Quantitative MRI Brain Studies in Mild Cognitive Impairment and Alzheimer's Disease: A Methodological Review

Association of gut microbiota with cerebral cortical thickness: A Mendelian randomization study

BACKGROUND

The causal relationship between gut microbiota and cerebral cortex development remains unclear. We aimed to scrutinize the plausible causal impact of gut microbiota on cortical thickness via Mendelian randomization (MR) study.

METHODS

Genome-wide association study (GWAS) data for 196 gut microbiota phenotypes (N = 18,340) were obtained as exposures, and GWAS data for cortical thickness-related traits (N = 51,665) were selected as outcomes. Inverse variance weighted was used as the main estimate method. A series of sensitivity analyses was used to test the robustness of the estimates including Cochran's Q test, MR-Egger intercept analysis, Steiger filtering, scatter plot funnel plot and leave-one-out analysis.

RESULTS

Genetic prediction of high Bacillales (β = 0.005, P = 0.032) and Lactobacillales (β = 0.010, P = 0.012) abundance was associated with a potential increase in global cortical thickness. For specific functional brain subdivisions, genetically predicted order Lactobacillales would potentially increase the thickness of the fusiform (β = 0.014, P = 0.016) and supramarginal (β = 0.017, P = 0.003). Meanwhile, order Bacillales would increase the thickness of fusiform (β = 0.007, P = 0.039), insula (β = 0.011, P = 0.003), rostralanteriorcingulate (β = 0.014, P = 0.002) and supramarginal (β = 0.006, P = 0.043). No significant estimates of heterogeneity or pleiotropy were found.

CONCLUSIONS

Through MR studies, we discovered genetic prediction of the Lactobacillales and Bacillales orders potentially linked to cortical thickness, affirming gut microbiota may enhance brain structure. Genetically predicted supramarginal and fusiform may be potential targets.

Effects of mixed metal exposures on MRI diffusion features in the medial temporal lobe

Background

Environmental exposure to metal mixtures is common and may be associated with increased risk for neurodegenerative disorders including Alzheimer's disease.

Objective

This study examined associations of mixed metal exposures with medial temporal lobe (MTL) MRI structural metrics and neuropsychological performance.

Methods

Metal exposure history, whole blood metal, and neuropsychological tests were obtained from subjects with/without a history of mixed metal exposure from welding fumes (42 exposed subjects; 31 controls). MTL structures (hippocampus, entorhinal and parahippocampal cortices) were assessed by morphologic (volume, cortical thickness) and diffusion tensor imaging [mean (MD), axial (AD), radial diffusivity (RD), and fractional anisotropy (FA)] metrics. In exposed subjects, correlation, multiple linear, Bayesian kernel machine regression, and mediation analyses were employed to examine effects of single- or mixed-metal predictor(s) and their interactions on MTL structural and neuropsychological metrics; and on the path from metal exposure to neuropsychological consequences.

Results

Compared to controls, exposed subjects had higher blood Cu, Fe, K, Mn, Pb, Se, and Zn levels (p's<0.026) and poorer performance in processing/psychomotor speed, executive, and visuospatial domains (p's<0.046). Exposed subjects displayed higher MD, AD, and RD in all MTL ROIs (p's<0.040) and lower FA in entorhinal and parahippocampal cortices (p's<0.033), but not morphological differences. Long-term mixed-metal exposure history indirectly predicted lower processing speed performance via lower parahippocampal FA (p=0.023). Higher whole blood Mn and Cu predicted higher entorhinal diffusivity (p's<0.043) and lower Delayed Story Recall performance (p=0.007) without overall metal mixture or interaction effects.

Discussion

Mixed metal exposure predicted MTL structural and neuropsychological features that are similar to Alzheimer's disease at-risk populations. These data warrant follow-up as they may illuminate the path for environmental exposure to Alzheimer's disease-related health outcomes.

Structural, static, and dynamic functional MRI predictors for conversion from mild cognitive impairment to Alzheimer's disease: Inter-cohort validation of Shanghai Memory Study and ADNI

Mild cognitive impairment (MCI) is a critical prodromal stage of Alzheimer's disease (AD), and the mechanism underlying the conversion is not fully explored. Construction and inter-cohort validation of imaging biomarkers for predicting MCI conversion is of great challenge at present, due to lack of longitudinal cohorts and poor reproducibility of various study-specific imaging indices. We proposed a novel framework for inter-cohort MCI conversion prediction, involving comparison of structural, static, and dynamic functional brain features from structural magnetic resonance imaging (sMRI) and resting-state functional MRI (fMRI) between MCI converters (MCI_C) and non-converters (MCI_NC), and support vector machine for construction of prediction models. A total of 218 MCI patients with 3-year follow-up outcome were selected from two independent cohorts: Shanghai Memory Study cohort for internal cross-validation, and Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort for external validation. In comparison with MCI_NC, MCI_C were mainly characterized by atrophy, regional hyperactivity and inter-network hypo-connectivity, and dynamic alterations characterized by regional and connectional instability, involving medial temporal lobe (MTL), posterior parietal cortex (PPC), and occipital cortex. All imaging-based prediction models achieved an area under the curve (AUC) > 0.7 in both cohorts, with the multi-modality MRI models as the best with excellent performances of AUC > 0.85. Notably, the combination of static and dynamic fMRI resulted in overall better performance as relative to static or dynamic fMRI solely, supporting the contribution of dynamic features. This inter-cohort validation study provides a new insight into the mechanisms of MCI conversion involving brain dynamics, and paves a way for clinical use of structural and functional MRI biomarkers in future.

Bidirectional Mapping Perception-enhanced Cycle-consistent Generative Adversarial Network for Super-resolution of Brain MRI images

As an effective tool for visualizing neurodegeneration, high-resolution structural magnetism facilitates quantitative image analysis and clinical applications. Super-resolution reconstruction technology allows to improve the resolution of images without upgrading the scanning hardware. However, existing super-resolution techniques relied on paired image data sets and lacked further quantitative analysis of the generated images. In this study, we proposed a semi-supervised generative adversarial network (GAN) model for super-resolution of brain MRI, and the synthetic images were evaluated using various quantitative measures. This model adopted the cycle-consistency structure to allow for a mixture of unpaired data for training. Perceptual loss was further introduced into the model to preserve detailed texture features at high frequencies. 363 subjects with both high-resolution (HR) and low-resolution (LR) scans and 217 subjects with HR scans only were used for model derivation, training, and validation. We extracted multiple voxel-based and surface-based morphological features of the synthetic and real 3D HR images for comparison. We further evaluated the synthetic images in the differential diagnosis of diseases. Our model achieved superior mean absolute error (0.049±0.021), mean squared error (0.0059±0.0043), peak signal-to-noise ratio (29.41±3.71), structural similarity index measure (0.914±0.048). Eight morphological metrics, both voxel-based and surface-based, showed significant agreement (P<0.0001). The gap of accuracy in disease diagnosis between synthetic and real HR images was within 5% and significantly outperformed the LR images. Our proposed model enables the reconstruction of HR MRI and could be used accurately for image quantification.Clinical relevance- Quantitative evaluation of the synthetic high-resolution images was used to determine whether the synthetic images have sufficient realism and diversity.

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

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

A cross-sectional study of explainable machine learning in Alzheimer's disease: diagnostic classification using MR radiomic features

Introduction

Alzheimer's disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD.

Methods

In this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated.

Results

The model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively.

Discussion

These directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.

Predicting Conversion from Subjective Cognitive Decline to Mild Cognitive Impairment and Alzheimer's Disease Dementia Using Ensemble Machine Learning

BACKGROUND

Subjective cognitive decline (SCD) may represent a preclinical stage of Alzheimer's disease (AD). Predicting progression of SCD patients is of great importance in AD-related research but remains a challenge.

OBJECTIVE

To develop and implement an ensemble machine learning (ML) algorithm to identify SCD subjects at risk of conversion to mild cognitive impairment (MCI) or AD.

METHODS

Ninety-nine SCD patients were included. Thirty-two progressed to MCI/AD, while 67 remained stable. To minimize the effect of class imbalance, both classes were balanced, and sensitivity was taken as evaluation metric. Bagging and boosting ML models were developed by using socio-demographic and clinical information, Mini-Mental State Examination and Geriatric Depression Scale (GDS) scores (feature-set 1a); socio-demographic characteristics and neuropsychological tests scores (feature-set 1b) and regional magnetic resonance imaging grey matter volumes (feature-set 2). The most relevant variables were combined to find the best model.

RESULTS

Good prediction performances were obtained with feature-sets 1a and 2. The most relevant variables (variable importance exceeding 20%) were: Age, GDS, and grey matter volumes measured in four cortical regions of interests. Their combination provided the optimal classification performance (highest sensitivity and specificity) ensemble ML model, Extreme Gradient Boosting with over-sampling of the minority class, with performance metrics: sensitivity = 1.00, specificity = 0.92 and area-under-the-curve = 0.96. The median values based on fifty random train/test splits were sensitivity = 0.83 (interquartile range (IQR) = 0.17), specificity = 0.77 (IQR = 0.23) and area-under-the-curve = 0.75 (IQR = 0.11).

CONCLUSION

A high-performance algorithm that could be translatable into practice was able to predict SCD conversion to MCI/AD by using only six predictive variables.

Exploring the ATN classification system using brain morphology

BACKGROUND

The NIA-AA proposed amyloid-tau-neurodegeneration (ATN) as a classification system for AD biomarkers. The amyloid cascade hypothesis (ACH) implies a sequence across ATN groups that patients might undergo during transition from healthy towards AD: A-T-N-➔A+T-N-➔A+T+N-➔A+T+N+. Here we assess the evidence for monotonic brain volume decline for this particular (amyloid-conversion first, tau-conversion second, N-conversion last) and alternative progressions using voxel-based morphometry (VBM) in a large cross-sectional MRI cohort.

METHODS

We used baseline data of the DELCODE cohort of 437 subjects (127 controls, 168 SCD, 87 MCI, 55 AD patients) which underwent lumbar puncture, MRI scanning, and neuropsychological assessment. ATN classification was performed using CSF-Aβ42/Aβ40 (A+/-), CSF phospho-tau (T+/-), and adjusted hippocampal volume or CSF total-tau (N+/-). We compared voxel-wise model evidence for monotonic decline of gray matter volume across various sequences over ATN groups using the Bayesian Information Criterion (including also ROIs of Braak stages). First, face validity of the ACH transition sequence A-T-N-➔A+T-N-➔A+T+N-➔A+T+N+ was compared against biologically less plausible (permuted) sequences among AD continuum ATN groups. Second, we evaluated evidence for 6 monotonic brain volume progressions from A-T-N- towards A+T+N+ including also non-AD continuum ATN groups.

RESULTS

The ACH-based progression A-T-N-➔A+T-N-➔A+T+N-➔A+T+N+ was consistent with cognitive decline and clinical diagnosis. Using hippocampal volume for operationalization of neurodegeneration (N), ACH was most evident in 9% of gray matter predominantly in the medial temporal lobe. Many cortical regions suggested alternative non-monotonic volume progressions over ACH progression groups, which is compatible with an early amyloid-related tissue expansion or sampling effects, e.g., due to brain reserve. Volume decline in 65% of gray matter was consistent with a progression where A status converts before T or N status (i.e., ACH/ANT) when compared to alternative sequences (TAN/TNA/NAT/NTA). Brain regions earlier affected by tau tangle deposition (Braak stage I-IV, MTL, limbic system) present stronger evidence for volume decline than late Braak stage ROIs (V/VI, cortical regions). Similar findings were observed when using CSF total-tau for N instead.

CONCLUSION

Using the ATN classification system, early amyloid status conversion (before tau and neurodegeneration) is associated with brain volume loss observed during AD progression. The ATN system and the ACH are compatible with monotonic progression of MTL atrophy.

TRIAL REGISTRATION

DRKS00007966, 04/05/2015, retrospectively registered.

Effect of APOE4 Allele and Gender on the Rate of Atrophy in the Hippocampus, Entorhinal Cortex, and Fusiform Gyrus in Alzheimer's Disease

BACKGROUND

The hippocampus, entorhinal cortex, and fusiform gyrus are brain areas that deteriorate during early-stage Alzheimer's disease (AD). The ApoE4 allele has been identified as a risk factor for AD development, is linked to an increase in the aggregation of amyloid ß (Aß) plaques in the brain, and is responsible for atrophy of the hippocampal area. However, to our knowledge, the rate of deterioration over time in individuals with AD, with or without the ApoE4 allele, has not been investigated.

METHOD

In this study, we, for the first time, analyze atrophy in these brain structures in AD patients with and without the ApoE4 using the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.

RESULTS

It was found that the rate of decrease in the volume of these brain areas over 12 months was related to the presence of ApoE4. Further, we found that neural atrophy was not different for female and male patients, unlike prior studies, suggesting that the presence of ApoE4 is not linked to the gender difference in AD.

CONCLUSION

Our results confirm and extend previous findings, showing that the ApoE4 allele gradually impacts brain regions impacted by AD.

Sex Difference in General Cognition Associated with Coupling of Whole-brain Functional Connectivity Strength to Cerebral Blood Flow Changes During Alzheimer's Disease Progression

Alzheimer's disease (AD) is a progressive age-related neurodegenerative disorder that results in irreversible cognitive impairments. Nonetheless, there are numerous sex-dependent differences in clinical course. We examined potential contributions of neurovascular coupling deficits to sex differences in AD progression. T1-weighted three-dimensional structural magnetic resonance images, functional blood oxygen level dependent and arterial spin labeling images were acquired from 50 AD patients (28 females), 52 amnesic mild cognitive impairment patients (31 females), and 59 healthy controls (36 females). Short- and long-range functional connectivity strength (FCS) and cerebral blood flow (CBF) values were calculated for all participants. Then, the CBF/FCS coupling ratio, which represented the amount of blood supply per unit of connectivity strength, was calculated for each voxel. Two-way ANOVA was performed to identify group × sex interactions and main effects of group. Correlation analysis was used to assess associations between CBF/FCS ratios and Mini-Mental State Examination (MMSE). There were significant group × sex interaction effects on short-range coupling ratios of right middle temporal gyrus, left angular gyrus, left inferior orbital frontal gyrus, and left superior frontal gyrus as well as on the long-range coupling ratios of right middle temporal gyrus, left precuneus, left posterior cingulate cortex, and left angular gyrus. There were significant negative correlations between MMSE scores and CBF/FCS ratios for all regions with significant group × sex interactions among female patients, while positive correlations were found among male patients. Our results demonstrate significant sex differences in neurovascular coupling mechanisms associated with cognitive function during the course of AD.

Hormone replacement therapy is associated with improved cognition and larger brain volumes in at-risk APOE4 women: results from the European Prevention of Alzheimer's Disease (EPAD) cohort

BACKGROUND

The risk of dementia is higher in women than men. The metabolic consequences of estrogen decline during menopause accelerate neuropathology in women. The use of hormone replacement therapy (HRT) in the prevention of cognitive decline has shown conflicting results. Here we investigate the modulating role of APOE genotype and age at HRT initiation on the heterogeneity in cognitive response to HRT.

METHODS

The analysis used baseline data from participants in the European Prevention of Alzheimer's Dementia (EPAD) cohort (total n= 1906, women= 1178, 61.8%). Analysis of covariate (ANCOVA) models were employed to test the independent and interactive impact of APOE genotype and HRT on select cognitive tests, such as MMSE, RBANS, dot counting, Four Mountain Test (FMT), and the supermarket trolley test (SMT), together with volumes of the medial temporal lobe (MTL) regions by MRI. Multiple linear regression models were used to examine the impact of age of HRT initiation according to APOE4 carrier status on these cognitive and MRI outcomes.

RESULTS

APOE4 HRT users had the highest RBANS delayed memory index score (P-APOE*HRT interaction = 0.009) compared to APOE4 non-users and to non-APOE4 carriers, with 6-10% larger entorhinal (left) and amygdala (right and left) volumes (P-interaction= 0.002, 0.003, and 0.005 respectively). Earlier introduction of HRT was associated with larger right (standardized β= -0.555, p=0.035) and left hippocampal volumes (standardized β= -0.577, p=0.028) only in APOE4 carriers.

CONCLUSION

HRT introduction is associated with improved delayed memory and larger entorhinal and amygdala volumes in APOE4 carriers only. This may represent an effective targeted strategy to mitigate the higher life-time risk of AD in this large at-risk population subgroup. Confirmation of findings in a fit for purpose RCT with prospective recruitment based on APOE genotype is needed to establish causality.

Radiomics for Alzheimer's Disease: Fundamental Principles and Clinical Applications

Alzheimer's disease is a neurodegenerative disease with a huge impact on people's quality of life, life expectancy, and morbidity. The ongoing prevalence of the disease, in conjunction with an increased financial burden to healthcare services, necessitates the development of new technologies to be employed in this field. Hence, advanced computational methods have been developed to facilitate early and accurate diagnosis of the disease and improve all health outcomes. Artificial intelligence is now deeply involved in the fight against this disease, with many clinical applications in the field of medical imaging. Deep learning approaches have been tested for use in this domain, while radiomics, an emerging quantitative method, are already being evaluated to be used in various medical imaging modalities. This chapter aims to provide an insight into the fundamental principles behind radiomics, discuss the most common techniques alongside their strengths and weaknesses, and suggest ways forward for future research standardization and reproducibility.

Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs

Background

As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low‐dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics’ reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect.

Purpose

In this article, we investigate the possibility of denoising low‐dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets.

Methods and materials

Two cycle GANs were trained: (1) from paired data, by simulating low‐dose CTs (i.e., introducing noise) from high‐dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice‐paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low‐dose CT images and (2) same‐day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder–decoder network (EDN) trained on simulated paired data.

Results

The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]).

Conclusion

The results show that cycle GANs trained on both simulated and real data can improve radiomics’ reproducibility and performance in low‐dose CT and achieve similar results compared to CGANs and EDNs.

The Coupled Representation of Hierarchical Features for Mild Cognitive Impairment and Alzheimer's Disease Classification

Structural magnetic resonance imaging (MRI) features have played an increasingly crucial role in discriminating patients with Alzheimer's disease (AD) and mild cognitive impairment (MCI) from normal controls (NC). However, the large number of structural MRI studies only extracted low-level neuroimaging features or simply concatenated multitudinous features while ignoring the interregional covariate information. The appropriate representation and integration of multilevel features will be preferable for the precise discrimination in the progression of AD. In this study, we proposed a novel inter-coupled feature representation method and built an integration model considering the two-level (the regions of interest (ROI) level and the network level) coupled features based on structural MRI data. For the intra-coupled interactions about the network-level features, we performed the ROI-level (intra- and inter-) coupled interaction within each network by feature expansion and coupling learning. For the inter-coupled interaction of the network-level features, we measured the coupled relationships among different networks via Canonical correlation analysis. We evaluated the classification performance using coupled feature representations on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Results showed that the coupled integration model with hierarchical features achieved the optimal classification performance with an accuracy of 90.44% for AD and NC groups, with an accuracy of 87.72% for the MCI converter (MCI-c) and MCI non-converter (MCI-nc) groups. These findings suggested that our two-level coupled interaction representation of hierarchical features has been the effective means for the precise discrimination of MCI-c from MCI-nc groups and, therefore, helpful in the characterization of different AD courses.

Hippocampal-amygdalo-ventricular atrophy score: Alzheimer disease detection using normative and pathological lifespan models

In this article, we present an innovative MRI-based method for Alzheimer disease (AD) detection and mild cognitive impairment (MCI) prognostic, using lifespan trajectories of brain structures. After a full screening of the most discriminant structures between AD and normal aging based on MRI volumetric analysis of 3,032 subjects, we propose a novel Hippocampal-Amygdalo-Ventricular Atrophy score (HAVAs) based on normative lifespan models and AD lifespan models. During a validation on three external datasets on 1,039 subjects, our approach showed very accurate detection (AUC ≥ 94%) of patients with AD compared to control subjects and accurate discrimination (AUC = 78%) between progressive MCI and stable MCI (during a 3-year follow-up). Compared to normative modeling, classical machine learning methods and recent state-of-the-art deep learning methods, our method demonstrated better classification performance. Moreover, HAVAs simplicity makes it fully understandable and thus well-suited for clinical practice or future pharmaceutical trials.

An in vivo implementation of the MEX MRI for myelin fraction of mice brain

OBJECTIVE

Magnetization EXchange (MEX) sequence measures a signal linearly dependent on the myelin proton fraction by selective suppression of water magnetization and a recovery period. Varying the recovery period enables extraction of the percentile fraction of myelin bound protons. We aim to demonstrate the MEX sequence sensitivity to the fraction of protons associated with myelin in mice brain, in vivo.

METHODS

The cuprizone mouse model was used to manipulate the myelin content. Mice fed cuprizone (n = 15) and normal chow (n = 8) were imaged in vivo using MEX sequence. MR images were segmented into corpus callosum and internal capsule (white matter) and cortical gray matter, and fitted to the recovery equation. Results were analyzed with correlation to MWF and histopathology.

RESULTS

The extracted parameters show significant differences in the corpus callosum between the cuprizone and control groups. The cuprizone group exhibited reduced myelin fraction 26.5% (P < 0.01). The gray matter values were less affected, with 13.5% reduction (P < 0.05); no changes were detected in the internal capsule. Results were validated by MWF scans and good correlation to the histology analysis (R² = 0.685).

CONCLUSION

The results of this first in vivo implementation of the MEX sequence provide a quantitative measure of demyelination in brain white matter.

A Novel Explainability Approach for Technology-Driven Translational Research on Brain Aging

Brain aging leads to difficulties in functional independence. Mitigating these difficulties can benefit from technology that predicts, monitors, and modifies brain aging. Translational research prioritizes solutions that can be causally linked to specific pathophysiologies at the same time as demonstrating improvements in impactful real-world outcome measures. This poses a challenge for brain aging technology that needs to address the tension between mechanism-driven precision and clinical relevance. In the current opinion, by synthesizing emerging mechanistic, translational, and clinical research-related frameworks, and our own development of technology-driven brain aging research, we suggest incorporating the appreciation of four desiderata (causality, informativeness, transferability, and fairness) of explainability into early-stage research that designs and tests brain aging technology. We apply a series of work on electrocardiography-based "peripheral" neuroplasticity markers from our work as an illustration of our proposed approach. We believe this novel approach will promote the development and adoption of brain aging technology that links and addresses brain pathophysiology and functional independence in the field of translational research.

Detecting Cognitive Impairment Status Using Keystroke Patterns and Physical Activity Data among the Older Adults: A Machine Learning Approach

Cognitive impairment has a significantly negative impact on global healthcare and the community. Holding a person's cognition and mental retention among older adults is improbable with aging. Early detection of cognitive impairment will decline the most significant impact of extended disease to permanent mental damage. This paper aims to develop a machine learning model to detect and differentiate cognitive impairment categories like severe, moderate, mild, and normal by analyzing neurophysical and physical data. Keystroke and smartwatch have been used to extract individuals' neurophysical and physical data, respectively. An advanced ensemble learning algorithm named Gradient Boosting Machine (GBM) is proposed to classify the cognitive severity level (absence, mild, moderate, and severe) based on the Standardised Mini-Mental State Examination (SMMSE) questionnaire scores. The statistical method "Pearson's correlation" and the wrapper feature selection technique have been used to analyze and select the best features. Then, we have conducted our proposed algorithm GBM on those features. And the result has shown an accuracy of more than 94%. This paper has added a new dimension to the state-of-the-art to predict cognitive impairment by implementing neurophysical data and physical data together.

Agreement Between Automated and Manual MRI Volumetry in Alzheimer's Disease: A Systematic Review and Meta-Analysis

BACKGROUND

Automated magnetic resonance imaging (MRI) volumetry is a promising tool to evaluate regional brain volumes in dementia and especially Alzheimer's disease (AD).

PURPOSE

To compare automated methods and the gold standard manual segmentation in measuring regional brain volumes on MRI across healthy controls, patients with mild cognitive impairment, and patients with dementia due to AD.

STUDY TYPE

Systematic review and meta-analysis.

DATA SOURCES

MEDLINE, Embase, and PsycINFO were searched through October 2021.

FIELD STRENGTH

1.0 T, 1.5 T, or 3.0 T.

ASSESSMENT

Two review authors independently identified studies for inclusion and extracted data. Methodological quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2).

STATISTICAL TESTS

Standardized mean differences (SMD; Hedges' g) were pooled using random-effects meta-analysis with robust variance estimation. Subgroup analyses were undertaken to explore potential sources of heterogeneity. Sensitivity analyses were conducted to examine the impact of the within-study correlation between effect estimates on the meta-analysis results.

RESULTS

Seventeen studies provided sufficient data to evaluate the hippocampus, lateral ventricles, and parahippocampal gyrus. The pooled SMD for the hippocampus, lateral ventricles, and parahippocampal gyrus were 0.22 (95% CI -0.50 to 0.93), 0.12 (95% CI -0.13 to 0.37), and -0.48 (95% CI -1.37 to 0.41), respectively. For the hippocampal data, subgroup analyses suggested that the pooled SMD was invariant across clinical diagnosis and field strength. Subgroup analyses could not be conducted on the lateral ventricles data and the parahippocampal gyrus data due to insufficient data. The results were robust to the selected within-study correlation value.

DATA CONCLUSION

While automated methods are generally comparable to manual segmentation for measuring hippocampal, lateral ventricle, and parahippocampal gyrus volumes, wide 95% CIs and large heterogeneity suggest that there is substantial uncontrolled variance. Thus, automated methods may be used to measure these regions in patients with AD but should be used with caution.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 3.

Pursuit of precision medicine: Systems biology approaches in Alzheimer's disease mouse models

Alzheimer's disease (AD) is a complex disease that is mediated by numerous factors and manifests in various forms. A systems biology approach to studying AD involves analyses of various body systems, biological scales, environmental elements, and clinical outcomes to understand the genotype to phenotype relationship that potentially drives AD development. Currently, there are many research investigations probing how modifiable and nonmodifiable factors impact AD symptom presentation. This review specifically focuses on how imaging modalities can be integrated into systems biology approaches using model mouse populations to link brain level functional and structural changes to disease onset and progression. Combining imaging and omics data promotes the classification of AD into subtypes and paves the way for precision medicine solutions to prevent and treat AD.

Multimodal Prediction of Alzheimer's Disease Severity Level Based on Resting-State EEG and Structural MRI

While several biomarkers have been developed for the detection of Alzheimer's disease (AD), not many are available for the prediction of disease severity, particularly for patients in the mild stages of AD. In this paper, we explore the multimodal prediction of Mini-Mental State Examination (MMSE) scores using resting-state electroencephalography (EEG) and structural magnetic resonance imaging (MRI) scans. Analyses were carried out on a dataset comprised of EEG and MRI data collected from 89 patients diagnosed with minimal-mild AD. Three feature selection algorithms were assessed alongside four machine learning algorithms. Results showed that while MRI features alone outperformed EEG features, when both modalities were combined, improved results were achieved. The top-selected EEG features conveyed information about amplitude modulation rate-of-change, whereas top-MRI features comprised information about cortical area and white matter volume. Overall, a root mean square error between predicted MMSE values and true MMSE scores of 1.682 was achieved with a multimodal system and a random forest regression model.

Cortical Thickness, Volume, and Surface Area in the Motoric Cognitive Risk Syndrome

BACKGROUND

The motoric cognitive risk (MCR) syndrome is a pre-clinical stage of dementia characterized by slow gait and cognitive complaint. Yet, the brain substrates of MCR are not well established.

OBJECTIVE

To examine cortical thickness, volume, and surface area associated with MCR in the MCR-Neuroimaging Consortium, which harmonizes image processing/analysis of multiple cohorts.

METHODS

Two-hundred MRIs (M age 72.62 years; 47.74%female; 33.17%MCR) from four different cohorts (50 each) were first processed with FreeSurfer 6.0, and then analyzed using multivariate and univariate general linear models with 1,000 bootstrapped samples (n-1; with resampling). All models adjusted for age, sex, education, white matter lesions, total intracranial volume, and study site.

RESULTS

Overall, cortical thickness was lower in individuals with MCR than in those without MCR. There was a trend in the same direction for cortical volume (p = 0.051). Regional cortical thickness was also lower among individuals with MCR than individuals without MCR in prefrontal, insular, temporal, and parietal regions.

CONCLUSION

Cortical atrophy in MCR is pervasive, and include regions previously associated with human locomotion, but also social, cognitive, affective, and motor functions. Cortical atrophy in MCR is easier to detect in cortical thickness than volume and surface area because thickness is more affected by healthy and pathological aging.

Dual Attention Multi-Instance Deep Learning for Alzheimer's Disease Diagnosis With Structural MRI

Structural magnetic resonance imaging (sMRI) is widely used for the brain neurological disease diagnosis, which could reflect the variations of brain. However, due to the local brain atrophy, only a few regions in sMRI scans have obvious structural changes, which are highly correlative with pathological features. Hence, the key challenge of sMRI-based brain disease diagnosis is to enhance the identification of discriminative features. To address this issue, we propose a dual attention multi-instance deep learning network (DA-MIDL) for the early diagnosis of Alzheimer's disease (AD) and its prodromal stage mild cognitive impairment (MCI). Specifically, DA-MIDL consists of three primary components: 1) the Patch-Nets with spatial attention blocks for extracting discriminative features within each sMRI patch whilst enhancing the features of abnormally changed micro-structures in the cerebrum, 2) an attention multi-instance learning (MIL) pooling operation for balancing the relative contribution of each patch and yield a global different weighted representation for the whole brain structure, and 3) an attention-aware global classifier for further learning the integral features and making the AD-related classification decisions. Our proposed DA-MIDL model is evaluated on the baseline sMRI scans of 1689 subjects from two independent datasets (i.e., ADNI and AIBL). The experimental results show that our DA-MIDL model can identify discriminative pathological locations and achieve better classification performance in terms of accuracy and generalizability, compared with several state-of-the-art methods.

A Personalized Computer-Aided Diagnosis System for Mild Cognitive Impairment (MCI) Using Structural MRI (sMRI)

Alzheimer's disease (AD) is a neurodegenerative disorder that targets the central nervous system (CNS). Statistics show that more than five million people in America face this disease. Several factors hinder diagnosis at an early stage, in particular, the divergence of 10-15 years between the onset of the underlying neuropathological changes and patients becoming symptomatic. This study surveyed patients with mild cognitive impairment (MCI), who were at risk of conversion to AD, with a local/regional-based computer-aided diagnosis system. The described system allowed for visualization of the disorder's effect on cerebral cortical regions individually. The CAD system consists of four steps: (1) preprocess the scans and extract the cortex, (2) reconstruct the cortex and extract shape-based features, (3) fuse the extracted features, and (4) perform two levels of diagnosis: cortical region-based followed by global. The experimental results showed an encouraging performance of the proposed system when compared with related work, with a maximum accuracy of 86.30%, specificity 88.33%, and sensitivity 84.88%. Behavioral and cognitive correlations identified brain regions involved in language, executive function/cognition, and memory in MCI subjects, which regions are also involved in the neuropathology of AD.

Hippocampal neurobiology and function in an aged mouse model of TDP-43 proteinopathy in an APP/PSEN1 background

Aging is a major risk factor for Alzheimer's disease (AD), the most common cause of dementia worldwide. TDP-43 proteinopathy is reported to be associated with AD pathology is almost 50% of cases. Our exploratory study examined near end-stage (28 months old) mice selectively driving expression of human TDP-43 in the hippocampus and cortex in an APP/PSEN1 background. We hypothesized that hippocampal neuropathology caused by β-amyloidosis with TDP-43 proteinopathy induced in this model, resembling the pathology seen in AD cases, manifest with changes in resting state functional connectivity. In vivo magnetic resonance imaging and post-mortem histology were performed on four genotypes: wild type, APP/PSEN1, Camk2a/TDP-43, and Camk2a/TDP-43/APP/PSEN1. Our results revealed loss of functional coupling in hippocampus and amygdala that was associated with severe neuronal loss in dentate gyrus of Camk2a/TDP-43/APP/PSEN1 mice compared to APP/PSEN1 and wild type mice. The loss of cells was accompanied by high background of β-amyloid plaques with sparse phosphorylated TDP-43 pathology. The survival rate was also reduced in Camk2a/TDP-43/APP/PSEN1 mice compared to other groups. This end-of-life study provides exploratory data to reach a better understanding of the role of TDP-43 hippocampal neuropathology in diseases with co-pathologies of TDP-43 proteinopathy and β-amyloidosis such as AD and limbic predominant age-related TDP-43 encephalopathy (LATE).

Joint cortical surface and structural connectivity analysis of Alzheimer's Disease

Prior neuroimaging studies have demonstrated isolated structural and connectivity changes in the brain due to Alzheimer's Disease (AD). However, how these changes relate to each other is not well understood. We present a preliminary study to begin to fill this gap by leveraging joint independent component analysis (jICA). We explore how jICA performs in an analysis of T1 and diffusion weighted MRI by characterizing the joint changes of complex cortical surface and structural connectivity metrics in AD in subjects from the Baltimore Longitudinal Study of Aging. We calculate 588 region-based cortical metrics and 4,753 fractional anisotropy-based connectivity metrics and project them into a low-dimensional manifold with principal component analysis. We perform jICA on the manifold and subsequently backproject the independent components to the original data space. We demonstrate component stability with 3-fold cross validation and find differential component loadings between 776 cognitively unimpaired control subjects and 23 with AD that generalizes across folds. In addition, we perform the same analysis on the surface and connectivity metrics separately and find that the joint approach identifies both novel and similar components to the separate approaches. To illustrate the joint approach's primary utility, we provide an example hypothesis for how surface and connectivity components may vary together with AD. These preliminary results suggest jointly varying independent cortical surface and structural connectivity components can be consistently extracted from MRI data and provide a data-driven way for generating novel hypotheses about AD that may not be captured by separate analyses.

Multimodal deep learning models for early detection of Alzheimer's disease stage

Most current Alzheimer's disease (AD) and mild cognitive disorders (MCI) studies use single data modality to make predictions such as AD stages. The fusion of multiple data modalities can provide a holistic view of AD staging analysis. Thus, we use deep learning (DL) to integrally analyze imaging (magnetic resonance imaging (MRI)), genetic (single nucleotide polymorphisms (SNPs)), and clinical test data to classify patients into AD, MCI, and controls (CN). We use stacked denoising auto-encoders to extract features from clinical and genetic data, and use 3D-convolutional neural networks (CNNs) for imaging data. We also develop a novel data interpretation method to identify top-performing features learned by the deep-models with clustering and perturbation analysis. Using Alzheimer's disease neuroimaging initiative (ADNI) dataset, we demonstrate that deep models outperform shallow models, including support vector machines, decision trees, random forests, and k-nearest neighbors. In addition, we demonstrate that integrating multi-modality data outperforms single modality models in terms of accuracy, precision, recall, and meanF1 scores. Our models have identified hippocampus, amygdala brain areas, and the Rey Auditory Verbal Learning Test (RAVLT) as top distinguished features, which are consistent with the known AD literature.

A Survey on State-of-the-art Denoising Techniques for Brain Magnetic Resonance Images

The accuracy of the magnetic resonance (MR) image diagnosis depends on the quality of the image, which degrades mainly due to noise and artifacts. The noise is introduced because of erroneous imaging environment or distortion in the transmission system. Therefore, denoising methods play an important role in enhancing the image quality. However, a tradeoff between denoising and preserving the structural details is required. Most of the existing surveys are conducted on a specific MR image modality or on limited denoising schemes. In this context, a comprehensive review on different MR image denoising techniques is inevitable. This survey suggests a new direction in categorizing the MR image denoising techniques. The categorization of the different image models used in medical image processing serves as the basis of our classification. This study includes recent improvements on deep learning-based denoising methods alongwith important traditional MR image denoising methods. The major challenges and their scope of improvement are also discussed. Further, many more evaluation indices are considered for a fair comparison. An elaborate discussion on selecting appropriate method and evaluation metric as per the kind of data is presented. This study may encourage researchers for further work in this domain.

A preliminary study of cortical morphology changes in acute brainstem ischemic stroke patients

The study aimed to explore the cortical thickness and gyrification abnormalities in acute brainstem ischemic patients in both the ipsilateral and contralateral hemisphere compared with healthy controls. Structural magnetic resonance imaging data were prospectively acquired in 48 acute brainstem ischemic patients, 21 patients with left lesion and 27 with right lesion, respectively. Thirty healthy controls were recruited. Cortical morphometry based on surface-based data analysis driven by CAT12 toolbox implemented in SPM12 was used to compare changes in cortical thickness and gyrification. Significant decreases of cortical thickness loss were found in bilateral cerebral hemispheres of the brainstem ischemic patients compared to the healthy controls (P < .05, family-wise error (FWE)-corrected). We also found significant gyrification decreases in the insula, transverse temporal, supramarginal of the ipsilateral on hemisphere in the right brainstem ischemic patients compared to the healthy controls (P < .05, FWE-corrected). Brainstem ischemic patients have widely morphological changes in the early phase and may be helpful in designing individualized rehabilitative strategies for these patients.

Aggregation of Vascular Risk Factors Modulates the Amplitude of Low-Frequency Fluctuation in Mild Cognitive Impairment Patients

Background: Several vascular risk factors, including hypertension, diabetes, body mass index, and smoking status are found to be associated with cognitive decline and the risk of Alzheimer's disease (AD). We aimed to investigate whether an aggregation of vascular risk factors modulates the amplitude of low-frequency fluctuation (ALFF) in patients with mild cognitive impairment (MCI).

Methods: Forty-three MCI patients and twenty-nine healthy controls (HCs) underwent resting-state functional MRI scans, and spontaneous brain activity was measured by the ALFF technique. The vascular risk profile was represented with the Framingham Heart Study general cardiovascular disease (FHS-CVD) risk score, and each group was further divided into high and low risk subgroups. Two-way ANOVA was performed to explore the main effects of diagnosis and vascular risk and their interaction on ALFF.

Results: The main effect of diagnosis on ALFF was found in left middle temporal gyrus (LMTG) and left superior parietal gyrus (LSPG), and the main effect of risk on ALFF was detected in left fusiform gyrus (LFFG), left precuneus (LPCUN), and left cerebellum posterior lobe (LCPL). Patients with MCI exhibited increased ALFF in the LMTG and LSPG than HCs, and participants with high vascular risk showed increased ALFF in the LFFG and LCPL, while decreased ALFF in the LPCUN. An interaction between diagnosis (MCI vs. HC) and FHS-CVD risk (high vs. low) regarding ALFF was observed in the left hippocampus (LHIP). HCs with high vascular risk showed significantly increased ALFF in the LHIP than those with low vascular risk, while MCI patients with high vascular risk showed decreased ALFF in the LHIP than HCs with high vascular risk. Interestingly, the mean ALFF of LHIP positively correlated with word recall test in HCs with high vascular risk (rho = 0.630, P = 0.016), while negatively correlated with the same test in MCI patients with high vascular risk (rho = −0.607, P = 0.001).

Conclusions: This study provides preliminary evidence highlighting that the aggregation of vascular risk factors modulates the spontaneous brain activity in MCI patients, and this may serve as a potential imaging mechanism underlying vascular contribution to AD.

Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15% of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.

Assessment of Alzheimer's Disease Based on Texture Analysis of the Entorhinal Cortex

Alzheimer’s disease (AD) brain magnetic resonance imaging (MRI) biomarkers based on larger-scale tissue neurodegeneration changes, such as atrophy, are currently widely used. Texture analysis evaluates the statistical properties of the tissue image quantitatively; therefore, it could detect smaller-scale changes of neurodegeneration. Entorhinal cortex is the first region affected, and no study has investigated texture analysis on this region before. This study aims to differentiate AD patients from Normal Control (NC) and Mild Cognitive Impairment (MCI) subjects using entorhinal cortex texture features. Furthermore, it was evaluated whether texture has association to MCI beyond that of volume, to evaluate if atrophy development may precede. Texture features were extracted from 194 NC, 200 MCI, 84 MCI who converted to AD (MCIc), and 130 AD subjects. Receiving operating characteristic curves determined the performance of the various features in discriminating the groups, and a predictive model was used to predict conversion of MCIc subjects to AD. An area under the curve (AUC) of 0.872, 0.710, 0.730, and 0.764 was seen between NC vs. AD, NC vs. MCI, MCI vs. MCIc, and MCI vs. AD subjects, respectively. Including entorhinal cortex volume improved the AUCs to 0.914, 0.740, 0.756, and 0.780, respectively. For the disease prediction, binary logistic regression was applied on five randomly selected test groups and achieved on average AUC’s of 0.760 and 0.764 on the training and validation cohorts, respectively. Entorhinal cortex texture features were significantly different between the four groups and in many cases provided better results compared to other methods such as volumetry.

Prediction of conversion to Alzheimer's disease using deep survival analysis of MRI images

The prediction of the conversion of healthy individuals and those with mild cognitive impairment to the status of active Alzheimer’s disease is a challenging task. Recently, a survival analysis based upon deep learning was developed to enable predictions regarding the timing of an event in a dataset containing censored data. Here, we investigated whether a deep survival analysis could similarly predict the conversion to Alzheimer’s disease. We selected individuals with mild cognitive impairment and cognitively normal subjects and used the grey matter volumes of brain regions in these subjects as predictive features. We then compared the prediction performances of the traditional standard Cox proportional-hazard model, the DeepHit model and our deep survival model based on a Weibull distribution. Our model achieved a maximum concordance index of 0.835, which was higher than that yielded by the Cox model and comparable to that of the DeepHit model. To our best knowledge, this is the first report to describe the application of a deep survival model to brain magnetic resonance imaging data. Our results demonstrate that this type of analysis could successfully predict the time of an individual’s conversion to Alzheimer’s disease.

The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping

Background Radiomic features may quantify characteristics present in medical imaging. However, the lack of standardized definitions and validated reference values have hampered clinical use. Purpose To standardize a set of 174 radiomic features. Materials and Methods Radiomic features were assessed in three phases. In phase I, 487 features were derived from the basic set of 174 features. Twenty-five research teams with unique radiomics software implementations computed feature values directly from a digital phantom, without any additional image processing. In phase II, 15 teams computed values for 1347 derived features using a CT image of a patient with lung cancer and predefined image processing configurations. In both phases, consensus among the teams on the validity of tentative reference values was measured through the frequency of the modal value and classified as follows: less than three matches, weak; three to five matches, moderate; six to nine matches, strong; 10 or more matches, very strong. In the final phase (phase III), a public data set of multimodality images (CT, fluorine 18 fluorodeoxyglucose PET, and T1-weighted MRI) from 51 patients with soft-tissue sarcoma was used to prospectively assess reproducibility of standardized features. Results Consensus on reference values was initially weak for 232 of 302 features (76.8%) at phase I and 703 of 1075 features (65.4%) at phase II. At the final iteration, weak consensus remained for only two of 487 features (0.4%) at phase I and 19 of 1347 features (1.4%) at phase II. Strong or better consensus was achieved for 463 of 487 features (95.1%) at phase I and 1220 of 1347 features (90.6%) at phase II. Overall, 169 of 174 features were standardized in the first two phases. In the final validation phase (phase III), most of the 169 standardized features could be excellently reproduced (166 with CT; 164 with PET; and 164 with MRI). Conclusion A set of 169 radiomics features was standardized, which enabled verification and calibration of different radiomics software. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Kuhl and Truhn in this issue.

Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review

Alzheimer's Disease (AD) is one of the leading causes of death in developed countries. From a research point of view, impressive results have been reported using computer-aided algorithms, but clinically no practical diagnostic method is available. In recent years, deep models have become popular, especially in dealing with images. Since 2013, deep learning has begun to gain considerable attention in AD detection research, with the number of published papers in this area increasing drastically since 2017. Deep models have been reported to be more accurate for AD detection compared to general machine learning techniques. Nevertheless, AD detection is still challenging, and for classification, it requires a highly discriminative feature representation to separate similar brain patterns. This paper reviews the current state of AD detection using deep learning. Through a systematic literature review of over 100 articles, we set out the most recent findings and trends. Specifically, we review useful biomarkers and features (personal information, genetic data, and brain scans), the necessary pre-processing steps, and different ways of dealing with neuroimaging data originating from single-modality and multi-modality studies. Deep models and their performance are described in detail. Although deep learning has achieved notable performance in detecting AD, there are several limitations, especially regarding the availability of datasets and training procedures.

Characterizing Alzheimer's Disease With Image and Genetic Biomarkers Using Supervised Topic Models

Neuroimaging and genetic biomarkers have been widely studied from discriminative perspectives towards Alzheimer's disease (AD) classification, since neuroanatomical patterns and genetic variants are jointly critical indicators for AD diagnosis. Generative methods, designed to model common occurring patterns, could potentially advance the understanding of this disease, but have not been fully explored for AD characterization. Moreover, the introduction of a supervised component into the generative process can constrain the model for more discriminative characterization. In this study, we propose an original method based on supervised topic modeling to characterize AD from a generative perspective, yet maintaining discriminative power at differentiating disease populations. Our topic modeling jointly exploits discretized image features and categorical genetic features. Diagnostic information - cognitively normal (CN), mild cognitive impairment (MCI) and AD - is introduced as a supervision variable. Experimental results on the ADNI cohort demonstrate that our model, while achieving competitive discriminative performance, can discover topics revealing both well-known and novel neuroanatomical patterns including temporal, parietal and frontal regions; as well as associations between genetic factors and neuroanatomical patterns.

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.

Modelling prognostic trajectories of cognitive decline due to Alzheimer's disease

Alzheimer's disease (AD) is characterised by a dynamic process of neurocognitive changes from normal cognition to mild cognitive impairment (MCI) and progression to dementia. However, not all individuals with MCI develop dementia. Predicting whether individuals with MCI will decline (i.e. progressive MCI) or remain stable (i.e. stable MCI) is impeded by patient heterogeneity due to comorbidities that may lead to MCI diagnosis without progression to AD. Despite the importance of early diagnosis of AD for prognosis and personalised interventions, we still lack robust tools for predicting individual progression to dementia. Here, we propose a novel trajectory modelling approach based on metric learning (Generalised Metric Learning Vector Quantization) that mines multimodal data from MCI patients in the Alzheimer's disease Neuroimaging Initiative (ADNI) cohort to derive individualised prognostic scores of cognitive decline due to AD. We develop an integrated biomarker generation- using partial least squares regression- and classification methodology that extends beyond binary patient classification into discrete subgroups (i.e. stable vs. progressive MCI), determines individual profiles from baseline (i.e. cognitive or biological) data and predicts individual cognitive trajectories (i.e. change in memory scores from baseline). We demonstrate that a metric learning model trained on baseline cognitive data (memory, executive function, affective measurements) discriminates stable vs. progressive MCI individuals with high accuracy (81.4%), revealing an interaction between cognitive (memory, executive functions) and affective scores that may relate to MCI comorbidity (e.g. affective disturbance). Training the model to perform the same binary classification on biological data (mean cortical β-amyloid burden, grey matter density, APOE 4) results in similar prediction accuracy (81.9%). Extending beyond binary classifications, we develop and implement a trajectory modelling approach that shows significantly better performance in predicting individualised rate of future cognitive decline (i.e. change in memory scores from baseline), when the metric learning model is trained with biological (r = -0.68) compared to cognitive (r = -0.4) data. Our trajectory modelling approach reveals interpretable and interoperable markers of progression to AD and has strong potential to guide effective stratification of individuals based on prognostic disease trajectories, reducing MCI patient misclassification, that is critical for clinical practice and discovery of personalised interventions.

Deep Feature Selection and Causal Analysis of Alzheimer's Disease

Deep convolutional neural networks (DCNNs) have achieved great success for image classification in medical research. Deep learning with brain imaging is the imaging method of choice for the diagnosis and prediction of Alzheimer’s disease (AD). However, it is also well known that DCNNs are “black boxes” owing to their low interpretability to humans. The lack of transparency of deep learning compromises its application to the prediction and mechanism investigation in AD. To overcome this limitation, we develop a novel general framework that integrates deep leaning, feature selection, causal inference, and genetic-imaging data analysis for predicting and understanding AD. The proposed algorithm not only improves the prediction accuracy but also identifies the brain regions underlying the development of AD and causal paths from genetic variants to AD via image mediation. The proposed algorithm is applied to the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset with diffusion tensor imaging (DTI) in 151 subjects (51 AD and 100 non-AD) who were measured at four time points of baseline, 6 months, 12 months, and 24 months. The algorithm identified brain regions underlying AD consisting of the temporal lobes (including the hippocampus) and the ventricular system.

Machine Learning-Based Framework for Differential Diagnosis Between Vascular Dementia and Alzheimer's Disease Using Structural MRI Features

Background and Objective: Vascular dementia (VaD) and Alzheimer's disease (AD) could be characterized by the same syndrome of dementia. This study aims to assess whether multi-parameter features derived from structural MRI can serve as the informative biomarker for differential diagnosis between VaD and AD using machine learning.

Methods: A total of 93 patients imaged with brain MRI including 58 AD and 35 VaD confirmed by two chief physicians were recruited in this study from June 2013 to July 2019. Automated brain tissue segmentation was performed by the AccuBrain tool to extract multi-parameter volumetric measurements from different brain regions. Firstly, a total of 62 structural MRI biomarkers were addressed to select significantly different features between VaD and AD for dimensionality reduction. Then, the least absolute shrinkage and selection operator (LASSO) was further used to construct a feature set that is fed into a support vector machine (SVM) classifier. To ensure the unbiased evaluation of model performance, a comparative study of classification models was implemented by using different machine learning algorithms in order to determine which performs best in the application of differential diagnosis between VaD and AD. The diagnostic performance of the classification models was evaluated by the quantitative metrics derived from the receiver operating characteristic curve (ROC).

Results: The experimental results demonstrate that the SVM with RBF achieved an encouraging performance with sensitivity (SEN), specificity (SPE), and accuracy (ACC) values of 82.65%, 87.17%, and 84.35%, respectively (AUC = 0.861, 95% CI = 0.820–0.902), for the differential diagnosis between VaD and AD.

Conclusions: The proposed computer-aided diagnosis method highlights the potential of combining structural MRI and machine learning to support clinical decision making in distinction of VaD vs. AD.