New preclinical Alzheimer disease (AD) diagnostic criteria have been developed using biomarkers in cognitively normal (CN) adults. We implemented these criteria using an MRI biomarker previously ...associated with AD dementia, testing the hypothesis that individuals at high risk for preclinical AD would be at elevated risk for cognitive decline.
The Alzheimer's Disease Neuroimaging Initiative database was interrogated for CN individuals. MRI data were processed using a published set of a priori regions of interest to derive a single measure known as the AD signature (ADsig). Each individual was classified as ADsig-low (≥ 1 SD below the mean: high risk for preclinical AD), ADsig-average (within 1 SD of mean), or ADsig-high (≥ 1 SD above mean). A 3-year cognitive decline outcome was defined a priori using change in Clinical Dementia Rating sum of boxes and selected neuropsychological measures.
Individuals at high risk for preclinical AD were more likely to experience cognitive decline, which developed in 21% compared with 7% of ADsig-average and 0% of ADsig-high groups (p = 0.03). Logistic regression demonstrated that every 1 SD of cortical thinning was associated with a nearly tripled risk of cognitive decline (p = 0.02). Of those for whom baseline CSF data were available, 60% of the high risk for preclinical AD group had CSF characteristics consistent with AD while 36% of the ADsig-average and 19% of the ADsig-high groups had such CSF characteristics (p = 0.1).
This approach to the detection of individuals at high risk for preclinical AD-identified in single CN individuals using this quantitative ADsig MRI biomarker-may provide investigators with a population enriched for AD pathobiology and with a relatively high likelihood of imminent cognitive decline consistent with prodromal AD.
It is challenging at baseline to predict when and which individuals who meet criteria for mild cognitive impairment (MCI) will ultimately progress to Alzheimer's disease (AD) dementia.
A deep ...learning method is developed and validated based on magnetic resonance imaging scans of 2146 subjects (803 for training and 1343 for validation) to predict MCI subjects' progression to AD dementia in a time-to-event analysis setting.
The deep-learning time-to-event model predicted individual subjects' progression to AD dementia with a concordance index of 0.762 on 439 Alzheimer's Disease Neuroimaging Initiative testing MCI subjects with follow-up duration from 6 to 78 months (quartiles: 24, 42, 54) and a concordance index of 0.781 on 40 Australian Imaging Biomarkers and Lifestyle Study of Aging testing MCI subjects with follow-up duration from 18 to 54 months (quartiles: 18, 36, 54). The predicted progression risk also clustered individual subjects into subgroups with significant differences in their progression time to AD dementia (P < .0002). Improved performance for predicting progression to AD dementia (concordance index = 0.864) was obtained when the deep learning–based progression risk was combined with baseline clinical measures.
Our method provides a cost effective and accurate means for prognosis and potentially to facilitate enrollment in clinical trials with individuals likely to progress within a specific temporal period.
Brain aging is a complex process that includes atrophy, vascular injury, and a variety of age-associated neurodegenerative pathologies, together determining an individual’s course of cognitive ...decline. While Alzheimer's disease and related dementias contribute to the heterogeneity of brain aging, these conditions themselves are also heterogeneous in their clinical presentation, progression, and pattern of neural injury. We reviewed studies that leveraged data-driven approaches to examining heterogeneity in Alzheimer's disease and related dementias, with a principal focus on neuroimaging studies exploring subtypes of regional neurodegeneration patterns. Over the past decade, the steadily increasing wealth of clinical, neuroimaging, and molecular biomarker information collected within large-scale observational cohort studies has allowed for a richer understanding of the variability of disease expression within the aging and Alzheimer's disease and related dementias continuum. Moreover, the availability of these large-scale datasets has supported the development and increasing application of clustering techniques for studying disease heterogeneity in a data-driven manner. In particular, data-driven studies have led to new discoveries of previously unappreciated disease subtypes characterized by distinct neuroimaging patterns of regional neurodegeneration, which are paralleled by heterogeneous profiles of pathological, clinical, and molecular biomarker characteristics. Incorporating these findings into novel frameworks for more differentiated disease stratification holds great promise for improving individualized diagnosis and prognosis of expected clinical progression, and provides opportunities for development of precision medicine approaches for therapeutic intervention. We conclude with an account of the principal challenges associated with data-driven heterogeneity analyses and outline avenues for future developments in the field.
