Manhua Liu

Ensemble sparse classification of Alzheimer's disease

The high-dimensional pattern classification methods, e.g., support vector machines (SVM), have been widely investigated for analysis of structural and functional brain images (such as magnetic resonance imaging (MRI)) to assist the diagnosis of Alzheimers disease (AD) including its prodromal stage, i.e., mild cognitive impairment (MCI). Most existing classification methods extract features from neuroimaging data and then construct a single classifier to perform classification. However, due to noise and small sample size of neuroimaging data, it is challenging to train only a global classifier that can be robust enough to achieve good classification performance. In this paper, instead of building a single global classifier, we propose a local patch-based subspace ensemble method which builds multiple individual classifiers based on different subsets of local patches and then combines them for more accurate and robust classification. Specifically, to capture the local spatial consistency, each brain image is partitioned into a number of local patches and a subset of patches is randomly selected from the patch pool to build a weak classifier. Here, the sparse representation-based classifier (SRC) method, which has shown to be effective for classification of image data (e.g., face), is used to construct each weak classifier. Then, multiple weak classifiers are combined to make the final decision. We evaluate our method on 652 subjects (including 198 AD patients, 225 MCI and 229 normal controls) from Alzheimers Disease Neuroimaging Initiative (ADNI) database using MR images. The experimental results show that our method achieves an accuracy of 90.8% and an area under the ROC curve (AUC) of 94.86% for AD classification and an accuracy of 87.85% and an AUC of 92.90% for MCI classification, respectively, demonstrating a very promising performance of our method compared with the state-of-the-art methods for AD/MCI classification using MR images.

Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis.

Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimers disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large‐scale classification problem can be divided into a set of small‐scale and easier‐to‐solve problems in a bottom‐up and local‐to‐global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low‐level classifiers to transform local imaging features and the inter‐region correlations into high‐level features. Then, we generate multiple high‐level classifiers, with each evaluating the high‐level features from the respective brain regions. Finally, we combine the outputs of all high‐level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimers Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0% and 85.3% for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state‐of‐the‐art classification methods. Hum Brain Mapp 35:1305–1319, 2014.

Hierarchical ensemble of multi-level classifiers for diagnosis of Alzheimer's disease

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.

Tree-Guided Sparse Coding for Brain Disease Classification

Neuroimage analysis based on machine learning technologies has been widely employed to assist the diagnosis of brain diseases such as Alzheimers disease and its prodromal stage--mild cognitive impairment. One of the major problems in brain image analysis involves learning the most relevant features from a huge set of raw imaging features, which are far more numerous than the training samples. This makes the tasks of both disease classification and interpretation extremely challenging. Sparse coding via L1 regularization, such as Lasso, can provide an effective way to select the most relevant features for alleviating the curse of dimensionality and achieving more accurate classification. However, the selected features may distribute randomly throughout the whole brain, although in reality disease-induced abnormal changes often happen in a few contiguous regions. To address this issue, we investigate a tree-guided sparse coding method to identify grouped imaging features in the brain regions for guiding disease classification and interpretation. Spatial relationships of the image structures are imposed during sparse coding with a tree-guided regularization. Our experimental results on the ADNI dataset show that the tree-guided sparse coding method not only achieves better classification accuracy, but also allows for more meaningful diagnosis of brain diseases compared with the conventional L1-regularized LASSO.

Identifying Informative Imaging Biomarkers via Tree Structured Sparse Learning for AD Diagnosis

Neuroimaging provides a powerful tool to characterize neurodegenerative progression and therapeutic efficacy in Alzheimer’s disease (AD) and its prodromal stage—mild cognitive impairment (MCI). However, since the disease pathology might cause different patterns of structural degeneration, which is not pre-known, it is still a challenging problem to identify the relevant imaging markers for facilitating disease interpretation and classification. Recently, sparse learning methods have been investigated in neuroimaging studies for selecting the relevant imaging biomarkers and have achieved very promising results on disease classification. However, in the standard sparse learning method, the spatial structure is often ignored, although it is important for identifying the informative biomarkers. In this paper, a sparse learning method with tree-structured regularization is proposed to capture patterns of pathological degeneration from fine to coarse scale, for helping identify the informative imaging biomarkers to guide the disease classification and interpretation. Specifically, we first develop a new tree construction method based on the hierarchical agglomerative clustering of voxel-wise imaging features in the whole brain, by taking into account their spatial adjacency, feature similarity and discriminability. In this way, the complexity of all possible multi-scale spatial configurations of imaging features can be reduced to a single tree of nested regions. Second, we impose the tree-structured regularization on the sparse learning to capture the imaging structures, and then use them for selecting the most relevant biomarkers. Finally, we train a support vector machine (SVM) classifier with the selected features to make the classification. We have evaluated our proposed method by using the baseline MR images of 830 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, which includes 198 AD patients, 167 progressive MCI (pMCI), 236 stable MCI (sMCI), and 229 normal controls (NC). Our experimental results show that our method can achieve accuracies of 90.2xa0%, 87.2xa0%, and 70.7xa0% for classifications of AD vs. NC, pMCI vs. NC, and pMCI vs. sMCI, respectively, demonstrating promising performance compared with other state-of-the-art methods.

