Dataset Information

Integration of multimodal MRI data via PCA to explain language performance.

ABSTRACT:

Objective/methods

Neuroimaging research has predominantly focused on exploring how cortical or subcortical brain abnormalities are related to language dysfunction in patients with neurological disease through the use of single modality imaging. Still, limited knowledge exists on how various MRI measures relate to each other and to patients' language performance. In this study, we explored the relationship between measures of regional cortical thickness, gray-white matter contrast (GWMC), white matter diffusivity [mean diffusivity (MD) and fractional anisotropy (FA)] and the relative contributions of these MRI measures to predicting language function across patients with temporal lobe epilepsy (TLE) and healthy controls. T1- and diffusion-weighted MRI data were collected from 56 healthy controls and 52 patients with TLE. By focusing on frontotemporal regions implicated in language function, we reduced each domain of MRI data to its principal component (PC) and quantified the correlations among these PCs and the ability of these PCs to explain the variation in vocabulary, naming and fluency. We followed up our significant findings by assessing the predictive power of the implicated PCs with respect to language impairment in our sample.

Results

We found significant positive associations between PCs representing cortical thickness, GWMC and FA that appeared to be partially mediated by changes in total brain volume. We also found a significant association between reduced FA and increased MD after controlling for confounding factors (e.g., age, field strength, total brain volume). Reduced FA was significantly associated with reductions in visual naming while increased MD was associated with reductions in auditory naming scores, even after controlling for the variability explained by reductions in hippocampal volumes. Inclusion of FA and MD PCs in predictive models of language impairment resulted in significant improvements in sensitivity and specificity of the predictions.

Conclusions

Quantitative MRI measures from T1 and diffusion-weighted scans are unlikely to represent perfectly orthogonal vectors of disease in individuals with epilepsy. On the contrary, they exhibit highly intercorrelated PCs in their factor structures, which is consistent with an underlying pathological process that affects both the cortical and the subcortical structures simultaneously. In addition to hippocampal volume, the PCs of diffusion weighted measures (FA and MD) increase the sensitivity and specificity for determining naming impairment in patients with TLE. These findings underline the importance of combining multimodal imaging measures to better predict language performance in TLE that could extend to other patients with prominent language impairments.

SUBMITTER: Kucukboyaci NE

PROVIDER: S-EPMC4110349 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integration of multimodal MRI data via PCA to explain language performance.

Kucukboyaci N E NE Kemmotsu N N Leyden K M KM Girard H M HM Tecoma E S ES Iragui V J VJ McDonald C R CR

NeuroImage. Clinical 20140514

<h4>Objective/methods</h4>Neuroimaging research has predominantly focused on exploring how cortical or subcortical brain abnormalities are related to language dysfunction in patients with neurological disease through the use of single modality imaging. Still, limited knowledge exists on how various MRI measures relate to each other and to patients' language performance. In this study, we explored the relationship between measures of regional cortical thickness, gray-white matter contrast (GWMC), ...[more]

PMID: 25068109

Similar Datasets

Project description:Magnetic resonance imaging (MRI) has been proposed as a source of information for automatic prediction of individual diagnosis in schizophrenia. Optimal integration of data from different MRI modalities is an active area of research aimed at increasing diagnostic accuracy. Based on a sample of 96 patients with schizophrenia and a matched sample of 115 healthy controls that had undergone a single multimodal MRI session, we generated individual brain maps of gray matter vbm, 1back, and 2back levels of activation (nback fMRI), maps of amplitude of low-frequency fluctuations (resting-state fMRI), and maps of weighted global brain connectivity (resting-state fMRI). Four unimodal classifiers (Ridge, Lasso, Random Forests, and Gradient boosting) were applied to these maps to evaluate their classification accuracies. Based on the assignments made by the algorithms on test individuals, we quantified the amount of predictive information shared between maps (what we call redundancy analysis). Finally, we explored the added accuracy provided by a set of multimodal strategies that included post-classification integration based on probabilities, two-step sequential integration, and voxel-level multimodal integration through one-dimensional-convolutional neural networks (1D-CNNs). All four unimodal classifiers showed the highest test accuracies with the 2back maps (80% on average) achieving a maximum of 84% with the Lasso. Redundancy levels between brain maps were generally low (overall mean redundancy score of 0.14 in a 0-1 range), indicating that each brain map contained differential predictive information. The highest multimodal accuracy was delivered by the two-step Ridge classifier (87%) followed by the Ridge maximum and mean probability classifiers (both with 85% accuracy) and by the 1D-CNN, which achieved the same accuracy as the best unimodal classifier (84%). From these results, we conclude that from all MRI modalities evaluated task-based fMRI may be the best unimodal diagnostic option in schizophrenia. Low redundancy values point to ample potential for accuracy improvements through multimodal integration, with the two-step Ridge emerging as a suitable strategy.

