Combining MR imaging, positron-emission tomography, and CSF biomarkers in the diagnosis and prognosis of Alzheimer disease

3D Multimodal Fusion Network With Disease-Induced Joint Learning for Early Alzheimer's Disease Diagnosis

Multimodal neuroimaging provides complementary information critical for accurate early diagnosis of Alzheimer's disease (AD). However, the inherent variability between multimodal neuroimages hinders the effective fusion of multimodal features. Moreover, achieving reliable and interpretable diagnoses in the field of multimodal fusion remains challenging. To address them, we propose a novel multimodal diagnosis network based on multi-fusion and disease-induced learning (MDL-Net) to enhance early AD diagnosis by efficiently fusing multimodal data. Specifically, MDL-Net proposes a multi-fusion joint learning (MJL) module, which effectively fuses multimodal features and enhances the feature representation from global, local, and latent learning perspectives. MJL consists of three modules, global-aware learning (GAL), local-aware learning (LAL), and outer latent-space learning (LSL) modules. GAL via a self-adaptive Transformer (SAT) learns the global relationships among the modalities. LAL constructs local-aware convolution to learn the local associations. LSL module introduces latent information through outer product operation to further enhance feature representation. MDL-Net integrates the disease-induced region-aware learning (DRL) module via gradient weight to enhance interpretability, which iteratively learns weight matrices to identify AD-related brain regions. We conduct the extensive experiments on public datasets and the results confirm the superiority of our proposed method. Our code will be available at: https://github.com/qzf0320/MDL-Net.

AD plasma biomarkers are stable for an extended period at -20°C: implications for resource-constrained environments

Standard procedures for measuring Alzheimer's disease (AD) plasma biomarkers include storage at -80°C. This is challenging in countries lacking research infrastructure, such -80°C freezer. To investigate stability of AD biomarkers from plasma stored at -20°C, we compared aliquots stored at -80°C and others at -20°C for two, four, six, fifteen, and thirty-five weeks. pTau181, Aβ42, Aβ40, NfL, and GFAP were measured for each timepoint. pTau181 and Aβ42/Aβ40 ratios showed minimal variation for up to 15 weeks. NfL and GFAP had higher variability. This finding of 15-week stability at -20°C enables greater participation in AD biomarker studies in resource constrained environments.

Alteration of medial temporal lobe metabolism related to Alzheimer's disease and dementia with lewy bodies

BACKGROUND

Association of medial temporal lobe (MTL) metabolism with Alzheimer's disease (AD) and dementia with Lewy bodies (DLB) has not been evaluated considering their mixed disease (MD).

METHODS

131 patients with AD, 133 with DLB, 122 with MD, and 28 normal controls (NCs) underwent neuropsychological tests, assessments for parkinsonism, cognitive fluctuation (CF), and visual hallucinations (VH), and 18F-fluorodeoxyglucose PET to quantify MTL metabolism in the amygdala, hippocampus, and entorhinal cortex. The effects of AD and DLB on MTL metabolism were evaluated using general linear models (GLMs). Associations between MTL metabolism, cognition, and clinical features were evaluated using GLMs or logistic regression models separately performed for the AD spectrum (NC + AD + MD), DLB spectrum (NC + DLB + MD), and disease groups (AD + DLB + MD). Covariates included age, sex, and education.

RESULTS

AD was associated with hippocampal/entorhinal hypometabolism, whereas DLB was associated with relative amygdalar/hippocampal hypermetabolism. Relative MTL hypermetabolism was associated with lower attention/visuospatial/executive scores and severe parkinsonism in both the AD and DLB spectra and disease groups. Left hippocampal/entorhinal hypometabolism was associated with lower verbal memory scores, whereas right hippocampal hypometabolism was associated with lower visual memory scores in both the AD spectrum and disease groups. Relative MTL hypermetabolism was associated with an increased risk of CF and VH in the disease group, and relative amygdalar hypermetabolism was associated with an increased risk of VH in the DLB spectrum.

CONCLUSIONS

Entorhinal-hippocampal hypometabolism and relative amygdala-hippocampal hypermetabolism could be characteristics of AD- and DLB-related neurodegeneration, respectively.

Short-Term Practice Effects on Cognitive Tests Across the Late Life Cognitive Spectrum and How They Compare to Biomarkers of Alzheimer's Disease

Background

Practice effects on cognitive testing in mild cognitive impairment (MCI) and Alzheimer's disease (AD) remain understudied, especially with how they compare to biomarkers of AD.

Objective

The current study sought to add to this growing literature.

Methods

Cognitively intact older adults (n = 68), those with amnestic MCI (n = 52), and those with mild AD (n = 45) completed a brief battery of cognitive tests at baseline and again after one week, and they also completed a baseline amyloid PET scan, a baseline MRI, and a baseline blood draw to obtain APOE ɛ4 status.

Results

The intact participants showed significantly larger baseline cognitive scores and practice effects than the other two groups on overall composite measures. Those with MCI showed significantly larger baseline scores and practice effects than AD participants on the composite. For amyloid deposition, the intact participants had significantly less tracer uptake, whereas MCI and AD participants were comparable. For total hippocampal volumes, all three groups were significantly different in the expected direction (intact > MCI > AD). For APOE ɛ4, the intact had significantly fewer copies of ɛ4 than MCI and AD. The effect sizes of the baseline cognitive scores and practice effects were comparable, and they were significantly larger than effect sizes of biomarkers in 7 of the 9 comparisons.

Conclusion

Baseline cognition and short-term practice effects appear to be sensitive markers in late life cognitive disorders, as they separated groups better than commonly-used biomarkers in AD. Further development of baseline cognition and short-term practice effects as tools for clinical diagnosis, prognostic indication, and enrichment of clinical trials seems warranted.

Multi-modal cross-attention network for Alzheimer's disease diagnosis with multi-modality data

Alzheimer's disease (AD) is a neurodegenerative disorder, the most common cause of dementia, so the accurate diagnosis of AD and its prodromal stage mild cognitive impairment (MCI) is significant. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis. Many existing multi-modal models based on deep learning simply concatenate each modality's features despite substantial differences in representation spaces. In this paper, we propose a novel multi-modal cross-attention AD diagnosis (MCAD) framework to learn the interaction between modalities for better playing their complementary roles for AD diagnosis with multi-modal data including structural magnetic resonance imaging (sMRI), fluorodeoxyglucose-positron emission tomography (FDG-PET) and cerebrospinal fluid (CSF) biomarkers. Specifically, the imaging and non-imaging representations are learned by the image encoder based on cascaded dilated convolutions and CSF encoder, respectively. Then, a multi-modal interaction module is introduced, which takes advantage of cross-modal attention to integrate imaging and non-imaging information and reinforce relationships between these modalities. Moreover, an extensive objective function is designed to reduce the discrepancy between modalities for effectively fusing the features of multi-modal data, which could further improve the diagnosis performance. We evaluate the effectiveness of our proposed method on the ADNI dataset, and the extensive experiments demonstrate that our MCAD achieves superior performance for multiple AD-related classification tasks, compared to several competing methods. Also, we investigate the importance of cross-attention and the contribution of each modality to the diagnostics performance. The experimental results demonstrate that combining multi-modality data via cross-attention is helpful for accurate AD diagnosis.

Baseline structural MRI and plasma biomarkers predict longitudinal structural atrophy and cognitive decline in early Alzheimer's disease

BACKGROUND

Crucial to the success of clinical trials targeting early Alzheimer's disease (AD) is recruiting participants who are more likely to progress over the course of the trials. We hypothesize that a combination of plasma and structural MRI biomarkers, which are less costly and non-invasive, is predictive of longitudinal progression measured by atrophy and cognitive decline in early AD, providing a practical alternative to PET or cerebrospinal fluid biomarkers.

METHODS

Longitudinal T1-weighted MRI, cognitive (memory-related test scores and clinical dementia rating scale), and plasma measurements of 245 cognitively normal (CN) and 361 mild cognitive impairment (MCI) patients from ADNI were included. Subjects were further divided into β-amyloid positive/negative (Aβ+/Aβ-)] subgroups. Baseline plasma (p-tau181 and neurofilament light chain) and MRI-based structural medial temporal lobe subregional measurements and their association with longitudinal measures of atrophy and cognitive decline were tested using stepwise linear mixed effect modeling in CN and MCI, as well as separately in the Aβ+/Aβ- subgroups. Receiver operating characteristic (ROC) analyses were performed to investigate the discriminative power of each model in separating fast and slow progressors (first and last terciles) of each longitudinal measurement.

RESULTS

A total of 245 CN (35.0% Aβ+) and 361 MCI (53.2% Aβ+) participants were included. In the CN and MCI groups, both baseline plasma and structural MRI biomarkers were included in most models. These relationships were maintained when limited to the Aβ+ and Aβ- subgroups, including Aβ- CN (normal aging). ROC analyses demonstrated reliable discriminative power in identifying fast from slow progressors in MCI [area under the curve (AUC): 0.78-0.93] and more modestly in CN (0.65-0.73).

CONCLUSIONS

The present data support the notion that plasma and MRI biomarkers, which are relatively easy to obtain, provide a prediction for the rate of future cognitive and neurodegenerative progression that may be particularly useful in clinical trial stratification and prognosis. Additionally, the effect in Aβ- CN indicates the potential use of these biomarkers in predicting a normal age-related decline.

Identifying Hair Biomarker Candidates for Alzheimer's Disease Using Three High Resolution Mass Spectrometry-Based Untargeted Metabolomics Strategies

High-resolution mass spectrometry (HRMS)-based untargeted metabolomics strategies have emerged as an effective tool for discovering biomarkers of Alzheimer's disease (AD). There are various HRMS-based untargeted metabolomics strategies for biomarker discovery, including the data-dependent acquisition (DDA) method, the combination of full scan and target MS/MS, and the all ion fragmentation (AIF) method. Hair has emerged as a potential biospecimen for biomarker discovery in clinical research since it might reflect the circulating metabolic profiles over several months, while the analytical performances of the different data acquisition methods for hair biomarker discovery have been rarely investigated. Here, the analytical performances of three data acquisition methods in HRMS-based untargeted metabolomics for hair biomarker discovery were evaluated. The human hair samples from AD patients (N = 23) and cognitively normal individuals (N = 23) were used as an example. The most significant number of discriminatory features was acquired using the full scan (407), which is approximately 10-fold higher than that using the DDA strategy (41) and 11% higher than that using the AIF strategy (366). Only 66% of discriminatory chemicals discovered in the DDA strategy were discriminatory features in the full scan dataset. Moreover, compared to the deconvoluted MS/MS spectra with coeluted and background ions from the AIF method, the MS/MS spectrum obtained from the targeted MS/MS approach is cleaner and purer. Therefore, an untargeted metabolomics strategy combining the full scan with the targeted MS/MS method could obtain most discriminatory features along with a high quality MS/MS spectrum for discovering the AD biomarkers.

Computational Models for Biomarker Discovery

Alzheimer's disease (AD) is a prevalent and debilitating neurodegenerative disorder characterized by progressive cognitive decline. Early diagnosis and accurate prediction of disease progression are critical for developing effective therapeutic interventions. In recent years, computational models have emerged as powerful tools for biomarker discovery and disease prediction in Alzheimer's and other neurodegenerative diseases. This paper explores the use of computational models, particularly machine learning techniques, in analyzing large volumes of data and identifying patterns related to disease progression. The significance of early diagnosis, the challenges in classifying patients at the mild cognitive impairment (MCI) stage, and the potential of computational models to improve diagnostic accuracy are examined. Furthermore, the importance of incorporating diverse biomarkers, including genetic, molecular, and neuroimaging indicators, to enhance the predictive capabilities of these models is highlighted. The paper also presents case studies on the application of computational models in simulating disease progression, analyzing neurodegenerative cascades, and predicting the future development of Alzheimer's. Overall, computational models for biomarker discovery offer promising opportunities to advance our understanding of Alzheimer's disease, facilitate early diagnosis, and guide the development of targeted therapeutic strategies.

Early dementia diagnosis, MCI-to-dementia risk prediction, and the role of machine learning methods for feature extraction from integrated biomarkers, in particular for EEG signal analysis

INTRODUCTION

Dementia in its various forms represents one of the most frightening emergencies for the aging population. Cognitive decline-including Alzheimer's disease (AD) dementia-does not develop in few days; disease mechanisms act progressively for several years before clinical evidence.

METHODS

A preclinical stage, characterized by measurable cognitive impairment, but not overt dementia, is represented by mild cognitive impairment (MCI), which progresses to-or, more accurately, is already in a prodromal form of-AD in about half cases; people with MCI are therefore considered the population at risk for AD deserving special attention for validating screening methods.

RESULTS

Graph analysis tools, combined with machine learning methods, represent an interesting probe to identify the distinctive features of physiological/pathological brain aging focusing on functional connectivity networks evaluated on electroencephalographic data and neuropsychological/imaging/genetic/metabolic/cerebrospinal fluid/blood biomarkers.

DISCUSSION

On clinical data, this innovative approach for early diagnosis might provide more insight into pathophysiological processes underlying degenerative changes, as well as toward a personalized risk evaluation for pharmacological, nonpharmacological, and rehabilitation treatments.

Latent feature representation learning for Alzheimer's disease classification

Early detection and treatment of Alzheimer's Disease (AD) are significant. Recently, multi-modality imaging data have promoted the development of the automatic diagnosis of AD. This paper proposes a method based on latent feature fusion to make full use of multi-modality image data information. Specifically, we learn a specific projection matrix for each modality by introducing a binary label matrix and local geometry constraints and then project the original features of each modality into a low-dimensional target space. In this space, we fuse latent feature representations of different modalities for AD classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative database demonstrate the proposed methods effectiveness in classifying AD.

A reusable benchmark of brain-age prediction from M/EEG resting-state signals

Population-level modeling can define quantitative measures of individual aging by applying machine learning to large volumes of brain images. These measures of brain age, obtained from the general population, helped characterize disease severity in neurological populations, improving estimates of diagnosis or prognosis. Magnetoencephalography (MEG) and Electroencephalography (EEG) have the potential to further generalize this approach towards prevention and public health by enabling assessments of brain health at large scales in socioeconomically diverse environments. However, more research is needed to define methods that can handle the complexity and diversity of M/EEG signals across diverse real-world contexts. To catalyse this effort, here we propose reusable benchmarks of competing machine learning approaches for brain age modeling. We benchmarked popular classical machine learning pipelines and deep learning architectures previously used for pathology decoding or brain age estimation in 4 international M/EEG cohorts from diverse countries and cultural contexts, including recordings from more than 2500 participants. Our benchmarks were built on top of the M/EEG adaptations of the BIDS standard, providing tools that can be applied with minimal modification on any M/EEG dataset provided in the BIDS format. Our results suggest that, regardless of whether classical machine learning or deep learning was used, the highest performance was reached by pipelines and architectures involving spatially aware representations of the M/EEG signals, leading to R^2 scores between 0.60-0.71. Hand-crafted features paired with random forest regression provided robust benchmarks even in situations in which other approaches failed. Taken together, this set of benchmarks, accompanied by open-source software and high-level Python scripts, can serve as a starting point and quantitative reference for future efforts at developing M/EEG-based measures of brain aging. The generality of the approach renders this benchmark reusable for other related objectives such as modeling specific cognitive variables or clinical endpoints.

Non-Invasive Nasal Discharge Fluid and Other Body Fluid Biomarkers in Alzheimer’s Disease

The key to current Alzheimer’s disease (AD) therapy is the early diagnosis for prompt intervention, since available treatments only slow the disease progression. Therefore, this lack of promising therapies has called for diagnostic screening tests to identify those likely to develop full-blown AD. Recent AD diagnosis guidelines incorporated core biomarker analyses into criteria, including amyloid-β (Aβ), total-tau (T-tau), and phosphorylated tau (P-tau). Though effective, the accessibility of screening tests involving conventional cerebrospinal fluid (CSF)- and blood-based analyses is often hindered by the invasiveness and high cost. In an attempt to overcome these shortcomings, biomarker profiling research using non-invasive body fluid has shown the potential to capture the pathological changes in the patients’ bodies. These novel non-invasive body fluid biomarkers for AD have emerged as diagnostic and pathological targets. Here, we review the potential peripheral biomarkers, including non-invasive peripheral body fluids of nasal discharge, tear, saliva, and urine for AD.

Investigation of Underlying Association Between Whole Brain Regions and Alzheimer’s Disease: A Research Based on an Artificial Intelligence Model

Alzheimer’s disease (AD) is the most common form of dementia, causing progressive cognitive decline. Radiomic features obtained from structural magnetic resonance imaging (sMRI) have shown a great potential in predicting this disease. However, radiomic features based on the whole brain segmented regions have not been explored yet. In our study, we collected sMRI data that include 80 patients with AD and 80 healthy controls (HCs). For each patient, the T1 weighted image (T1WI) images were segmented into 106 subregions, and radiomic features were extracted from each subregion. Then, we analyzed the radiomic features of specific brain subregions that were most related to AD. Based on the selective radiomic features from specific brain subregions, we built an integrated model using the best machine learning algorithms, and the diagnostic accuracy was evaluated. The subregions most relevant to AD included the hippocampus, the inferior parietal lobe, the precuneus, and the lateral occipital gyrus. These subregions exhibited several important radiomic features that include shape, gray level size zone matrix (GLSZM), and gray level dependence matrix (GLDM), among others. Based on the comparison among different algorithms, we constructed the best model using the Logistic regression (LR) algorithm, which reached an accuracy of 0.962. Conclusively, we constructed an excellent model based on radiomic features from several specific AD-related subregions, which could give a potential biomarker for predicting AD.

Examining a role for the retrosplenial cortex in age-related memory impairment

Aging is often characterized by changes in the ability to form and accurately recall episodic memories, and this is especially evident in neuropsychiatric conditions including Alzheimer's disease and dementia. Memory impairments and cognitive decline associated with aging mirror the impairments observed following damage to the retrosplenial cortex, suggesting that this region might be important for continued cognitive function throughout the lifespan. Here, we review lines of evidence demonstrating that degeneration of the retrosplenial cortex is critically involved in age-related memory impairment and suggest that preservation of function in this region as part of a larger circuit that supports memory maintenance will decrease the deleterious effects of aging on memory processing.

Multimodal Classification of Alzheimer's Disease and Amnestic Mild Cognitive Impairment: Integrated 18F-FDG PET and DTI Study

BACKGROUND

Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline and memory impairment. Amnestic mild cognitive impairment (aMCI) is the intermediate stage between normal cognitive aging and early dementia caused by AD. It can be challenging to differentiate aMCI patients from healthy controls (HC) and mild AD patients.

OBJECTIVE

To validate whether the combination of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) and diffusion tensor imaging (DTI) will improve classification performance compared with that based on a single modality.

METHODS

A total of thirty patients with AD, sixty patients with aMCI, and fifty healthy controls were included. AD was diagnosed according to the National Institute of Neurological and Communicative Diseases and Stroke/Alzheimer's Disease and Related Disorders Association (NINCDS-ADRDA) criteria for probable. aMCI diagnosis was based on Petersen's criteria. The 18F-FDG PET and DTI measures were each used separately or in combination to evaluate sensitivity, specificity, and accuracy for differentiating HC, aMCI, and AD using receiver operating characteristic analysis together with binary logistic regression. The rate of accuracy was based on the area under the curve (AUC).

RESULTS

For classifying AD from HC, we achieve an AUC of 0.96 when combining two modalities of biomarkers and 0.93 when using 18F-FDG PET individually. For classifying aMCI from HC, we achieve an AUC of 0.79 and 0.76 using the best individual modality of biomarkers.

CONCLUSION

Our results show that the combination of two modalities improves classification performance, compared with that using any individual modality.

Identifying Type 2 Diabetic Brains by Investigating Disease-Related Structural Changes in Magnetic Resonance Imaging

Diabetes with high blood glucose levels may damage the brain nerves and thus increase the risk of dementia. Previous studies have shown that dementia can be reflected in altered brain structure, facilitating computer-aided diagnosis of brain diseases based on structural magnetic resonance imaging (MRI). However, type 2 diabetes mellitus (T2DM)-mediated changes in the brain structures have not yet been studied, and only a few studies have focused on the use of brain MRI for automated diagnosis of T2DM. Hence, identifying MRI biomarkers is essential to evaluate the association between changes in brain structure and T2DM as well as cognitive impairment (CI). The present study aims to investigate four methods to extract features from MRI, characterize imaging biomarkers, as well as identify subjects with T2DM and CI.

Input Agnostic Deep Learning for Alzheimer's Disease Classification Using Multimodal MRI Images

Alzheimer's disease (AD) is a progressive brain disorder that causes memory and functional impairments. The advances in machine learning and publicly available medical datasets initiated multiple studies in AD diagnosis. In this work, we utilize a multi-modal deep learning approach in classifying normal cognition, mild cognitive impairment and AD classes on the basis of structural MRI and diffusion tensor imaging (DTI) scans from the OASIS-3 dataset. In addition to a conventional multi-modal network, we also present an input agnostic architecture that allows diagnosis with either sMRI or DTI scan, which distinguishes our method from previous multi-modal machine learning-based methods. The results show that the input agnostic model achieves 0.96 accuracy when both structural MRI and DTI scans are provided as inputs.

Artificial Intelligence for Alzheimer's Disease: Promise or Challenge?

Decades of experimental and clinical research have contributed to unraveling many mechanisms in the pathogenesis of Alzheimer's disease (AD), but the puzzle is still incomplete. Although we can suppose that there is no complete set of puzzle pieces, the recent growth of open data-sharing initiatives collecting lifestyle, clinical, and biological data from AD patients has provided a potentially unlimited amount of information about the disease, far exceeding the human ability to make sense of it. Moreover, integrating Big Data from multi-omics studies provides the potential to explore the pathophysiological mechanisms of the entire biological continuum of AD. In this context, Artificial Intelligence (AI) offers a wide variety of methods to analyze large and complex data in order to improve knowledge in the AD field. In this review, we focus on recent findings and future challenges for AI in AD research. In particular, we discuss the use of Computer-Aided Diagnosis tools for AD diagnosis and the use of AI to potentially support clinical practices for the prediction of individual risk of AD conversion as well as patient stratification in order to finally develop effective and personalized therapies.

Alzheimer's disease detection using depthwise separable convolutional neural networks

To diagnose Alzheimer's disease (AD), neuroimaging methods such as magnetic resonance imaging have been employed. Recent progress in computer vision with deep learning (DL) has further inspired research focused on machine learning algorithms. However, a few limitations of these algorithms, such as the requirement for large number of training images and the necessity for powerful computers, still hinder the extensive usage of AD diagnosis based on machine learning. In addition, large number of training parameters and heavy computation make the DL systems difficult in integrating with mobile embedded devices, for example the mobile phones. For AD detection using DL, most of the current research solely focused on improving the classification performance, while few studies have been done to obtain a more compact model with less complexity and relatively high recognition accuracy. In order to solve this problem and improve the efficiency of the DL algorithm, a deep separable convolutional neural network model is proposed for AD classification in this paper. The depthwise separable convolution (DSC) is used in this work to replace the conventional convolution. Compared to the traditional neural networks, the parameters and computing cost of the proposed neural network are found greatly reduced. The parameters and computational costs of the proposed neural network are found to be significantly reduced compared with conventional neural networks. With its low power consumption, the proposed model is particularly suitable for embedding mobile devices. Experimental findings show that the DSC algorithm, based on the OASIS magnetic resonance imaging dataset, is very successful for AD detection. Moreover, transfer learning is employed in this work to improve model performance. Two trained models with complex networks, namely AlexNet and GoogLeNet, are used for transfer learning, with average classification rates of 91.40%, 93.02% and a less power consumption.

Comparison of the clinical impact of 2-[18F]FDG-PET and cerebrospinal fluid biomarkers in patients suspected of Alzheimer's disease

BACKGROUND

The two biomarkers 2-[18F]FDG-PET and cerebrospinal fluid biomarkers are both recommended to support the diagnosis of Alzheimer's disease. However, there is a lack of knowledge for the comparison of the two biomarkers in a routine clinical setting.

OBJECTIVE

The aim was to compare the clinical impact of 2-[18F]FDG-PET and cerebrospinal fluid biomarkers on diagnosis, prognosis, and patient management in patients suspected of Alzheimer's disease.

METHODS

Eighty-one patients clinically suspected of Alzheimer's disease were retrospectively included from the Copenhagen Memory Clinic. As part of the clinical work-up all patients had a standard diagnostic program examination including MRI and ancillary investigations with 2-[18F]FDG-PET and cerebrospinal fluid biomarkers. An incremental study design was used to evaluate the clinical impact of the biomarkers. First, the diagnostic evaluation was based on the standard diagnostic program, then the diagnostic evaluation was revised after addition of either cerebrospinal fluid biomarkers or 2-[18F]FDG-PET. At each diagnostic evaluation, two blinded dementia specialists made a consensus decision on diagnosis, prediction of disease course, and change in patient management. Confidence in the decision was measured on a visual analogue scale (0-100). After 6 months, the diagnostic evaluation was performed with addition of the other biomarker. A clinical follow-up after 12 months was used as reference for diagnosis and disease course.

RESULTS

The two biomarkers had a similar clinical value across all diagnosis when added individually to the standard diagnostic program. However, for the correctly diagnosed patient with Alzheimer's disease cerebrospinal fluid biomarkers had a significantly higher impact on diagnostic confidence (mean scores±SD: 88±11 vs. 82±11, p = 0.046) and a significant reduction in the need for ancillary investigations (23 vs. 18 patients, p = 0.049) compared to 2-[18F]FDG-PET.

CONCLUSION

The two biomarkers had similar clinical impact on diagnosis, but cerebrospinal fluid biomarkers had a more significant value in corroborating the diagnosis of Alzheimer's disease compared to 2-[18F]FDG-PET.

2020 update on the clinical validity of cerebrospinal fluid amyloid, tau, and phospho-tau as biomarkers for Alzheimer's disease in the context of a structured 5-phase development framework

Purpose

In the last decade, the research community has focused on defining reliable biomarkers for the early detection of Alzheimer’s disease (AD) pathology. In 2017, the Geneva AD Biomarker Roadmap Initiative adapted a framework for the systematic validation of oncological biomarkers to cerebrospinal fluid (CSF) AD biomarkers—encompassing the 42 amino-acid isoform of amyloid-β (Aβ42), phosphorylated-tau (P-tau), and Total-tau (T-tau)—with the aim to accelerate their development and clinical implementation. The aim of this work is to update the current validation status of CSF AD biomarkers based on the Biomarker Roadmap methodology.

Methods

A panel of experts in AD biomarkers convened in November 2019 at a 2-day workshop in Geneva. The level of maturity (fully achieved, partly achieved, preliminary evidence, not achieved, unsuccessful) of CSF AD biomarkers was assessed based on the Biomarker Roadmap methodology before the meeting and presented and discussed during the workshop.

Results

By comparison to the previous 2017 Geneva Roadmap meeting, the primary advances in CSF AD biomarkers have been in the area of a unified protocol for CSF sampling, handling and storage, the introduction of certified reference methods and materials for Aβ42, and the introduction of fully automated assays. Additional advances have occurred in the form of defining thresholds for biomarker positivity and assessing the impact of covariates on their discriminatory ability.

Conclusions

Though much has been achieved for phases one through three, much work remains in phases four (real world performance) and five (assessment of impact/cost). To a large degree, this will depend on the availability of disease-modifying treatments for AD, given these will make accurate and generally available diagnostic tools key to initiate therapy.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00259-021-05258-7.

Reciprocal Incremental Value of 18F-FDG-PET and Cerebrospinal Fluid Biomarkers in Mild Cognitive Impairment Patients Suspected for Alzheimer's Disease and Inconclusive First Biomarker

BACKGROUND

In Alzheimer's disease (AD) diagnosis, both cerebrospinal fluid (CSF) biomarkers and FDG-PET sometimes give inconclusive results.

OBJECTIVE

To evaluate the incremental diagnostic value of FDG-PET over CSF biomarkers, and vice versa, in patients with mild cognitive impairment (MCI) and suspected AD, in which the first biomarker resulted inconclusive.

METHODS

A consecutive series of MCI patients was retrospectively selected from two Memory Clinics where, as per clinical routine, either the first biomarker choice is FDG-PET and CSF biomarkers are only used in patients with uninformative FDG-PET, or vice versa. We defined criteria of uncertainty in interpretation of FDG-PET and CSF biomarkers, according to current evidence. The final diagnosis was established according to clinical-neuropsychological follow-up of at least one year (mean 4.4±2.2).

RESULTS

When CSF was used as second biomarker after FDG-PET, 14 out of 36 (39%) received informative results. Among these 14 patients, 11 (79%) were correctly classified with respect to final diagnosis, thus with a relative incremental value of CSF over FDG-PET of 30.6%. When FDG-PET was used as second biomarker, 26 out of 39 (67%) received informative results. Among these 26 patients, 15 (58%) were correctly classified by FDG-PET with respect to final diagnosis, thus with a relative incremental value over CSF of 38.5%.

CONCLUSION

Our real-world data confirm the added values of FDG-PET (or CSF) in a diagnostic pathway where CSF (or FDG-PET) was used as first biomarkers in suspected AD. These findings should be replicated in larger studies with prospective enrolment according to a Phase III design.

Within-session verbal learning slope is predictive of lifespan delayed recall, hippocampal volume, and memory training benefit, and is heritable

Memory performance results from plasticity, the ability to change with experience. We show that benefit from practice over a few trials, learning slope, is predictive of long-term recall and hippocampal volume across a broad age range and a long period of time, relates to memory training benefit, and is heritable. First, in a healthy lifespan sample (n = 1825, age 4-93 years), comprising 3483 occasions of combined magnetic resonance imaging (MRI) scans and memory tests over a period of up to 11 years, learning slope across 5 trials was uniquely related to performance on a delayed free recall test, as well as hippocampal volume, independent from first trial memory or total memory performance across the five learning trials. Second, learning slope was predictive of benefit from memory training across ten weeks in an experimental subsample of adults (n = 155). Finally, in an independent sample of male twins (n = 1240, age 51-50 years), learning slope showed significant heritability. Within-session learning slope may be a useful marker beyond performance per se, being heritable and having unique predictive value for long-term memory function, hippocampal volume and training benefit across the human lifespan.

Associating Multi-Modal Brain Imaging Phenotypes and Genetic Risk Factors via a Dirty Multi-Task Learning Method

Brain imaging genetics becomes more and more important in brain science, which integrates genetic variations and brain structures or functions to study the genetic basis of brain disorders. The multi-modal imaging data collected by different technologies, measuring the same brain distinctly, might carry complementary information. Unfortunately, we do not know the extent to which the phenotypic variance is shared among multiple imaging modalities, which further might trace back to the complex genetic mechanism. In this paper, we propose a novel dirty multi-task sparse canonical correlation analysis (SCCA) to study imaging genetic problems with multi-modal brain imaging quantitative traits (QTs) involved. The proposed method takes advantages of the multi-task learning and parameter decomposition. It can not only identify the shared imaging QTs and genetic loci across multiple modalities, but also identify the modality-specific imaging QTs and genetic loci, exhibiting a flexible capability of identifying complex multi-SNP-multi-QT associations. Using the state-of-the-art multi-view SCCA and multi-task SCCA, the proposed method shows better or comparable canonical correlation coefficients and canonical weights on both synthetic and real neuroimaging genetic data. In addition, the identified modality-consistent biomarkers, as well as the modality-specific biomarkers, provide meaningful and interesting information, demonstrating the dirty multi-task SCCA could be a powerful alternative method in multi-modal brain imaging genetics.

Multivariate Data Analysis and Machine Learning for Prediction of MCI-to-AD Conversion

There has always been a need for discovering efficient and dependable Alzheimer's disease (AD) diagnostic biomarkers. Like the majority of diseases, the earlier the diagnosis, the most effective the treatment. (Semi)-automated structural magnetic resonance imaging (MRI) processing approaches are very popular in AD research. Mild cognitive impairment (MCI) is considered to be a stage between normal cognitive ageing and dementia. MCI can often be the prodromal stage of AD. Around 10-15% of MCI patients convert to AD per year. In this study, we used three supervised machine learning (ML) techniques to differentiate MCI converters (MCIc) from MCI non-converters (MCInc) and predict their conversion rates from baseline MRI data (cortical thickness (CTH) and hippocampal volume (HCV)). A total of 803 participants from the ADNI cohort were included in this study (188 AD, 107 MCIc, 257 MCInc and 156 healthy controls (HC)). We studied the classification abilities of three different WEKA classifiers (support vector machine (SVM), decision trees (J48) and Naive Bayes (NB)). We built six different classification models, three models based on CTH and three based on HCV (CTH-SVM, CTH-J48, CTH-NB, HCV-SVM, HCV-J48 and HCV-NB). For the classification experiments, we obtained up to 71% sensitivity and up to 56% specificity. The prediction of conversion showed accuracy for up to 84%. The value of certain multivariate models derived from the classification experiments has exhibited robust and effective results in MCIc identification. However, there was a limitation in this study since we could not compare the CTH with the HCV models seeing as the data used originated from different subjects. As future direction, we propose the creation of a model that would combine various features with data originating from the same subjects, thus being a far more reliable and accurate prognostic tool.

Spatially-Constrained Fisher Representation for Brain Disease Identification With Incomplete Multi-Modal Neuroimages

Multi-modal neuroimages, such as magnetic resonance imaging (MRI) and positron emission tomography (PET), can provide complementary structural and functional information of the brain, thus facilitating automated brain disease identification. Incomplete data problem is unavoidable in multi-modal neuroimage studies due to patient dropouts and/or poor data quality. Conventional methods usually discard data-missing subjects, thus significantly reducing the number of training samples. Even though several deep learning methods have been proposed, they usually rely on pre-defined regions-of-interest in neuroimages, requiring disease-specific expert knowledge. To this end, we propose a spatially-constrained Fisher representation framework for brain disease diagnosis with incomplete multi-modal neuroimages. We first impute missing PET images based on their corresponding MRI scans using a hybrid generative adversarial network. With the complete (after imputation) MRI and PET data, we then develop a spatially-constrained Fisher representation network to extract statistical descriptors of neuroimages for disease diagnosis, assuming that these descriptors follow a Gaussian mixture model with a strong spatial constraint (i.e., images from different subjects have similar anatomical structures). Experimental results on three databases suggest that our method can synthesize reasonable neuroimages and achieve promising results in brain disease identification, compared with several state-of-the-art methods.

Prognostic value of complementary biomarkers of neurodegeneration in a mixed memory clinic cohort

Background

Biomarkers of neurodegeneration, e.g. MRI brain atrophy and [¹⁸F]FDG-PET hypometabolism, are often evaluated in patients suspected of neurodegenerative disease.

Objective

Our primary objective was to investigate prognostic properties of atrophy and hypometabolism.

Methods

From March 2015-June 2016, 149 patients referred to a university hospital memory clinic were included. The primary outcome was progression/stable disease course as assessed by a clinician at 12 months follow-up. Intracohort defined z-scores of baseline MRI automatic quantified volume and [¹⁸F]FDG-PET standardized uptake value ratios were calculated for all unilaterally defined brain lobes and dichotomized as pronounced atrophy (+A)/ pronounced hypometabolism (+H) at z-score <0. A logistic regression model with progression status as the outcome was carried out with number of lobes with the patterns +A/-H, -A/+H, +A/+H respectively as predictors. The model was mutually adjusted along with adjustment for age and sex. A sensitivity analysis with a z-score dichotomization at −0.1 and −0.5 and dichotomization regarding number of lobes affected at one and three lobes was done.

Results

Median follow-up time was 420 days [IQR: 387-461 days] and 50 patients progressed. Patients with two or more lobes affected by the pattern +A/+H compared to patients with 0–1 lobes affected had a statistically significant increased risk of progression (odds ratio, 95 % confidence interval: 4.33, 1.90–9.86) in a multivariable model. The model was partially robust to the applied sensitivity analysis.

Conclusion

Combined atrophy and hypometabolism as assessed by MRI and [¹⁸F]FDG-PET in patients under suspicion of neurodegenerative disease predicts progression over 1 year.

Molecular and Imaging Biomarkers in Alzheimer's Disease: A Focus on Recent Insights

Alzheimer’s disease (AD) is the most common neurodegenerative disease among the elderly, affecting millions of people worldwide and clinically characterized by a progressive and irreversible cognitive decline. The rapid increase in the incidence of AD highlights the need for an easy, efficient and accurate diagnosis of the disease in its initial stages in order to halt or delay the progression. The currently used diagnostic methods rely on measures of amyloid-β (Aβ), phosphorylated (p-tau) and total tau (t-tau) protein levels in the cerebrospinal fluid (CSF) aided by advanced neuroimaging techniques like positron emission tomography (PET) and magnetic resonance imaging (MRI). However, the invasiveness of these procedures and the high cost restrict their utilization. Hence, biomarkers from biological fluids obtained using non-invasive methods and novel neuroimaging approaches provide an attractive alternative for the early diagnosis of AD. Such biomarkers may also be helpful for better understanding of the molecular mechanisms underlying the disease, allowing differential diagnosis or at least prolonging the pre-symptomatic stage in patients suffering from AD. Herein, we discuss the advantages and limits of the conventional biomarkers as well as recent promising candidates from alternative body fluids and new imaging techniques.

Deep residual learning for neuroimaging: An application to predict progression to Alzheimer's disease

BACKGROUND

The unparalleled performance of deep learning approaches in generic image processing has motivated its extension to neuroimaging data. These approaches learn abstract neuroanatomical and functional brain alterations that could enable exceptional performance in classification of brain disorders, predicting disease progression, and localizing brain abnormalities.

NEW METHOD

This work investigates the suitability of a modified form of deep residual neural networks (ResNet) for studying neuroimaging data in the specific application of predicting progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD). Prediction was conducted first by training the deep models using MCI individuals only, followed by a domain transfer learning version that additionally trained on AD and controls. We also demonstrate a network occlusion based method to localize abnormalities.

RESULTS

The implemented framework captured non-linear features that successfully predicted AD progression and also conformed to the spectrum of various clinical scores. In a repeated cross-validated setup, the learnt predictive models showed highly similar peak activations that corresponded to previous AD reports.

COMPARISON WITH EXISTING METHODS

The implemented architecture achieved a significant performance improvement over the classical support vector machine and the stacked autoencoder frameworks (p <  0.005), numerically better than state-of-the-art performance using sMRI data alone (> 7% than the second-best performing method) and within 1% of the state-of-the-art performance considering learning using multiple neuroimaging modalities as well.

CONCLUSIONS

The explored frameworks reflected the high potential of deep learning architectures in learning subtle predictive features and utility in critical applications such as predicting and understanding disease progression.

ACR Appropriateness Criteria® Dementia

Degenerative disease of the central nervous system is a growing public health concern. The primary role of neuroimaging in the workup of patients with probable or possible Alzheimer disease has typically been to exclude other significant intracranial abnormalities. In general, the imaging findings in structural studies, such as MRI, are nonspecific and have limited potential in differentiating different types of dementia. Advanced imaging methods are not routinely used in community or general practices for the diagnosis or differentiation of forms of dementia. Nonetheless, in patients who have been evaluated by a dementia expert, FDG-PET helps to distinguish Alzheimer disease from frontotemporal dementia. In patients with suspected dementia with Lewy bodies, functional imaging of the dopamine transporter (ioflupane) using SPECT may be helpful. In patients with suspected normal-pressure hydrocephalus, DTPA cisternography and HMPAO SPECT/CT brain may provide assessment. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

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

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

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

BACKGROUND

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

OBJECTIVES

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

SEARCH METHODS

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

SELECTION CRITERIA

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

DATA COLLECTION AND ANALYSIS

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

MAIN RESULTS

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

AUTHORS' CONCLUSIONS

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

Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer's disease

The accurate diagnosis of Alzheimer's disease (AD) and its early stage, e.g., mild cognitive impairment (MCI), is essential for timely treatment or possible intervention to slow down AD progression. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis and prognosis. Therefore, information fusion strategies with multi-modal neuroimaging data, such as voxel-based measures extracted from structural MRI (VBM-MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET), have shown their effectiveness for AD diagnosis. However, most existing methods are proposed to simply integrate the multi-modal data, but do not make full use of structure information across the different modalities. In this paper, we propose a novel multi-modal neuroimaging feature selection method with consistent metric constraint (MFCC) for AD analysis. First, the similarity is calculated for each modality (i.e. VBM-MRI or FDG-PET) individually by random forest strategy, which can extract pairwise similarity measures for multiple modalities. Then the group sparsity regularization term and the sample similarity constraint regularization term are used to constrain the objective function to conduct feature selection from multiple modalities. Finally, the multi-kernel support vector machine (MK-SVM) is used to fuse the features selected from different models for final classification. The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) show that the proposed method has better classification performance than the start-of-the-art multimodality-based methods. Specifically, we achieved higher accuracy and area under the curve (AUC) for AD versus normal controls (NC), MCI versus NC, and MCI converters (MCI-C) versus MCI non-converters (MCI-NC) on ADNI datasets. Therefore, the proposed model not only outperforms the traditional method in terms of AD/MCI classification, but also discovers the characteristics associated with the disease, demonstrating its promise for improving disease-related mechanistic understanding.

Leveraging Coupled Interaction for Multimodal Alzheimer's Disease Diagnosis

As the population becomes older worldwide, accurate computer-aided diagnosis for Alzheimer's disease (AD) in the early stage has been regarded as a crucial step for neurodegeneration care in recent years. Since it extracts the low-level features from the neuroimaging data, previous methods regarded this computer-aided diagnosis as a classification problem that ignored latent featurewise relation. However, it is known that multiple brain regions in the human brain are anatomically and functionally interlinked according to the current neuroscience perspective. Thus, it is reasonable to assume that the extracted features from different brain regions are related to each other to some extent. Also, the complementary information between different neuroimaging modalities could benefit multimodal fusion. To this end, we consider leveraging the coupled interactions in the feature level and modality level for diagnosis in this paper. First, we propose capturing the feature-level coupled interaction using a coupled feature representation. Then, to model the modality-level coupled interaction, we present two novel methods: 1) the coupled boosting (CB) that models the correlation of pairwise coupled-diversity on both inconsistently and incorrectly classified samples between different modalities and 2) the coupled metric ensemble (CME) that learns an informative feature projection from different modalities by integrating the intrarelation and interrelation of training samples. We systematically evaluated our methods with the AD neuroimaging initiative data set. By comparison with the baseline learning-based methods and the state-of-the-art methods that are specially developed for AD/MCI (mild cognitive impairment) diagnosis, our methods achieved the best performance with accuracy of 95.0% and 80.7% (CB), 94.9% and 79.9% (CME) for AD/NC (normal control), and MCI/NC identification, respectively.

Benchmarking machine learning models for late-onset alzheimer's disease prediction from genomic data

BACKGROUND

Late-Onset Alzheimer's Disease (LOAD) is a leading form of dementia. There is no effective cure for LOAD, leaving the treatment efforts to depend on preventive cognitive therapies, which stand to benefit from the timely estimation of the risk of developing the disease. Fortunately, a growing number of Machine Learning methods that are well positioned to address this challenge are becoming available.

RESULTS

We conducted systematic comparisons of representative Machine Learning models for predicting LOAD from genetic variation data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. Our experimental results demonstrate that the classification performance of the best models tested yielded ∼72% of area under the ROC curve.

CONCLUSIONS

Machine learning models are promising alternatives for estimating the genetic risk of LOAD. Systematic machine learning model selection also provides the opportunity to identify new genetic markers potentially associated with the disease.

Plasma Transthyretin as a Predictor of Amnestic Mild Cognitive Impairment Conversion to Dementia

Amnestic mild cognitive impairment (MCI) is a prodromal stage of dementia, with a higher incidence of these patients progressing to Alzheimer’s disease (AD) than normal aging people. A biomarker for the early detection and prediction for this progression is important. We recruited MCI subjects in three teaching hospitals and conducted longitudinal follow-up for 5 years at one-year intervals. Cognitively healthy controls were recruited for comparisom at baseline. Plasma transthyretin (TTR) levels were measured by ELISA. Survival analysis with time to AD conversion as an outcome variable was calculated with the multivariable Cox proportional hazards models using TTR as a continuous variable with adjustment for other covariates and bootstrapping resampling analysis. In total, 184 MCI subjects and 40 sex- and age-matched controls were recruited at baseline. At baseline, MCI patients had higher TTR levels compared with the control group. During the longitudinal follow-ups, 135 MCI patients (73.4%) completed follow-up at least once. The TTR level was an independent predictor for MCI conversion to AD when using TTR as a continuous variable (p = 0.023, 95% CI 1.001–1.007). In addition, in MCI converters, the TTR level at the point when they converted to AD was significantly lower than that at baseline (328.6 ± 66.5 vs. 381.9 ± 77.6 ug/ml, p < 0.001). Our study demonstrates the temporal relationship between the plasma TTR level and the conversion from MCI to AD.

Prediction and Classification of Alzheimer's Disease Based on Combined Features From Apolipoprotein-E Genotype, Cerebrospinal Fluid, MR, and FDG-PET Imaging Biomarkers

Alzheimer's disease (AD), including its mild cognitive impairment (MCI) phase that may or may not progress into the AD, is the most ordinary form of dementia. It is extremely important to correctly identify patients during the MCI stage because this is the phase where AD may or may not develop. Thus, it is crucial to predict outcomes during this phase. Thus far, many researchers have worked on only using a single modality of a biomarker for the diagnosis of AD or MCI. Although recent studies show that a combination of one or more different biomarkers may provide complementary information for the diagnosis, it also increases the classification accuracy distinguishing between different groups. In this paper, we propose a novel machine learning-based framework to discriminate subjects with AD or MCI utilizing a combination of four different biomarkers: fluorodeoxyglucose positron emission tomography (FDG-PET), structural magnetic resonance imaging (sMRI), cerebrospinal fluid (CSF) protein levels, and Apolipoprotein-E (APOE) genotype. The Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline dataset was used in this study. In total, there were 158 subjects for whom all four modalities of biomarker were available. Of the 158 subjects, 38 subjects were in the AD group, 82 subjects were in MCI groups (including 46 in MCIc [MCI converted; conversion to AD within 24 months of time period], and 36 in MCIs [MCI stable; no conversion to AD within 24 months of time period]), and the remaining 38 subjects were in the healthy control (HC) group. For each image, we extracted 246 regions of interest (as features) using the Brainnetome template image and NiftyReg toolbox, and later we combined these features with three CSF and two APOE genotype features obtained from the ADNI website for each subject using early fusion technique. Here, a different kernel-based multiclass support vector machine (SVM) classifier with a grid-search method was applied. Before passing the obtained features to the classifier, we have used truncated singular value decomposition (Truncated SVD) dimensionality reduction technique to reduce high dimensional features into a lower-dimensional feature. As a result, our combined method achieved an area under the receiver operating characteristic (AU-ROC) curve of 98.33, 93.59, 96.83, 94.64, 96.43, and 95.24% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIs, AD vs. MCIc, HC vs. MCIc, and HC vs. MCIs subjects which are high relative to single modality results and other state-of-the-art approaches. Moreover, combined multimodal methods have improved the classification performance over the unimodal classification.

Cerebral Microvascular Injury: A Potentially Treatable Endophenotype of Traumatic Brain Injury-Induced Neurodegeneration

Traumatic brain injury (TBI) is one the most common human afflictions, contributing to long-term disability in survivors. Emerging data indicate that functional improvement or deterioration can occur years after TBI. In this regard, TBI is recognized as risk factor for late-life neurodegenerative disorders. TBI encompasses a heterogeneous disease process in which diverse injury subtypes and multiple molecular mechanisms overlap. To develop precision medicine approaches where specific pathobiological processes are targeted by mechanistically appropriate therapies, techniques to identify and measure these subtypes are needed. Traumatic microvascular injury is a common but relatively understudied TBI endophenotype. In this review, we describe evidence of microvascular dysfunction in human and animal TBI, explore the role of vascular dysfunction in neurodegenerative disease, and discuss potential opportunities for vascular-directed therapies in ameliorating TBI-related neurodegeneration. We discuss the therapeutic potential of vascular-directed therapies in TBI and the use and limitations of preclinical models to explore these therapies.

Structured sparsity regularized multiple kernel learning for Alzheimer's disease diagnosis

Multimodal data fusion has shown great advantages in uncovering information that could be overlooked by using single modality. In this paper, we consider the integration of high-dimensional multi-modality imaging and genetic data for Alzheimer's disease (AD) diagnosis. With a focus on taking advantage of both phenotype and genotype information, a novel structured sparsity, defined by ℓ 1, p-norm (p > 1), regularized multiple kernel learning method is designed. Specifically, to facilitate structured feature selection and fusion from heterogeneous modalities and also capture feature-wise importance, we represent each feature with a distinct kernel as a basis, followed by grouping the kernels according to modalities. Then, an optimally combined kernel presentation of multimodal features is learned in a data-driven approach. Contrary to the Group Lasso (i.e., ℓ 2, 1-norm penalty) which performs sparse group selection, the proposed regularizer enforced on kernel weights is to sparsely select concise feature set within each homogenous group and fuse the heterogeneous feature groups by taking advantage of dense norms. We have evaluated our method using data of subjects from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The effectiveness of the method is demonstrated by the clearly improved prediction diagnosis and also the discovered brain regions and SNPs relevant to AD.

Association of short-term cognitive decline and MCI-to-AD dementia conversion with CSF, MRI, amyloid- and 18F-FDG-PET imaging

Disease-modifying treatment trials are increasingly advanced to the prodromal or preclinical phase of Alzheimer's disease (AD), and inclusion criteria are based on biomarkers rather than clinical symptoms. Therefore, it is of great interest to determine which biomarkers should be combined to accurately predict conversion from mild cognitive impairment (MCI) to AD dementia. However, up to date, only few studies performed a complete A/T/N subject characterization using each of the CSF and imaging markers, or they only investigated long-term (≥ 2 years) prognosis. This study aimed to investigate the association between cerebrospinal fluid (CSF), magnetic resonance imaging (MRI), amyloid- and ¹⁸F-FDG positron emission tomography (PET) measures at baseline, in relation to cognitive changes and conversion to AD dementia over a short-term (12-month) period. We included 13 healthy controls, 49 MCI and 16 AD dementia patients with a clinical-based diagnosis and a complete A/T/N characterization at baseline. Global cortical amyloid-β (Aβ) burden was quantified using the ¹⁸F-AV45 standardized uptake value ratio (SUVR) with two different reference regions (cerebellar grey and subcortical white matter), whereas metabolism was assessed based on ¹⁸F-FDG SUVR. CSF measures included Aβ_1–42, Aβ_1–40, T-tau, P-tau₁₈₁, and their ratios, and MRI markers included hippocampal volumes (HV), white matter hyperintensities, and cortical grey matter volumes. Cognitive functioning was measured by MMSE and RBANS index scores. All statistical analyses were corrected for age, sex, education, and APOE ε4 genotype. As a result, faster cognitive decline was most strongly associated with hypometabolism (posterior cingulate) and smaller hippocampal volume (e.g., Δstory recall: β = +0.43 [p < 0.001] and + 0.37 [p = 0.005], resp.) at baseline. In addition, faster cognitive decline was significantly associated with higher baseline Aβ burden only if SUVR was referenced to the subcortical white matter (e.g., Δstory recall: β = −0.28 [p = 0.020]). Patients with MCI converted to AD dementia at an annual rate of 31%, which could be best predicted by combining neuropsychological testing (visuospatial construction skills) with either MRI-based HV or ¹⁸F-FDG-PET. Combining all three markers resulted in 96% specificity and 92% sensitivity. Neither amyloid-PET nor CSF biomarkers could discriminate short-term converters from non-converters.

•

FDG-PET and MRI HV are the strongest predictors of cognitive decline and conversion to AD.

•

Combination of visuospatial construction testing with FDG-PET or MRI HV present high predicting power of conversion.

•

CSF and amyloid-PET seem less suitable markers of disease progression.

•

Increased AV45-PET predicts short-term cognitive decline if SUVR is referenced to WM instead of CB.

Region-specific association between basal blood insulin and cerebral glucose metabolism in older adults

Background

Although previous studies have suggested that insulin plays a role in brain function, it still remains unclear whether or not insulin has a region-specific association with neuronal and synaptic activity in the living human brain. We investigated the regional pattern of association between basal blood insulin and resting-state cerebral glucose metabolism (CMglu), a proxy for neuronal and synaptic activity, in older adults.

Method

A total of 234 nondiabetic, cognitively normal (CN) older adults underwent comprehensive clinical assessment, resting-state 18F-fluodeoxyglucose (FDG)-positron emission tomography (PET) and blood sampling to determine overnight fasting blood insulin and glucose levels, as well as apolipoprotein E (APOE) genotyping.

Results

An exploratory voxel-wise analysis of FDG-PET without a priori hypothesis demonstrated a positive association between basal blood insulin levels and resting-state CMglu in specific cerebral cortices and hippocampus, rather than in non-specific overall cerebral regions, even after controlling for the effects of APOE e4 carrier status, vascular risk factor score, body mass index, fasting blood glucose, and demographic variables. Particularly, a positive association of basal blood insulin with CMglu in the right posterior hippocampus and adjacent parahippocampal region as well as in the right inferior parietal region remained significant after multiple comparison correction. Conversely, no region showed negative association between basal blood insulin and CMglu.

Conclusions

Our finding suggests that basal fasting blood insulin may have association with neuronal and synaptic activity in specific cerebral regions, particularly in the hippocampal/parahippocampal and inferior parietal regions.

•

We investigated regional pattern of association between basal blood insulin and resting-state cerebral glucose metabolism.

•

Significant clusters with positive associations were found mainly in the hippocampal and inferior parietal regions.

•

Our finding suggests a region-specific association of basal blood insulin with resting-state cerebral glucose metabolism.

•

Further studies to elucidate underlying mechanism and implication of this region-specific association will be necessary.

Multimodal cortical and hippocampal prediction of episodic-memory plasticity in young and older adults

Episodic memory can be trained in both early and late adulthood, but there is considerable variation in cognitive improvement across individuals. Which brain characteristics make some individuals benefit more than others? We used a multimodal approach to investigate whether volumetric magnetic resonance imaging (MRI) and resting-state functional MRI characteristics of the cortex and hippocampus, brain regions involved in episodic-memory function, were predictive of cognitive improvement after memory training. We hypothesized that these brain characteristics would differentially predict memory improvement in young and older adults, given the vulnerability of cortical regions as well as the hippocampus to healthy aging. Following structural and resting-state activity magnetic resonance scans, 50 young and 76 older participants completed 10 weeks of strategic episodic-memory training. Both age groups improved their memory performance, but the young adults more so than the older. Vertex-wise analyses of cortical volume showed no significant relation to memory benefit. When analyzing the two age groups separately, hippocampal volume was predictive of memory improvement in the group of older participants only. In this age group, the lower resting-state activity of the hippocampus was also predictive of memory improvement. Both volumetric and resting-state characteristics of the hippocampus explained unique variance of the improvement in the older participants suggesting that a multimodal imaging approach is valuable for the understanding of mechanisms underlying memory plasticity in aging.

Inhaled Xenon Washout as a Biomarker of Alzheimer's Disease

Biomarkers have the potential to aid in the study of Alzheimer’s disease (AD); unfortunately, AD biomarker values often have a high degree of overlap between healthy and AD individuals. This study investigates the potential utility of a series of novel AD biomarkers, the sixty second 129Xe retention time, and the xenon washout parameter, based on the washout of hyperpolarized 129Xe from the brain of AD participants following inhalation. The xenon washout parameter is influenced by cerebral perfusion, T1 relaxation of xenon, and the xenon partition coefficient, all factors influenced by AD. Participants with AD (n = 4) and healthy volunteers (n = 4) were imaged using hyperpolarized 129Xe magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS) to determine the amount of retained xenon in the brain. At 60 s after the breath hold, AD patients retained significantly higher amounts of 129Xe compared to healthy controls. Data was fit to a pharmacokinetic model and the xenon washout parameter was extracted. Xenon washout in white and grey matter occurs at a slower rate in Alzheimer’s participants (129Xe half-life time of 42 s and 43 s, respectively) relative to controls (20 s and 16 s, respectively). Following larger scale clinical trials for validation, the xenon washout parameter has the potential to become a useful biomarker for the support of AD diagnosis.

Brain MRI analysis for Alzheimer's disease diagnosis using an ensemble system of deep convolutional neural networks

Alzheimer's disease is an incurable, progressive neurological brain disorder. Earlier detection of Alzheimer's disease can help with proper treatment and prevent brain tissue damage. Several statistical and machine learning models have been exploited by researchers for Alzheimer's disease diagnosis. Analyzing magnetic resonance imaging (MRI) is a common practice for Alzheimer's disease diagnosis in clinical research. Detection of Alzheimer's disease is exacting due to the similarity in Alzheimer's disease MRI data and standard healthy MRI data of older people. Recently, advanced deep learning techniques have successfully demonstrated human-level performance in numerous fields including medical image analysis. We propose a deep convolutional neural network for Alzheimer's disease diagnosis using brain MRI data analysis. While most of the existing approaches perform binary classification, our model can identify different stages of Alzheimer's disease and obtains superior performance for early-stage diagnosis. We conducted ample experiments to demonstrate that our proposed model outperformed comparative baselines on the Open Access Series of Imaging Studies dataset.

Histogram-Based Features Selection and Volume of Interest Ranking for Brain PET Image Classification

Positron emission tomography (PET) is a molecular medical imaging modality which is commonly used for neurodegenerative diseases diagnosis. Computer-aided diagnosis, based on medical image analysis, could help quantitative evaluation of brain diseases such as Alzheimer's disease (AD). A novel method of ranking the effectiveness of brain volume of interest (VOI) to separate healthy control from AD brains PET images is presented in this paper. Brain images are first mapped into anatomical VOIs using an atlas. Histogram-based features are then extracted and used to select and rank VOIs according to the area under curve (AUC) parameter, which produces a hierarchy of the ability of VOIs to separate between groups of subjects. The top-ranked VOIs are then input into a support vector machine classifier. The developed method is evaluated on a local database image and compared to the known selection feature methods. Results show that using AUC outperforms classification results in the case of a two group separation.