Brain Connectivity Based Prediction of Alzheimer's Disease in Patients With Mild Cognitive Impairment Based on Multi-Modal Images

The Coupled Representation of Hierarchical Features for Mild Cognitive Impairment and Alzheimer's Disease Classification

Structural magnetic resonance imaging (MRI) features have played an increasingly crucial role in discriminating patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI) from normal controls (NC). However, the large number of structural MRI studies only extracted low-level neuroimaging features or simply concatenated multitudinous features while ignoring the interregional covariate information. The appropriate representation and integration of multilevel features will be preferable for the precise discrimination in the progression of AD. In this study, we proposed a novel inter-coupled feature representation method and built an integration model considering the two-level (the regions of interest (ROI) level and the network level) coupled features based on structural MRI data. For the intra-coupled interactions about the network-level features, we performed the ROI-level (intra- and inter-) coupled interaction within each network by feature expansion and coupling learning. For the inter-coupled interaction of the network-level features, we measured the coupled relationships among different networks via Canonical correlation analysis. We evaluated the classification performance using coupled feature representations on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results showed that the coupled integration model with hierarchical features achieved the optimal classification performance with an accuracy of 90.44% for AD and NC groups, with an accuracy of 87.72% for the MCI converter (MCI-c) and MCI non-converter (MCI-nc) groups. These findings suggested that our two-level coupled interaction representation of hierarchical features has been the effective means for the precise discrimination of MCI-c from MCI-nc groups and, therefore, helpful in the characterization of different AD courses.

Wavelet-Based Fractal Analysis of rs-fMRI for Classification of Alzheimer's Disease

The resting-state functional magnetic resonance imaging (rs-fMRI) modality has gained widespread acceptance as a promising method for analyzing a variety of neurological and psychiatric diseases. It is established that resting-state neuroimaging data exhibit fractal behavior, manifested in the form of slow-decaying auto-correlation and power-law scaling of the power spectrum across low-frequency components. With this property, the rs-fMRI signal can be broken down into fractal and nonfractal components. The fractal nature originates from several sources, such as cardiac fluctuations, respiration and system noise, and carries no information on the brain’s neuronal activities. As a result, the conventional correlation of rs-fMRI signals may not accurately reflect the functional dynamic of spontaneous neuronal activities. This problem can be solved by using a better representation of neuronal activities provided by the connectivity of nonfractal components. In this work, the nonfractal connectivity of rs-fMRI is used to distinguish Alzheimer’s patients from healthy controls. The automated anatomical labeling (AAL) atlas is used to extract the blood-oxygenation-level-dependent time series signals from 116 brain regions, yielding a 116 × 116 nonfractal connectivity matrix. From this matrix, significant connections evaluated using the p-value are selected as an input to a classifier for the classification of Alzheimer’s vs. normal controls. The nonfractal-based approach provides a good representation of the brain’s neuronal activity. It outperformed the fractal and Pearson-based connectivity approaches by 16.4% and 17.2%, respectively. The classification algorithm developed based on the nonfractal connectivity feature and support vector machine classifier has shown an excellent performance, with an accuracy of 90.3% and 83.3% for the XHSLF dataset and ADNI dataset, respectively. For further validation of our proposed work, we combined the two datasets (XHSLF+ADNI) and still received an accuracy of 90.2%. The proposed work outperformed the recently published work by a margin of 8.18% and 11.2%, respectively.

Mitochondrial Deficits With Neural and Social Damage in Early-Stage Alzheimer's Disease Model Mice

Alzheimer’s disease (AD) is the most common neurodegenerative disorder worldwide. Mitochondrial dysfunction is thought to be an early event in the onset and progression of AD; however, the precise underlying mechanisms remain unclear. In this study, we investigated mitochondrial proteins involved in organelle dynamics, morphology and energy production in the medial prefrontal cortex (mPFC) and hippocampus (HIPP) of young (1∼2 months), adult (4∼5 months) and aged (9∼10, 12∼18 months) APP/PS1 mice. We observed increased levels of mitochondrial fission protein, Drp1, and decreased levels of ATP synthase subunit, ATP5A, leading to abnormal mitochondrial morphology, increased oxidative stress, glial activation, apoptosis, and altered neuronal morphology as early as 4∼5 months of age in APP/PS1 mice. Electrophysiological recordings revealed abnormal miniature excitatory postsynaptic current in the mPFC together with a minor connectivity change between the mPFC and HIPP, correlating with social deficits. These results suggest that abnormal mitochondrial dynamics, which worsen with disease progression, could be a biomarker of early-stage AD. Therapeutic interventions that improve mitochondrial function thus represent a promising approach for slowing the progression or delaying the onset of AD.

A Comparative Study of Structural and Metabolic Brain Networks in Patients With Mild Cognitive Impairment

Background: Changes in the metabolic and structural brain networks in mild cognitive impairment (MCI) have been widely researched. However, few studies have compared the differences in the topological properties of the metabolic and structural brain networks in patients with MCI.

Methods: We analyzedmagnetic resonance imaging (MRI) and fluoro-deoxyglucose positron emission tomography (FDG-PET) data of 137 patients with MCI and 80 healthy controls (HCs). The HC group data comes from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The permutation test was used to compare the network parameters (characteristic path length, clustering coefficient, local efficiency, and global efficiency) between the two groups. Partial Pearson’s correlation analysis was used to calculate the correlations of the changes in gray matter volume and glucose intake in the key brain regions in MCI with the Alzheimer’s Disease Assessment Scale-Cognitive (ADAS-cog) sub-item scores.

Results: Significant changes in the brain network parameters (longer characteristic path length, larger clustering coefficient, and lower local efficiency and global efficiency) were greater in the structural network than in the metabolic network (longer characteristic path length) in MCI patients than in HCs. We obtained the key brain regions (left globus pallidus, right calcarine fissure and its surrounding cortex, left lingual gyrus) by scanning the hubs. The volume of gray matter atrophy in the left globus pallidus was significantly positively correlated with comprehension of spoken language (p = 0.024) and word-finding difficulty in spontaneous speech item scores (p = 0.007) in the ADAS-cog. Glucose intake in the three key brain regions was significantly negatively correlated with remembering test instructions items in ADAS-cog (p = 0.020, p = 0.014, and p = 0.008, respectively).

Conclusion: Structural brain networks showed more changes than metabolic brain networks in patients with MCI. Some brain regions with significant changes in betweenness centrality in both structural and metabolic networks were associated with MCI.

Sex-specific accelerated decay in time/activity-dependent plasticity and associative memory in an animal model of Alzheimer's disease

Clinical studies have shown that female brains are more predisposed to neurodegenerative diseases such as Alzheimer's disease (AD), but the cellular and molecular mechanisms behind this disparity remain unknown. In several mouse models of AD, synaptic plasticity dysfunction is an early event and appears before significant accumulation of amyloid plaques and neuronal degeneration. However, it is unclear whether sexual dimorphism at the synaptic level contributes to the higher risk and prevalence of AD in females. Our studies on APP/PS1 (APPSwe/PS1dE9) mouse model show that AD impacts hippocampal long‐term plasticity in a sex‐specific manner. Long‐term potentiation (LTP) induced by strong tetanic stimulation (STET), theta burst stimulation (TBS) and population spike timing‐dependent plasticity (pSTDP) show a faster decay in AD females compared with age‐matched AD males. In addition, behavioural tagging (BT), a model of associative memory, is specifically impaired in AD females with a faster decay in memory compared with males. Together with the plasticity and behavioural data, we also observed an upregulation of neuroinflammatory markers, along with downregulation of transcripts that regulate cellular processes associated with synaptic plasticity and memory in females. Immunohistochemistry of AD brains confirms that female APP/PS1 mice carry a higher amyloid plaque burden and have enhanced microglial activation compared with male APP/PS1 mice. Their presence in the diseased mice also suggests a link between the impairment of LTP and the upregulation of the inflammatory response. Overall, our data show that synaptic plasticity and associative memory impairments are more prominent in females and this might account for the faster progression of AD in females.

