Neuroimaging Biomarkers for Alzheimer's Disease

Choroid plexus volume as a novel candidate neuroimaging marker of the Alzheimer's continuum

BACKGROUND

Enlarged choroid plexus (ChP) volume has been reported in patients with Alzheimer's disease (AD) and inversely correlated with cognitive performance. However, its clinical diagnostic and predictive value, and mechanisms by which ChP impacts the AD continuum remain unclear.

METHODS

This prospective cohort study enrolled 607 participants [healthy control (HC): 110, mild cognitive impairment (MCI): 269, AD dementia: 228] from the Chinese Imaging, Biomarkers, and Lifestyle study between January 1, 2021, and December 31, 2022. Of the 497 patients on the AD continuum, 138 underwent lumbar puncture for cerebrospinal fluid (CSF) hallmark testing. The relationships between ChP volume and CSF pathological hallmarks (Aβ42, Aβ40, Aβ42/40, tTau, and pTau181), neuropsychological tests [Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), Neuropsychiatric Inventory (NPI), and Activities of Daily Living (ADL) scores], and multimodal neuroimaging measures [gray matter volume, cortical thickness, and corrected cerebral blood flow (cCBF)] were analyzed using partial Spearman's correlation. The mediating effects of four neuroimaging measures [ChP volume, hippocampal volume, lateral ventricular volume (LVV), and entorhinal cortical thickness (ECT)] on the relationship between CSF hallmarks and neuropsychological tests were examined. The ability of the four neuroimaging measures to identify cerebral Aβ42 changes or differentiate among patients with AD dementia, MCI and HCs was determined using receiver operating characteristic analysis, and their associations with neuropsychological test scores at baseline were evaluated by linear regression. Longitudinal associations between the rate of change in the four neuroimaging measures and neuropsychological tests scores were evaluated on the AD continuum using generalized linear mixed-effects models.

RESULTS

The participants' mean age was 65.99 ± 8.79 years. Patients with AD dementia exhibited the largest baseline ChP volume than the other groups (P < 0.05). ChP volume enlargement correlated with decreased Aβ42 and Aβ40 levels; lower MMSE and MoCA and higher NPI and ADL scores; and lower volume, cortical thickness, and cCBF in other cognition-related regions (all P < 0.05). ChP volume mediated the association of Aβ42 and Aβ40 levels with MMSE scores (19.08% and 36.57%), and Aβ42 levels mediated the association of ChP volume and MMSE or MoCA scores (39.49% and 34.36%). ChP volume alone better identified cerebral Aβ42 changes than LVV alone (AUC = 0.81 vs. 0.67, P = 0.04) and EC thickness alone (AUC = 0.81 vs.0.63, P = 0.01) and better differentiated patients with MCI from HCs than hippocampal volume alone (AUC = 0.85 vs. 0.81, P = 0.01), and LVV alone (AUC = 0.85 vs.0.82, P = 0.03). Combined ChP and hippocampal volumes significantly increased the ability to differentiate cerebral Aβ42 changes and patients among AD dementia, MCI, and HCs groups compared with hippocampal volume alone (all P < 0.05). After correcting for age, sex, years of education, APOE ε4 status, eTIV, and hippocampal volume, ChP volume was associated with MMSE, MoCA, NPI, and ADL score at baseline, and rapid ChP volume enlargement was associated with faster deterioration in NPI scores with an average follow-up of 10.03 ± 4.45 months (all P < 0.05).

CONCLUSIONS

ChP volume may be a novel neuroimaging marker associated with neurodegenerative changes and clinical AD manifestations. It could better detect the early stages of the AD and predict prognosis, and significantly enhance the differential diagnostic ability of hippocampus on the AD continuum.

Tensor Completion for Alzheimer's Disease Prediction From Diffusion Tensor Imaging

OBJECTIVE

Alzheimer's disease (AD) is a slowly progressive neurodegenerative disorder with insidious onset. Accurate prediction of the disease progression has received increasing attention. Cognitive scores that reflect patients' cognitive status have become important criteria for predicting AD. Most existing methods consider the relationship between neuroimages and cognitive scores to improve prediction results. However, the inherent structure information in interrelated cognitive scores is rarely considered.

METHOD

In this article, we propose a relation-aware tensor completion multitask learning method (RATC-MTL), in which the cognitive scores are represented as a third-order tensor to preserve the global structure information in clinical scores. We combine both tensor completion and linear regression into a unified framework, which allows us to capture both inter and intra modes correlations in cognitive tensor with a low-rank constraint, as well as incorporate the relationship between biological features and cognitive status by imposing a regression model on multiple cognitive scores.

RESULT

Compared to the single-task and state-of-the-art multi-task algorithms, our proposed method obtains the best results for predicting cognitive scores in terms of four commonly used metrics. Furthermore, the overall performance of our method in classifying AD progress is also the best.

CONCLUSION

Our results demonstrate the effectiveness of the proposed framework in fully exploring the global structure information in cognitive scores.

SIGNIFICANCE

This study introduces a novel concept of leveraging tensor completion to assist in disease diagnoses, potentially offering a solution to the issue of data scarcity encountered in prolonged monitoring scenarios.

Classifying Alzheimer's Disease Neuropathology Using Clinical and MRI Measurements

Background

Computer-aided machine learning models are being actively developed with clinically available biomarkers to diagnose Alzheimer's disease (AD) in living persons. Despite considerable work with cross-sectional in vivo data, many models lack validation against postmortem AD neuropathological data.

Objective

Train machine learning models to classify the presence or absence of autopsy-confirmed severe AD neuropathology using clinically available features.

Methods

AD neuropathological status are assessed at postmortem for participants from the National Alzheimer's Coordinating Center (NACC). Clinically available features are utilized, including demographics, Apolipoprotein E(APOE) genotype, and cortical thicknesses derived from ante-mortem MRI scans encompassing AD meta regions of interest (meta-ROI). Both logistic regression and random forest models are trained to identify linearly and nonlinearly separable features between participants with the presence (N = 91, age-at-MRI = 73.6±9.24, 38 women) or absence (N = 53, age-at-MRI = 68.93±19.69, 24 women) of severe AD neuropathology. The trained models are further validated in an external data set against in vivo amyloid biomarkers derived from PET imaging (amyloid-positive: N = 71, age-at-MRI = 74.17±6.37, 26 women; amyloid-negative: N = 73, age-at-MRI = 71.59±6.80, 41 women).

Results

Our models achieve a cross-validation accuracy of 84.03% in classifying the presence or absence of severe AD neuropathology, and an external-validation accuracy of 70.14% in classifying in vivo amyloid positivity status.

Conclusions

Our models show that clinically accessible features, including APOE genotype and cortical thinning encompassing AD meta-ROIs, are able to classify both postmortem confirmed AD neuropathological status and in vivo amyloid status with reasonable accuracies. These results suggest the potential utility of AD meta-ROIs in determining AD neuropathological status in living persons.

Alzheimer's disease approaches - Focusing on pathology, biomarkers and clinical trial candidates

The strategy for the development of new drugs for Alzheimer's disease (AD) recognizes that an effective therapy requires early therapeutic intervention and a multifactorial approach that considers the individual initiators of AD development. Current knowledge of AD includes the understanding of pathophysiology, risk factors, biomarkers, and the evolving patterns of biomarker abnormalities. This knowledge is essential in identifying potential molecular targets for new drug development. This review summarizes promising AD drug candidates, many of which are currently in phase 2 or 3 clinical trials. New agents are classified according to the Common Alzheimer's Disease Research Ontology (CADRO). The main targets of new drugs for AD are processes related to amyloid beta and tau neurotoxicity, neurotransmission, inflammation, metabolism and bioenergetics, synaptic plasticity, and oxidative stress. These interventions are aimed at preventing disease onset and slowing or eliminating disease progression. The efficacy of pharmacotherapy may be enhanced by combining these drugs with other treatments, antioxidants, and dietary supplements. Ongoing research into AD pathophysiology, risk factors, biomarkers, and the dynamics of biomarker abnormalities may contribute to the understanding of AD and offer hope for effective therapeutic strategies in the near future.

ER-stress response in retinal Müller glia occurs significantly earlier than amyloid pathology in the Alzheimer's mouse brain and retina

Alzheimer's Disease (AD) pathogenesis is thought to begin up to 20 years before cognitive symptoms appear, suggesting the need for more sensitive diagnostic biomarkers of AD. In this report, we demonstrated pathological changes in retinal Müller glia significantly earlier than amyloid pathology in AD mouse models. By utilizing the knock-in NLGF mouse model, we surprisingly discovered an increase in reticulon 3 (RTN3) protein levels in the NLGF retina as early as postnatal day 30 (P30). Despite RTN3 being a canonically neuronal protein, this increase was noted in the retinal Müller glia, confirmed by immunohistochemical characterization. Further unbiased transcriptomic assays of the P30 NLGF retina revealed that retinal Müller glia were the most sensitive responding cells in this mouse retina, compared with other cell types including photoreceptor cells and ganglion neurons. Pathway analyses of differentially expressed genes in glia cells showed activation of ER stress response via the upregulation of unfolded protein response (UPR) proteins such as ATF4 and CHOP. Early elevation of RTN3 in response to challenges by toxic Aβ likely facilitated UPR. Altogether, these findings suggest that Müller glia act as a sentinel for AD pathology in the retina and should aid for both intervention and diagnosis.

Which neuroimaging and fluid biomarkers method is better in theranostic of Alzheimer's disease? An umbrella review

Biomarkers are measured to evaluate physiological and pathological processes as well as responses to a therapeutic intervention. Biomarkers can be classified as diagnostic, prognostic, predictor, clinical, and therapeutic. In Alzheimer's disease (AD), multiple biomarkers have been reported so far. Nevertheless, finding a specific biomarker in AD remains a major challenge. Three databases, including PubMed, Web of Science, and Scopus were selected with the keywords of Alzheimer's disease, neuroimaging, biomarker, and blood. The results were finalized with 49 potential CSF/blood and 35 neuroimaging biomarkers. To distinguish normal from AD patients, amyloid-beta42 (Aβ42), plasma glial fibrillary acidic protein (GFAP), and neurofilament light (NFL) as potential biomarkers in cerebrospinal fluid (CSF) as well as the serum could be detected. Nevertheless, most of the biomarkers fairly change in the CSF during AD, listed as kallikrein 6, virus-like particles (VLP-1), galectin-3 (Gal-3), and synaptotagmin-1 (Syt-1). From the neuroimaging aspect, atrophy is an accepted biomarker for the neuropathologic progression of AD. In addition, Magnetic resonance spectroscopy (MRS), diffusion weighted imaging (DWI), diffusion tensor imaging (DTI), tractography (DTT), positron emission tomography (PET), and functional magnetic resonance imaging (fMRI), can be used to detect AD. Using neuroimaging and CSF/blood biomarkers, in combination with artificial intelligence, it is possible to obtain information on prognosis and follow-up on the different stages of AD. Hence physicians could select the suitable therapy to attenuate disease symptoms and follow up on the efficiency of the prescribed drug.

Clinical and Neuroimaging Predictors of Alzheimer's Dementia Conversion in Patients with Mild Cognitive Impairment Using Amyloid Positron Emission Tomography by Quantitative Analysis over 2 Years

Patients with mild cognitive impairment (MCI) have a relatively high risk of developing Alzheimer's dementia (AD), so early identification of the risk for AD conversion can lessen the socioeconomic burden. In this study, 18F-Florapronol, newly developed in Korea, was used for qualitative and quantitative analyses to assess amyloid positivity. We also investigated the clinical predictors of the progression from MCI to dementia over 2 years. From December 2019 to December 2022, 50 patients with MCI were recruited at a single center, and 34 patients were included finally. Based on visual analysis, 13 (38.2%) of 34 participants were amyloid-positive, and 12 (35.3%) were positive by quantitative analysis. Moreover, 6 of 34 participants (17.6%) converted to dementia after a 2-year follow-up (p = 0.173). Among the 15 participants who were positive for amyloid in the posterior cingulate region, 5 (33.3%) patients developed dementia (p = 0.066). The Clinical Dementia Rating-Sum of Boxes (CDR-SOB) at baseline was significantly associated with AD conversion in multivariate Cox regression analyses (p = 0.043). In conclusion, these results suggest that amyloid positivity in the posterior cingulate region and higher CDR-SOB scores at baseline can be useful predictors of AD conversion in patients with MCI.

The diagnostic, therapeutic, and ethical impact of artificial intelligence in modern medicine

In the evolution of modern medicine, artificial intelligence (AI) has been proven to provide an integral aspect of revolutionizing clinical diagnosis, drug discovery, and patient care. With the potential to scrutinize colossal amounts of medical data, radiological and histological images, and genomic data in healthcare institutions, AI-powered systems can recognize, determine, and associate patterns and provide impactful insights that would be strenuous and challenging for clinicians to detect during their daily clinical practice. The outcome of AI-mediated search offers more accurate, personalized patient diagnoses, guides in research for new drug therapies, and provides a more effective multidisciplinary treatment plan that can be implemented for patients with chronic diseases. Among the many promising applications of AI in modern medicine, medical imaging stands out distinctly as an area with tremendous potential. AI-powered algorithms can now accurately and sensitively identify cancer cells and other lesions in medical images with greater accuracy and sensitivity. This allows for earlier diagnosis and treatment, which can significantly impact patient outcomes. This review provides a comprehensive insight into diagnostic, therapeutic, and ethical issues with the advent of AI in modern medicine.

Longitudinal MRI analysis using a hybrid DenseNet-BiLSTM method for Alzheimer's disease prediction

Alzheimer's disease is a progressive neurological disorder characterized by brain atrophy and cell death, leading to cognitive decline and impaired functioning. Previous research has primarily focused on using cross-sectional data for Alzheimer's disease identification, but analyzing longitudinal sequential MR images is crucial for improved diagnostic accuracy and understanding disease progression. However, existing deep learning models face challenges in learning spatial and temporal features from such data. To address these challenges, this study presents a novel hybrid DenseNet-BiLSTM method for Alzheimer's disease prediction using longitudinal MRI analysis. The proposed framework combines Convolutional DenseNet for spatial information extraction and joined BiLSTM layers for capturing temporal characteristics and relationships between longitudinal images at different time points. This approach overcomes issues like overfitting, vanishing gradients, and incomplete patient data. We evaluated the model on 684 longitudinal MRI images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, including normal controls, individuals with mild cognitive impairment, and Alzheimer's disease patients. The results demonstrate high classification accuracy, with 95.28% for AD/CN, 88.19% for NC/MCI, 83.51% for sMCI/pMCI, and 92.14% for MCI/AD. These findings highlight the substantial improvement in Alzheimer's disease diagnosis achieved through the utilization of longitudinal MRI images. The contributions of this study lie in both the deep learning and medical domains. In the deep learning domain, our hybrid framework effectively learns spatial and temporal features from longitudinal data, addressing the challenges associated with multi-dimensional and sequential time series data. In the medical domain, our study emphasizes the importance of analyzing baseline and longitudinal MR images for accurate diagnosis and understanding disease progression.

A novel method for PET connectomics guided by fibre-tracking MRI: Application to Alzheimer's disease

This study introduces a novel brain connectome matrix, track-weighted PET connectivity (twPC) matrix, which combines positron emission tomography (PET) and diffusion magnetic resonance imaging data to compute a PET-weighted connectome at the individual subject level. The new method is applied to characterise connectivity changes in the Alzheimer's disease (AD) continuum. The proposed twPC samples PET tracer uptake guided by the underlying white matter fibre-tracking streamline point-to-point connectivity calculated from diffusion MRI (dMRI). Using tau-PET, dMRI and T1-weighted MRI from the Alzheimer's Disease Neuroimaging Initiative database, structural connectivity (SC) and twPC matrices were computed and analysed using the network-based statistic (NBS) technique to examine topological alterations in early mild cognitive impairment (MCI), late MCI and AD participants. Correlation analysis was also performed to explore the coupling between SC and twPC. The NBS analysis revealed progressive topological alterations in both SC and twPC as cognitive decline progressed along the continuum. Compared to healthy controls, networks with decreased SC were identified in late MCI and AD, and networks with increased twPC were identified in early MCI, late MCI and AD. The altered network topologies were mostly different between twPC and SC, although with several common edges largely involving the bilateral hippocampus, fusiform gyrus and entorhinal cortex. Negative correlations were observed between twPC and SC across all subject groups, although displaying an overall reduction in the strength of anti-correlation with disease progression. twPC provides a new means for analysing subject-specific PET and MRI-derived information within a hybrid connectome using established network analysis methods, providing valuable insights into the relationship between structural connections and molecular distributions. PRACTITIONER POINTS: New method is proposed to compute patient-specific PET connectome guided by MRI fibre-tracking. Track-weighted PET connectivity (twPC) matrix allows to leverage PET and structural connectivity information. twPC was applied to dementia, to characterise the PET nework abnormalities in Alzheimer's disease and mild cognitive impairment.

A multi-cohort study of the hippocampal radiomics model and its associated biological changes in Alzheimer's Disease

There have been no previous reports of hippocampal radiomics features associated with biological functions in Alzheimer's Disease (AD). This study aims to develop and validate a hippocampal radiomics model from structural magnetic resonance imaging (MRI) data for identifying patients with AD, and to explore the mechanism underlying the developed radiomics model using peripheral blood gene expression. In this retrospective multi-study, a radiomics model was developed based on the radiomics discovery group (n = 420) and validated in other cohorts. The biological functions underlying the model were identified in the radiogenomic analysis group using paired MRI and peripheral blood transcriptome analyses (n = 266). Mediation analysis and external validation were applied to further validate the key module and hub genes. A 12 radiomics features-based prediction model was constructed and this model showed highly robust predictive power for identifying AD patients in the validation and other three cohorts. Using radiogenomics mapping, myeloid leukocyte and neutrophil activation were enriched, and six hub genes were identified from the key module, which showed the highest correlation with the radiomics model. The correlation between hub genes and cognitive ability was confirmed using the external validation set of the AddneuroMed dataset. Mediation analysis revealed that the hippocampal radiomics model mediated the association between blood gene expression and cognitive ability. The hippocampal radiomics model can accurately identify patients with AD, while the predictive radiomics model may be driven by neutrophil-related biological pathways.

CoQ10 and Mitochondrial Dysfunction in Alzheimer's Disease

The progress in understanding the pathogenesis and treatment of Alzheimer's disease (AD) is based on the recognition of the primary causes of the disease, which can be deduced from the knowledge of risk factors and biomarkers measurable in the early stages of the disease. Insights into the risk factors and the time course of biomarker abnormalities point to a role for the connection of amyloid beta (Aβ) pathology, tau pathology, mitochondrial dysfunction, and oxidative stress in the onset and development of AD. Coenzyme Q10 (CoQ10) is a lipid antioxidant and electron transporter in the mitochondrial electron transport system. The availability and activity of CoQ10 is crucial for proper mitochondrial function and cellular bioenergetics. Based on the mitochondrial hypothesis of AD and the hypothesis of oxidative stress, the regulation of the efficiency of the oxidative phosphorylation system by means of CoQ10 can be considered promising in restoring the mitochondrial function impaired in AD, or in preventing the onset of mitochondrial dysfunction and the development of amyloid and tau pathology in AD. This review summarizes the knowledge on the pathophysiology of AD, in which CoQ10 may play a significant role, with the aim of evaluating the perspective of the pharmacotherapy of AD with CoQ10 and its analogues.

Dynamic reconfiguration of brain coactivation states that underlying working memory correlates with cognitive decline in clinically unimpaired older adults

Impairments in working memory (WM) are evident in both clinically diagnosed patients with mild cognitive decline and older adults at risk, as indicated by lower scores on neuropsychological tests. Examining the WM-related neural signatures in at-risk older adults becomes essential for timely intervention. WM functioning relies on dynamic brain activities, particularly within the frontoparietal system. However, it remains unclear whether the cognitive decline would be reflected in the decreased dynamic reconfiguration of brain coactivation states during WM tasks. We enrolled 47 older adults and assessed their cognitive function using the Montreal Cognitive Assessment. The temporal dynamics of brain coactivations during a WM task were investigated through graph-based time-frame modularity analysis. Four primary recurring states emerged: two task-positive states with positive activity in the frontoparietal system (dorsal attention and central executive); two task-negative states with positive activity in the default mode network accompanied by negative activity in the frontoparietal networks. Heightened WM load was associated with increased flexibility of the frontoparietal networks, but the cognitive decline was correlated with reduced capacity for neuroplastic changes in response to increased task demands. These findings advance our understanding of aberrant brain reconfiguration linked to cognitive decline, potentially aiding early identification of at-risk individuals.

Aging-Dependent Loss of Connectivity in Alzheimer's Model Mice with Rescue by mGluR5 Modulator

Amyloid accumulation in Alzheimer's disease (AD) is associated with synaptic damage and altered connectivity in brain networks. While measures of amyloid accumulation and biochemical changes in mouse models have utility for translational studies of certain therapeutics, preclinical analysis of altered brain connectivity using clinically relevant fMRI measures has not been well developed for agents intended to improve neural networks. Here, we conduct a longitudinal study in a double knock-in mouse model for AD ( App NL-G-F /hMapt ), monitoring brain connectivity by means of resting-state fMRI. While the 4-month-old AD mice are indistinguishable from wild-type controls (WT), decreased connectivity in the default-mode network is significant for the AD mice relative to WT mice by 6 months of age and is pronounced by 9 months of age. In a second cohort of 20-month-old mice with persistent functional connectivity deficits for AD relative to WT, we assess the impact of two-months of oral treatment with a silent allosteric modulator of mGluR5 (BMS-984923) known to rescue synaptic density. Functional connectivity deficits in the aged AD mice are reversed by the mGluR5-directed treatment. The longitudinal application of fMRI has enabled us to define the preclinical time trajectory of AD-related changes in functional connectivity, and to demonstrate a translatable metric for monitoring disease emergence, progression, and response to synapse-rescuing treatment.

Sleep Biomarkers for Predicting Cognitive Decline and Alzheimer's Disease: A Systematic Review of Longitudinal Studies

BACKGROUND

Sleep disturbances are considered a hallmark of dementia, and strong evidence supports the association between alterations in sleep parameters and cognitive decline in patients with mild cognitive impairment and Alzheimer's disease (AD).

OBJECTIVE

This systematic review aims to summarize the existing evidence on the longitudinal association between sleep parameters and cognitive decline, with the goal of identifying potential sleep biomarkers of AD-related neurodegeneration.

METHODS

Literature search was conducted in PubMed, Web of Science, and Scopus databases from inception to 28 March 2023. Longitudinal studies investigating the association between baseline objectively-measured sleep parameters and cognitive decline were assessed for eligibility.

RESULTS

Seventeen studies were included in the qualitative synthesis. Sleep fragmentation, reduced sleep efficiency, reduced REM sleep, increased light sleep, and sleep-disordered breathing were identified as predictors of cognitive decline. Sleep duration exhibited a U-shaped relation with subsequent neurodegeneration. Additionally, several sleep microstructural parameters were associated with cognitive decline, although inconsistencies were observed across studies.

CONCLUSIONS

These findings suggest that sleep alterations hold promise as early biomarker of cognitive decline, but the current evidence is limited due to substantial methodological heterogeneity among studies. Further research is necessary to identify the most reliable sleep parameters for predicting cognitive impairment and AD, and to investigate interventions targeting sleep that can assist clinicians in the early recognition and treatment of cognitive decline. Standardized procedures for longitudinal studies evaluating sleep and cognition should be developed and the use of continuous sleep monitoring techniques, such as actigraphy or EEG headband, might be encouraged.

Brain-Cognition Associations in Older Patients With Remitted Major Depressive Disorder or Mild Cognitive Impairment: A Multivariate Analysis of Gray and White Matter Integrity

BACKGROUND

Almost half of older patients with major depressive disorder (MDD) present with cognitive impairment, and one-third meet diagnostic criteria for mild cognitive impairment (MCI). However, mechanisms linking MDD and MCI remain unclear. We investigated multivariate associations between brain structural alterations and cognition in 3 groups of older patients at risk for dementia, remitted MDD (rMDD), MCI, and rMDD+MCI, as well as cognitively healthy nondepressed control participants.

METHODS

We analyzed magnetic resonance imaging data and cognitive domain scores in participants from the PACt-MD (Prevention of Alzheimer's Disease With Cognitive Remediation Plus Transcranial Direct Current Stimulation in Mild Cognitive Impairment and Depression) study. Following quality control, we measured cortical thickness and subcortical volumes of selected regions from 283 T1-weighted scans and fractional anisotropy of white matter tracts from 226 diffusion-weighted scans. We assessed brain-cognition associations using partial least squares regressions in the whole sample and in each subgroup.

RESULTS

In the entire sample, atrophy in the medial temporal lobe and subregions of the motor and prefrontal cortex was associated with deficits in verbal and visuospatial memory, language skills, and, to a lesser extent, processing speed (p < .0001; multivariate r = 0.30, 0.34, 0.26, and 0.18, respectively). Widespread reduced white matter integrity was associated with deficits in executive functioning, working memory, and processing speed (p = .008; multivariate r = 0.21, 0.26, 0.35, respectively). Overall, associations remained significant in the MCI and rMDD+MCI groups, but not the rMDD or healthy control groups.

CONCLUSIONS

We confirm findings of brain-cognition associations previously reported in MCI and extend them to rMDD+MCI, but similar associations in rMDD are not supported. Early-onset and treated MDD might not contribute to structural alterations associated with cognitive impairment.

The Biochemistry Behind Cognitive Decline: Biomarkers of Alzheimer's Disease

Alzheimer's disease (AD) is the most prevalent type of dementia. Pathologically, the disease is marked by neurofibrillary tangles (NFT), which are aberrant accumulations of the tau protein that develop inside neurons, and extracellular plaque deposits of the amyloid β peptide (Aβ). These pathological lesions are present in the brain before the beginning of clinical manifestations. However, despite advancements in the comprehension of AD pathophysiology, timely and accurate clinical diagnosis remains challenging. Therefore, developing biomarkers capable of detecting AD during the preclinical phase holds enormous promise for precise diagnosis since detecting the disease early is crucial because it enables interventions when treatments may be more effective. This article intends to provide a comprehensive review of AD biomarkers, discussing their significance, classification, and recent developments in the field.

Artificial intelligence for biomarker discovery in Alzheimer's disease and dementia

With the increase in large multimodal cohorts and high-throughput technologies, the potential for discovering novel biomarkers is no longer limited by data set size. Artificial intelligence (AI) and machine learning approaches have been developed to detect novel biomarkers and interactions in complex data sets. We discuss exemplar uses and evaluate current applications and limitations of AI to discover novel biomarkers. Remaining challenges include a lack of diversity in the data sets available, the sheer complexity of investigating interactions, the invasiveness and cost of some biomarkers, and poor reporting in some studies. Overcoming these challenges will involve collecting data from underrepresented populations, developing more powerful AI approaches, validating the use of noninvasive biomarkers, and adhering to reporting guidelines. By harnessing rich multimodal data through AI approaches and international collaborative innovation, we are well positioned to identify clinically useful biomarkers that are accurate, generalizable, unbiased, and acceptable in clinical practice. HIGHLIGHTS: Artificial intelligence and machine learning approaches may accelerate dementia biomarker discovery. Remaining challenges include data set suitability due to size and bias in cohort selection. Multimodal data, diverse data sets, improved machine learning approaches, real-world validation, and interdisciplinary collaboration are required.

Alzheimer's Related Neurodegeneration Mediates Air Pollution Effects on Medial Temporal Lobe Atrophy

Exposure to ambient air pollution, especially particulate matter with aerodynamic diameter <2.5 μm (PM2.5) and nitrogen dioxide (NO2), are environmental risk factors for Alzheimer's disease and related dementia. The medial temporal lobe (MTL) is an important brain region subserving episodic memory that atrophies with age, during the Alzheimer's disease continuum, and is vulnerable to the effects of cerebrovascular disease. Despite the importance of air pollution it is unclear whether exposure leads to atrophy of the MTL and by what pathways. Here we conducted a longitudinal study examining associations between ambient air pollution exposure and MTL atrophy and whether putative air pollution exposure effects resembled Alzheimer's disease-related neurodegeneration or cerebrovascular disease-related neurodegeneration. Participants included older women (n = 627; aged 71-87) who underwent two structural brain MRI scans (MRI-1: 2005-6; MRI-2: 2009-10) as part of the Women's Health Initiative Memory Study of Magnetic Resonance Imaging. Regionalized universal kriging was used to estimate annual concentrations of PM2.5 and NO2 at residential locations aggregated to 3-year averages prior to MRI-1. The outcome was 5-year standardized change in MTL volumes. Mediators included voxel-based MRI measures of the spatial pattern of neurodegeneration of Alzheimer's disease (Alzheimer's disease pattern similarity scores [AD-PS]) and whole-brain white matter small-vessel ischemic disease (WM-SVID) volume as a proxy of global cerebrovascular damage. Structural equation models were constructed to examine whether the associations between exposures with MTL atrophy were mediated by the initial level or concurrent change in AD-PS score or WM-SVID while adjusting for sociodemographic, lifestyle, clinical characteristics, and intracranial volume. Living in locations with higher PM2.5 (per interquartile range [IQR]=3.17μg/m3) or NO2 (per IQR=6.63ppb) was associated with greater MTL atrophy (βPM2.5 = -0.29, 95% confidence interval [CI]=[-0.41,-0.18]; βNO2 =-0.12, 95%CI=[-0.23,-0.02]). Greater PM2.5 was associated with larger increases in AD-PS (βPM2.5 = 0.23, 95%CI=[0.12,0.33]) over time, which partially mediated associations with MTL atrophy (indirect effect= -0.10; 95%CI=[-0.15, -0.05]), explaining approximately 32% of the total effect. NO2 was positively associated with AD-PS at MRI-1 (βNO2=0.13, 95%CI=[0.03,0.24]), which partially mediated the association with MTL atrophy (indirect effect= -0.01, 95% CI=[-0.03,-0.001]). Global WM-SVID at MRI-1 or concurrent change were not significant mediators between exposures and MTL atrophy. Findings support the mediating role of Alzheimer's disease-related neurodegeneration contributing to MTL atrophy associated with late-life exposures to air pollutants. Alzheimer's disease-related neurodegeneration only partially explained associations between exposure and MTL atrophy suggesting the role of multiple neuropathological processes underlying air pollution neurotoxicity on brain aging.

Early changes of fecal short-chain fatty acid levels in patients with mild cognitive impairments

AIMS

To compare the fecal levels of short-chain fatty acids (SCFAs) in patients with mild cognitive impairment (MCI) and normal controls (NCs) and to examine whether fecal SCFAs could be used as the biomarker for the identification of patients with MCI. To examine the relationship between fecal SCFAs and amyloid-β (Aβ) deposition in the brain.

METHODS

A cohort of 32 MCI patients, 23 Parkinson's disease (PD) patients, and 27 NC were recruited in our study. Fecal levels of SCFAs were measured using chromatography and mass spectrometry. Disease duration, ApoE genotype, body mass index, constipation, and diabetes were evaluated. To assess cognitive impairment, we used the Mini-Mental Status Examination (MMSE). To assess brain atrophy, the degree of medial temporal atrophy (MTA score, Grade 0-4) was measured by structural MRI. Aβ positron emission tomography with 18 F-florbetapir (FBP) was performed in seven MCI patients at the time of stool sampling and in 28 MCI patients at an average of 12.3 ± 0.4 months from the time of stool sampling to detect and quantify Aβ deposition in the brain.

RESULTS

Compared with NC, MCI patients had significantly lower fecal levels of acetic acid, butyric acid, and caproic acid. Among fecal SCFAs, acetic acid performed the best in discriminating MCI from NC, achieved an AUC of 0.752 (p = 0.001, 95% CI: 0.628-0.876), specificity of 66.7%, and sensitivity of 75%. By combining fecal levels of acetic acid, butyric acid, and caproic acid, the diagnostic specificity was significantly improved, reaching 88.9%. To better verify the diagnostic performance of SCFAs, we randomly assigned 60% of participants into training dataset and 40% into testing dataset. Only acetic acid showed significantly difference between these two groups in the training dataset. Based on the fecal levels of acetic acid, we achieved the ROC curve. Next, the ROC curve was evaluated in the independent test data and 61.5% (8 in 13) of patients with MCI, and 72.7% (8 in 11) of NC could be identified correctly. Subgroup analysis showed that reduced fecal SCFAs in MCI group were negatively associated with Aβ deposition in cognition-related brain regions.

CONCLUSION

Reductions in fecal SCFAs were observed in patients with MCI compared with NC. Reduced fecal SCFAs were negatively associated with Aβ deposition in cognition-related brain regions in MCI group. Our findings suggest that gut metabolite SCFAs have the potential to serve as early diagnostic biomarkers for distinguishing patients with MCI from NC and could serve as potential targets for preventing AD.

Bayesian workflow for the investigation of hierarchical classification models from tau-PET and structural MRI data across the Alzheimer's disease spectrum

Background

Alzheimer's disease (AD) diagnosis in its early stages remains difficult with current diagnostic approaches. Though tau neurofibrillary tangles (NFTs) generally follow the stereotypical pattern described by the Braak staging scheme, the network degeneration hypothesis (NDH) has suggested that NFTs spread selectively along functional networks of the brain. To evaluate this, we implemented a Bayesian workflow to develop hierarchical multinomial logistic regression models with increasing levels of complexity of the brain from tau-PET and structural MRI data to investigate whether it is beneficial to incorporate network-level information into an ROI-based predictive model for the presence/absence of AD.

Methods

This study included data from the Translational Biomarkers in Aging and Dementia (TRIAD) longitudinal cohort from McGill University's Research Centre for Studies in Aging (MCSA). Baseline and 1 year follow-up structural MRI and [18F]MK-6240 tau-PET scans were acquired for 72 cognitive normal (CN), 23 mild cognitive impairment (MCI), and 18 Alzheimer's disease dementia subjects. We constructed the four following hierarchical Bayesian models in order of increasing complexity: (Model 1) a complete-pooling model with observations, (Model 2) a partial-pooling model with observations clustered within ROIs, (Model 3) a partial-pooling model with observations clustered within functional networks, and (Model 4) a partial-pooling model with observations clustered within ROIs that are also clustered within functional brain networks. We then investigated which of the models had better predictive performance given tau-PET or structural MRI data as an input, in the form of a relative annualized rate of change.

Results

The Bayesian leave-one-out cross-validation (LOO-CV) estimate of the expected log pointwise predictive density (ELPD) results indicated that models 3 and 4 were substantially better than other models for both tau-PET and structural MRI inputs. For tau-PET data, model 3 was slightly better than 4 with an absolute difference in ELPD of 3.10 ± 1.30. For structural MRI data, model 4 was considerably better than other models with an absolute difference in ELPD of 29.83 ± 7.55 relative to model 3, the second-best model.

Conclusion

Our results suggest that representing the data generating process in terms of a hierarchical model that encompasses both ROI-level and network-level heterogeneity leads to better predictive ability for both tau-PET and structural MRI inputs over all other model iterations.

NODDI-derived measures of microstructural integrity in medial temporal lobe white matter pathways are associated with Alzheimer's disease pathology and cognitive outcomes

INTRODUCTION

Diffusion tensor imaging has been used to assess white matter (WM) changes in the early stages of Alzheimer's disease (AD). However, the tensor model is necessarily limited by its assumptions. Neurite Orientation Dispersion and Density Imaging (NODDI) can offer insights into microstructural features of WM change. We assessed whether NODDI more sensitively detects AD-related changes in medial temporal lobe WM than traditional tensor metrics.

METHODS

Standard diffusion and NODDI metrics were calculated for medial temporal WM tracts from 199 older adults drawn from ADNI3 who also received PET to measure pathology and neuropsychological testing.

RESULTS

NODDI measures in medial temporal tracts were more strongly correlated to cognitive performance and pathology than standard measures. The combination of NODDI and standard metrics exhibited the strongest prediction of cognitive performance in random forest analyses.

CONCLUSIONS

NODDI metrics offer additional insights into contributions of WM degeneration to cognitive outcomes in the aging brain.

Optimized Convolutional Fusion for Multimodal Neuroimaging in Alzheimer's Disease Diagnosis: Enhancing Data Integration and Feature Extraction

Multimodal neuroimaging has gained traction in Alzheimer's Disease (AD) diagnosis by integrating information from multiple imaging modalities to enhance classification accuracy. However, effectively handling heterogeneous data sources and overcoming the challenges posed by multiscale transform methods remains a significant hurdle. This article proposes a novel approach to address these challenges. To harness the power of diverse neuroimaging data, we employ a strategy that leverages optimized convolution techniques. These optimizations include varying kernel sizes and the incorporation of instance normalization, both of which play crucial roles in feature extraction from magnetic resonance imaging (MRI) and positron emission tomography (PET) images. Specifically, varying kernel sizes allow us to adapt the receptive field to different image characteristics, enhancing the model's ability to capture relevant information. Furthermore, we employ transposed convolution, which increases spatial resolution of feature maps, and it is optimized with varying kernel sizes and instance normalization. This heightened resolution facilitates the alignment and integration of data from disparate MRI and PET data. The use of larger kernels and strides in transposed convolution expands the receptive field, enabling the model to capture essential cross-modal relationships. Instance normalization, applied to each modality during the fusion process, mitigates potential biases stemming from differences in intensity, contrast, or scale between modalities. This enhancement contributes to improved model performance by reducing complexity and ensuring robust fusion. The performance of the proposed fusion method is assessed on three distinct neuroimaging datasets, which include: Alzheimer's Disease Neuroimaging Initiative (ADNI), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD, and Early Mild Cognitive); Open Access Series of Imaging Studies (OASIS), consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, Mild Dementia, Very Mild Dementia); and whole-brain atlas neuroimaging (AANLIB) (consisting of 50 participants each at various stages of AD for both MRI and PET (Cognitive Normal, AD). To evaluate the quality of the fused images generated via our method, we employ a comprehensive set of evaluation metrics, including Structural Similarity Index Measurement (SSIM), which assesses the structural similarity between two images; Peak Signal-to-Noise Ratio (PSNR), which measures how closely the generated image resembles the ground truth; Entropy (E), which assesses the amount of information preserved or lost during fusion; the Feature Similarity Indexing Method (FSIM), which assesses the structural and feature similarities between two images; and Edge-Based Similarity (EBS), which measures the similarity of edges between the fused and ground truth images. The obtained fused image is further evaluated using a Mobile Vision Transformer. In the classification of AD vs. Cognitive Normal, the model achieved an accuracy of 99.00%, specificity of 99.00%, and sensitivity of 98.44% on the AANLIB dataset.

