Longitudinal progression of Alzheimer's-like patterns of atrophy in normal older adults: the SPARE-AD index

Amyloid imaging and memory change for prediction of cognitive impairment

PET radiotracers for in vivo measurement of β-amyloid (Aβ) deposition throughout the brain are contributing to early detection of the neuropathology associated with Alzheimer's disease and enhancing prediction of individuals most likely to develop cognitive impairment and dementia. However, the fact that 30 to 50% of cognitively normal older adults have varying but detectable levels of Aβ poses challenges and opportunities in using amyloid imaging in research and clinical applications. In this review, we summarize studies of the relationship between Aβ burden and cognitive status in impaired and unimpaired individuals and the relationship between Aβ burden and cognitive function. We conclude by operationalizing the way in which information on imaging-assessed Aβ burden and cognitive performance can be used jointly to improve prediction of clinical outcomes, to enhance understanding of the role of Aβ deposition in cognitive impairment, and to identify factors that promote cognitive resilience in the presence of Aβ.

Discriminant analysis of longitudinal cortical thickness changes in Alzheimer's disease using dynamic and network features

Neuroimage measures from magnetic resonance (MR) imaging, such as cortical thickness, have been playing an increasingly important role in searching for biomarkers of Alzheimer's disease (AD). Recent studies show that, AD, mild cognitive impairment (MCI) and normal control (NC) can be distinguished with relatively high accuracy using the baseline cortical thickness. With the increasing availability of large longitudinal datasets, it also becomes possible to study the longitudinal changes of cortical thickness and their correlation with the development of pathology in AD. In this study, the longitudinal cortical thickness changes of 152 subjects from 4 clinical groups (AD, NC, Progressive-MCI and Stable-MCI) selected from Alzheimer's Disease Neuroimaging Initiative (ADNI) are measured by our recently developed 4 D (spatial+temporal) thickness measuring algorithm. It is found that the 4 clinical groups demonstrate very similar spatial distribution of grey matter (GM) loss on cortex. To fully utilize the longitudinal information and better discriminate the subjects from 4 groups, especially between Stable-MCI and Progressive-MCI, 3 different categories of features are extracted for each subject, i.e., (1) static cortical thickness measures computed from the baseline and endline, (2) cortex thinning dynamics, such as the thinning speed (mm/year) and the thinning ratio (endline/baseline), and (3) network features computed from the brain network constructed based on the correlation between the longitudinal thickness changes of different regions of interest (ROIs). By combining the complementary information provided by features from the 3 categories, 2 classifiers are trained to diagnose AD and to predict the conversion to AD in MCI subjects, respectively. In the leave-one-out cross-validation, the proposed method can distinguish AD patients from NC at an accuracy of 96.1%, and can detect 81.7% (AUC = 0.875) of the MCI converters 6 months ahead of their conversions to AD. Also, by analyzing the brain network built via longitudinal cortical thickness changes, a significant decrease (p < 0.02) of the network clustering coefficient (associated with the development of AD pathology) is found in the Progressive-MCI group, which indicates the degenerated wiring efficiency of the brain network due to AD. More interestingly, the decreasing of network clustering coefficient of the olfactory cortex region was also found in the AD patients, which suggests olfactory dysfunction. Although the smell identification test is not performed in ADNI, this finding is consistent with other AD-related olfactory studies.

Brain morphometry and functional imaging techniques in dementia: methods, findings and relevance in forensic neurology

PURPOSE OF REVIEW

The ability to predict what people perceive from patterns of brain activity raises futuristic questions. Amongst these are questions about the role of brain activity in predicting misdemeanours or preventing them. Two obvious cases in point are the tendency of some patients with fronto-temporal lobar degeneration to become aggressive and the difficulty deciding when Alzheimer patients need to stop driving for reasons of safety. These two situations will be used to structure a review of the literature in this general area.

RECENT FINDINGS

Multivariate classification techniques (MCT) improve early accurate diagnosis of dementia. Given the known frequency of behavioural abnormalities, this information allows better prediction of the future frequency of such behaviour. In addition, MCT could prove suitable for providing reasonably accurate information of relevance to individuals about the combination of future symptoms. However, no study has applied MCT to the prediction of future behavioural problems or to assessments of road safety in dementia.

SUMMARY

MCT could improve the prediction of offensive or risky behaviour in which standard neuropsychological testing is less than conclusive. Cognitive function in multiple domains, as required for driving, is likely to be best examined using well established neuropsychological tests and possibly driving simulators.

Semi-supervised pattern classification of medical images: application to mild cognitive impairment (MCI)

Many progressive disorders are characterized by unclear or transient diagnoses for specific subgroups of patients. Commonly used supervised pattern recognition methodology may not be the most suitable approach to deriving image-based biomarkers in such cases, as it relies on the availability of categorically labeled data (e.g., patients and controls). In this paper, we explore the potential of semi-supervised pattern classification to provide image-based biomarkers in the absence of precise diagnostic information for some individuals. We employ semi-supervised support vector machines (SVM) and apply them to the problem of classifying MR brain images of patients with uncertain diagnoses. We examine patterns in serial scans of ADNI participants with mild cognitive impairment (MCI), and propose that in the absence of sufficient follow-up evaluations of individuals with MCI, semi-supervised strategy is potentially more appropriate than the fully-supervised paradigm employed up to date.

Diagnosis and biomarkers of predementia in Alzheimer's disease

In view of the growing prevalence of Alzheimer's disease (AD) worldwide, there is an urgent need for the development of better diagnostic tools and more effective therapeutic interventions. At the earliest stages of AD, no significant cognitive or functional impairment is detected by conventional clinical methods. However, new technologies based on structural and functional neuroimaging, and on the biochemical analysis of cerebrospinal fluid (CSF) may reveal correlates of intracerebral pathology in individuals with mild, predementia symptoms. These putative correlates are commonly referred to as AD-related biomarkers. The relevance of the early diagnosis of AD relies on the hypothesis that pharmacological interventions with disease-modifying compounds are likely to produce clinically relevant benefits if started early enough in the continuum towards dementia. Here we review the clinical characteristics of the prodromal and transitional states from normal cognitive ageing to dementia in AD. We further address recent developments in biomarker research to support the early diagnosis and prediction of dementia, and point out the challenges and perspectives for the translation of research data into clinical practice.

Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population

Alzheimer's Disease (AD) and other neurodegenerative diseases affect over 20 million people worldwide, and this number is projected to significantly increase in the coming decades. Proposed imaging-based markers have shown steadily improving levels of sensitivity/specificity in classifying individual subjects as AD or normal. Several of these efforts have utilized statistical machine learning techniques, using brain images as input, as means of deriving such AD-related markers. A common characteristic of this line of research is a focus on either (1) using a single imaging modality for classification, or (2) incorporating several modalities, but reporting separate results for each. One strategy to improve on the success of these methods is to leverage all available imaging modalities together in a single automated learning framework. The rationale is that some subjects may show signs of pathology in one modality but not in another-by combining all available images a clearer view of the progression of disease pathology will emerge. Our method is based on the Multi-Kernel Learning (MKL) framework, which allows the inclusion of an arbitrary number of views of the data in a maximum margin, kernel learning framework. The principal innovation behind MKL is that it learns an optimal combination of kernel (similarity) matrices while simultaneously training a classifier. In classification experiments MKL outperformed an SVM trained on all available features by 3%-4%. We are especially interested in whether such markers are capable of identifying early signs of the disease. To address this question, we have examined whether our multi-modal disease marker (MMDM) can predict conversion from Mild Cognitive Impairment (MCI) to AD. Our experiments reveal that this measure shows significant group differences between MCI subjects who progressed to AD, and those who remained stable for 3 years. These differences were most significant in MMDMs based on imaging data. We also discuss the relationship between our MMDM and an individual's conversion from MCI to AD.

[New possibilities for automated diagnosis of dementia]

Dementia is underdiagnosed and undertreated in Germany. Automatic diagnosing of dementia based on standard magnetic resonance imaging has the capacity to reduce diagnostic uncertainties. The algorithm learns a disease specific pattern of atrophy from training samples. It is independent from radiological expertise which may be scarce outside specialised centres and can be installed on MRT-machines or desktop PCs. It can also play its part in planning and conducting treatment trials by recruiting a sample with predicted fast future decline. Extension, based e.g. on resting state functional imaging are possible but are further away from clinical routine.

Brain beta-amyloid measures and magnetic resonance imaging atrophy both predict time-to-progression from mild cognitive impairment to Alzheimer's disease

Biomarkers of brain Aβ amyloid deposition can be measured either by cerebrospinal fluid Aβ42 or Pittsburgh compound B positron emission tomography imaging. Our objective was to evaluate the ability of Aβ load and neurodegenerative atrophy on magnetic resonance imaging to predict shorter time-to-progression from mild cognitive impairment to Alzheimer’s dementia and to characterize the effect of these biomarkers on the risk of progression as they become increasingly abnormal. A total of 218 subjects with mild cognitive impairment were identified from the Alzheimer’s Disease Neuroimaging Initiative. The primary outcome was time-to-progression to Alzheimer’s dementia. Hippocampal volumes were measured and adjusted for intracranial volume. We used a new method of pooling cerebrospinal fluid Aβ42 and Pittsburgh compound B positron emission tomography measures to produce equivalent measures of brain Aβ load from either source and analysed the results using multiple imputation methods. We performed our analyses in two phases. First, we grouped our subjects into those who were ‘amyloid positive’ (n = 165, with the assumption that Alzheimer's pathology is dominant in this group) and those who were ‘amyloid negative’ (n = 53). In the second phase, we included all 218 subjects with mild cognitive impairment to evaluate the biomarkers in a sample that we assumed to contain a full spectrum of expected pathologies. In a Kaplan–Meier analysis, amyloid positive subjects with mild cognitive impairment were much more likely to progress to dementia within 2 years than amyloid negative subjects with mild cognitive impairment (50 versus 19%). Among amyloid positive subjects with mild cognitive impairment only, hippocampal atrophy predicted shorter time-to-progression (P < 0.001) while Aβ load did not (P = 0.44). In contrast, when all 218 subjects with mild cognitive impairment were combined (amyloid positive and negative), hippocampal atrophy and Aβ load predicted shorter time-to-progression with comparable power (hazard ratio for an inter-quartile difference of 2.6 for both); however, the risk profile was linear throughout the range of hippocampal atrophy values but reached a ceiling at higher values of brain Aβ load. Our results are consistent with a model of Alzheimer’s disease in which Aβ deposition initiates the pathological cascade but is not the direct cause of cognitive impairment as evidenced by the fact that Aβ load severity is decoupled from risk of progression at high levels. In contrast, hippocampal atrophy indicates how far along the neurodegenerative path one is, and hence how close to progressing to dementia. Possible explanations for our finding that many subjects with mild cognitive impairment have intermediate levels of Aβ load include: (i) individual subjects may reach an Aβ load plateau at varying absolute levels; (ii) some subjects may be more biologically susceptible to Aβ than others; and (iii) subjects with mild cognitive impairment with intermediate levels of Aβ may represent individuals with Alzheimer’s disease co-existent with other pathologies.

