Abnormal Resting-State Functional Connectivity Strength in Mild Cognitive Impairment and Its Conversion to Alzheimer's Disease

Could Accelerated Long-Term Forgetting Be a Feature of the Higher Rate of Memory Complaints Associated with Subjective Cognitive Decline? An Exploratory Study

Background

Recently, subjective cognitive decline (SCD) was proposed as an early risk factor for future Alzheimer's disease (AD).

Objective

In this study, we investigated whether accelerated long-term forgetting (ALF), assessed with extended testing intervals than those adopted in clinical practice, might be a cognitive feature of SCD. Using an explorative MRI analysis of the SCD sample, we attempted to investigate the areas most likely involved in the ALF pattern.

Methods

We recruited 31 individuals with SCD from our memory clinic and subdivided them based on their rate of memory complaints into mild SCDs (n = 18) and severe SCDs (n = 13). A long-term forgetting procedure, involving the recall of verbal and visuo-spatial material at four testing delays (i.e., immediate, 30 min, 24 h, and 7 days post-encoding) was used to compare the two sub-groups of SCDs with a healthy control group (HC; n = 16).

Results

No significant between-group difference was found on the standard neuropsychological tests, nor in the immediate and 30 min recall of the experimental procedure. By contrast, on the verbal test severe SCDs forgot significantly more than HCs in the prolonged intervals (i.e., 24 h and 7 days), with the greatest decline between 30 min and 24 h. Finally, in the whole SCD sample, we found significant associations between functional connectivity values within some cortical networks involved in memory (default mode network, salience network, and fronto-parietal network) and verbal long-term measures.

Conclusions

Our preliminary findings suggest that long-term forgetting procedures could be a sensitive neuropsychological tool for detecting memory concerns in SCDs, contributing to early AD detection.

Differential network knockoff filter with application to brain connectivity analysis

The brain functional connectivity can typically be represented as a brain functional network, where nodes represent regions of interest (ROIs) and edges symbolize their connections. Studying group differences in brain functional connectivity can help identify brain regions and recover the brain functional network linked to neurodegenerative diseases. This process, known as differential network analysis focuses on the differences between estimated precision matrices for two groups. Current methods struggle with individual heterogeneity in measuring the brain connectivity, false discovery rate (FDR) control, and accounting for confounding factors, resulting in biased estimates and diminished power. To address these issues, we present a two-stage FDR-controlled feature selection method for differential network analysis using functional magnetic resonance imaging (fMRI) data. First, we create individual brain connectivity measures using a high-dimensional precision matrix estimation technique. Next, we devise a penalized logistic regression model that employs individual brain connectivity data and integrates a new knockoff filter for FDR control when detecting significant differential edges. Through extensive simulations, we showcase the superiority of our approach compared to other methods. Additionally, we apply our technique to fMRI data to identify differential edges between Alzheimer's disease and control groups. Our results are consistent with prior experimental studies, emphasizing the practical applicability of our method.

Detecting Alzheimer's Disease Stages and Frontotemporal Dementia in Time Courses of Resting-State fMRI Data Using a Machine Learning Approach

Early, accurate diagnosis of neurodegenerative dementia subtypes such as Alzheimer's disease (AD) and frontotemporal dementia (FTD) is crucial for the effectiveness of their treatments. However, distinguishing these conditions becomes challenging when symptoms overlap or the conditions present atypically. Resting-state fMRI (rs-fMRI) studies have demonstrated condition-specific alterations in AD, FTD, and mild cognitive impairment (MCI) compared to healthy controls (HC). Here, we used machine learning to build a diagnostic classification model based on these alterations. We curated all rs-fMRIs and their corresponding clinical information from the ADNI and FTLDNI databases. Imaging data underwent preprocessing, time course extraction, and feature extraction in preparation for the analyses. The imaging features data and clinical variables were fed into gradient-boosted decision trees with fivefold nested cross-validation to build models that classified four groups: AD, FTD, HC, and MCI. The mean and 95% confidence intervals for model performance metrics were calculated using the unseen test sets in the cross-validation rounds. The model built using only imaging features achieved 74.4% mean balanced accuracy, 0.94 mean macro-averaged AUC, and 0.73 mean macro-averaged F1 score. It accurately classified FTD (F1 = 0.99), HC (F1 = 0.99), and MCI (F1 = 0.86) fMRIs but mostly misclassified AD scans as MCI (F1 = 0.08). Adding clinical variables to model inputs raised balanced accuracy to 91.1%, macro-averaged AUC to 0.99, macro-averaged F1 score to 0.92, and improved AD classification accuracy (F1 = 0.74). In conclusion, a multimodal model based on rs-fMRI and clinical data accurately differentiates AD-MCI vs. FTD vs. HC.

Resting-state functional MRI study of conventional MRI-negative intractable epilepsy in children

Objective

The study aimed at investigating functional connectivity strength (FCS) changes in children with MRI-negative intractable epilepsy (ITE) and evaluating correlations between aberrant FCS and both disease duration and intelligence quotient (IQ).

Methods

Fifteen children with ITE, 24 children with non-intractable epilepsy (nITE) and 25 matched healthy controls (HCs) were subjected to rs-fMRI. IQ was evaluated by neuropsychological assessment. Voxelwise analysis of covariance was conducted in the whole brain, and then pairwise comparisons were made across three groups using Bonferroni corrections.

Results

FCS was significantly different among three groups. Relative to HCs, ITE patients exhibited decreased FCS in right temporal pole of the superior temporal gyrus, middle temporal gyrus, bilateral precuneus, etc and increased FCS values in left triangular part of the inferior frontal gyrus, parahippocampal gyrus, supplementary motor area, caudate and right calcarine fissure and surrounding cortex and midbrain. The nITE patients presented decreased FCS in right orbital superior frontal gyrus, precuneus etc and increased FCS in bilateral fusiform gyri, parahippocampal gyri, etc. In comparison to nITE patients, the ITE patients presented decreased FCS in right medial superior frontal gyrus and left inferior temporal gyrus and increased FCS in right middle temporal gyrus, inferior temporal gyrus and calcarine fissure and surrounding cortex. Correlation analysis indicated that FCS in left caudate demonstrated correlation with verbal IQ (VIQ) and disease duration.

Conclusion

ITE patients demonstrated changed FCS values in the temporal and prefrontal cortices relative to nITE patients, which may be related to drug resistance in epilepsy. FCS in the left caudate nucleus associated with VIQ, suggesting the caudate may become a key target for improving cognitive impairment and seizures in children with ITE.

Resting-state functional connectivity and cognitive performance in aging adults with cognitive decline: A data-driven multivariate pattern analysis

BACKGROUND

Cognitive impairments occur on a continuous spectrum in multiple cognitive domains showing individual variability of the deteriorating patterns; however, often, cognitive domains are studied separately.

METHODS

The present study investigated aging individual variations of cognitive abilities and related resting-state functional connectivity (rsFC) using data-driven approach. Cognitive and neuroimaging data were obtained from 62 elderly outpatients with cognitive decline. Principal component analysis (PCA) was conducted on the cognitive data to determine patterns of cognitive performance, then data-driven whole-brain connectome multivariate pattern analysis (MVPA) was applied on the neuroimaging data to discover neural regions associated with the cognitive characteristic.

RESULTS

The first component (PC1) delineated an overall decline in all domains of cognition, and the second component (PC2) represented a compensatory relationship within basic cognitive functions. MVPA indicated rsFC of the cerebellum lobule VIII and insula with the default-mode network, frontoparietal network, and salience network inversely correlated with PC1 scores. Additionally, PC2 score was related to rsFC patterns with temporal pole and occipital cortex.

CONCLUSIONS

The featured primary cognitive characteristic depicted the importance of the cerebellum and insula connectivity patterns in of the general cognitive decline. The findings also discovered a secondary characteristic that communicated impaired interactions within the basic cognitive function, which was independent from the impairment severity.

Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer's disease: Inter-cohort validation of Shanghai Memory Study and ADNI

Mild cognitive impairment (MCI) is a critical prodromal stage of Alzheimer's disease (AD), and the mechanism underlying the conversion is not fully explored. Construction and inter-cohort validation of imaging biomarkers for predicting MCI conversion is of great challenge at present, due to lack of longitudinal cohorts and poor reproducibility of various study-specific imaging indices. We proposed a novel framework for inter-cohort MCI conversion prediction, involving comparison of structural, static, and dynamic functional brain features from structural magnetic resonance imaging (sMRI) and resting-state functional MRI (fMRI) between MCI converters (MCI_C) and non-converters (MCI_NC), and support vector machine for construction of prediction models. A total of 218 MCI patients with 3-year follow-up outcome were selected from two independent cohorts: Shanghai Memory Study cohort for internal cross-validation, and Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for external validation. In comparison with MCI_NC, MCI_C were mainly characterized by atrophy, regional hyperactivity and inter-network hypo-connectivity, and dynamic alterations characterized by regional and connectional instability, involving medial temporal lobe (MTL), posterior parietal cortex (PPC), and occipital cortex. All imaging-based prediction models achieved an area under the curve (AUC) > 0.7 in both cohorts, with the multi-modality MRI models as the best with excellent performances of AUC > 0.85. Notably, the combination of static and dynamic fMRI resulted in overall better performance as relative to static or dynamic fMRI solely, supporting the contribution of dynamic features. This inter-cohort validation study provides a new insight into the mechanisms of MCI conversion involving brain dynamics, and paves a way for clinical use of structural and functional MRI biomarkers in future.

Relationship between default mode network and resting-state electroencephalographic alpha rhythms in cognitively unimpaired seniors and patients with dementia due to Alzheimer's disease

Here we tested the hypothesis of a relationship between the cortical default mode network (DMN) structural integrity and the resting-state electroencephalographic (rsEEG) rhythms in patients with Alzheimer's disease with dementia (ADD). Clinical and instrumental datasets in 45 ADD patients and 40 normal elderly (Nold) persons originated from the PDWAVES Consortium (www.pdwaves.eu). Individual rsEEG delta, theta, alpha, and fixed beta and gamma bands were considered. Freeware platforms served to derive (1) the (gray matter) volume of the DMN, dorsal attention (DAN), and sensorimotor (SMN) cortical networks and (2) the rsEEG cortical eLORETA source activities. We found a significant positive association between the DMN gray matter volume, the rsEEG alpha source activity estimated in the posterior DMN nodes (parietal and posterior cingulate cortex), and the global cognitive status in the Nold and ADD participants. Compared with the Nold, the ADD group showed lower DMN gray matter, lower rsEEG alpha source activity in those nodes, and lower global cognitive status. This effect was not observed in the DAN and SMN. These results suggest that the DMN structural integrity and the rsEEG alpha source activities in the DMN posterior hubs may be related and predict the global cognitive status in ADD and Nold persons.

Genetic risk factors of Alzheimer's Disease disrupt resting-state functional connectivity in cognitively intact young individuals

BACKGROUND

Past evidence shows that changes in functional brain connectivity in multiple resting-state networks occur in cognitively healthy individuals who have non-modifiable risk factors for Alzheimer's Disease. Here, we aimed to investigate how those changes differ in early adulthood and how they might relate to cognition.

METHODS

We investigated the effects of genetic risk factors of AD, namely APOEe4 and MAPTA alleles, on resting-state functional connectivity in a cohort of 129 cognitively intact young adults (aged 17-22 years). We used Independent Component Analysis to identify networks of interest, and Gaussian Random Field Theory to compare connectivity between groups. Seed-based analysis was used to quantify inter-regional connectivity strength from the clusters that exhibited significant between-group differences. To investigate the relationship with cognition, we correlated the connectivity and the performance on the Stroop task.

RESULTS

The analysis revealed a decrease in functional connectivity in the Default Mode Network (DMN) in both APOEe4 carriers and MAPTA carriers in comparison with non-carriers. APOEe4 carriers showed decreased connectivity in the right angular gyrus (size = 246, p-FDR = 0.0079), which was correlated with poorer performance on the Stroop task. MAPTA carriers showed decreased connectivity in the left middle temporal gyrus (size = 546, p-FDR = 0.0001). In addition, we found that only MAPTA carriers had a decreased connectivity between the DMN and multiple other brain regions.

CONCLUSIONS

Our findings indicate that APOEe4 and MAPTA alleles modulate brain functional connectivity in the brain regions within the DMN in cognitively intact young adults. APOEe4 carriers also showed a link between connectivity and cognition.

Gamma neuromodulation improves episodic memory and its associated network in amnestic mild cognitive impairment: a pilot study

Amnestic mild cognitive impairment (aMCI) is a predementia stage of Alzheimer's disease associated with dysfunctional episodic memory and limited treatment options. We aimed to characterize feasibility, clinical, and biomarker effects of noninvasive neurostimulation for aMCI. 13 individuals with aMCI received eight 60-minute sessions of 40-Hz (gamma) transcranial alternating current stimulation (tACS) targeting regions related to episodic memory processing. Feasibility, episodic memory, and plasma Alzheimer's disease biomarkers were assessed. Neuroplastic changes were characterized by resting-state functional connectivity (RSFC) and neuronal excitatory/inhibitory balance. Gamma tACS was feasible and aMCI participants demonstrated improvement in multiple metrics of episodic memory, but no changes in biomarkers. Improvements in episodic memory were most pronounced in participants who had the highest modeled tACS-induced electric fields and exhibited the greatest changes in RSFC. Increased RSFC was also associated with greater hippocampal excitability and higher baseline white matter integrity. This study highlights initial feasibility and the potential of gamma tACS to rescue episodic memory in an aMCI population by modulating connectivity and excitability within an episodic memory network.

The Importance of Subjective Cognitive Decline Recognition and the Potential of Molecular and Neurophysiological Biomarkers-A Systematic Review

Subjective cognitive decline (SCD) and mild cognitive impairment (MCI) are early stages of Alzheimer's disease (AD). Neurophysiological markers such as electroencephalography (EEG) and event-related potential (ERP) are emerging as alternatives to traditional molecular and imaging markers. This paper aimed to review the literature on EEG and ERP markers in individuals with SCD. We analysed 30 studies that met our criteria, with 17 focusing on resting-state or cognitive task EEG, 11 on ERPs, and two on both EEG and ERP parameters. Typical spectral changes were indicative of EEG rhythm slowing and were associated with faster clinical progression, lower education levels, and abnormal cerebrospinal fluid biomarkers profiles. Some studies found no difference in ERP components between SCD subjects, controls, or MCI, while others reported lower amplitudes in the SCD group compared to controls. Further research is needed to explore the prognostic value of EEG and ERP in relation to molecular markers in individuals with SCD.

Multicenter and Multichannel Pooling GCN for Early AD Diagnosis Based on Dual-Modality Fused Brain Network

For significant memory concern (SMC) and mild cognitive impairment (MCI), their classification performance is limited by confounding features, diverse imaging protocols, and limited sample size. To address the above limitations, we introduce a dual-modality fused brain connectivity network combining resting-state functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI), and propose three mechanisms in the current graph convolutional network (GCN) to improve classifier performance. First, we introduce a DTI-strength penalty term for constructing functional connectivity networks. Stronger structural connectivity and bigger structural strength diversity between groups provide a higher opportunity for retaining connectivity information. Second, a multi-center attention graph with each node representing a subject is proposed to consider the influence of data source, gender, acquisition equipment, and disease status of those training samples in GCN. The attention mechanism captures their different impacts on edge weights. Third, we propose a multi-channel mechanism to improve filter performance, assigning different filters to features based on feature statistics. Applying those nodes with low-quality features to perform convolution would also deteriorate filter performance. Therefore, we further propose a pooling mechanism, which introduces the disease status information of those training samples to evaluate the quality of nodes. Finally, we obtain the final classification results by inputting the multi-center attention graph into the multi-channel pooling GCN. The proposed method is tested on three datasets (i.e., an ADNI 2 dataset, an ADNI 3 dataset, and an in-house dataset). Experimental results indicate that the proposed method is effective and superior to other related algorithms, with a mean classification accuracy of 93.05% in our binary classification tasks. Our code is available at: https://github.com/Xuegang-S.

Sex Difference in General Cognition Associated with Coupling of Whole-brain Functional Connectivity Strength to Cerebral Blood Flow Changes During Alzheimer's Disease Progression

Alzheimer's disease (AD) is a progressive age-related neurodegenerative disorder that results in irreversible cognitive impairments. Nonetheless, there are numerous sex-dependent differences in clinical course. We examined potential contributions of neurovascular coupling deficits to sex differences in AD progression. T1-weighted three-dimensional structural magnetic resonance images, functional blood oxygen level dependent and arterial spin labeling images were acquired from 50 AD patients (28 females), 52 amnesic mild cognitive impairment patients (31 females), and 59 healthy controls (36 females). Short- and long-range functional connectivity strength (FCS) and cerebral blood flow (CBF) values were calculated for all participants. Then, the CBF/FCS coupling ratio, which represented the amount of blood supply per unit of connectivity strength, was calculated for each voxel. Two-way ANOVA was performed to identify group × sex interactions and main effects of group. Correlation analysis was used to assess associations between CBF/FCS ratios and Mini-Mental State Examination (MMSE). There were significant group × sex interaction effects on short-range coupling ratios of right middle temporal gyrus, left angular gyrus, left inferior orbital frontal gyrus, and left superior frontal gyrus as well as on the long-range coupling ratios of right middle temporal gyrus, left precuneus, left posterior cingulate cortex, and left angular gyrus. There were significant negative correlations between MMSE scores and CBF/FCS ratios for all regions with significant group × sex interactions among female patients, while positive correlations were found among male patients. Our results demonstrate significant sex differences in neurovascular coupling mechanisms associated with cognitive function during the course of AD.

