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

In vivo parahippocampal white matter pathology as a biomarker of disease progression to Alzheimer's disease

Noninvasive diagnostic tests for Alzheimer's disease (AD) are limited. Postmortem diagnosis is based on density and distribution of neurofibrillary tangles (NFTs) and amyloid-rich neuritic plaques. In preclinical stages of AD, the cells of origin for the perforant pathway within the entorhinal cortex are among the first to display NFTs, indicating its compromise in early stages of AD. We used diffusion tensor imaging (DTI) to assess the integrity of the parahippocampal white matter in mild cognitive impairment (MCI) and AD, as a first step in developing a noninvasive tool for early diagnosis. Subjects with AD (N = 9), MCI (N = 8), or no cognitive impairment (NCI; N = 20) underwent DTI-MRI. Fractional anisotropy (FA) and mean (MD) and radial (RD) diffusivity measured from the parahippocampal white matter in AD and NCI subjects differed greatly. Discriminant analysis in the MCI cases assigned statistical membership of 38% of MCI subjects to the AD group. Preliminary data 1 year later showed that all MCI cases assigned to the AD group either met the diagnostic criteria for probable AD or showed significant cognitive decline. Voxelwise analysis in the parahippocampal white matter revealed a progressive change in the DTI patterns in MCI and AD subjects: whereas converted MCI cases showed structural changes restricted to the anterior portions of this region, in AD the pathology was generalized along the entire anterior-posterior axis. The use of DTI for in vivo assessment of the parahippocampal white matter may be useful for identifying individuals with MCI at highest risk for conversion to AD and for assessing disease progression.

What is normal in normal aging? Effects of aging, amyloid and Alzheimer's disease on the cerebral cortex and the hippocampus

What can be expected in normal aging, and where does normal aging stop and pathological neurodegeneration begin? With the slow progression of age-related dementias such as Alzheimer's disease (AD), it is difficult to distinguish age-related changes from effects of undetected disease. We review recent research on changes of the cerebral cortex and the hippocampus in aging and the borders between normal aging and AD. We argue that prominent cortical reductions are evident in fronto-temporal regions in elderly even with low probability of AD, including regions overlapping the default mode network. Importantly, these regions show high levels of amyloid deposition in AD, and are both structurally and functionally vulnerable early in the disease. This normalcy-pathology homology is critical to understand, since aging itself is the major risk factor for sporadic AD. Thus, rather than necessarily reflecting early signs of disease, these changes may be part of normal aging, and may inform on why the aging brain is so much more susceptible to AD than is the younger brain. We suggest that regions characterized by a high degree of life-long plasticity are vulnerable to detrimental effects of normal aging, and that this age-vulnerability renders them more susceptible to additional, pathological AD-related changes. We conclude that it will be difficult to understand AD without understanding why it preferably affects older brains, and that we need a model that accounts for age-related changes in AD-vulnerable regions independently of AD-pathology.

[Neuroimaging in psychiatry: multivariate analysis techniques for diagnosis and prognosis]

BACKGROUND

Multiple studies successfully applied multivariate analysis to neuroimaging data demonstrating the potential utility of neuroimaging for clinical diagnostic and prognostic purposes.

OBJECTIVES

Summary of the current state of research regarding the application of neuroimaging in the field of psychiatry.

MATERIAL AND METHODS

Literature review of current studies.

RESULTS

Results of current studies indicate the potential application of neuroimaging data across various diagnoses, such as depression, schizophrenia, bipolar disorder and dementia. Potential applications include disease classification, differential diagnosis and prediction of disease course.

CONCLUSION

The results of the studies are heterogeneous although some studies report promising findings. Further multicentre studies are needed with clearly specified patient populations to systematically investigate the potential utility of neuroimaging for the clinical routine.

Mild cognitive impairment. Part 2: Biological markers for diagnosis and prediction of dementia in Alzheimer's disease

OBJECTIVE

To present a critical review of publications reporting on the rationale and clinical implications of the use of biomarkers for the early diagnosis of Alzheimer's disease (AD).

METHODS

We conducted a systematic search of the PubMed and Web of Science electronic databases, limited to articles published in English between 1999 and 2012, and based on the following terms: mild cognitive impairment, Alzheimer's disease OR dementia, biomarkers. We retrieved 1,130 articles, of which 175 were reviews. Overall, 955 original articles were eligible.

RESULTS

The following points were considered relevant for the present review: a) rationale for biomarkers research in AD and mild cognitive impairment (MCI); b) usefulness of distinct biomarkers for the diagnosis and prediction of AD; c) the role of multimodality biomarkers for the diagnosis and prediction of AD; d) the role of biomarkers in clinical trials of patients with AD and MCI; and e) current limitations to the widespread use of biomarkers in research and clinical settings.

CONCLUSION

Different biomarkers are useful for the early diagnosis and prediction of AD in at-risk subjects. Nonetheless, important methodological limitations need to be overcome for widespread use of biomarkers in research and clinical settings.

Individualized Gaussian process-based prediction and detection of local and global gray matter abnormalities in elderly subjects

Structural imaging based on MRI is an integral component of the clinical assessment of patients with potential dementia. We here propose an individualized Gaussian process-based inference scheme for clinical decision support in healthy and pathological aging elderly subjects using MRI. The approach aims at quantitative and transparent support for clinicians who aim to detect structural abnormalities in patients at risk of Alzheimer's disease or other types of dementia. Firstly, we introduce a generative model incorporating our knowledge about normative decline of local and global gray matter volume across the brain in elderly. By supposing smooth structural trajectories the models account for the general course of age-related structural decline as well as late-life accelerated loss. Considering healthy subjects' demography and global brain parameters as informative about normal brain aging variability affords individualized predictions in single cases. Using Gaussian process models as a normative reference, we predict new subjects' brain scans and quantify the local gray matter abnormalities in terms of Normative Probability Maps (NPM) and global z-scores. By integrating the observed expectation error and the predictive uncertainty, the local maps and global scores exploit the advantages of Bayesian inference for clinical decisions and provide a valuable extension of diagnostic information about pathological aging. We validate the approach in simulated data and real MRI data. We train the GP framework using 1238 healthy subjects with ages 18–94 years, and predict in 415 independent test subjects diagnosed as healthy controls, Mild Cognitive Impairment and Alzheimer's disease.

•

We propose an approach to support individualized clinical decisions in elderlies.

•

Gaussian process models are used to build a normative generative model of aging.

•

It affords probabilistic predictions of local gray matter volume in subjects.

•

We validate the model using simulated and large real MRI data samples.

Cognitive decline and brain pathology in aging--need for a dimensional, lifespan and systems vulnerability view

Changes in brain structure and activity as well as cognitive function are commonly seen in aging. However, it is not known when aging of brain and cognition starts, and how much of the changes observed in seemingly healthy older adults that can be ascribed to incipient neurodegenerative disease. Recent research has yielded evidence that the borders between development and aging sometimes can be fuzzy, as can the borders between dementing disease and normal age changes. In this review, we argue that many factors affecting cognitive decline and dementia represents quantitative rather than qualitative differences in characteristics that commonly exist in the population. Further, factors known to affect brain and cognition in aging will often do so through a life-long accumulation of impact, and does not need to be specific to aging. And finally, a host of environmental and genetic factors and their interplay determine optimal aging, leaving room for potential for environmental interventions to affect the outcome of the aging process. Together, we argue that these factors call for a dimensional rather than categorical, lifespan rather than aging, and multidimensional systems-vulnerability rather than simple "hypothetical biomarker" model of age-associated cognitive decline and dementia. This has implications for how we should view lifespan trajectories of change in brain and cognitive function, and how we can study, prevent, diagnose and treat age-associated cognitive deficits.

What is normal in normal aging? Effects of aging, amyloid and Alzheimer's disease on the cerebral cortex and the hippocampus

What can be expected in normal aging, and where does normal aging stop and pathological neurodegeneration begin? With the slow progression of age-related dementias such as Alzheimer's disease (AD), it is difficult to distinguish age-related changes from effects of undetected disease. We review recent research on changes of the cerebral cortex and the hippocampus in aging and the borders between normal aging and AD. We argue that prominent cortical reductions are evident in fronto-temporal regions in elderly even with low probability of AD, including regions overlapping the default mode network. Importantly, these regions show high levels of amyloid deposition in AD, and are both structurally and functionally vulnerable early in the disease. This normalcy-pathology homology is critical to understand, since aging itself is the major risk factor for sporadic AD. Thus, rather than necessarily reflecting early signs of disease, these changes may be part of normal aging, and may inform on why the aging brain is so much more susceptible to AD than is the younger brain. We suggest that regions characterized by a high degree of life-long plasticity are vulnerable to detrimental effects of normal aging, and that this age-vulnerability renders them more susceptible to additional, pathological AD-related changes. We conclude that it will be difficult to understand AD without understanding why it preferably affects older brains, and that we need a model that accounts for age-related changes in AD-vulnerable regions independently of AD-pathology.

Age estimation using cortical surface pattern combining thickness with curvatures

Brain development and healthy aging have been proved to follow a specific pattern, which, in turn, can be applied to help doctors diagnose mental diseases. In this paper, we design a cortical surface pattern (CSP) combining the cortical thickness with curvatures, which constructs an accurate human age estimation model with relevance vector regression. We test our model with two public databases. One is the IXI database (360 healthy subjects aging from 20 to 82 years old were selected), and the other is the INDI database (303 subjects aging from 7 to 22 years old were selected). The results show that our model can achieve as small as 4.57 years deviation in the IXI database and 1.38 years deviation in the INDI database. Furthermore, we employ this surface pattern to age groups classification and get a remarkably high accuracy (97.77 %) and a significantly high sensitivity/specificity (97.30/98.10 %). These results suggest that our designed CSP combining thickness with curvatures is stable and sensitive to brain development, and it is much more powerful than voxel-based morphometry used in previous methods for age estimation.

Imaging-based biomarkers of cognitive performance in older adults constructed via high-dimensional pattern regression applied to MRI and PET

In this study, we used high-dimensional pattern regression methods based on structural (gray and white matter; GM and WM) and functional (positron emission tomography of regional cerebral blood flow; PET) brain data to identify cross-sectional imaging biomarkers of cognitive performance in cognitively normal older adults from the Baltimore Longitudinal Study of Aging (BLSA). We focused on specific components of executive and memory domains known to decline with aging, including manipulation, semantic retrieval, long-term memory (LTM), and short-term memory (STM). For each imaging modality, brain regions associated with each cognitive domain were generated by adaptive regional clustering. A relevance vector machine was adopted to model the nonlinear continuous relationship between brain regions and cognitive performance, with cross-validation to select the most informative brain regions (using recursive feature elimination) as imaging biomarkers and optimize model parameters. Predicted cognitive scores using our regression algorithm based on the resulting brain regions correlated well with actual performance. Also, regression models obtained using combined GM, WM, and PET imaging modalities outperformed models based on single modalities. Imaging biomarkers related to memory performance included the orbito-frontal and medial temporal cortical regions with LTM showing stronger correlation with the temporal lobe than STM. Brain regions predicting executive performance included orbito-frontal, and occipito-temporal areas. The PET modality had higher contribution to most cognitive domains except manipulation, which had higher WM contribution from the superior longitudinal fasciculus and the genu of the corpus callosum. These findings based on machine-learning methods demonstrate the importance of combining structural and functional imaging data in understanding complex cognitive mechanisms and also their potential usage as biomarkers that predict cognitive status.

Detection of preclinical neural dysfunction from functional connectivity graphs derived from task fMRI. An example from degeneration

The early, preferably pre-clinical, identification of neurodegenerative diseases is important as treatment will be most successful before substantial neuronal loss. Here, we reasoned that functional brain changes as measured using functional magnetic resonance imaging (fMRI) will precede neurodegeneration. Three independent cohorts of patients with the genetic mutation leading to Huntington's Disease (HD) but without any clinical symptoms and matched controls performed three different fMRI tasks: Sequential finger tapping engaged the motor system, which is primarily affected by HD, whereas a working-memory task and a task aiming to induce irritation represented the range of low- and high-level cognitive functions also affected by HD. Each diagnostic group of every cohort included 11-16 subjects. After segmentation into 76 cortical and 14 subcortical regions, we extracted functional connectivity patterns through pairwise correlation between the signals in the regions. The resulting coefficients were directly embedded as input to a pattern classifier aiming to separate controls from gene mutation carriers. Alternatively, graph-theory measures such as degree and clustering coefficient were used as features for the discrimination. Classification accuracy never outperformed the accuracy of a grouping based on parameter estimates from a general-linear model approach or a grouping based on features extracted from anatomical images as reported in a previous analysis. Despite good within-subject stability between two runs of the same task, a high between-subject variability led to chance-level accuracy. These results indicate that standard graph-metrics are insufficient to detect subtle disease related changes when within-group variability is high. Developing methods that reduce variability related to noise should be the focus of future studies.

Integration and relative value of biomarkers for prediction of MCI to AD progression: spatial patterns of brain atrophy, cognitive scores, APOE genotype and CSF biomarkers

This study evaluates the individual, as well as relative and joint value of indices obtained from magnetic resonance imaging (MRI) patterns of brain atrophy (quantified by the SPARE-AD index), cerebrospinal fluid (CSF) biomarkers, APOE genotype, and cognitive performance (ADAS-Cog) in progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) within a variable follow-up period up to 6 years, using data from the Alzheimer's Disease Neuroimaging Initiative-1 (ADNI-1). SPARE-AD was first established as a highly sensitive and specific MRI-marker of AD vs. cognitively normal (CN) subjects (AUC = 0.98). Baseline predictive values of all aforementioned indices were then compared using survival analysis on 381 MCI subjects. SPARE-AD and ADAS-Cog were found to have similar predictive value, and their combination was significantly better than their individual performance. APOE genotype did not significantly improve prediction, although the combination of SPARE-AD, ADAS-Cog and APOE ε4 provided the highest hazard ratio estimates of 17.8 (last vs. first quartile). In a subset of 192 MCI patients who also had CSF biomarkers, the addition of Aβ1-42, t-tau, and p-tau181p to the previous model did not improve predictive value significantly over SPARE-AD and ADAS-Cog combined. Importantly, in amyloid-negative patients with MCI, SPARE-AD had high predictive power of clinical progression. Our findings suggest that SPARE-AD and ADAS-Cog in combination offer the highest predictive power of conversion from MCI to AD, which is improved, albeit not significantly, by APOE genotype. The finding that SPARE-AD in amyloid-negative MCI patients was predictive of clinical progression is not expected under the amyloid hypothesis and merits further investigation.

Alzheimer's disease risk assessment using large-scale machine learning methods

The goal of this work is to introduce new metrics to assess risk of Alzheimer's disease (AD) which we call AD Pattern Similarity (AD-PS) scores. These metrics are the conditional probabilities modeled by large-scale regularized logistic regression. The AD-PS scores derived from structural MRI and cognitive test data were tested across different situations using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. The scores were computed across groups of participants stratified by cognitive status, age and functional status. Cox proportional hazards regression was used to evaluate associations with the distribution of conversion times from mild cognitive impairment to AD. The performances of classifiers developed using data from different types of brain tissue were systematically characterized across cognitive status groups. We also explored the performance of anatomical and cognitive-anatomical composite scores generated by combining the outputs of classifiers developed using different types of data. In addition, we provide the AD-PS scores performance relative to other metrics used in the field including the Spatial Pattern of Abnormalities for Recognition of Early AD (SPARE-AD) index and total hippocampal volume for the variables examined.

Frequency and clinicopathological characteristics of presenilin 1 Gly206Ala mutation in Puerto Rican Hispanics with dementia

The frequency and clinical and pathological characteristics associated with the Gly206Ala presenilin 1 (PSEN1) mutation in Puerto Rican and non-Puerto Rican Hispanics were evaluated at the University of Pennsylvania's Alzheimer's Disease Center. DNAs from all cohort subjects were genotyped for the Gly206Ala PSEN1 mutation. Carriers and non-carriers with neurodegenerative disease dementias were compared for demographic, clinical, psychometric, and biomarker variables. Nineteen (12.6%) of 151 unrelated subjects with dementia were discovered to carry the PSEN1 Gly206Ala mutation. Microsatellite marker genotyping determined a common ancestral haplotype for all carriers. Carriers were all of Puerto Rican heritage with significantly younger age of onset, but otherwise were clinically and neuropsychologically comparable to those of non-carriers with AD. Three subjects had extensive topographic and biochemical biomarker assessments that were also typical of non-carriers with AD. Neuropathological examination in one subject revealed severe, widespread plaque and tangle pathology without other meaningful disease lesions. The PSEN1 Gly206Ala mutation is notably frequent in unrelated Puerto Rican immigrants with dementia in Philadelphia. Considered together with the increased prevalence and mortality of AD reported in Puerto Rico, these high rates may reflect hereditary risk concentrated in the island which warrants further study.

A longitudinal study of brain atrophy over two years in community-dwelling older individuals

Most previous neuroimaging studies of age-related brain structural changes in older individuals have been cross-sectional and/or restricted to clinical samples. The present study of 345 community-dwelling non-demented individuals aged 70-90years aimed to examine age-related brain volumetric changes over two years. T1-weighted magnetic resonance imaging scans were obtained at baseline and at 2-year follow-up and analyzed using the FMRIB Software Library and FreeSurfer to investigate cortical thickness and shape and volumetric changes of subcortical structures. The results showed significant atrophy across much of the cerebral cortex with bilateral transverse temporal regions shrinking the fastest. Atrophy was also found in a number of subcortical structures, including the CA1 and subiculum subfields of the hippocampus. In some regions, such as left and right entorhinal cortices, right hippocampus and right precentral area, the rate of atrophy increased with age. Our analysis also showed that rostral middle frontal regions were thicker bilaterally in older participants, which may indicate its ability to compensate for medial temporal lobe atrophy. Compared to men, women had thicker cortical regions but greater rates of cortical atrophy. Women also had smaller subcortical structures. A longer period of education was associated with greater thickness in a number of cortical regions. Our results suggest a pattern of brain atrophy with non-demented people that resembles a less extreme form of the changes associated with Alzheimer's disease (AD).

How early can we predict Alzheimer's disease using computational anatomy?

Computational anatomy with magnetic resonance imaging (MRI) is well established as a noninvasive biomarker of Alzheimer's disease (AD); however, there is less certainty about its dependency on the staging of AD. We use classical group analyses and automated machine learning classification of standard structural MRI scans to investigate AD diagnostic accuracy from the preclinical phase to clinical dementia. Longitudinal data from the Alzheimer's Disease Neuroimaging Initiative were stratified into 4 groups according to the clinical status-(1) AD patients; (2) mild cognitive impairment (MCI) converters; (3) MCI nonconverters; and (4) healthy controls-and submitted to a support vector machine. The obtained classifier was significantly above the chance level (62%) for detecting AD already 4 years before conversion from MCI. Voxel-based univariate tests confirmed the plausibility of our findings detecting a distributed network of hippocampal-temporoparietal atrophy in AD patients. We also identified a subgroup of control subjects with brain structure and cognitive changes highly similar to those observed in AD. Our results indicate that computational anatomy can detect AD substantially earlier than suggested by current models. The demonstrated differential spatial pattern of atrophy between correctly and incorrectly classified AD patients challenges the assumption of a uniform pathophysiological process underlying clinically identified AD.

Gray matter atrophy pattern in elderly with subjective memory impairment

BACKGROUND

Individuals with subjective memory impairment (SMI) report worsening of memory without impairment in cognitive tests. Despite normal cognitive performance, they may be at higher risk of cognitive decline compared with individuals without SMI.

METHODS

We used a discriminative function (a support vector machine) trained on an independent data set of 226 healthy control subjects and 191 patients with probable Alzheimer's disease (AD) dementia to characterize the baseline gray matter patterns of 24 individuals with SMI and 53 control subjects. We tested for associations of these gray matter patterns with SMI presence, cognitive performance at baseline, and cognitive decline at follow-up.

RESULTS

Individuals with SMI showed greater similarity to an AD gray matter pattern compared with control subjects without SMI. In addition, episodic memory decline was associated with an AD gray matter pattern in the SMI group.

CONCLUSIONS

Our results indicate a link between the gray matter atrophy pattern of patients with AD and the presence of SMI. Furthermore, multivariate pattern recognition approaches seem to be a sensitive method for identifying subtle brain changes that correspond to future memory decline in SMI.

Insomnia does not appear to be associated with substantial structural brain changes

STUDY OBJECTIVES

Sleep has been demonstrated to significantly modulate brain plasticity and the manifestation of mental disorders. However, previous studies on the effect of disrupted sleep on brain structure have reported inconsistent results. The goal of the current study was to investigate brain morphometry in a well-characterized large sample of patients with primary insomnia (PI) in comparison with good sleeper controls.

DESIGN

Automated parcellation and pattern recognition approaches were supplemented by voxelwise analyses of gray and white matter volumes to analyze magnetic resonance images. All analyses included age, sex, and total intracranial volume as covariates.

SETTING

Department of Psychiatry and Psychotherapy of the University of Freiburg Medical Center.

PARTICIPANTS

There were 28 patients with PI (10 males; 18 females; age 43.7 ± 14.2 y) and 38 healthy, good sleepers (17 males; 21 females; age 39.6 ± 8.9 y).

INTERVENTIONS

N/A.

