Spatial patterns of brain atrophy in MCI patients, identified via high-dimensional pattern classification, predict subsequent cognitive decline

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.

Quantifying Brain Atrophy Using a CSF-Focused Segmentation Approach

Background and Purpose

Brain atrophy, characterized by sulcal widening and ventricular enlargement, is a hallmark of neurodegenerative diseases such as Alzheimer's disease. Visual assessments are subjective and variable, while automated methods struggle with subtle intensity differences and standardization, highlighting limitations in both approaches. This study aimed to develop and evaluate a novel method focusing on cerebrospinal fluid (CSF) regions by assessing segmentation accuracy, detecting stage-specific atrophy patterns, and testing generalizability to unstandardized datasets.

Methods

We utilized T1-weighted magnetic resonance imaging data from 3,315 participants from Samsung Medical Center and 1,439 participants from other hospitals. Segmentation accuracy was evaluated using the Dice similarity coefficient (DSC), and W-scores were calculated for each region of interest (ROI) to assess stage-specific atrophy patterns.

Results

The segmentation demonstrated high accuracy, with average DSC values exceeding 0.9 for ventricular and hippocampal regions and above 0.8 for cortical regions. Significant differences in W-scores were observed across cognitive stages (cognitively unimpaired, mild cognitive impairment, dementia of Alzheimer's type) for all ROIs (all, p<0.05). Similar trends were observed in the images from other hospitals, confirming the algorithm's generalizability to datasets without prior standardization.

Conclusions

This study demonstrates the robustness and clinical applicability of a novel CSF-focused segmentation method for assessing brain atrophy. The method provides a scalable and objective framework for evaluating structural changes across cognitive stages and holds potential for broader application in neurodegenerative disease research and clinical practice.

Deep learning to quantify the pace of brain aging in relation to neurocognitive changes

Brain age (BA), distinct from chronological age (CA), can be estimated from MRIs to evaluate neuroanatomic aging in cognitively normal (CN) individuals. BA, however, is a cross-sectional measure that summarizes cumulative neuroanatomic aging since birth. Thus, it conveys poorly recent or contemporaneous aging trends, which can be better quantified by the (temporal) pace P of brain aging. Many approaches to map P, however, rely on quantifying DNA methylation in whole-blood cells, which the blood-brain barrier separates from neural brain cells. We introduce a three-dimensional convolutional neural network (3D-CNN) to estimate P noninvasively from longitudinal MRI. Our longitudinal model (LM) is trained on MRIs from 2,055 CN adults, validated in 1,304 CN adults, and further applied to an independent cohort of 104 CN adults and 140 patients with Alzheimer's disease (AD). In its test set, the LM computes P with a mean absolute error (MAE) of 0.16 y (7% mean error). This significantly outperforms the most accurate cross-sectional model, whose MAE of 1.85 y has 83% error. By synergizing the LM with an interpretable CNN saliency approach, we map anatomic variations in regional brain aging rates that differ according to sex, decade of life, and neurocognitive status. LM estimates of P are significantly associated with changes in cognitive functioning across domains. This underscores the LM's ability to estimate P in a way that captures the relationship between neuroanatomic and neurocognitive aging. This research complements existing strategies for AD risk assessment that estimate individuals' rates of adverse cognitive change with age.

Evaluating conversion from mild cognitive impairment to Alzheimer's disease with structural MRI: a machine learning study

Alzheimer's disease is a disabling neurodegenerative disorder for which no effective treatment currently exists. To predict the diagnosis of Alzheimer's disease could be crucial for patients' outcome, but current Alzheimer's disease biomarkers are invasive, time consuming or expensive. Thus, developing MRI-based computational methods for Alzheimer's disease early diagnosis would be essential to narrow down the phenotypic measures predictive of cognitive decline. Amnestic mild cognitive impairment (aMCI) is associated with higher risk for Alzheimer's disease, and here, we aimed to identify MRI-based quantitative rules to predict aMCI to possible Alzheimer's disease conversion, applying different machine learning algorithms sequentially. At baseline, T1-weighted brain images were collected for 104 aMCI patients and processed to obtain 146 volumetric measures of cerebral grey matter regions [regions of interest (ROIs)]. One year later, patients were classified as converters (aMCI-c = 32) or non-converters, i.e. clinically and neuropsychologically stable (aMCI-s = 72) based on cognitive performance. Feature selection was performed by random forest (RF), and the identified seven ROIs volumetric data were used to implement support vector machine (SVM) and decision tree (DT) classification algorithms. Both SVM and DT reached an average accuracy of 86% in identifying aMCI-c and aMCI-s. DT found a critical threshold volume of the right entorhinal cortex (EC-r) as the first feature for differentiating aMCI-c/aMCI-s. Almost all aMCI-c had an EC-r volume <1286 mm3, while more than half of the aMCI-s patients had a volume above the identified threshold for this structure. Other key regions for the classification between aMCI-c/aMCI-s were the left lateral occipital (LOC-l), the middle temporal gyrus and the temporal pole cortices. Our study reinforces previous evidence suggesting that the morphometry of the EC-r and LOC-l best predicts aMCI to Alzheimer's disease conversion. Further investigations are needed prior to deeming our findings as a broadly applicable predictive framework. However, here, a first indication was derived for volumetric thresholds that, being easy to obtain, may assist in early identification of Alzheimer's disease in clinical practice, thus contributing to establishing MRI as a useful non-invasive prognostic instrument for dementia onset.

Visual and Auditory Sensory Impairments Differentially Relate with Alzheimer's Pathology

Objective

We intended to investigate the relationships between visual sensory impairment (VSI) or auditory sensory impairment (ASI) and brain pathological changes associated with cognitive decline in older adults.

Methods

We primarily tried to examine whether each sensory impairment is related to Alzheimer's disease (AD) pathology, specifically beta-amyloid (Aβ) deposition, through both cross-sectional and longitudinal approaches in cognitively unimpaired older adults. Self-report questionnaires on vision and hearing status were administered at the baseline. Neuroimaging scans including brain [11C] Pittsburgh Compound B PET and MRI, as well as clinical assessments, were performed at baseline and 2-year follow-up.

Results

Cross-sectional analyses showed that the VSI-positive group had significantly higher Aβ deposition than the VSI-negative group, whereas there was no significant association between ASI positivity and Aβ deposition. Longitudinal analyses revealed that VSI positivity at baseline was significantly associated with increased Aβ deposition over 2 years (β = 0.153, p = 0.025), although ASI positivity was not (β = 0.045, p = 0.518). VSI positivity at baseline was also significantly associated with greater atrophic changes in AD-related brain regions over the 2-year follow-up period (β = -0.207, p = 0.005), whereas ASI positivity was not (β = 0.024, p = 0.753). Neither VSI nor ASI positivity was related to cerebrovascular injury, as measured based on the white matter hyperintensity volume.

Conclusion

The findings suggest that VSI is probably related to AD-specific pathological changes, which possibly mediate the reported relationship between VSI and cognitive decline. In contrast, ASI appears not associated with AD pathologies but may contribute to cognitive decline via other mechanisms.

Baseline multimodal imaging to predict longitudinal clinical decline in atypical Alzheimer's disease

There are recognized neuroimaging regions of interest in typical Alzheimer's disease which have been used to track disease progression and aid prognostication. However, there is a need for validated baseline imaging markers to predict clinical decline in atypical Alzheimer's Disease. We aimed to address this need by producing models from baseline imaging features using penalized regression and evaluating their predictive performance on various clinical measures. Baseline multimodal imaging data, in combination with clinical testing data at two time points from 46 atypical Alzheimer's Disease patients with a diagnosis of logopenic progressive aphasia (N = 24) or posterior cortical atrophy (N = 22), were used to generate our models. An additional 15 patients (logopenic progressive aphasia = 7, posterior cortical atrophy = 8), whose data were not used in our original analysis, were used to test our models. Patients underwent MRI, FDG-PET and Tau-PET imaging and a full neurologic battery at two time points. The Schaefer functional atlas was used to extract network-based and regional gray matter volume or PET SUVR values from baseline imaging. Penalized regression (Elastic Net) was used to create models to predict scores on testing at Time 2 while controlling for baseline performance, education, age, and sex. In addition, we created models using clinical or Meta Region of Interested (ROI) data to serve as comparisons. We found the degree of baseline involvement on neuroimaging was predictive of future performance on cognitive testing while controlling for the above measures on all three imaging modalities. In many cases, model predictability improved with the addition of network-based neuroimaging data to clinical data. We also found our network-based models performed superiorly to the comparison models comprised of only clinical or a Meta ROI score. Creating predictive models from imaging studies at a baseline time point that are agnostic to clinical diagnosis as we have described could prove invaluable in both the clinical and research setting, particularly in the development and implementation of future disease modifying therapies.

