Dataset Information

Development of a Bayesian multimodal model to detect biomarkers in neuroimaging studies.

ABSTRACT: In this article, we developed a Bayesian multimodal model to detect biomarkers (or neuromarkers) using resting-state functional and structural data while comparing a late-life depression group with a healthy control group. Biomarker detection helps determine a target for treatment intervention to get the optimal therapeutic benefit for treatment-resistant patients. The borrowing strength of the structural connectivity has been quantified for functional activity while detecting the biomarker. In the biomarker searching process, thousands of hypotheses are generated and tested simultaneously using our novel method to control the false discovery rate for small samples. Several existing statistical approaches, frequently used in analyzing neuroimaging data have been investigated and compared via simulation with the proposed approach to show its excellent performance. Results are illustrated with a live data set generated in a late-life depression study. The role of detected biomarkers in terms of cognitive function has been explored.

SUBMITTER: Bhaumik DK

PROVIDER: S-EPMC10406277 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of a Bayesian multimodal model to detect biomarkers in neuroimaging studies.

Bhaumik Dulal K DK Wang Yue Y Yen Pei-Shan PS Ajilore Olusola A OA

Frontiers in neuroimaging 20230524

In this article, we developed a Bayesian multimodal model to detect biomarkers (or neuromarkers) using resting-state functional and structural data while comparing a late-life depression group with a healthy control group. Biomarker detection helps determine a target for treatment intervention to get the optimal therapeutic benefit for treatment-resistant patients. The borrowing strength of the structural connectivity has been quantified for functional activity while detecting the biomarker. In ...[more]

PMID: 37554638

Similar Datasets

Project description:Recent advancements of multimodal neuroimaging such as functional MRI (fMRI) and diffusion MRI (dMRI) offers unprecedented opportunities to understand brain development. Most existing neurodevelopmental studies focus on using a single imaging modality to study microstructure or neural activations in localized brain regions. The developmental changes of brain network architecture in childhood and adolescence are not well understood. Our study made use of dMRI and resting-state fMRI imaging data sets from Philadelphia Neurodevelopmental Cohort (PNC) study to characterize developmental changes in both structural as well as functional brain connectomes. A multimodal multilevel model (MMM) is developed and implemented in PNC study to investigate brain maturation in both white matter structural connection and intrinsic functional connection. MMM addresses several major challenges in multimodal connectivity analysis. First, by using a first-level data generative model for observed measures and a second-level latent network modeling, MMM effectively infers underlying connection states from noisy imaging-based connectivity measurements. Secondly, MMM models the interplay between the structural and functional connections to capture the relationship between different brain connectomes. Thirdly, MMM incorporates covariate effects in the network modeling to investigate network heterogeneity across subpopoulations. Finally, by using a module-wise parameterization based on brain network topology, MMM is scalable to whole-brain connectomics. MMM analysis of the PNC study generates new insights in neurodevelopment during adolescence including revealing the majority of the white fiber connectivity growth are related to the cognitive networks where the most significant increase is found between the default mode and the executive control network with a 15% increase in the probability of structural connections. We also uncover functional connectome development mainly derived from global functional integration rather than direct anatomical connections. To the best of our knowledge, these findings have not been reported in the literature using multimodal connectomics. Supplementary materials for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.

Project description:BackgroundThe cognitive deficits of schizophrenia are largely resistant to current treatments and thus are a lifelong illness burden. The Measurement and Treatment Research to Improve Cognition in Schizophrenia (MATRICS) Consensus Cognitive Battery (MCCB) provides a reliable and valid assessment of cognition across major cognitive domains; however, the multimodal brain alterations specifically associated with MCCB in schizophrenia have not been examined.MethodsThe interrelationships between MCCB and the abnormalities seen in three types of neuroimaging-derived maps-fractional amplitude of low-frequency fluctuations (fALFF) from resting-state functional magnetic resonance imaging (MRI), gray matter (GM) density from structural MRI, and fractional anisotropy from diffusion MRI-were investigated by using multiset canonical correlation analysis in data from 47 schizophrenia patients treated with antipsychotic medications and 50 age-matched healthy control subjects.ResultsOne multimodal component (canonical variant 8) was identified as both group differentiating and significantly correlated with the MCCB composite. It demonstrated 1) increased cognitive performance associated with higher fALFF (intensity of regional spontaneous brain activity) and higher GM volumes in thalamus, striatum, hippocampus, and the mid-occipital region, with co-occurring fractional anisotropy changes in superior longitudinal fascicules, anterior thalamic radiation, and forceps major; 2) higher fALFF but lower GM volume in dorsolateral prefrontal cortex related to worse cognition in schizophrenia; and 3) distinct domains of MCCB might exhibit dissociable multimodal signatures, e.g., increased fALFF in inferior parietal lobule particularly correlated with decreased social cognition. Medication dose did not relate to these findings in schizophrenia.ConclusionsOur results suggest linked functional and structural deficits in distributed cortico-striato-thalamic circuits may be closely related to MCCB-measured cognitive impairments in schizophrenia.