Project description:The amounts and types of available multimodal tumor data are rapidly increasing, and their integration is critical for fully understanding the underlying cancer biology and personalizing treatment. However, the development of methods for effectively integrating multimodal data in a principled manner is lagging behind our ability to generate the data. In this article, we introduce an extension to a multiview nonnegative matrix factorization algorithm (NNMF) for dimensionality reduction and integration of heterogeneous data types and compare the predictive modeling performance of the method on unimodal and multimodal data. We also present a comparative evaluation of our novel multiview approach and current data integration methods. Our work provides an efficient method to extend an existing dimensionality reduction method. We report rigorous evaluation of the method on large-scale quantitative protein and phosphoprotein tumor data from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) acquired using state-of-the-art liquid chromatography mass spectrometry. Exome sequencing and RNA-Seq data were also available from The Cancer Genome Atlas for the same tumors. For unimodal data, in case of breast cancer, transcript levels were most predictive of estrogen and progesterone receptor status and copy number variation of human epidermal growth factor receptor 2 status. For ovarian and colon cancers, phosphoprotein and protein levels were most predictive of tumor grade and stage and residual tumor, respectively. When multiview NNMF was applied to multimodal data to predict outcomes, the improvement in performance is not overall statistically significant beyond unimodal data, suggesting that proteomics data may contain more predictive information regarding tumor phenotypes than transcript levels, probably due to the fact that proteins are the functional gene products and therefore a more direct measurement of the functional state of the tumor. Here, we have applied our proposed approach to multimodal molecular data for tumors, but it is generally applicable to dimensionality reduction and joint analysis of any type of multimodal data.

Project description:Introduction: Corticobasal syndrome (CBS) is a progressive neurological disorder related to multiple underlying pathologies, including four-repeat tauopathies, such as corticobasal degeneration and progressive supranuclear palsy, and Alzheimer's disease (AD). Speech and language are commonly impaired, encompassing a broad spectrum of deficits. We aimed to investigate CBS speech and language impairment patterns in light of a multimodal imaging approach. Materials and Methods: Thirty-one patients with probable CBS were prospectively evaluated concerning their speech-language, cognitive, and motor profiles. They underwent positron emission tomography with [18F]fluorodeoxyglucose (FDG-PET) and [11C]Pittsburgh Compound-B (PIB-PET) on a hybrid PET-MRI machine to assess their amyloid status. PIB-PET images were classified based on visual and semi-quantitative analyses. Quantitative group analyses were performed on FDG-PET data, and atrophy patterns on MRI were investigated using voxel-based morphometry (VBM). Thirty healthy participants were recruited as imaging controls. Results: Aphasia was the second most prominent cognitive impairment, presented in 67.7% of the cases, following apraxia (96.8%). We identified a wide linguistic profile, ranging from nonfluent variant-primary progressive aphasia to lexical-semantic deficits, mostly with impaired verbal fluency. PIB-PET was classified as negative (CBS-A- group) in 18/31 (58%) and positive (CBS-A+ group) in 13/31 (42%) patients. The frequency of dysarthria was significantly higher in the CBS-A- group than in the CBS-A+ group (55.6 vs. 7.7%, p = 0.008). CBS patients with dysarthria had a left-sided hypometabolism at frontal regions, with a major cluster at the left inferior frontal gyrus and premotor cortex. They showed brain atrophy mainly at the opercular frontal gyrus and putamen. There was a positive correlation between [18F]FDG uptake and semantic verbal fluency at the left inferior (p = 0.006, R 2 = 0.2326), middle (0.0054, R 2 = 0.2376), and superior temporal gyri (p = 0.0066, R 2 = 0.2276). Relative to the phonemic verbal fluency, we found a positive correlation at the left frontal opercular gyrus (p = 0.0003, R 2 = 0.3685), the inferior (p = 0.0004, R 2 = 0.3537), and the middle temporal gyri (p = 0.0001, R 2 = 0.3993). Discussion: In the spectrum of language impairment profile, dysarthria might be helpful to distinguish CBS patients not related to AD. Metabolic and structural signatures depicted from this feature provide further insights into the motor speech production network and are also helpful to differentiate CBS variants.

Dataset Information

Integration of multimodal MRI data via PCA to explain language performance.

Objective/methods

Results

Conclusions

Publications

Integration of multimodal MRI data via PCA to explain language performance.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets