Dataset Information

Joint analysis of structural and perfusion MRI for cognitive assessment and classification of Alzheimer's disease and normal aging.

ABSTRACT: Structural magnetic resonance imaging (MRI) of brain tissue loss and physiological imaging of regional cerebral blood flow (rCBF) can provide complimentary information for the characterization of brain disorders, such as Alzheimer's disease (AD) but studies into gains in classification power for AD using these image modalities jointly have been limited. Our aim in this study was to determine the joint contribution of structural and perfusion-weighted imaging for the classification of AD in a cross-sectional study using an integrated multimodality MRI processing framework and a cortical surface-based analysis approach. We used logistic regression analysis to determine sequentially the value of cortical thickness, rCBF, and cortical thickness and rCBF jointly for classification for diagnosis of AD compared to controls. We further tested the extent to which cortical thinning and reduced rCBF explain individually or together variability in dementia severity. Separate analysis of structural MRI and perfusion-weighted MRI data yielded the well-established pattern of cortical thinning and rCBF reduction in AD, affecting predominantly temporo-parietal brain regions. Using structural MRI and perfusion-weighted MRI jointly indicated that cortical thinning dominated the classification of AD and controls without significant contributions from rCBF. However there was also a positive interaction between reduced rCBF and cortical thinning in the right superior temporal sulcus, implying that structural and physiological brain alterations in AD can be complementary. Compared to reduced rCBF, regional cortical thinning better explained the variability in dementia severity. In conclusion, structural brain alterations compared to physiological variations are the dominant features of MRI in AD.

SUBMITTER: Tosun D

PROVIDER: S-EPMC4667806 | biostudies-literature | 2010 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Joint analysis of structural and perfusion MRI for cognitive assessment and classification of Alzheimer's disease and normal aging.

Tosun Duygu D Mojabi Pouria P Weiner Michael W MW Schuff Norbert N

NeuroImage 20100418 1

Structural magnetic resonance imaging (MRI) of brain tissue loss and physiological imaging of regional cerebral blood flow (rCBF) can provide complimentary information for the characterization of brain disorders, such as Alzheimer's disease (AD) but studies into gains in classification power for AD using these image modalities jointly have been limited. Our aim in this study was to determine the joint contribution of structural and perfusion-weighted imaging for the classification of AD in a cro ...[more]

PMID: 20406691

Similar Datasets

Project description:One of the central features of brain aging is the accumulation of multiple age-related structural changes, which occur heterogeneously in individuals and can have immediate or potential clinical consequences. Each of these deficits can coexist and interact, producing both independent and additive impacts on brain health. Many of the changes can be visualized using MRI. To collectively assess whole-brain structural changes, the MRI-based Brain Atrophy and Lesion Index (BALI) has been developed. In this study, we validate this whole-brain health assessment approach using several clinical MRI examinations.Data came from three independent studies: the Alzheimer's Disease Neuroimaging Initiative Phase II (n=950; women =47.9%; age =72.7±7.4 years); the National Alzheimer's Coordinating Center (n=722; women =55.1%; age =72.7±9.9 years); and the Tianjin Medical University General Hospital Research database on older adults (n=170; women =60.0%; age =62.9±9.3 years). The 3.0-Tesla MRI scans were evaluated using the BALI rating scheme on the basis of T1-weighted (T1WI), T2-weighted (T2WI), T2-weighted fluid-attenuated inversion recovery (T2-FLAIR), and T2*-weighted gradient-recalled echo (T2*GRE) images.Atrophy and lesion changes were commonly seen in each MRI test. The BALI scores based on different sequences were highly correlated (Spearman r2>0.69; P<0.00001). They were associated with age (r2>0.29; P<0.00001) and differed by cognitive status (?2>26.48, P<0.00001). T2-FLAIR revealed a greater level of periventricular (?2=29.09) and deep white matter (?2=26.65, P<0.001) lesions than others, but missed revealing certain dilated perivascular spaces that were seen in T2WI (P<0.001). Microhemorrhages occurred in 15.3% of the sample examined and were detected using only T2*GRE.The T1WI- and T2WI-based BALI evaluations consistently identified the burden of aging and dementia-related decline of structural brain health. Inclusion of additional MRI tests increased lesion differentiation. Further research is to integrate MRI tests for a clinical tool to aid the diagnosis and intervention of brain aging.

Project description:BackgroundThe combined analysis of imaging and functional modalities is supposed to improve diagnostics of neurodegenerative diseases with advanced data science techniques.ObjectiveTo get an insight into normal and accelerated brain aging by developing the machine learning models that predict individual performance in neuropsychological and cognitive tests from brain MRI. With these models we endeavor to look for patterns of brain structure-function association (SFA) indicative of mild cognitive impairment (MCI) and Alzheimer's dementia.Materials and methodsWe explored the age-related variability of cognitive and neuropsychological test scores in normal and accelerated aging and constructed regression models predicting functional performance in cognitive tests from brain radiomics data. The models were trained on the three study cohorts from ADNI dataset-cognitively normal individuals, patients with MCI or dementia-separately. We also looked for significant correlations between cortical parcellation volumes and test scores in the cohorts to investigate neuroanatomical differences in relation to cognitive status. Finally, we worked out an approach for the classification of the examinees according to the pattern of structure-function associations into the cohorts of the cognitively normal elderly and patients with MCI or dementia.ResultsIn the healthy population, the global cognitive functioning slightly changes with age. It also remains stable across the disease course in the majority of cases. In healthy adults and patients with MCI or dementia, the trendlines of performance in digit symbol substitution test and trail making test converge at the approximated point of 100 years of age. According to the SFA pattern, we distinguish three cohorts: the cognitively normal elderly, patients with MCI, and dementia. The highest accuracy is achieved with the model trained to predict the mini-mental state examination score from voxel-based morphometry data. The application of the majority voting technique to models predicting results in cognitive tests improved the classification performance up to 91.95% true positive rate for healthy participants, 86.21%-for MCI and 80.18%-for dementia cases.ConclusionThe machine learning model, when trained on the cases of this of that group, describes a disease-specific SFA pattern. The pattern serves as a "stamp" of the disease reflected by the model.

Project description:BackgroundMachine 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.MethodologyBaseline 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 findingsIn 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 significanceWe 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.

Project description:Semantic category learning is dependent upon several factors, including the nature of the learning task, as well as individual differences in the quality and heterogeneity of exemplars that an individual encounters during learning. We trained healthy older adults (n=39) and individuals with a diagnosis of Alzheimer's disease or Mild Cognitive Impairment (n=44) to recognize instances of a fictitious animal, a "crutter". Each stimulus item contained 10 visual features (e.g., color, tail shape) which took one of two values for each feature (e.g., yellow/red, curly/straight tails). Participants were presented with a series of items (learning phase) and were either told the items belonged to a semantic category (explicit condition) or were told to think about the appearance of the items (implicit condition). Half of participants saw learning items with higher similarity to an unseen prototype (high typicality learning set), and thus lower between-item variability in their constituent features; the other half learned from items with lower typicality (low typicality learning set) and higher between-item feature variability. After the learning phase, participants were presented with test items one at a time that varied in the number of typical features from 0 (antitype) to 10 (prototype). We examined between-subjects factors of learning set (lower or higher typicality), instruction type (explicit or implicit), and group (patients vs. elderly control). Learning in controls was aided by higher learning set typicality: while controls in both learning set groups demonstrated significant learning, those exposed to a high-typicality learning set appeared to develop a prototype that helped guide their category membership judgments. Overall, patients demonstrated more difficulty with category learning than elderly controls. Patients exposed to the higher-typicality learning set were sensitive to the typical features of the category and discriminated between the most and least typical test items, although less reliably than controls. In contrast, patients exposed to the low-typicality learning set showed no evidence of learning. Analysis of structural imaging data indicated a positive association between left hippocampal grey matter density in elderly controls but a negative association in the patient group, suggesting differential reliance on hippocampal-mediated learning. Contrary to hypotheses, learning did not differ between explicit and implicit conditions for either group. Results demonstrate that category learning is improved when learning materials are highly similar to the prototype.

Dataset Information

Joint analysis of structural and perfusion MRI for cognitive assessment and classification of Alzheimer's disease and normal aging.

Publications

Joint analysis of structural and perfusion MRI for cognitive assessment and classification of Alzheimer's disease and normal aging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets