Luping Zhou

Multimodal Classification of Alzheimer’s Disease and Mild Cognitive Impairment

Effective and accurate diagnosis of Alzheimers disease (AD), as well as its prodromal stage (i.e., mild cognitive impairment (MCI)), has attracted more and more attention recently. So far, multiple biomarkers have been shown to be sensitive to the diagnosis of AD and MCI, i.e., structural MR imaging (MRI) for brain atrophy measurement, functional imaging (e.g., FDG-PET) for hypometabolism quantification, and cerebrospinal fluid (CSF) for quantification of specific proteins. However, most existing research focuses on only a single modality of biomarkers for diagnosis of AD and MCI, although recent studies have shown that different biomarkers may provide complementary information for the diagnosis of AD and MCI. In this paper, we propose to combine three modalities of biomarkers, i.e., MRI, FDG-PET, and CSF biomarkers, to discriminate between AD (or MCI) and healthy controls, using a kernel combination method. Specifically, ADNI baseline MRI, FDG-PET, and CSF data from 51AD patients, 99 MCI patients (including 43 MCI converters who had converted to AD within 18 months and 56 MCI non-converters who had not converted to AD within 18 months), and 52 healthy controls are used for development and validation of our proposed multimodal classification method. In particular, for each MR or FDG-PET image, 93 volumetric features are extracted from the 93 regions of interest (ROIs), automatically labeled by an atlas warping algorithm. For CSF biomarkers, their original values are directly used as features. Then, a linear support vector machine (SVM) is adopted to evaluate the classification accuracy, using a 10-fold cross-validation. As a result, for classifying AD from healthy controls, we achieve a classification accuracy of 93.2% (with a sensitivity of 93% and a specificity of 93.3%) when combining all three modalities of biomarkers, and only 86.5% when using even the best individual modality of biomarkers. Similarly, for classifying MCI from healthy controls, we achieve a classification accuracy of 76.4% (with a sensitivity of 81.8% and a specificity of 66%) for our combined method, and only 72% even using the best individual modality of biomarkers. Further analysis on MCI sensitivity of our combined method indicates that 91.5% of MCI converters and 73.4% of MCI non-converters are correctly classified. Moreover, we also evaluate the classification performance when employing a feature selection method to select the most discriminative MR and FDG-PET features. Again, our combined method shows considerably better performance, compared to the case of using an individual modality of biomarkers.

Discriminant analysis of longitudinal cortical thickness changes in Alzheimer’s disease using dynamic and network features

Neuroimage measures from magnetic resonance (MR) imaging, such as cortical thickness, have been playing an increasingly important role in searching for biomarkers of Alzheimers disease (AD). Recent studies show that, AD, mild cognitive impairment (MCI) and normal control (NC) can be distinguished with relatively high accuracy using the baseline cortical thickness. With the increasing availability of large longitudinal datasets, it also becomes possible to study the longitudinal changes of cortical thickness and their correlation with the development of pathology in AD. In this study, the longitudinal cortical thickness changes of 152 subjects from 4 clinical groups (AD, NC, Progressive-MCI and Stable-MCI) selected from Alzheimers Disease Neuroimaging Initiative (ADNI) are measured by our recently developed 4 D (spatial+temporal) thickness measuring algorithm. It is found that the 4 clinical groups demonstrate very similar spatial distribution of grey matter (GM) loss on cortex. To fully utilize the longitudinal information and better discriminate the subjects from 4 groups, especially between Stable-MCI and Progressive-MCI, 3 different categories of features are extracted for each subject, i.e., (1) static cortical thickness measures computed from the baseline and endline, (2) cortex thinning dynamics, such as the thinning speed (mm/year) and the thinning ratio (endline/baseline), and (3) network features computed from the brain network constructed based on the correlation between the longitudinal thickness changes of different regions of interest (ROIs). By combining the complementary information provided by features from the 3 categories, 2 classifiers are trained to diagnose AD and to predict the conversion to AD in MCI subjects, respectively. In the leave-one-out cross-validation, the proposed method can distinguish AD patients from NC at an accuracy of 96.1%, and can detect 81.7% (AUC = 0.875) of the MCI converters 6 months ahead of their conversions to AD. Also, by analyzing the brain network built via longitudinal cortical thickness changes, a significant decrease (p < 0.02) of the network clustering coefficient (associated with the development of AD pathology) is found in the Progressive-MCI group, which indicates the degenerated wiring efficiency of the brain network due to AD. More interestingly, the decreasing of network clustering coefficient of the olfactory cortex region was also found in the AD patients, which suggests olfactory dysfunction. Although the smell identification test is not performed in ADNI, this finding is consistent with other AD-related olfactory studies.