Deep Fusion of Brain Structure-Function in Mild Cognitive Impairment

Multimodal fusion of different types of neural image data provides an irreplaceable opportunity to take advantages of complementary cross-modal information that may only partially be contained in single modality. To jointly analyze multimodal data, deep neural networks can be especially useful because many studies have suggested that deep learning strategy is very efficient to reveal complex and non-linear relations buried in the data. However, most deep models, e.g., convolutional neural network and its numerous extensions, can only operate on regular Euclidean data like voxels in 3D MRI. The interrelated and hidden structures that beyond the grid neighbors, such as brain connectivity, may be overlooked. Moreover, how to effectively incorporate neuroscience knowledge into multimodal data fusion with a single deep framework is understudied. In this work, we developed a graph-based deep neural network to simultaneously model brain structure and function in Mild Cognitive Impairment (MCI): the topology of the graph is initialized using structural network (from diffusion MRI) and iteratively updated by incorporating functional information (from functional MRI) to maximize the capability of differentiating MCI patients from elderly normal controls. This resulted in a new connectome by exploring "deep relations" between brain structure and function in MCI patients and we named it as Deep Brain Connectome. Though deep brain connectome is learned individually, it shows consistent patterns of alteration comparing to structural network at group level. With deep brain connectome, our developed deep model can achieve 92.7% classification accuracy on ADNI dataset.

Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

BACKGROUND

Graph theory and machine learning have been shown to be effective ways of classifying different stages of Alzheimer's disease (AD). Most previous studies have only focused on inter-subject classification with single-mode neuroimaging data. However, whether this classification can truly reflect the changes in the structure and function of the brain region in disease progression remains unverified. In the current study, we aimed to evaluate the classification framework, which combines structural Magnetic Resonance Imaging (sMRI) and resting-state functional Magnetic Resonance Imaging (rs-fMRI) metrics, to distinguish mild cognitive impairment non-converters (MCInc)/AD from MCI converters (MCIc) by using graph theory and machine learning.

METHODS

With the intra-subject (MCInc vs. MCIc) and inter-subject (MCIc vs. AD) design, we employed cortical thickness features, structural brain network features, and sub-frequency (full-band, slow-4, slow-5) functional brain network features for classification. Three feature selection methods [random subset feature selection algorithm (RSFS), minimal redundancy maximal relevance (mRMR), and sparse linear regression feature selection algorithm based on stationary selection (SS-LR)] were used respectively to select discriminative features in the iterative combinations of MRI and network measures. Then support vector machine (SVM) classifier with nested cross-validation was employed for classification. We also compared the performance of multiple classifiers (Random Forest, K-nearest neighbor, Adaboost, SVM) and verified the reliability of our results by upsampling.

RESULTS

We found that in the classifications of MCIc vs. MCInc, and MCIc vs. AD, the proposed RSFS algorithm achieved the best accuracies (84.71, 89.80%) than the other algorithms. And the high-sensitivity brain regions found with the two classification groups were inconsistent. Specifically, in MCIc vs. MCInc, the high-sensitivity brain regions associated with both structural and functional features included frontal, temporal, caudate, entorhinal, parahippocampal, and calcarine fissure and surrounding cortex. While in MCIc vs. AD, the high-sensitivity brain regions associated only with functional features included frontal, temporal, thalamus, olfactory, and angular.

CONCLUSIONS

These results suggest that our proposed method could effectively predict the conversion of MCI to AD, and the inconsistency of specific brain regions provides a novel insight for clinical AD diagnosis.

Understanding the Variability in Graph Data Sets through Statistical Modeling on the Stiefel Manifold

Network analysis provides a rich framework to model complex phenomena, such as human brain connectivity. It has proven efficient to understand their natural properties and design predictive models. In this paper, we study the variability within groups of networks, i.e., the structure of connection similarities and differences across a set of networks. We propose a statistical framework to model these variations based on manifold-valued latent factors. Each network adjacency matrix is decomposed as a weighted sum of matrix patterns with rank one. Each pattern is described as a random perturbation of a dictionary element. As a hierarchical statistical model, it enables the analysis of heterogeneous populations of adjacency matrices using mixtures. Our framework can also be used to infer the weight of missing edges. We estimate the parameters of the model using an Expectation-Maximization-based algorithm. Experimenting on synthetic data, we show that the algorithm is able to accurately estimate the latent structure in both low and high dimensions. We apply our model on a large data set of functional brain connectivity matrices from the UK Biobank. Our results suggest that the proposed model accurately describes the complex variability in the data set with a small number of degrees of freedom.

