Detection of Alzheimer's disease signature in MR images seven years before conversion to dementia: Toward an early individual prognosis

A multimodal machine learning model for predicting dementia conversion in Alzheimer's disease

Alzheimer's disease (AD) accounts for 60-70% of the population with dementia. Mild cognitive impairment (MCI) is a diagnostic entity defined as an intermediate stage between subjective cognitive decline and dementia, and about 10-15% of people annually convert to AD. We aimed to investigate the most robust model and modality combination by combining multi-modality image features based on demographic characteristics in six machine learning models. A total of 196 subjects were enrolled from four hospitals and the Alzheimer's Disease Neuroimaging Initiative dataset. During the four-year follow-up period, 47 (24%) patients progressed from MCI to AD. Volumes of the regions of interest, white matter hyperintensity, and regional Standardized Uptake Value Ratio (SUVR) were analyzed using T1, T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRIs, and amyloid PET (αPET), along with automatically provided hippocampal occupancy scores (HOC) and Fazekas scales. As a result of testing the robustness of the model, the GBM model was the most stable, and in modality combination, model performance was further improved in the absence of T2-FLAIR image features. Our study predicts the probability of AD conversion in MCI patients, which is expected to be useful information for clinician's early diagnosis and treatment plan design.

Artificial intelligence for diagnostic and prognostic neuroimaging in dementia: A systematic review

INTRODUCTION

Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.

METHODS

We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.

RESULTS

A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.

DISCUSSION

The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.

HIGHLIGHTS

There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias.

Hippocampal subfield associations with memory depend on stimulus modality and retrieval mode

Hippocampal atrophy is a well-known feature of age-related memory decline, and hippocampal subfields may contribute differently to this decline. In this cross-sectional study, we investigated the associations between hippocampal subfield volumes and performance in free recall and recognition memory tasks in both verbal and visual modalities in older adults without dementia. We collected MRIs from 97 (41 males) right-handed participants aged over 60. We segmented the right and left hippocampi into (i) dentate gyrus and cornu ammonis 4 (DG/CA4); (ii) CA2 and CA3 (CA2/CA3); (iii) CA1; (iv) strata radiatum, lacunosum and moleculare; and (v) subiculum. Memory was assessed with verbal free recall and recognition tasks, as well as visual free recall and recognition tasks. Amyloid-β and hippocampal tau positivity were assessed using [18F]AZD4694 and [18F]MK6240 PET tracers, respectively. The verbal free recall and verbal recognition performances were positively associated with CA1 and strata radiatum, lacunosum and moleculare volumes. The verbal free recall and visual free recall were positively correlated with the right DG/CA4. The visual free recall, but not verbal free recall, was also associated with the right CA2/CA3. The visual recognition was not significantly associated with any subfield volume. Hippocampal tau positivity, but not amyloid-β positivity, was associated with reduced DG/CA4, CA2/CA3 and strata radiatum, lacunosum and moleculare volumes. Our results suggest that memory performances are linked to specific subfields. CA1 appears to contribute to the verbal modality, irrespective of the free recall or recognition mode of retrieval. In contrast, DG/CA4 seems to be involved in the free recall mode, irrespective of verbal or visual modalities. These results are concordant with the view that DG/CA4 plays a primary role in encoding a stimulus' distinctive attributes, and that CA2/CA3 could be instrumental in recollecting a visual memory from one of its fragments. Overall, we show that hippocampal subfield segmentation can be useful for detecting early volume changes and improve our understanding of the hippocampal subfields' roles in memory.

Hippocampal grading provides higher classification accuracy for those in the AD trajectory than hippocampal volume

Much research has focused on neurodegeneration in aging and Alzheimer's disease (AD). We developed Scoring by Nonlocal Image Patch Estimator (SNIPE), a non-local patch-based measure of anatomical similarity and hippocampal segmentation to measure hippocampal change. While SNIPE shows enhanced predictive power over hippocampal volume, it is unknown whether SNIPE is more strongly associated with group differences between normal controls (NC), early MCI (eMCI), late (lMCI), and AD than hippocampal volume. Alzheimer's Disease Neuroimaging Initiative older adults were included in the first analyses (N = 1666, 513 NCs, 269 eMCI, 556 lMCI, and 328 AD). Sub-analyses investigated amyloid positive individuals (N = 834; 179 NC, 148 eMCI, 298 lMCI, and 209 AD) to determine accuracy in those on the AD trajectory. We compared SNIPE grading, SNIPE volume, and Freesurfer volume as features in seven different machine learning techniques classifying participants into their correct cohort using 10-fold cross-validation. The best model was then validated in the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL). SNIPE grading provided the highest classification accuracy for all classifications in both the full and amyloid positive sample. When classifying NC:AD, SNIPE grading provided an 89% accuracy (full sample) and 87% (amyloid positive sample). Freesurfer volume provided much lower accuracies of 65% (full sample) and 46% (amyloid positive sample). In the AIBL validation cohort, SNIPE grading provided a 90% classification accuracy for NC:AD. These findings suggest SNIPE grading provides increased classification accuracy over both SNIPE and Freesurfer volume. SNIPE grading offers promise to accurately identify people with and without AD.

Longitudinal changes in hippocampal texture from healthy aging to Alzheimer's disease