Cross-sectional and Longitudinal Analysis of the Relationship Between Aβ Deposition, Cortical Thickness, and Memory in Cognitively Unimpaired Individuals and in Alzheimer Disease

IMPORTANCE β-amyloid (Aβ) deposition is one of the hallmarks of Alzheimer disease. Aβ deposition accelerates gray matter atrophy at early stages of the disease even before objective cognitive impairment is manifested. Identification of at-risk individuals at the presymptomatic stage has become a major research interest because it will allow early therapeutic interventions before irreversible synaptic and neuronal loss occur. We aimed to further characterize the cross-sectional and longitudinal relationship between Aβ deposition, gray matter atrophy, and cognitive impairment. OBJECTIVE To investigate the topographical relationship of Aβ deposition, gray matter atrophy, and memory impairment in asymptomatic individuals with Alzheimer disease pathology as assessed by Pittsburgh compound B positron emission tomography (PiB-PET). DESIGN Regional analysis was performed on the cortical surface to relate cortical thickness to PiB retention and episodic memory. SETTING The Australian Imaging, Biomarkers, and Lifestyle Study of Aging, Austin Hospital, Melbourne, Australia. PARTICIPANTS Ninety-three healthy elderly control subjects (NCs) and 40 patients with Alzheimer disease from the Australian Imaging, Biomarkers, and Lifestyle Study of Aging cohort. INTERVENTION Participants underwent neuropsychological evaluation as well as magnetic resonance imaging and PiB-PET scans. Fifty-four NCs underwent repeated scans and neuropsychological evaluation 18 and 36 months later. MAIN OUTCOMES AND MEASURES Correlations between cortical thickness, PiB retention, and episodic memory. RESULTS There was a significant reduction in cortical thickness in the precuneus and hippocampus associated with episodic memory impairment in the NC PiB-positive (NC+) group when compared with the NC- group. Cortical thickness was also correlated negatively with neocortical PiB in the NC+ group. Longitudinal analysis showed a faster rate of gray matter (GM) atrophy in the temporal lobe and the hippocampi of the NC+ group. Over time, GM atrophy became more extensive in the NC+ group, especially in the temporal lobe. CONCLUSIONS AND RELEVANCE In asymptomatic individuals, Aβ deposition is associated with GM atrophy and memory impairment. The earliest signs of GM atrophy were detected in the hippocampus and the posterior cingulate and precuneus regions, and with disease progression, atrophy became more extensive in the temporal lobes. These findings support the notion that Aβ deposition is not a benign process and that interventions with anti-Aβ therapy at these early stages have a higher chance to be effective.