Kernel-based multi-task joint sparse classification for Alzheimer'S disease

Multi-modality imaging provides complementary information for diagnosis of neurodegenerative disorders such as Alzheimers disease (AD) and its prodrome, mild cognitive impairment (MCI). In this paper, we propose a kernel-based multi-task sparse representation model to combine the strengths of MRI and PET imaging features for improved classification of AD. Sparse representation based classification seeks to represent the testing data with a sparse linear combination of training data. Here, our approach allows information from different imaging modalities to be used for enforcing class level joint sparsity via multi-task learning. Thus the common most representative classes in the training samples for all modalities are jointly selected to reconstruct the testing sample. We further improve the discriminatory power by extending the framework to the reproducing kernel Hilbert space (RKHS) so that nonlinearity in the features can be captured for better classification. Experiments on Alzheimers Disease Neuroimaging Initiative database shows that our proposed method can achieve 93.3% and 78.9% accuracy for classification of AD and MCI from healthy controls, respectively, demonstrating promising performance in AD study.

Atlas construction via dictionary learning and group sparsity

Atlas construction generally includes first an image registration step to normalize all images into a common space and then an atlas building step to fuse all the aligned images. Although numerous atlas construction studies have been performed to improve the accuracy of image registration step, simple averaging or weighted averaging is often used for the atlas building step. In this paper, we propose a novel patch-based sparse representation method for atlas construction, especially for the atlas building step. By taking advantage of local sparse representation, more distinct anatomical details can be revealed in the built atlas. Also, together with the constraint on group structure of representations and the use of overlapping patches, anatomical consistency between neighboring patches can be ensured. The proposed method has been applied to 73 neonatal MR images with poor spatial resolution and low tissue contrast, for building unbiased neonatal brain atlas. Experimental results demonstrate that the proposed method can enhance the quality of built atlas by discovering more anatomical details especially in cortical regions, and perform better in a neonatal data normalization application, compared to other existing start-of-the-art nonlinear neonatal brain atlases.

Multi-task Sparse Classifier for Diagnosis of MCI Conversion to AD with Longitudinal MR Images

Mild cognitive impairment (MCI) patients are at a high risk of turning into Alzheimers disease (AD) within years. But it is known that not all MCI patients will progress to AD. Therefore, it is of great interest to accurately diagnose whether a MCI patient will convert to AD (namely MCI converter; MCI-C) or not (namely MCI non-converter; MCI-NC), for early diagnosis and proper treatment. In this paper, we propose a multi-task sparse representation classifier to discriminate between MCI-C and MCI-NC utilizing longitudinal neuroimaging data. Unlike the previous methods that explicitly combined the longitudinal information in a feature domain, thus requiring the same number of measurements in time, the proposed method is not limited to the availability of the data. Specifically, by means of multi-task learning, we impose a group constraint that the same training samples, ideally belonging to the same class, are used to represent the longitudinal feature vectors across time points. Then we utilize a sparse representation classifier for label decision. From a machine learning perspective, the proposed method can be considered as the combination of the generative and discriminative methods, which are known to be effective in classification enhancement. In our experiments on magnetic resonance brain images of 349 MCI subjects (164 MCI-C and 185 MCI-NC) from ADNI database, we demonstrate the validity of the proposed method, which also outperforms the competing methods.

Brain Disease Classification and Progression Using Machine Learning Techniques

In the past two decades, many machine learning techniques have been applied to the detection of neurologic or neuropsychiatric disorders such as Alzheimer’s disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI), based on different modalities of biomarkers including structural magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), and cerebrospinal fluid (CSF), etc. This chapter presents some latest developments in application of machine learning tools to AD and MCI diagnosis and progression. We divide our discussions into two parts, pattern classification and pattern regression. We will discuss how the cortical morphological change patterns and the ensemble sparse classifiers can be used for pattern classification and then discuss how the multi-modal multi-task learning (M3T) and the semi-supervised multi-modal relevance vector regression can be applied to pattern regression.