Early detection of Alzheimer's disease is essential to develop preventive treatment strategies. Detectible change in brain volume emerges relatively late in the pathogenic progression of disease, but microstructural changes caused by early neuropathology may cause subtle changes in the MR signal, quantifiable using texture analysis. Texture analysis quantifies spatial patterns in an image, such as smoothness, randomness and heterogeneity. We investigated whether the MRI texture of the hippocampus, an early site of Alzheimer's disease pathology, is sensitive to changes in brain microstructure before the onset of cognitive impairment. We also explored the longitudinal trajectories of hippocampal texture across the Alzheimer's continuum in relation to hippocampal volume and other biomarkers. Finally, we assessed the ability of texture to predict future cognitive decline, over and above hippocampal volume. Data were acquired from the Alzheimer's Disease Neuroimaging Initiative. Texture was calculated for bilateral hippocampi on 3T T1-weighted MRI scans. Two hundred and ninety-three texture features were reduced to five principal components that described 88% of total variance within cognitively unimpaired participants. We assessed cross-sectional differences in these texture components and hippocampal volume between four diagnostic groups: cognitively unimpaired amyloid-β- (n = 406); cognitively unimpaired amyloid-β+ (n = 213); mild cognitive impairment amyloid-β+ (n = 347); and Alzheimer's disease dementia amyloid-β+ (n = 202). To assess longitudinal texture change across the Alzheimer's continuum, we used a multivariate mixed-effects spline model to calculate a 'disease time' for all timepoints based on amyloid PET and cognitive scores. This was used as a scale on which to compare the trajectories of biomarkers, including volume and texture of the hippocampus. The trajectories were modelled in a subset of the data: cognitively unimpaired amyloid-β- (n = 345); cognitively unimpaired amyloid-β+ (n = 173); mild cognitive impairment amyloid-β+ (n = 301); and Alzheimer's disease dementia amyloid-β+ (n = 161). We identified a difference in texture component 4 at the earliest stage of Alzheimer's disease, between cognitively unimpaired amyloid-β- and cognitively unimpaired amyloid-β+ older adults (Cohen's d = 0.23, Padj = 0.014). Differences in additional texture components and hippocampal volume emerged later in the disease continuum alongside the onset of cognitive impairment (d = 0.30-1.22, Padj < 0.002). Longitudinal modelling of the texture trajectories revealed that, while most elements of texture developed over the course of the disease, noise reduced sensitivity for tracking individual textural change over time. Critically, however, texture provided additional information than was provided by volume alone to more accurately predict future cognitive change (d = 0.32-0.63, Padj < 0.0001). Our results support the use of texture as a measure of brain health, sensitive to Alzheimer's disease pathology, at a time when therapeutic intervention may be most effective.

Preliminary validation of a structural magnetic resonance imaging metric for tracking dementia-related neurodegeneration and future decline

Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline and atrophy in the medial temporal lobe (MTL) and subsequent brain regions. Structural magnetic resonance imaging (sMRI) has been widely used in research and clinical care for diagnosis and monitoring AD progression. However, atrophy patterns are complex and vary by patient. To address this issue, researchers have made efforts to develop more concise metrics that can summarize AD-specific atrophy. Many of these methods can be difficult to interpret clinically, hampering adoption. In this study, we introduce a novel index which we call an "AD-NeuroScore," that uses a modified Euclidean-inspired distance function to calculate differences between regional brain volumes associated with cognitive decline. The index is adjusted for intracranial volume (ICV), age, sex, and scanner model. We validated AD-NeuroScore using 929 older adults from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study, with a mean age of 72.7 years (SD = 6.3; 55.1-91.5) and cognitively normal (CN), mild cognitive impairment (MCI), or AD diagnoses. Our validation results showed that AD-NeuroScore was significantly associated with diagnosis and disease severity scores (measured by MMSE, CDR-SB, and ADAS-11) at baseline. Furthermore, baseline AD-NeuroScore was associated with both changes in diagnosis and disease severity scores at all time points with available data. The performance of AD-NeuroScore was equivalent or superior to adjusted hippocampal volume (AHV), a widely used metric in AD research. Further, AD-NeuroScore typically performed as well as or sometimes better when compared to other existing sMRI-based metrics. In conclusion, we have introduced a new metric, AD-NeuroScore, which shows promising results in detecting AD, benchmarking disease severity, and predicting disease progression. AD-NeuroScore differentiates itself from other metrics by being clinically practical and interpretable.

The use of hippocampal grading as a biomarker for preclinical and prodromal Alzheimer's disease

Hippocampal changes are associated with increased age and cognitive decline due to mild cognitive impairment (MCI) and Alzheimer's disease (AD). These associations are often observed only in the later stages of decline. This study examined if hippocampal grading, a method measuring local morphological similarity of the hippocampus to cognitively normal controls (NCs) and AD participants, is associated with cognition in NCs, subjective cognitive decline (SCD), early (eMCI), late (lMCI), and AD. A total of 1620 Alzheimer's Disease Neuroimaging Initiative participants were examined (495 NC, 262 eMCI, 545 lMCI, and 318 AD) because they had baseline MRIs and Alzheimer's disease Assessment Scale (ADAS-13) and Clinical Dementia Rating-Sum of Boxes (CDR-SB) scores. In a sub-analysis, NCs with episodic memory scores (as measured by Rey Auditory Verbal Learning Test, RAVLT) were divided into those with subjective cognitive decline (SCD+; 103) and those without (SCD-; 390). Linear regressions evaluated the influence of hippocampal grading on cognition in preclinical and prodromal AD. Lower global cognition, as measured by increased ADAS-13, was associated with hippocampal grading: NC (p < .001), eMCI (p < .05), lMCI (p < .05), and AD (p = .01). Lower global cognition as measured increased CDR-SB was associated with hippocampal grading in lMCI (p < .05) and AD (p < .001). Lower RAVLT performance was associated with hippocampal grading in SCD- (p < .05) and SCD+ (p < .05). These findings suggest that hippocampal grading is associated with global cognition in NC, eMCI, lMCI, and AD. Early changes in episodic memory during pre-clinical AD are associated with changes in hippocampal grading. Hippocampal grading may be sensitive to progressive changes early in the disease course.

Prospective classification of Alzheimer's disease conversion from mild cognitive impairment

Alzheimer's disease (AD) is emerging as a serious problem with the rapid aging of the population, but due to the unclear cause of the disease and the absence of therapy, appropriate preventive measures are the next best thing. For this reason, it is important to early detect whether the disease converts from mild cognitive impairment (MCI) which is a prodromal phase of AD. With the advance in brain imaging techniques, various machine learning algorithms have become able to predict the conversion from MCI to AD by learning brain atrophy patterns. However, at the time of diagnosis, it is difficult to distinguish between the conversion group and the non-conversion group of subjects because the difference between groups is small, but the within-group variability is large in brain images. After a certain period of time, the subjects of conversion group show significant brain atrophy, whereas subjects of non-conversion group show only subtle changes due to the normal aging effect. This difference on brain atrophy makes the brain images more discriminative for learning. Motivated by this, we propose a method to perform classification by projecting brain images into the future, namely prospective classification. The experiments on the Alzheimer's Disease Neuroimaging Initiative dataset show that the prospective classification outperforms ordinary classification. Moreover, the features of prospective classification indicate the brain regions that significantly influence the conversion from MCI to AD.

Towards better interpretable and generalizable AD detection using collective artificial intelligence

Alzheimer's Disease is the most common cause of dementia. Accurate diagnosis and prognosis of this disease are essential to design an appropriate treatment plan, increasing the life expectancy of the patient. Intense research has been conducted on the use of machine learning to identify Alzheimer's Disease from neuroimaging data, such as structural magnetic resonance imaging. In recent years, advances of deep learning in computer vision suggest a new research direction for this problem. Current deep learning-based approaches in this field, however, have a number of drawbacks, including the interpretability of model decisions, a lack of generalizability information and a lower performance compared to traditional machine learning techniques. In this paper, we design a two-stage framework to overcome these limitations. In the first stage, an ensemble of 125 U-Nets is used to grade the input image, producing a 3D map that reflects the disease severity at voxel-level. This map can help to localize abnormal brain areas caused by the disease. In the second stage, we model a graph per individual using the generated grading map and other information about the subject. We propose to use a graph convolutional neural network classifier for the final classification. As a result, our framework demonstrates comparative performance to the state-of-the-art methods in different datasets for both diagnosis and prognosis. We also demonstrate that the use of a large ensemble of U-Nets offers a better generalization capacity for our framework.

External validation of existing dementia prediction models on observational health data

BACKGROUND

Many dementia prediction models have been developed, but only few have been externally validated, which hinders clinical uptake and may pose a risk if models are applied to actual patients regardless. Externally validating an existing prediction model is a difficult task, where we mostly rely on the completeness of model reporting in a published article. In this study, we aim to externally validate existing dementia prediction models. To that end, we define model reporting criteria, review published studies, and externally validate three well reported models using routinely collected health data from administrative claims and electronic health records.

METHODS

We identified dementia prediction models that were developed between 2011 and 2020 and assessed if they could be externally validated given a set of model criteria. In addition, we externally validated three of these models (Walters' Dementia Risk Score, Mehta's RxDx-Dementia Risk Index, and Nori's ADRD dementia prediction model) on a network of six observational health databases from the United States, United Kingdom, Germany and the Netherlands, including the original development databases of the models.

RESULTS

We reviewed 59 dementia prediction models. All models reported the prediction method, development database, and target and outcome definitions. Less frequently reported by these 59 prediction models were predictor definitions (52 models) including the time window in which a predictor is assessed (21 models), predictor coefficients (20 models), and the time-at-risk (42 models). The validation of the model by Walters (development c-statistic: 0.84) showed moderate transportability (0.67-0.76 c-statistic). The Mehta model (development c-statistic: 0.81) transported well to some of the external databases (0.69-0.79 c-statistic). The Nori model (development AUROC: 0.69) transported well (0.62-0.68 AUROC) but performed modestly overall. Recalibration showed improvements for the Walters and Nori models, while recalibration could not be assessed for the Mehta model due to unreported baseline hazard.

CONCLUSION

We observed that reporting is mostly insufficient to fully externally validate published dementia prediction models, and therefore, it is uncertain how well these models would work in other clinical settings. We emphasize the importance of following established guidelines for reporting clinical prediction models. We recommend that reporting should be more explicit and have external validation in mind if the model is meant to be applied in different settings.

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.

Regional brain atrophy and cognitive decline depend on definition of subjective cognitive decline

Background

People with subjective cognitive decline (SCD) may be at increased risk for Alzheimer’s disease (AD). However, not all studies have observed this increased risk. This project examined whether four common methods of defining SCD yields different patterns of atrophy and future cognitive decline between cognitively normal older adults with (SCD+ ) and without SCD (SCD−).

Methods

Data from 273 Alzheimer’s Disease Neuroimaging Initiative cognitively normal older adults were examined. To operationalize SCD we used four common methods: Cognitive Change Index (CCI), Everyday Cognition Scale (ECog), ECog + Worry, and Worry. Voxel-based logistic regressions were applied to deformation-based morphology results to determine if regional atrophy between SCD− and SCD+ differed by SCD definition. Linear mixed-effects models were used to evaluate differences in future cognitive decline.

Results

Results varied between the four methods of defining SCD. Left hippocampal grading was more similar to AD in SCD+ than SCD− when using the CCI (p = .041) and Worry (p = .021) definitions. The right (p=.008) and left (p=.003) superior temporal regions had smaller volumes in SCD+ than SCD−, but only with the ECog. SCD+ was associated with greater future cognitive decline measured by Alzheimer’s Disease Assessment Scale, but only with the CCI definition. In contrast, only the ECog definition of SCD was associated with future decline on the Montreal Cognitive Assessment.

Conclusion

These findings suggest that the various methods used to differentiate between SCD− and SCD+ influence whether volume differences and findings of cognitive decline are observed between groups in this retrospective analysis.

Prediction of Alzheimer's Disease Progression Based on Magnetic Resonance Imaging

The neuroimaging method of multimodal magnetic resonance imaging (MRI) can identify the changes in brain structure and function caused by Alzheimer's disease (AD) at different stages, and it is a practical method to study the mechanism of AD progression. This paper reviews the studies of methods and biomarkers for predicting AD progression based on multimodal MRI. First, different approaches for predicting AD progression are analyzed and summarized, including machine learning, deep learning, regression, and other MRI analysis methods. Then, the effective biomarkers of AD progression under structural magnetic resonance imaging, diffusion tensor imaging, functional magnetic resonance imaging, and arterial spin labeling modes of MRI are summarized. It is believed that the brain changes shown on MRI may be related to the cognitive decline in different prodrome stages of AD, which is conducive to the further realization of early intervention and prevention of AD. Finally, the deficiencies of the existing studies are analyzed in terms of data set size, data heterogeneity, processing methods, and research depth. More importantly, future research directions are proposed, including enriching data sets, simplifying biomarkers, utilizing multimodal magnetic resonance, etc. In the future, the study of AD progression by multimodal MRI will still be a challenge but also a significant research hotspot.

Automatic Prediction of Cognitive and Functional Decline Can Significantly Decrease the Number of Subjects Required for Clinical Trials in Early Alzheimer's Disease

Background:

While both cognitive and magnetic resonance imaging (MRI) data has been used to predict progression in Alzheimer’s disease, heterogeneity between patients makes it challenging to predict the rate of cognitive and functional decline for individual subjects.

Objective:

To investigate prognostic power of MRI-based biomarkers of medial temporal lobe atrophy and macroscopic tissue change to predict cognitive decline in individual patients in clinical trials of early Alzheimer’s disease.

Methods:

Data used in this study included 312 patients with mild cognitive impairment from the ADNI dataset with baseline MRI, cerebrospinal fluid amyloid-β, cognitive test scores, and a minimum of two-year follow-up information available. We built a prognostic model using baseline cognitive scores and MRI-based features to determine which subjects remain stable and which functionally decline over 2 and 3-year follow-up periods.

Results:

Combining both sets of features yields 77%accuracy (81%sensitivity and 75%specificity) to predict cognitive decline at 2 years (74%accuracy at 3 years with 75%sensitivity and 73%specificity). When used to select trial participants, this tool yields a 3.8-fold decrease in the required sample size for a 2-year study (2.8-fold decrease for a 3-year study) for a hypothesized 25%treatment effect to reduce cognitive decline.

Conclusion:

When used in clinical trials for cohort enrichment, this tool could accelerate development of new treatments by significantly increasing statistical power to detect differences in cognitive decline between arms. In addition, detection of future decline can help clinicians improve patient management strategies that will slow or delay symptom progression.

Risk of early-onset dementia among persons with tinnitus: a retrospective case-control study

Higher rates of poor cognitive performance are known to prevail among persons with tinnitus in all age groups. However, no study has explored the association between tinnitus and early-onset dementia. We hypothesize that tinnitus may precede or occur concurrently with subclinical or early onset dementia in adults younger than 65 years of age. This case–control study used data from the Taiwan National Health Insurance Research Database, identifying 1308 patients with early-onset dementia (dementia diagnosed before 65 years of age) and 1308 matched controls. We used multivariable logistic regressions to estimate odds ratios (ORs) for prior tinnitus among patients with dementia versus controls. Among total 2616 sample participants, the prevalence of prior tinnitus was 18%, 21.5% among cases and 14.5% among controls (p < 0.001). Multivariable logistic regression showed and adjusted OR for prior tinnitus of 1.6 for cases versus controls (95% CI: 1.3 ~ 2.0). After adjusting for sociodemographic characteristics and medical co-morbidities, patients with early-onset dementia had a 67% higher likelihood of having prior tinnitus (OR = 1.628; 95% CI = 1.321–2.006). Our findings showed that pre-existing tinnitus was associated with a 68% increased risk of developing early-onset dementia among young and middle-aged adults. The results call for greater awareness of tinnitus as a potential harbinger of future dementia in this population.

Accuracy of MRI Classification Algorithms in a Tertiary Memory Center Clinical Routine Cohort

BACKGROUND

Automated volumetry software (AVS) has recently become widely available to neuroradiologists. MRI volumetry with AVS may support the diagnosis of dementias by identifying regional atrophy. Moreover, automatic classifiers using machine learning techniques have recently emerged as promising approaches to assist diagnosis. However, the performance of both AVS and automatic classifiers have been evaluated mostly in the artificial setting of research datasets.

OBJECTIVE

Our aim was to evaluate the performance of two AVS and an automatic classifier in the clinical routine condition of a memory clinic.

METHODS

We studied 239 patients with cognitive troubles from a single memory center cohort. Using clinical routine T1-weighted MRI, we evaluated the classification performance of: 1) univariate volumetry using two AVS (volBrain and Neuroreader™); 2) Support Vector Machine (SVM) automatic classifier, using either the AVS volumes (SVM-AVS), or whole gray matter (SVM-WGM); 3) reading by two neuroradiologists. The performance measure was the balanced diagnostic accuracy. The reference standard was consensus diagnosis by three neurologists using clinical, biological (cerebrospinal fluid) and imaging data and following international criteria.

RESULTS

Univariate AVS volumetry provided only moderate accuracies (46% to 71% with hippocampal volume). The accuracy improved when using SVM-AVS classifier (52% to 85%), becoming close to that of SVM-WGM (52 to 90%). Visual classification by neuroradiologists ranged between SVM-AVS and SVM-WGM.

CONCLUSION

In the routine practice of a memory clinic, the use of volumetric measures provided by AVS yields only moderate accuracy. Automatic classifiers can improve accuracy and could be a useful tool to assist diagnosis.

Early diagnosis of Alzheimer's disease on ADNI data using novel longitudinal score based on functional principal component analysis

Methods: Alzheimer's disease (AD) is a worldwide prevalent age-related neurodegenerative disease with no available cure yet. Early prognosis is therefore crucial for planning proper clinical intervention. It is especially true for people diagnosed with mild cognitive impairment, to whom the prediction of whether and when the future disease onset would happen is particularly valuable. However, such prognostic prediction has been proven to be challenging, and previous studies have only achieved limited success. Approach: In this study, we seek to extract the principal component of the longitudinal disease progression trajectory in the early stage of AD, measured as the magnetic resonance imaging (MRI)-derived structural volume, to predict the onset of AD for mild cognitive impaired patients two years ahead. Results: Cross-validation results of LASSO regression using the longitudinal functional principal component (FPC) features show significant improved predictive power compared to training using the baseline volume 12 months before AD conversion [area under the receiver operating characteristic curve (AUC) of 0.802 versus 0.732] and 24 months before AD conversion (AUC of 0.816 versus 0.717). Conclusions: We present a framework using the FPCA to extract features from MRI-derived information collected from multiple timepoints. The results of our study demonstrate the advantageous predictive power of the population-based longitudinal features to predict the disease onset compared with using only cross-sectional data-based on volumetric features extracted from a single timepoint, demonstrating the improved prediction power using FPC-derived longitudinal features.

Multi-scale graph-based grading for Alzheimer's disease prediction

The prediction of subjects with mild cognitive impairment (MCI) who will progress to Alzheimer's disease (AD) is clinically relevant, and may above all have a significant impact on accelerating the development of new treatments. In this paper, we present a new MRI-based biomarker that enables us to accurately predict conversion of MCI subjects to AD. In order to better capture the AD signature, we introduce two main contributions. First, we present a new graph-based grading framework to combine inter-subject similarity features and intra-subject variability features. This framework involves patch-based grading of anatomical structures and graph-based modeling of structure alteration relationships. Second, we propose an innovative multiscale brain analysis to capture alterations caused by AD at different anatomical levels. Based on a cascade of classifiers, this multiscale approach enables the analysis of alterations of whole brain structures and hippocampus subfields at the same time. During our experiments using the ADNI-1 dataset, the proposed multiscale graph-based grading method obtained an area under the curve (AUC) of 81% to predict conversion of MCI subjects to AD within three years. Moreover, when combined with cognitive scores, the proposed method obtained 85% of AUC. These results are competitive in comparison to state-of-the-art methods evaluated on the same dataset.

Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases

Biomarkers for dementia of Alzheimer's type (DAT) are sought to facilitate accurate prediction of the disease onset, ideally predating the onset of cognitive deterioration. T1-weighted magnetic resonance imaging (MRI) is a commonly used neuroimaging modality for measuring brain structure in vivo, potentially providing information enabling the design of biomarkers for DAT. We propose a novel biomarker using structural MRI volume-based features to compute a similarity score for the individual's structural patterns relative to those observed in the DAT group. We employed ensemble-learning framework that combines structural features in most discriminative ROIs to create an aggregate measure of neurodegeneration in the brain. This classifier is trained on 423 stable normal control (NC) and 330 DAT subjects, where clinical diagnosis is likely to have the highest certainty. Independent validation on 8,834 unseen images from ADNI, AIBL, OASIS, and MIRIAD Alzheimer's disease (AD) databases showed promising potential to predict the development of DAT depending on the time-to-conversion (TTC). Classification performance on stable versus progressive mild cognitive impairment (MCI) groups achieved an AUC of 0.81 for TTC of 6 months and 0.73 for TTC of up to 7 years, achieving state-of-the-art results. The output score, indicating similarity to patterns seen in DAT, provides an intuitive measure of how closely the individual's brain features resemble the DAT group. This score can be used for assessing the presence of AD structural atrophy patterns in normal aging and MCI stages, as well as monitoring the progression of the individual's brain along with the disease course.

MRI and cognitive scores complement each other to accurately predict Alzheimer's dementia 2 to 7 years before clinical onset

BACKGROUND

Predicting cognitive decline and the eventual onset of dementia in patients with Mild Cognitive Impairment (MCI) is of high value for patient management and potential cohort enrichment in pharmaceutical trials. We used cognitive scores and MRI biomarkers from a single baseline visit to predict the onset of dementia due to AD in an amnestic MCI (aMCI) population over a nine-year follow-up period.

METHOD

All aMCI subjects from ADNI1, ADNI2, and ADNI-GO with available baseline neurocognitive scores and T1w MRI were included in the study (n = 756). We built a Naïve Bayes classifier for every year over a 9-year follow-up period and tested each one with Leave one out cross validation.

RESULTS

We reached 87% prediction accuracy at five years follow-up with an AUC > 0.85 from two to seven years (peaking at 0.92 at five years). Both neurocognitive scores and MRI biomarkers were needed to make the prognostic models highly sensitive and specific, especially for longer follow-ups. MRI features are more sensitive, while cognitive features bring specificity to the prediction.

CONCLUSION

Combining cognitive scores and MRI biomarkers yield accurate prediction years before onset of dementia. Such a tool may be helpful in selecting patients that would most benefit from lifestyle changes, and eventually early treatments that would slow cognitive decline and delay the onset of dementia.

Correlation Between Hippocampal Volume and Autobiographical Memory Depending on Retrieval Frequency in Healthy Individuals and Patients with Alzheimer's Disease

The hippocampus plays an indispensable role in episodic memory, particularly during the consolidation process. However, its precise role in retrieval of episodic memory is still ambiguous. In this study, we investigated the correlation of hippocampal morphometry and the performance in an autobiographical memory task in 27 healthy controls and 24 patients suffering from Alzheimer's disease (AD). Most importantly, correlations were defined separately and comparatively for memory contents with different retrieval frequency in the past. In healthy subjects, memory performance for seldom retrieved autobiographical events was significantly associated with gray matter density in the bilateral hippocampus, whereas this correlation was not present for events with high retrieval frequency. This pattern of findings confirms that retrieval frequency plays a critical role in the consolidation of episodic autobiographical memories, thereby making them more independent of the hippocampal system. In AD patients, on the other hand, successful memory retrieval appeared to be related to hippocampal morphometry irrespective of the contents' retrieval frequency, comprising events with high retrieval frequency, too. The observed differences between patients and control subjects suggest that AD-related neurodegeneration not only impairs the function, but also decreases the functional specialization of the hippocampal memory system, which, thus, may be considered as marker for AD.

Multimodal Hippocampal Subfield Grading For Alzheimer's Disease Classification

Numerous studies have proposed biomarkers based on magnetic resonance imaging (MRI) to detect and predict the risk of evolution toward Alzheimer's disease (AD). Most of these methods have focused on the hippocampus, which is known to be one of the earliest structures impacted by the disease. To date, patch-based grading approaches provide among the best biomarkers based on the hippocampus. However, this structure is complex and is divided into different subfields, not equally impacted by AD. Former in-vivo imaging studies mainly investigated structural alterations of these subfields using volumetric measurements and microstructural modifications with mean diffusivity measurements. The aim of our work is to improve the current classification performances based on the hippocampus with a new multimodal patch-based framework combining structural and diffusivity MRI. The combination of these two MRI modalities enables the capture of subtle structural and microstructural alterations. Moreover, we propose to study the efficiency of this new framework applied to the hippocampal subfields. To this end, we compare the classification accuracy provided by the different hippocampal subfields using volume, mean diffusivity, and our novel multimodal patch-based grading framework combining structural and diffusion MRI. The experiments conducted in this work show that our new multimodal patch-based method applied to the whole hippocampus provides the most discriminating biomarker for advanced AD detection while our new framework applied into subiculum obtains the best results for AD prediction, improving by two percentage points the accuracy compared to the whole hippocampus.

Brain atrophy and patch-based grading in individuals from the CIMA-Q study: a progressive continuum from subjective cognitive decline to AD

It has been proposed that individuals developing Alzheimer's disease (AD) first experience a phase expressing subjective complaints of cognitive decline (SCD) without objective cognitive impairment. Using magnetic resonance imaging (MRI), our objective was to verify whether SNIPE probability grading, a new MRI analysis technique, would distinguish between clinical dementia stage of AD: Cognitively healthy controls without complaint (CH), SCD, mild cognitive impairment, and AD. SNIPE score in the hippocampus and entorhinal cortex was applied to anatomical T1-weighted MRI of 143 participants from the Consortium pour l'identification précoce de la maladie Alzheimer - Québec (CIMA-Q) study and compared to standard atrophy measures (volumes and cortical thicknesses). Compared to standard atrophy measures, SNIPE score appeared more sensitive to differentiate clinical AD since differences between groups reached a higher level of significance and larger effect sizes. However, no significant difference was observed between SCD and CH groups. Combining both types of measures did not improve between-group differences. Further studies using a combination of biomarkers beyond anatomical MRI might be needed to identify individuals with SCD who are on the beginning of the clinical continuum of AD.

Supervised pathway analysis of blood gene expression profiles in Alzheimer's disease

Early identification and treatment of Alzheimer's disease (AD) is hampered by the lack of easily accessible biomarkers. Currently available fluid biomarkers of AD provide indications of the disease stage; however, these are measured in the cerebrospinal fluid, requiring invasive procedures, which are not applicable at the population level. Thus, gene expression profiling of blood provides a viable alternative as a way to screen individuals at risk of AD. Previous studies have shown that despite the limited permeability of the blood-brain barriers, expression profiles of blood genes can be used for the diagnosis and prognosis of several brain disorders. Here, we propose a new approach to pathway analysis of blood gene expression profiles to classify healthy (control [CTL]), mildly cognitively impaired (mild cognitive impairment [MCI]; preclinical stage of AD), and AD subjects. In the pathway analysis, gene expression data are mapped to pathway scores according to a predefined gene set instead of considering each gene separately. The robustness of the analysis enables detection of weak differences between groups owing to the inherent dimension reduction. Our proposed method for pathway analysis takes advantage of linear discriminant analysis for identifying a linear combination of features best separating groups of subjects within each gene set. The gene expression data were retrieved from Gene Expression Omnibus (batch 1: GSE63060; batch 2: GSE63061). Predefined gene sets for pathway analysis were obtained from the Broad Institute Collection of Curated Pathways. The method achieved a 10-fold cross-validated area under receiver operating characteristic curve of 0.84 for classification of AD versus CTL and 0.80 for classification of mild cognitive impairment versus CTL. These results reveal the good potential of blood-based biomarkers for assisting early diagnosis and disease monitoring of AD.

Predicting progression from normal cognition to mild cognitive impairment for individuals at 5 years

Recent evidence indicates that measures from cerebrospinal fluid, MRI scans and cognitive testing obtained from cognitively normal individuals can be used to predict likelihood of progression to mild cognitive impairment several years later, for groups of individuals. However, it remains unclear whether these measures are useful for predicting likelihood of progression for an individual. The increasing focus on early intervention in clinical trials for Alzheimer's disease emphasizes the importance of improving the ability to identify which cognitively normal individuals are more likely to progress over time, thus allowing researchers to efficiently screen participants, as well as determine the efficacy of any treatment intervention. The goal of this study was to determine which measures, obtained when individuals were cognitively normal, predict on an individual basis, the onset of clinical symptoms associated with a diagnosis of mild cognitive impairment due to Alzheimer's disease. Cognitively normal participants (n = 224, mean baseline age = 57 years) were evaluated with a range of measures, including: cerebrospinal fluid amyloid-β and phosphorylated-tau, hippocampal and entorhinal cortex volume, cognitive tests scores and APOE genotype. They were then followed to determine which individuals developed mild cognitive impairment over time (mean follow-up = 11 years). The primary outcome was progression from normal cognition to the onset of clinical symptoms of mild cognitive impairment due to Alzheimer's disease at 5 years post-baseline. Time-dependent receiver operating characteristic analyses examined the sensitivity and specificity of individual measures, and combinations of measures, as predictors of the outcome. Six measures, in combination, were the most parsimonious predictors of transition to mild cognitive impairment 5 years after baseline (area under the curve = 0.85; sensitivity = 0.80, specificity = 0.75). The addition of variables from each domain significantly improved the accuracy of prediction. The incremental accuracy of prediction achieved by adding individual measures or sets of measures successively to one another was also examined, as might be done when enrolling individuals in a clinical trial. The results indicate that biomarkers obtained when individuals are cognitively normal can be used to predict which individuals are likely to develop clinical symptoms at 5 years post-baseline. As a number of the measures included in the study could also be used as subject selection criteria in a clinical trial, the findings also provide information about measures that would be useful for screening in a clinical trial aimed at individuals with preclinical Alzheimer's disease.

Lifespan Changes of the Human Brain In Alzheimer's Disease

Brain imaging studies have shown that slow and progressive cerebral atrophy characterized the development of Alzheimer's Disease (AD). Despite a large number of studies dedicated to AD, key questions about the lifespan evolution of AD biomarkers remain open. When does the AD model diverge from the normal aging model? What is the lifespan trajectory of imaging biomarkers for AD? How do the trajectories of biomarkers in AD differ from normal aging? To answer these questions, we proposed an innovative way by inferring brain structure model across the entire lifespan using a massive number of MRI (N = 4329). We compared the normal model based on 2944 control subjects with the pathological model based on 3262 patients (AD + Mild cognitive Impaired subjects) older than 55 years and controls younger than 55 years. Our study provides evidences of early divergence of the AD models from the normal aging trajectory before 40 years for the hippocampus, followed by the lateral ventricles and the amygdala around 40 years. Moreover, our lifespan model reveals the evolution of these biomarkers and suggests close abnormality evolution for the hippocampus and the amygdala, whereas trajectory of ventricular enlargement appears to follow an inverted U-shape. Finally, our models indicate that medial temporal lobe atrophy and ventricular enlargement are two mid-life physiopathological events characterizing AD brain.

T2 Relaxometry and Diffusion Tensor Indices of the Hippocampus and Entorhinal Cortex Improve Sensitivity and Specificity of MRI to Detect Amnestic Mild Cognitive Impairment and Alzheimer's Disease Dementia

BACKGROUND

Quantitative T2 and diffusion MRI indices inform about tissue state and microstructure, both of which may be affected by pathology before tissue atrophy.

PURPOSE

To evaluate the capability of both volumetric and quantitative MRI (qMRI) of the hippocampus and entorhinal cortex (EC) for classification of amnestic mild cognitive impairment (aMCI) and Alzheimer's disease dementia (ADD).

STUDY TYPE

Retrospective cross-sectional study.

POPULATION

Consecutive cohorts of healthy age-matched controls (n = 62), aMCI patients (n = 25), and ADD patients (n = 14).

FIELD STRENGTH/SEQUENCE

3T using T1-weighted imaging, T2-weighted imaging, T2 relaxometry and diffusion tensor imaging (DTI).

ASSESSMENT

Montreal Cognitive Assessment and paired associate learning tests for cognitive state. Hippocampal subfield volumes by the automated segmentation of hippocampal subfields system from structural brain images. T2 relaxation time and DTI indices quantified for hippocampal subfields. The fraction of voxels with high T2 values (>20 ms above subfield median) was calculated and regionalized for hippocampus and EC.

STATISTICAL TESTS

Support vector machine and receiver operating characteristic analyses from cognitive and MRI data.

RESULTS

qMRI classified aMCI and ADD with excellent sensitivity (79.0% and 94.5%, respectively) and specificity (85.6% and 86.1%, respectively), superior to volumes alone (70.0% and 84.5% for respective sensitivities; 82.2 and 91.1 for respective specificities) and similar to cognitive tests (61.7% and 87.5% for respective sensitivities; 88.2% and 90.7% for respective specificities). Regions of high T2 are dispersed throughout each hippocampal subfield in aMCI and ADD with higher concentration than controls, and was most pronounced in the EC. No other individual qMRI marker than EC volume can separate aMCI from ADD, however. DATA CONCLUSION: qMRI markers of hippocampal and entorhinal tissue states are sensitive and specific classifiers of aMCI and ADD. They may serve as markers of a neurodegenerative state preceding volume loss.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;49:445-455.

Adaptive fusion of texture-based grading for Alzheimer's disease classification

Alzheimer's disease is a neurodegenerative process leading to irreversible mental dysfunctions. To date, diagnosis is established after incurable brain structure alterations. The development of new biomarkers is crucial to perform an early detection of this disease. With the recent improvement of magnetic resonance imaging, numerous methods were proposed to improve computer-aided detection. Among these methods, patch-based grading framework demonstrated state-of-the-art performance. Usually, methods based on this framework use intensity or grey matter maps. However, it has been shown that texture filters improve classification performance in many cases. The aim of this work is to improve performance of patch-based grading framework with the development of a novel texture-based grading method. In this paper, we study the potential of multi-directional texture maps extracted with 3D Gabor filters to improve patch-based grading method. We also proposed a novel patch-based fusion scheme to efficiently combine multiple grading maps. To validate our approach, we study the optimal set of filters and compare the proposed method with different fusion schemes. In addition, we also compare our new texture-based grading biomarker with state-of-the-art methods. Experiments show an improvement of AD detection and prediction accuracy. Moreover, our method obtains competitive performance with 91.3% of accuracy and 94.6% of area under a curve for AD detection.

Reproducible evaluation of classification methods in Alzheimer's disease: Framework and application to MRI and PET data

A large number of papers have introduced novel machine learning and feature extraction methods for automatic classification of Alzheimer's disease (AD). However, while the vast majority of these works use the public dataset ADNI for evaluation, they are difficult to reproduce because different key components of the validation are often not readily available. These components include selected participants and input data, image preprocessing and cross-validation procedures. The performance of the different approaches is also difficult to compare objectively. In particular, it is often difficult to assess which part of the method (e.g. preprocessing, feature extraction or classification algorithms) provides a real improvement, if any. In the present paper, we propose a framework for reproducible and objective classification experiments in AD using three publicly available datasets (ADNI, AIBL and OASIS). The framework comprises: i) automatic conversion of the three datasets into a standard format (BIDS); ii) a modular set of preprocessing pipelines, feature extraction and classification methods, together with an evaluation framework, that provide a baseline for benchmarking the different components. We demonstrate the use of the framework for a large-scale evaluation on 1960 participants using T1 MRI and FDG PET data. In this evaluation, we assess the influence of different modalities, preprocessing, feature types (regional or voxel-based features), classifiers, training set sizes and datasets. Performances were in line with the state-of-the-art. FDG PET outperformed T1 MRI for all classification tasks. No difference in performance was found for the use of different atlases, image smoothing, partial volume correction of FDG PET images, or feature type. Linear SVM and L2-logistic regression resulted in similar performance and both outperformed random forests. The classification performance increased along with the number of subjects used for training. Classifiers trained on ADNI generalized well to AIBL and OASIS. All the code of the framework and the experiments is publicly available: general-purpose tools have been integrated into the Clinica software (www.clinica.run) and the paper-specific code is available at: https://gitlab.icm-institute.org/aramislab/AD-ML.

Radiological-Pathological Correlation in Alzheimer's Disease: Systematic Review of Antemortem Magnetic Resonance Imaging Findings

BACKGROUND

The standard method of ascertaining Alzheimer's disease (AD) remains postmortem assessment of amyloid plaques and neurofibrillary degeneration. Vascular pathology, Lewy bodies, TDP-43, and hippocampal sclerosis are frequent comorbidities. There is therefore a need for biomarkers that can assess these etiologies and provide a diagnosis in vivo.

OBJECTIVE

We conducted a systematic review of published radiological-pathological correlation studies to determine the relationship between antemortem magnetic resonance imaging (MRI) and neuropathological findings in AD.

METHODS

We explored PubMed in June-July 2015 using "Alzheimer's disease" and combinations of radiological and pathological terms. After exclusion following screening and full-text assessment of the 552 extracted manuscripts, three others were added from their reference list. In the end, we report results based on 27 articles.

RESULTS

Independently of normal age-related brain atrophy, AD pathology is associated with whole-brain and hippocampal atrophy and ventricular expansion as observed on T1-weighted images. Moreover, cerebral amyloid angiopathy and cortical microinfarcts are also related to brain volume loss in AD. Hippocampal sclerosis and TDP-43 are associated with hippocampal and medial temporal lobe atrophy, respectively. Brain volume loss correlates more strongly with tangles than with any other pathological finding. White matter hyperintensities observed on proton density, T2-weighted and FLAIR images are strongly related to vascular pathologies, but are also associated with other histological changes such as gliosis or demyelination.

CONCLUSION

Cerebral atrophy and white matter changes in the living brain reflect underlying neuropathology and may be detectable using antemortem MRI. In vivo MRI may therefore be an avenue for AD pathological staging.

Your algorithm might think the hippocampus grows in Alzheimer's disease: Caveats of longitudinal automated hippocampal volumetry

Hippocampal atrophy rate-measured using automated techniques applied to structural MRI scans-is considered a sensitive marker of disease progression in Alzheimer's disease, frequently used as an outcome measure in clinical trials. Using publicly accessible data from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we examined 1-year hippocampal atrophy rates generated by each of five automated or semiautomated hippocampal segmentation algorithms in patients with Alzheimer's disease, subjects with mild cognitive impairment, or elderly controls. We analyzed MRI data from 398 and 62 subjects available at baseline and at 1 year at MRI field strengths of 1.5 T and 3 T, respectively. We observed a high rate of hippocampal segmentation failures across all algorithms and diagnostic categories, with only 50.8% of subjects at 1.5 T and 58.1% of subjects at 3 T passing stringent segmentation quality control. We also found that all algorithms identified several subjects (between 2.94% and 48.68%) across all diagnostic categories showing increases in hippocampal volume over 1 year. For any given algorithm, hippocampal "growth" could not entirely be explained by excluding patients with flawed hippocampal segmentations, scan-rescan variability, or MRI field strength. Furthermore, different algorithms did not uniformly identify the same subjects as hippocampal "growers," and showed very poor concordance in estimates of magnitude of hippocampal volume change over time (intraclass correlation coefficient 0.319 at 1.5 T and 0.149 at 3 T). This precluded a meaningful analysis of whether hippocampal "growth" represents a true biological phenomenon. Taken together, our findings suggest that longitudinal hippocampal volume change should be interpreted with considerable caution as a biomarker. Hum Brain Mapp 38:2875-2896, 2017. © 2017 Wiley Periodicals, Inc.

Recent publications from the Alzheimer's Disease Neuroimaging Initiative: Reviewing progress toward improved AD clinical trials

INTRODUCTION

The Alzheimer's Disease Neuroimaging Initiative (ADNI) has continued development and standardization of methodologies for biomarkers and has provided an increased depth and breadth of data available to qualified researchers. This review summarizes the over 400 publications using ADNI data during 2014 and 2015.

METHODS

We used standard searches to find publications using ADNI data.

RESULTS

(1) Structural and functional changes, including subtle changes to hippocampal shape and texture, atrophy in areas outside of hippocampus, and disruption to functional networks, are detectable in presymptomatic subjects before hippocampal atrophy; (2) In subjects with abnormal β-amyloid deposition (Aβ+), biomarkers become abnormal in the order predicted by the amyloid cascade hypothesis; (3) Cognitive decline is more closely linked to tau than Aβ deposition; (4) Cerebrovascular risk factors may interact with Aβ to increase white-matter (WM) abnormalities which may accelerate Alzheimer's disease (AD) progression in conjunction with tau abnormalities; (5) Different patterns of atrophy are associated with impairment of memory and executive function and may underlie psychiatric symptoms; (6) Structural, functional, and metabolic network connectivities are disrupted as AD progresses. Models of prion-like spreading of Aβ pathology along WM tracts predict known patterns of cortical Aβ deposition and declines in glucose metabolism; (7) New AD risk and protective gene loci have been identified using biologically informed approaches; (8) Cognitively normal and mild cognitive impairment (MCI) subjects are heterogeneous and include groups typified not only by "classic" AD pathology but also by normal biomarkers, accelerated decline, and suspected non-Alzheimer's pathology; (9) Selection of subjects at risk of imminent decline on the basis of one or more pathologies improves the power of clinical trials; (10) Sensitivity of cognitive outcome measures to early changes in cognition has been improved and surrogate outcome measures using longitudinal structural magnetic resonance imaging may further reduce clinical trial cost and duration; (11) Advances in machine learning techniques such as neural networks have improved diagnostic and prognostic accuracy especially in challenges involving MCI subjects; and (12) Network connectivity measures and genetic variants show promise in multimodal classification and some classifiers using single modalities are rivaling multimodal classifiers.

DISCUSSION

Taken together, these studies fundamentally deepen our understanding of AD progression and its underlying genetic basis, which in turn informs and improves clinical trial design.

Detection of Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Longitudinal Brain MRI

Mild Cognitive Impairment (MCI) is an intermediate stage between healthy and Alzheimer's disease (AD). To enable early intervention it is important to identify the MCI subjects that will convert to AD in an early stage. In this paper, we provide a new method to distinguish between MCI patients that either convert to Alzheimer's Disease (MCIc) or remain stable (MCIs), using only longitudinal T1-weighted MRI. Currently, most longitudinal studies focus on volumetric comparison of a few anatomical structures, thereby ignoring more detailed development inside and outside those structures. In this study we propose to exploit the anatomical development within the entire brain, as found by a non-rigid registration approach. Specifically, this anatomical development is represented by the Stationary Velocity Field (SVF) from registration between the baseline and follow-up images. To make the SVFs comparable among subjects, we use the parallel transport method to align them in a common space. The normalized SVF together with derived features are then used to distinguish between MCIc and MCIs subjects. This novel feature space is reduced using a Kernel Principal Component Analysis method, and a linear support vector machine is used as a classifier. Extensive comparative experiments are performed to inspect the influence of several aspects of our method on classification performance, specifically the feature choice, the smoothing parameter in the registration and the use of dimensionality reduction. The optimal result from a 10-fold cross-validation using 36 month follow-up data shows competitive results: accuracy 92%, sensitivity 95%, specificity 90%, and AUC 94%. Based on the same dataset, the proposed approach outperforms two alternative ones that either depends on the baseline image only, or uses longitudinal information from larger brain areas. Good results were also obtained when scans at 6, 12, or 24 months were used for training the classifier. Besides the classification power, the proposed method can quantitatively compare brain regions that have a significant difference in development between the MCIc and MCIs groups.

Rey's Auditory Verbal Learning Test scores can be predicted from whole brain MRI in Alzheimer's disease

Rey's Auditory Verbal Learning Test (RAVLT) is a powerful neuropsychological tool for testing episodic memory, which is widely used for the cognitive assessment in dementia and pre-dementia conditions. Several studies have shown that an impairment in RAVLT scores reflect well the underlying pathology caused by Alzheimer's disease (AD), thus making RAVLT an effective early marker to detect AD in persons with memory complaints. We investigated the association between RAVLT scores (RAVLT Immediate and RAVLT Percent Forgetting) and the structural brain atrophy caused by AD. The aim was to comprehensively study to what extent the RAVLT scores are predictable based on structural magnetic resonance imaging (MRI) data using machine learning approaches as well as to find the most important brain regions for the estimation of RAVLT scores. For this, we built a predictive model to estimate RAVLT scores from gray matter density via elastic net penalized linear regression model. The proposed approach provided highly significant cross-validated correlation between the estimated and observed RAVLT Immediate (R = 0.50) and RAVLT Percent Forgetting (R = 0.43) in a dataset consisting of 806 AD, mild cognitive impairment (MCI) or healthy subjects. In addition, the selected machine learning method provided more accurate estimates of RAVLT scores than the relevance vector regression used earlier for the estimation of RAVLT based on MRI data. The top predictors were medial temporal lobe structures and amygdala for the estimation of RAVLT Immediate and angular gyrus, hippocampus and amygdala for the estimation of RAVLT Percent Forgetting. Further, the conversion of MCI subjects to AD in 3-years could be predicted based on either observed or estimated RAVLT scores with an accuracy comparable to MRI-based biomarkers.