The Alzheimer's Disease Neuroimaging Initiative: a review of papers published since its inception

Cerebrospinal fluid levels of tumour necrosis factor-α and its receptors are not associated with disease progression in Alzheimer's disease

Introduction

Tumour necrosis factor-α (TNF-α) is a proinflammatory cytokine implicated in the regulation of innate and adaptive immunity. Two receptors exist for TNF-α: TNF receptors 1 (TNFR-1) and 2 (TNFR-2). TNFR-1 and TNFR-2 have been reported to be involved in pleiotropic functions. Multiple lines of evidence implicate TNF-α and its receptors as potential risk factors for Alzheimer's disease (AD). Studies are warranted to assess the association of TNF-α, TNFR-1, and TNFR-2 with AD pathogenesis and whether they can serve as prognostic biomarkers indicative of AD.

Methods

In the present study, baseline levels of cerebrospinal fluid (CSF) TNF-α, TNFR-1, and TNFR-2 were explored, and their potential as biomarkers to differentiate between individuals who remain stable and those who experience disease progression over 10 years in the Alzheimer's Disease Neuroimaging Initiative (ADNI) was assessed. The study also examined the correlation between baseline CSF proteins with established AD biomarkers, neuroimaging measures, and cognition.

Results

Whilst the present study shows associations between baseline CSF levels of TNFs with AD biomarkers, the nature of the relationship is ambiguous.

Discussion

The present study concludes that CSF TNFs do not serve as reliable or robust disease biomarkers of AD.

Understanding the complex interplay between tau, amyloid and the network in the spatiotemporal progression of Alzheimer's disease

INTRODUCTION

The interaction of amyloid and tau in neurodegenerative diseases is a central feature of AD pathophysiology. While experimental studies point to various interaction mechanisms, their causal direction and mode (local, remote or network-mediated) remain unknown in human subjects. The aim of this study was to compare mathematical reaction-diffusion models encoding distinct cross-species couplings to identify which interactions were key to model success.

METHODS

We tested competing mathematical models of network spread, aggregation, and amyloid-tau interactions on publicly available data from ADNI.

RESULTS

Although network spread models captured the spatiotemporal evolution of tau and amyloid in human subjects, the model including a one-way amyloid-to-tau aggregation interaction performed best.

DISCUSSION

This mathematical exposition of the "pas de deux" of co-evolving proteins provides quantitative, whole-brain support to the concept of amyloid-facilitated-tauopathy rather than the classic amyloid-cascade or pure-tau hypotheses, and helps explain certain known but poorly understood aspects of AD.

Drug repurposing for Alzheimer's disease and other neurodegenerative disorders

Repurposed drugs provide a rich source of potential therapies for Alzheimer's disease (AD) and other neurodegenerative disorders (NDD). Repurposed drugs have information from non-clinical studies, phase 1 dosing, and safety and tolerability data collected with the original indication. Computational approaches, "omic" studies, drug databases, and electronic medical records help identify candidate therapies. Generic repurposed agents lack intellectual property protection and are rarely advanced to late-stage trials for AD/NDD. In this review we define repurposing, describe the advantages and challenges of repurposing, offer strategies for overcoming the obstacles, and describe the key contributions of repurposing to the drug development ecosystem.

Prediction of cognitive conversion within the Alzheimer's disease continuum using deep learning

BACKGROUND

Early diagnosis and accurate prognosis of cognitive decline in Alzheimer's disease (AD) is important to timely assignment to optimal treatment modes. We aimed to develop a deep learning model to predict cognitive conversion to guide re-assignment decisions to more intensive therapies where needed.

METHODS

Longitudinal data including five variable sets, i.e. demographics, medical history, neuropsychological outcomes, laboratory and neuroimaging results, from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort were analyzed. We first developed a deep learning model to predicted cognitive conversion using all five variable sets. We then gradually removed variable sets to obtained parsimonious models for four different years of forecasting after baseline within acceptable frames of reduction in overall model fit (AUC remaining > 0.8).

RESULTS

A total of 607 individuals were included at baseline, of whom 538 participants were followed up at 12 months, 482 at 24 months, 268 at 36 months and 280 at 48 months. Predictive performance was excellent with AUCs ranging from 0.87 to 0.92 when all variable sets were considered. Parsimonious prediction models that still had a good performance with AUC 0.80-0.84 were established, each only including two variable sets. Neuropsychological outcomes were included in all parsimonious models. In addition, biomarker was included at year 1 and year 2, imaging data at year 3 and demographics at year 4. Under our pre-set threshold, the rate of upgrade to more intensive therapies according to predicted cognitive conversion was always higher than according to actual cognitive conversion so as to decrease the false positive rate, indicating the proportion of patients who would have missed upgraded treatment based on prognostic models although they actually needed it.

CONCLUSIONS

Neurophysiological tests combined with other indicator sets that vary along the AD continuum can improve can provide aid for clinical treatment decisions leading to improved management of the disease.

TRAIL REGISTRATION INFORMATION

ClinicalTrials.gov Identifier: NCT00106899 (Registration Date: 31 March 2005).

Enhanced Multimodal Low-Rank Embedding-Based Feature Selection Model for Multimodal Alzheimer's Disease Diagnosis

Identification of Alzheimer's disease (AD) with multimodal neuroimaging data has been receiving increasing attention. However, the presence of numerous redundant features and corrupted neuroimages within multimodal datasets poses significant challenges for existing methods. In this paper, we propose a feature selection method named Enhanced Multimodal Low-rank Embedding (EMLE) for multimodal AD diagnosis. Unlike previous methods utilizing convex relaxations of the -norm, EMLE exploits an -norm regularized projection matrix to obtain an embedding representation and select informative features jointly for each modality. The -norm, employing an upper-bounded nonconvex Minimax Concave Penalty (MCP) function to characterize sparsity, offers a superior approximation for the -norm compared to other convex relaxations. Next, a similarity graph is learned based on the self-expressiveness property to increase the robustness to corrupted data. As the approximation coefficient vectors of samples from the same class should be highly correlated, an MCP function introduced norm, i.e., matrix -norm, is applied to constrain the rank of the graph. Furthermore, recognizing that diverse modalities should share an underlying structure related to AD, we establish a consensus graph for all modalities to unveil intrinsic structures across multiple modalities. Finally, we fuse the embedding representations of all modalities into the label space to incorporate supervisory information. The results of extensive experiments on the Alzheimer's Disease Neuroimaging Initiative datasets verify the discriminability of the features selected by EMLE.

ADNI Biomarker Core: A review of progress since 2004 and future challenges

BACKGROUND

We describe the Alzheimer's Disease Neuroimaging Initiative (ADNI) Biomarker Core major activities from October 2004 to March 2024, including biobanking ADNI cerebrospinal fluid (CSF), plasma, and serum biofluid samples, biofluid analyses for Alzheimer's disease (AD) biomarkers in the Biomarker Core and various non-ADNI laboratories, and continuous assessments of pre-analytics.

RESULTS

Validated immunoassay and mass spectrometry-based assays were performed in CSF with a shift to plasma, a more accessible biofluid, as qualified assays became available. Performance comparisons across different CSF and plasma AD biomarker measurement platforms have enriched substantially the ADNI participant database enabling method performance determinations for AD pathology detection and longitudinal assessments of disease progression.

DISCUSSION

Close collaboration with academic and industrial partners in the validation and implementation of AD biomarkers for early detection of disease pathology in treatment trials and ultimately in clinical practice is a key factor for the success of the work done in the Biomarker Core.

HIGHLIGHTS

Describe ADNI Biomarker Core biobanking and sample distribution from 2007 to 2024. Discuss validated mass spectrometry and immunoassay methods for ADNI biofluid analyses. Review collaborations with academic and industrial partners to detect AD and progression. Discuss major challenges, and progress to date, for co-pathology detection. Implementation in the ATN scheme: co-pathology and modeling disease progression.