Proteomic analyses reveal plasma EFEMP1 and CXCL12 as biomarkers and determinants of neurodegeneration

INTRODUCTION

Plasma proteomic analyses of unique brain atrophy patterns may illuminate peripheral drivers of neurodegeneration and identify novel biomarkers for predicting clinically relevant outcomes.

METHODS

We identified proteomic signatures associated with machine learning-derived aging- and Alzheimer's disease (AD) -related brain atrophy patterns in the Baltimore Longitudinal Study of Aging (n = 815). Using data from five cohorts, we examined whether candidate proteins were associated with AD endophenotypes and long-term dementia risk.

RESULTS

Plasma proteins associated with distinct patterns of age- and AD-related atrophy were also associated with plasma/cerebrospinal fluid (CSF) AD biomarkers, cognition, AD risk, as well as mid-life (20-year) and late-life (8-year) dementia risk. EFEMP1 and CXCL12 showed the most consistent associations across cohorts and were mechanistically implicated as determinants of brain structure using genetic methods, including Mendelian randomization.

DISCUSSION

Our findings reveal plasma proteomic signatures of unique aging- and AD-related brain atrophy patterns and implicate EFEMP1 and CXCL12 as important molecular drivers of neurodegeneration.

HIGHLIGHTS

Plasma proteomic signatures are associated with unique patterns of brain atrophy. Brain atrophy-related proteins predict clinically relevant outcomes across cohorts. Genetic variation underlying plasma EFEMP1 and CXCL12 influences brain structure. EFEMP1 and CXCL12 may be important molecular drivers of neurodegeneration.

Integrating Multi-omics to Identify Age-Related Macular Degeneration Subtypes and Biomarkers

Age-related macular degeneration (AMD) is one of the most common causes of irreversible vision loss in the elderly. Its pathogenesis is likely multifactorial, involving a complex interaction of metabolic and environmental factors, and remains poorly understood. Previous studies have shown that mitochondrial dysfunction and oxidative stress play a crucial role in the development of AMD. Oxidative damage to the retinal pigment epithelium (RPE) has been identified as one of the major mediators in the pathogenesis of age-related macular degeneration (AMD). Therefore, this article combines transcriptome sequencing (RNA-seq) and single-cell sequencing (scRNA-seq) data to explore the role of mitochondria-related genes (MRGs) in AMD. Firstly, differential expression analysis was performed on the raw RNA-seq data. The intersection of differentially expressed genes (DEGs) and MRGs was performed. This paper proposes a deep subspace nonnegative matrix factorization (DS-NMF) algorithm to perform a multi-layer nonlinear transformation on the intersection of gene expression profiles corresponding to AMD samples. The age of AMD patients is used as prior information at the network's top level to change the data distribution. The classification is based on reconstructed data with altered distribution. The types obtained significantly differ in scores of multiple immune-related pathways and immune cell infiltration abundance. Secondly, an optimal AMD diagnosis model was constructed using multiple machine learning algorithms for external and qRT-PCR verification. Finally, ten potential therapeutic drugs for AMD were identified based on cMAP analysis. The AMD subtypes identified in this article and the diagnostic model constructed can provide a reference for treating AMD and discovering new drug targets.

Predicting the Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Graph Frequency Bands and Functional Connectivity-Based Features

Accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is crucial for disease management. Machine learning techniques have demonstrated success in classifying AD and MCI cases, particularly with the use of resting-state functional magnetic resonance imaging (rs-fMRI) data.This study utilized three years of rs-fMRI data from the ADNI, involving 142 patients with stable MCI (sMCI) and 136 with progressive MCI (pMCI). Graph signal processing was applied to filter rs-fMRI data into low, middle, and high frequency bands. Connectivity-based features were derived from both filtered and unfiltered data, resulting in a comprehensive set of 100 features, including global graph metrics, minimum spanning tree (MST) metrics, triadic interaction metrics, hub tendency metrics, and the number of links. Feature selection was enhanced using particle swarm optimization (PSO) and simulated annealing (SA). A support vector machine (SVM) with a radial basis function (RBF) kernel and a 10-fold cross-validation setup were employed for classification. The proposed approach demonstrated superior performance, achieving optimal accuracy with minimal feature utilization. When PSO selected five features, SVM exhibited accuracy, specificity, and sensitivity rates of 77%, 70%, and 83%, respectively. The identified features were as follows: (Mean of clustering coefficient, Mean of strength)/Radius/(Mean Eccentricity, and Modularity) from low/middle/high frequency bands of graph. The study highlights the efficacy of the proposed framework in identifying individuals at risk of AD development using a parsimonious feature set. This approach holds promise for advancing the precision of MCI to AD progression prediction, aiding in early diagnosis and intervention strategies.

Proteomic Indicators of Health Predict Alzheimer's Disease Biomarker Levels and Dementia Risk

OBJECTIVE

Few studies have comprehensively examined how health and disease risk influence Alzheimer's disease (AD) biomarkers. The present study examined the association of 14 protein-based health indicators with plasma and neuroimaging biomarkers of AD and neurodegeneration.

METHODS

In 706 cognitively normal adults, we examined whether 14 protein-based health indices (ie, SomaSignal® tests) were associated with concurrently measured plasma-based biomarkers of AD pathology (amyloid-β [Aβ]42/40 , tau phosphorylated at threonine-181 [pTau-181]), neuronal injury (neurofilament light chain [NfL]), and reactive astrogliosis (glial fibrillary acidic protein [GFAP]), brain volume, and cortical Aβ and tau. In a separate cohort (n = 11,285), we examined whether protein-based health indicators associated with neurodegeneration also predict 25-year dementia risk.

RESULTS

Greater protein-based risk for cardiovascular disease, heart failure mortality, and kidney disease was associated with lower Aβ42/40 and higher pTau-181, NfL, and GFAP levels, even in individuals without cardiovascular or kidney disease. Proteomic indicators of body fat percentage, lean body mass, and visceral fat were associated with pTau-181, NfL, and GFAP, whereas resting energy rate was negatively associated with NfL and GFAP. Together, these health indicators predicted 12, 31, 50, and 33% of plasma Aβ42/40 , pTau-181, NfL, and GFAP levels, respectively. Only protein-based measures of cardiovascular risk were associated with reduced regional brain volumes; these measures predicted 25-year dementia risk, even among those without clinically defined cardiovascular disease.

INTERPRETATION

Subclinical peripheral health may influence AD and neurodegenerative disease processes and relevant biomarker levels, particularly NfL. Cardiovascular health, even in the absence of clinically defined disease, plays a central role in brain aging and dementia. ANN NEUROL 2024;95:260-273.

Feature Importance Analysis and Machine Learning for Alzheimer's Disease Early Detection: Feature Fusion of the Hippocampus, Entorhinal Cortex, and Standardized Uptake Value Ratio

Introduction

Alzheimer's disease (AD) is a progressive neurological disorder characterized by mild memory loss and ranks as a leading cause of mortality in the USA, accounting for approximately 120,000 deaths per year. It is also the primary form of dementia. Early detection is critical for timely intervention as the neurodegenerative process often starts 15-20 years before cognitive symptoms manifest. This study focuses on determining feature importance in AD classification using fused texture features from 3D magnetic resonance imaging hippocampal and entorhinal cortex and standardized uptake value ratio (SUVR) derived from positron emission tomography (PET) images.

Methods

To achieve this objective, we employed four distinct classifiers (Linear Support Vector Classification, Linear Discriminant Analysis, Logistic Regression, and Logistic Regression Classifier with Stochastic Gradient Descent Learning). These classifiers were used to derive both average and top-ranked importance scores for each feature based on their outputs. Our framework is designed to distinguish between two classes, AD-negative (or mild cognitive impairment stable [MCIs]) and AD-positive (or MCI conversion [MCIc]), using a probabilistic neural network classifier and the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.

Results

The findings from the feature importance highlight the crucial role of the GLCM texture features extracted from the hippocampus and entorhinal cortex, demonstrating their superior performance compared to the volume and SUVR. GLCM texture AD classification achieved approximately 90% sensitivity in identifying MCIc cases while maintaining low false positives (below 30%) when fused with other features. Moreover, the receiver operating characteristic curves validate the GLCMs' superior performance in distinguishing between MCIs and MCIc. Additionally, fusing different types of features improved classification performance compared to relying solely on any single feature category.

Conclusion

Our study emphasizes the pivotal role of GLCM texture features in early Alzheimer's detection.

Alterations in Gray Matter Structural Networks in Amnestic Mild Cognitive Impairment: A Source-Based Morphometry Study

Background

Amnestic mild cognitive impairment (aMCI), considered as the prodromal stage of Alzheimer's disease, is characterized by isolated memory impairment and cerebral gray matter volume (GMV) alterations. Previous structural MRI studies in aMCI have been mainly based on univariate statistics using voxel-based morphometry.

Objective

We investigated structural network differences between aMCI patients and cognitively normal older adults by using source-based morphometry, a multivariate approach that considers the relationship between voxels of various parts of the brain.

Methods

Ninety-one aMCI patients and 80 cognitively normal controls underwent structural MRI and neuropsychological assessment. Spatially independent components (ICs) that covaried between participants were estimated and a multivariate analysis of covariance was performed with ICs as dependent variables, diagnosis as independent variable, and age, sex, education level, and site as covariates.

Results

aMCI patients exhibited reduced GMV in the precentral, temporo-cerebellar, frontal, and temporal network, and increased GMV in the left superior parietal network compared to controls (pFWER < 0.05, Holm-Bonferroni correction). Moreover, we found that diagnosis, more specifically aMCI, moderated the positive relationship between occipital network and Mini-Mental State Examination scores (pFWER < 0.05, Holm-Bonferroni correction).

Conclusions

Our results showed GMV alterations in temporo-fronto-parieto-cerebellar networks in aMCI, extending previous results obtained with univariate approaches.

Relationship between hippocampal subfield volumes and cognitive decline in healthy subjects

We examined the relationship between hippocampal subfield volumes and cognitive decline over a 4-year period in a healthy older adult population with the goal of identifying subjects at risk of progressive cognitive impairment which could potentially guide therapeutic interventions and monitoring. 482 subjects (68.1 years +/- 7.4; 52.9% female) from the Irish Longitudinal Study on Ageing underwent magnetic resonance brain imaging and a series of cognitive tests. Using K-means longitudinal clustering, subjects were first grouped into three separate global and domain-specific cognitive function trajectories; High-Stable, Mid-Stable and Low-Declining. Linear mixed effects models were then used to establish associations between hippocampal subfield volumes and cognitive groups. Decline in multiple hippocampal subfields was associated with global cognitive decline, specifically the presubiculum (estimate -0.20; 95% confidence interval (CI) -0.78 - -0.02; p = 0.03), subiculum (-0.44; -0.82 - -0.06; p = 0.02), CA1 (-0.34; -0.78 - -0.02; p = 0.04), CA4 (-0.55; -0.93 - -0.17; p = 0.005), molecular layer (-0.49; -0.87 - -0.11; p = 0.01), dentate gyrus (-0.57; -0.94 - -0.19; p = 0.003), hippocampal tail (-0.53; -0.91 - -0.15; p = 0.006) and HATA (-0.41; -0.79 - -0.03; p = 0.04), with smaller volumes for the Low-Declining cognition group compared to the High-Stable cognition group. In contrast to global cognitive decline, when specifically assessing the memory domain, cornu ammonis 1 subfield was not found to be associated with low declining cognition (-0.14; -0.37 - 0.10; p = 0.26). Previously published data shows that atrophy of specific hippocampal subfields is associated with cognitive decline but our study confirms the same effect in subjects asymptomatic at time of enrolment. This strengthens the predictive value of hippocampal subfield atrophy in risk of cognitive decline and may provide a biomarker for monitoring treatment efficacy.

Class-Balanced Deep Learning with Adaptive Vector Scaling Loss for Dementia Stage Detection

Alzheimer's disease (AD) leads to irreversible cognitive decline, with Mild Cognitive Impairment (MCI) as its prodromal stage. Early detection of AD and related dementia is crucial for timely treatment and slowing disease progression. However, classifying cognitive normal (CN), MCI, and AD subjects using machine learning models faces class imbalance, necessitating the use of balanced accuracy as a suitable metric. To enhance model performance and balanced accuracy, we introduce a novel method called VS-Opt-Net. This approach incorporates the recently developed vector-scaling (VS) loss into a machine learning pipeline named STREAMLINE. Moreover, it employs Bayesian optimization for hyperparameter learning of both the model and loss function. VS-Opt-Net not only amplifies the contribution of minority examples in proportion to the imbalance level but also addresses the challenge of generalization in training deep networks. In our empirical study, we use MRI-based brain regional measurements as features to conduct the CN vs MCI and AD vs MCI binary classifications. We compare the balanced accuracy of our model with other machine learning models and deep neural network loss functions that also employ class-balanced strategies. Our findings demonstrate that after hyperparameter optimization, the deep neural network using the VS loss function substantially improves balanced accuracy. It also surpasses other models in performance on the AD dataset. Moreover, our feature importance analysis highlights VS-Opt-Net's ability to elucidate biomarker differences across dementia stages.

Evaluation of MRI-based machine learning approaches for computer-aided diagnosis of dementia in a clinical data warehouse

A variety of algorithms have been proposed for computer-aided diagnosis of dementia from anatomical brain MRI. These approaches achieve high accuracy when applied to research data sets but their performance on real-life clinical routine data has not been evaluated yet. The aim of this work was to study the performance of such approaches on clinical routine data, based on a hospital data warehouse, and to compare the results to those obtained on a research data set. The clinical data set was extracted from the hospital data warehouse of the Greater Paris area, which includes 39 different hospitals. The research set was composed of data from the Alzheimer's Disease Neuroimaging Initiative data set. In the clinical set, the population of interest was identified by exploiting the diagnostic codes from the 10th revision of the International Classification of Diseases that are assigned to each patient. We studied how the imbalance of the training sets, in terms of contrast agent injection and image quality, may bias the results. We demonstrated that computer-aided diagnosis performance was strongly biased upwards (over 17 percent points of balanced accuracy) by the confounders of image quality and contrast agent injection, a phenomenon known as the Clever Hans effect or shortcut learning. When these biases were removed, the performance was very poor. In any case, the performance was considerably lower than on the research data set. Our study highlights that there are still considerable challenges for translating dementia computer-aided diagnosis systems to clinical routine.

Metacognitive Strategy Training Improves Decision-Making Abilities in Amnestic Mild Cognitive Impairment

Mild cognitive impairment (MCI) is associated with deficits in decision-making, which is of utmost importance for daily functioning. Despite evidence of declined decision-making abilities, research on decision-making interventions for MCI is scarce. As metacognition seems to play an important role in decision-making, the present study's aim was to examine whether a metacognitive strategy training can improve MCI patients' decision-making abilities. Older adults-patients of a day care center, diagnosed with amnestic MCI (n = 55) were randomly allocated in two groups, which were matched in gender, age and educational level. Τhe experimental group (n = 27, 18 women, mean age = 70.63, mean years of education = 13.44) received the metacognitive strategy training in parallel with the cognitive and physical training programs of the day care center, and the active control group (n = 28, 21 women, mean age = 70.86, mean years of education = 13.71) received only the cognitive and physical training of the center. The metacognitive strategy training included three online meeting sessions that took place once per week. The basis of the intervention was using analytical thinking, by answering four metacognitive-strategic questions, to make decisions about everyday situations. To examine the efficacy of the training, the ability to make decisions about everyday decision-making situations and the ability to apply decision rules were measured. Both groups participated in a pre-test session and a post-test session, while the experimental group also participated in a follow-up session, one month after the post-test session. The results showed that the experimental group improved its ability to decide, based on analytical thinking, about economic and healthcare-related everyday decision-making situations after they received the metacognitive strategy training. This improvement was maintained one month later. However, the ability to apply decision rules, which requires high cognitive effort, did not improve. In conclusion, it is important that some aspects of the analytical decision-making ability of amnestic MCI patients were improved due to the present metacognitive intervention.

Genetic algorithms based optimized hybrid deep learning model for explainable Alzheimer's prediction based on temporal multimodal cognitive data.. [DOI: 10.21203/rs.3.rs-3250006/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Alzheimer's Disease (AD) is an irreversible neurodegenerative disease. Its early detection is crucial to stop disease progression at an early stage. Most deep learning (DL) literature focused on neuroimage analysis. However, there is no noticed effect of these studies in the real environment. Model's robustness, cost, and interpretability are considered the main reasons for these limitations. The medical intuition of physicians is to evaluate the clinical biomarkers of patients then test their neuroimages. Cognitive scores provide an medically acceptable and cost-effective alternative for the neuroimages to predict AD progression. Each score is calculated from a collection of sub-scores which provide a deeper insight about patient conditions. No study in the literature have explored the role of these multimodal time series sub-scores to predict AD progression. We propose a hybrid CNN-LSTM DL model for predicting AD progression based on the fusion of four longitudinal cognitive sub-scores modalities. Bayesian optimizer has been used to select the best DL architecture. A genetic algorithms based feature selection optimization step has been added to the pipeline to select the best features from extracted deep representations of CNN-LSTM. The SoftMax classifier has been replaced by a robust and optimized random forest classifier. Extensive experiments using the ADNI dataset investigated the role of each optimization step, and the proposed model achieved the best results compared to other DL and classical machine learning models. The resulting model is robust, but it is a black box and it is difficult to understand the logic behind its decisions. Trustworthy AI models must be robust and explainable. We used SHAP and LIME to provide explainability features for the proposed model. The resulting trustworthy model has a great potential to be used to provide decision support in the real environments.

Learn-Explain-Reinforce: Counterfactual Reasoning and its Guidance to Reinforce an Alzheimer's Disease Diagnosis Model

Existing studies on disease diagnostic models focus either on diagnostic model learning for performance improvement or on the visual explanation of a trained diagnostic model. We propose a novel learn-explain-reinforce (LEAR) framework that unifies diagnostic model learning, visual explanation generation (explanation unit), and trained diagnostic model reinforcement (reinforcement unit) guided by the visual explanation. For the visual explanation, we generate a counterfactual map that transforms an input sample to be identified as an intended target label. For example, a counterfactual map can localize hypothetical abnormalities within a normal brain image that may cause it to be diagnosed with Alzheimer's disease (AD). We believe that the generated counterfactual maps represent data-driven knowledge about a target task, i.e., AD diagnosis using structural MRI, which can be a vital source of information to reinforce the generalization of the trained diagnostic model. To this end, we devise an attention-based feature refinement module with the guidance of the counterfactual maps. The explanation and reinforcement units are reciprocal and can be operated iteratively. Our proposed approach was validated via qualitative and quantitative analysis on the ADNI dataset. Its comprehensibility and fidelity were demonstrated through ablation studies and comparisons with existing methods.

Predicting Alzheimer's Disease and Quantifying Asymmetric Degeneration of the Hippocampus Using Deep Learning of Magnetic Resonance Imaging Data

In order to quantify lateral asymmetric degeneration of the hippocampus for early predicting Alzheimer's disease (AD), we develop a deep learning (DL) model to learn informative features from the hippocampal magnetic resonance imaging (MRI) data for predicting AD conversion in a time-to-event prediction modeling framework. The DL model is trained on unilateral hippocampal data with an autoencoder based regularizer, facilitating quantification of lateral asymmetry in the hippocampal prediction power of AD conversion and identification of the optimal strategy to integrate the bilateral hippocampal MRI data for predicting AD. Experimental results on MRI scans of 1307 subjects (817 for training and 490 for validation) have demonstrated that the left hippocampus can better predict AD than the right hippocampus, and an integration of the bilateral hippocampal data with the instance based DL method improved AD prediction, compared with alternative predictive modeling strategies.

Two Routes to Alzheimer's Disease Based on Differential Structural Changes in Key Brain Regions

BACKGROUND

Alzheimer's disease (AD) is a neurodegenerative disorder with homogenous disease patterns. Neuropathological changes precede symptoms by up to two decades making neuroimaging biomarkers a prime candidate for early diagnosis, prognosis, and patient stratification.

OBJECTIVE

The goal of the study was to discern intermediate AD stages and their precursors based on neuroanatomical features for stratifying patients on their progression through different stages.

METHODS

Data include grey matter features from 14 brain regions extracted from longitudinal structural MRI and cognitive data obtained from 1,017 healthy controls and AD patients of ADNI. AD progression was modeled with a Hidden Markov Model, whose hidden states signify disease stages derived from the neuroanatomical data. To tie the progression in brain atrophy to a behavioral marker, we analyzed the ADAS-cog sub-scores in the stages.

RESULTS

The optimal model consists of eight states with differentiable neuroanatomical features, forming two routes crossing once at a very early point and merging at the final state. The cortical route is characterized by early and sustained atrophy in cortical regions. The limbic route is characterized by early decrease in limbic regions. Cognitive differences between the two routes are most noticeable in the memory domain with subjects from the limbic route experiencing stronger memory impairments.

CONCLUSION

Our findings corroborate that more than one pattern of grey matter deterioration with several discernable stages can be identified in the progression of AD. These neuroanatomical subtypes are behaviorally meaningful and provide a door into early diagnosis of AD and prognosis of the disease's progression.

A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images

Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (N_rmC) but, it still requires a lot of work to be done for MCI/ N_rmC and MCI/AD, which would help in detecting AD at its early stage.

Gray Matter Volume as Evidence for Cognitive Reserve in Bilinguals With Mild Cognitive Impairment

BACKGROUND

Compared with monolinguals, bilinguals have a later onset of mild cognitive impairment (MCI) and Alzheimer disease symptoms and greater neuropathology at similar cognitive and clinical levels. The present study follows a previous report showing the faster conversion from MCI to Alzheimer disease for bilingual patients than comparable monolinguals, as predicted by a cognitive reserve (CR).

PURPOSE

Identify whether the increased CR found for bilinguals in the previous study was accompanied by greater gray matter (GM) atrophy than was present for the monolinguals.

METHODS

A novel deep-learning technique based on convolutional neural networks was used to enhance clinical scans into 1 mm MPRAGEs and analyze the GM volume at the time of MCI diagnosis in the earlier study.

PATIENTS

Twenty-four bilingual and 24 monolingual patients were diagnosed with MCI at a hospital memory clinic.

RESULTS

Bilingual patients had more GM loss than monolingual patients in areas related to language processing, attention, decision-making, motor function, and episodic memory retrieval. Bilingualism and age were the strongest predictors of atrophy after other variables such as immigration and education were included in a multivariate model.

DISCUSSION

CR from bilingualism is evident in the initial stages of neurodegeneration after MCI has been diagnosed.

Generalizable deep learning model for early Alzheimer's disease detection from structural MRIs

Early diagnosis of Alzheimer's disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer's disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer's dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer's disease dementia by the model were faster to progress to dementia over time. An analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.

Voting Ensemble Approach for Enhancing Alzheimer's Disease Classification

Alzheimer's disease is dementia that impairs one's thinking, behavior, and memory. It starts as a moderate condition affecting areas of the brain that make it challenging to retain recently learned information, causes mood swings, and causes confusion regarding occasions, times, and locations. The most prevalent type of dementia, called Alzheimer's disease (AD), causes memory-related problems in patients. A precise medical diagnosis that correctly classifies AD patients results in better treatment. Currently, the most commonly used classification techniques extract features from longitudinal MRI data before creating a single classifier that performs classification. However, it is difficult to train a reliable classifier to achieve acceptable classification performance due to limited sample size and noise in longitudinal MRI data. Instead of creating a single classifier, we propose an ensemble voting method that generates multiple individual classifier predictions and then combines them to develop a more accurate and reliable classifier. The ensemble voting classifier model performs better in the Open Access Series of Imaging Studies (OASIS) dataset for older adults than existing methods in important assessment criteria such as accuracy, sensitivity, specificity, and AUC. For the binary classification of with dementia and no dementia, an accuracy of 96.4% and an AUC of 97.2% is attained.

Multimodal neuroimage data fusion based on multikernel learning in personalized medicine

Neuroimaging has been widely used as a diagnostic technique for brain diseases. With the development of artificial intelligence, neuroimaging analysis using intelligent algorithms can capture more image feature patterns than artificial experience-based diagnosis. However, using only single neuroimaging techniques, e.g., magnetic resonance imaging, may omit some significant patterns that may have high relevance to the clinical target. Therefore, so far, combining different types of neuroimaging techniques that provide multimodal data for joint diagnosis has received extensive attention and research in the area of personalized medicine. In this study, based on the regularized label relaxation linear regression model, we propose a multikernel version for multimodal data fusion. The proposed method inherits the merits of the regularized label relaxation linear regression model and also has its own superiority. It can explore complementary patterns across different modal data and pay more attention to the modal data that have more significant patterns. In the experimental study, the proposed method is evaluated in the scenario of Alzheimer’s disease diagnosis. The promising performance indicates that the performance of multimodality fusion via multikernel learning is better than that of single modality. Moreover, the decreased square difference between training and testing performance indicates that overfitting is reduced and hence the generalization ability is improved.

Self- and Partner-Reported Subjective Memory Complaints: Association with Objective Cognitive Impairment and Risk of Decline

Background

Episodic memory decline is a hallmark of Alzheimer's disease (AD). Subjective memory complaints (SMCs) may represent one of the earliest signs of impending cognitive decline. The degree to which self- or partner-reported SMCs predict cognitive change remains unclear.

Objective

We aimed to evaluate the relationship between self- and partner-reported SMCs, objective cognitive performance, AD biomarkers, and risk of future decline in a well-characterized longitudinal memory center cohort. We also evaluated whether study partner characteristics influence reports of SMCs.

Methods

758 participants and 690 study partners were recruited from the Penn Alzheimer's Disease Research Center Clinical Core. Participants included those with Normal Cognition, Mild Cognitive Impairment, and AD. SMCs were measured using the Prospective and Retrospective Memory Questionnaire (PRMQ), and were evaluated for their association with cognition, genetic, plasma, and neuroimaging biomarkers of AD, cognitive and functional decline, and diagnostic progression over an average of four years.

Results

We found that partner-reported SMCs were more consistent with cognitive test performance and increasing symptom severity than self-reported SMCs. Partner-reported SMCs showed stronger correlations with AD-associated brain atrophy, plasma biomarkers of neurodegeneration, and longitudinal cognitive and functional decline. A 10-point increase on baseline PRMQ increased the annual risk of diagnostic progression by approximately 70%. Study partner demographics and relationship to participants influenced reports of SMCs in AD participants only.

Conclusion

Partner-reported SMCs, using the PRMQ, have a stronger relationship with the neuroanatomic and cognitive changes associated with AD than patient-reported SMCs. Further work is needed to evaluate whether SMCs could be used to screen for future decline.

The Correlation Between White Matter Hyperintensity Burden and Regional Brain Volumetry in Patients With Alzheimer's Disease

Background

White matter hyperintensities (WMHs) and regional brain lobe atrophy coexist in the brain of patients with Alzheimer's disease (AD), but the association between them in patients with AD still lacks comprehensive investigation and solid imaging data support.

Objective

We explored whether WMHs can promote the pathological process of AD by aggravating atrophy in specific brain regions and tried to explain the regional specificity of these relationships.

Methods

A sample of 240 adults including 180 normal controls (NCs) and 80 cases with AD were drawn from the ADNI database. T1-weighted magnetic resonance imaging (MRI) and T2-weighted fluid-attenuated MRI of the participants were downloaded and were analyzed using AccuBrain^® to generate the quantitative ratio of WMHs (WMHr, WMH volumes corrected by intracranial volume) and regional brain atrophy. We also divided WMHr into periventricular WMHr (PVWMHr) and deep WMHr (DWMHr) for the purpose of this study. The Cholinergic Pathways Hyperintensities Scale (CHIPS) scores were conducted by two evaluators. Independent t-test, Mann–Whitney U test, or χ² test were used to compare the demographic characteristics, and Spearman correlation coefficient values were used to determine the association between WMHs and different regions of brain atrophy.

Results

Positive association between WMHr and quantitative medial temporal lobe atrophy (QMTA) (r_s = 0.281, p = 0.011), temporal lobe atrophy (r_s = 0.285, p = 0.011), and insular atrophy (r_s = 0.406, p < 0.001) was found in the AD group before Bonferroni correction. PVWMHr contributed to these correlations. By separately analyzing the relationship between PVWMHr and brain atrophy, we found that there were still positive correlations after correction in QMTA (r_s = 0.325, p = 0.003), temporal lobe atrophy (r_s = 0.298, p = 0.007), and insular atrophy (r_s = 0.429, p < 0.001) in AD group.

Conclusion

WMH severity tends to be associated with regional brain atrophy in patients with AD, especially with medial temporal lobe, temporal lobe, and insular lobe atrophy. PVWMHs were devoted to these correlations.

A Multi-Modal and Multi-Atlas Integrated Framework for Identification of Mild Cognitive Impairment

BACKGROUND

Multi-modal neuroimaging with appropriate atlas is vital for effectively differentiating mild cognitive impairment (MCI) from healthy controls (HC).

METHODS

The resting-state functional magnetic resonance imaging (rs-fMRI) and structural MRI (sMRI) of 69 MCI patients and 61 HC subjects were collected. Then, the gray matter volumes obtained from the sMRI and Hurst exponent (HE) values calculated from rs-fMRI data in the Automated Anatomical Labeling (AAL-90), Brainnetome (BN-246), Harvard-Oxford (HOA-112) and AAL3-170 atlases were extracted, respectively. Next, these characteristics were selected with a minimal redundancy maximal relevance algorithm and a sequential feature collection method in single or multi-modalities, and only the optimal features were retained after this procedure. Lastly, the retained characteristics were served as the input features for the support vector machine (SVM)-based method to classify MCI patients, and the performance was estimated with a leave-one-out cross-validation (LOOCV).

RESULTS

Our proposed method obtained the best 92.00% accuracy, 94.92% specificity and 89.39% sensitivity with the sMRI in AAL-90 and the fMRI in HOA-112 atlas, which was much better than using the single-modal or single-atlas features.

CONCLUSION

The results demonstrated that the multi-modal and multi-atlas integrated method could effectively recognize MCI patients, which could be extended into various neurological and neuropsychiatric diseases.

Extracting ROI-Based Contourlet Subband Energy Feature From the sMRI Image for Alzheimer's Disease Classification

Structural magnetic resonance imaging (sMRI)-based Alzheimer's disease (AD) classification and its prodromal stage-mild cognitive impairment (MCI) classification have attracted many attentions and been widely investigated in recent years. Owing to the high dimensionality, representation of the sMRI image becomes a difficult issue in AD classification. Furthermore, regions of interest (ROI) reflected in the sMRI image are not characterized properly by spatial analysis techniques, which has been a main cause of weakening the discriminating ability of the extracted spatial feature. In this study, we propose a ROI-based contourlet subband energy (ROICSE) feature to represent the sMRI image in the frequency domain for AD classification. Specifically, a preprocessed sMRI image is first segmented into 90 ROIs by a constructed brain mask. Instead of extracting features from the 90 ROIs in the spatial domain, the contourlet transform is performed on each of these ROIs to obtain their energy subbands. And then for an ROI, a subband energy (SE) feature vector is constructed to capture its energy distribution and contour information. Afterwards, SE feature vectors of the 90 ROIs are concatenated to form a ROICSE feature of the sMRI image. Finally, support vector machine (SVM) classifier is used to classify 880 subjects from ADNI and OASIS databases. Experimental results show that the ROICSE approach outperforms six other state-of-the-art methods, demonstrating that energy and contour information of the ROI are important to capture differences between the sMRI images of AD and HC subjects. Meanwhile, brain regions related to AD can also be found using the ROICSE feature, indicating that the ROICSE feature can be a promising assistant imaging marker for the AD diagnosis via the sMRI image. Code and Sample IDs of this paper can be downloaded at https://github.com/NWPU-903PR/ROICSE.git.

Classification of Alzheimer's disease progression based on sMRI using gray matter volume and lateralization index

Note that identifying Mild Cognitive Impairment (MCI) is crucial to early detection and diagnosis of Alzheimer's disease (AD). This work explores how classification features and experimental algorithms influence classification performances on the ADNI database. Based on structural Magnetic Resonance Images (sMRI), two features including gray matter (GM) volume and lateralization index (LI) are firstly extracted through hypothesis testing. Afterward, several classifier algorithms including Random Forest (RF), Decision Tree (DT), K-Nearest Neighbor(KNN) and Support Vector Machine (SVM) with RBF kernel, Linear kernel or Polynomial kernel are established to realize binary classification among Normal Control (NC), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI) and AD groups. The main experimental results are as follows. (1) The classification performance in the feature of LI is poor compared with those in the feature of GM volume or the combined feature of LI and GM volume, i.e., the classification accuracies in the feature of LI are relatively low and unstable for most classifier models and subject groups. (2) Comparing with the classification performances in the feature of GM volume and the combined feature of LI and GM volume, the classification accuracy of NC group versus AD group is relatively stable for different classifier models, moreover, the accuracy of AD group versus NC group is almost the highest, with the most classification accuracy of 98.0909%. (3) For different subject groups, the SVM classifier algorithm with Polynomial kernel and the KNN classifier algorithm show relatively stable and high classification accuracy, while DT classifier algorithm shows relatively unstable and lower classification accuracy. (4) Except the groups of EMCI versus LMCI and NC versus EMCI, the classification accuracies are significantly enhanced by emerging the LI into the original feature of GM volume, with the maximum accuracy increase of 5.6364%. These results indicate that various factors of subject data, feature types and experimental algorithms influence classification performances remarkably, especially the newly introduced feature of LI into the feature of GM volume is helpful to improve classification results in some certain extent.

Modeling Brain Volume Using Deep Learning-Based Physical Activity Features in Patients With Dementia

There is a proven correlation between the severity of dementia and reduced brain volumes. Several studies have attempted to use activity data to estimate brain volume as a means of detecting reduction early; however, raw activity data are not directly interpretable and are unstructured, making them challenging to utilize. Furthermore, in the previous research, brain volume estimates were limited to total brain volume and the investigators were unable to detect reductions in specific regions of the brain that are typically used to characterize disease progression. We aimed to evaluate volume prediction of 116 brain regions through activity data obtained combining time-frequency domain- and unsupervised deep learning-based feature extraction methods. We developed a feature extraction model based on unsupervised deep learning using activity data from the National Health and Nutrition Examination Survey (NHANES) dataset (n = 14,482). Then, we applied the model and the time-frequency domain feature extraction method to the activity data of the Biobank Innovations for chronic Cerebrovascular disease With ALZheimer's disease Study (BICWALZS) datasets (n = 177) to extract activity features. Brain volumes were calculated from the brain magnetic resonance imaging of the BICWALZS dataset and anatomically subdivided into 116 regions. Finally, we fitted linear regression models to estimate each regional volume of the 116 brain areas based on the extracted activity features. Regression models were statistically significant for each region, with an average correlation coefficient of 0.990 ± 0.006. In all brain regions, the correlation was > 0.964. Particularly, regions of the temporal lobe that exhibit characteristic atrophy in the early stages of Alzheimer's disease showed the highest correlation (0.995). Through a combined deep learning-time-frequency domain feature extraction method, we could extract activity features based solely on the activity dataset, without including clinical variables. The findings of this study indicate the possibility of using activity data for the detection of neurological disorders such as Alzheimer's disease.

A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images

Early diagnosis of Alzheimers disease and its prodromal stage, also known as mild cognitive impairment (MCI), is critical since some patients with progressive MCI will develop the disease. We propose a multi-stream deep convolutional neural network fed with patch-based imaging data to classify stable MCI and progressive MCI. First, we compare MRI images of Alzheimers disease with cognitively normal subjects to identify distinct anatomical landmarks using a multivariate statistical test. These landmarks are then used to extract patches that are fed into the proposed multi-stream convolutional neural network to classify MRI images. Next, we train the architecture in a separate scenario using samples from Alzheimers disease images, which are anatomically similar to the progressive MCI ones and cognitively normal images to compensate for the lack of progressive MCI training data. Finally, we transfer the trained model weights to the proposed architecture in order to fine-tune the model using progressive MCI and stable MCI data. Experimental results on the ADNI-1 dataset indicate that our method outperforms existing methods for MCI classification, with an F1-score of 85.96%.

Corpus Callosum Atrophy in Detection of Mild and Moderate Alzheimer's Disease Using Brain Magnetic Resonance Image Processing and Machine Learning Techniques

Background:

The total number of people with dementia is projected to reach 82 million in 2030 and 152 in 2050. Early and accurate identification of the underlying causes of dementia, such as Alzheimer’s disease (AD) is of utmost importance. A large body of research has shown that imaging techniques are most promising technologies to improve subclinical and early diagnosis of dementia. Morphological changes, especially atrophy in various structures like cingulate gyri, caudate nucleus, hippocampus, frontotemporal lobe, etc., have been established as markers for AD. Being the largest white matter structure with a high demand of blood supply from several main arterial systems, anatomical alterations of the corpus callosum (CC) may serve as potential indication neurodegenerative disease.

Objective:

To detect mild and moderate AD using brain magnetic resonance image (MRI) processing and machine learning techniques.

Methods:

We have performed automatic detection and segmentation of the CC and calculated its morphological features to feed into a multivariate pattern analysis using support vector machine (SVM) learning techniques.

Results:

Our results using large patients’ cohort show CC atrophy-based features are capable of distinguishing healthy and mild/moderate AD patients. Our classifiers obtain more than 90%sensitivity and specificity in differentiating demented patients from healthy cohorts and importantly, achieved more than 90%sensitivity and > 80%specificity in detecting mild AD patients.

Conclusion:

Results from this analysis are encouraging and advocate development of an image analysis software package to detect dementia from brain MRI using morphological alterations of the CC.

Leveraging machine learning predictive biomarkers to augment the statistical power of clinical trials with baseline magnetic resonance imaging

A key factor in designing randomized clinical trials is the sample size required to achieve a particular level of power to detect the benefit of a treatment. Sample size calculations depend upon the expected benefits of a treatment (effect size), the accuracy of measurement of the primary outcome, and the level of power specified by the investigators. In this study, we show that radiomic models, which leverage complex brain MRI patterns and machine learning, can be utilized in clinical trials with protocols that incorporate baseline MR imaging to significantly increase statistical power to detect treatment effects. Akin to the historical control paradigm, we propose to utilize a radiomic prediction model to generate a pseudo-control sample for each individual in the trial of interest. Because the variability of expected outcome across patients can mask our ability to detect treatment effects, we can increase the power to detect a treatment effect in a clinical trial by reducing that variability through using radiomic predictors as surrogates. We illustrate this method with simulations based on data from two cohorts in different neurologic diseases, Alzheimer's disease and glioblastoma multiforme. We present sample size requirements across a range of effect sizes using conventional analysis and models that include a radiomic predictor. For our Alzheimer's disease cohort, at an effect size of 0.35, total sample size requirements for 80% power declined from 246 to 212 for the endpoint cognitive decline. For our glioblastoma multiforme cohort, at an effect size of 1.65 with the endpoint survival time, total sample size requirements declined from 128 to 74. This methodology can decrease the required sample sizes by as much as 50%, depending on the strength of the radiomic predictor. The power of this method grows with increased accuracy of radiomic prediction, and furthermore, this method is most helpful when treatment effect sizes are small. Neuroimaging biomarkers are a powerful and increasingly common suite of tools that are, in many cases, highly predictive of disease outcomes. Here, we explore the possibility of using MRI-based radiomic biomarkers for the purpose of improving statistical power in clinical trials in the contexts of brain cancer and prodromal Alzheimer's disease. These methods can be applied to a broad range of neurologic diseases using a broad range of predictors of outcome to make clinical trials more efficient.

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

BACKGROUND

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

METHODS

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

RESULTS

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

CONCLUSIONS

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

Biomarker Extraction Based on Subspace Learning for the Prediction of Mild Cognitive Impairment Conversion

Accurate recognition of progressive mild cognitive impairment (MCI) is helpful to reduce the risk of developing Alzheimer's disease (AD). However, it is still challenging to extract effective biomarkers from multivariate brain structural magnetic resonance imaging (MRI) features to accurately differentiate the progressive MCI from stable MCI. We develop novel biomarkers by combining subspace learning methods with the information of AD as well as normal control (NC) subjects for the prediction of MCI conversion using multivariate structural MRI data. Specifically, we first learn two projection matrices to map multivariate structural MRI data into a common label subspace for AD and NC subjects, where the original data structure and the one-to-one correspondence between multiple variables are kept as much as possible. Afterwards, the multivariate structural MRI features of MCI subjects are mapped into a common subspace according to the projection matrices. We then perform the self-weighted operation and weighted fusion on the features in common subspace to extract the novel biomarkers for MCI subjects. The proposed biomarkers are tested on Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Experimental results indicate that our proposed biomarkers outperform the competing biomarkers on the discrimination between progressive MCI and stable MCI. And the improvement from the proposed biomarkers is not limited to a particular classifier. Moreover, the results also confirm that the information of AD and NC subjects is conducive to predicting conversion from MCI to AD. In conclusion, we find a good representation of brain features from high-dimensional MRI data, which exhibits promising performance for predicting conversion from MCI to AD.

Predicting MCI to AD Conversation Using Integrated sMRI and rs-fMRI: Machine Learning and Graph Theory Approach

BACKGROUND

Graph theory and machine learning have been shown to be effective ways of classifying different stages of Alzheimer's disease (AD). Most previous studies have only focused on inter-subject classification with single-mode neuroimaging data. However, whether this classification can truly reflect the changes in the structure and function of the brain region in disease progression remains unverified. In the current study, we aimed to evaluate the classification framework, which combines structural Magnetic Resonance Imaging (sMRI) and resting-state functional Magnetic Resonance Imaging (rs-fMRI) metrics, to distinguish mild cognitive impairment non-converters (MCInc)/AD from MCI converters (MCIc) by using graph theory and machine learning.

METHODS

With the intra-subject (MCInc vs. MCIc) and inter-subject (MCIc vs. AD) design, we employed cortical thickness features, structural brain network features, and sub-frequency (full-band, slow-4, slow-5) functional brain network features for classification. Three feature selection methods [random subset feature selection algorithm (RSFS), minimal redundancy maximal relevance (mRMR), and sparse linear regression feature selection algorithm based on stationary selection (SS-LR)] were used respectively to select discriminative features in the iterative combinations of MRI and network measures. Then support vector machine (SVM) classifier with nested cross-validation was employed for classification. We also compared the performance of multiple classifiers (Random Forest, K-nearest neighbor, Adaboost, SVM) and verified the reliability of our results by upsampling.

RESULTS

We found that in the classifications of MCIc vs. MCInc, and MCIc vs. AD, the proposed RSFS algorithm achieved the best accuracies (84.71, 89.80%) than the other algorithms. And the high-sensitivity brain regions found with the two classification groups were inconsistent. Specifically, in MCIc vs. MCInc, the high-sensitivity brain regions associated with both structural and functional features included frontal, temporal, caudate, entorhinal, parahippocampal, and calcarine fissure and surrounding cortex. While in MCIc vs. AD, the high-sensitivity brain regions associated only with functional features included frontal, temporal, thalamus, olfactory, and angular.

CONCLUSIONS

These results suggest that our proposed method could effectively predict the conversion of MCI to AD, and the inconsistency of specific brain regions provides a novel insight for clinical AD diagnosis.

Advances in computerized MRI‐based biomarkers in Alzheimer’s disease

The use of neuroimaging examinations is crucial in Alzheimer’s disease (AD), in both research and clinical settings. Over the years, magnetic resonance imaging (MRI)–based computer‐aided diagnosis has been shown to be helpful for early screening and predicting cognitive decline. Meanwhile, an increasing number of studies have adopted machine learning for the classification of AD, with promising results. In this review article, we focus on computerized MRI‐based biomarkers of AD by reviewing representative studies that used computerized techniques to identify AD patients and predict cognitive progression. We categorized these studies based on the following applications: (1) identifying AD from normal control; (2) identifying AD from other dementia types, including vascular dementia, dementia with Lewy bodies, and frontotemporal dementia; and (3) predicting conversion from NC to mild cognitive impairment (MCI) and from MCI to AD. This systematic review could act as a state‐of‐the‐art overview of this emerging field as well as a basis for designing future studies.

Structural volume and cortical thickness differences between males and females in cognitively normal, cognitively impaired and Alzheimer's dementia population

We investigated differences due to sex in brain structural volume and cortical thickness in older cognitively normal (N=742), cognitively impaired (MCI; N=540) and Alzheimer's Dementia (AD; N=402) individuals from the ADNI and AIBL datasets (861 Males and 823 Females). General linear models were used to control the effect of relevant covariates including age, intracranial volume, magnetic resonance imaging (MRI) scanner field strength and scanner types. Significant volumetric differences due to sex were observed within different cortical and subcortical regions of the cognitively normal group. The number of significantly different regions was reduced in the MCI group, and no region remained different in the AD group. Cortical thickness was overall thinner in males than females in the cognitively normal group, and likewise, the differences due to sex were reduced in the MCI and AD groups. These findings were sustained after including cerebrospinal fluid (CSF) Tau and phosphorylated tau (pTau) as additional covariates.

An integrative multivariate approach for predicting functional recovery using magnetic resonance imaging parameters in a translational pig ischemic stroke model

Magnetic resonance imaging (MRI) is a clinically relevant, real-time imaging modality that is frequently utilized to assess stroke type and severity. However, specific MRI biomarkers that can be used to predict long-term functional recovery are still a critical need. Consequently, the present study sought to examine the prognostic value of commonly utilized MRI parameters to predict functional outcomes in a porcine model of ischemic stroke. Stroke was induced via permanent middle cerebral artery occlusion. At 24 hours post-stroke, MRI analysis revealed focal ischemic lesions, decreased diffusivity, hemispheric swelling, and white matter degradation. Functional deficits including behavioral abnormalities in open field and novel object exploration as well as spatiotemporal gait impairments were observed at 4 weeks post-stroke. Gaussian graphical models identified specific MRI outputs and functional recovery variables, including white matter integrity and gait performance, that exhibited strong conditional dependencies. Canonical correlation analysis revealed a prognostic relationship between lesion volume and white matter integrity and novel object exploration and gait performance. Consequently, these analyses may also have the potential of predicting patient recovery at chronic time points as pigs and humans share many anatomical similarities (e.g., white matter composition) that have proven to be critical in ischemic stroke pathophysiology. The study was approved by the University of Georgia (UGA) Institutional Animal Care and Use Committee (IACUC; Protocol Number: A2014-07-021-Y3-A11 and 2018-01-029-Y1-A5) on November 22, 2017.

Exercise Training-Related Changes in Cortical Gray Matter Diffusivity and Cognitive Function in Mild Cognitive Impairment and Healthy Older Adults

Individuals with Mild Cognitive Impairment (MCI) are at an elevated risk of dementia and exhibit deficits in cognition and cortical gray matter (GM) volume, thickness, and microstructure. Meanwhile, exercise training appears to preserve brain function and macrostructure may help delay or prevent the onset of dementia in individuals with MCI. Yet, our understanding of the neurophysiological effects of exercise training in individuals with MCI remains limited. Recent work suggests that the measures of gray matter microstructure using diffusion imaging may be sensitive to early cognitive and neurophysiological changes in the aging brain. Therefore, this study is aimed to determine the effects of exercise training in cognition and cortical gray matter microstructure in individuals with MCI vs. cognitively healthy older adults. Fifteen MCI participants and 17 cognitively intact controls (HC) volunteered for a 12-week supervised walking intervention. Following the intervention, MCI and HC saw improvements in cardiorespiratory fitness, performance on Trial 1 of the Rey Auditory Verbal Learning Test (RAVLT), a measure of verbal memory, and the Controlled Oral Word Association Test (COWAT), a measure of verbal fluency. After controlling for age, a voxel-wise analysis of cortical gray matter diffusivity showed individuals with MCI exhibited greater increases in mean diffusivity (MD) in the left insular cortex than HC. This increase in MD was positively associated with improvements in COWAT performance. Additionally, after controlling for age, the voxel-wise analysis indicated a main effect of Time with both groups experiencing an increase in left insular and left and right cerebellar MD. Increases in left insular diffusivity were similarly found to be positively associated with improvements in COWAT performance in both groups, while increases in cerebellar MD were related to gains in episodic memory performance. These findings suggest that exercise training may be related to improvements in neural circuits that govern verbal fluency performance in older adults through the microstructural remodeling of cortical gray matter. Furthermore, changes in left insular cortex microstructure may be particularly relevant to improvements in verbal fluency among individuals diagnosed with MCI.

Synergistic Effect of Serum Homocysteine and Diabetes Mellitus on Brain Alterations

BACKGROUND

Both elevated blood homocysteine and diabetes mellitus (DM) are related to cognitive impairments or dementia. A previous study also demonstrated that the association between homocysteine and cognitive decline was much stronger in individuals with DM than in those without DM.

OBJECTIVE

This study aimed to examine the interactive effect of blood homocysteine and DM on brain pathological changes including brain atrophy, amyloid-β and tau deposition, and small vessel disease (SVD) related to cognitive impairments.

METHODS

A total of 430 non-demented older adults underwent comprehensive clinical assessment, measurement of serum homocysteine level, [11C] Pittsburgh Compound B (PiB) PET, [18F] AV-1451 PET, and brain MRI.

RESULTS

The interactive effect of homocysteine with the presence of DM on brain atrophy, especially in aging-related brain regions, was significant. Higher homocysteine concentration was associated with more prominent brain atrophy in individuals with DM, but not in those without DM. In contrast, interaction effect of homocysteine and DM was found neither on Alzheimer's disease (AD) pathologies, including amyloid-β and tau deposition, nor white matter hyperintensity volume as a measure of SVD.

CONCLUSION

The present findings suggest that high blood homocysteine level and DM synergistically aggravate brain damage independently of AD and cerebrovascular disease. With regard to preventing dementia or cognitive decline in older adults, these results support the importance of strictly controlling blood glucose in individuals with hyperhomocysteinemia and lowering blood homocysteine level in those with DM.

Decoding with confidence: Statistical control on decoder maps

In brain imaging, decoding is widely used to infer relationships between brain and cognition, or to craft brain-imaging biomarkers of pathologies. Yet, standard decoding procedures do not come with statistical guarantees, and thus do not give confidence bounds to interpret the pattern maps that they produce. Indeed, in whole-brain decoding settings, the number of explanatory variables is much greater than the number of samples, hence classical statistical inference methodology cannot be applied. Specifically, the standard practice that consists in thresholding decoding maps is not a correct inference procedure. We contribute a new statistical-testing framework for this type of inference. To overcome the statistical inefficiency of voxel-level control, we generalize the Family Wise Error Rate (FWER) to account for a spatial tolerance δ, introducing the δ-Family Wise Error Rate (δ-FWER). Then, we present a decoding procedure that can control the δ-FWER: the Ensemble of Clustered Desparsified Lasso (EnCluDL), a procedure for multivariate statistical inference on high-dimensional structured data. We evaluate the statistical properties of EnCluDL with a thorough empirical study, along with three alternative procedures including decoder map thresholding. We show that EnCluDL exhibits the best recovery properties while ensuring the expected statistical control.

Recursive Support Vector Machine Biomarker Selection for Alzheimer's Disease

BACKGROUND

There is a need for more reliable diagnostic tools for the early detection of Alzheimer's disease (AD). This can be a challenge due to a number of factors and logistics making machine learning a viable option.

OBJECTIVE

In this paper, we present on a Support Vector Machine Leave-One-Out Recursive Feature Elimination and Cross Validation (SVM-RFE-LOO) algorithm for use in the early detection of AD and show how the SVM-RFE-LOO method can be used for both classification and prediction of AD.

METHODS

Data were analyzed on n = 300 participants (n = 150 AD; n = 150 cognitively normal controls). Serum samples were assayed via a multi-plex biomarker assay platform using electrochemiluminescence (ECL).

RESULTS

The SVM-RFE-LOO method reduced the number of features in the model from 21 to 16 biomarkers and achieved an area under the curve (AUC) of 0.980 with a sensitivity of 94.0% and a specificity of 93.3%. When the classification and prediction performance of SVM-RFE-LOO was compared to that of SVM and SVM-RFE, we found similar performance across the models; however, the SVM-RFE-LOO method utilized fewer markers.

CONCLUSION

We found that 1) the SVM-RFE-LOO is suitable for analyzing noisy high-throughput proteomic data, 2) it outperforms SVM-RFE in the robustness to noise and in the ability to recover informative features, and 3) it can improve the prediction performance. Our recursive feature elimination model can serve as a general model for biomarker discovery in other diseases.

Low Cerebrospinal Fluid Levels of Hemopexin Are Associated With Increased Alzheimer's Pathology, Hippocampal Hypometabolism, and Cognitive Decline

Brain iron dyshomeostasis is a feature of Alzheimer's disease. Conventionally, research has focused on non-heme iron although degradation of heme from hemoglobin subunits can generate iron to augment the redox-active iron pool. Hemopexin both detoxifies heme to maintain iron homeostasis and bolsters antioxidant capacity via catabolic products, biliverdin and carbon monoxide to combat iron-mediated lipid peroxidation. The aim of the present study was to examine the association of cerebrospinal fluid levels (CSF) hemopexin and hemoglobin subunits (α and β) to Alzheimer's pathological proteins (amyloid and tau), hippocampal volume and metabolism, and cognitive performance. We analyzed baseline CSF heme/iron proteins (multiplexed mass spectrometry-based assay), amyloid and tau (Luminex platform), baseline/longitudinal neuroimaging (MRI, FDG-PET) and cognitive outcomes in 86 cognitively normal, 135 mild-cognitive impairment and 66 Alzheimer's participants from the Alzheimer's Disease Neuroimaging Initiative-1 (ADNI-1) cohort. Multivariate regression analysis was performed to delineate differences in CSF proteins between diagnosis groups and evaluated their association to amyloid and tau, neuroimaging and cognition. A p-value ≤ 0.05 was considered significant. Higher hemopexin was associated with higher CSF amyloid (implying decreased brain amyloid deposition), improved hippocampal metabolism and cognitive performance. Meanwhile, hemoglobin subunits were associated with increased CSF tau (implying increased brain tau deposition). When dichotomizing individuals with mild-cognitive impairment into stable and converters to Alzheimer's disease, significantly higher baseline hemoglobin subunits were observed in the converters compared to non-converters. Heme/iron dyshomeostasis is an early and crucial event in AD pathophysiology, which warrants further investigation as a potential therapeutic target.

Cognitive Processing Speed Is Strongly Related to Driving Skills, Financial Abilities, and Other Instrumental Activities of Daily Living in Persons With Mild Cognitive Impairment and Mild Dementia

BACKGROUND

Cognitive processing speed is important for performing everyday activities in persons with mild cognitive impairment (MCI). However, its role in daily function has not been examined while simultaneously accounting for contributions of Alzheimer's disease (AD) risk biomarkers. We examine the relationships of processing speed and genetic and neuroimaging biomarkers to composites of daily function, mobility, and driving.

METHOD

We used baseline data from 103 participants on the MCI/mild dementia spectrum from the Applying Programs to Preserve Skills trial. Linear regression models examined relationships of processing speed, structural magnetic resonance imaging (MRI), and genetic risk alleles for AD to composites of performance-based instrumental activities of daily living (IADLs), community mobility, and on-road driving evaluations.

RESULTS

In multivariable models, processing speed and the brain MRI neurodegeneration biomarker Spatial Pattern of Abnormality for Recognition of Early Alzheimer's disease (SPARE-AD) were significantly associated with functional and mobility composite performance. Better processing speed and younger age were associated with on-road driving ratings. Genetic risk markers, left hippocampal atrophy, and white matter lesion volumes were not significant correlates of these abilities. Processing speed had a strong positive association with IADL function (p < .001), mobility (p < .001), and driving (p = .002).

CONCLUSIONS

Cognitive processing speed is strongly and consistently associated with critical daily functions in persons with MCI in models including genetic and neuroimaging biomarkers of AD risk. SPARE-AD scores also significantly correlate with IADL performance and mobility. Results highlight the central role of processing speed in everyday task performance among persons with MCI/mild dementia.

Associations between texture of T1-weighted magnetic resonance imaging and radiographic pathologies in Alzheimer's disease

BACKGROUND AND PURPOSE

Texture analysis of magnetic resonance imaging (MRI) brain scans have been proposed as a promising tool in the early diagnosis of Alzheimer's disease (AD), but its biological correlates remain unknown. In this study, we examined the relationship between MRI texture features and AD pathology.

METHODS

The study included 150 participants who had a 3.0T T1-weighted image, amyloid-β positron emission tomography (PET), and tau PET within 3 months of each other. In each of six brain regions (hippocampus, precuneus, and entorhinal, middle temporal, posterior cingulate and superior frontal cortices), linear regression analyses adjusting for age and sex was performed to examine the effects of regional amyloid-β and tau burden on regional texture features. We also compared neuroimaging measures based on pathological severity using ANOVA.

RESULTS

In all regions, tau burden (p < 0.05), but not amyloid-β burden, were associated with a certain texture feature that varied with the region's cytoarchitecture. Specifically, autocorrelation and cluster shade were associated with tau burden in allocortical and periallocortical regions, whereas entropy and contrast were associated with tau burden in neocortical regions. Mean signal intensity of each region did not show any associations with AD pathology. The values of the region-specific textures also varied across groups of varying pathological severity.

CONCLUSIONS

Our results suggest that textures of T1-weighted MRI reflect changes in the brain that are associated with regional tau burden and the local cytoarchitecture. This study provides insight into how MRI texture can be used for detection of microstructural changes in AD.