Alzheimer's Disease Projection From Normal to Mild Dementia Reflected in Functional Network Connectivity: A Longitudinal Study

Background

Alzheimer's disease (AD) is the most common age-related problem and progresses in different stages, including mild cognitive impairment (early stage), mild dementia (middle-stage), and severe dementia (late-stage). Recent studies showed changes in functional network connectivity obtained from resting-state functional magnetic resonance imaging (rs-fMRI) during the transition from healthy aging to AD. By assuming that the brain interaction is static during the scanning time, most prior studies are focused on static functional or functional network connectivity (sFNC). Dynamic functional network connectivity (dFNC) explores temporal patterns of functional connectivity and provides additional information to its static counterpart.

Method

We used longitudinal rs-fMRI from 1385 scans (from 910 subjects) at different stages of AD (from normal to very mild AD or vmAD). We used group-independent component analysis (group-ICA) and extracted 53 maximally independent components (ICs) for the whole brain. Next, we used a sliding-window approach to estimate dFNC from the extracted 53 ICs, then group them into 3 different brain states using a clustering method. Then, we estimated a hidden Markov model (HMM) and the occupancy rate (OCR) for each subject. Finally, we investigated the link between the clinical rate of each subject with state-specific FNC, OCR, and HMM.

Results

All states showed significant disruption during progression normal brain to vmAD one. Specifically, we found that subcortical network, auditory network, visual network, sensorimotor network, and cerebellar network connectivity decrease in vmAD compared with those of a healthy brain. We also found reorganized patterns (i.e., both increases and decreases) in the cognitive control network and default mode network connectivity by progression from normal to mild dementia. Similarly, we found a reorganized pattern of between-network connectivity when the brain transits from normal to mild dementia. However, the connectivity between visual and sensorimotor network connectivity decreases in vmAD compared with that of a healthy brain. Finally, we found a normal brain spends more time in a state with higher connectivity between visual and sensorimotor networks.

Conclusion

Our results showed the temporal and spatial pattern of whole-brain FNC differentiates AD form healthy control and suggested substantial disruptions across multiple dynamic states. In more detail, our results suggested that the sensory network is affected more than other brain network, and default mode network is one of the last brain networks get affected by AD In addition, abnormal patterns of whole-brain dFNC were identified in the early stage of AD, and some abnormalities were correlated with the clinical score.

Developmental pattern of the cortical topology in high-functioning individuals with autism spectrum disorder

A number of studies have indicated alterations of brain morphology in individuals with autism spectrum disorder (ASD); however, how ASD influences the topological organization of the brain cortex at different developmental stages is not yet well characterized. In this study, we used structural images of 492 high‐functioning participants in the Autism Brain Imaging Data Exchange database acquired from 17 international imaging centers, including 75 autistic children (age 7–11 years), 91 adolescents with ASD (age 12–17 years), and 80 young adults with ASD (age 18–29 years), and 246 typically developing controls (TDCs) that were age, gender, handedness, and full‐scale IQ matched. Cortical thickness (CT) and surface area (SA) were extracted and the covariance between cortical regions across participants were treated as a network to examine developmental patterns of the cortical topological organization at different stages. A center‐paired resampling strategy was developed to control the center bias during the permutation test. Compared with the TDCs, network of SA (but not CT) of individuals with ASD showed reduced small‐worldness in childhood, and the network hubs were reorganized in the adulthood such that hubs inclined to connect with nonhub nodes and demonstrated more dispersed spatial distribution. Furthermore, the SA network of the ASD cohort exhibited increased segregation of the inferior parietal lobule and prefrontal cortex, and insular‐opercular cortex in all three age groups, resulting in the emergence of two unique modules in the autistic brain. Our findings suggested that individuals with ASD may undergo remarkable remodeling of the cortical topology from childhood to adulthood, which may be associated with the altered social and cognitive functions in ASD.