Atrophy of the medial occipitotemporal, inferior, and middle temporal gyri in non-demented elderly predict decline to Alzheimer's disease

Unveiling DNA methylation in Alzheimer's disease: a review of array-based human brain studies

The intricacies of Alzheimer's disease pathogenesis are being increasingly illuminated by the exploration of epigenetic mechanisms, particularly DNA methylation. This review comprehensively surveys recent human-centered studies that investigate whole genome DNA methylation in Alzheimer's disease neuropathology. The examination of various brain regions reveals distinctive DNA methylation patterns that associate with the Braak stage and Alzheimer's disease progression. The entorhinal cortex emerges as a focal point due to its early histological alterations and subsequent impact on downstream regions like the hippocampus. Notably, ANK1 hypermethylation, a protein implicated in neurofibrillary tangle formation, was recurrently identified in the entorhinal cortex. Further, the middle temporal gyrus and prefrontal cortex were shown to exhibit significant hypermethylation of genes like HOXA3, RHBDF2, and MCF2L, potentially influencing neuroinflammatory processes. The complex role of BIN1 in late-onset Alzheimer's disease is underscored by its association with altered methylation patterns. Despite the disparities across studies, these findings highlight the intricate interplay between epigenetic modifications and Alzheimer's disease pathology. Future research efforts should address methodological variations, incorporate diverse cohorts, and consider environmental factors to unravel the nuanced epigenetic landscape underlying Alzheimer's disease progression.

Cluster-Based White Matter Signatures and the Risk of Dementia, Stroke, and Mortality in Community-Dwelling Adults

BACKGROUND AND OBJECTIVES

Markers of white matter (WM) injury on brain MRI are important indicators of brain health. Different patterns of WM atrophy, WM hyperintensities (WMHs), and microstructural integrity could reflect distinct pathologies and disease risks, but large-scale imaging studies investigating WM signatures are lacking. This study aims to identify distinct WM signatures using brain MRI in community-dwelling adults, determine underlying risk factor profiles, and assess risks of dementia, stroke, and mortality associated with each signature.

METHODS

Between 2005 and 2016, we measured WMH volume, WM volume, fractional anisotropy (FA), and mean diffusivity (MD) using automated pipelines on structural and diffusion MRI in community-dwelling adults aged older than 45 years of the Rotterdam study. Continuous surveillance was conducted for dementia, stroke, and mortality. We applied hierarchical clustering to identify separate WM injury clusters and Cox proportional hazard models to determine their risk of dementia, stroke, and mortality.

RESULTS

We included 5,279 participants (mean age 65.0 years, 56.0% women) and identified 4 distinct data-driven WM signatures: (1) above-average microstructural integrity and little WM atrophy and WMH; (2) above-average microstructural integrity and little WMH, but substantial WM atrophy; (3) poor microstructural integrity and substantial WMH, but little WM atrophy; and (4) poor microstructural integrity with substantial WMH and WM atrophy. Prevalence of cardiovascular risk factors, lacunes, and cerebral microbleeds was higher in clusters 3 and 4 than in clusters 1 and 2. During a median 10.7 years of follow-up, 291 participants developed dementia, 220 had a stroke, and 910 died. Compared with cluster 1, dementia risk was increased for all clusters, notably cluster 3 (hazard ratio [HR] 3.06, 95% CI 2.12-4.42), followed by cluster 4 (HR 2.31, 95% CI 1.58-3.37) and cluster 2 (HR 1.67, 95% CI 1.17-2.38). Compared with cluster 1, risk of stroke was higher only for clusters 3 (HR 1.55, 95% CI 1.02-2.37) and 4 (HR 1.94, 95% CI 1.30-2.89), whereas mortality risk was increased in all clusters (cluster 2: HR 1.27, 95% CI 1.06-1.53, cluster 3: HR 1.65, 95% CI 1.35-2.03, cluster 4: HR 1.76, 95% CI 1.44-2.15), compared with cluster 1. Models including clusters instead of an individual imaging marker showed a superior goodness of fit for dementia and mortality, but not for stroke.

DISCUSSION

Clustering can derive WM signatures that are differentially associated with dementia, stroke, and mortality risk. Future research should incorporate spatial information of imaging markers.

Automated free speech analysis reveals distinct markers of Alzheimer's and frontotemporal dementia

Dementia can disrupt how people experience and describe events as well as their own role in them. Alzheimer's disease (AD) compromises the processing of entities expressed by nouns, while behavioral variant frontotemporal dementia (bvFTD) entails a depersonalized perspective with increased third-person references. Yet, no study has examined whether these patterns can be captured in connected speech via natural language processing tools. To tackle such gaps, we asked 96 participants (32 AD patients, 32 bvFTD patients, 32 healthy controls) to narrate a typical day of their lives and calculated the proportion of nouns, verbs, and first- or third-person markers (via part-of-speech and morphological tagging). We also extracted objective properties (frequency, phonological neighborhood, length, semantic variability) from each content word. In our main study (with 21 AD patients, 21 bvFTD patients, and 21 healthy controls), we used inferential statistics and machine learning for group-level and subject-level discrimination. The above linguistic features were correlated with patients' scores in tests of general cognitive status and executive functions. We found that, compared with HCs, (i) AD (but not bvFTD) patients produced significantly fewer nouns, (ii) bvFTD (but not AD) patients used significantly more third-person markers, and (iii) both patient groups produced more frequent words. Machine learning analyses showed that these features identified individuals with AD and bvFTD (AUC = 0.71). A generalizability test, with a model trained on the entire main study sample and tested on hold-out samples (11 AD patients, 11 bvFTD patients, 11 healthy controls), showed even better performance, with AUCs of 0.76 and 0.83 for AD and bvFTD, respectively. No linguistic feature was significantly correlated with cognitive test scores in either patient group. These results suggest that specific cognitive traits of each disorder can be captured automatically in connected speech, favoring interpretability for enhanced syndrome characterization, diagnosis, and monitoring.

Synaptic density patterns in early Alzheimer's disease assessed by independent component analysis

Synaptic loss is a primary pathology in Alzheimer's disease and correlates best with cognitive impairment as found in post-mortem studies. Previously, we observed in vivo reductions of synaptic density with [11C]UCB-J PET (radiotracer for synaptic vesicle protein 2A) throughout the neocortex and medial temporal brain regions in early Alzheimer's disease. In this study, we applied independent component analysis to synaptic vesicle protein 2A-PET data to identify brain networks associated with cognitive deficits in Alzheimer's disease in a blinded data-driven manner. [11C]UCB-J binding to synaptic vesicle protein 2A was measured in 38 Alzheimer's disease (24 mild Alzheimer's disease dementia and 14 mild cognitive impairment) and 19 cognitively normal participants. [11C]UCB-J distribution volume ratio values were calculated with a whole cerebellum reference region. Principal components analysis was first used to extract 18 independent components to which independent component analysis was then applied. Subject loading weights per pattern were compared between groups using Kruskal-Wallis tests. Spearman's rank correlations were used to assess relationships between loading weights and measures of cognitive and functional performance: Logical Memory II, Rey Auditory Verbal Learning Test-long delay, Clinical Dementia Rating sum of boxes and Mini-Mental State Examination. We observed significant differences in loading weights among cognitively normal, mild cognitive impairment and mild Alzheimer's disease dementia groups in 5 of the 18 independent components, as determined by Kruskal-Wallis tests. Only Patterns 1 and 2 demonstrated significant differences in group loading weights after correction for multiple comparisons. Excluding the cognitively normal group, we observed significant correlations between the loading weights for Pattern 1 (left temporal cortex and the cingulate gyrus) and Clinical Dementia Rating sum of boxes (r = -0.54, P = 0.0019), Mini-Mental State Examination (r = 0.48, P = 0.0055) and Logical Memory II score (r = 0.44, P = 0.013). For Pattern 2 (temporal cortices), significant associations were demonstrated between its loading weights and Logical Memory II score (r = 0.34, P = 0.0384). Following false discovery rate correction, only the relationship between the Pattern 1 loading weights with Clinical Dementia Rating sum of boxes (r = -0.54, P = 0.0019) and Mini-Mental State Examination (r = 0.48, P = 0.0055) remained statistically significant. We demonstrated that independent component analysis could define coherent spatial patterns of synaptic density. Furthermore, commonly used measures of cognitive performance correlated significantly with loading weights for two patterns within only the mild cognitive impairment/mild Alzheimer's disease dementia group. This study leverages data-centric approaches to augment the conventional region-of-interest-based methods, revealing distinct patterns that differentiate between mild cognitive impairment and mild Alzheimer's disease dementia, marking a significant advancement in the field.

Automated detection of Alzheimer's disease: a multi-modal approach with 3D MRI and amyloid PET

Recent advances in deep learning and imaging technologies have revolutionized automated medical image analysis, especially in diagnosing Alzheimer's disease through neuroimaging. Despite the availability of various imaging modalities for the same patient, the development of multi-modal models leveraging these modalities remains underexplored. This paper addresses this gap by proposing and evaluating classification models using 2D and 3D MRI images and amyloid PET scans in uni-modal and multi-modal frameworks. Our findings demonstrate that models using volumetric data learn more effective representations than those using only 2D images. Furthermore, integrating multiple modalities enhances model performance over single-modality approaches significantly. We achieved state-of-the-art performance on the OASIS-3 cohort. Additionally, explainability analyses with Grad-CAM indicate that our model focuses on crucial AD-related regions for its predictions, underscoring its potential to aid in understanding the disease's causes.

Predicting cognitive dysfunction and regional hubs using Braak staging amyloid-beta biomarkers and machine learning

Mild cognitive impairment (MCI) is a transitional stage between normal aging and early Alzheimer's disease (AD). The presence of extracellular amyloid-beta (Aβ) in Braak regions suggests a connection with cognitive dysfunction in MCI/AD. Investigating the multivariate predictive relationships between regional Aβ biomarkers and cognitive function can aid in the early detection and prevention of AD. We introduced machine learning approaches to estimate cognitive dysfunction from regional Aβ biomarkers and identify the Aβ-related dominant brain regions involved with cognitive impairment. We employed Aβ biomarkers and cognitive measurements from the same individuals to train support vector regression (SVR) and artificial neural network (ANN) models and predict cognitive performance solely based on Aβ biomarkers on the test set. To identify Aβ-related dominant brain regions involved in cognitive prediction, we built the local interpretable model-agnostic explanations (LIME) model. We found elevated Aβ in MCI compared to controls and a stronger correlation between Aβ and cognition, particularly in Braak stages III-IV and V-VII (p < 0.05) biomarkers. Both SVR and ANN, especially ANN, showed strong predictive relationships between regional Aβ biomarkers and cognitive impairment (p < 0.05). LIME integrated with ANN showed that the parahippocampal gyrus, inferior temporal gyrus, and hippocampus were the most decisive Braak regions for predicting cognitive decline. Consistent with previous findings, this new approach suggests relationships between Aβ biomarkers and cognitive impairment. The proposed analytical framework can estimate cognitive impairment from Braak staging Aβ biomarkers and delineate the dominant brain regions collectively involved in AD pathophysiology.

Hypermetabolic Cerebellar Connectome in Alzheimer's Disease

Introduction: Regional hypermetabolism in Alzheimer's disease (AD), especially in the cerebellum, has been consistently observed but often neglected as an artefact produced by the commonly used proportional scaling procedure in the statistical parametric mapping. We hypothesize that the hypermetabolic regions are also important in disease pathology in AD. Methods: Using fluorodeoxyglucose (FDG)-positron emission tomography (PET) images from 88 AD subjects and 88 age-sex matched normal controls (NL) from the publicly available Alzheimer's Disease Neuroimaging Initiative database, we developed a general linear model-based classifier that differentiated AD patients from normal individuals (sensitivity = 87.50%, specificity = 82.95%). We constructed region-region group-wise correlation matrices and evaluated differences in network organization by using the graph theory analysis between AD and control subjects. Results: We confirmed that hypermetabolism found in AD is not an artefact by replicating it using white matter as the reference region. The role of the hypermetabolic regions has been further investigated by using the graph theory. The differences in betweenness centrality (BC) between AD and NL network were correlated with region weights of FDG PET-based AD classifier. In particular, the hypermetabolism in cerebellum was accompanied with higher BC. The brain regions with higher BC in AD network showed a progressive increase in FDG uptake over 2 years in prodromal AD patients (n = 39). Discussion: This study suggests that hypermetabolism found in AD may play an important role in forming the AD-related metabolic network. In particular, hypermetabolic cerebellar regions represent a good candidate for further investigation in altered network organization in AD.

Elevated Soluble TNF-Receptor 1 in the Serum of Predementia Subjects with Cerebral Small Vessel Disease

Tumor necrosis factor-receptor 1 (TNF-R1)-mediated signaling is critical to the regulation of inflammatory responses. TNF-R1 can be proteolytically released into systemic blood circulation in a soluble form (sTNF-R1), where it binds to circulating TNF and functions to attenuate TNF-mediated inflammation. Increases of peripheral sTNF-R1 have been reported in both Alzheimer’s disease (AD) dementia and vascular dementia (VaD). However, the status of sTNF-R1 in predementia subjects (cognitive impairment, no dementia, CIND) is unknown, and putative associations with cerebral small vessel disease (CSVD), as well as with longitudinal changes in cognitive functions are unclear. We measured baseline serum sTNF-R1 in a longitudinally assessed cohort of 93 controls and 103 CIND, along with neuropsychological evaluations and neuroimaging assessments. Serum sTNF-R1 levels were increased in CIND compared with controls (p < 0.001). Higher baseline sTNF-R1 levels were specifically associated with lacunar infarcts (rate ratio = 6.91, 95% CI 3.19–14.96, p < 0.001), as well as lower rates of cognitive decline in the CIND subgroup. Our data suggest that sTNF-R1 interacts with vascular cognitive impairment in a complex manner at predementia stages, with elevated levels associated with more severe CSVD at baseline, but which may subsequently be protective against cognitive decline.

Neuroanatomical and neurocognitive changes associated with subjective cognitive decline

Introduction

Subjective Cognitive Decline (SCD) can progress to mild cognitive impairment (MCI) and Alzheimer's disease (AD) dementia and thus may represent a preclinical stage of the AD continuum. However, evidence about structural changes observed in the brain during SCD remains inconsistent.

Materials and methods

This cross-sectional study aimed to evaluate, in subjects recruited from the CompAS project, neurocognitive and neurostructural differences between a group of forty-nine control subjects and forty-nine individuals who met the diagnostic criteria for SCD and exhibited high levels of subjective cognitive complaints (SCCs). Structural magnetic resonance imaging was used to compare neuroanatomical differences in brain volume and cortical thickness between both groups.

Results

Relative to the control group, the SCD group displayed structural changes involving frontal, parietal, and medial temporal lobe regions of critical importance in AD etiology and functionally related to several cognitive domains, including executive control, attention, memory, and language.

Conclusion

Despite the absence of clinical deficits, SCD may constitute a preclinical entity with a similar (although subtle) pattern of neuroanatomical changes to that observed in individuals with amnestic MCI or AD dementia.

Decoupling of Regional Cerebral Blood Flow and Brain Function Along the Alzheimer's Disease Continuum

BACKGROUND

Alzheimer's disease (AD) is accompanied with impaired neurovascular coupling. However, its early alteration remains elusive along the AD continuum.

OBJECTIVE

This study aimed to investigate the early disruption of neurovascular coupling in cognitively normal (CN) and mild cognitive impairment (MCI) elderly and its association with cognition and AD pathologies.

METHODS

We included 43 amyloid-β-negative CN participants and 38 amyloid-β-positive individuals (18 CN and 20 MCI) from the Alzheimer's Disease Neuroimaging Initiative dataset. Regional homogeneity (ReHo) map was used to represent neuronal activity and cerebral blood flow (CBF) map was used to represent cerebral blood perfusion. Neurovascular coupling was assessed by CBF/ReHo ratio at the voxel level. Analyses of covariance to detect the between-group differences and to further investigate the relations between CBF/ReHo ratio and AD biomarkers or cognition. In addition, the correlation of cerebral small vessel disease (SVD) burden and neurovascular coupling was assessed as well.

RESULTS

Related to amyloid-β-negative CN group, amyloid-β-positive groups showed decreased CBF/ReHo ratio mainly in the left medial and inferior temporal gyrus. Furthermore, lower CBF/ReHo ratio was associated with a lower Mini-Mental State Examination score as well as higher AD pathological burden. No association between CBF/ReHo ratio and SVD burden was observed.

CONCLUSION

AD pathology is a major correlate of the disturbed neurovascular coupling along the AD continuum, independent of SVD pathology. The CBF/ReHo ratio may be an index for detecting neurovascular coupling abnormalities, which could be used for early diagnosis in the future.

Uncovering the System Vulnerability and Criticality of Human Brain Under Dynamical Neuropathological Events in Alzheimer's Disease

BACKGROUND

Despite the striking efforts in investigating neurobiological factors behind the acquisition of amyloid-β (A), protein tau (T), and neurodegeneration ([N]) biomarkers, the mechanistic pathways of how AT[N] biomarkers spreading throughout the brain remain elusive.

OBJECTIVE

To disentangle the massive heterogeneities in Alzheimer's disease (AD) progressions and identify vulnerable/critical brain regions to AD pathology.

METHODS

In this work, we characterized the interaction of AT[N] biomarkers and their propagation across brain networks using a novel bistable reaction-diffusion model, which allows us to establish a new systems biology underpinning of AD progression. We applied our model to large-scale longitudinal neuroimages from the ADNI database and studied the systematic vulnerability and criticality of brains.

RESULTS

Our model yields long term prediction that is statistically significant linear correlated with temporal imaging data, produces clinically consistent risk prediction, and captures the Braak-like spreading pattern of AT[N] biomarkers in AD development.

CONCLUSIONS

Our major findings include (i) tau is a stronger indicator of regional risk compared to amyloid, (ii) temporal lobe exhibits higher vulnerability to AD-related pathologies, (iii) proposed critical brain regions outperform hub nodes in transmitting disease factors across the brain, and (iv) comparing the spread of neuropathological burdens caused by amyloid-β and tau diffusions, disruption of metabolic balance is the most determinant factor contributing to the initiation and progression of AD.

Identifying the regional substrates predictive of Alzheimer's disease progression through a convolutional neural network model and occlusion

Progressive brain atrophy is a key neuropathological hallmark of Alzheimer's disease (AD) dementia. However, atrophy patterns along the progression of AD dementia are diffuse and variable and are often missed by univariate methods. Consequently, identifying the major regional atrophy patterns underlying AD dementia progression is challenging. In the current study, we propose a method that evaluates the degree to which specific regional atrophy patterns are predictive of AD dementia progression, while holding all other atrophy changes constant using a total sample of 334 subjects. We first trained a dense convolutional neural network model to differentiate individuals with mild cognitive impairment (MCI) who progress to AD dementia versus those with a stable MCI diagnosis. Then, we retested the model multiple times, each time occluding different regions of interest (ROIs) from the model's testing set's input. We also validated this approach by occluding ROIs based on Braak's staging scheme. We found that the hippocampus, fusiform, and inferior temporal gyri were the strongest predictors of AD dementia progression, in agreement with established staging models. We also found that occlusion of limbic ROIs defined according to Braak stage III had the largest impact on the performance of the model. Our predictive model reveals the major regional patterns of atrophy predictive of AD dementia progression. These results highlight the potential for early diagnosis and stratification of individuals with prodromal AD dementia based on patterns of cortical atrophy, prior to interventional clinical trials.

The association of reproductive stage with lobular cerebellar network connectivity across female adulthood

Sex-specific differences in the aging cerebellum may be related to hormone changes with menopause. We evaluated the association between reproductive stage and lobular cerebellar network connectivity using data from the Cambridge Centre for Ageing and Neuroscience repository. We used raw structural and resting state neuroimaging data and information regarding age, sex, and menopause-related variables. Crus I and II and Lobules V and VI were our cerebellar seeds of interest. We characterized reproductive stage using the Stages of Reproductive Aging Workshop criteria. Results show that postmenopausal females have lower cerebello-striatal and cerebello-cortical connectivity, particularly in frontal regions, along with lower connectivity within the cerebellum, compared to reproductive females. Postmenopausal females also exhibit greater connectivity in some brain areas as well. Differences begin to emerge across transitional stages of menopause. Further, results reveal sex-specific differences in connectivity between female reproductive groups and age-matched male control groups. This suggests that menopause may be associated with cerebellar network connectivity in aging females, and sex differences in the aging brain may be related to this biological process.

A Phenome-wide Association and Mendelian Randomization Study for Alzheimer's Disease: A Prospective Cohort Study of 502,493 Participants From the UK Biobank

BACKGROUND

Considerable uncertainty remains regarding associations of multiple risk factors with Alzheimer's disease (AD). We aimed to systematically screen and validate a wide range of potential risk factors for AD.

METHODS

Among 502,493 participants from the UK Biobank, baseline data were extracted for 4171 factors spanning 10 different categories. Phenome-wide association analyses and time-to-event analyses were conducted to identify factors associated with both polygenic risk scores for AD and AD diagnosis at follow-up. We performed two-sample Mendelian randomization analysis to further assess their potential causal relationships with AD and imaging association analysis to discover underlying mechanisms.

RESULTS

We identified 39 factors significantly associated with both AD polygenic risk scores and risk of incident AD, where higher levels of education, body size, basal metabolic rate, fat-free mass, computer use, and cognitive functions were associated with a decreased risk of developing AD, and selective food intake and more outdoor exposures were associated with an increased risk of developing AD. The identified factors were also associated with AD-related brain structures, including the hippocampus, entorhinal cortex, and inferior/middle temporal cortex, and 21 of these factors were further supported by Mendelian randomization evidence.

CONCLUSIONS

To our knowledge, this is the first study to comprehensively and rigorously assess the effects of wide-ranging risk factors on AD. Strong evidence was found for fat-free body mass, basal metabolic rate, computer use, selective food intake, and outdoor exposures as new risk factors for AD. Integration of genetic, clinical, and neuroimaging information may help prioritize risk factors and prevention targets for AD.

Voxel-Mirrored Homotopic Connectivity Is Altered in Meibomian Gland Dysfunction Patients That Are Morbidly Obese

Purpose: To investigate the altered functional connectivity (FC) of the cerebral hemispheres in patients with morbid obesity (MO) with meibomian gland dysfunction (MGD) by voxel-mirrored homotopic connectivity (VMHC). Methods: Patients and matched healthy controls (HCs) were recruited, and all subjects underwent functional resonance magnetic imaging (fMRI), and VMHC results were processed statistically to assess the differences in FC in different brain regions between the two groups. We further used ROC curves to evaluate the diagnostic value of these differences. We also used Pearson’s correlation analysis to explore the relationship between changes in VMHC values in specific brain regions, visual acuity, and Mini-Mental State Examination (MMSE) score. Conclusions: Patients with morbid obesity and MGD had abnormal FC in the cerebral hemispheres in several specific brain areas, which were mainly concentrated in pathways related to vision and perception and may correlate to some extent with the clinical presentations of the patients.

Hippocampus-based static functional connectivity mapping within white matter in mild cognitive impairment

Mild cognitive impairment (MCI) is clinically characterized by memory loss and cognitive impairment closely associated with the hippocampal atrophy. Accumulating studies have confirmed the presence of neural signal changes within white matter (WM) in resting-state functional magnetic resonance imaging (fMRI). However, it remains unclear how abnormal hippocampus activity affects the WM regions in MCI. The current study employs 43 MCI, 71 very MCI (VMCI) and 87 age-, gender-, and education-matched healthy controls (HCs) from the public OASIS-3 dataset. Using the left and right hippocampus as seed points, we obtained the whole-brain functional connectivity (FC) maps for each subject. We then perform one-way ANOVA analysis to investigate the abnormal FC regions among HCs, VMCI, and MCI. We further performed probabilistic tracking to estimate whether the abnormal FC correspond to structural connectivity disruptions. Compared to HCs, MCI and VMCI groups exhibited reduced FC in the right middle temporal gyrus within gray matter, and right temporal pole, right inferior frontal gyrus within white matter. Specific dysconnectivity is shown in the cerebellum Crus II, left inferior temporal gyrus within gray matter, and right frontal gyrus within white matter. In addition, the fiber bundles connecting the left hippocampus and right temporal pole within white matter show abnormally increased mean diffusivity in MCI. The current study proposes a new functional imaging direction for exploring the mechanism of memory decline and pathophysiological mechanisms in different stages of Alzheimer's disease.

Depression symptoms moderate the relationship between gray matter volumes and cognitive function in patients with mild cognitive impairment

Previous studies have demonstrated that decreased gray matter volume (GMV) correlates with cognitive function in elderly patients with mild cognitive impairment (MCI). However, it is unclear whether those correlations are present in MCI patients with depressive symptoms (MCID). This study investigated the association among depressive symptoms, GMV and cognitive function. We included 210 participants, namely, 70 elderly MCID patients, 70 MCI patients without depressive symptoms (MCIND) and 70 healthy controls (HCs). Voxel-based morphometry (VBM) was used to investigate the structural disruptions among the patients in the three groups, and correlation analysis was performed between the GMV of regions showing group differences and cognitive function. Moderation analyses were conducted to verify the conditional effect of depressive symptoms on the relationship between structural changes and cognitive function. We found decreased GMV in the bilateral fusiform gyrus, inferior temporal gyrus, parahippocampal gyrus, and hippocampus in the MCIND group compared to the HC group. Moreover, we identified decreased GMV in the bilateral fusiform gyrus in the elderly MCID patients compared with the elderly MCIND patients, which provides further insights into the neural mechanisms of depressive symptoms in patients with MCID. Most importantly, the severity of depressive symptoms moderated the positive correlation between the GMV of abnormal brain regions and cognitive function. Furthermore, this study is the first report of the moderating effect of depressive symptoms on the GMV of abnormal brain areas and cognitive function in patients with MCID, indicating the significance of clinical intervention in elderly MCI patients with depressive symptoms.

Generalized Liquid Association Analysis for Multimodal Data Integration

Multimodal data are now prevailing in scientific research. One of the central questions in multimodal integrative analysis is to understand how two data modalities associate and interact with each other given another modality or demographic variables. The problem can be formulated as studying the associations among three sets of random variables, a question that has received relatively less attention in the literature. In this article, we propose a novel generalized liquid association analysis method, which offers a new and unique angle to this important class of problems of studying three-way associations. We extend the notion of liquid association of Li (2002) from the univariate setting to the sparse, multivariate, and high-dimensional setting. We establish a population dimension reduction model, transform the problem to sparse Tucker decomposition of a three-way tensor, and develop a higher-order orthogonal iteration algorithm for parameter estimation. We derive the non-asymptotic error bound and asymptotic consistency of the proposed estimator, while allowing the variable dimensions to be larger than and diverge with the sample size. We demonstrate the efficacy of the method through both simulations and a multimodal neuroimaging application for Alzheimer's disease research.

Kernel Knockoffs Selection for Nonparametric Additive Models

Thanks to its fine balance between model flexibility and interpretability, the nonparametric additive model has been widely used, and variable selection for this type of model has been frequently studied. However, none of the existing solutions can control the false discovery rate (FDR) unless the sample size tends to infinity. The knockoff framework is a recent proposal that can address this issue, but few knockoff solutions are directly applicable to nonparametric models. In this article, we propose a novel kernel knockoffs selection procedure for the nonparametric additive model. We integrate three key components: the knockoffs, the subsampling for stability, and the random feature mapping for nonparametric function approximation. We show that the proposed method is guaranteed to control the FDR for any sample size, and achieves a power that approaches one as the sample size tends to infinity. We demonstrate the efficacy of our method through intensive simulations and comparisons with the alternative solutions. our proposal thus makes useful contributions to the methodology of nonparametric variable selection, FDR-based inference, as well as knockoffs.

Aberrant Changes in Cortical Complexity in Right-Onset Versus Left-Onset Parkinson's Disease in Early-Stage

There is increasing evidence to show that motor symptom lateralization in Parkinson’s disease (PD) is linked to non-motor features, progression, and prognosis of the disease. However, few studies have reported the difference in cortical complexity between patients with left-onset of PD (LPD) and right-onset of PD (RPD). This study aimed to investigate the differences in the cortical complexity between early-stage LPD and RPD. High-resolution T1-weighted magnetic resonance images of the brain were acquired in 24 patients with LPD, 34 patients with RPD, and 37 age- and sex-matched healthy controls (HCs). Cortical complexity including gyrification index, fractal dimension (FD), and sulcal depth was analyzed using surface-based morphometry via CAT12/SPM12. Familywise error (FWE) peak-level correction at p < 0.05 was performed for significance testing. In patients with RPD, we found decreased mean FD and mean sulcal depth in the banks of the left superior temporal sulcus (STS) compared with LPD and HCs. The mean FD in the left superior temporal gyrus (STG) was decreased in RPD compared with HCs. However, in patients with LPD, we did not identify significantly abnormal cortical complex change compared with HCs. Moreover, we observed that the mean FD in STG was negatively correlated with the 17-item Hamilton Depression Scale (HAMD) among the three groups. Our findings support the specific influence of asymmetrical motor symptoms in cortical complexity in early-stage PD and reveal that the banks of left STS and left STG might play a crucial role in RPD.

Prediction of Alzheimer's Disease Progression Based on Magnetic Resonance Imaging

The neuroimaging method of multimodal magnetic resonance imaging (MRI) can identify the changes in brain structure and function caused by Alzheimer's disease (AD) at different stages, and it is a practical method to study the mechanism of AD progression. This paper reviews the studies of methods and biomarkers for predicting AD progression based on multimodal MRI. First, different approaches for predicting AD progression are analyzed and summarized, including machine learning, deep learning, regression, and other MRI analysis methods. Then, the effective biomarkers of AD progression under structural magnetic resonance imaging, diffusion tensor imaging, functional magnetic resonance imaging, and arterial spin labeling modes of MRI are summarized. It is believed that the brain changes shown on MRI may be related to the cognitive decline in different prodrome stages of AD, which is conducive to the further realization of early intervention and prevention of AD. Finally, the deficiencies of the existing studies are analyzed in terms of data set size, data heterogeneity, processing methods, and research depth. More importantly, future research directions are proposed, including enriching data sets, simplifying biomarkers, utilizing multimodal magnetic resonance, etc. In the future, the study of AD progression by multimodal MRI will still be a challenge but also a significant research hotspot.

A parallel attention-augmented bilinear network for early magnetic resonance imaging-based diagnosis of Alzheimer's disease

Structural magnetic resonance imaging (sMRI) can capture the spatial patterns of brain atrophy in Alzheimer's disease (AD) and incipient dementia. Recently, many sMRI‐based deep learning methods have been developed for AD diagnosis. Some of these methods utilize neural networks to extract high‐level representations on the basis of handcrafted features, while others attempt to learn useful features from brain regions proposed by a separate module. However, these methods require considerable manual engineering. Their stepwise training procedures would introduce cascading errors. Here, we propose the parallel attention‐augmented bilinear network, a novel deep learning framework for AD diagnosis. Based on a 3D convolutional neural network, the framework directly learns both global and local features from sMRI scans without any prior knowledge. The framework is lightweight and suitable for end‐to‐end training. We evaluate the framework on two public datasets (ADNI‐1 and ADNI‐2) containing 1,340 subjects. On both the AD classification and mild cognitive impairment conversion prediction tasks, our framework achieves competitive results. Furthermore, we generate heat maps that highlight discriminative areas for visual interpretation. Experiments demonstrate the effectiveness of the proposed framework when medical priors are unavailable or the computing resources are limited. The proposed framework is general for 3D medical image analysis with both efficiency and interpretability.

METTL3-dependent RNA m6A dysregulation contributes to neurodegeneration in Alzheimer's disease through aberrant cell cycle events

Background

N6-methyladenosine (m⁶A) modification of RNA influences fundamental aspects of RNA metabolism and m⁶A dysregulation is implicated in various human diseases. In this study, we explored the potential role of RNA m⁶A modification in the pathogenesis of Alzheimer disease (AD).

Methods

We investigated the m⁶A modification and the expression of m⁶A regulators in the brain tissues of AD patients and determined the impact and underlying mechanism of manipulated expression of m⁶A levels on AD-related deficits both in vitro and in vivo.

Results

We found decreased neuronal m⁶A levels along with significantly reduced expression of m⁶A methyltransferase like 3 (METTL3) in AD brains. Interestingly, reduced neuronal m⁶A modification in the hippocampus caused by METTL3 knockdown led to significant memory deficits, accompanied by extensive synaptic loss and neuronal death along with multiple AD-related cellular alterations including oxidative stress and aberrant cell cycle events in vivo. Inhibition of oxidative stress or cell cycle alleviated shMettl3-induced apoptotic activation and neuronal damage in primary neurons. Restored m⁶A modification by inhibiting its demethylation in vitro rescued abnormal cell cycle events, neuronal deficits and death induced by METTL3 knockdown. Soluble Aβ oligomers caused reduced METTL3 expression and METTL3 knockdown exacerbated while METTL3 overexpression rescued Aβ-induced synaptic PSD95 loss in vitro. Importantly, METTL3 overexpression rescued Aβ-induced synaptic damage and cognitive impairment in vivo.

Conclusions

Collectively, these data suggested that METTL3 reduction-mediated m⁶A dysregulation likely contributes to neurodegeneration in AD which may be a therapeutic target for AD.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13024-021-00484-x.

