Patients with mild cognitive impairment (MCI) are at high risk for developing Alzheimer's disease (AD), while some of them may remain stable over decades. The underlying mechanism is still not fully understood. In this study, we aimed to explore the connectivity differences between progressive MCI (PMCI) and stable MCI (SMCI) individuals on a whole-brain scale and on a voxel-wise basis, and we also aimed to reveal the differential dynamic alteration patterns between these two disease subtypes. The resting-state functional magnetic resonance images of PMCI and SMCI patients at baseline and year-one were obtained from the Alzheimer's Disease Neuroimaging Initiative dataset, and the progression was determined based on a 3-year follow-up. A whole-brain voxel-wise degree map that was calculated based on graph-theory was constructed for each subject, and then the cross-sectional and longitudinal analyses on the degree maps were performed between PMCI and SMCI patients. In longitudinal analyses, compared with SMCI group, PMCI group showed decreased long-range degree in the left middle occipital/supramarginal gyrus, while the short-range degree was increased in the left supplementary motor area and middle frontal gyrus and decreased in the right middle temporal pole. A significant longitudinal alteration of decreased short-range degree in the right middle occipital was found in PMCI group. Taken together with previous evidence, our current findings may suggest that PMCI, compared with SMCI, might be a "severe" presentation of disease along the AD continuum, and the rapidly reduced degree in the right middle occipital gyrus may have indicative value for the disease progression. Moreover, the cross-sectional comparison results and corresponding receiver-operator characteristic-curves analyses may indicate that the baseline degree difference is not a good predictor of disease progression in MCI patients. Overall, these findings may provide objective evidence and an indicator to characterize the progression-related brain connectivity changes in MCI patients.

Neuroimaging measurements derived from magnetic resonance imaging provide important information required for detecting changes related to the progression of mild cognitive impairment (MCI). Cortical features and changes play a crucial role in revealing unique anatomical patterns of brain regions, and further differentiate MCI patients from normal states. Four cortical features, namely, gray matter volume, cortical thickness, surface area, and mean curvature, were explored for discriminative analysis among three groups including the stable MCI (sMCI), the converted MCI (cMCI), and the normal control (NC) groups. In this study, 158 subjects (72 NC, 46 sMCI, and 40 cMCI) were selected from the Alzheimer's Disease Neuroimaging Initiative. A sparse-constrained regression model based on the l2-1-norm was introduced to reduce the feature dimensionality and retrieve essential features for the discrimination of the three groups by using a support vector machine (SVM). An optimized strategy of feature addition based on the weight of each feature was adopted for the SVM classifier in order to achieve the best classification performance. The baseline cortical features combined with the longitudinal measurements for 2 years of follow-up data yielded prominent classification results. In particular, the cortical thickness produced a classification with 98.84% accuracy, 97.5% sensitivity, and 100% specificity for the sMCI-cMCI comparison; 92.37% accuracy, 84.78% sensitivity, and 97.22% specificity for the cMCI-NC comparison; and 93.75% accuracy, 92.5% sensitivity, and 94.44% specificity for the sMCI-NC comparison. The best performances obtained by the SVM classifier using the essential features were 5-40% more than those using all of the retained features. The feasibility of the cortical features for the recognition of anatomical patterns was certified; thus, the proposed method has the potential to improve the clinical diagnosis of sub-types of MCI and predict the risk of its conversion to Alzheimer's disease.

In this paper, we explore the effects of integrating multi-dimensional imaging genomics data for Alzheimer's disease (AD) prediction using machine learning approaches. Precisely, we compare our three recent proposed feature selection methods [i.e., multiple kernel learning (MKL), high-order graph matching based feature selection (HGM-FS), sparse multimodal learning (SMML)] using four widely-used modalities [i.e., magnetic resonance imaging (MRI), positron emission tomography (PET), cerebrospinal fluid (CSF), and genetic modality single-nucleotide polymorphism (SNP)]. This study demonstrates the performance of each method using these modalities individually or integratively, and may be valuable to clinical tests in practice. Our experimental results suggest that for AD prediction, in general, (1) in terms of accuracy, PET is the best modality; (2) Even though the discriminant power of genetic SNP features is weak, adding this modality to other modalities does help improve the classification accuracy; (3) HGM-FS works best among the three feature selection methods; (4) Some of the selected features are shared by all the feature selection methods, which may have high correlation with the disease. Using all the modalities on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the best accuracies, described as (mean ± standard deviation)%, among the three methods are (76.2 ± 11.3)% for AD vs. MCI, (94.8 ± 7.3)% for AD vs. HC, (76.5 ± 11.1)% for MCI vs. HC, and (71.0 ± 8.4)% for AD vs. MCI vs. HC, respectively.

Alzheimer's disease (AD) causes the progressive deterioration of neural connections, disrupting structural connectivity (SC) networks within the brain. Graph-based analyses of SC networks have shown that topological properties can reveal the course of AD propagation. Different whole-brain parcellation schemes have been developed to define the nodes of these SC networks, although it remains unclear which scheme can best describe the AD-related deterioration of SC networks. In this study, four whole-brain parcellation schemes with different numbers of parcels were used to define SC network nodes. SC networks were constructed based on high angular resolution diffusion imaging (HARDI) tractography for a mixed cohort that includes 20 normal controls (NC), 20 early mild cognitive impairment (EMCI), 20 late mild cognitive impairment (LMCI), and 20 AD patients, from the Alzheimer's Disease Neuroimaging Initiative. Parcellation schemes investigated in this study include the OASIS-TRT-20 (62 regions), AAL (116 regions), HCP-MMP (180 regions), and Gordon-rsfMRI (333 regions), which have all been widely used for the construction of brain structural or functional connectivity networks. Topological characteristics of the SC networks, including the network strength, global efficiency, clustering coefficient, rich-club, characteristic path length, k-core, rich-club coefficient, and modularity, were fully investigated at the network level. Statistical analyses were performed on these metrics using Kruskal-Wallis tests to examine the group differences that were apparent at different stages of AD progression. Results suggest that the HCP-MMP scheme is the most robust and sensitive to AD progression, while the OASIS-TRT-20 scheme is sensitive to group differences in network strength, global efficiency, k-core, and rich-club coefficient at k-levels from 18 and 39. With the exception of the rich-club and modularity coefficients, AAL could not significantly identify group differences on other topological metrics. Further, the Gordon-rsfMRI atlas only significantly differentiates the groups on network strength, characteristic path length, k-core, and rich-club coefficient. Results show that the topological examination of SC networks with different parcellation schemes can provide important complementary AD-related information and thus contribute to a more accurate and earlier diagnosis of AD.

Resting-state functional connectivity is a promising biomarker for Alzheimer's disease. However, previous resting-state functional magnetic resonance imaging studies in Alzheimer's disease and amnestic mild cognitive impairment (aMCI) have shown limited reproducibility as they have had small sample sizes and substantial variation in study protocol. We sought to identify functional brain networks and connections that could consistently discriminate normal aging from aMCI despite variations in scanner manufacturer, imaging protocol, and diagnostic procedure. We therefore combined four datasets collected independently, including 112 healthy controls and 143 patients with aMCI. We systematically tested multiple brain connections for associations with aMCI using a weighted average routinely used in meta-analyses. The largest effects involved the superior medial frontal cortex (including the anterior cingulate), dorsomedial prefrontal cortex, striatum, and middle temporal lobe. Compared with controls, patients with aMCI exhibited significantly decreased connectivity between default mode network nodes and between regions of the cortico-striatal-thalamic loop. Despite the heterogeneity of methods among the four datasets, we identified common aMCI-related connectivity changes with small to medium effect sizes and sample size estimates recommending a minimum of 140 to upwards of 600 total subjects to achieve adequate statistical power in the context of a multisite study with 5-10 scanning sites and about 10 subjects per group and per site. If our findings can be replicated and associated with other established biomarkers of Alzheimer's disease (e.g., amyloid and tau quantification), then these functional connections may be promising candidate biomarkers for Alzheimer's disease.