Recent diagnostic techniques for the detection of Alzheimer's disease: a short review

Alzheimer's disease (AD) is a neurological condition that affects millions of individuals around the world and for which there are few effective therapies. Dementia is characterized by the formation of senile plaques and neurofibrillary tangles, which is followed by neurotoxicity, which results in memory loss and mortality. Pathogenesis occurs several years before the onset of disease. As the disease-modifying drugs are most effective in the early stages of Alzheimer's disease, biomarkers for early detection of disease and their development are crucial. This review discusses the diagnostic utility, benefits, and limitations of traditional techniques such as neuroimaging, cognitive testing, positron emission tomography, and biomarkers, as well as the novel techniques such as artificial intelligence, machine learning, immunotherapy, and blood test approaches for early detection, understanding, and treatment of AD.

Astrogliosis, neuritic microstructure, and sex effects: GFAP is an indicator of neuritic orientation in women

BACKGROUND

Data from human studies suggest that immune dysregulation is associated with Alzheimer's disease (AD) pathology and cognitive decline and that neurites may be affected early in the disease trajectory. Data from animal studies further indicate that dysfunction in astrocytes and inflammation may have a pivotal role in facilitating dendritic damage, which has been linked with negative cognitive outcomes. To elucidate these relationships further, we have examined the relationship between astrocyte and immune dysregulation, AD-related pathology, and neuritic microstructure in AD-vulnerable regions in late life.

METHODS

We evaluated panels of immune, vascular, and AD-related protein markers in blood and conducted in vivo multi-shell neuroimaging using Neurite Orientation Dispersion and Density Imaging (NODDI) to assess indices of neuritic density (NDI) and dispersion (ODI) in brain regions vulnerable to AD in a cohort of older adults (n = 109).

RESULTS

When examining all markers in tandem, higher plasma GFAP levels were strongly related to lower neurite dispersion (ODI) in grey matter. No biomarker associations were found with higher neuritic density. Associations between GFAP and neuritic microstructure were not significantly impacted by symptom status, APOE status, or plasma Aβ42/40 ratio; however, there was a large sex effect observed for neurite dispersion, wherein negative associations between GFAP and ODI were only observed in females.

DISCUSSION

This study provides a comprehensive, concurrent appraisal of immune, vascular, and AD-related biomarkers in the context of advanced grey matter neurite orientation and dispersion methodology. Sex may be an important modifier of the complex associations between astrogliosis, immune dysregulation, and brain microstructure in older adults.

Gut-brain connections in neurodegenerative disease: immunotherapeutic targeting of Bin1 in inflammatory bowel disease and Alzheimer's disease

Longer lifespan produces risks of age-associated neurodegenerative disorders such as Alzheimer's disease (AD), which is characterized by declines in memory and cognitive function. The pathogenic causes of AD are thought to reflect a progressive aggregation in the brain of amyloid plaques composed of beta-amyloid (Aß) peptides and neurofibrillary tangles composed of phosphorylated tau protein. Recently, long-standing investigations of the Aß disease hypothesis gained support via a passive immunotherapy targeting soluble Aß protein. Tau-targeting approaches using antibodies are also being pursued as a therapeutic approach to AD. In genome-wide association studies, the disease modifier gene Bin1 has been identified as a top risk factor for late-onset AD in human populations, with recent studies suggesting that Bin1 binds tau and influences its extracellular deposition. Interestingly, before AD emerges in the brain, tau levels rise in the colon, where Bin1-a modifier of tissue barrier function and inflammation-acts to promote inflammatory bowel disease (IBD). This connection is provocative given clinical evidence of gut-brain communication in age-associated neurodegenerative disorders, including AD. In this review, we discuss a Bin1-targeting passive immunotherapy developed in our laboratory to treat IBD that may offer a strategy to indirectly reduce tau deposition and limit AD onset or progression.

Exploring the Frontiers of Neuroimaging: A Review of Recent Advances in Understanding Brain Functioning and Disorders

Neuroimaging has revolutionized our understanding of brain function and has become an essential tool for researchers studying neurological disorders. Functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) are two widely used neuroimaging techniques to review changes in brain activity. fMRI is a noninvasive technique that uses magnetic fields and radio waves to produce detailed brain images. An EEG is a noninvasive technique that records the brain's electrical activity through electrodes placed on the scalp. This review overviews recent developments in noninvasive functional neuroimaging methods, including fMRI and EEG. Recent advances in fMRI technology, its application to studying brain function, and the impact of neuroimaging techniques on neuroscience research are discussed. Advances in EEG technology and its applications to analyzing brain function and neural oscillations are also highlighted. In addition, advanced courses in neuroimaging, such as diffusion tensor imaging (DTI) and transcranial electrical stimulation (TES), are described, along with their role in studying brain connectivity, white matter tracts, and potential treatments for schizophrenia and chronic pain. Application. The review concludes by examining neuroimaging studies of neurodevelopmental and neurological disorders such as autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), Alzheimer's disease (AD), and Parkinson's disease (PD). We also described the role of transcranial direct current stimulation (tDCS) in ASD, ADHD, AD, and PD. Neuroimaging techniques have significantly advanced our understanding of brain function and provided essential insights into neurological disorders. However, further research into noninvasive treatments such as EEG, MRI, and TES is necessary to continue to develop new diagnostic and therapeutic strategies for neurological disorders.

Neuroimaging modalities in the detection of Alzheimer's disease-associated biomarkers

Alzheimer's disease (AD) is the most common cause of dementia. Neuropathological changes in AD patients occur up to 10-20 years before the emergence of clinical symptoms. Specific diagnosis and appropriate intervention strategies are crucial during the phase of mild cognitive impairment (MCI) and AD. The detection of biomarkers has emerged as a promising tool for tracking the efficacy of potential therapies, making an early disease diagnosis, and prejudging treatment prognosis. Specifically, multiple neuroimaging modalities, including magnetic resonance imaging (MRI), positron emission tomography, optical imaging, and single photon emission-computed tomography, have provided a few potential biomarkers for clinical application. The MRI modalities described in this review include structural MRI, functional MRI, diffusion tensor imaging, magnetic resonance spectroscopy, and arterial spin labelling. These techniques allow the detection of presymptomatic diagnostic biomarkers in the brains of cognitively normal elderly people and might also be used to monitor AD disease progression after the onset of clinical symptoms. This review highlights potential biomarkers, merits, and demerits of different neuroimaging modalities and their clinical value in MCI and AD patients. Further studies are necessary to explore more biomarkers and overcome the limitations of multiple neuroimaging modalities for inclusion in diagnostic criteria for AD.

Deep learning application for the classification of Alzheimer's disease using 18F-flortaucipir (AV-1451) tau positron emission tomography

The positron emission tomography (PET) with 18F-flortaucipir can distinguish individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD) from cognitively unimpaired (CU) individuals. This study aimed to evaluate the utility of 18F-flortaucipir-PET images and multimodal data integration in the differentiation of CU from MCI or AD through DL. We used cross-sectional data (18F-flortaucipir-PET images, demographic and neuropsychological score) from the ADNI. All data for subjects (138 CU, 75 MCI, 63 AD) were acquired at baseline. The 2D convolutional neural network (CNN)-long short-term memory (LSTM) and 3D CNN were conducted. Multimodal learning was conducted by adding the clinical data with imaging data. Transfer learning was performed for classification between CU and MCI. The AUC for AD classification from CU was 0.964 and 0.947 in 2D CNN-LSTM and multimodal learning. The AUC of 3D CNN showed 0.947, and 0.976 in multimodal learning. The AUC for MCI classification from CU had 0.840 and 0.923 in 2D CNN-LSTM and multimodal learning. The AUC of 3D CNN showed 0.845, and 0.850 in multimodal learning. The 18F-flortaucipir PET is effective for the classification of AD stage. Furthermore, the effect of combination images with clinical data increased the performance of AD classification.

Machine learning application for classification of Alzheimer's disease stages using 18F-flortaucipir positron emission tomography

BACKGROUND

The progression of Alzheimer's dementia (AD) can be classified into three stages: cognitive unimpairment (CU), mild cognitive impairment (MCI), and AD. The purpose of this study was to implement a machine learning (ML) framework for AD stage classification using the standard uptake value ratio (SUVR) extracted from ¹⁸F-flortaucipir positron emission tomography (PET) images. We demonstrate the utility of tau SUVR for AD stage classification. We used clinical variables (age, sex, education, mini-mental state examination scores) and SUVR extracted from PET images scanned at baseline. Four types of ML frameworks, such as logistic regression, support vector machine (SVM), extreme gradient boosting, and multilayer perceptron (MLP), were used and explained by Shapley Additive Explanations (SHAP) to classify the AD stage.

RESULTS

Of a total of 199 participants, 74, 69, and 56 patients were in the CU, MCI, and AD groups, respectively; their mean age was 71.5 years, and 106 (53.3%) were men. In the classification between CU and AD, the effect of clinical and tau SUVR was high in all classification tasks and all models had a mean area under the receiver operating characteristic curve (AUC) > 0.96. In the classification between MCI and AD, the independent effect of tau SUVR in SVM had an AUC of 0.88 (p < 0.05), which was the highest compared to other models. In the classification between MCI and CU, the AUC of each classification model was higher with tau SUVR variables than with clinical variables independently, which yielded an AUC of 0.75(p < 0.05) in MLP, which was the highest. As an explanation by SHAP for the classification between MCI and CU, and AD and CU, the amygdala and entorhinal cortex greatly affected the classification results. In the classification between MCI and AD, the para-hippocampal and temporal cortex affected model performance. Especially entorhinal cortex and amygdala showed a higher effect on model performance than all clinical variables in the classification between MCI and CU.