Classification-Biased Apparent Brain Age for the Prediction of Alzheimer's Disease

Machine Learning methods are often adopted to infer useful biomarkers for the early diagnosis of many neurodegenerative diseases and, in general, of neuroanatomical ageing. Some of these methods estimate the subject age from morphological brain data, which is then indicated as “brain age”. The difference between such a predicted brain age and the actual chronological age of a subject can be used as an indication of a pathological deviation from normal brain ageing. An important use of the brain age model as biomarker is the prediction of Alzheimer's disease (AD) from structural Magnetic Resonance Imaging (MRI). Many different machine learning approaches have been applied to this specific predictive task, some of which have achieved high accuracy at the expense of the descriptiveness of the model. This work investigates an appropriate combination of data science techniques and linear models to provide, at the same time, high accuracy and good descriptiveness. The proposed method is based on a data workflow that include typical data science methods, such as outliers detection, feature selection, linear regression, and logistic regression. In particular, a novel inductive bias is introduced in the regression model, which is aimed at improving the accuracy and the specificity of the classification task. The method is compared to other machine learning approaches for AD classification based on morphological brain data with and without the use of the brain age, including Support Vector Machines and Deep Neural Networks. This study adopts brain MRI scans of 1, 901 subjects which have been acquired from three repositories (ADNI, AIBL, and IXI). A predictive model based only on the proposed apparent brain age and the chronological age has an accuracy of 88% and 92%, respectively, for male and female subjects, in a repeated cross-validation analysis, thus achieving a comparable or superior performance than state of the art machine learning methods. The advantage of the proposed method is that it maintains the morphological semantics of the input space throughout the regression and classification tasks. The accurate predictive model is also highly descriptive and can be used to generate potentially useful insights on the predictions.

Association of Speech Recognition Thresholds With Brain Volumes and White Matter Microstructure: The Rotterdam Study

OBJECTIVES

Brain volumetric declines may underlie the association between hearing loss and dementia. While much is known about the peripheral auditory function and brain volumetric declines, poorer central auditory speech processing may also be associated with decreases in brain volumes.

METHODS

Central auditory speech processing, measured by the speech recognition threshold (SRT) from the Digits-in-Noise task, and neuroimaging assessments (structural magnetic resonance imaging [MRI] and fractional anisotropy and mean diffusivity from diffusion tensor imaging), were assessed cross-sectionally in 2,368 Rotterdam Study participants aged 51.8 to 97.8 years. SRTs were defined continuously and categorically by degrees of auditory performance (normal, insufficient, and poor). Brain volumes from structural MRI were assessed on a global and lobar level, as well as for specific dementia-related structures (hippocampus, entorhinal cortex, parahippocampal gyrus). Multivariable linear regression models adjusted by age, age-squared, sex, educational level, alcohol consumption, intracranial volume (MRI only), cardiovascular risk factors (hypertension, diabetes, obesity, current smoking), and pure-tone average were used to determine associations between SRT and brain structure.

RESULTS

Poorer central auditory speech processing was associated with larger parietal lobe volume (difference in mL per dB increase= 0.24, 95% CI: 0.05, 0.42), but not with diffusion tensor imaging measures. Degrees of auditory performance were not associated with brain volumes and white matter microstructure.

CONCLUSIONS

Central auditory speech processing in the presence of both vascular burden and pure-tone average may not be related to brain volumes and white matter microstructure. Longitudinal follow-up is needed to explore these relationships thoroughly.

Using Fractal Dimension Analysis with the Desikan-Killiany Atlas to Assess the Effects of Normal Aging on Subregional Cortex Alterations in Adulthood

Normal aging is associated with functional and structural alterations in the human brain. The effects of normal aging and gender on morphological changes in specific regions of the brain are unknown. The fractal dimension (FD) can be a quantitative measure of cerebral folding. In this study, we used 3D-FD analysis with the Desikan–Killiany (DK) atlas to assess subregional morphological changes in adulthood. A total of 258 participants (112 women and 146 men) aged 30–85 years participated in this study. Participants in the middle-age group exhibited a decreased FD in the lateral frontal lobes, which then spread to the temporal and parietal lobes. Men exhibited an earlier and more significant decrease in FD values, mainly in the right frontal and left parietal lobes. Men exhibited more of a decrease in FD values in the subregions on the left than those in the right, whereas women exhibited more of a decrease in the lateral subregions. Older men were at a higher risk of developing mild cognitive impairment (MCI) and exhibited age-related memory decline earlier than women. Our FD analysis using the DK atlas-based prediagnosis may provide a suitable tool for assessing normal aging and neurodegeneration between groups or in individual patients.

Identification of hub ubiquitin ligase genes affecting Alzheimer's disease by analyzing transcriptome data from multiple brain regions

The ubiquitin-proteasome system (UPS) plays crucial roles in numerous cellular functions. Dysfunction of the UPS shows certain correlations with the pathological changes in Alzheimer's disease (AD). This study aimed to explore the different impairments of the UPS in multiple brain regions and identify hub ubiquitin ligase (E3) genes in AD. The brain transcriptome, blood transcriptome and proteome data of AD were downloaded from a public database. The UPS genes were collected from the Ubiquitin and Ubiquitin-like Conjugation Database. The hub E3 genes were defined as the differentially expressed E3 genes shared by more than three brain regions. E3Miner and UbiBrowser were used to predict the substrate of hub E3. This study shows varied impairment of the UPS in different brain regions in AD. Furthermore, we identify seven hub E3 genes (CUL1, CUL3, EIF3I, NSMCE1, PAFAH1B1, RNF175, and UCHL1) that are downregulated in more than three brain regions. Three of these genes (CUL1, EIF3I, and NSMCE1) showed consistent low expression in blood. Most of these genes have been reported to promote AD, whereas the impact of RNF175 on AD is not yet reported. Further analysis revealed a potential regulatory mechanism by which hub E3 and its substrate genes may affect transcription functions and then exacerbate AD. This study identified seven hub E3 genes and their substrate genes affect transcription functions and then exacerbate AD. These findings may be helpful for the development of diagnostic biomarkers and therapeutic targets for AD.

Transcriptome Changes in the Alzheimer's Disease Middle Temporal Gyrus: Importance of RNA Metabolism and Mitochondria-Associated Membrane Genes

We used Illumina Human HT-12 v4 arrays to compare RNA expression of middle temporal gyrus (MTG; BA21) in Alzheimer's disease (AD = 97) and non-demented controls (ND = 98). A total of 938 transcripts were highly differentially expressed (adj p < 0.01; log2 FC ≥ |0.500|, with 411 overexpressed and 527 underexpressed in AD. Our results correlated with expression profiling in neurons from AD and ND obtained by laser capture microscopy in MTG from an independent dataset (log2 FC correlation: r = 0.504; p = 2.2e-16). Additionally, selected effects were validated by qPCR. ANOVA analysis yielded no difference between genders in response to AD, but some gender specific genes were detected (e.g., IL8 and AGRN in males, and HSPH1 and GRM1 in females). Several transcripts were associated with Braak staging (e.g., AEBP1 and DNALI1), antemortem MMSE (e.g., AEBP1 and GFAP), and tangle density (e.g., RNU1G2, and DNALI1). At the pathway level, we detected enrichment of synaptic vesicle processes and GABAergic transmission genes. Finally, applying the Weighted Correlation Network Analysis, we identified four expression modules enriched for neuronal and synaptic genes, mitochondria-associated membrane, chemical stimulus and olfactory receptor and non-coding RNA metabolism genes. Our results represent an extensive description of MTG mRNA profiling in a large sample of AD and ND. These data provide a list of genes associated with AD, and correlated to neurofibrillary tangles density. In addition, these data emphasize the importance of mitochondrial membranes and transcripts related to olfactory receptors in AD.

Association of hippocampal volume polygenic predictor score with baseline and change in brain volumes and cognition among cognitively healthy older adults

A high hippocampal volume polygenic predictor score (HV-PPS), computed based on GWAS summary statistics (n = 33,536), could be protective against declines in brain volume and cognition in older adults. Linear mixed-effects models with random intercepts and slopes were used to estimate associations of HV-PPS with baseline and annual rate of change in both brain volumes (n = 508) and cognitive performance (n = 1041) in Caucasian Baltimore Longitudinal Study of Aging participants. Higher HV-PPS was associated with greater baseline volumes of the hippocampus and parahippocampal gyrus, and slower rates of ventricular enlargement and volume loss in frontal and parietal white matter, all adjusted for intracranial volume. In addition, higher HV-PPS was associated with better executive function performance and slower rates of decline in verbal fluency scores over time. Individuals with a genetic predisposition toward larger hippocampal volumes show better baseline executive function, slower decline in verbal fluency performance, and slower rates of longitudinal brain atrophy.

Spatial-Temporal Dependency Modeling and Network Hub Detection for Functional MRI Analysis via Convolutional-Recurrent Network

Early identification of dementia at the stage of mild cognitive impairment (MCI) is crucial for timely diagnosis and intervention of Alzheimer's disease (AD). Although several pioneering studies have been devoted to automated AD diagnosis based on resting-state functional magnetic resonance imaging (rs-fMRI), their performance is somewhat limited due to non-effective mining of spatial-temporal dependency. Besides, few of these existing approaches consider the explicit detection and modeling of discriminative brain regions (i.e., network hubs) that are sensitive to AD progression. In this paper, we propose a unique Spatial-Temporal convolutional-recurrent neural Network (STNet) for automated prediction of AD progression and network hub detection from rs-fMRI time series. Our STNet incorporates the spatial-temporal information mining and AD-related hub detection into an end-to-end deep learning model. Specifically, we first partition rs-fMRI time series into a sequence of overlapping sliding windows. A sequence of convolutional components are then designed to capture the local-to-global spatially-dependent patterns within each sliding window, based on which we are able to identify discriminative hubs and characterize their unique contributions to disease diagnosis. A recurrent component with long short-term memory (LSTM) units is further employed to model the whole-brain temporal dependency from the spatially-dependent pattern sequences, thus capturing the temporal dynamics along time. We evaluate the proposed method on 174 subjects with 563 rs-fMRI scans from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, with results suggesting the effectiveness of our method in both tasks of disease progression prediction and AD-related hub detection.

Evidence that levels of nine essential metals in post-mortem human-Alzheimer's-brain and ex vivo rat-brain tissues are unaffected by differences in post-mortem delay, age, disease staging, and brain bank location

Studies of neurodegenerative conditions such as Alzheimer's disease (AD) using post mortem brain tissues have uncovered several perturbations in metals such as copper, iron, and zinc. However, studies of the effects of key, potentially confounding variables on these tissues are currently lacking. Moreover, human-brain tissues have limited availability, further enhancing the difficulty of matching potentially-significant variables including age, sex-matching, post-mortem delay (PMD), and neuropathological stage. This study aimed to investigate the effects of such factors and how they might influence metal concentrations in post-mortem brains. Cingulate gyrus from AD cases and matched controls was obtained from two brain banks, based in Auckland, New Zealand and Manchester, UK. Inductively-coupled plasma mass spectrometry (ICP-MS) was employed to measure levels of nine essential metals in brain tissues, and compared concentrations between cases and controls, and between cohorts, to analyse effects of age, sex, Braak stage, brain weight, and PMD. The same methods were used to investigate the effects of PMD under more controlled conditions using ex vivo healthy adult rat-brain tissue. Metal concentrations in human brain were found to be unmodified by differences in age, sex-matching, Braak stage, brain weight, and PMD between cohorts. Some metals were, however, found to vary significantly across different regions in rat brains. These results indicate that investigations of metal homeostasis in AD and other neurodegenerative conditions can be reliably performed using brain tissues without confounding by varying PMD, age, sex-matching, brain weight, and Braak stage. However, regions of study should be selected carefully.

Joint Multi-Modal Longitudinal Regression and Classification for Alzheimer's Disease Prediction

Alzheimer's disease (AD) is a serious neurodegenerative condition that affects millions of individuals across the world. As the average age of individuals in the United States and the world increases, the prevalence of AD will continue to grow. To address this public health problem, the research community has developed computational approaches to sift through various aspects of clinical data and uncover their insights, among which one of the most challenging problem is to determine the biological mechanisms that cause AD to develop. To study this problem, in this paper we present a novel Joint Multi-Modal Longitudinal Regression and Classification method and show how it can be used to identify the cognitive status of the participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort and the underlying biological mechanisms. By intelligently combining clinical data of various modalities (i.e., genetic information and brain scans) using a variety of regularizations that can identify AD-relevant biomarkers, we perform the regression and classification tasks simultaneously. Because the proposed objective is a non-smooth optimization problem that is difficult to solve in general, we derive an efficient iterative algorithm and rigorously prove its convergence. To validate our new method in predicting the cognitive scores of patients and their clinical diagnosis, we conduct comprehensive experiments on the ADNI cohort. Our promising results demonstrate the benefits and flexibility of the proposed method. We anticipate that our new method is of interest to clinical communities beyond AD research and have open-sourced the code of our method online.11 The code package for the proposed Joint Multi-Modal Longitudinal Regression and Classification model have been made publicly available online at https://github.com/minds-mines/jmmlrc.

Classification of Alzheimer's Disease using volumetric features of multiple MRI scans

Volumetric measurements from magnetic resonance imaging (MRI) scans can be used to predict the future conversion to Alzheimer's disease (AD) for patients with mild cognitive impairment (MCI). Previous studies achieved good classification results using the volumes of a single as well as multiple scans per subject. The purpose of this study is to evaluate, if and how volumetric features of a baseline (BL) and a follow-up (FU) MRI scan can be combined to improve classification accuracy. For this reason, random forest (RF) models were trained on different volumetric feature sets of 513 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and 22 subjects from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL) database. The results show that models, which use combinations of both acquisition times yield better accuracies in comparison to the models solely based on FU or BL data. Furthermore, a clear pattern of which combination of representations performs best could not be found. The best model achieves a test classification accuracy of 75.49% (specificity: 80.52%, sensitivity: 60%). Models trained with cognitive test results and MRI data outperform models which use only MRI data. The observed results could not be reproduced on the AIBL dataset.

Predicting Alzheimer's Disease Conversion From Mild Cognitive Impairment Using an Extreme Learning Machine-Based Grading Method With Multimodal Data

Identifying patients with mild cognitive impairment (MCI) who are at high risk of progressing to Alzheimer's disease (AD) is crucial for early treatment of AD. However, it is difficult to predict the cognitive states of patients. This study developed an extreme learning machine (ELM)-based grading method to efficiently fuse multimodal data and predict MCI-to-AD conversion. First, features were extracted from magnetic resonance (MR) images, and useful features were selected using a feature selection method. Second, multiple modalities of MCI subjects, including MRI, positron emission tomography, cerebrospinal fluid biomarkers, and gene data, were individually graded using the ELM method. Finally, these grading scores calculated from different modalities were fed into a classifier to discriminate subjects with progressive MCI from those with stable MCI. The proposed approach has been validated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, and an accuracy of 84.7% was achieved for an AD prediction within 3 years. Experiments on predicting AD conversion from MCI within different periods showed similar results with the 3-year prediction. The experimental results demonstrate that the proposed approach benefits from the efficient fusion of four modalities, resulting in an accurate prediction of MCI-to-AD conversion.

The impact of aging on the subregions of the fusiform gyrus in healthy older adults

The fusiform gyrus is known to decrease in size with increasing age. However, reported findings are inconsistent and existing studies differ in terms of the cohorts examined and/or the methods applied. Here, we analyzed age-related links in four distinct subregions of the fusiform gyrus through integrating imaging-based intensity information with microscopically defined cytoarchitectonic probabilities. In addition to age effects we investigated sex effects as well as age-by-sex interactions in a relatively large sample of 468 healthy subjects (272 females/196 males) covering a broad age range (42-97 years). We observed significant negative correlations between age and all four subregions of the fusiform gyrus indicating volume decreases over time, albeit with subregion-specific trajectories. Additionally, we observed significant negative quadratic associations with age for some subregions, suggesting an accelerating volume loss over time. These findings may serve as a frame of reference for future cross-sectional as well as longitudinal studies, not only for normative samples but also potentially for clinical conditions that present with abnormal atrophy of the fusiform gyrus. We did not detect any significant sex differences or sex-by-age interactions, suggesting that the size of the fusiform gyrus is similar in male and female brains and that age-related atrophy follows a similar trajectory in both men and women.

Structural magnetic resonance imaging for the early diagnosis of dementia due to Alzheimer's disease in people with mild cognitive impairment

BACKGROUND

Mild cognitive impairment (MCI) due to Alzheimer's disease is the symptomatic predementia phase of Alzheimer's disease dementia, characterised by cognitive and functional impairment not severe enough to fulfil the criteria for dementia. In clinical samples, people with amnestic MCI are at high risk of developing Alzheimer's disease dementia, with annual rates of progression from MCI to Alzheimer's disease estimated at approximately 10% to 15% compared with the base incidence rates of Alzheimer's disease dementia of 1% to 2% per year.

OBJECTIVES

To assess the diagnostic accuracy of structural magnetic resonance imaging (MRI) for the early diagnosis of dementia due to Alzheimer's disease in people with MCI versus the clinical follow-up diagnosis of Alzheimer's disease dementia as a reference standard (delayed verification). To investigate sources of heterogeneity in accuracy, such as the use of qualitative visual assessment or quantitative volumetric measurements, including manual or automatic (MRI) techniques, or the length of follow-up, and age of participants. MRI was evaluated as an add-on test in addition to clinical diagnosis of MCI to improve early diagnosis of dementia due to Alzheimer's disease in people with MCI.

SEARCH METHODS

On 29 January 2019 we searched Cochrane Dementia and Cognitive Improvement's Specialised Register and the databases, MEDLINE, Embase, BIOSIS Previews, Science Citation Index, PsycINFO, and LILACS. We also searched the reference lists of all eligible studies identified by the electronic searches.

