must constitute spatially contiguous chunks, i.e., "regions" must be preferred over isolated voxels. This prior belief turns out to be useful for significantly reducing the space of possible classifiers and leads to substantial benefits in generalization. In our method, the requirement of spatial contiguity (of selected discriminating voxels) is incorporated within the optimization framework directly. Other methods have made use of similar biases as a pre- or post-processing step, however, our model incorporates this emphasis on spatial smoothness directly into the learning step. We report on extensive evaluations of our algorithm on MR and FDG-PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, and discuss the relationship of the classification output with the clinical and cognitive biomarker data available within ADNI.

Download full-text


Available from: Moo K Chung, Feb 01, 2016
  • Source
    • "Thus, it is critical for early and accurate diagnosis of AD, especially in its early stage [i.e., mild cognitive impairment (MCI)], for timely therapy and possible delay of the progression [Li et al., 2012; Wee et al., 2012; Wee et al., 2014; Zhang et al., 2012]. Over the past decade, advances in magnetic resonance imaging (MRI) have enabled significant progress in understanding neural changes that are related to AD and other diseases [Chan et al., 2003; Chen et al., 2009b; Davatzikos et al., 2008; Fan et al., 2008; Fox et al., 1996; Hinrichs et al., 2009; Magnin et al., 2009; Mueller et al., 2005; Shi et al., 2012]. By directly accessing the structures provided by MRI, brain morphometry can identify the anatomical differences between populations of AD patients and normal controls (NC) for assisting diagnosis and also evaluating the progression of MCI [Dickerson et al., 2001; Fox et al., 1996; Jack et al., 2008; Wang et al., 2014]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Multi-atlas based methods have been recently used for classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Compared with traditional single-atlas based methods, multiatlas based methods adopt multiple predefined atlases and thus are less biased by a certain atlas. However, most existing multiatlas based methods simply average or concatenate the features from multiple atlases, which may ignore the potentially important diagnosis information related to the anatomical differences among different atlases. In this paper, we propose a novel view (i.e., atlas) centralized multi-atlas classification method, which can better exploit useful information in multiple feature representations from different atlases. Specifically, all brain images are registered onto multiple atlases individually, to extract feature representations in each atlas space. Then, the proposed view-centralized multi-atlas feature selection method is used to select the most discriminative features from each atlas with extra guidance from other atlases. Next, we design a support vector machine (SVM) classifier using the selected features in each atlas space. Finally, we combine multiple SVM classifiers for multiple atlases through a classifier ensemble strategy for making a final decision. We have evaluated our method on 459 subjects [including 97 AD, 117 progressive MCI (p-MCI), 117 stable MCI (s-MCI), and 128 normal controls (NC)] from the Alzheimer's Disease Neuroimaging Initiative database, and achieved an accuracy of 92.51% for AD versus NC classification and an accuracy of 78.88% for p-MCI versus s-MCI classification. These results demonstrate that the proposed method can significantly outperform the previous multi-atlas based classification methods. Hum Brain Mapp, 2015. © 2014 Wiley Periodicals, Inc.
    Full-text · Article · Jan 2015 · Human Brain Mapping
  • Source
    • "Recently, a number of machine learning and pattern classification methods have been widely used in neuroimaging analysis of AD and MCI, including both group comparison (i.e., between clinically different groups) and individual classification [Jie et al., 2014b; Orru et al., 2012; Ye et al., 2011]. Early studies mainly focus on extracting features [e.g., based on regions of interest (ROIs) or voxels] from single imaging modality such as structural magnetic resonance imaging (MRI) [Chincarini et al., 2011; Fan et al., 2008a,b; Liu et al., 2012; Oliveira et al., 2010; Westman et al., 2011] and fluorodeoxyglucose positron emission tomography (FDG-PET) [Drzezga et al., 2003; Foster et al., 2007; Higdon et al., 2004; Hinrichs et al., 2009], and so forth. More recently, researchers have begun to integrate multiple imaging modalities to further improve the accuracy of disease diagnosis [Hinrichs et al., 2011; Zhang et al., 2011; Zhou et al., 2013]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Multimodality based methods have shown great advantages in classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Recently, multitask feature selection methods are typically used for joint selection of common features across multiple modalities. However, one disadvantage of existing multimodality based methods is that they ignore the useful data distribution information in each modality, which is essential for subsequent classification. Accordingly, in this paper we propose a manifold regularized multitask feature learning method to preserve both the intrinsic relatedness among multiple modalities of data and the data distribution information in each modality. Specifically, we denote the feature learning on each modality as a single task, and use group-sparsity regularizer to capture the intrinsic relatedness among multiple tasks (i.e., modalities) and jointly select the common features from multiple tasks. Furthermore, we introduce a new manifold-based Laplacian regularizer to preserve the data distribution information from each task. Finally, we use the multikernel support vector machine method to fuse multimodality data for eventual classification. Conversely, we also extend our method to the semisupervised setting, where only partial data are labeled. We evaluate our method using the baseline magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), and cerebrospinal fluid (CSF) data of subjects from AD neuroimaging initiative database. The experimental results demonstrate that our proposed method can not only achieve improved classification performance, but also help to discover the disease-related brain regions useful for disease diagnosis. Hum Brain Mapp, 2014. © 2014 Wiley Periodicals, Inc.
    Full-text · Article · Oct 2014 · Human Brain Mapping
  • Source
    • "Comparative studies of various methods are presented in [11] [12] used for Alzheimer's disease identification and classification. Various classification techniques have been used for identification of structural changes in brain that can be possible indicators of the disease with the help of neuroimaging data [13] [14] [15]. The studies mentioned in literature are either based on region of interest (ROI) [16] or voxel-based morphometry (VBM) [17]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Structural brain imaging is playing a vital role in identification of changes that occur in brain associated with Alzheimer's disease. This paper proposes an automated image processing based approach for the identification of AD from MRI of the brain. The proposed approach is novel in a sense that it has higher specificity/accuracy values despite the use of smaller feature set as compared to existing approaches. Moreover, the proposed approach is capable of identifying AD patients in early stages. The dataset selected consists of 85 age and gender matched individuals from OASIS database. The features selected are volume of GM, WM, and CSF and size of hippocampus. Three different classification models (SVM, MLP, and J48) are used for identification of patients and controls. In addition, an ensemble of classifiers, based on majority voting, is adopted to overcome the error caused by an independent base classifier. Ten-fold cross validation strategy is applied for the evaluation of our scheme. Moreover, to evaluate the performance of proposed approach, individual features and combination of features are fed to individual classifiers and ensemble based classifier. Using size of left hippocampus as feature, the accuracy achieved with ensemble of classifiers is 93.75%, with 100% specificity and 87.5% sensitivity.
    Full-text · Article · Sep 2014 · Computational and Mathematical Methods in Medicine
Show more