RESULTS

No significant between-group differences were observed in any of the investigated brain morphometry variables.

CONCLUSIONS

Altered brain function in insomnia does not appear to have a substantial effect on brain morphometry on a macroscopic level.

Relevance of magnetic resonance imaging for early detection and diagnosis of Alzheimer disease

Hippocampus volumetry currently is the best-established imaging biomarker for AD. However, the effect of multicenter acquisition on measurements of hippocampus volume needs to be explicitly considered when it is applied in large clinical trials, for example by using mixed-effects models to take the clustering of data within centers into account. The marker needs further validation in respect of the underlying neurobiological substrate and potential confounds such as vascular disease, inflammation, hydrocephalus, and alcoholism, and with regard to clinical outcomes such as cognition but also to demographic and socioeconomic outcomes such as mortality and institutionalization. The use of hippocampus volumetry for risk stratification of predementia study samples will further increase with the availability of automated measurement approaches. An important step in this respect will be the development of a standard hippocampus tracing protocol that harmonizes the large range of presently available manual protocols. In the near future, regionally differentiated automated methods will become available together with an appropriate statistical model, such as multivariate analysis of deformation fields, or techniques such as cortical-thickness measurements that yield a meaningful metrics for the detection of treatment effects. More advanced imaging protocols, including DTI, DSI, and functional MRI, are presently being used in monocenter and first multicenter studies. In the future these techniques will be relevant for the risk stratification in phase IIa type studies (small proof-of-concept trials). By contrast, the application of the broader established structural imaging biomarkers, such as hippocampus volume, for risk stratification and as surrogate end point is already today part of many clinical trial protocols. However, clinical care will also be affected by these new technologies. Radiologic expert centers already offer “dementia screening” for well-off middle-aged people who undergo an MRI scan with subsequent automated, typically VBM-based analysis, and determination of z-score deviation from a matched control cohort. Next-generation scanner software will likely include radiologic expert systems for automated segmentation, deformation-based morphometry, and multivariate analysis of anatomic MRI scans for the detection of a typical AD pattern. As these developments will start to change medical practice, first for selected subject groups that can afford this type of screening but later eventually also for other cohorts, clinicians must become aware of the potentials and limitations of these technologies. It is decidedly unclear to date how a middle-aged cognitively intact subject with a seemingly AD-positive MRI scan should be clinically advised. There is no evidence for individual risk prediction and even less for specific treatments. Thus, the development of preclinical diagnostic imaging poses not only technical but also ethical problems that must be critically discussed on the basis of profound knowledge. From a neurobiological point of view, the main determinants of cognitive impairment in AD are the density of synapses and neurons in distributed cortical and subcortical networks. MRI-based measures of regional gray matter volume and associated multivariate analysis techniques of regional interactions of gray matter densities provide insight into the onset and temporal dynamics of cortical atrophy as a close proxy for regional neuronal loss and a basis of functional impairment in specific neuronal networks. From the clinical point of view, clinicians must bear in mind that patients do not suffer from hippocampus atrophy or disconnection but from memory impairment, and that dementia screening in asymptomatic subjects should not be used outside of clinical studies.

Voxel-based classification of FDG PET in dementia using inter-scanner normalization

Statistical mapping of FDG PET brain images has become a common tool in differential diagnosis of patients with dementia. We present a voxel-based classification system of neurodegenerative dementias based on partial least squares (PLS). Such a classifier relies on image databases of normal controls and dementia cases as training data. Variations in PET image characteristics can be expected between databases, for example due to differences in instrumentation, patient preparation, and image reconstruction. This study evaluates (i) the impact of databases from different scanners on classification accuracy and (ii) a method to improve inter-scanner classification. Brain FDG PET databases from three scanners (A, B, C) at two clinical sites were evaluated. Diagnostic categories included normal controls (NC, nA=26, nB=20, nC=24 for each scanner respectively), Alzheimer's disease (AD, nA=44, nB=11, nC=16), and frontotemporal dementia (FTD, nA=13, nB=13, nC=5). Spatially normalized images were classified as NC, AD, or FTD using partial least squares. Supervised learning was employed to determine classifier parameters, whereby available data is sub-divided into training and test sets. Four different database setups were evaluated: (i) "in-scanner": training and test data from the same scanner, (ii) "x-scanner": training and test data from different scanners, (iii) "train other": train on both x-scanners, and (iv) "train all": train on all scanners. In order to moderate the impact of inter-scanner variations on image evaluation, voxel-by-voxel scaling was applied based on "ratio images". Good classification accuracy of on average 94% was achieved for the in-scanner setups. Accuracy deteriorated for setups with mismatched scanners (79-91%). Ratio-image normalization improved all results with mismatched scanners (85-92%). In conclusion, automatic classification of individual FDG PET in differential diagnosis of dementia is feasible. Accuracy can vary with respect to scanner or acquisition characteristics of the training image data. The adopted approach of ratio-image normalization has been demonstrated to effectively moderate these effects.

Vulnerable neural systems and the borderland of brain aging and neurodegeneration

Brain aging is characterized by considerable heterogeneity, including varying degrees of dysfunction in specific brain systems, notably a medial temporal lobe memory system and a frontostriatal executive system. These same systems are also affected by neurodegenerative diseases. Recent work using techniques for presymptomatic detection of disease in cognitively normal older people has shown that some of the late life alterations in cognition, neural structure, and function attributed to aging probably reflect early neurodegeneration. However, it has become clear that these same brain systems are also vulnerable to aging in the absence of even subtle disease. Thus, fundamental systemic limitations appear to confer vulnerability of these neural systems to a variety of insults, including those recognized as typical disease and those that are attributed to age. By focusing on the fundamental causes of neural system vulnerability, the prevention or treatment of a wide range of late-life neural dysfunction might be possible.

Relationship between plasma analytes and SPARE-AD defined brain atrophy patterns in ADNI

Different inflammatory and metabolic pathways have been associated with Alzheimeŕs disease (AD). However, only recently multi-analyte panels to study a large number of molecules in well characterized cohorts have been made available. These panels could help identify molecules that point to the affected pathways. We studied the relationship between a panel of plasma biomarkers (Human DiscoveryMAP) and presence of AD-like brain atrophy patterns defined by a previously published index (SPARE-AD) at baseline in subjects of the ADNI cohort. 818 subjects had MRI-derived SPARE-AD scores, of these subjects 69% had plasma biomarkers and 51% had CSF tau and Aβ measurements. Significant analyte-SPARE-AD and analytes correlations were studied in adjusted models. Plasma cortisol and chromogranin A showed a significant association that did not remain significant in the CSF signature adjusted model. Plasma macrophage inhibitory protein-1α and insulin-like growth factor binding protein 2 showed a significant association with brain atrophy in the adjusted model. Cortisol levels showed an inverse association with tests measuring processing speed. Our results indicate that stress and insulin responses and cytokines associated with recruitment of inflammatory cells in MCI-AD are associated with its characteristic AD-like brain atrophy pattern and correlate with clinical changes or CSF biomarkers.