Although both normal aging and Alzheimer's disease (AD) are associated with regional cortical atrophy, few studies have directly compared the spatial patterns and magnitude of effects of these two ...processes. The extant literature has not addressed two important questions: 1) Is the pattern of age-related cortical atrophy different if cognitively intact elderly individuals with silent AD pathology are excluded? and 2) Does the age- or AD-related atrophy relate to cognitive function? Here we studied 142 young controls, 87 older controls, and 28 mild AD patients. In addition, we studied 35 older controls with neuroimaging data indicating the absence of brain amyloid. Whole-cortex analyses identified regions of interest (ROIs) of cortical atrophy in aging and in AD. Results showed that some regions are predominantly affected by age with relatively little additional atrophy in patients with AD, e.g., calcarine cortex; other regions are predominantly affected by AD with much less of an effect of age, e.g., medial temporal cortex. Finally, other regions are affected by both aging and AD, e.g., dorsolateral prefrontal cortex and inferior parietal lobule. Thus, the processes of aging and AD have both differential and partially overlapping effects on specific regions of the cerebral cortex. In particular, some frontoparietal regions are affected by both processes, most temporal lobe regions are affected much more prominently by AD than aging, while sensorimotor and some prefrontal regions are affected specifically by aging and minimally more by AD. Within normal older adults, atrophy in aging-specific cortical regions relates to cognitive performance, while in AD patients atrophy in AD-specific regions relates to cognitive performance. Further work is warranted to investigate the behavioral and clinical relevance of these findings in additional detail, as well as their histological basis; ROIs generated from the present study could be used strategically in such investigations.
•Some cortical regions atrophy in normal aging, while others atrophy in Alzheimer's.•Some cortical—especially frontoparietal—regions are affected by both processes.•In normal older adults, thinning in aging-specific regions relates to cognition.•In AD patients, thinning in AD-specific regions relates to cognitive performance.
As medical imaging enters its information era and presents rapidly increasing needs for big data analytics, robust pooling and harmonization of imaging data across diverse cohorts with varying ...acquisition protocols have become critical. We describe a comprehensive effort that merges and harmonizes a large-scale dataset of 10,477 structural brain MRI scans from participants without a known neurological or psychiatric disorder from 18 different studies that represent geographic diversity. We use this dataset and multi-atlas-based image processing methods to obtain a hierarchical partition of the brain from larger anatomical regions to individual cortical and deep structures and derive age trends of brain structure through the lifespan (3–96 years old). Critically, we present and validate a methodology for harmonizing this pooled dataset in the presence of nonlinear age trends. We provide a web-based visualization interface to generate and present the resulting age trends, enabling future studies of brain structure to compare their data with this reference of brain development and aging, and to examine deviations from ranges, potentially related to disease.
•Multi-site harmonization method that pools volumetric data from 18 studies, controlling for nonlinear age effects.•Resulting dataset covers ages 3 to 96 and used to derive age trends of brain structure through the lifespan.•Interactive visualization tool provided for exploring age trends and comparing new data.
Deep learning has emerged as a powerful approach to constructing imaging signatures of normal brain ageing as well as of various neuropathological processes associated with brain diseases. In ...particular, MRI-derived brain age has been used as a comprehensive biomarker of brain health that can identify both advanced and resilient ageing individuals via deviations from typical brain ageing. Imaging signatures of various brain diseases, including schizophrenia and Alzheimer's disease, have also been identified using machine learning. Prior efforts to derive these indices have been hampered by the need for sophisticated and not easily reproducible processing steps, by insufficiently powered or diversified samples from which typical brain ageing trajectories were derived, and by limited reproducibility across populations and MRI scanners. Herein, we develop and test a sophisticated deep brain network (DeepBrainNet) using a large (n = 11 729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages and geographic locations around the world. Tests using both cross-validation and a separate replication cohort of 2739 individuals indicate that DeepBrainNet obtains robust brain-age estimates from these diverse datasets without the need for specialized image data preparation and processing. Furthermore, we show evidence that moderately fit brain ageing models may provide brain age estimates that are most discriminant of individuals with pathologies. This is not unexpected as tightly-fitting brain age models naturally produce brain-age estimates that offer little information beyond age, and loosely fitting models may contain a lot of noise. Our results offer some experimental evidence against commonly pursued tightly-fitting models. We show that the moderately fitting brain age models obtain significantly higher differentiation compared to tightly-fitting models in two of the four disease groups tested. Critically, we demonstrate that leveraging DeepBrainNet, along with transfer learning, allows us to construct more accurate classifiers of several brain diseases, compared to directly training classifiers on patient versus healthy control datasets or using common imaging databases such as ImageNet. We, therefore, derive a domain-specific deep network likely to reduce the need for application-specific adaptation and tuning of generic deep learning networks. We made the DeepBrainNet model freely available to the community for MRI-based evaluation of brain health in the general population and over the lifespan.
The connection between Alzheimer's disease (AD) and olfactory deficits is well documented and further, alterations in olfactory functioning may signal declines in functions associated with dementia. ...The aim of the present comprehensive meta-analysis was to investigate the nature of olfactory deficits in mild cognitive impairment (MCI).
Articles were identified through computerised literature search from inception to 30 June 2016 using PubMed, MEDLINE and PsychInfo databases. In order to control for differences in sample size during effect size computation, studies were weighted according to their inverse variance estimates.
31 articles (62 effects) were identified, which included 1993 MCI patients and 2861 healthy older adults (HOA). Included studies contrasted odour identification, discrimination, detection threshold and/or memory between cases and controls. Moderate to large and heterogeneous effects were seen for olfactory deficits in MCI relative to HOA (d=-0.76, 95% CI -0.87<δ<-0.64). Moderator analysis revealed that tests of odour identification yielded larger effect sizes than those of odour detection threshold or memory. In addition, a potential interaction between age and sex was observed, with male patients carrying a larger burden of olfactory deficit and older female patients performing better on olfactory tests.
Olfactory deficits are present and robust in MCI. Odour identification is most impaired in MCI, which parallels the most prominent sensory deficit seen in AD. As such, a simple-to-administer test of odour identification warrants inclusion in the screening of individuals at risk for developing AD.
Automatic segmentation of brain anatomy has been a key processing step in quantitative neuroimaging analyses. An extensive body of literature has relied on Freesurfer segmentations. Yet, in recent ...years, the multi-atlas segmentation framework has consistently obtained results with superior accuracy in various evaluations. We compared brain anatomy segmentations from Freesurfer, which uses a single probabilistic atlas strategy, against segmentations from Multi-atlas region Segmentation utilizing Ensembles of registration algorithms and parameters and locally optimal atlas selection (MUSE), one of the leading ensemble-based methods that calculates a consensus segmentation through fusion of anatomical labels from multiple atlases and registrations. The focus of our evaluation was twofold. First, using manual ground-truth hippocampus segmentations, we found that Freesurfer segmentations showed a bias towards over-segmentation of larger hippocampi, and under-segmentation in older age. This bias was more pronounced in Freesurfer-v5.3, which has been used in multiple previous studies of aging, while the effect was mitigated in more recent Freesurfer-v6.0, albeit still present. Second, we evaluated inter-scanner segmentation stability using same day scan pairs from ADNI acquired on 1.5T and 3T scanners. We also found that MUSE obtains more consistent segmentations across scanners compared to Freesurfer, particularly in the deep structures.