SELECTION CRITERIA

We considered cohort studies of any size that included prospectively recruited people of any age with a diagnosis of MCI. We included studies that compared the diagnostic test accuracy of baseline structural MRI versus the clinical follow-up diagnosis of Alzheimer's disease dementia (delayed verification). We did not exclude studies on the basis of length of follow-up. We included studies that used either qualitative visual assessment or quantitative volumetric measurements of MRI to detect atrophy in the whole brain or in specific brain regions, such as the hippocampus, medial temporal lobe, lateral ventricles, entorhinal cortex, medial temporal gyrus, lateral temporal lobe, amygdala, and cortical grey matter.

DATA COLLECTION AND ANALYSIS

Four teams of two review authors each independently reviewed titles and abstracts of articles identified by the search strategy. Two teams of two review authors each independently assessed the selected full-text articles for eligibility, extracted data and solved disagreements by consensus. Two review authors independently assessed the quality of studies using the QUADAS-2 tool. We used the hierarchical summary receiver operating characteristic (HSROC) model to fit summary ROC curves and to obtain overall measures of relative accuracy in subgroup analyses. We also used these models to obtain pooled estimates of sensitivity and specificity when sufficient data sets were available.

MAIN RESULTS

We included 33 studies, published from 1999 to 2019, with 3935 participants of whom 1341 (34%) progressed to Alzheimer's disease dementia and 2594 (66%) did not. Of the participants who did not progress to Alzheimer's disease dementia, 2561 (99%) remained stable MCI and 33 (1%) progressed to other types of dementia. The median proportion of women was 53% and the mean age of participants ranged from 63 to 87 years (median 73 years). The mean length of clinical follow-up ranged from 1 to 7.6 years (median 2 years). Most studies were of poor methodological quality due to risk of bias for participant selection or the index test, or both. Most of the included studies reported data on the volume of the total hippocampus (pooled mean sensitivity 0.73 (95% confidence interval (CI) 0.64 to 0.80); pooled mean specificity 0.71 (95% CI 0.65 to 0.77); 22 studies, 2209 participants). This evidence was of low certainty due to risk of bias and inconsistency. Seven studies reported data on the atrophy of the medial temporal lobe (mean sensitivity 0.64 (95% CI 0.53 to 0.73); mean specificity 0.65 (95% CI 0.51 to 0.76); 1077 participants) and five studies on the volume of the lateral ventricles (mean sensitivity 0.57 (95% CI 0.49 to 0.65); mean specificity 0.64 (95% CI 0.59 to 0.70); 1077 participants). This evidence was of moderate certainty due to risk of bias. Four studies with 529 participants analysed the volume of the total entorhinal cortex and four studies with 424 participants analysed the volume of the whole brain. We did not estimate pooled sensitivity and specificity for the volume of these two regions because available data were sparse and heterogeneous. We could not statistically evaluate the volumes of the lateral temporal lobe, amygdala, medial temporal gyrus, or cortical grey matter assessed in small individual studies. We found no evidence of a difference between studies in the accuracy of the total hippocampal volume with regards to duration of follow-up or age of participants, but the manual MRI technique was superior to automatic techniques in mixed (mostly indirect) comparisons. We did not assess the relative accuracy of the volumes of different brain regions measured by MRI because only indirect comparisons were available, studies were heterogeneous, and the overall accuracy of all regions was moderate.

AUTHORS' CONCLUSIONS

The volume of hippocampus or medial temporal lobe, the most studied brain regions, showed low sensitivity and specificity and did not qualify structural MRI as a stand-alone add-on test for an early diagnosis of dementia due to Alzheimer's disease in people with MCI. This is consistent with international guidelines, which recommend imaging to exclude non-degenerative or surgical causes of cognitive impairment and not to diagnose dementia due to Alzheimer's disease. In view of the low quality of most of the included studies, the findings of this review should be interpreted with caution. Future research should not focus on a single biomarker, but rather on combinations of biomarkers to improve an early diagnosis of Alzheimer's disease dementia.

A soluble truncated tau species related to cognitive dysfunction is elevated in the brain of cognitively impaired human individuals

Neurofibrillary tangles are a pathological hallmark of Alzheimer’s disease, and their levels correlate with the severity of cognitive dysfunction in humans. However, experimental evidence suggests that soluble tau species cause cognitive deficits and memory impairment. Our recent study suggests that caspase-2 (Casp2)-catalyzed tau cleavage at aspartate 314 mediates synaptic dysfunction and memory impairment in mouse and cellular models of neurodegenerative disorders. Δtau314, the C-terminally-truncated cleavage products, are soluble and present in human brain. In addition, levels of Δtau314 proteins are elevated in the brain of the cognitively impaired individuals compared to the cognitively normal individuals, indicating a possible role for Δtau314 proteins in cognitive deterioration. Here we show that (1) Δtau314 proteins are present in the inferior temporal gyrus of human brains; (2) Δtau314 proteins are generated from all six tau splicing isoforms, (3) levels of both Casp2 and Δtau314 proteins are elevated in cognitively impaired individuals compared to cognitively normal individuals, and (4) levels of Δtau314 proteins show a modest predictive value for dementia. These findings advance our understanding of the characteristics of Δtau314 proteins and their relevance to cognitive dysfunction and shed light on the contribution of Casp2-mediated Δtau314 production to cognitive deterioration.

A Classification Algorithm by Combination of Feature Decomposition and Kernel Discriminant Analysis (KDA) for Automatic MR Brain Image Classification and AD Diagnosis

Magnetic resonance (MR) imaging is a widely used imaging modality for detection of brain anatomical variations caused by brain diseases such as Alzheimer's disease (AD) and mild cognitive impairment (MCI). AD considered as an irreversible neurodegenerative disorder with progressive memory impairment moreover cognitive functions, while MCI would be considered as a transitional phase amongst age-related cognitive weakening. Numerous machine learning approaches have been examined, aiming at AD computer-aided diagnosis through employing MR image analysis. Conversely, MR brain image changes could be caused by different effects such as aging and dementia. It is still a challenging difficulty to extract the relevant imaging features and classify the subjects of different groups. This paper would propose an automatic classification technique based on feature decomposition and kernel discriminant analysis (KDA) for classifications of progressive MCI (pMCI) vs. normal control (NC), AD vs. NC, and pMCI vs. stable MCI (sMCI). Feature decomposition would be based on dictionary learning, which is used for separation of class-specific components from the non-class-specific components in the features, while KDA would be applied for mapping original nonlinearly separable feature space to the separable features that are linear. The proposed technique would be evaluated by employing T1-weighted MR brain images from 830 subjects comprising 198 AD patients, 167 pMCI, 236 sMCI, and 229 NC from the Alzheimer's disease neuroimaging initiative (ADNI) dataset. Experimental results demonstrate that classification accuracy (ACC) of 90.41%, 84.29%, and 65.94% can be achieved for classification of AD vs. NC, pMCI vs. NC, and pMCI vs. sMCI, respectively, indicating the promising performance of the proposed method.

Emphasis Learning, Features Repetition in Width Instead of Length to Improve Classification Performance: Case Study-Alzheimer's Disease Diagnosis

In the past decade, many studies have been conducted to advance computer-aided systems for Alzheimer's disease (AD) diagnosis. Most of them have recently developed systems concentrated on extracting and combining features from MRI, PET, and CSF. For the most part, they have obtained very high performance. However, improving the performance of a classification problem is complicated, specifically when the model's accuracy or other performance measurements are higher than 90%. In this study, a novel methodology is proposed to address this problem, specifically in Alzheimer's disease diagnosis classification. This methodology is the first of its kind in the literature, based on the notion of replication on the feature space instead of the traditional sample space. Briefly, the main steps of the proposed method include extracting, embedding, and exploring the best subset of features. For feature extraction, we adopt VBM-SPM; for embedding features, a concatenation strategy is used on the features to ultimately create one feature vector for each subject. Principal component analysis is applied to extract new features, forming a low-dimensional compact space. A novel process is applied by replicating selected components, assessing the classification model, and repeating the replication until performance divergence or convergence. The proposed method aims to explore most significant features and highest-preforming model at the same time, to classify normal subjects from AD and mild cognitive impairment (MCI) patients. In each epoch, a small subset of candidate features is assessed by support vector machine (SVM) classifier. This repeating procedure is continued until the highest performance is achieved. Experimental results reveal the highest performance reported in the literature for this specific classification problem. We obtained a model with accuracies of 98.81%, 81.61%, and 81.40% for AD vs. normal control (NC), MCI vs. NC, and AD vs. MCI classification, respectively.

Altered Directed Functional Connectivity of the Hippocampus in Mild Cognitive Impairment and Alzheimer's Disease: A Resting-State fMRI Study

The hippocampus is generally reported as one of the regions most impacted by Alzheimer's disease (AD) and is closely associated with memory function and orientation. Undirected functional connectivity (FC) alterations occur in patients with mild cognitive impairment (MCI) and AD, and these alterations have been the subject of many studies. However, abnormal patterns of directed FC remain poorly understood. In this study, to identify changes in directed FC between the hippocampus and other brain regions, Granger causality analysis (GCA) based on voxels was applied to resting-state functional magnetic resonance imaging (rs-fMRI) data from 29 AD, 65 MCI, and 30 normal control (NC) subjects. The results showed significant differences in the patterns of directed FC among the three groups. There were fewer brain regions showing changes in directed FC with the hippocampus in the MCI group than the NC group, and these regions were mainly located in the temporal lobe, frontal lobe, and cingulate cortex. However, regarding the abnormalities in directed FC in the AD group, the number of affected voxels was greater, the size of the clusters was larger, and the distribution was wider. Most of the abnormal connections were unidirectional and showed hemispheric asymmetry. In addition, we also investigated the correlations between the abnormal directional FCs and cognitive and clinical measurement scores in the three groups and found that some of them were significantly correlated. This study revealed abnormalities in the transmission and reception of information in the hippocampus of MCI and AD patients and offer insight into the neurophysiological mechanisms underlying MCI and AD.

Braak neurofibrillary tangle staging prediction from in vivo MRI metrics

INTRODUCTION

Alzheimer's disease diagnosis requires postmortem visualization of amyloid and tau deposits. As brain atrophy can provide assessment of consequent neurodegeneration, our objective was to predict postmortem neurofibrillary tangles (NFT) from in vivo MRI measurements.

METHODS

All participants with neuroimaging and neuropathological data from the Alzheimer's Disease Neuroimaging Initiative, the National Alzheimer's Coordinating Center and the Rush Memory and Aging Project were selected (n = 186). Two hundred and thirty two variables were extracted from last MRI before death using FreeSurfer. Nonparametric correlation analysis and multivariable support vector machine classification were performed to provide a predictive model of Braak NFT staging.

RESULTS

We demonstrated that 59 of our MRI variables, mostly temporal lobe structures, were significantly associated with Braak NFT stages (P < .005). We obtained a 62.4% correct classification rate for discrimination between transentorhinal, limbic, and isocortical groups.

DISCUSSION

Structural neuroimaging may therefore be considered as a potential biomarker for early detection of Alzheimer's disease-associated neurofibrillary degeneration.

Deep learning for clustering of multivariate clinical patient trajectories with missing values

BACKGROUND

Precision medicine requires a stratification of patients by disease presentation that is sufficiently informative to allow for selecting treatments on a per-patient basis. For many diseases, such as neurological disorders, this stratification problem translates into a complex problem of clustering multivariate and relatively short time series because (i) these diseases are multifactorial and not well described by single clinical outcome variables and (ii) disease progression needs to be monitored over time. Additionally, clinical data often additionally are hindered by the presence of many missing values, further complicating any clustering attempts.

FINDINGS

The problem of clustering multivariate short time series with many missing values is generally not well addressed in the literature. In this work, we propose a deep learning-based method to address this issue, variational deep embedding with recurrence (VaDER). VaDER relies on a Gaussian mixture variational autoencoder framework, which is further extended to (i) model multivariate time series and (ii) directly deal with missing values. We validated VaDER by accurately recovering clusters from simulated and benchmark data with known ground truth clustering, while varying the degree of missingness. We then used VaDER to successfully stratify patients with Alzheimer disease and patients with Parkinson disease into subgroups characterized by clinically divergent disease progression profiles. Additional analyses demonstrated that these clinical differences reflected known underlying aspects of Alzheimer disease and Parkinson disease.

CONCLUSIONS

We believe our results show that VaDER can be of great value for future efforts in patient stratification, and multivariate time-series clustering in general.

Quantifying Neurodegenerative Progression With DeepSymNet, an End-to-End Data-Driven Approach

Alzheimer's disease (AD) is the most common neurodegenerative disorder worldwide and is one of the leading sources of morbidity and mortality in the aging population. There is a long preclinical period followed by mild cognitive impairment (MCI). Clinical diagnosis and the rate of decline is variable. Progression monitoring remains a challenge in AD, and it is imperative to create better tools to quantify this progression. Brain magnetic resonance imaging (MRI) is commonly used for patient assessment. However, current approaches for analysis require strong a priori assumptions about regions of interest used and complex preprocessing pipelines including computationally expensive non-linear registrations and iterative surface deformations. These preprocessing steps are composed of many stacked processing layers. Any error or bias in an upstream layer will be propagated throughout the pipeline. Failures or biases in the non-linear subject registration and the subjective choice of atlases of specific regions are common in medical neuroimaging analysis and may hinder the translation of many approaches to the clinical practice. Here we propose a data-driven method based on an extension of a deep learning architecture, DeepSymNet, that identifies longitudinal changes without relying on prior brain regions of interest, an atlas, or non-linear registration steps. Our approach is trained end-to-end and learns how a patient's brain structure dynamically changes between two-time points directly from the raw voxels. We compare our approach with Freesurfer longitudinal pipelines and voxel-based methods using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Our model can identify AD progression with comparable results to existing Freesurfer longitudinal pipelines without the need of predefined regions of interest, non-rigid registration algorithms, or iterative surface deformation at a fraction of the processing time. When compared to other voxel-based methods which share some of the same benefits, our model showed a statistically significant performance improvement. Additionally, we show that our model can differentiate between healthy subjects and patients with MCI. The model's decision was investigated using the epsilon layer-wise propagation algorithm. We found that the predictions were driven by the pallidum, putamen, and the superior temporal gyrus. Our novel longitudinal based, deep learning approach has the potential to diagnose patients earlier and enable new computational tools to monitor neurodegeneration in clinical practice.

Latent Representation Learning for Alzheimer's Disease Diagnosis With Incomplete Multi-Modality Neuroimaging and Genetic Data

The fusion of complementary information contained in multi-modality data [e.g., magnetic resonance imaging (MRI), positron emission tomography (PET), and genetic data] has advanced the progress of automated Alzheimer's disease (AD) diagnosis. However, multi-modality based AD diagnostic models are often hindered by the missing data, i.e., not all the subjects have complete multi-modality data. One simple solution used by many previous studies is to discard samples with missing modalities. However, this significantly reduces the number of training samples, thus leading to a sub-optimal classification model. Furthermore, when building the classification model, most existing methods simply concatenate features from different modalities into a single feature vector without considering their underlying associations. As features from different modalities are often closely related (e.g., MRI and PET features are extracted from the same brain region), utilizing their inter-modality associations may improve the robustness of the diagnostic model. To this end, we propose a novel latent representation learning method for multi-modality based AD diagnosis. Specifically, we use all the available samples (including samples with incomplete modality data) to learn a latent representation space. Within this space, we not only use samples with complete multi-modality data to learn a common latent representation, but also use samples with incomplete multi-modality data to learn independent modality-specific latent representations. We then project the latent representations to the label space for AD diagnosis. We perform experiments using 737 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and the experimental results verify the effectiveness of our proposed method.

Differential Associations Between Volumes of Atrophic Cortical Brain Regions and Memory Performances in Early and Late Mild Cognitive Impairment

Background

Early and late mild cognitive impairment (MCI) patients have been reported to have a distinctive prognosis of converting to Alzheimer’s disease.

Objective

To evaluate the difference in gray matter volume and assess the association between cognitive function evaluated by comprehensive cognitive function test, and cortical thickness across healthy controls (HCs) (n = 37), early (n = 30), and late MCI patients (n = 35).

Methods

Differences in gray matter volume were evaluated by whole brain voxel-based morphometry across the groups. Multiple regression analysis was used to analyze group by memory performance interactions for the normalized gray matter volume.

Results

The early MCI group showed reduced gray matter volume in the right middle temporal gyrus in comparison to the HC group. The late MCI group displayed atrophy in the left parahippocampal gyrus in comparison to the HC group. Late MCI patients exhibited a decreased gray matter volume in the left fusiform gyrus in comparison to patients in the early MCI group (Monte Carlo simulation corrected p < 0.01, Tukey post hoc tests). Furthermore, there was a significant group (HC vs. early MCI) by memory performance interaction for the normalized cortical volume of the right middle temporal gyrus. Additionally, a significant group (early MCI vs. late MCI) by memory performance interaction was found for the normalized gray matter volume of the left fusiform gyrus (p < 0.001).

Conclusion

Early and late MCI patients showed distinctive associations of gray matter volumes in compensatory brain regions with memory performances. The findings can contribute to a better understanding of the structural changes in compensatory brain regions to elucidate memory decline in the trajectory of the subdivided prodromal stages of the Alzheimer’s disease (AD).