Structural networks in Alzheimer's disease

Alzheimer's disease (AD) appears to be a uniquely human condition, which is possibly attributable to our expanded longevity and peculiar capacity for episodic memory. Due to a lack of naturally-occurring animal model for investigating AD pathogenesis, our knowledge about the disease must be derived from correlational observation of humans, or from animal models produced by genetic manipulation of known risk factors in humans. Advances in neuroimaging, cellular and molecular science, and computational methods have proven useful for the improvement of such techniques, but the general limitation persists; as a result we remain without clear answers to some of the fundamental questions posed by AD. On the other hand, much progress has been made in characterizing the longitudinal progression of AD pathology, which includes the formation of "plaques and tangles", a distinct topological pattern of atrophy of grey and white matter, and the concurrent decline of specific cognitive functions, beginning with mild memory impairments and ending with general debilitating dementia. In this review, we first discuss the existing literature which characterizes AD etiology, pathology, and pathogenesis, with the intention of framing the disease as primarily a "disconnection syndrome". We next describe methodologies for investigating the topological properties of human brain networks, using graph theoretical techniques and connectivity information derived from anatomical and diffusion-weighted MR imaging. Finally, we discuss how these methodologies have been applied to systems-level analyses of AD, to help characterize the network changes underlying the disease process, and how these patterns relate to specific cognitive outcome measures.

Accelerating cortical thinning: unique to dementia or universal in aging?

Does accelerated cortical atrophy in aging, especially in areas vulnerable to early Alzheimer's disease (AD), unequivocally signify neurodegenerative disease or can it be part of normal aging? We addressed this in 3 ways. First, age trajectories of cortical thickness were delineated cross-sectionally (n = 1100) and longitudinally (n = 207). Second, effects of undetected AD on the age trajectories were simulated by mixing the sample with a sample of patients with very mild to moderate AD. Third, atrophy in AD-vulnerable regions was examined in older adults with very low probability of incipient AD based on 2-year neuropsychological stability, CSF Aβ(1-42) levels, and apolipoprotein ε4 negativity. Steady decline was seen in most regions, but accelerated cortical thinning in entorhinal cortex was observed across groups. Very low-risk older adults had longitudinal entorhinal atrophy rates similar to other healthy older adults, and this atrophy was predictive of memory change. While steady decline in cortical thickness is the norm in aging, acceleration in AD-prone regions does not uniquely signify neurodegenerative illness but can be part of healthy aging. The relationship between the entorhinal changes and changes in memory performance suggests that non-AD mechanisms in AD-prone areas may still be causative for cognitive reductions.

Longitudinal measures of cholinergic forebrain atrophy in the transition from healthy aging to Alzheimer's disease

Recent evidence from cross-sectional in vivo imaging studies suggests that atrophy of the cholinergic basal forebrain (BF) in Alzheimer's disease (AD) can be distinguished from normal age-related degeneration even at predementia stages of the disease. Longitudinal study designs are needed to specify the dynamics of BF degeneration in the transition from normal aging to AD. We applied recently developed techniques for in vivo volumetry of the BF to serial magnetic resonance imaging scans of 82 initially healthy elderly individuals (60-93 years) and 50 patients with very mild AD (Clinical Dementia Rating score = 0.5) that were clinically followed over an average of 3 ± 1.5 years. BF atrophy rates were found to be significantly higher than rates of global brain shrinkage even in cognitively stable healthy elderly individuals. Compared with healthy control subjects, very mild AD patients showed reduced BF volumes at baseline and increased volume loss over time. Atrophy of the BF was more pronounced in progressive patients compared with those that remained stable. The cholinergic BF undergoes disproportionate degeneration in the aging process, which is further increased by the presence of AD.

Classification of structural MRI images in Alzheimer's disease from the perspective of ill-posed problems

BACKGROUND

Machine learning neuroimaging researchers have often relied on regularization techniques when classifying MRI images. Although these were originally introduced to deal with "ill-posed" problems it is rare to find studies that evaluate the ill-posedness of MRI image classification problems. In addition, to avoid the effects of the "curse of dimensionality" very often dimension reduction is applied to the data.

METHODOLOGY

Baseline structural MRI data from cognitively normal and Alzheimer's disease (AD) patients from the AD Neuroimaging Initiative database were used in this study. We evaluated here the ill-posedness of this classification problem across different dimensions and sample sizes and its relationship to the performance of regularized logistic regression (RLR), linear support vector machine (SVM) and linear regression classifier (LRC). In addition, these methods were compared with their principal components space counterparts.

PRINCIPAL FINDINGS

In voxel space the prediction performance of all methods increased as sample sizes increased. They were not only relatively robust to the increase of dimension, but they often showed improvements in accuracy. We linked this behavior to improvements in conditioning of the linear kernels matrices. In general the RLR and SVM performed similarly. Surprisingly, the LRC was often very competitive when the linear kernel matrices were best conditioned. Finally, when comparing these methods in voxel and principal component spaces, we did not find large differences in prediction performance.

CONCLUSIONS AND SIGNIFICANCE

We analyzed the problem of classifying AD MRI images from the perspective of linear ill-posed problems. We demonstrate empirically the impact of the linear kernel matrix conditioning on different classifiers' performance. This dependence is characterized across sample sizes and dimensions. In this context we also show that increased dimensionality does not necessarily degrade performance of machine learning methods. In general, this depends on the nature of the problem and the type of machine learning method.

Alzheimer disease: new concepts on its neurobiology and the clinical role imaging will play

Alzheimer disease (AD) is one of, if not the most, feared diseases associated with aging. The prevalence of AD increases exponentially with age after 60 years. Increasing life expectancy coupled with the absence of any approved disease-modifying therapies at present position AD as a dominant public health problem. Major advances have occurred in the development of disease biomarkers for AD in the past 2 decades. At present, the most well-developed AD biomarkers are the cerebrospinal fluid analytes amyloid-β 42 and tau and the brain imaging measures amyloid positron emission tomography (PET), fluorodeoxyglucose PET, and magnetic resonance imaging. CSF and imaging biomarkers are incorporated into revised diagnostic guidelines for AD, which have recently been updated for the first time since their original formulation in 1984. Results of recent studies suggest the possibility of an ordered evolution of AD biomarker abnormalities that can be used to stage the typical 20-30-year course of the disease. When compared with biomarkers in other areas of medicine, however, the absence of standardized quantitative metrics for AD imaging biomarkers constitutes a major deficiency. Failure to move toward a standardized system of quantitative metrics has substantially limited potential diagnostic usefulness of imaging in AD. This presents an important opportunity that, if widely embraced, could greatly expand the application of imaging to improve clinical diagnosis and the quality and efficiency of clinical trials.

Diagnostic neuroimaging across diseases

Fully automated classification algorithms have been successfully applied to diagnose a wide range of neurological and psychiatric diseases. They are sufficiently robust to handle data from different scanners for many applications and in specific cases outperform radiologists. This article provides an overview of current applications taking structural imaging in Alzheimer's disease and schizophrenia as well as functional imaging to diagnose depression as examples. In this context, we also report studies aiming to predict the future course of the disease and the response to treatment for the individual. This has obvious clinical relevance but is also important for the design of treatment studies that may aim to include a cohort with a predicted fast disease progression to be more sensitive to detect treatment effects. In the second part, we present our own opinions on i) the role these classification methods can play in the clinical setting; ii) where their limitations are at the moment and iii) how those can be overcome. Specifically, we discuss strategies to deal with disease heterogeneity, diagnostic uncertainties, a probabilistic framework for classification and multi-class classification approaches.

JointMMCC: joint maximum-margin classification and clustering of imaging data

A number of conditions are characterized by pathologies that form continuous or nearly-continuous spectra spanning from the absence of pathology to very pronounced pathological changes (e.g., normal aging, mild cognitive impairment, Alzheimer's). Moreover, diseases are often highly heterogeneous with a number of diagnostic subcategories or subconditions lying within the spectra (e.g., autism spectrum disorder, schizophrenia). Discovering coherent subpopulations of subjects within the spectrum of pathological changes may further our understanding of diseases, and potentially identify subconditions that require alternative or modified treatment options. In this paper, we propose an approach that aims at identifying coherent subpopulations with respect to the underlying MRI in the scenario where the condition is heterogeneous and pathological changes form a continuous spectrum. We describe a joint maximum-margin classification and clustering (JointMMCC) approach that jointly detects the pathologic population via semi-supervised classification, as well as disentangles heterogeneity of the pathological cohort by solving a clustering subproblem. We propose an efficient solution to the nonconvex optimization problem associated with JointMMCC. We apply our proposed approach to an medical resonance imaging study of aging, and identify coherent subpopulations (i.e., clusters) of cognitively less stable adults.

Nonlinear time course of brain volume loss in cognitively normal and impaired elders

The goal was to elucidate the time course of regional brain atrophy rates relative to age in cognitively normal (CN) aging, mild cognitively impairment (MCI), and Alzheimer's disease (AD), without a priori models for atrophy progression. Regional brain volumes from 147 cognitively normal subjects, 164 stable MCI, 93 MCI-to-AD converters and 111 ad patients, between 51 and 91 years old and who had repeated 1.5 T magnetic resonance imaging (MRI) scans over 30 months, were analyzed. Relations between regional brain volume change and age were determined using generalized additive models, an established nonparametric concept for approximating nonlinear relations. Brain atrophy rates varied nonlinearly with age, predominantly in regions of the temporal lobe. Moreover, the atrophy rates of some regions leveled off with increasing age in control and stable MCI subjects whereas those rates progressed further in MCI-to-AD converters and AD patients. The approach has potential uses for early detection of AD and differentiation between stable and progressing MCI.

Predicting future clinical changes of MCI patients using longitudinal and multimodal biomarkers

Accurate prediction of clinical changes of mild cognitive impairment (MCI) patients, including both qualitative change (i.e., conversion to Alzheimer's disease (AD)) and quantitative change (i.e., cognitive scores) at future time points, is important for early diagnosis of AD and for monitoring the disease progression. In this paper, we propose to predict future clinical changes of MCI patients by using both baseline and longitudinal multimodality data. To do this, we first develop a longitudinal feature selection method to jointly select brain regions across multiple time points for each modality. Specifically, for each time point, we train a sparse linear regression model by using the imaging data and the corresponding clinical scores, with an extra 'group regularization' to group the weights corresponding to the same brain region across multiple time points together and to allow for selection of brain regions based on the strength of multiple time points jointly. Then, to further reflect the longitudinal changes on the selected brain regions, we extract a set of longitudinal features from the original baseline and longitudinal data. Finally, we combine all features on the selected brain regions, from different modalities, for prediction by using our previously proposed multi-kernel SVM. We validate our method on 88 ADNI MCI subjects, with both MRI and FDG-PET data and the corresponding clinical scores (i.e., MMSE and ADAS-Cog) at 5 different time points. We first predict the clinical scores (MMSE and ADAS-Cog) at 24-month by using the multimodality data at previous time points, and then predict the conversion of MCI to AD by using the multimodality data at time points which are at least 6-month ahead of the conversion. The results on both sets of experiments show that our proposed method can achieve better performance in predicting future clinical changes of MCI patients than the conventional methods.

Linking white matter integrity loss to associated cortical regions using structural connectivity information in Alzheimer's disease and fronto-temporal dementia: the Loss in Connectivity (LoCo) score

It is well known that gray matter changes occur in neurodegenerative diseases like Alzheimer's (AD) and fronto-temporal dementia (FTD), and several studies have investigated their respective patterns of atrophy progression. Recent work, however, has revealed that diffusion MRI that is able to detect white matter integrity changes may be an earlier or more sensitive biomarker in both diseases. However, studies that examine white matter changes only are limited in that they do not provide the functional specificity of GM region-based analysis. In this study, we develop a new metric called the Loss in Connectivity (LoCo) score that gives the amount of structural network disruption incurred by a gray matter region for a particular pattern of white matter integrity loss. Leveraging the relative strengths of WM and GM markers, this metric links areas of WM integrity loss to their connected GM regions as a first step in understanding their functional implications. The LoCo score is calculated for three groups: 18AD, 18 FTD, and 19 age-matched normal controls. We show significant correlations of the LoCo with the respective atrophy patterns in AD (R=0.51, p=2.2 × 10(-9)) and FTD (R=0.49, p=2.5 × 10(-8)) for a standard 116 region gray matter atlas. In addition, we demonstrate that the LoCo outperforms a measure of gray matter atrophy when classifying individuals into AD, FTD, and normal groups.

Longitudinal imaging pattern analysis (SPARE-CD index) detects early structural and functional changes before cognitive decline in healthy older adults

This article investigates longitudinal imaging characteristics of early cognitive decline during normal aging, leveraging on high-dimensional imaging pattern classification methods for the development of early biomarkers of cognitive decline. By combining magnetic resonance imaging (MRI) and resting positron emission tomography (PET) cerebral blood flow (CBF) images, an individualized score is generated using high-dimensional pattern classification, which predicts subsequent cognitive decline in cognitively normal older adults of the Baltimore Longitudinal Study of Aging. The resulting score, termed SPARE-CD (Spatial Pattern of Abnormality for Recognition of Early Cognitive Decline), analyzed longitudinally for 143 cognitively normal subjects over 8 years, shows functional and structural changes well before (2.3-2.9 years) changes in neurocognitive testing (California Verbal Learning Test [CVLT] scores) can be measured. Additionally, this score is found to be correlated to the [(11)C] Pittsburgh compound B (PiB) PET mean distribution volume ratio at a later time. This work indicates that MRI and PET images, combined with advanced pattern recognition methods, may be useful for very early detection of cognitive decline.

Neuroimaging results impose new views on Alzheimer's disease--the role of amyloid revised

Huge progress has been made in unraveling the mysteries of Alzheimer's disease (AD), but we still do not understand the basic mechanisms that set off the cascade of pathological events. In May 2011, the National Institute on Aging-Alzheimer's Association published new diagnostic guidelines, expected to have huge impact on AD research and clinical practice. However, the new guidelines are already criticized for being biased in favor of a specific theory of the pathophysiological origins of AD-the amyloid cascade hypothesis. Shortly before publication of the guidelines, a hypothetical model of the dynamic biomarkers of the Alzheimer's pathological cascade was published, taking as starting point that biomarkers reflecting brain levels of amyloid become deviant long before brain atrophy, cognitive dysfunction, or clinical symptoms are manifest. This model has already attracted substantial interest and arguably represents a dominating view within human research on AD. Here we critically review the evidence for the view of amyloid as an initiating event in the pathological cascade and discuss how central assumptions of this hypothesis affect how results from contemporary human AD research are understood. Interpretations of new results are greatly impacted by researchers' view on the role of amyloid, and identical observations are sometimes taken to support radically opposing views on the amyloid hypothesis. We argue that the canonical view of the role of amyloid as the main causal factor in AD may not be correct and that evidence from recent neuroimaging studies indicates that amyloid is neither necessary nor sufficient, for the manifestation of AD-like brain atrophy.

Sparse reduced-rank regression detects genetic associations with voxel-wise longitudinal phenotypes in Alzheimer's disease

Scanning the entire genome in search of variants related to imaging phenotypes holds great promise in elucidating the genetic etiology of neurodegenerative disorders. Here we discuss the application of a penalized multivariate model, sparse reduced-rank regression (sRRR), for the genome-wide detection of markers associated with voxel-wise longitudinal changes in the brain caused by Alzheimer's disease (AD). Using a sample from the Alzheimer's Disease Neuroimaging Initiative database, we performed three separate studies that each compared two groups of individuals to identify genes associated with disease development and progression. For each comparison we took a two-step approach: initially, using penalized linear discriminant analysis, we identified voxels that provide an imaging signature of the disease with high classification accuracy; then we used this multivariate biomarker as a phenotype in a genome-wide association study, carried out using sRRR. The genetic markers were ranked in order of importance of association to the phenotypes using a data re-sampling approach. Our findings confirmed the key role of the APOE and TOMM40 genes but also highlighted some novel potential associations with AD.

Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification

Magnetic resonance imaging (MRI) patterns were examined together with cerebrospinal fluid (CSF) biomarkers in serial scans of Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI). The SPARE-AD score, summarizing brain atrophy patterns, was tested as a predictor of short-term conversion to Alzheimer's disease (AD). MCI individuals that converted to AD (MCI-C) had mostly positive baseline SPARE-AD (Spatial Pattern of Abnormalities for Recognition of Early AD) and atrophy in temporal lobe gray matter (GM) and white matter (WM), posterior cingulate/precuneous, and insula. MCI individuals that converted to AD had mostly AD-like baseline CSF biomarkers. MCI nonconverters (MCI-NC) had mixed baseline SPARE-AD and CSF values, suggesting that some MCI-NC subjects may later convert. Those MCI-NC with most negative baseline SPARE-AD scores (normal brain structure) had significantly higher baseline Mini Mental State Examination (MMSE) scores (28.67) than others, and relatively low annual rate of Mini Mental State Examination decrease (-0.25). MCI-NC with midlevel baseline SPARE-AD displayed faster annual rates of SPARE-AD increase (indicating progressing atrophy). SPARE-AD and CSF combination improved prediction over individual values. In summary, both SPARE-AD and CSF biomarkers showed high baseline sensitivity, however, many MCI-NC had abnormal baseline SPARE-AD and CSF biomarkers. Longer follow-up will elucidate the specificity of baseline measurements.

Alliance for aging research AD biomarkers work group: structural MRI

Biomarkers of Alzheimer's disease (AD) are increasingly important. All modern AD therapeutic trials employ AD biomarkers in some capacity. In addition, AD biomarkers are an essential component of recently updated diagnostic criteria for AD from the National Institute on Aging--Alzheimer's Association. Biomarkers serve as proxies for specific pathophysiological features of disease. The 5 most well established AD biomarkers include both brain imaging and cerebrospinal fluid (CSF) measures--cerebrospinal fluid Abeta and tau, amyloid positron emission tomography (PET), fluorodeoxyglucose (FDG) positron emission tomography, and structural magnetic resonance imaging (MRI). This article reviews evidence supporting the position that MRI is a biomarker of neurodegenerative atrophy. Topics covered include methods of extracting quantitative and semiquantitative information from structural MRI; imaging-autopsy correlation; and evidence supporting diagnostic and prognostic value of MRI measures. Finally, the place of MRI in a hypothetical model of temporal ordering of AD biomarkers is reviewed.

Alzheimer's disease pattern of brain atrophy predicts cognitive decline in Parkinson's disease

Research suggests overlap in brain regions undergoing neurodegeneration in Parkinson's and Alzheimer's disease. To assess the clinical significance of this, we applied a validated Alzheimer's disease-spatial pattern of brain atrophy to patients with Parkinson's disease with a range of cognitive abilities to determine its association with cognitive performance and decline. At baseline, 84 subjects received structural magnetic resonance imaging brain scans and completed the Dementia Rating Scale-2, and new robust and expanded Dementia Rating Scale-2 norms were applied to cognitively classify participants. Fifty-nine non-demented subjects were assessed annually with the Dementia Rating Scale-2 for two additional years. Magnetic resonance imaging scans were quantified using both a region of interest approach and voxel-based morphometry analysis, and a method for quantifying the presence of an Alzheimer's disease spatial pattern of brain atrophy was applied to each scan. In multivariate models, higher Alzheimer's disease pattern of atrophy score was associated with worse global cognitive performance (β = -0.31, P = 0.007), including in non-demented patients (β = -0.28, P = 0.05). In linear mixed model analyses, higher baseline Alzheimer's disease pattern of atrophy score predicted long-term global cognitive decline in non-demented patients [F(1, 110) = 9.72, P = 0.002], remarkably even in those with normal cognition at baseline [F(1, 80) = 4.71, P = 0.03]. In contrast, in cross-sectional and longitudinal analyses there was no association between region of interest brain volumes and cognitive performance in patients with Parkinson's disease with normal cognition. These findings support involvement of the hippocampus and parietal-temporal cortex with cognitive impairment and long-term decline in Parkinson's disease. In addition, an Alzheimer's disease pattern of brain atrophy may be a preclinical biomarker of cognitive decline in Parkinson's disease.

Episodic memory on the path to Alzheimer's disease

This review is focused on specific circuits of the medial temporal lobe that have become better understood in recent years for their computational properties contributing to episodic memory and to memory impairment associated with aging and other risk for AD. The layer II neurons in the entorhinal cortex and their targets in the dentate gyrus and CA3 region of hippocampus comprise a system that rapidly encodes representations that are distinct from prior memories. Frank neuron loss in the entorhinal cortex is specific for AD, and related structural and functional changes across the network comprised of the entorhinal cortex and the dentate/CA3 regions hold promise for predicting progression on the path to AD.

High dimensional classification of structural MRI Alzheimer's disease data based on large scale regularization

In this work we use a large scale regularization approach based on penalized logistic regression to automatically classify structural MRI images (sMRI) according to cognitive status. Its performance is illustrated using sMRI data from the Alzheimer Disease Neuroimaging Initiative (ADNI) clinical database. We downloaded sMRI data from 98 subjects (49 cognitive normal and 49 patients) matched by age and sex from the ADNI website. Images were segmented and normalized using SPM8 and ANTS software packages. Classification was performed using GLMNET library implementation of penalized logistic regression based on coordinate-wise descent optimization techniques. To avoid optimistic estimates classification accuracy, sensitivity, and specificity were determined based on a combination of three-way split of the data with nested 10-fold cross-validations. One of the main features of this approach is that classification is performed based on large scale regularization. The methodology presented here was highly accurate, sensitive, and specific when automatically classifying sMRI images of cognitive normal subjects and Alzheimer disease (AD) patients. Higher levels of accuracy, sensitivity, and specificity were achieved for gray matter (GM) volume maps (85.7, 82.9, and 90%, respectively) compared to white matter volume maps (81.1, 80.6, and 82.5%, respectively). We found that GM and white matter tissues carry useful information for discriminating patients from cognitive normal subjects using sMRI brain data. Although we have demonstrated the efficacy of this voxel-wise classification method in discriminating cognitive normal subjects from AD patients, in principle it could be applied to any clinical population.