Hierarchical anatomical brain networks for MCI prediction: Revisiting volumetric measures

Owning to its clinical accessibility, T1-weighted MRI (Magnetic Resonance Imaging) has been extensively studied in the past decades for prediction of Alzheimers disease (AD) and mild cognitive impairment (MCI). The volumes of gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) are the most commonly used measurements, resulting in many successful applications. It has been widely observed that disease-induced structural changes may not occur at isolated spots, but in several inter-related regions. Therefore, for better characterization of brain pathology, we propose in this paper a means to extract inter-regional correlation based features from local volumetric measurements. Specifically, our approach involves constructing an anatomical brain network for each subject, with each node representing a Region of Interest (ROI) and each edge representing Pearson correlation of tissue volumetric measurements between ROI pairs. As second order volumetric measurements, network features are more descriptive but also more sensitive to noise. To overcome this limitation, a hierarchy of ROIs is used to suppress noise at different scales. Pairwise interactions are considered not only for ROIs with the same scale in the same layer of the hierarchy, but also for ROIs across different scales in different layers. To address the high dimensionality problem resulting from the large number of network features, a supervised dimensionality reduction method is further employed to embed a selected subset of features into a low dimensional feature space, while at the same time preserving discriminative information. We demonstrate with experimental results the efficacy of this embedding strategy in comparison with some other commonly used approaches. In addition, although the proposed method can be easily generalized to incorporate other metrics of regional similarities, the benefits of using Pearson correlation in our application are reinforced by the experimental results. Without requiring new sources of information, our proposed approach improves the accuracy of MCI prediction from (of conventional volumetric features) to (of hierarchical network features), evaluated using data sets randomly drawn from the ADNI (Alzheimers Disease Neuroimaging Initiative) dataset.

Multiple Kernel Learning in the Primal for Multimodal Alzheimer’s Disease Classification

To achieve effective and efficient detection of Alzheimers disease (AD), many machine learning methods have been introduced into this realm. However, the general case of limited training samples, as well as different feature representations typically makes this problem challenging. In this paper, we propose a novel multiple kernel-learning framework to combine multimodal features for AD classification, which is scalable and easy to implement. Contrary to the usual way of solving the problem in the dual, we look at the optimization from a new perspective. By conducting Fourier transform on the Gaussian kernel, we explicitly compute the mapping function, which leads to a more straightforward solution of the problem in the primal. Furthermore, we impose the mixed L21 norm constraint on the kernel weights, known as the group lasso regularization, to enforce group sparsity among different feature modalities. This actually acts as a role of feature modality selection, while at the same time exploiting complementary information among different kernels. Therefore, it is able to extract the most discriminative features for classification. Experiments on the ADNI dataset demonstrate the effectiveness of the proposed method.

Feature Selection With Redundancy-Constrained Class Separability

Scatter-matrix-based class separability is a simple and efficient feature selection criterion in the literature. However, the conventional trace-based formulation does not take feature redundancy into account and is prone to selecting a set of discriminative but mutually redundant features. In this brief, we first theoretically prove that in the context of this trace-based criterion the existence of sufficiently correlated features can always prevent selecting the optimal feature set. Then, on top of this criterion, we propose the redundancy-constrained feature selection (RCFS). To ensure the algorithms efficiency and scalability, we study the characteristic of the constraints with which the resulted constrained 0-1 optimization can be efficiently and globally solved. By using the totally unimodular (TUM) concept in integer programming, a necessary condition for such constraints is derived. This condition reveals an interesting special case in which qualified redundancy constraints can be conveniently generated via a clustering of features. We study this special case and develop an efficient feature selection approach based on Dinkelbachs algorithm. Experiments on benchmark data sets demonstrate the superior performance of our approach to those without redundancy constraints.

HEp-2 Cell Image Classification With Deep Convolutional Neural Networks

Efficient Human Epithelial-2 cell image classification can facilitate the diagnosis of many autoimmune diseases. This paper proposes an automatic framework for this classification task, by utilizing the deep convolutional neural networks (CNNs) which have recently attracted intensive attention in visual recognition. In addition to describing the proposed classification framework, this paper elaborates several interesting observations and findings obtained by our investigation. They include the important factors that impact network design and training, the role of rotation-based data augmentation for cell images, the effectiveness of cell image masks for classification, and the adaptability of the CNN-based classification system across different datasets. Extensive experimental study is conducted to verify the above findings and compares the proposed framework with the well-established image classification models in the literature. The results on benchmark datasets demonstrate that 1) the proposed framework can effectively outperform existing models by properly applying data augmentation, 2) our CNN-based framework has excellent adaptability across different datasets, which is highly desirable for cell image classification under varying laboratory settings. Our system is ranked high in the cell image classification competition hosted by ICPR 2014.

MR-Less Surface-Based Amyloid Assessment Based on 11C PiB PET

Background β-amyloid (Aβ) plaques in brains grey matter (GM) are one of the pathological hallmarks of Alzheimers disease (AD), and can be imaged in vivo using Positron Emission Tomography (PET) with 11C or 18F radiotracers. Estimating Aβ burden in cortical GM has been shown to improve diagnosis and monitoring of AD. However, lacking structural information in PET images requires such assessments to be performed with anatomical MRI scans, which may not be available at different clinical settings or being contraindicated for particular reasons. This study aimed to develop an MR-less Aβ imaging quantification method that requires only PET images for reliable Aβ burden estimations. Materials and Methods The proposed method has been developed using a multi-atlas based approach on 11C-PiB scans from 143 subjects (75 PiB+ and 68 PiB- subjects) in AIBL study. A subset of 20 subjects (PET and MRI) were used as atlases: 1) MRI images were co-registered with tissue segmentation; 2) 3D surface at the GM-WM interfacing was extracted and registered to a canonical space; 3) Mean PiB retention within GM was estimated and mapped to the surface. For other participants, each atlas PET image (and surface) was registered to the subjects PET image for PiB estimation within GM. The results are combined by subject-specific atlas selection and Bayesian fusion to generate estimated surface values. Results All PiB+ subjects (N = 75) were highly correlated between the MR-dependent and the PET-only methods with Intraclass Correlation (ICC) of 0.94, and an average relative difference error of 13% (or 0.23 SUVR) per surface vertex. All PiB- subjects (N = 68) revealed visually akin patterns with a relative difference error of 16% (or 0.19 SUVR) per surface vertex. Conclusion The demonstrated accuracy suggests that the proposed method could be an effective clinical inspection tool for Aβ imaging scans when MRI images are unavailable.

Beyond Covariance: Feature Representation with Nonlinear Kernel Matrices

Covariance matrix has recently received increasing attention in computer vision by leveraging Riemannian geometry of symmetric positive-definite (SPD) matrices. Originally proposed as a region descriptor, it has now been used as a generic representation in various recognition tasks. However, covariance matrix has shortcomings such as being prone to be singular, limited capability in modeling complicated feature relationship, and having a fixed form of representation. This paper argues that more appropriate SPD-matrix-based representations shall be explored to achieve better recognition. It proposes an open framework to use the kernel matrix over feature dimensions as a generic representation and discusses its properties and advantages. The proposed framework significantly elevates covariance representation to the unlimited opportunities provided by this new representation. Experimental study shows that this representation consistently outperforms its covariance counterpart on various visual recognition tasks. In particular, it achieves significant improvement on skeleton-based human action recognition, demonstrating the state-of-the-art performance over both the covariance and the existing non-covariance representations.

A Fast Algorithm for Creating a Compact and Discriminative Visual Codebook

In patch-based object recognition, using a compact visual codebook can boost computational efficiency and reduce memory cost. Nevertheless, compared with a large-sized codebook, it also risks the loss of discriminative power. Moreover, creating a compact visual codebook can be very time-consuming, especially when the number of initial visual words is large. In this paper, to minimize its loss of discriminative power, we propose an approach to build a compact visual codebook by maxi- mally preserving the separability of the object classes. Furthermore, a fast algorithm is designed to accomplish this task effortlessly, which can hierarchically merge 10,000 visual words down to 2 in ninety seconds. Experimental study shows that the compact visual codebook created in this way can achieve excellent classification performance even after a considerable reduction in size.