Efficacy and safety of simultaneous rTMS-tDCS over bilateral angular gyrus on neuropsychiatric symptoms in patients with moderate Alzheimer's disease: A prospective, randomized, sham-controlled pilot study

BACKGROUND

Treating neuropsychiatric symptoms (NPS) in Alzheimer's disease (AD) remains highly challenging. Noninvasive brain stimulation using repetitive transcranial magnetic stimulation (rTMS) or transcranial direct current stimulation (tDCS) is of considerable interest in this context.

OBJECTIVE

To investigate the efficacy and safety of a novel technique involving simultaneous application of rTMS and tDCS (rTMS-tDCS) over bilateral angular gyrus (AG, P5/P6 electrode site) for AD-related NPS.

METHODS

Eighty-four AD patients were randomized to receive rTMS-tDCS, single-rTMS, single-tDCS, or sham stimulation for 4 weeks, with evaluation at week-4 (W4, immediately after treatment) and week-12 (W12, follow-up period) after initial examination. Primary outcome comprising Neuropsychiatric Inventory (NPI) score and secondary outcomes comprising mini-mental state examination (MMSE), AD assessment scale-cognitive subscale (ADAS-cog), and Pittsburgh sleep quality index (PSQI) scores were collected and analyzed by a two-factor (time and treatment), mixed-design ANOVA.

RESULTS

rTMS-tDCS produced greater improvement in NPI scores than single-tDCS and sham at W4 and W12 (both P < 0.017) and trended better than single-rTMS (W4: P = 0.058, W12: P = 0.034). rTMS-tDCS improved MMSE scores compared with single-tDCS at W4 (P = 0.011) and sham at W4 and W12 (both P < 0.017). rTMS-tDCS also significantly improved PSQI compared with single-rTMS and sham (both P < 0.017). Interestingly, rTMS-tDCS-induced NPI/PSQI improvement was significantly associated with MMSE/ADAS-cog improvement. tDCS- and/or rTMS-related adverse events appeared slightly and briefly.

CONCLUSIONS

rTMS-tDCS application to bilateral AG can effectively improve AD-related NPS, cognitive function, and sleep quality with considerable safety.

Theta Band-Power Shapes Amyloid-Driven Longitudinal EEG Changes in Elderly Subjective Memory Complainers At-Risk for Alzheimer's Disease

BACKGROUND

Alzheimer's disease (AD) includes progressive symptoms spread along a continuum of preclinical and clinical stages. Although numerous studies uncovered the neuro-cognitive changes of AD, very little is known on the natural history of brain lesions and modifications of brain networks in elderly cognitively-healthy memory complainers at risk of AD for carrying pathophysiological biomarkers (amyloidopathy and tauopathy).

OBJECTIVE

We analyzed resting-state electroencephalography (EEG) of 318 cognitively-healthy subjective memory complainers from the INSIGHT-preAD cohort at the time of their first visit (M0) and two-years later (M24).

METHODS

Using 18F-florbetapir PET-scanner, subjects were stratified between amyloid negative (A-; n = 230) and positive (A+; n = 88) groups. Differences between A+ and A-were estimated at source-level in each band-power of the EEG spectrum.

RESULTS

At M0, we found an increase of theta power in the mid-frontal cortex in A+ compared to A-. No significant association was found between mid-frontal theta and the individuals' cognitive performance. At M24, theta power increased in A+ relative to A-individuals in the posterior cingulate cortex and the pre-cuneus. Alpha band revealed a peculiar decremental trend in posterior brain regions in the A+ relative to the A-group only at M24. Theta power increase over the mid-frontal and mid-posterior cortices suggests an hypoactivation of the default-mode network in the A+ individuals and a non-linear longitudinal progression at M24.

CONCLUSION

We provide the first source-level longitudinal evidence on the impact of brain amyloidosis on the EEG dynamics of a large-scale, monocentric cohort of elderly individuals at-risk for AD.

Deep Spatio-Temporal Attention-based Recurrent Network from Dynamic Adaptive Functional Connectivity for MCI Identification

Most existing methods of constructing dynamic functional connectivity (dFC) network obtain the connectivity strength via the sliding window correlation (SWC) method, which estimates the connectivity strength at each time segment, rather than at each time point, and thus is difficult to produce accurate dFC network due to the influence of the window type and window width. Furthermore, the deep learning methods may not capture the discriminative spatio-temporal information that is closely related to disease, thus impacting the performance of (mild cognitive impairment) MCI identification. In this paper, a novel spatio-temporal attention-based bidirectional gated recurrent unit (STA-BiGRU) network is proposed to extract inherent spatio-temporal information from a dynamic adaptive functional connectivity (dAFC) network for MCI diagnosis. Specifically, we adopt a group lasso-based Kalman filter algorithm to obtain the dAFC network with more accurate connectivity strength at each time step. Then a spatial attention module with self-attention and a temporal attention module with multiple temporal attention vectors are incorporated into the BiGRU network to extract more discriminative disease-related spatio-temporal information. Finally, the spatio-temporal regularizations are employed to better guide the attention learning of STA-BiGRU network to enhance the robustness of the deep network. Experimental results show that the proposed framework achieves mean accuracies of 90.2%, 90.0%, and 81.5%, respectively, for three MCI classification tasks. This study provides a more effective deep spatio-temporal attention-based recurrent network and obtains good performance and interpretability of deep learning for psychiatry diagnosis research.

Deep learning of MRI contrast enhancement for mapping cerebral blood volume from single-modal non-contrast scans of aging and Alzheimer's disease brains

While MRI contrast agents such as those based on Gadolinium are needed for high-resolution mapping of brain metabolism, these contrast agents require intravenous administration, and there are rising concerns over their safety and invasiveness. Furthermore, non-contrast MRI scans are more commonly performed than those with contrast agents and are readily available for analysis in public databases such as the Alzheimer's Disease Neuroimaging Initiative (ADNI). In this article, we hypothesize that a deep learning model, trained using quantitative steady-state contrast-enhanced structural MRI datasets, in mice and humans, can generate contrast-equivalent information from a single non-contrast MRI scan. The model was first trained, optimized, and validated in mice, and was then transferred and adapted to humans. We observe that the model can substitute for Gadolinium-based contrast agents in approximating cerebral blood volume, a quantitative representation of brain activity, at sub-millimeter granularity. Furthermore, we validate the use of our deep-learned prediction maps to identify functional abnormalities in the aging brain using locally obtained MRI scans, and in the brain of patients with Alzheimer's disease using publicly available MRI scans from ADNI. Since it is derived from a commonly-acquired MRI protocol, this framework has the potential for broad clinical utility and can also be applied retrospectively to research scans across a host of neurological/functional diseases.

Perceived social isolation is correlated with brain structure and cognitive trajectory in Alzheimer’s disease

Both objective and perceived social isolations were associated with future cognitive decline and increase risk of Alzheimer’s disease (AD). However, the impacts of perceived social isolation depending on different clinical stages of AD have not been elucidated. The aim of this study was to investigate the influence of perceived social isolation or loneliness on brain structure and future cognitive trajectories in patients who are living with or are at risk for AD. A total of 176 elderly patients (mean age of 78 years) who had complaint of memory problems (39 subjective cognitive decline [SCD], 53 mild cognitive impairment [MCI], 84 AD) underwent structural MRI and neuropsychological testing. Loneliness was measured by one binary item question “Do you often feel lonely?.” Voxel-based morphometry was conducted to evaluate regional gray matter volume (rGMV) difference associated with loneliness in each group. To evaluate individual differences in cognitive trajectories based on loneliness, subgroup analysis was performed in 51 patients with AD (n = 23) and pre-dementia status (SCD-MCI, n = 28) using the longitudinal scores of Alzheimer’s Disease Assessment Scale-cognitive component-Japanese version (ADAS-Jcog). Whole brain VBM analysis comparing lonely to non-lonely patients revealed loneliness was associated with decreased rGMV in bilateral thalamus in SCD patients and in the left middle occipital gyrus and the cerebellar vermal lobules I − V in MCI patients. Annual change of ADAS-Jcog in patients who reported loneliness was significantly greater comparing to these non-lonely in SCD-MCI group, but not in AD group. Our results indicate that perceived social isolation, or loneliness, might be a comorbid symptom of patients with SCD or MCI, which makes them more vulnerable to the neuropathology of future AD progression.

Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data

The intervention at the stage of mild cognitive impairment (MCI) is promising for preventing Alzheimer's disease (AD). This study aims to search for the optimal machine learning (ML) model to classify early and late MCI (EMCI and LMCI) subtypes using multimodal MRI data. First, the tract-based spatial statistics (TBSS) analyses showed LMCI-related white matter changes in the Corpus Callosum. The ROI-based tractography addressed the connected cortical areas by affected callosal fibers. We then prepared two feature subsets for ML by measuring resting-state functional connectivity (TBSS-RSFC method) and graph theory metrics (TBSS-Graph method) in these cortical areas, respectively. We also prepared feature subsets of diffusion parameters in the regions of LMCI-related white matter alterations detected by TBSS analyses. Using these feature subsets, we trained and tested multiple ML models for EMCI/LMCI classification with cross-validation. Our results showed the ensemble ML model (AdaBoost) with feature subset of diffusion parameters achieved better performance of mean accuracy 70%. The useful brain regions for classification were those, including frontal, parietal lobe, Corpus Callosum, cingulate regions, insula, and thalamus regions. Our findings indicated the optimal ML model using diffusion parameters might be effective to distinguish LMCI from EMCI subjects at the prodromal stage of AD.

Subcortical and Cerebellar Neural Correlates of Prodromal Alzheimer’s Disease with Prolonged Sleep Latency

Background: Despite the important associations among sleep, Alzheimer’s disease (AD), subcortical structures, and the cerebellum, structural and functional magnetic resonance imaging (MRI) with regard to these regions and sleep on patients in AD trajectory are scarce. Objective: This study aimed to evaluate the influence of prolonged sleep latency on the structural and functional alterations in the subcortical and cerebellar neural correlates in amyloid-β positive amnestic mild cognitive impairment patients (Aβ+aMCI). Methods: A total of 60 patients with aMCI who were identified as amyloid positive ([18F] flutemetamol+) were recruited in the study, 24 patients with normal sleep latency (aMCI-n) and 36 patients prolonged sleep latency (aMCI-p). Cortical thickness and volumes between the two groups were compared. Volumetric analyses were implemented on the brainstem, thalamus, and hippocampus. Subcortical and cerebellar resting state functional connectivity (FC) differences were measured between the both groups through seed-to-voxel analysis. Additionally, group x Aβ interactive effects on FC values were tested with a general linear model. Result: There was a significantly decreased brainstem volume in aMCI-p subjects. We observed a significant reduction of the locus coeruleus (LC) FC with frontal, temporal, insular cortices, hippocampus, and left thalamic FC with occipital cortex. Moreover, the LC FC with occipital cortex and left hippocampal FC with frontal cortex were increased in aMCI-p subjects. In addition, there was a statistically significant group by regional standardized uptake value ratio interactions discovered in cerebro-cerebellar networks. Conclusion: The aforementioned findings suggest that prolonged sleep latency may be a detrimental factor in compromising structural and functional correlates of subcortical structures and the cerebellum, which may accelerate AD pathophysiology.

Baseline Neuroimaging Predicts Decline to Dementia From Amnestic Mild Cognitive Impairment

Background and Objectives: Prediction of decline to dementia using objective biomarkers in high-risk patients with amnestic mild cognitive impairment (aMCI) has immense utility. Our objective was to use multimodal MRI to (1) determine whether accurate and precise prediction of dementia conversion could be achieved using baseline data alone, and (2) generate a map of the brain regions implicated in longitudinal decline to dementia. Methods: Participants meeting criteria for aMCI at baseline (N = 55) were classified at follow-up as remaining stable/improved in their diagnosis (N = 41) or declined to dementia (N = 14). Baseline T1 structural MRI and resting-state fMRI (rsfMRI) were combined and a semi-supervised support vector machine (SVM) which separated stable participants from those who decline at follow-up with maximal margin. Cross-validated model performance metrics and MRI feature weights were calculated to include the strength of each brain voxel in its ability to distinguish the two groups. Results: Total model accuracy for predicting diagnostic change at follow-up was 92.7% using baseline T1 imaging alone, 83.5% using rsfMRI alone, and 94.5% when combining T1 and rsfMRI modalities. Feature weights that survived the p < 0.01 threshold for separation of the two groups revealed the strongest margin in the combined structural and functional regions underlying the medial temporal lobes in the limbic system. Discussion: An MRI-driven SVM model demonstrates accurate and precise prediction of later dementia conversion in aMCI patients. The multi-modal regions driving this prediction were the strongest in the medial temporal regions of the limbic system, consistent with literature on the progression of Alzheimer's disease.

Comparative analysis of default mode networks in major psychiatric disorders using resting-state EEG

Default mode network (DMN) is a set of functional brain structures coherently activated when individuals are in resting-state. In this study, we constructed multi-frequency band resting-state EEG-based DMN functional network models for major psychiatric disorders to easily compare their pathophysiological characteristics. Phase-locking values (PLVs) were evaluated to quantify functional connectivity; global and nodal clustering coefficients (CCs) were evaluated to quantify global and local connectivity patterns of DMN nodes, respectively. DMNs of patients with post-traumatic stress disorder (PTSD), obsessive compulsive disorder (OCD), panic disorder, major depressive disorder (MDD), bipolar disorder, schizophrenia (SZ), mild cognitive impairment (MCI), and Alzheimer's disease (AD) were constructed relative to their demographically-matched healthy control groups. Overall DMN patterns were then visualized and compared with each other. In global CCs, SZ and AD showed hyper-clustering in the theta band; OCD, MCI, and AD showed hypo-clustering in the low-alpha band; OCD and MDD showed hypo-clustering and hyper-clustering in low-beta, and high-beta bands, respectively. In local CCs, disease-specific patterns were observed. In the PLVs, lowered theta-band functional connectivity between the left lingual gyrus and the left hippocampus was frequently observed. Our comprehensive comparisons suggest EEG-based DMN as a useful vehicle for understanding altered brain networks of major psychiatric disorders.

Short- and Long-Term Functional Connectivity Differences Associated with Alzheimer's Disease Progression

Introduction

Progression of amnestic mild cognitive impairment (aMCI) to Alzheimer's disease (AD) is a clinical event with highly variable progression rates varying from 10–15% up to 30–34%. Functional connectivity (FC), the temporal similarity between spatially remote neurophysiological events, has previously been reported to differ between aMCI patients who progress to AD (pMCI) and those who do not (i.e., remain stable; sMCI). However, these reports had a short-term follow-up and do not provide insight into long-term AD progression.

Methods

Seventy-nine participants with a baseline and 78 with a 12-month, 51 with a 24-month, and 22 with a +48-month follow-up resting-state fMRI with aMCI diagnosis from the Alzheimer's Disease Neuroimaging Initiative database were included. FC was assessed using the CONN toolbox. Local correlation and group independent component analysis were utilized to compare regional functional coupling and between-network FC, respectively, between sMCI and pMCI groups. Two-sample t tests were used to test for statistically significant differences between groups, and paired t-tests were used to assess cognitive changes over time.

Results

All participants (i.e., 66 sMCI and 19 pMCI) had a baseline and a year follow-up fMRI scan. Progression from aMCI to AD occurred in 19 patients (10 at 12 months, 5 at 24 months, and 4 at >48 months), while 73 MCI patients remained cognitively stable (sMCI). The pMCI and sMCI cognitive profiles were different. More between-network FC than regional functional coupling differences were present between sMCI and pMCI patients. Activation in the salience network (SN) and the default mode network (DMN) was consistently different between sMCI and pMCI patients across time.

Discussion

sMCI and pMCI patients have different cognitive and FC profiles. Only pMCI patients showed cognitive differences across time. The DMN and SN showed local correlation and between-network FC differences between the sMCI and pMCI patient groups at multiple moments in time.

Convergent Functional Changes of Default Mode Network in Mild Cognitive Impairment Using Activation Likelihood Estimation

Background: Mild cognitive impairment (MCI) represents a transitional state between normal aging and dementia disorders, especially Alzheimer's disease (AD). The disruption of the default mode network (DMN) is often considered to be a potential biomarker for the progression from MCI to AD. The purpose of this study was to assess MRI-specific changes of DMN in MCI patients by elucidating the convergence of brain regions with abnormal DMN function.

Methods: We systematically searched PubMed, Ovid, and Web of science for relevant articles. We identified neuroimaging studies by using amplitude of low frequency fluctuation /fractional amplitude of low frequency fluctuation (ALFF/fALFF), regional homogeneity (ReHo), and functional connectivity (FC) in MCI patients. Based on the activation likelihood estimation (ALE) algorithm, we carried out connectivity modeling of coordination-based meta-analysis and functional meta-analysis.

Results: In total, this meta-analysis includes 39 articles on functional neuroimaging studies. Using computer software analysis, we discovered that DMN changes in patients with MCI mainly occur in bilateral inferior frontal lobe, right medial frontal lobe, left inferior parietal lobe, bilateral precuneus, bilateral temporal lobe, and parahippocampal gyrus (PHG).

Conclusions: Herein, we confirmed the presence of DMN-specific damage in MCI, which is helpful in revealing pathology of MCI and further explore mechanisms of conversion from MCI to AD. Therefore, we provide a new specific target and direction for delaying conversion from MCI to AD.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Combining Visual Rating Scales for Medial Temporal Lobe Atrophy and Posterior Atrophy to Identify Amnestic Mild Cognitive Impairment from Cognitively Normal Older Adults: Evidence Based on Two Cohorts

BACKGROUND

Visual rating scales for medial temporal lobe atrophy (MTA) and posterior atrophy (PA) have been reported to be useful for Alzheimer's disease diagnosis in routine clinical practice.

OBJECTIVE

To investigate the efficacy of combined MTA and PA visual rating scales to discriminate amnestic mild cognitive impairment (aMCI) patients from healthy controls.