Overview of Alzheimer's Disease Neuroimaging Initiative and future clinical trials

The overall goal of the Alzheimer's Disease Neuroimaging Initiative (ADNI) is to optimize and validate biomarkers for clinical trials while sharing all data and biofluid samples with the global scientific community. ADNI has been instrumental in standardizing and validating amyloid beta (Aβ) and tau positron emission tomography (PET) imaging. ADNI data were used for the US Food and Drug Administration (FDA) approval of the Fujirebio and Roche Elecsys cerebrospinal fluid diagnostic tests. Additionally, ADNI provided data for the trials of the FDA-approved treatments aducanumab, lecanemab, and donanemab. More than 6000 scientific papers have been published using ADNI data, reflecting ADNI's promotion of open science and data sharing. Despite its enormous success, ADNI has some limitations, particularly in generalizing its data and findings to the entire US/Canadian population. This introduction provides a historical overview of ADNI and highlights its significant accomplishments and future vision to pioneer "the clinical trial of the future" focusing on demographic inclusivity. HIGHLIGHTS: The Alzheimer's Disease Neuroimaging Initiative (ADNI) introduced a novel model for public-private partnerships and data sharing. It successfully validated amyloid and Tau PET imaging, as well as CSF and plasma biomarkers, for diagnosing Alzheimer's disease. ADNI generated and disseminated vital data for designing AD clinical trials.

Brain change trajectories in healthy adults correlate with Alzheimer's related genetic variation and memory decline across life

Throughout adulthood and ageing our brains undergo structural loss in an average pattern resembling faster atrophy in Alzheimer's disease (AD). Using a longitudinal adult lifespan sample (aged 30-89; 2-7 timepoints) and four polygenic scores for AD, we show that change in AD-sensitive brain features correlates with genetic AD-risk and memory decline in healthy adults. We first show genetic risk links with more brain loss than expected for age in early Braak regions, and find this extends beyond APOE genotype. Next, we run machine learning on AD-control data from the Alzheimer's Disease Neuroimaging Initiative using brain change trajectories conditioned on age, to identify AD-sensitive features and model their change in healthy adults. Genetic AD-risk linked with multivariate change across many AD-sensitive features, and we show most individuals over age ~50 are on an accelerated trajectory of brain loss in AD-sensitive regions. Finally, high genetic risk adults with elevated brain change showed more memory decline through adulthood, compared to high genetic risk adults with less brain change. Our findings suggest quantitative AD risk factors are detectable in healthy individuals, via a shared pattern of ageing- and AD-related neurodegeneration that occurs along a continuum and tracks memory decline through adulthood.

Multiclass classification of Alzheimer's disease prodromal stages using sequential feature embeddings and regularized multikernel support vector machine

The detection of patients in the cognitive normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD) stages of neurodegeneration is crucial for early treatment interventions. However, the heterogeneity of MCI data samples poses a challenge for CN vs. MCI vs. AD multiclass classification, as some samples are closer to AD while others are closer to CN in the feature space. Previous attempts to address this challenge produced inaccurate results, leading most frameworks to break the assessment into binary classification tasks such as AD vs. CN, AD vs. MCI, and CN vs. MCI. Other methods proposed sequential binary classifications such as CN vs. others and dividing others into AD vs. MCI. While those approaches may have yielded encouraging results, the sequential binary classification method makes interpretation and comparison with other frameworks challenging and subjective. Those frameworks exhibited varying accuracy scores for different binary tasks, making it unclear how to compare the model performance with other direct multiclass methods. Therefore, we introduce a classification framework comprising unsupervised ensemble manifold regularized sparse low-rank approximation and regularized multikernel support vector machine (SVM). This framework first extracts a joint feature embedding from MRI and PET neuroimaging features, which were then combined with the Apoe4, Adas11, MPACC digits, and Intracranial volume features using a regularized multikernel SVM. Using that framework, we achieved a state-of-the-art (SOTA) result in a CN vs. MCI vs. AD multiclass classification (mean accuracy: 84.87±6.09, F1 score: 84.83±6.12 vs 67.69). The methods generalize well to binary classification tasks, achieving SOTA results in all but the CN vs. MCI category, which was slightly lower than the best score by just 0.2%.

The ADNI Administrative Core: Ensuring ADNI's success and informing future AD clinical trials

The Alzheimer's Disease Neuroimaging Initiative (ADNI) Administrative Core oversees and coordinates all ADNI activities, to ensure the success and maximize the impact of ADNI in advancing Alzheimer's disease (AD) research and clinical trials. It manages finances and develops policies for data sharing, publications using ADNI data, and access to ADNI biospecimens. The Core develops and executes pilot projects to guide future ADNI activities and identifies key innovative methods for inclusion in ADNI. For ADNI4, the Administrative Core collaborates with the Engagement, Clinical, and Biomarker Cores to develop and evaluate novel, digital methods and infrastructure for participant recruitment, screening, and assessment of participants. The goal of these efforts is to enroll 500 participants, including > 50% from underrepresented populations, 40% with mild cognitive impairment, and 80% with elevated AD biomarkers. This new approach also provides a unique opportunity to validate novel methods. HIGHLIGHTS: The Alzheimer's Disease Neuroimaging Initiative (ADNI) Administrative Core oversees and coordinates all ADNI activities. The overall goal is to ensure ADNI's success and help design future Alzheimer's disease (AD) clinical trials. A key innovation is data sharing without embargo to maximize scientific impact. For ADNI4, novel, digital methods for recruitment and assessment were developed. New methods are designed to improve the participation of underrepresented populations.

The Alzheimer's Disease Neuroimaging Initiative Clinical Core

The Alzheimer's Disease Neuroimaging Initiative (ADNI) Clinical Core is responsible for coordination of all clinical activities at the ADNI sites, including project management, regulatory oversight, and site management and monitoring, as well as the collection of all clinical data and management of all study data. The Clinical Core is also charged with determining the clinical classifications and criteria for enrollment in evolving AD trials and enabling the ongoing characterization of the cross-sectional features and longitudinal trajectories of the ADNI cohorts with application of these findings to optimal clinical trial designs. More than 2400 individuals have been enrolled in the cohorts since the inception of ADNI, facilitating refinement of our understanding of the AD trajectory and allowing academic and industry investigators to model therapeutic trials across the disease spectrum from the presymptomatic stage through dementia. HIGHLIGHTS: Since 2004, the Alzheimer's Disease Neuroimaging Initiative (ADNI) Clinical Core has overseen the enrollment of > 2400 participants with mild cognitive impairment, mild Alzheimer's disease (AD) dementia, and normal cognition. The longitudinal dataset has elucidated the full cognitive and clinical trajectory of AD from its presymptomatic stage through the onset of dementia. The ADNI data have supported the design of most major trials in the field.

Understanding the complex interplay between tau, amyloid and the network in the spatiotemporal progression of Alzheimer's Disease

INTRODUCTION

The interaction of amyloid and tau in neurodegenerative diseases is a central feature of AD pathophysiology. While experimental studies point to various interaction mechanisms, their causal direction and mode (local, remote or network-mediated) remain unknown in human subjects. The aim of this study was to compare mathematical reaction-diffusion models encoding distinct cross-species couplings to identify which interactions were key to model success.

METHODS

We tested competing mathematical models of network spread, aggregation, and amyloid-tau interactions on publicly available data from ADNI.

RESULTS

Although network spread models captured the spatiotemporal evolution of tau and amyloid in human subjects, the model including a one-way amyloid-to-tau aggregation interaction performed best.

DISCUSSION

This mathematical exposition of the "pas de deux" of co-evolving proteins provides quantitative, whole-brain support to the concept of amyloid-facilitated-tauopathy rather than the classic amyloid-cascade or pure-tau hypotheses, and helps explain certain known but poorly understood aspects of AD.

A new and unified method for regression analysis of interval-censored failure time data under semiparametric transformation models with missing covariates

This paper discusses regression analysis of interval-censored failure time data arising from semiparametric transformation models in the presence of missing covariates. Although some methods have been developed for the problem, they either apply only to limited situations or may have some computational issues. Corresponding to these, we propose a new and unified two-step inference procedure that can be easily implemented using the existing or standard software. The proposed method makes use of a set of working models to extract partial information from incomplete observations and yields a consistent estimator of regression parameters assuming missing at random. An extensive simulation study is conducted and indicates that it performs well in practical situations. Finally, we apply the proposed approach to an Alzheimer's Disease study that motivated this study.

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Atrophy of the cholinergic regions advances from early to late mild cognitive impairment

PURPOSE

We investigated the volumetric changes in the components of the cholinergic pathway for patients with early mild cognitive impairment (EMCI) and those with late mild cognitive impairment (LMCI). The effect of patients' apolipoprotein 4 (APOE-ε4) allele status on the structural changes were analyzed.

METHODS

Structural magnetic resonance imaging data were collected. Patients' demographic information, plasma data, and validated global cognitive composite scores were included. Relevant features were extracted for constructing machine learning models to differentiate between EMCI (n = 312) and LMCI (n = 541) and predict patients' neurocognitive function. The data were analyzed primarily through one-way analysis of variance and two-way analysis of covariance.

RESULTS

Considerable differences were observed in cholinergic structural changes between patients with EMCI and LMCI. Cholinergic atrophy was more prominent in the LMCI cohort than in the EMCI cohort (P < 0.05 family-wise error corrected). APOE-ε4 differentially affected cholinergic atrophy in the LMCI and EMCI cohorts. For LMCI cohort, APOE-ε4 carriers exhibited increased brain atrophy (left amygdala: P = 0.001; right amygdala: P = 0.006, and right Ch123, P = 0.032). EMCI and LCMI patients showed distinctive associations of gray matter volumes in cholinergic regions with executive (R2 = 0.063 and 0.030 for EMCI and LMCI, respectively) and language (R2 = 0.095 and 0.042 for EMCI and LMCI, respectively) function.

CONCLUSIONS

Our data confirmed significant cholinergic atrophy differences between early and late stages of mild cognitive impairment. The impact of the APOE-ε4 allele on cholinergic atrophy varied between the LMCI and EMCI groups.

A 3D Sparse Autoencoder for Fully Automated Quality Control of Affine Registrations in Big Data Brain MRI Studies

This paper presents a fully automated pipeline using a sparse convolutional autoencoder for quality control (QC) of affine registrations in large-scale T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) studies. Here, a customized 3D convolutional encoder-decoder (autoencoder) framework is proposed and the network is trained in a fully unsupervised manner. For cross-validating the proposed model, we used 1000 correctly aligned MRI images of the human connectome project young adult (HCP-YA) dataset. We proposed that the quality of the registration is proportional to the reconstruction error of the autoencoder. Further, to make this method applicable to unseen datasets, we have proposed dataset-specific optimal threshold calculation (using the reconstruction error) from ROC analysis that requires a subset of the correctly aligned and artificially generated misalignments specific to that dataset. The calculated optimum threshold is used for testing the quality of remaining affine registrations from the corresponding datasets. The proposed framework was tested on four unseen datasets from autism brain imaging data exchange (ABIDE I, 215 subjects), information eXtraction from images (IXI, 577 subjects), Open Access Series of Imaging Studies (OASIS4, 646 subjects), and "Food and Brain" study (77 subjects). The framework has achieved excellent performance for T1w and T2w affine registrations with an accuracy of 100% for HCP-YA. Further, we evaluated the generality of the model on four unseen datasets and obtained accuracies of 81.81% for ABIDE I (only T1w), 93.45% (T1w) and 81.75% (T2w) for OASIS4, and 92.59% for "Food and Brain" study (only T1w) and in the range 88-97% for IXI (for both T1w and T2w and stratified concerning scanner vendor and magnetic field strengths). Moreover, the real failures from "Food and Brain" and OASIS4 datasets were detected with sensitivities of 100% and 80% for T1w and T2w, respectively. In addition, AUCs of > 0.88 in all scenarios were obtained during threshold calculation on the four test sets.

Improving Regression Analysis with Imputation in a Longitudinal Study of Alzheimer's Disease

Background

Missing data is prevalent in the Alzheimer's Disease Neuroimaging Initiative (ADNI). It is common to deal with missingness by removing subjects with missing entries prior to statistical analysis; however, this can lead to significant efficiency loss and sometimes bias. It has yet to be demonstrated that the imputation approach to handling this issue can be valuable in some longitudinal regression settings.

Objective

The purpose of this study is to demonstrate the importance of imputation and how imputation is correctly done in ADNI by analyzing longitudinal Alzheimer's Disease Assessment Scale -Cognitive Subscale 13 (ADAS-Cog 13) scores and their association with baseline patient characteristics.

Methods

We studied 1,063 subjects in ADNI with mild cognitive impairment. Longitudinal ADAS-Cog 13 scores were modeled with a linear mixed-effects model with baseline clinical and demographic characteristics as predictors. The model estimates obtained without imputation were compared with those obtained after imputation with Multiple Imputation by Chained Equations (MICE). We justify application of MICE by investigating the missing data mechanism and model assumptions. We also assess robustness of the results to the choice of imputation method.

Results

The fixed-effects estimates of the linear mixed-effects model after imputation with MICE yield valid, tighter confidence intervals, thus improving the efficiency of the analysis when compared to the analysis done without imputation.

Conclusions

Our study demonstrates the importance of accounting for missing data in ADNI. When deciding to perform imputation, care should be taken in choosing the approach, as an invalid one can compromise the statistical analyses.

The Alzheimer's Disease Neuroimaging Initiative in the era of Alzheimer's disease treatment: A review of ADNI studies from 2021 to 2022

The Alzheimer's Disease Neuroimaging Initiative (ADNI) aims to improve Alzheimer's disease (AD) clinical trials. Since 2006, ADNI has shared clinical, neuroimaging, and cognitive data, and biofluid samples. We used conventional search methods to identify 1459 publications from 2021 to 2022 using ADNI data/samples and reviewed 291 impactful studies. This review details how ADNI studies improved disease progression understanding and clinical trial efficiency. Advances in subject selection, detection of treatment effects, harmonization, and modeling improved clinical trials and plasma biomarkers like phosphorylated tau showed promise for clinical use. Biomarkers of amyloid beta, tau, neurodegeneration, inflammation, and others were prognostic with individualized prediction algorithms available online. Studies supported the amyloid cascade, emphasized the importance of neuroinflammation, and detailed widespread heterogeneity in disease, linked to genetic and vascular risk, co-pathologies, sex, and resilience. Biological subtypes were consistently observed. Generalizability of ADNI results is limited by lack of cohort diversity, an issue ADNI-4 aims to address by enrolling a diverse cohort.

Positron Emission Tomography/Computed Tomography Imaging in Therapeutic Clinical Trials in Alzheimer's Disease: An Overview of the Current State of the Art of Research

The integration of positron emission tomography/computed tomography (PET/CT) has revolutionized the landscape of Alzheimer's disease (AD) research and therapeutic interventions. By combining structural and functional imaging, PET/CT provides a comprehensive understanding of disease pathology and response to treatment assessment. PET/CT, particularly with 2-deoxy-2-[fluorine-18]fluoro-D-glucose (18F-FDG), facilitates the visualization of glucose metabolism in the brain, enabling early diagnosis, staging, and monitoring of neurodegenerative disease progression. The advent of amyloid and tau PET imaging has further propelled the field forward, offering invaluable tools for tracking pathological hallmarks, assessing treatment response, and predicting clinical outcomes. While some therapeutic interventions targeting amyloid plaque load showed promising results with the reduction of cerebral amyloid accumulation over time, others failed to demonstrate a significant impact of anti-amyloid agents for reducing the amyloid plaques burden in AD brains. Tau PET imaging has conversely fueled the advent of disease-modifying therapeutic strategies in AD by supporting the assessment of neurofibrillary tangles of tau pathology deposition over time. Looking ahead, PET imaging holds immense promise for studying additional targets such as neuroinflammation, cholinergic deficit, and synaptic dysfunction. Advances in radiotracer development, dedicated brain PET/CT scanners, and Artificial Intelligence-powered software are poised to enhance the quality, sensitivity, and diagnostic power of molecular neuroimaging. Consequently, PET/CT remains at the forefront of AD research, offering unparalleled opportunities for unravelling the complexities of the disease and advancing therapeutic interventions, although it is not yet enough alone to allow patients' recruitment in therapeutic clinical trials.

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

UK Biobank is a large-scale epidemiological resource for investigating prospective correlations between various lifestyle, environmental, and genetic factors with health and disease progression. In addition to individual subject information obtained through surveys and physical examinations, a comprehensive neuroimaging battery consisting of multiple modalities provides imaging-derived phenotypes (IDPs) that can serve as biomarkers in neuroscience research. In this study, we augment the existing set of UK Biobank neuroimaging structural IDPs, obtained from well-established software libraries such as FSL and FreeSurfer, with related measurements acquired through the Advanced Normalization Tools Ecosystem. This includes previously established cortical and subcortical measurements defined, in part, based on the Desikan-Killiany-Tourville atlas. Also included are morphological measurements from two recent developments: medial temporal lobe parcellation of hippocampal and extra-hippocampal regions in addition to cerebellum parcellation and thickness based on the Schmahmann anatomical labeling. Through predictive modeling, we assess the clinical utility of these IDP measurements, individually and in combination, using commonly studied phenotypic correlates including age, fluid intelligence, numeric memory, and several other sociodemographic variables. The predictive accuracy of these IDP-based models, in terms of root-mean-squared-error or area-under-the-curve for continuous and categorical variables, respectively, provides comparative insights between software libraries as well as potential clinical interpretability. Results demonstrate varied performance between package-based IDP sets and their combination, emphasizing the need for careful consideration in their selection and utilization.

Volume atrophy in medial temporal cortex and verbal memory scores in American Indians: Data from the Strong Heart Study

INTRODUCTION

Distinguishing Alzheimer's disease (AD) patient subgroups may optimize positive clinical outcomes. Cortical atrophy is correlated with memory deficits, but these associations are understudied in American Indians.

METHODS

We collected imaging and cognition data in the Strong Heart Study (SHS), a cohort of 11 tribes across three regions. We processed 1.5T MRI using FreeSurfer and iterative principal component analysis. Linear mixed models estimated volumetric associations with diabetes.

RESULTS

Over mean 7 years follow-up (N = 818 age 65-89 years), overall volume loss was 0.5% per year. Significant losses associated with diabetes were especially strong in the right hemisphere. Annualized hippocampal, parahippocampal, entorhinal atrophy were worse for men, older age, diabetes, hypertension, stroke; and associated with both encoding and retrieval memory losses.

DISCUSSION

Our findings suggest that diabetes is an important risk factor in American Indians for cortical atrophy and memory loss. Future research should examine opportunities for primary prevention in this underserved population.

Diagnostic evaluation of pharmacokinetic features of functional markers

The dynamicity of functional (curve) markers from modern clinical studies offers deeper insights into complex disease physiology. A frequent clinical practice is to examine various 'pharmacokinetic features' of functional markers (definite integral, maximum value, time to maximum, etc.) that reflect important physiological underpinnings. For instance, the current diagnostic procedure for kidney obstruction is to examine several pharmacokinetic features of renogram curves characterizing renal function. Motivated by such clinical practices, we develop a statistical framework for evaluating diagnostic accuracy of pharmacokinetic features using area under the receiver operating characteristic curve (AUC). The major challenge is that functional markers are observed at discrete time points with measurement error. To address this challenge, we develop a two-stage non-parametric AUC estimator based on summary functionals providing unified representation of various pharmacokinetic features and study its asymptotic properties. We also propose a sensible adaptation of a semiparametric regression model that can describe heterogeneity of AUC across different subpopulations, while appropriately handling discreteness and noise in observed functional markers. Here, a novel data-driven approach that balances between bias and efficiency of the regression coefficient estimates is introduced. Finally, the framework is applied to rigorously evaluate pharmacokinetic features of renogram curves potentially useful for detecting kidney obstruction.

Connectome-based biophysics models of Alzheimer's disease diagnosis and prognosis

With the increasing prevalence of Alzheimer's disease (AD) among aging populations and the limited therapeutic options available to slow or reverse its progression, the need has never been greater for improved diagnostic tools for identifying patients in the preclinical and prodomal phases of AD. Biophysics models of the connectome-based spread of amyloid-beta (Aβ) and microtubule-associated protein tau (τ) have enjoyed recent success as tools for predicting the time course of AD-related pathological changes. However, given the complex etiology of AD, which involves not only connectome-based spread of protein pathology but also the interactions of many molecular and cellular players over multiple spatiotemporal scales, more robust, complete biophysics models are needed to better understand AD pathophysiology and ultimately provide accurate patient-specific diagnoses and prognoses. Here we discuss several areas of active research in AD whose insights can be used to enhance the mathematical modeling of AD pathology as well as recent attempts at developing improved connectome-based biophysics models. These efforts toward a comprehensive yet parsimonious mathematical description of AD hold great promise for improving both the diagnosis of patients at risk for AD and our mechanistic understanding of how AD progresses.

Genome-wide association study of brain biochemical phenotypes reveals distinct genetic architecture of Alzheimer's disease related proteins

BACKGROUND

Alzheimer's disease (AD) is neuropathologically characterized by amyloid-beta (Aβ) plaques and neurofibrillary tangles. The main protein components of these hallmarks include Aβ40, Aβ42, tau, phosphor-tau, and APOE. We hypothesize that genetic variants influence the levels and solubility of these AD-related proteins in the brain; identifying these may provide key insights into disease pathogenesis.

METHODS

Genome-wide genotypes were collected from 441 AD cases, imputed to the haplotype reference consortium (HRC) panel, and filtered for quality and frequency. Temporal cortex levels of five AD-related proteins from three fractions, buffer-soluble (TBS), detergent-soluble (Triton-X = TX), and insoluble (Formic acid = FA), were available for these same individuals. Variants were tested for association with each quantitative biochemical measure using linear regression, and GSA-SNP2 was used to identify enriched Gene Ontology (GO) terms. Implicated variants and genes were further assessed for association with other relevant variables.

RESULTS

We identified genome-wide significant associations at seven novel loci and the APOE locus. Genes and variants at these loci also associate with multiple AD-related measures, regulate gene expression, have cell-type specific enrichment, and roles in brain health and other neuropsychiatric diseases. Pathway analysis identified significant enrichment of shared and distinct biological pathways.

CONCLUSIONS

Although all biochemical measures tested reflect proteins core to AD pathology, our results strongly suggest that each have unique genetic architecture and biological pathways that influence their specific biochemical states in the brain. Our novel approach of deep brain biochemical endophenotype GWAS has implications for pathophysiology of proteostasis in AD that can guide therapeutic discovery efforts focused on these proteins.

Detecting Dementia by Saliva Analysis: A Fingerprinting Unobtrusive Method Based on a Fast and Cheap Sensor System

BACKGROUND

Recent studies have shown that oxidative stress plays a relevant role in Alzheimer's disease (AD), and in the pathogenesis of vascular dementia (VaD). New diagnostic methods look for biological samples with non-invasive sampling methods. Among these, saliva shows an increase in oxidative stress products, thus a corresponding reduction in antioxidant products were found in dementia cases compared to healthy controls. Compounds identified in saliva include some hydrocarbons whose production has been related to the presence of reactive oxygen species.

OBJECTIVE

The hypothesis is that the voltammetric analysis performed on saliva could be a useful test for diagnosing dementia, potentially discriminating between AD and VaD.

METHODS

A single-center observational study was conducted on patients referred to the dementia clinic in the Neurology area and healthy controls recruited in the Orthopedics area of the Campus Bio-Medico Hospital in Rome. The study was aimed at evaluating the discriminative properties of salivary voltammetric analysis between healthy subjects and patients with dementia and, as a secondary outcome, between AD and VaD. A total of 69 subjects were enrolled, including 29 healthy controls, 20 patients with AD, and 20 patients with VaD. The degree of cognitive impairment was classified on the basis of the Mini-Mental State Examination score.

RESULTS

The results obtained are promising, with an accuracy of 79.7%, a sensitivity of 82.5%, and a specificity of 75.8%, in the discrimination of dementia versus controls.

CONCLUSIONS

The methods tested demonstrate to be relevant in the discrimination between dementia and controls. A confirmatory study is already running.

Neuroimaging Genetics and Network Analysis in Alzheimer's Disease

The issue of the genetics in brain imaging phenotypes serves as a crucial link between two distinct scientific fields: neuroimaging genetics (NG). The articles included here provide solid proof that this NG link has considerable synergy. There is a suitable collection of articles that offer a wide range of viewpoints on how genetic variations affect brain structure and function. They serve as illustrations of several study approaches used in contemporary genetics and neuroscience. Genome-wide association studies and candidate-gene association are two examples of genetic techniques. Cortical gray matter structural/volumetric measures from magnetic resonance imaging (MRI) are sources of information on brain phenotypes. Together, they show how various scientific disciplines have benefited from significant technological advances, such as the single-nucleotide polymorphism array in genetics and the development of increasingly higher-resolution MRI imaging. Moreover, we discuss NG's contribution to expanding our knowledge about the heterogeneity within Alzheimer's disease as well as the benefits of different network analyses.

Increasing participant diversity in AD research: Plans for digital screening, blood testing, and a community-engaged approach in the Alzheimer's Disease Neuroimaging Initiative 4

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) aims to validate biomarkers for Alzheimer's disease (AD) clinical trials. To improve generalizability, ADNI4 aims to enroll 50-60% of its new participants from underrepresented populations (URPs) using new biofluid and digital technologies. ADNI4 has received funding from the National Institute on Aging beginning September 2022.

METHODS

ADNI4 will recruit URPs using community-engaged approaches. An online portal will screen 20,000 participants, 4000 of whom (50-60% URPs) will be tested for plasma biomarkers and APOE. From this, 500 new participants will undergo in-clinic assessment joining 500 ADNI3 rollover participants. Remaining participants (∼3500) will undergo longitudinal plasma and digital cognitive testing. ADNI4 will add MRI sequences and new PET tracers. Project 1 will optimize biomarkers in AD clinical trials.

RESULTS AND DISCUSSION

ADNI4 will improve generalizability of results, use remote digital and blood screening, and continue providing longitudinal clinical, biomarker, and autopsy data to investigators.

Advanced Diagnostic Technique for Alzheimer's Disease using MRI Top-Ranked Volume and Surface-based Features

Background

Alzheimer's disease (AD) is the most dominant type of dementia that has not been treated completely yet. Few Alzheimer's patients are correctly diagnosed on time. Therefore, diagnostic tools are needed for better and more efficient diagnoses.

Objective

This study aimed to develop an efficient automated method to differentiate Alzheimer's patients from normal elderly and present the essential features with accurate Alzheimer's diagnosis.

Material and Methods

In this analytical study, 154 Magnetic Resonance Imaging (MRI) scans were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, preprocessed, and normalized by the head size for extracting features (volume, cortical thickness, Sulci depth, and Gyrification Index Features (GIF). Relief-F algorithm, t-test, and one way-ANOVA were used for feature ranking to obtain the most effective features representing the AD for the classification process. Finally, in the classification step, four classifiers were used with 10 folds cross-validation as follows: Gaussian Support Vector Machine (GSVM), Linear Support Vector Machine (LSVM), Weighted K-Nearest Neighbors (W-KNN), and Decision Tree algorithm.

Results

The LSVM classifier and W-KNN produce a testing accuracy of 100% with only seven features. Additionally, GSVM and decision tree produce a testing accuracy of 97.83% and 93.48%, respectively.

Conclusion

The proposed system represents an automatic and highly accurate AD detection with a few reliable and effective features and minimum time.

Heart fatty acid-binding protein is associated with phosphorylated tau and longitudinal cognitive changes

Background

Perturbation of lipid metabolism is associated with Alzheimer’s disease (AD). Heart fatty acid-binding protein (HFABP) is an adipokine playing an important role in lipid metabolism regulation.

Materials and methods

Two datasets separately enrolled 303 and 197 participants. First, we examine the associations of cerebrospinal fluid (CSF) HFABP levels with cognitive measures [including Mini-Mental State Examination (MMSE), Clinical Dementia Rating sum of boxes (CDRSB), and the cognitive section of Alzheimer’s Disease Assessment Scale] and AD biomarkers (CSF amyloid beta and tau levels). Second, we examine the longitudinal associations of baseline CSF HFABP levels and the variability of HFABP with cognitive measures and AD biomarkers. Structural equation models explored the mediation effects of AD pathologies on cognition.

Results

We found a significant relationship between CSF HFABP level and P-tau (dataset 1: β = 2.04, p &lt; 0.001; dataset 2: β = 1.51, p &lt; 0.001). We found significant associations of CSF HFABP with longitudinal cognitive measures (dataset 1: ADAS13, β = 0.09, p = 0.008; CDRSB, β = 0.10, p = 0.003; MMSE, β = −0.15, p &lt; 0.001; dataset 2: ADAS13, β = 0.07, p = 0.004; CDRSB, β = 0.07, p = 0.005; MMSE, β = −0.09, p &lt; 0.001) in longitudinal analysis. The variability of HFABP was associated with CSF P-tau (dataset 2: β = 3.62, p = 0.003). Structural equation modeling indicated that tau pathology mediated the relationship between HFABP and cognition.

Conclusion

Our findings demonstrated that HFABP was significantly associated with longitudinal cognitive changes, which might be partially mediated by tau pathology.

Dementia Prevention Research Clinic: a longitudinal study investigating factors influencing the development of Alzheimer's disease in Aotearoa, New Zealand

Aotearoa New Zealand's population is ageing. Increasing life expectancy is accompanied by increases in prevalence of Alzheimer's Disease (AD) and ageing-related disorders. The multicentre Dementia Prevention Research Clinic longitudinal study aims to improve understanding of AD and dementia in Aotearoa, in order to develop interventions that delay or prevent progression to dementia. Comprising research clinics in Auckland, Christchurch and Dunedin, this multi-disciplinary study involves community participants who undergo biennial investigations informed by international protocols and best practice: clinical, neuropsychological, neuroimaging, lifestyle evaluations, APOE genotyping, blood collection and processing. A key research objective is to identify a 'biomarker signature' that predicts progression from mild cognitive impairment to AD. Candidate biomarkers include: blood proteins and microRNAs, genetic, neuroimaging and neuropsychological markers, health, cultural, lifestyle, sensory and psychosocial factors. We are examining a range of mechanisms underlying the progression of AD pathology (e.g. faulty blood-brain barrier, excess parenchymal iron, vascular dysregulation). This paper will outline key aspects of the Dementia Prevention Research Clinic's research, provide an overview of data collection, and a summary of 266 participants recruited to date. The national outreach of the clinics is a strength; the heart of the Dementia Prevention Research Clinics are its people.

Alzheimer's Disease Assessments Optimized for Diagnostic Accuracy and Administration Time

OBJECTIVE

Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the time taken to administer diagnostic assessment has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer's disease diagnosis.

METHODS

We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open-source dementia dataset. We use cost-sensitive feature selection to optimise our feature selection results for assessment time as well as diagnostic accuracy. To encourage clinical adoption and further evaluation of our proposed accuracy-vs-cost optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items.

RESULTS

We find that there are subsets of accuracy-cost optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments.

DISCUSSION

Overall, our analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments. Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.

Using the Alzheimer's Disease Neuroimaging Initiative to improve early detection, diagnosis, and treatment of Alzheimer's disease

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) has accumulated 15 years of clinical, neuroimaging, cognitive, biofluid biomarker and genetic data, and biofluid samples available to researchers, resulting in more than 3500 publications. This review covers studies from 2018 to 2020.

METHODS

We identified 1442 publications using ADNI data by conventional search methods and selected impactful studies for inclusion.

RESULTS

Disease progression studies supported pivotal roles for regional amyloid beta (Aβ) and tau deposition, and identified underlying genetic contributions to Alzheimer's disease (AD). Vascular disease, immune response, inflammation, resilience, and sex modulated disease course. Biologically coherent subgroups were identified at all clinical stages. Practical algorithms and methodological changes improved determination of Aβ status. Plasma Aβ, phosphorylated tau181, and neurofilament light were promising noninvasive biomarkers. Prognostic and diagnostic models were externally validated in ADNI but studies are limited by lack of ethnocultural cohort diversity.

DISCUSSION

ADNI has had a profound impact in improving clinical trials for AD.

BPGAN: Brain PET synthesis from MRI using generative adversarial network for multi-modal Alzheimer's disease diagnosis

BACKGROUND AND OBJECTIVE

Multi-modal medical images, such as magnetic resonance imaging (MRI) and positron emission tomography (PET), have been widely used for the diagnosis of brain disorder diseases like Alzheimer's disease (AD) since they can provide various information. PET scans can detect cellular changes in organs and tissues earlier than MRI. Unlike MRI, PET data is difficult to acquire due to cost, radiation, or other limitations. Moreover, PET data is missing for many subjects in the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. To solve this problem, a 3D end-to-end generative adversarial network (named BPGAN) is proposed to synthesize brain PET from MRI scans, which can be used as a potential data completion scheme for multi-modal medical image research.

METHODS

We propose BPGAN, which learns an end-to-end mapping function to transform the input MRI scans to their underlying PET scans. First, we design a 3D multiple convolution U-Net (MCU) generator architecture to improve the visual quality of synthetic results while preserving the diverse brain structures of different subjects. By further employing a 3D gradient profile (GP) loss and structural similarity index measure (SSIM) loss, the synthetic PET scans have higher-similarity to the ground truth. In this study, we explore alternative data partitioning ways to study their impact on the performance of the proposed method in different medical scenarios.

RESULTS

We conduct experiments on a publicly available ADNI database. The proposed BPGAN is evaluated by mean absolute error (MAE), peak-signal-to-noise-ratio (PSNR) and SSIM, superior to other compared models in these quantitative evaluation metrics. Qualitative evaluations also validate the effectiveness of our approach. Additionally, combined with MRI and our synthetic PET scans, the accuracies of multi-class AD diagnosis on dataset-A and dataset-B are 85.00% and 56.47%, which have been improved by about 1% and 1%, respectively, compared to the stand-alone MRI.

CONCLUSIONS

The experimental results of quantitative measures, qualitative displays, and classification evaluation demonstrate that the synthetic PET images by BPGAN are reasonable and high-quality, which provide complementary information to improve the performance of AD diagnosis. This work provides a valuable reference for multi-modal medical image analysis.

Novel Ultrasensitive Detection Technologies for the Identification of Early and Minimally Invasive Alzheimer's Disease Blood Biomarkers

BACKGROUND

Single molecule array (SIMOA) and other ultrasensitive detection technologies have allowed the determination of blood-based biomarkers of Alzheimer's disease (AD) for diagnosis and monitoring, thereby opening up a promising field of research.

OBJECTIVE

To review the published bibliography on plasma biomarkers in AD using new ultrasensitive techniques.

METHODS

A systematic review of the PubMed database was carried out to identify reports on the use of blood-based ultrasensitive technology to identify biomarkers for AD.

RESULTS

Based on this search, 86 works were included and classified according to the biomarker determined. First, plasma amyloid-β showed satisfactory accuracy as an AD biomarker in patients with a high risk of developing dementia. Second, plasma t-Tau displayed good sensitivity in detecting different neurodegenerative diseases. Third, plasma p-Tau was highly specific for AD. Fourth, plasma NfL was highly sensitive for distinguishing between patients with neurodegenerative diseases and healthy controls. In general, the simultaneous determination of several biomarkers facilitated greater accuracy in diagnosing AD (Aβ42/Aβ40, p-Tau181/217).

CONCLUSION

The recent development of ultrasensitive technology allows the determination of blood-based biomarkers with high sensitivity, thus facilitating the early detection of AD through the analysis of easily obtained biological samples. In short, as a result of this knowledge, pre-symptomatic and early AD diagnosis may be possible, and the recruitment process for future clinical trials could be more precise. However, further studies are necessary to standardize levels of blood-based biomarkers in the general population and thus achieve reproducible results among different laboratories.

Bridging gaps between images and data: a systematic update on imaging biobanks

BACKGROUND AND OBJECTIVE

The systematic collection of medical images combined with imaging biomarkers and patient non-imaging data is the core concept of imaging biobanks, a key element for fuelling the development of modern precision medicine. Our purpose is to review the existing image repositories fulfilling the criteria for imaging biobanks.

METHODS

Pubmed, Scopus and Web of Science were searched for articles published in English from January 2010 to July 2021 using a combination of the terms: "imaging" AND "biobanks" and "imaging" AND "repository". Moreover, the Community Research and Development Information Service (CORDIS) database ( https://cordis.europa.eu/projects ) was searched using the terms: "imaging" AND "biobanks", also including collections, projects, project deliverables, project publications and programmes.

RESULTS

Of 9272 articles retrieved, only 54 related to biobanks containing imaging data were finally selected, of which 33 were disease-oriented (61.1%) and 21 population-based (38.9%). Most imaging biobanks were European (26/54, 48.1%), followed by American biobanks (20/54, 37.0%). Among disease-oriented biobanks, the majority were focused on neurodegenerative (9/33, 27.3%) and oncological diseases (9/33, 27.3%). The number of patients enrolled ranged from 240 to 3,370,929, and the imaging modality most frequently involved was MRI (40/54, 74.1%), followed by CT (20/54, 37.0%), PET (13/54, 24.1%), and ultrasound (12/54, 22.2%). Most biobanks (38/54, 70.4%) were accessible under request.

CONCLUSIONS

Imaging biobanks can serve as a platform for collecting, sharing and analysing medical images integrated with imaging biomarkers, biological and clinical data. A relatively small proportion of current biobanks also contain images and can thus be classified as imaging biobanks.

KEY POINTS

• Imaging biobanks are a powerful tool for large-scale collection and processing of medical images integrated with imaging biomarkers and patient non-imaging data. • Most imaging biobanks retrieved were European, disease-oriented and accessible under user request. • While many biobanks have been developed so far, only a relatively small proportion of them are imaging biobanks.

Combined Structural MR and Diffusion Tensor Imaging Classify the Presence of Alzheimer's Disease With the Same Performance as MR Combined With Amyloid Positron Emission Tomography: A Data Integration Approach

Background: In recent years, classification frameworks using imaging data have shown that multimodal classification methods perform favorably over the use of a single imaging modality for the diagnosis of Alzheimer's Disease. The currently used clinical approach often emphasizes the use of qualitative MRI and/or PET data for clinical diagnosis. Based on the hypothesis that classification of isolated imaging modalities is not predictive of their respective value in combined approaches, we investigate whether the combination of T1 Weighted MRI and diffusion tensor imaging (DTI) can yield an equivalent performance as the combination of quantitative structural MRI (sMRI) with amyloid-PET. Methods: We parcellated the brain into regions of interest (ROI) following different anatomical labeling atlases. For each region of interest different metrics were extracted from the different imaging modalities (sMRI, PiB-PET, and DTI) to be used as features. Thereafter, the feature sets were reduced using an embedded-based feature selection method. The final reduced sets were then used as input in support vector machine (SVM) classifiers. Three different base classifiers were created, one for each imaging modality, and validated using internal (n = 41) and external data from the ADNI initiative (n = 330 for sMRI, n = 148 for DTI and n = 55 for PiB-PET) sources. Finally, the classifiers were ensembled using a weighted method in order to evaluate the performance of different combinations. Results: For the base classifiers the following performance levels were found: sMRI-based classifier (accuracy, 92%; specificity, 97% and sensitivity, 87%), PiB-PET (accuracy, 91%; specificity, 89%; and sensitivity, 92%) and the lowest performance was attained with DTI (accuracy, 80%; specificity, 76%; and sensitivity, 82%). From the multimodal approaches, when integrating two modalities, the following results were observed: sMRI+PiB-PET (accuracy, 98%; specificity, 98%; and sensitivity, 99%), sMRI+DTI (accuracy, 97%; specificity, 99%; and sensitivity, 94%) and PiB-PET+DTI (accuracy, 91%; specificity, 90%; and sensitivity, 93%). Finally, the combination of all imaging modalities yielded an accuracy of 98%, specificity of 97% and sensitivity of 99%. Conclusion: Although DTI in isolation shows relatively poor performance, when combined with structural MR, it showed a surprising classification performance which was comparable to MR combined with amyloid PET. These results are consistent with the notion that white matter changes are also important in Alzheimer's Disease.

Neuroanatomical associations of depression, anxiety and apathy neuropsychiatric symptoms in patients with Alzheimer's disease

Depression, anxiety and apathy are 'common neuropsychiatric symptoms (NPS) in Alzheimer's disease (AD). We aimed to find regional gray matter (GM) volume difference of these symptoms, in AD patients compared to AD control, and investigate possible associations of GM atrophy with cognitive covariant. Study subjects were retrieved from the Alzheimer's Disease Neuroimaging Initiative database. Thirty-five participants are AD control, 27 AD patients with anxiety, 19 with depression and 24 with apathy, ages ≥ 55.1 years. Recruited subjects had an assessment of their clinical and structural MRI data. GM differences and clinical data were analyzed using voxel-based morphometry and ANOVA with Scheffe post hoc test, respectively. We found significant GM volumes differences in the left insula, left parahippocampal, posterior cingulate and the bilateral putamen in the anxiety group. The results also revealed that the right parahippocampal, Brodmann area 38 and the middle frontal gyrus were significant in patients with depression. Significant results were with a p < 0.05, corrected with AlphaSim program for multiple comparisons. The left insula had a strong negative association with Clinical Dementia Rate Sum of Boxes and Alzheimer's Disease Assessment Scale-cognitive subscale-13 items in anxiety and apathy groups. The difference in GM density in the left insula and hippocampus plays a crucial role in depression, anxiety and apathy NPS and outline precise approaches to test these symptoms.

It Is Time to Study Overlapping Molecular and Circuit Pathophysiologies in Alzheimer's and Lewy Body Disease Spectra

Alzheimer's disease (AD) is the leading cause of dementia due to neurodegeneration and is characterized by extracellular senile plaques composed of amyloid β1 - 42 (Aβ) as well as intracellular neurofibrillary tangles consisting of phosphorylated tau (p-tau). Dementia with Lewy bodies constitutes a continuous spectrum with Parkinson's disease, collectively termed Lewy body disease (LBD). LBD is characterized by intracellular Lewy bodies containing α-synuclein (α-syn). The core clinical features of AD and LBD spectra are distinct, but the two spectra share common cognitive and behavioral symptoms. The accumulation of pathological proteins, which acquire pathogenicity through conformational changes, has long been investigated on a protein-by-protein basis. However, recent evidence suggests that interactions among these molecules may be critical to pathogenesis. For example, Aβ/tau promotes α-syn pathology, and α-syn modulates p-tau pathology. Furthermore, clinical evidence suggests that these interactions may explain the overlapping pathology between AD and LBD in molecular imaging and post-mortem studies. Additionally, a recent hypothesis points to a common mechanism of prion-like progression of these pathological proteins, via neural circuits, in both AD and LBD. This suggests a need for understanding connectomics and their alterations in AD and LBD from both pathological and functional perspectives. In AD, reduced connectivity in the default mode network is considered a hallmark of the disease. In LBD, previous studies have emphasized abnormalities in the basal ganglia and sensorimotor networks; however, these account for movement disorders only. Knowledge about network abnormalities common to AD and LBD is scarce because few previous neuroimaging studies investigated AD and LBD as a comprehensive cohort. In this paper, we review research on the distribution and interactions of pathological proteins in the brain in AD and LBD, after briefly summarizing their clinical and neuropsychological manifestations. We also describe the brain functional and connectivity changes following abnormal protein accumulation in AD and LBD. Finally, we argue for the necessity of neuroimaging studies that examine AD and LBD cases as a continuous spectrum especially from the proteinopathy and neurocircuitopathy viewpoints. The findings from such a unified AD and Parkinson's disease (PD) cohort study should provide a new comprehensive perspective and key data for guiding disease modification therapies targeting the pathological proteins in AD and LBD.

The Effect of the APOE-ε4 Allele on the Cholinergic Circuitry for Subjects With Different Levels of Cognitive Impairment

Background: Cholinergic deficiency has been suggested to associate with the abnormal accumulation of Aβ and tau for patients with Alzheimer's disease (AD). However, no studies have investigated the effect of APOE-ε4 and group differences in modulating the cholinergic basal forebrain-amygdala network for subjects with different levels of cognitive impairment. We evaluated the effect of APOE-ε4 on the cholinergic structural association and the neurocognitive performance for subjects with different levels of cognitive impairment. Methods: We used the structural brain magnetic resonance imaging scans from the Alzheimer's Disease Neuroimaging Initiative dataset. The study included cognitively normal (CN, n = 167) subjects and subjects with significant memory concern (SMC, n = 96), early mild cognitive impairment (EMCI, n = 146), late cognitive impairment (LMCI, n = 138), and AD (n = 121). Subjects were further categorized according to the APOE-ε4 allele carrier status. The main effects of APOE-ε4 and group difference on the brain volumetric measurements were assessed. Regression analyses were conducted to evaluate the associations among cholinergic structural changes, APOE-ε4 status, and cognitive performance. Results: We found that APOE-ε4 carriers in the disease group showed higher brain atrophy than non-carriers in the cholinergic pathway, while there is no difference between carriers and non-carriers in the CN group. APOE-ε4 allele carriers in the disease groups also exhibited a stronger cholinergic structural correlation than non-carriers did, while there is no difference between the carriers and non-carriers in the CN subjects. Disease subjects exhibited a stronger structural correlation in the cholinergic pathway than CN subjects did. Moreover, APOE-ε4 allele carriers in the disease group exhibited a stronger correlation between the volumetric changes and cognitive performance than non-carriers did, while there is no difference between carriers and non-carriers in CN subjects. Disease subjects exhibited a stronger correlation between the volumetric changes and cognitive performance than CN subjects did. Conclusion: Our results confirmed the effect of APOE-ε4 on and group differences in the associations with the cholinergic structural changes that may reflect impaired brain function underlying neurocognitive degeneration in AD.

Toward more robust and reproducible diffusion kurtosis imaging

PURPOSE

The general utility of diffusion kurtosis imaging (DKI) is challenged by its poor robustness to imaging artifacts and thermal noise that often lead to implausible kurtosis values.

THEORY AND METHODS

A robust scalar kurtosis index can be estimated from powder-averaged diffusion-weighted data. We introduce a novel DKI estimator that uses this scalar kurtosis index as a proxy for the mean kurtosis to regularize the fit.

RESULTS

The regularized DKI estimator improves the robustness and reproducibility of the kurtosis metrics and results in parameter maps with enhanced quality and contrast.

CONCLUSION

Our novel DKI estimator promotes the wider use of DKI in clinical research and potentially diagnostics by improving the reproducibility and precision of DKI fitting and, as such, enabling enhanced visual, quantitative, and statistical analyses of DKI parameters.

Multi-Resemblance Multi-Target Low-Rank Coding for Prediction of Cognitive Decline With Longitudinal Brain Images

An effective presymptomatic diagnosis and treatment of Alzheimer's disease (AD) would have enormous public health benefits. Sparse coding (SC) has shown strong potential for longitudinal brain image analysis in preclinical AD research. However, the traditional SC computation is time-consuming and does not explore the feature correlations that are consistent over the time. In addition, longitudinal brain image cohorts usually contain incomplete image data and clinical labels. To address these challenges, we propose a novel two-stage Multi-Resemblance Multi-Target Low-Rank Coding (MMLC) method, which encourages that sparse codes of neighboring longitudinal time points are resemblant to each other, favors sparse code low-rankness to reduce the computational cost and is resilient to both source and target data incompleteness. In stage one, we propose an online multi-resemblant low-rank SC method to utilize the common and task-specific dictionaries in different time points to immune to incomplete source data and capture the longitudinal correlation. In stage two, supported by a rigorous theoretical analysis, we develop a multi-target learning method to address the missing clinical label issue. To solve such a multi-task low-rank sparse optimization problem, we propose multi-task stochastic coordinate coding with a sequence of closed-form update steps which reduces the computational costs guaranteed by a theoretical convergence proof. We apply MMLC on a publicly available neuroimaging cohort to predict two clinical measures and compare it with six other methods. Our experimental results show our proposed method achieves superior results on both computational efficiency and predictive accuracy and has great potential to assist the AD prevention.

Affective symptoms and regional cerebral tau burden in early-stage Alzheimer's disease

OBJECTIVE

Neuropsychiatric symptoms (NPS) are often present in individuals with mild cognitive impairment (MCI) and Alzheimer's disease (AD) dementia. NPS are associated with structural and functional changes in the brain such as atrophy, regional hypometabolism, and hypoperfusion, considered proxies of neurodegeneration. Our objective was to evaluate the association between NPS and regional cerebral tau burden, a more direct representation of neurodegeneration, in cognitively normal (CN), MCI, and AD dementia individuals.

METHODS

Cross-sectional NPS were assessed using the Neuropsychiatric Inventory (NPI) in 410 CN, 199 MCI, and 61 AD dementia participants who underwent flortaucipir tau positron emission tomography as part of the AD Neuroimaging Initiative (ADNI). Total NPI score and two factors of NPS (affective and hyperactive) were used in analyses. Linear regression models with backward elimination were employed with NPI as dependent variable and regional tau or tau-amyloid interaction as predictor of interest. Covariates included education, age, sex, Rey Auditory Verbal Learning Test Total Learning, and Trail Making Test B.

RESULTS

There were significant associations (p < 0.05) between the NPI variables (total score, Affective factor) and entorhinal and precuneus tau across all participants. These associations were also significant for the tau-amyloid interaction. These effects were significant in cognitively symptomatic participants (MCI and AD dementia), but not in CN participants.

CONCLUSIONS

Increased tau burden in the entorhinal and precuneus cortices was modestly associated with greater NPS in MCI and AD dementia. Further evaluation of NPS and their effect on early-stage AD could aid in finding new interventions and slowing disease progression.

Bridging the Brain and Data Sciences

Brain scientists are now capable of collecting more data in a single experiment than researchers a generation ago might have collected over an entire career. Indeed, the brain itself seems to thirst for more and more data. Such digital information not only comprises individual studies but is also increasingly shared and made openly available for secondary, confirmatory, and/or combined analyses. Numerous web resources now exist containing data across spatiotemporal scales. Data processing workflow technologies running via cloud-enabled computing infrastructures allow for large-scale processing. Such a move toward greater openness is fundamentally changing how brain science results are communicated and linked to available raw data and processed results. Ethical, professional, and motivational issues challenge the whole-scale commitment to data-driven neuroscience. Nevertheless, fueled by government investments into primary brain data collection coupled with increased sharing and community pressure challenging the dominant publishing model, large-scale brain and data science is here to stay.

Early Detection of Alzheimer's Disease Based on Clinical Trials, Three-Dimensional Imaging Data, and Personal Information Using Autoencoders

Background:

A timely diagnosis of Alzheimer's disease (AD) is crucial to obtain more practical treatments. In this article, a novel approach using Auto-Encoder Neural Networks (AENN) for early detection of AD was proposed.

Method:

The proposed method mainly deals with the classification of multimodal data and the imputation of missing data. The data under study involve the MiniMental State Examination, magnetic resonance imaging, positron emission tomography, cerebrospinal fluid data, and personal information. Natural logarithm was used for normalizing the data. The Auto-Encoder Neural Networks was used for imputing missing data. Principal component analysis algorithm was used for reducing dimensionality of data. Support Vector Machine (SVM) was used as classifier. The proposed method was evaluated using Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Then, 10fold crossvalidation was used to audit the detection accuracy of the method.

Results:

The effectiveness of the proposed approach was studied under several scenarios considering 705 cases of ADNI database. In three binary classification problems, that is AD vs. normal controls (NCs), mild cognitive impairment (MCI) vs. NC, and MCI vs. AD, we obtained the accuracies of 95.57%, 83.01%, and 78.67%, respectively.

Conclusion:

Experimental results revealed that the proposed method significantly outperformed most of the stateoftheart methods.

A longitudinal observational population-based study of brain volume associated with changes in sleep timing from middle to late-life

STUDY OBJECTIVES

Sleep behaviors are related to brain structure and function, but the impact of long-term changes in sleep timing on brain health has not been clearly addressed. The purpose of this study was to examine the association of longitudinal changes in sleep timing from middle to late-life with gray matter volume (GMV), an important marker of brain aging.

METHODS

We enrolled 1798 adults (aged 49-82 years, men 54.6%) who underwent magnetic resonance imaging (MRI) between 2011 and 2014. Midsleep time (MST) on free days corrected for sleep debt on workdays was adopted as a marker of sleep timing. Data on MST were available at the time of MRI assessment and at examinations that were given 9 years earlier (2003-2004). Longitudinal changes in MST over the 9-year period were derived and categorized into quartiles. Subjects in quartile 1 were defined as "advancers" (MST advanced ≥ 1 h) while those in quartile 4 were defined as "delayers" (MST delayed ≥ 0.2 h). Quartiles 2-3 defined a reference group (MST change was considered modest). The relationship of GMV with MST changes over 9 years was investigated.

RESULTS

Nine-year change in MST were significantly associated with GMV. Compared to the reference group, advancers had smaller GMVs in the frontal and temporal regions. A delay in MST was also associated with smaller cerebellar GMV.

CONCLUSIONS

In middle-to-late adulthood, the direction of change in MST is associated with GMV. While advancers and delayers in MST tend to present lower GMV, associations appear to differ across brain regions.

Light-weight cross-view hierarchical fusion network for joint localization and identification in Alzheimer's disease with adaptive instance-declined pruning

Magnetic resonance imaging (MRI) has been widely used in assessing development of Alzheimer's disease (AD) by providing structural information of disease-associated regions (e.g. atrophic regions). In this paper, we propose a light-weight cross-view hierarchical fusion network (CvHF-net), consisting of local patch and global subject subnets, for joint localization and identification of the discriminative local patches and regions in the whole brain MRI, upon which feature representations are then jointly learned and fused to construct hierarchical classification models for AD diagnosis. Firstly, based on the extracted class-discriminative 3D patches, we employ the local patch subnets to utilize multiple 2D views to represent 3D patches by using an attention-aware hierarchical fusion structure in a divide-and-conquer manner. Since different local patches are with various abilities in AD identification, the global subject subnet is developed to bias the allocation of available resources towards the most informative parts among these local patches to obtain global information for AD identification. Besides, an instance declined pruning algorithm is embedded in the CvHF-net for adaptively selecting most discriminant patches in a task-driven manner. The proposed method was evaluated on the AD Neuroimaging Initiative dataset and the experimental results show that our proposed method can achieve good performance on AD diagnosis.

Cerebrospinal Fluid Biomarkers of Alzheimer's Disease: Current Evidence and Future Perspectives

Alzheimer's disease is a progressive, clinically heterogeneous, and particularly complex neurodegenerative disease characterized by a decline in cognition. Over the last two decades, there has been significant growth in the investigation of cerebrospinal fluid (CSF) biomarkers for Alzheimer's disease. This review presents current evidence from many clinical neurochemical studies, with findings that attest to the efficacy of existing core CSF biomarkers such as total tau, phosphorylated tau, and amyloid-β (Aβ42), which diagnose Alzheimer's disease in the early and dementia stages of the disorder. The heterogeneity of the pathophysiology of the late-onset disease warrants the growth of the Alzheimer's disease CSF biomarker toolbox; more biomarkers showing other aspects of the disease mechanism are needed. This review focuses on new biomarkers that track Alzheimer's disease pathology, such as those that assess neuronal injury (VILIP-1 and neurofilament light), neuroinflammation (sTREM2, YKL-40, osteopontin, GFAP, progranulin, and MCP-1), synaptic dysfunction (SNAP-25 and GAP-43), vascular dysregulation (hFABP), as well as CSF α-synuclein levels and TDP-43 pathology. Some of these biomarkers are promising candidates as they are specific and predict future rates of cognitive decline. Findings from the combinations of subclasses of new Alzheimer's disease biomarkers that improve their diagnostic efficacy in detecting associated pathological changes are also presented.

Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning

Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on pre-engineered features depriving DL of its main advantage — representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.

Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) for brain imaging data analysis. Here, the authors show that if trained following prevalent DL practices, DL methods substantially improve compared to SML methods by encoding robust discriminative brain representations.

Financial Capacity and Regional Cerebral Tau in Cognitively Normal Older Adults, Mild Cognitive Impairment, and Alzheimer's Disease Dementia

BACKGROUND

Financial capacity is often one of the first instrumental activities of daily living to be affected in cognitively normal (CN) older adults who later progress to amnestic mild cognitive impairment (MCI) and Alzheimer's disease (AD) dementia.

OBJECTIVE

The objective of this study was to investigate the association between financial capacity and regional cerebral tau.

METHODS

Cross-sectional financial capacity was assessed using the Financial Capacity Instrument -Short Form (FCI-SF) in 410 CN, 199 MCI, and 61 AD dementia participants who underwent flortaucipir tau positron emission tomography from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Linear regression models with backward elimination were used with FCI-SF total score as the dependent variable and regional tau and tau-amyloid interaction as predictors of interest in separate analyses. Education, age, sex, Rey Auditory Verbal Learning Test Total Learning, and Trail Making Test B were used as covariates.

RESULTS

Significant associations were found between FCI-SF and tau regions (entorhinal: p < 0.001; inferior temporal: p < 0.001; dorsolateral prefrontal: p = 0.01; posterior cingulate: p = 0.03; precuneus: p < 0.001; and supramarginal gyrus: p = 0.005) across all participants. For the tau-amyloid interaction, significant associations were found in four regions (amyloid and dorsolateral prefrontal tau interaction: p = 0.005; amyloid and posterior cingulate tau interaction: p = 0.005; amyloid and precuneus tau interaction: p < 0.001; and amyloid and supramarginal tau interaction: p = 0.002).

CONCLUSION

Greater regional tau burden was modestly associated with financial capacity impairment in early-stage AD. Extending this work with longitudinal analyses will further illustrate the utility of such assessments in detecting clinically meaningful decline, which may aid clinical trials of early-stage AD.