Decoding the neural correlates of consciousness

PURPOSE OF REVIEW

Multivariate pattern analysis (MVPA) is an emerging technique for analysing functional imaging data that is capable of a much closer approximation of neuronal activity than conventional methods. This review will outline the advantages, applications and limitations of MVPA in understanding the neural correlates of consciousness.

RECENT FINDINGS

MVPA has provided important insights into the processing of perceptual information by revealing content-specific information at early stages of perceptual processing. It has also shed light on the processing of memories and decisions. In combination with techniques to reconstruct viewed images, MVPA can also be used to reveal the contents of consciousness.

SUMMARY

The development of multivariate pattern analysis techniques allows content-specific and detailed information to be extracted from functional MRI data. This may lead to new therapeutic applications but also raises important ethical considerations.

Registration of longitudinal brain image sequences with implicit template and spatial-temporal heuristics

Accurate measurement of longitudinal changes of brain structures and functions is very important but challenging in many clinical studies. Also, across-subject comparison of longitudinal changes is critical in identifying disease-related changes. In this paper, we propose a novel method to meet these two requirements by simultaneously registering sets of longitudinal image sequences of different subjects to the common space, without assuming any explicit template. Specifically, our goal is to 1) consistently measure the longitudinal changes from a longitudinal image sequence of each subject, and 2) jointly align all image sequences of different subjects to a hidden common space. To achieve these two goals, we first introduce a set of temporal fiber bundles to explore the spatial-temporal behavior of anatomical changes in each longitudinal image sequence. Then, a probabilistic model is built upon the temporal fibers to characterize both spatial smoothness and temporal continuity. Finally, the transformation fields that connect each time-point image of each subject to the common space are simultaneously estimated by the expectation maximization (EM) approach, via the maximum a posterior (MAP) estimation of the probabilistic models. Promising results have been obtained in quantitative measurement of longitudinal brain changes, i.e., hippocampus volume changes, showing better performance than those obtained by either the pairwise or the groupwise only registration methods.

A comparison of different automated methods for the detection of white matter lesions in MRI data

White matter hyperintensities (WMH) are the focus of intensive research and have been linked to cognitive impairment and depression in the elderly. Cumbersome manual outlining procedures make research on WMH labour intensive and prone to subjective bias. This study compares fully automated supervised detection methods that learn to identify WMH from manual examples against unsupervised approaches on the combination of FLAIR and T1 weighted images. Data were collected from ten subjects with mild cognitive impairment and another set of ten individuals who fulfilled diagnostic criteria for dementia. Data were split into balanced groups to create a training set used to optimize the different methods. Manual outlining served as gold standard to evaluate performance of the automated methods that identified each voxel either as intact or as part of a WMH. Otsu's approach for multiple thresholds which is based only on voxel intensities of the FLAIR image produced a high number of false positives at grey matter boundaries. Performance on an independent test set was similarly disappointing when simply applying a threshold to the FLAIR that was found from training data. Among the supervised methods, precision-recall curves of support vector machines (SVM) indicated advantages over the performance achieved by K-nearest-neighbor classifiers (KNN). The curves indicated a clear benefit from optimizing the threshold of the SVM decision value and the voting rule of the KNN. Best performance was reached by selecting training voxels according to their distance to the lesion boundary and repeated training after replacing the feature vectors from those voxels that did not form support vectors of the SVM. The study demonstrates advantages of SVM for the problem of detecting WMH at least for studies that include only FLAIR and T1 weighted images. Various optimization strategies are discussed and compared against each other.

MRI-based age prediction using hidden Markov models

Cortical thinning and intracortical gray matter volume losses are widely observed in normal ageing, while the decreasing rate of the volume loss in subjects with neurodegenerative disorders such as Alzheimer's disease is reported to be faster than the average speed. Therefore, neurodegenerative disease is considered as accelerated ageing. Accurate detection of accelerated ageing based on the magnetic resonance imaging (MRI) of the brain is a relatively new direction of research in computational neuroscience as it has the potential to offer positive clinical outcome through early intervention. In order to capture the faster structural alterations in the brain with ageing, we propose in this paper a computational approach for modelling the MRI-based structure of the brain using the framework of hidden Markov models, which can be utilized for age prediction. Experiments were carried out on healthy subjects to validate its accuracy and its robustness. The results have shown its ability of predicting the brain age with an average normalized age-gap error of two to three years, which is superior to several recently developed methods for brain age prediction.

New tools for the study of Alzheimer's disease: what are biomarkers and morphometric markers teaching us?

Early detection is vital in the quest to develop a cure for Alzheimer's disease (AD), and CSF biomarkers (Aβ42, t-tau, p-tau) and MRI morphometry distinguish AD from healthy controls. Aβ42 and neurodegenerative biomarkers may precede clinical symptoms, but it is not clear whether AD invariably follows and whether neuropsychological tests are as sensitive. Aβ42 is related to plaque burden, which was assumed to be the main cause of AD. Evidence is now pointing to other forms of Aβ, for example, soluble Aβ oligomers, and it is possible that plaques are secondary rather than causative to neuronal damage. This makes it less obvious that CSF Aβ42 necessarily is the most potent marker. Atrophy has been regarded as a downstream event, but novel MRI analysis techniques detect atrophy at a stage where the cognitive reductions are small and possibly reversible, and MRI is superior to CSF biomarkers in the prediction of cognitive decline. The impact of biomarkers may be dynamic; changed Aβ42 is seen in cognitively normal, while atrophy causes decrements later. In conclusion, CSF and MRI biomarkers are extremely important, but it is not known whether they can distinguish events that will lead to AD from events that will not before cognitive reductions are measurable.

Amyloid-β associated cortical thinning in clinically normal elderly

Objective

Both amyloid-β (Aβ) deposition and brain atrophy are associated with Alzheimer's disease (AD) and the disease process likely begins many years before symptoms appear. We sought to determine whether clinically normal (CN) older individuals with Aβ deposition revealed by positron emission tomography (PET) imaging using Pittsburgh Compound B (PiB) also have evidence of both cortical thickness and hippocampal volume reductions in a pattern similar to that seen in AD.

Methods

A total of 119 older individuals (87 CN subjects and 32 patients with mild AD) underwent PiB PET and high-resolution structural magnetic resonance imaging (MRI). Regression models were used to relate PiB retention to cortical thickness and hippocampal volume.

Results

We found that PiB retention in CN subjects was (1) age-related and (2) associated with cortical thickness reductions, particularly in parietal and posterior cingulate regions extending into the precuneus, in a pattern similar to that observed in mild AD. Hippocampal volume reduction was variably related to Aβ deposition.

Interpretation

We conclude that Aβ deposition is associated with a pattern of cortical thickness reduction consistent with AD prior to the development of cognitive impairment. ANN NEUROL 2010;