METHODS

This study included T1-weighted MRI images from two different cohorts. In the first cohort, we recruited 73 patients with aMCI and 48 group-matched cognitively normal controls for training and validation. Visual assessments of MTA and PA were carried out for each participant. Global gray matter volume and density were estimated using voxel-based morphometry analysis as the objective reference. We investigated the discriminative power of a single visual rating scale and the combination of the MTA and PA rating scales for identifying aMCI. The second cohort, consisting of 33 aMCI patients and 45 controls, was used to verify the reliability of the visual assessments.

RESULTS

Compared with the single visual rating scale, the combination of the MTA and PA exhibited the best discriminative power, with an AUC of 0.818±0.041, which was similar to the diagnostic accuracy of the gray matter volumetric measures. The discriminative power of the combined MTA and PA was verified in the second cohort (AUC 0.824±0.058).

CONCLUSION

The combined MTA and PA rating scales demonstrated practical diagnostic value for distinguishing aMCI patients from controls, suggesting its potential to serve as a convenient and reproducible method to assess the degree of atrophy in clinical settings.

Altered Functional Connectivity of Hippocampal Subfields in Poststroke Dementia

BACKGROUND

The hippocampus (HP) plays a critical role in memory and orientational functions and is functionally heterogeneous along the longitudinal anterior-posterior axis. Although the previous study has reported volumetric atrophy in hippocampal subfields of patients with poststroke dementia (PSD), how the functional connectivity (FC) is altered in these subfields remains unclear.

PURPOSE

To examine the FC changes of the HP subfields in patients with PSD.

STUDY TYPE

Prospective.

POPULATION

Seventeen normal controls, 20 PSD, and 24 nondemented poststroke (PSND) patients.

FIELD STRENGTH/SEQUENCE

A 3.0 T/ T1-weighted imaging, resting-state functional and diffusion tensor imaging.

ASSESSMENT

We first segmented the HP using independent component analysis, and then used granger causality analysis to calculate the directed FCs (dFCs) between the subfields and the whole brain, and compared the dFCs among PSD, PSND, and controls.

STATISTICAL TESTS

Student's t-test, chi-square test, one-way ANCOVA, multiple regression, support vector machine, multiple comparison correction, and reproducibility analysis. A P value < 0.05 was considered statistically significant.

RESULTS

Our results showed HP was functionally divided into HP_head , HP_body , and HP_tail bilaterally along the longitudinal axis. PSD patients showed significant dementia-specific decreases in the inward information flow and increases in the outward information flow associated with the bilateral entire HP/HP_head and left HP_body (P < 0.05). Moreover, we observed significant correlations (P < 0.05) between the cognition score and the dFCs related to the bilateral entire HP and left HP_head in the PSD group. Furthermore, dFCs of the HP and its subfields improved the classification between the PSD and PSND patients (accuracy/sensitivity/specificity: 94%/95%/93%) compared to the clinical and demographic parameters alone.

DATA CONCLUSION

These findings suggest that altered transmission and reception of information in the HP. These alternations were specific to individual subfields in PSD patients and may offer insight into the neurophysiological mechanisms underlying PSD.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Functional connectivity of the anterior cingulate cortex with pain-related regions in children with post-traumatic headache

Introduction:

Post-traumatic headaches (PTH) are common following mild traumatic brain injury (mTBI). There is evidence of altered central pain processing in adult PTH; however, little is known about how children with PTH process pain. The anterior cingulate cortex (ACC) plays a critical role in descending central pain modulation. In this study, we explored whether the functional connectivity (FC) of the ACC is altered in children with PTH.

Methods:

In this case-control study, we investigated resting-state FC of 5 ACC seeds (caudal, dorsal, rostral, perigenual, and subgenual) in children with PTH ( n = 73) and without PTH ( n = 29) following mTBI, and healthy controls ( n = 27). Post-concussion symptoms were assessed using the Post-Concussion Symptom Inventory and the Child Health Questionnaire. Resting-state functional Magnetic Resonance Imaging (fMRI) data were used to generate maps of ACC FC. Group-level comparisons were performed within a target mask comprised of pain-related regions using FSL Randomise.

Results:

We found decreased FC between the right perigenual ACC and the left cerebellum, and increased FC between the right subgenual ACC and the left dorsolateral prefrontal cortex in children with PTH compared to healthy controls. The ACC FC in children without PTH following mTBI did not differ from the group with PTH or healthy controls. FC between rostral and perigenual ACC seeds and the cerebellum was increased in children with PTH with pre-injury headaches compared to those with PTH without pre-injury headaches. There was a positive relationship between PTH severity and rostral ACC FC with the bilateral thalamus, right hippocampus and periaqueductal gray.

Conclusions:

Central pain processing is altered in children with PTH. Pre-existing headaches help to drive this process.

Trial registration:

The PlayGame Trial was registered in ClinicalTrials.gov database ( ClinicalTrials.gov Identifier: NCT01874847).

Abnormal Default-Mode Network Homogeneity in Patients With Mild Cognitive Impairment in Chinese Communities

Background and Objective: Current evidence suggests that abnormalities within the default-mode network (DMN) play a key role in the broad-scale cognitive problems that characterize mild cognitive impairment (MCI). However, little is known about the alterations of DMN network homogeneity (NH) in MCI.

Methods: Resting-state functional magnetic resonance imaging scans (rs-fMRI) were collected from 38 MCI patients and 69 healthy controls matched for age, gender, and education. NH approach was employed to analyze the imaging dataset. Cognitive performance was measured with the Chinese version of Alzheimer's disease assessment scale-Cognitive subscale (ADAS-Cog).

Results: Two groups have no significant differences between demographic factors. And mean ADAS-Cog score in MCI was 12.02. MCI patients had significantly lower NH values than controls in the right anterior cingulate cortex and significantly higher NH values in the ventral medial prefrontal cortex(vmPFC) than those in healthy controls. No significant correlations were found between abnormal NH values and ADAS-Cog in the patients.

Conclusions: These findings provide further evidence that abnormal NH of the DMN exists in MCI, and highlight the significance of DMN in the pathophysiology of cognitive problems occurring in MCI.

Aberrant Brain Functional Connectivity Strength and Effective Connectivity in Patients with Type 2 Diabetes Mellitus

Alterations of brain functional connectivity in patients with type 2 diabetes mellitus (T2DM) have been reported by resting-state functional magnetic resonance imaging studies, but the underlying precise neuropathological mechanism remains unclear. This study is aimed at investigating the implicit alterations of functional connections in T2DM by integrating functional connectivity strength (FCS) and Granger causality analysis (GCA) and further exploring their associations with clinical characteristics. Sixty T2DM patients and thirty-three sex-, age-, and education-matched healthy controls (HC) were recruited. Global FCS analysis of resting-state functional magnetic resonance imaging was performed to explore seed regions with significant differences between the two groups; then, GCA was applied to detect directional effective connectivity (EC) between the seeds and other brain regions. Correlations of EC with clinical variables were further explored in T2DM patients. Compared with HC, T2DM patients showed lower FCS in the bilateral fusiform gyrus, right superior frontal gyrus (SFG), and right postcentral gyrus, but higher FCS in the right supplementary motor area (SMA). Moreover, altered directional EC was found between the left fusiform gyrus and bilateral lingual gyrus and right medial frontal gyrus (MFG), as well as between the right SFG and bilateral frontal regions. In addition, triglyceride, insulin, and plasma glucose levels were correlated with the abnormal EC of the left fusiform, while disease duration and cognitive function were associated with the abnormal EC of the right SFG in T2DM patients. These results suggest that T2DM patients show aberrant brain function connectivity strength and effective connectivity which is associated with the diabetes-related metabolic characteristics, disease duration, and cognitive function, providing further insights into the complex neural basis of diabetes.

Neuroimaging advances regarding subjective cognitive decline in preclinical Alzheimer's disease

Subjective cognitive decline (SCD) is regarded as the first clinical manifestation in the Alzheimer’s disease (AD) continuum. Investigating populations with SCD is important for understanding the early pathological mechanisms of AD and identifying SCD-related biomarkers, which are critical for the early detection of AD. With the advent of advanced neuroimaging techniques, such as positron emission tomography (PET) and magnetic resonance imaging (MRI), accumulating evidence has revealed structural and functional brain alterations related to the symptoms of SCD. In this review, we summarize the main imaging features and key findings regarding SCD related to AD, from local and regional data to connectivity-based imaging measures, with the aim of delineating a multimodal imaging signature of SCD due to AD. Additionally, the interaction of SCD with other risk factors for dementia due to AD, such as age and the Apolipoprotein E (ApoE) ɛ4 status, has also been described. Finally, the possible explanations for the inconsistent and heterogeneous neuroimaging findings observed in individuals with SCD are discussed, along with future directions. Overall, the literature reveals a preferential vulnerability of AD signature regions in SCD in the context of AD, supporting the notion that individuals with SCD share a similar pattern of brain alterations with patients with mild cognitive impairment (MCI) and dementia due to AD. We conclude that these neuroimaging techniques, particularly multimodal neuroimaging techniques, have great potential for identifying the underlying pathological alterations associated with SCD. More longitudinal studies with larger sample sizes combined with more advanced imaging modeling approaches such as artificial intelligence are still warranted to establish their clinical utility.