CONCLUSIONS

The independent effect of tau deposition indicates that it is an effective biomarker in classifying CU and MCI into clinical stages using MLP. It is also very effective in classifying AD stages using SVM with clinical information that can be easily obtained at clinical screening.

Should artificial intelligence be used in conjunction with Neuroimaging in the diagnosis of Alzheimer's disease?

Alzheimer's disease (AD) is a progressive, neurodegenerative disorder that affects memory, thinking, behavior, and other cognitive functions. Although there is no cure, detecting AD early is important for the development of a therapeutic plan and a care plan that may preserve cognitive function and prevent irreversible damage. Neuroimaging, such as magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET), has served as a critical tool in establishing diagnostic indicators of AD during the preclinical stage. However, as neuroimaging technology quickly advances, there is a challenge in analyzing and interpreting vast amounts of brain imaging data. Given these limitations, there is great interest in using artificial Intelligence (AI) to assist in this process. AI introduces limitless possibilities in the future diagnosis of AD, yet there is still resistance from the healthcare community to incorporate AI in the clinical setting. The goal of this review is to answer the question of whether AI should be used in conjunction with neuroimaging in the diagnosis of AD. To answer the question, the possible benefits and disadvantages of AI are discussed. The main advantages of AI are its potential to improve diagnostic accuracy, improve the efficiency in analyzing radiographic data, reduce physician burnout, and advance precision medicine. The disadvantages include generalization and data shortage, lack of in vivo gold standard, skepticism in the medical community, potential for physician bias, and concerns over patient information, privacy, and safety. Although the challenges present fundamental concerns and must be addressed when the time comes, it would be unethical not to use AI if it can improve patient health and outcome.

Single‐value scores of memory‐related brain activity reflect dissociable neuropsychological and anatomical signatures of neurocognitive aging

Memory-related functional magnetic resonance imaging (fMRI) activations show age-related differences across multiple brain regions that can be captured in summary statistics like single-value scores. Recently, we described two single-value scores reflecting deviations from prototypical whole-brain fMRI activity of young adults during novelty processing and successful encoding. Here, we investigate the brain-behavior associations of these scores with age-related neurocognitive changes in 153 healthy middle-aged and older adults. All scores were associated with episodic recall performance. The memory network scores, but not the novelty network scores, additionally correlated with medial temporal gray matter and other neuropsychological measures including flexibility. Our results thus suggest that novelty-network-based fMRI scores show high brain-behavior associations with episodic memory and that encoding-network-based fMRI scores additionally capture individual differences in other aging-related functions. More generally, our results suggest that single-value scores of memory-related fMRI provide a comprehensive measure of individual differences in network dysfunction that may contribute to age-related cognitive decline.

Retinal Alterations as Potential Biomarkers of Structural Brain Changes in Alzheimer’s Disease Spectrum Patients

Retinal imaging being a potential biomarker for Alzheimer’s disease is gradually attracting the attention of researchers. However, the association between retinal parameters and AD neuroimaging biomarkers, particularly structural changes, is still unclear. In this cross-sectional study, we recruited 25 cognitively impaired (CI) and 21 cognitively normal (CN) individuals. All subjects underwent retinal layer thickness and microvascular measurements with optical coherence tomography angiography (OCTA). Gray matter and white matter (WM) data such as T1-weighted magnetic resonance imaging and diffusion tensor imaging, respectively, were also collected. In addition, hippocampal subfield volumes and WM tract microstructural alterations were investigated as classical AD neuroimaging biomarkers. The microvascular and retinal features and their correlation with brain structural imaging markers were further analyzed. We observed a reduction in vessel density (VD) at the inferior outer (IO) sector (p = 0.049), atrophy in hippocampal subfield volumes, such as the subiculum (p = 0.012), presubiculum (p = 0.015), molecular_layer_HP (p = 0.033), GC-ML-DG (p = 0.043) and whole hippocampus (p = 0.033) in CI patients. Altered microstructural integrity of WM tracts in CI patients was also discovered in the cingulum hippocampal part (CgH). Importantly, we detected significant associations between retinal VD and gray matter volumes of the hippocampal subfield in CI patients. These findings suggested that the retinal microvascular measures acquired by OCTA may be markers for the early prediction of AD-related structural brain changes.

Associations between different tau-PET patterns and longitudinal atrophy in the Alzheimer's disease continuum: biological and methodological perspectives from disease heterogeneity

BACKGROUND

Subtypes and patterns are defined using tau-PET (tau pathology) and structural MRI (atrophy) in Alzheimer's disease (AD). However, the relationship between tau pathology and atrophy across these subtypes/patterns remains unclear. Therefore, we investigated the biological association between baseline tau-PET patterns and longitudinal atrophy in the AD continuum; and the methodological characterization of heterogeneity as a continuous phenomenon over the conventional discrete subgrouping.

METHODS

In 366 individuals (amyloid-beta-positive cognitively normal, prodromal AD, AD dementia; amyloid-beta-negative cognitively normal), we examined the association between tau-PET patterns and longitudinal MRI. We modeled tau-PET patterns as a (a) continuous phenomenon with key dimensions: typicality and severity; and (b) discrete phenomenon by categorization into patterns: typical, limbic predominant, cortical predominant and minimal tau. Tau-PET patterns and associated longitudinal atrophy were contextualized within the Amyloid/Tau/Neurodegeneration (A/T/N) biomarker scheme.

RESULTS

Localization and longitudinal atrophy change vary differentially across different tau-PET patterns in the AD continuum. Atrophy, a downstream event, did not always follow a topography akin to the corresponding tau-PET pattern. Further, heterogeneity as a continuous phenomenon offered an alternative and useful characterization, sharing correspondence with the conventional subgrouping. Tau-PET patterns also show differential A/T/N profiles.

CONCLUSIONS

The site and rate of atrophy are different across the tau-PET patterns. Heterogeneity should be treated as a continuous, not discrete, phenomenon for greater sensitivity. Pattern-specific A/T/N profiles highlight differential multimodal interactions underlying heterogeneity. Therefore, tracking multimodal interactions among biomarkers longitudinally, modeling disease heterogeneity as a continuous phenomenon, and examining heterogeneity across the AD continuum could offer avenues for precision medicine.

Biomarkers of diagnosis, prognosis, pathogenesis, response to therapy: Convergence or divergence? Lessons from Alzheimer's disease and synucleinopathies

Alzheimer's disease (AD) is the most common disorder associated with cognitive impairment. Recent observations emphasize the pathogenic role of multiple factors inside and outside the central nervous system, supporting the notion that AD is a syndrome of many etiologies rather than a "heterogeneous" but ultimately unifying disease entity. Moreover, the defining pathology of amyloid and tau coexists with many others, such as α-synuclein, TDP-43, and others, as a rule, not an exception. Thus, an effort to shift our AD paradigm as an amyloidopathy must be reconsidered. Along with amyloid accumulation in its insoluble state, β-amyloid is becoming depleted in its soluble, normal states, as a result of biological, toxic, and infectious triggers, requiring a shift from convergence to divergence in our approach to neurodegeneration. These aspects are reflected-in vivo-by biomarkers, which have become increasingly strategic in dementia. Similarly, synucleinopathies are primarily characterized by abnormal deposition of misfolded α-synuclein in neurons and glial cells and, in the process, depleting the levels of the normal, soluble α-synuclein that the brain needs for many physiological functions. The soluble to insoluble conversion also affects other normal brain proteins, such as TDP-43 and tau, accumulating in their insoluble states in both AD and dementia with Lewy bodies (DLB). The two diseases have been distinguished by the differential burden and distribution of insoluble proteins, with neocortical phosphorylated tau deposition more typical of AD and neocortical α-synuclein deposition peculiar to DLB. We propose a reappraisal of the diagnostic approach to cognitive impairment from convergence (based on clinicopathologic criteria) to divergence (based on what differs across individuals affected) as a necessary step for the launch of precision medicine.

Modifiable Lifestyle Activities Affect Cognition in Cognitively Healthy Middle-Aged Individuals at Risk for Late-Life Alzheimer's Disease

BACKGROUND

It is now acknowledged that Alzheimer's disease (AD) processes are present decades before the onset of clinical symptoms, but it remains unknown whether lifestyle factors can protect against these early AD processes in mid-life.

OBJECTIVE

We asked whether modifiable lifestyle activities impact cognition in middle-aged individuals who are cognitively healthy, but at risk for late life AD. Participants (40-59 years) completed cognitive and clinical assessments at baseline (N = 206) and two years follow-up (N = 174).

METHODS

Mid-life activities were measured with the Lifetime of Experiences Questionnaire. We assessed the impact of lifestyle activities, known risk factors for sporadic late-onset AD (Apolipoprotein E ɛ4 allele status, family history of dementia, and the Cardiovascular Risk Factors Aging and Dementia score), and their interactions on cognition.

RESULTS

More frequent engagement in physically, socially, and intellectually stimulating activities was associated with better cognition (verbal, spatial, and relational memory), at baseline and follow-up. Critically, more frequent engagement in these activities was associated with stronger cognition (verbal and visuospatial functions, and conjunctive short-term memory binding) in individuals with family history of dementia. Impaired visuospatial function is one of the earliest cognitive deficits in AD and has previously associated with increased AD risk in this cohort. Additionally, conjunctive memory functions have been found impaired in the pre-symptomatic stages of AD.

CONCLUSION

These findings suggest that modifiable lifestyle activities offset cognitive decrements due to AD risk in mid-life and support the targeting of modifiable lifestyle activities for the prevention of AD.

A novel cascade machine learning pipeline for Alzheimer's disease identification and prediction

Introduction

Alzheimer's disease (AD) is a progressive and irreversible brain degenerative disorder early. Among all diagnostic strategies, hippocampal atrophy is considered a promising diagnostic method. In order to proactively detect patients with early Alzheimer's disease, we built an Alzheimer's segmentation and classification (AL-SCF) pipeline based on machine learning.

Methods

In our study, we collected coronal T1 weighted images that include 187 patients with AD and 230 normal controls (NCs). Our pipeline began with the segmentation of the hippocampus by using a modified U2-net. Subsequently, we extracted 851 radiomics features and selected 37 features most relevant to AD by the Hierarchical clustering method and Least Absolute Shrinkage and Selection Operator (LASSO) algorithm. At last, four classifiers were implemented to distinguish AD from NCs, and the performance of the models was evaluated by accuracy, specificity, sensitivity, and area under the curve.

Results

Our proposed pipeline showed excellent discriminative performance of classification with AD vs NC in the training set (AUC=0.97, 95% CI: (0.96-0.98)). The model was also verified in the validation set with Dice=0.93 for segmentation and accuracy=0.95 for classification.

Discussion

The AL-SCF pipeline can automate the process from segmentation to classification, which may assist doctors with AD diagnosis and develop individualized medical plans for AD in clinical practice.

Differences in structural MRI and diffusion tensor imaging underlie visuomotor performance declines in older adults with an increased risk for Alzheimer's disease

Introduction

Visuomotor impairments have been demonstrated in preclinical AD in individuals with a positive family history of dementia and APOE e4 carriers. Previous behavioral findings have also reported sex-differences in performance of visuomotor tasks involving a visual feedback reversal. The current study investigated the relationship between grey and white matter changes and non-standard visuomotor performance, as well as the effects of APOE status, family history of dementia, and sex on these brain-behavior relationships.

Methods

Older adults (n = 49) with no cognitive impairments completed non-standard visuomotor tasks involving a visual feedback reversal, plane-change, or combination of the two. Participants with a family history of dementia or who were APOE e4 carriers were considered at an increased risk for AD. T1-weighted anatomical scans were used to quantify grey matter volume and thickness, and diffusion tensor imaging measures were used to quantify white matter integrity.

Results

In APOE e4 carriers, grey and white matter structural measures were associated with visuomotor performance. Regression analyses showed that visuomotor deficits were predicted by lower grey matter thickness and volume in areas of the medial temporal lobe previously implicated in visuomotor control (entorhinal and parahippocampal cortices). This finding was replicated in the diffusion data, where regression analyses revealed that lower white matter integrity (lower FA, higher MD, higher RD, higher AxD) was a significant predictor of worse visuomotor performance in the forceps minor, forceps major, cingulum, inferior fronto-occipital fasciculus (IFOF), inferior longitudinal fasciculus (ILF), superior longitudinal fasciculus (SLF), and uncinate fasciculus (UF). Some of these tracts overlap with those important for visuomotor integration, namely the forceps minor, forceps major, SLF, IFOF, and ILF.

Conclusion

These findings suggest that measuring the dysfunction of brain networks underlying visuomotor control in early-stage AD may provide a novel behavioral target for dementia risk detection that is easily accessible, non-invasive, and cost-effective. The results also provide insight into the structural differences in inferior parietal lobule that may underlie previously reported sex-differences in performance of the visual feedback reversal task.

Frontostriatal and limbic contributions to cognitive decline in Parkinson's disease

BACKGROUND AND PURPOSE

The circuitry underlying heterogenous cognitive profiles in Parkinson's disease (PD) remains unclear. The purpose of this study is to investigate whether structural changes in frontostriatal and limbic pathways contribute to different cognitive trajectories in PD.

METHODS

We obtained clinical and multimodal MRI data from 120 control and 122 PD subjects without dementia or severe motor disability. T1/T2-weighted images estimated volume, and diffusion imaging evaluated fractional anisotropy (FA) of frontostriatal (striatum and frontostriatal white matter [FSWM]) and limbic (hippocampus and fornix) structures. Montreal Cognitive Assessment (MoCA) gauged total and domain-specific (attention/executive and memory) cognitive function. Linear mixed-effects models were used to compare MRI and cognitive progression over 4.5 years between controls and PD and evaluate associations between baseline MRI and cognitive changes in PD.

RESULTS

At baseline, control and PD groups were comparable, except PD participants had smaller striatal volume (p < 0.001). Longitudinally, PD showed faster decline in hippocampal volume, FSWM FA, and fornix FA (ps < .016), but not striatal volume (p = .218). Total and domain-specific MoCA scores declined faster in PD (ps < .030). In PD, lower baseline hippocampal volume (p = .005) and fornix FA (p = .032), but not striatal volume (p = .662) or FSWM FA (p = .143), were associated with faster total MoCA decline. Baseline frontostriatal metrics of striatal volume and FSWM FA were associated with faster attention/executive decline (p < .038), whereas lower baseline hippocampal volume was associated with faster memory decline (p = .005).

CONCLUSION

In PD, frontostriatal structural metrics are associated with attention/executive tasks, whereas limbic changes correlated with faster global cognitive decline, particularly in memory tasks.

Investigating neurological symptoms of infectious diseases like COVID-19 leading to a deeper understanding of neurodegenerative disorders such as Parkinson's disease

Apart from common respiratory symptoms, neurological symptoms are prevalent among patients with COVID-19. Research has shown that infection with SARS-CoV-2 accelerated alpha-synuclein aggregation, induced Lewy-body-like pathology, caused dopaminergic neuron senescence, and worsened symptoms in patients with Parkinson's disease (PD). In addition, SARS-CoV-2 infection can induce neuroinflammation and facilitate subsequent neurodegeneration in long COVID, and increase individual vulnerability to PD or parkinsonism. These findings suggest that a post-COVID-19 parkinsonism might follow the COVID-19 pandemic. In order to prevent a possible post-COVID-19 parkinsonism, this paper reviewed neurological symptoms and related findings of COVID-19 and related infectious diseases (influenza and prion disease) and neurodegenerative disorders (Alzheimer's disease, PD and amyotrophic lateral sclerosis), and discussed potential mechanisms underlying the neurological symptoms and the relationship between the infectious diseases and the neurodegenerative disorders, as well as the therapeutic and preventive implications in the neurodegenerative disorders. Infections with a relay of microbes (SARS-CoV-2, influenza A viruses, gut bacteria, etc.) and prion-like alpha-synuclein proteins over time may synergize to induce PD. Therefore, a systematic approach that targets these pathogens and the pathogen-induced neuroinflammation and neurodegeneration may provide cures for neurodegenerative disorders. Further, antiviral/antimicrobial drugs, vaccines, immunotherapies and new therapies (e.g., stem cell therapy) need to work together to treat, manage or prevent these disorders. As medical science and technology advances, it is anticipated that better vaccines for SARS-CoV-2 variants, new antiviral/antimicrobial drugs, effective immunotherapies (alpha-synuclein antibodies, vaccines for PD or parkinsonism, etc.), as well as new therapies will be developed and made available in the near future, which will help prevent a possible post-COVID-19 parkinsonism in the 21st century.

Differences in resting state functional connectivity underlie visuomotor performance declines in older adults with a genetic risk (APOE ε4) for Alzheimer’s disease

Introduction

Non-standard visuomotor integration requires the interaction of large networks in the brain. Previous findings have shown that non-standard visuomotor performance is impaired in individuals with specific dementia risk factors (family history of dementia and presence of the APOE ε4 allele) in advance of any cognitive impairments. These findings suggest that visuomotor impairments are associated with early dementia-related brain changes. The current study examined the underlying resting state functional connectivity (RSFC) associated with impaired non-standard visuomotor performance, as well as the impacts of dementia family history, sex, and APOE status.

Methods

Cognitively healthy older adults (n = 48) were tested on four visuomotor tasks where reach and gaze were increasingly spatially dissociated. Participants who had a family history of dementia or the APOE ε4 allele were considered to be at an increased risk for AD. To quantify RSFC within networks of interest, an EPI sequence sensitive to BOLD contrast was collected. The networks of interest were the default mode network (DMN), somatomotor network (SMN), dorsal attention network (DAN), ventral attention network (VAN), and frontoparietal control network (FPN).

Results

Individuals with the ε4 allele showed abnormalities in RSFC between posterior DMN nodes that predicted poorer non-standard visuomotor performance. Specifically, multiple linear regression analyses revealed lower RSFC between the precuneus/posterior cingulate cortex and the left inferior parietal lobule as well as the left parahippocampal cortex. Presence of the APOE ε4 allele also modified the relationship between mean DAN RSFC and visuomotor control, where lower mean RSFC in the DAN predicted worse non-standard visuomotor performance only in APOE ε4 carriers. There were otherwise no effects of family history, APOE ε4 status, or sex on the relationship between RSFC and visuomotor performance for any of the other resting networks.

Conclusion

The preliminary findings provide insight into the impact of APOE ε4-related genetic risk on neural networks underlying complex visuomotor transformations, and demonstrate that the non-standard visuomotor task paradigm discussed in this study may be used as a non-invasive, easily accessible assessment tool for dementia risk.

Linking the Amyloid, Tau, and Mitochondrial Hypotheses of Alzheimer's Disease and Identifying Promising Drug Targets

Damage or loss of brain cells and impaired neurochemistry, neurogenesis, and synaptic and nonsynaptic plasticity of the brain lead to dementia in neurodegenerative diseases, such as Alzheimer's disease (AD). Injury to synapses and neurons and accumulation of extracellular amyloid plaques and intracellular neurofibrillary tangles are considered the main morphological and neuropathological features of AD. Age, genetic and epigenetic factors, environmental stressors, and lifestyle contribute to the risk of AD onset and progression. These risk factors are associated with structural and functional changes in the brain, leading to cognitive decline. Biomarkers of AD reflect or cause specific changes in brain function, especially changes in pathways associated with neurotransmission, neuroinflammation, bioenergetics, apoptosis, and oxidative and nitrosative stress. Even in the initial stages, AD is associated with Aβ neurotoxicity, mitochondrial dysfunction, and tau neurotoxicity. The integrative amyloid-tau-mitochondrial hypothesis assumes that the primary cause of AD is the neurotoxicity of Aβ oligomers and tau oligomers, mitochondrial dysfunction, and their mutual synergy. For the development of new efficient AD drugs, targeting the elimination of neurotoxicity, mutual potentiation of effects, and unwanted protein interactions of risk factors and biomarkers (mainly Aβ oligomers, tau oligomers, and mitochondrial dysfunction) in the early stage of the disease seems promising.

Omics-based biomarkers discovery for Alzheimer's disease

Alzheimer's disease (AD) is the most common neurodegenerative disorders presenting with the pathological hallmarks of amyloid plaques and tau tangles. Over the past few years, great efforts have been made to explore reliable biomarkers of AD. High-throughput omics are a technology driven by multiple levels of unbiased data to detect the complex etiology of AD, and it provides us with new opportunities to better understand the pathophysiology of AD and thereby identify potential biomarkers. Through revealing the interaction networks between different molecular levels, the ultimate goal of multi-omics is to improve the diagnosis and treatment of AD. In this review, based on the current AD pathology and the current status of AD diagnostic biomarkers, we summarize how genomics, transcriptomics, proteomics and metabolomics are all conducing to the discovery of reliable AD biomarkers that could be developed and used in clinical AD management.

Unravelling the relationship between amyloid accumulation and brain network function in normal aging and very mild cognitive decline: a longitudinal analysis

Pathological changes in the brain begin accumulating decades before the appearance of cognitive symptoms in Alzheimer's disease. The deposition of amyloid beta proteins and other neurotoxic changes occur, leading to disruption in functional connections between brain networks. Discrete characterization of the changes that take place in preclinical Alzheimer's disease has the potential to help treatment development by targeting the neuropathological mechanisms to prevent cognitive decline and dementia from occurring entirely. Previous research has focused on the cross-sectional differences in the brains of patients with mild cognitive impairment or Alzheimer's disease and healthy controls or has concentrated on the stages immediately preceding cognitive symptoms. The present study emphasizes the early preclinical phases of neurodegeneration. We use a longitudinal approach to examine the brain changes that take place during the early stages of cognitive decline in the Open Access Series of Imaging Studies-3 data set. Among 1098 participants, 274 passed the inclusion criteria (i.e. had at least two cognitive assessments and two amyloid scans). Over 90% of participants were healthy at baseline. Over 8-10 years, some participants progressed to very mild cognitive impairment (n = 48), while others stayed healthy (n = 226). Participants with cognitive decline show faster amyloid accumulation in the lateral temporal, motor and parts of the lateral prefrontal cortex. These changes in amyloid levels were linked to longitudinal increases in the functional connectivity of select networks, including default mode, frontoparietal and motor components. Our findings advance the understanding of amyloid staging and the corresponding changes in functional organization of large-scale brain networks during the progression of early preclinical Alzheimer's disease.

Science disconnected: the translational gap between basic science, clinical trials, and patient care in Alzheimer's disease

Both research and clinical practice have traditionally centred on the dementia syndrome of Alzheimer's disease rather than its preclinical and prodromal stages. However, there is a strong scientific and ethical impetus to shift focus to earlier disease stages to improve brain health outcomes and help to keep affected individuals symptom-free (dementia-free) for as long as possible. We provide an overview of recent advancements in early detection, drug development, and trial methodology that should be utilised in the development of new therapies for use in brain health clinics. We propose a triad approach to Alzheimer's disease clinical trials, encompassing (1) experimental medicine studies to gather greater knowledge of disease mechanisms, (2) a more comprehensive platform of phase 2 learning trials to inform phase 3 confirmatory trials, and (3) precision medicine involving smaller subgroups of patients with shared characteristics. This triad would ensure that treatment targets are identified accurately, trial methodology focuses on at-risk populations, and sensitive outcome measures capture potential treatment effects. Clinical services around the world must embrace the brain health clinic model so that neurodegenerative diseases can be detected in their earliest phase to quicken drug development pipelines and potentially improve prognosis.

Brain state transition analysis using ultra-fast fMRI differentiates MCI from cognitively normal controls

Purpose

Conventional resting-state fMRI studies indicate that many cortical and subcortical regions have altered function in Alzheimer's disease (AD) but the nature of this alteration has remained unclear. Ultrafast fMRIs with sub-second acquisition times have the potential to improve signal contrast and enable advanced analyses to understand temporal interactions between brain regions as opposed to spatial interactions. In this work, we leverage such fast fMRI acquisitions from Alzheimer's disease Neuroimaging Initiative to understand temporal differences in the interactions between resting-state networks in 55 older adults with mild cognitive impairment (MCI) and 50 cognitively normal healthy controls.

Methods

We used a sliding window approach followed by k-means clustering. At each window, we computed connectivity i.e., correlations within and across the regions of the default mode, salience, dorsal attention, and frontoparietal network. Visual and somatosensory networks were excluded due to their lack of association with AD. Using the Davies-Bouldin index, we identified clusters of windows with distinct connectivity patterns, also referred to as brain states. The fMRI time courses were converted into time courses depicting brain state transition. From these state time course, we calculated the dwell time for each state i.e., how long a participant spent in each state. We determined how likely a participant transitioned between brain states. Both metrics were compared between MCI participants and controls using a false discovery rate correction of multiple comparisons at a threshold of. 0.05.

Results

We identified 8 distinct brain states representing connectivity within and between the resting state networks. We identified three transitions that were different between controls and MCI, all involving transitions in connectivity between frontoparietal, dorsal attention, and default mode networks (p<0.04).

Conclusion

We show that ultra-fast fMRI paired with dynamic functional connectivity analysis allows us to capture temporal transitions between brain states. Most changes were associated with transitions between the frontoparietal and dorsal attention networks connectivity and their interaction with the default mode network. Although future work needs to validate these findings, the brain networks identified in our work are known to interact with each other and play an important role in cognitive function and memory impairment in AD.

Interaction between Alzheimer's Disease and Cerebral Small Vessel Disease: A Review Focused on Neuroimaging Markers

Alzheimer's disease (AD) is characterized by the presence of β-amyloid (Aβ) and tau, and subcortical vascular cognitive impairment (SVCI) is characterized by cerebral small vessel disease (CSVD). They are the most common causes of cognitive impairment in the elderly population. Concurrent CSVD burden is more commonly observed in AD-type dementia than in other neurodegenerative diseases. Recent developments in Aβ and tau positron emission tomography (PET) have enabled the investigation of the relationship between AD biomarkers and CSVD in vivo. In this review, we focus on the interaction between AD and CSVD markers and the clinical effects of these two markers based on molecular imaging studies. First, we cover the frequency of AD imaging markers, including Aβ and tau, in patients with SVCI. Second, we discuss the relationship between AD and CSVD markers and the potential distinct pathobiology of AD markers in SVCI compared to AD-type dementia. Next, we discuss the clinical effects of AD and CSVD markers in SVCI, and hemorrhagic markers in cerebral amyloid angiopathy. Finally, this review provides both the current challenges and future perspectives for SVCI.

Layer-specific microstructural patterns of anterior hippocampus in Alzheimer's disease with ex vivo diffusion MRI at 14.1 T

High-resolution ex vivo diffusion MRI (dMRI) can provide exquisite mesoscopic details and microstructural information of the human brain. Microstructural pattern of the anterior part of human hippocampus, however, has not been well elucidated with ex vivo dMRI, either in normal or disease conditions. The present study collected high-resolution (0.1 mm isotropic) dMRI of post-mortem anterior hippocampal tissues from four Alzheimer's diseases (AD), three primary age-related tauopathy (PART), and three healthy control (HC) brains on a 14.1 T spectrometer. We evaluated how AD affected dMRI-based microstructural features in different layers and subfields of anterior hippocampus. In the HC samples, we found higher anisotropy, lower diffusivity, and more streamlines in the layers within cornu ammonis (CA) than those within dentate gyrus (DG). Comparisons between disease groups showed that (1) anisotropy measurements in the CA layers of AD, especially stratum lacunosum (SL) and stratum radiatum (SR), had higher regional variability than the other two groups; (2) streamline density in the DG layers showed a gradually increased variance from HC to PART to AD; (3) AD also showed the higher variability in terms of inter-layer connectivity than HC or PART. Moreover, voxelwise correlation analysis between the coregistered dMRI and histopathology images revealed significant correlations between dMRI measurements and the contents of amyloid beta (Aβ)/tau protein in specific layers of AD samples. These findings may reflect layer-specific microstructural characteristics in different hippocampal subfields at the mesoscopic resolution, which were associated with protein deposition in the anterior hippocampus of AD patients.

Tensorizing GAN With High-Order Pooling for Alzheimer's Disease Assessment

It is of great significance to apply deep learning for the early diagnosis of Alzheimer's disease (AD). In this work, a novel tensorizing GAN with high-order pooling is proposed to assess mild cognitive impairment (MCI) and AD. By tensorizing a three-player cooperative game-based framework, the proposed model can benefit from the structural information of the brain. By incorporating the high-order pooling scheme into the classifier, the proposed model can make full use of the second-order statistics of holistic magnetic resonance imaging (MRI). To the best of our knowledge, the proposed Tensor-train, High-order pooling and Semisupervised learning-based GAN (THS-GAN) is the first work to deal with classification on MR images for AD diagnosis. Extensive experimental results on Alzheimer's disease neuroimaging initiative (ADNI) data set are reported to demonstrate that the proposed THS-GAN achieves superior performance compared with existing methods, and to show that both tensor-train and high-order pooling can enhance classification performance. The visualization of generated samples also shows that the proposed model can generate plausible samples for semisupervised learning purpose.