Semi-supervised cluster analysis of imaging data

In this paper, we present a semi-supervised clustering-based framework for discovering coherent subpopulations in heterogeneous image sets. Our approach involves limited supervision in the form of labeled instances from two distributions that reflect a rough guess about subspace of features that are relevant for cluster analysis. By assuming that images are defined in a common space via registration to a common template, we propose a segmentation-based method for detecting locations that signify local regional differences in the two labeled sets. A PCA model of local image appearance is then estimated at each location of interest, and ranked with respect to its relevance for clustering. We develop an incremental k-means-like algorithm that discovers novel meaningful categories in a test image set. The application of our approach in this paper is in analysis of populations of healthy older adults. We validate our approach on a synthetic dataset, as well as on a dataset of brain images of older adults. We assess our method's performance on the problem of discovering clusters of MR images of human brain, and present a cluster-based measure of pathology that reflects the deviation of a subject's MR image from normal (i.e. cognitively stable) state. We analyze the clusters' structure, and show that clustering results obtained using our approach correlate well with clinical data.

Effect of brain-derived neurotrophic factor Val66Met polymorphism and serum levels on the progression of mild cognitive impairment

OBJECTIVES

Abnormalities in neurotrophic systems have been reported in Alzheimer's disease (AD), as shown by decreased serum brain-derived neurotrophic factor (BDNF) levels and association with BDNF genetic polymorphisms. In this study, we investigate whether these findings can be detected in patients with mild cognitive impairment (MCI), which is recognized as a high risk condition for AD. We also address the impact of these variables on the progression of cognitive deficits within the MCI-AD continuum.

METHODS

One hundred and sixty older adults with varying degrees of cognitive impairment (30 patients with AD, 71 with MCI, and 59 healthy controls) were longitudinally assessed for up to 60 months. Baseline serum BDNF levels were determined by sandwich ELISA, and the presence of polymorphisms of BDNF and apolipoprotein E (Val66Met and APOE*E4, respectively) was determined by allelic discrimination analysis on real time PCR. Modifications of cognitive state were ascertained for non-demented subjects.

RESULTS

Mean serum BDNF levels were reduced in patients with MCI and AD, as compared to controls (509.2+/-210.5; 581.9+/-379.4; and 777.5+/-467.8 pg/l respectively; P<0.001). Baseline serum BDNF levels were not associated with the progression of cognitive impairment upon follow-up in patients with MCI (progressive MCI, 750.8+/-463.0; stable MCI, 724.0+/-343.4; P=0.8), nor with the conversion to AD. Although Val66Met polymorphisms were not associated with the cross-sectional diagnoses of MCI or AD, the presence of Met-BDNF allele was associated with a higher risk of disease-progression in patients with MCI (OR=3.0 CI(95%) [1.2-7.8], P=0.02). We also found a significant interaction between the APOE*E4 and Met-BDNF allele increasing the risk of progression of cognitive impairment in MCI patients (OR=4.4 CI(95%) [1.6-12.1], P=0.004).

CONCLUSION

Decreased neurotrophic support, as indicated by a reduced systemic availability of BDNF, may play role in the neurodegenerative processes that underlie the continuum from MCI to AD. The presence of Met-BDNF allele, particularly in association with APOE*E4, may predict a worse cognitive outcome in patients with MCI.

Boosting power for clinical trials using classifiers based on multiple biomarkers

Machine learning methods pool diverse information to perform computer-assisted diagnosis and predict future clinical decline. We introduce a machine learning method to boost power in clinical trials. We created a Support Vector Machine algorithm that combines brain imaging and other biomarkers to classify 737 Alzheimer's disease Neuroimaging initiative (ADNI) subjects as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or normal controls. We trained our classifiers based on example data including: MRI measures of hippocampal, ventricular, and temporal lobe volumes, a PET-FDG numerical summary, CSF biomarkers (t-tau, p-tau, and Abeta(42)), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly Abeta(42), contributed more to MCI classification. Using all biomarkers jointly, we used our classifier to select the one-third of the subjects most likely to decline. In this subsample, fewer than 40 AD and MCI subjects would be needed to detect a 25% slowing in temporal lobe atrophy rates with 80% power--a substantial boosting of power relative to standard imaging measures.

Predicting clinical scores from magnetic resonance scans in Alzheimer's disease

Machine learning and pattern recognition methods have been used to diagnose Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) from individual MRI scans. Another application of such methods is to predict clinical scores from individual scans. Using relevance vector regression (RVR), we predicted individuals' performances on established tests from their MRI T1 weighted image in two independent datasets. From Mayo Clinic, 73 probable AD patients and 91 cognitively normal (CN) controls completed the Mini-Mental State Examination (MMSE), Dementia Rating Scale (DRS), and Auditory Verbal Learning Test (AVLT) within 3 months of their scan. Baseline MRI's from the Alzheimer's disease Neuroimaging Initiative (ADNI) comprised the other dataset; 113 AD, 351 MCI, and 122 CN subjects completed the MMSE and Alzheimer's Disease Assessment Scale—Cognitive subtest (ADAS-cog) and 39 AD, 92 MCI, and 32 CN ADNI subjects completed MMSE, ADAS-cog, and AVLT. Predicted and actual clinical scores were highly correlated for the MMSE, DRS, and ADAS-cog tests (P<.0001). Training with one dataset and testing with another demonstrated stability between datasets. DRS, MMSE, and ADAS-Cog correlated better than AVLT with whole brain grey matter changes associated with AD. This result underscores their utility for screening and tracking disease. RVR offers a novel way to measure interactions between structural changes and neuropsychological tests beyond that of univariate methods. In clinical practice, we envision using RVR to aid in diagnosis and predict clinical outcome.

Effects of music and art education in early life and oral functions on the QOL of the Takarazuka Revue Company OG compared with general elderly females

BACKGROUND

Today, Japan is becoming a super-aged society, with senior citizens already constituting over 21% of the population. In this situation, the question of how elderly people can extend their lives and enjoy independent lifestyles is becoming more important. The present study aims to clarify the relationship between the Quality of Life (QOL) of elderly females and their current oral functions and experiences of music and art education in early life.

METHODS

We carried out a survey study focusing on elderly females (Takarazuka Revue Company OG group and general female group) by carrying out a questionnaire survey and comparing cognitive function, oral examinations, cerebral atrophy in magnetic resonance imaging, and other characteristics.

RESULTS

It was shown that the Takarazuka Revue Company OG group had greater hippocampal volumes and significantly higher cognitive functions than the general female group. In addition, in the general female group, there was a significant correlation between a decrease in the number of remaining teeth and a decrease in activities in daily living, but in the Takarazuka Revue Company OG group, no such correlation was observed.

CONCLUSIONS

The results showed that those who have received art education as part of their careers over an extensive period since early life have higher levels of cognitive function, QOL, physical activity, social activity and life satisfaction compared with the general female group; showing that they sense a purpose in life and live with a positive attitude. In contrast, in the general female group, those who have continued to enjoy hobbies have higher levels of cognitive function, QOL, physical activity, social activity and life satisfaction than those who have not, thus showing that they live with a positive attitude.

Patterns of brain atrophy on magnetic resonance imaging and the boundary between ageing and Alzheimer's disease

Clinicians are increasingly faced with the problem of interpreting subtle, early cognitive symptoms. Enhanced awareness of Alzheimer's disease (AD) and available treatments has led to a growing demand for early assessment. Although it is known that a proportion of individuals with mild cognitive impairment will progress to dementia in following years, our ability to identify these individuals and predict individual cognitive trajectories is limited. The emergence of disease-modifying treatments would make these problems more acute. In this review, the potential role of magnetic resonance imaging (MRI) in aiding the clinician in early diagnosis of AD will be considered. The changes in grey matter structure that accompany ‘normal’ ageing will be described briefly, before moving on to studies that have attempted to distinguish the onset of disease from this background of structural change. Volumetric methods range from measurements of single key structures, such as the hippocampus, to methods based on computational neuroanatomy, which evaluate subtle structural alterations across the whole brain simultaneously. Computational methods are rapidly evolving and already perform as well as radiologists in distinguishing AD from normal ageing at an individual level. This article aims to provide a practical knowledge of how and why these methods work, point out the main advantages and disadvantages and sketch out outstanding issues and possible future directions.

Serum levels of S100B and NSE proteins in Alzheimer's disease patients

Background

Alzheimer's disease is the most common dementia in the elderly, and the potential of peripheral biochemical markers as complementary tools in the neuropsychiatric evaluation of these patients has claimed further attention.

Methods

We evaluated serum levels of S100B and neuron-specific enolase (NSE) in 54 mild, moderate and severe Alzheimer's disease (AD) patients and in 66 community-dwelling elderly. AD patients met the probable NINCDS-ADRDA criteria. Severity of dementia was ascertained by the Clinical Dementia Rating (CDR) scale, cognitive function by the Mini Mental State Examination (MMSE), and neuroimage findings with magnetic resonance imaging. Serum was obtained from all individuals and frozen at -70°C until analysis.

Results

By comparing both groups, serum S100B levels were lower in AD group, while serum NSE levels were the same both groups. In AD patients, S100B levels were positively correlated with CDR scores (rho = 0.269; p = 0.049) and negatively correlated with MMSE scores (rho = -0.33; P = 0.048). NSE levels decreased in AD patients with higher levels of brain atrophy.

Conclusions

The findings suggest that serum levels of S100B may be a marker for brain functional condition and serum NSE levels may be a marker for morphological status in AD.

High-dimensional pattern regression using machine learning: from medical images to continuous clinical variables

This paper presents a general methodology for high-dimensional pattern regression on medical images via machine learning techniques. Compared with pattern classification studies, pattern regression considers the problem of estimating continuous rather than categorical variables, and can be more challenging. It is also clinically important, since it can be used to estimate disease stage and predict clinical progression from images. In this work, adaptive regional feature extraction approach is used along with other common feature extraction methods, and feature selection technique is adopted to produce a small number of discriminative features for optimal regression performance. Then the Relevance Vector Machine (RVM) is used to build regression models based on selected features. To get stable regression models from limited training samples, a bagging framework is adopted to build ensemble basis regressors derived from multiple bootstrap training samples, and thus to alleviate the effects of outliers as well as facilitate the optimal model parameter selection. Finally, this regression scheme is tested on simulated data and real data via cross-validation. Experimental results demonstrate that this regression scheme achieves higher estimation accuracy and better generalizing ability than Support Vector Regression (SVR).

One-year brain atrophy evident in healthy aging

An accurate description of changes in the brain in healthy aging is needed to understand the basis of age-related changes in cognitive function. Cross-sectional magnetic resonance imaging (MRI) studies suggest thinning of the cerebral cortex, volumetric reductions of most subcortical structures, and ventricular expansion. However, there is a paucity of detailed longitudinal studies to support the cross-sectional findings. In the present study, 142 healthy elderly participants (60-91 years of age) were followed with repeated MRI, and were compared with 122 patients with mild to moderate Alzheimer's disease (AD). Volume changes were measured across the entire cortex and in 48 regions of interest. Cortical reductions in the healthy elderly were extensive after only 1 year, especially evident in temporal and prefrontal cortices, where annual decline was approximately 0.5%. All subcortical and ventricular regions except caudate nucleus and the fourth ventricle changed significantly over 1 year. Some of the atrophy occurred in areas vulnerable to AD, while other changes were observed in areas less characteristic of the disease in early stages. This suggests that the changes are not primarily driven by degenerative processes associated with AD, although it is likely that preclinical changes associated with AD are superposed on changes due to normal aging in some subjects, especially in the temporal lobes. Finally, atrophy was found to accelerate with increasing age, and this was especially prominent in areas vulnerable to AD. Thus, it is possible that the accelerating atrophy with increasing age is due to preclinical AD.