Large-Scale Structural Covariance Networks Predict Age in Middle-to-Late Adulthood: A Novel Brain Aging Biomarker

The aging process is accompanied by changes in the brain's cortex at many levels. There is growing interest in summarizing these complex brain-aging profiles into a single, quantitative index that could serve as a biomarker both for characterizing individual brain health and for identifying neurodegenerative and neuropsychiatric diseases. Using a large-scale structural covariance network (SCN)-based framework with machine learning algorithms, we demonstrate this framework's ability to predict individual brain age in a large sample of middle-to-late age adults, and highlight its clinical specificity for several disease populations from a network perspective. A proposed estimator with 40 SCNs could predict individual brain age, balancing between model complexity and prediction accuracy. Notably, we found that the most significant SCN for predicting brain age included the caudate nucleus, putamen, hippocampus, amygdala, and cerebellar regions. Furthermore, our data indicate a larger brain age disparity in patients with schizophrenia and Alzheimer's disease than in healthy controls, while this metric did not differ significantly in patients with major depressive disorder. These findings provide empirical evidence supporting the estimation of brain age from a brain network perspective, and demonstrate the clinical feasibility of evaluating neurological diseases hypothesized to be associated with accelerated brain aging.

Brain Homotopic Connectivity in Mild Cognitive Impairment APOE-ε4 Carriers

Individuals with mild cognitive impairment (MCI) are regarded as being at high risk of developing Alzheimer's disease (AD). The apolipoprotein E (APOE) ε4 allele is a well-established genetic risk factor for developing AD. In the present study, by using voxel-mirrored homotopic connectivity (VMHC), we aimed to explore the potential functional disruptions in MCI APOE-ε4 carriers. Resting-state functional magnetic resonance imaging was performed in 35 MCI APOE-ε4 carriers (27 APOE-ε3ε4, 8 APOE-ε4ε4) and 42 MCI APOE-ε4 noncarriers (APOE-ε3ε3). VMHC was employed to investigate the alterations in functional connectivity in MCI APOE-ε4 carriers. We further investigated the seed-based functional connectivity between the VMHC values of altered regions and other brain regions in the two groups. The results showed that MCI APOE-ε4 carriers presented increased VMHC in the inferior frontal gyrus/insula and middle frontal gyrus/superior frontal gyrus in comparison with noncarriers. We found that MCI APOE-ε4 carriers showed increased functional connectivity between the seed regions (bilateral inferior frontal gyri/insula and bilateral middle frontal gyri/superior frontal gyri) and broad brain areas, including the frontal, temporal, parietal, and cerebellar regions. Our findings provide neuroimaging evidence for the modulation of the APOE genotype on the neurodegenerative disease phenotype and may be potentially important for monitoring disease progression in double-high-risk populations of AD.

Increased intrinsic default-mode network activity as a compensatory mechanism in aMCI: a resting-state functional connectivity MRI study

Numerous studies have investigated the differences in the mean functional connectivity (FC) strength between amnestic mild cognitive impairment (aMCI) patients and normal subjects using resting-state functional magnetic resonance imaging. However, whether the mean FC is increased, decreased or unchanged in aMCI patients compared to normal controls remains unclear. Two factors might lead to inconsistent results: the determination of regions of interest and the reliability of the FC.

We explored differences in FC and the degree centrality (Dc) constructed by the bootstrap method, between and within networks (default-mode network (DN), frontoparietal control network (CN), dorsal attention network (AN)), and resulting from a hierarchical-clustering algorithm.

The mean FC within the DN and CN was significantly increased (P < 0.05, uncorrected) in patients. Significant increases (P < 0.05, uncorrected) in the mean FC were found in patients between DN and CN and between DN and AN. Five pairs of FC (false discovery rate corrected) and the Dc of six regions (Bonferroni corrected) displayed a significant increase in patients. Lower cognitive ability was significantly associated with a greater increase in the Dc of the left superior temporal sulcus.

Our results demonstrate that the early dysfunctions in aMCI disease are mainly compensatory impairments.

Functional Connectivity in Neurodegenerative Disorders: Alzheimer's Disease and Frontotemporal Dementia

Neurodegenerative disorders are a growing cause of morbidity and mortality worldwide. Onset is typically insidious and clinical symptoms of behavioral change, memory loss, or cognitive dysfunction may not be evident early in the disease process. Efforts have been made to discover biomarkers that allow for earlier diagnosis of neurodegenerative disorders, to initiate treatment that may slow the course of clinical deterioration. Neuronal dysfunction occurs earlier than clinical symptoms manifest. Thus, assessment of neuronal function using functional brain imaging has been examined as a potential biomarker. While most early studies used task-functional magnetic resonance imaging (fMRI), with the more recent technique of resting-state fMRI, "intrinsic" relationships between brain regions or brain networks have been studied in greater detail in neurodegenerative disorders. In Alzheimer's disease, the most common neurodegenerative disorder, and frontotemporal dementia, another of the common dementias, specific brain networks may be particularly susceptible to dysfunction. In this review, we highlight the major findings of functional connectivity assessed by resting state fMRI in Alzheimer's disease and frontotemporal dementia.

Feature Selection and Combination of Information in the Functional Brain Connectome for Discrimination of Mild Cognitive Impairment and Analyses of Altered Brain Patterns

Mild cognitive impairment (MCI) is often considered a critical time window for predicting early conversion to Alzheimer’s disease (AD). Brain functional connectome data (i.e., functional connections, global and nodal graph metrics) based on resting-state functional magnetic resonance imaging (rs-fMRI) provides numerous information about brain networks and has been used to discriminate normal controls (NCs) from subjects with MCI. In this paper, Student’s t-tests and group-least absolute shrinkage and selection operator (group-LASSO) were used to extract functional connections with significant differences and the most discriminative network nodes, respectively. Based on group-LASSO, the middle temporal, inferior temporal, lingual, posterior cingulate, and middle frontal gyri were the most predominant brain regions for nodal observation in MCI patients. Nodal graph metrics (within-module degree, participation coefficient, and degree centrality) showed the maximum discriminative ability. To effectively combine the multipattern information, we employed the multiple kernel learning support vector machine (MKL-SVM). Combined with functional connectome information, the MKL-SVM achieved a good classification performance (area under the receiving operating characteristic curve = 0.9728). Additionally, the altered brain connectome pattern revealed that functional connectivity was generally decreased in the whole-brain network, whereas graph theory topological attributes of some special nodes in the brain network were increased in MCI patients. Our findings demonstrate that optimal feature selection and combination of all connectome features (i.e., functional connections, global and nodal graph metrics) can achieve good performance in discriminating NCs from MCI subjects. Thus, the combination of functional connections and global and nodal graph metrics of brain networks can predict the occurrence of MCI and contribute to the early clinical diagnosis of AD.

Classification and Visualization of Alzheimer's Disease using Volumetric Convolutional Neural Network and Transfer Learning

Recently, deep-learning-based approaches have been proposed for the classification of neuroimaging data related to Alzheimer's disease (AD), and significant progress has been made. However, end-to-end learning that is capable of maximizing the impact of deep learning has yet to receive much attention due to the endemic challenge of neuroimaging caused by the scarcity of data. Thus, this study presents an approach meant to encourage the end-to-end learning of a volumetric convolutional neural network (CNN) model for four binary classification tasks (AD vs. normal control (NC), progressive mild cognitive impairment (pMCI) vs. NC, stable mild cognitive impairment (sMCI) vs. NC and pMCI vs. sMCI) based on magnetic resonance imaging (MRI) and visualizes its outcomes in terms of the decision of the CNNs without any human intervention. In the proposed approach, we use convolutional autoencoder (CAE)-based unsupervised learning for the AD vs. NC classification task, and supervised transfer learning is applied to solve the pMCI vs. sMCI classification task. To detect the most important biomarkers related to AD and pMCI, a gradient-based visualization method that approximates the spatial influence of the CNN model's decision was applied. To validate the contributions of this study, we conducted experiments on the ADNI database, and the results demonstrated that the proposed approach achieved the accuracies of 86.60% and 73.95% for the AD and pMCI classification tasks respectively, outperforming other network models. In the visualization results, the temporal and parietal lobes were identified as key regions for classification.

The effect of white matter signal abnormalities on default mode network connectivity in mild cognitive impairment

Regions within the default mode network (DMN) are particularly vulnerable to Alzheimer's disease pathology and mechanisms of DMN disruption in mild cognitive impairment (MCI) are still unclear. White matter lesions are presumed to be mechanistically linked to vascular dysfunction whereas cortical atrophy may be related to neurodegeneration. We examined associations between DMN seed‐based connectivity, white matter lesion load, and cortical atrophy in MCI and cognitively healthy controls. MCI showed decreased functional connectivity (FC) between the precuneus‐seed and bilateral lateral temporal cortex (LTC), medial prefrontal cortex (mPFC), posterior cingulate cortex, and inferior parietal lobe compared to those with controls. When controlling for white matter lesion volume, DMN connectivity differences between groups were diminished within bilateral LTC, although were significantly increased in the mPFC explained by significant regional associations between white matter lesion volume and DMN connectivity only in the MCI group. When controlling for cortical thickness, DMN FC was similarly decreased across both groups. These findings suggest that white matter lesions and cortical atrophy are differentially associated with alterations in FC patterns in MCI. Associations between white matter lesions and DMN connectivity in MCI further support at least a partial but important vascular contribution to age‐associated neural and cognitive impairment.

Automated Brain MRI Volumetry Differentiates Early Stages of Alzheimer's Disease From Normal Aging

As an enrichment strategy supplemented by the diagnostic framework of subjective cognitive decline (SCD), SCD plus identifies features that may increase the likelihood of including future-Alzheimer's disease (AD) patients. This study aimed to identify the shared and distinct atrophy patterns between patients specified by SCD plus and amnestic mild cognitive impairment (aMCI, a prodromal stage of AD) and to investigate the extent that automated brain magnetic resonance imaging (MRI) volumetry can differentiate patients with SCD from normal control (NC) participants and patients with aMCI. We acquired structural MRI brain scans from 44 patients with aMCI, 40 patients with SCD (who met the major criteria of SCD plus), and 48 NC participants. Automatic brain segmentation was performed to quantify the volumetric measures of cognitive-relevant areas. These volumetric measures were compared across the 3 groups with analysis of variance. In addition, we performed support vector machine analyses using volumetric measures of single regions or multiple regions to further evaluate the sensitivity of automated brain volumetry in differentiating a specific group from another. The atrophy patterns in patients with aMCI and SCD were similar. Using the regional volumetric measures, we achieved high performance in differentiating aMCI and SCD from NCs (average classification accuracy [ACC] > 90%). However, the performance was not ideal when differentiating aMCI from SCD (ACC < 63%). In conclusion, patients with SCD specified by SCD plus presented similar atrophy patterns as patients with aMCI, which was distinguishable from NC participants. Future studies should aim to associate the atrophy patterns of SCD with possible conversion to aMCI or AD in a longitudinal design.

Premorbid Alterations of Spontaneous Brain Activity in Elderly Patients With Early Post-operative Cognitive Dysfunction: A Pilot Resting-State Functional MRI Study

Background: Elderly patients with pre-existing cognitive impairment are susceptible to post-operative cognitive dysfunction (POCD). In this study, we investigated whether there is pre-existing local homogeneity and functional connectivity alteration in the brain before surgery for POCD patients as compared to that in non-POCD patients.

Methods: Eighty elderly patients undergoing major thoracic or abdominal surgeries were recruited. Resting-state functional MRI was scanned at least 1 day before surgery. Neuropsychological tests (NPTs) were performed before surgery and at discharge, respectively. Pre-operative regional homogeneity (ReHo) and resting-state functional connectivity (RSFC) were compared between POCD patients and non-POCD patients, respectively. Partial correlation between NPTs and ReHo or RSFC was analyzed by adjusting for confounding factors.

Results: Significant difference (P < 0.001, Gaussian Random Field (GRF) correction which is a multiple comparisons correction method at cluster level, cluster size > 49) in ReHo between POCD patients and non-POCD patients was detected in right hippocampus/parahippocampus. Pre-operative RSFC between right hippocampus/parahippocampus and right middle/inferior temporal gyrus increased in POCD patients (P < 0.001, GRF correction for multiple comparisons) when compared with that in non-POCD patients.RSFC significantly correlated with composite Z-score (r = 0.46, 95% CI [0.234, 0.767], P = 0.002) or Digit Symbol Substitution Test Z-scores (r = 0.31, 95% CI [0.068, 0.643], P = 0.046) after adjusting for confounding factors.

Conclusions: The results suggest that premorbid alterations of spontaneous brain activity might exist in elderly patients who develop early POCD. The neural mechanism by which patients with pre-operative abnormal spontaneous activity are susceptible to POCD requires further study.

No relationship between fornix and cingulum degradation and within-network decreases in functional connectivity in prodromal Alzheimer's disease

INTRODUCTION

The earliest changes in the brain due to Alzheimer's disease are associated with the neural networks related to memory function. We investigated changes in functional and structural connectivity among regions that support memory function in prodromal Alzheimer's disease, i.e., during the mild cognitive impairment (MCI) stage.

METHODS

Twenty-three older healthy controls and 25 adults with MCI underwent multimodal MRI scanning. Limbic white matter tracts-the fornix, parahippocampal cingulum, retrosplenial cingulum, subgenual cingulum and uncinate fasciculus-were reconstructed in ExploreDTI using constrained spherical deconvolution-based tractography. Using a network-of-interest approach, resting-state functional connectivity time-series correlations among sub-parcellations of the default mode and limbic networks, the hippocampus and the thalamus were calculated in Conn.

ANALYSIS

Controlling for age, education, and gender between group linear regressions of five diffusion-weighted measures and of resting state connectivity measures were performed per hemisphere. FDR-corrections were performed within each class of measures. Correlations of within-network Fisher Z-transformed correlation coefficients and the mean diffusivity per tract were performed. Whole-brain graph theory measures of cluster coefficient and average path length were inspecting using the resting state data.

RESULTS & CONCLUSION

MCI-related changes in white matter structure were found in the fornix, left parahippocampal cingulum, left retrosplenial cingulum and left subgenual cingulum. Functional connectivity decreases were observed in the MCI group within the DMN-a sub-network, between the hippocampus and sub-areas -a and -c of the DMN, between DMN-c and DMN-a, and, in the right hemisphere only between DMN-c and both the thalamus and limbic-a. No relationships between white matter tract 'integrity' (mean diffusivity) and within sub-network functional connectivity were found. Graph theory revealed that changes in the MCI group was mostly restricted to diminished between-neighbour connections of the hippocampi and of nodes within DMN-a and DMN-b.

ASAF: altered spontaneous activity fingerprinting in Alzheimer's disease based on multisite fMRI

Several monocentric studies have noted alterations in spontaneous brain activity in Alzheimer's disease (AD), although there is no consensus on the altered amplitude of low-frequency fluctuations in AD patients. The main aim of the present study was to identify a reliable and reproducible abnormal brain activity pattern in AD. The amplitude of local brain activity (AM), which can provide fast mapping of spontaneous brain activity across the whole brain, was evaluated based on multisite rs-fMRI data for 688 subjects (215 normal controls (NCs), 221 amnestic mild cognitive impairment (aMCI) 252 AD). Two-sample t-tests were used to detect group differences between AD patients and NCs from the same site. Differences in the AM maps were statistically analyzed via the Stouffer's meta-analysis. Consistent regions of lower spontaneous brain activity in the default mode network and increased activity in the bilateral hippocampus/parahippocampus, thalamus, caudate nucleus, orbital part of the middle frontal gyrus and left fusiform were observed in the AD patients compared with those in NCs. Significant correlations (P < 0.05, Bonferroni corrected) between the normalized amplitude index and Mini-Mental State Examination scores were found in the identified brain regions, which indicates that the altered brain activity was associated with cognitive decline in the patients. Multivariate analysis and leave-one-site-out cross-validation led to a 78.49% prediction accuracy for single-patient classification. The altered activity patterns of the identified brain regions were largely correlated with the FDG-PET results from another independent study. These results emphasized the impaired brain activity to provide a robust and reproducible imaging signature of AD.

Resting State Dynamic Functional Connectivity in Neurodegenerative Conditions: A Review of Magnetic Resonance Imaging Findings

In the last few decades, brain functional connectivity (FC) has been extensively assessed using resting-state functional magnetic resonance imaging (RS-fMRI), which is able to identify temporally correlated brain regions known as RS functional networks. Fundamental insights into the pathophysiology of several neurodegenerative conditions have been provided by studies in this field. However, most of these studies are based on the assumption of temporal stationarity of RS functional networks, despite recent evidence suggests that the spatial patterns of RS networks may change periodically over the time of an fMRI scan acquisition. For this reason, dynamic functional connectivity (dFC) analysis has been recently implemented and proposed in order to consider the temporal fluctuations of FC. These approaches hold promise to provide fundamental information for the identification of pathophysiological and diagnostic markers in the vast field of neurodegenerative diseases. This review summarizes the main currently available approaches for dFC analysis and reports their recent applications for the assessment of the most common neurodegenerative conditions, including Alzheimer’s disease, Parkinson’s disease, dementia with Lewy bodies, and frontotemporal dementia. Critical state-of-the-art findings, limitations, and future perspectives regarding the analysis of dFC in these diseases are provided from both a clinical and a technical point of view.

Hybrid multivariate pattern analysis combined with extreme learning machine for Alzheimer's dementia diagnosis using multi-measure rs-fMRI spatial patterns

Background

Early diagnosis of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) is essential for timely treatment. Machine learning and multivariate pattern analysis (MVPA) for the diagnosis of brain disorders are explicitly attracting attention in the neuroimaging community. In this paper, we propose a voxel-wise discriminative framework applied to multi-measure resting-state fMRI (rs-fMRI) that integrates hybrid MVPA and extreme learning machine (ELM) for the automated discrimination of AD and MCI from the cognitive normal (CN) state.

Materials and methods

We used two rs-fMRI cohorts: the public Alzheimer’s disease Neuroimaging Initiative database (ADNI2) and an in-house Alzheimer’s disease cohort from South Korea, both including individuals with AD, MCI, and normal controls. After extracting three-dimensional (3-D) patterns measuring regional coherence and functional connectivity during the resting state, we performed univariate statistical t-tests to generate a 3-D mask that retained only voxels showing significant changes. Given the initial univariate features, to enhance discriminative patterns, we implemented MVPA feature reduction using support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO), in combination with the univariate t-test. Classifications were performed by an ELM, and its efficiency was compared to linear and nonlinear (radial basis function) SVMs.

Results

The maximal accuracies achieved by the method in the ADNI2 cohort were 98.86% (p<0.001) and 98.57% (p<0.001) for AD and MCI vs. CN, respectively. In the in-house cohort, the same accuracies were 98.70% (p<0.001) and 94.16% (p<0.001).

Conclusion

From a clinical perspective, combining extreme learning machine and hybrid MVPA applied on concatenations of multiple rs-fMRI biomarkers can potentially assist the clinicians in AD and MCI diagnosis.

Prediction of Conversion From Amnestic Mild Cognitive Impairment to Alzheimer's Disease Based on the Brain Structural Connectome

Background: Early prediction of disease progression in patients with amnestic mild cognitive impairment (aMCI) is important for early diagnosis and intervention of Alzheimer's disease (AD). Previous brain network studies have suggested topological disruptions of the brain connectome in aMCI patients. However, whether brain connectome markers at baseline can predict longitudinal conversion from aMCI to AD remains largely unknown.

Methods: In this study, 52 patients with aMCI and 26 demographically matched healthy controls from a longitudinal cohort were evaluated. During 2 years of follow-up, 26 patients with aMCI were retrospectively classified as aMCI converters and 26 patients remained stable as aMCI non-converters based on whether they were subsequently diagnosed with AD. For each participant, diffusion tensor imaging at baseline and deterministic tractography were used to map the whole-brain white matter structural connectome. Graph theoretical analysis was applied to investigate the convergent and divergent connectivity patterns of structural connectome between aMCI converters and non-converters.

Results: Disrupted topological organization of the brain structural connectome were identified in both aMCI converters and non-converters. More severe disruptions of structural connectivity in aMCI converters compared with non-converters were found, especially in the default-mode network regions and connections. Finally, a support vector machine-based classification demonstrated the good discriminative ability of structural connectivity in differentiating aMCI patients from controls with an accuracy of 98%, and in discriminating converters from non-converters with an accuracy of 81%.

Conclusion: Our study provides potential structural connectome/connectivity-based biomarkers for predicting disease progression in aMCI, which is important for the early diagnosis of AD.

Resting State Abnormalities of the Default Mode Network in Mild Cognitive Impairment: A Systematic Review and Meta-Analysis

BACKGROUND

Large-scale brain networks such as the default mode network (DMN) are often disrupted in Alzheimer's disease (AD). Numerous studies have examined DMN functional connectivity in those with mild cognitive impairment (MCI), a presumed AD precursor, to discover a biomarker of AD risk. Prior reviews were qualitative or limited in scope or approach.

OBJECTIVE

We aimed to systematically and quantitatively review DMN resting state fMRI studies comparing MCI and healthy comparison (HC) groups.

METHODS

PubMed was searched for relevant articles. Study characteristics were abstracted and the number of studies showing no group difference or hyper- versus hypo-connnectivity in MCI was tallied. A voxel-wise (ES-SDM) meta-analysis was conducted to identify regional group differences.

RESULTS

Qualitatively, our review of 57 MCI versus HC comparisons suggests substantial inconsistency; 9 showed no group difference, 8 showed MCI > HC and 22 showed HC > MCI across the brain, and 18 showed regionally-mixed directions of effect. The meta-analysis of 31 studies revealed areas of significant hypo- and hyper-connectivity in MCI, including hypoconnectivity in the posterior cingulate cortex/precuneus (z = -3.1, p < 0.0001). Very few individual studies, however, showed patterns resembling the meta-analytic results. Methodological differences did not appear to explain inconsistencies.

CONCLUSIONS

The pattern of altered resting DMN function or connectivity in MCI is complex and variable across studies. To date, no index of DMN connectivity qualifies as a useful biomarker of MCI or risk for AD. Refinements to MCI diagnosis, including other biological markers, or longitudinal studies of progression to AD, might identify DMN alterations predictive of AD risk.

Resting-State Functional Connectivity Changes Associated with Visuospatial Cognitive Deficits in Patients with Mild Alzheimer Disease

BACKGROUND/AIMS

Alzheimer disease (AD) is a neurodegenerative disorder characterized by progressive disconnection of various brain networks leading to neuropsychological impairment. Pathology in the visual association areas has been documented in presymptomatic AD and therefore we aimed at examining the relationship between brain connectivity and visuospatial (VS) cognitive deficits in early AD.

METHODS

Tests for VS working memory, episodic memory and construction were used to classify patients with AD (n = 48) as having severe VS deficits (n = 12, female = 4) or mild deficits (n = 11, female = 4). Resting-state functional magnetic resonance imaging and structural images were acquired as per the standard protocols. Between-group differences in resting-state functional connectivity (rsFC) were examined by dual regression analysis correcting for age, gender, and total brain volume.

RESULTS

Patients with AD having severe VS deficits exhibited significantly reduced rsFC in bilateral lingual gyri of the visual network compared to patients with mild VS deficits.

CONCLUSION

Reduced rsFC in the visual network in patients with more severe VS deficits may be a functional neuroimaging biomarker reflecting hypoconnectivity of the brain with progressive VS deficits during early AD.

Non-linear ICA Analysis of Resting-State fMRI in Mild Cognitive Impairment

Compared to linear independent component analysis (ICA), non-linear ICA is more suitable for the decomposition of mixed components. Existing studies of functional magnetic resonance imaging (fMRI) data by using linear ICA assume that the brain's mixed signals, which are caused by the activity of brain, are formed through the linear combination of source signals. But the application of the non-linear combination of source signals is more suitable for the mixed signals of brain. For this reason, we investigated statistical differences in resting state networks (RSNs) on 32 healthy controls (HC) and 38 mild cognitive impairment (MCI) patients using post-nonlinear ICA. Post-nonlinear ICA is one of the non-linear ICA methods. Firstly, the fMRI data of all subjects was preprocessed. The second step was to extract independent components (ICs) of fMRI data of all subjects. In the third step, we calculated the correlation coefficient between ICs and RSN templates, and selected ICs of the largest spatial correlation coefficient. The ICs represent the corresponding RSNs. After finding out the eight RSNs of MCI group and HC group, one sample t-tests were performed. Finally, in order to compare the differences of RSNs between MCI and HC groups, the two-sample t-tests were carried out. We found that the functional connectivity (FC) of RSNs in MCI patients was abnormal. Compared with HC, MCI patients showed the increased and decreased FC in default mode network (DMN), central executive network (CEN), dorsal attention network (DAN), somato-motor network (SMN), visual network(VN), MCI patients displayed the specifically decreased FC in auditory network (AN), self-referential network (SRN). The FC of core network (CN) did not reveal significant group difference. The results indicate that the abnormal FC in RSNs is selective in MCI patients.

Classification of Alzheimer's Disease, Mild Cognitive Impairment, and Cognitively Unimpaired Individuals Using Multi-feature Kernel Discriminant Dictionary Learning

Accurate classification of either patients with Alzheimer's disease (AD) or patients with mild cognitive impairment (MCI), the prodromal stage of AD, from cognitively unimpaired (CU) individuals is important for clinical diagnosis and adequate intervention. The current study focused on distinguishing AD or MCI from CU based on the multi-feature kernel supervised within-Class-similar discriminative dictionary learning algorithm (MKSCDDL), which we introduced in a previous study, demonstrating that MKSCDDL had superior performance in face recognition. Structural magnetic resonance imaging (sMRI), fluorodeoxyglucose (FDG) positron emission tomography (PET), and florbetapir-PET data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were all included for classification of AD vs. CU, MCI vs. CU, as well as AD vs. MCI (113 AD patients, 110 MCI patients, and 117 CU subjects). By adopting MKSCDDL, we achieved a classification accuracy of 98.18% for AD vs. CU, 78.50% for MCI vs. CU, and 74.47% for AD vs. MCI, which in each instance was superior to results obtained using several other state-of-the-art approaches (MKL, JRC, mSRC, and mSCDDL). In addition, testing time results outperformed other high quality methods. Therefore, the results suggested that the MKSCDDL procedure is a promising tool for assisting early diagnosis of diseases using neuroimaging data.