Project description:BackgroundWhite matter hyperintensities (WMH) are frequently found in Alzheimer's disease (AD). Commonly considered as a marker of cerebrovascular disease, regional WMH may be related to pathological hallmarks of AD, including beta-amyloid (Aβ) plaques and neurodegeneration. The aim of this study was to examine the regional distribution of WMH associated with Aβ burden, glucose hypometabolism, and gray matter volume reduction.MethodsIn a total of 155 participants (IMAP+ cohort) across the cognitive continuum from normal cognition to AD dementia, FLAIR MRI, AV45-PET, FDG-PET, and T1 MRI were acquired. WMH were automatically segmented from FLAIR images. Mean levels of neocortical Aβ deposition (AV45-PET), temporo-parietal glucose metabolism (FDG-PET), and medial-temporal gray matter volume (GMV) were extracted from processed images using established AD meta-signature templates. Associations between AD brain biomarkers and WMH, as assessed in region-of-interest and voxel-wise, were examined, adjusting for age, sex, education, and systolic blood pressure.ResultsThere were no significant associations between global Aβ burden and region-specific WMH. Voxel-wise WMH in the splenium of the corpus callosum correlated with greater Aβ deposition at a more liberal threshold. Region- and voxel-based WMH in the posterior corpus callosum, along with parietal, occipital, and frontal areas, were associated with lower temporo-parietal glucose metabolism. Similarly, lower medial-temporal GMV correlated with WMH in the posterior corpus callosum in addition to parietal, occipital, and fontal areas.ConclusionsThis study demonstrates that local white matter damage is correlated with multimodal brain biomarkers of AD. Our results highlight modality-specific topographic patterns of WMH, which converged in the posterior white matter. Overall, these cross-sectional findings corroborate associations of regional WMH with AD-typical Aß deposition and neurodegeneration.

Project description:In this work we aimed to identify neural predictors of the efficacy of multimodal rehabilitative interventions in AD-continuum patients in the attempt to identify ideal candidates to improve the treatment outcome. Subjects in the AD continuum who participated in a multimodal rehabilitative treatment were included in the analysis [n = 82, 38 Males, mean age = 76 ± 5.30, mean education years = 9.09 ± 3.81, Mini Mental State Examination (MMSE) mean score = 23.31 ± 3.81]. All subjects underwent an MRI acquisition (1.5T) at baseline (T0) and a neuropsychological evaluation before (T0) and after intervention (T1). All subjects underwent an intensive multimodal cognitive rehabilitation (8-10 weeks). The MMSE and Neuropsychiatric Inventory (NPI) scores were considered as the main cognitive and behavioral outcome measures, and Delta change scores (T1-T0) were categorized in Improved (ΔMMSE > 0; ΔNPI < 0) and Not Improved (ΔMMSE ≤ 0; ΔNPI ≥ 0). Logistic Regression (LR) and Random Forest classification models were performed including neural markers (Medial Temporal Brain; Posterior Brain (PB); Frontal Brain (FB), Subcortical Brain indexes), neuropsychological (MMSE, NPI, verbal fluencies), and demographical variables (sex, age, education) at baseline. More than 50% of patients showed a positive effect of the treatment (ΔMMSE > 0: 51%, ΔNPI < 0: 52%). LR model on ΔMMSE (Improved vs. Not Improved) indicate a predictive role for MMSE score (p = 0.003) and PB index (p = 0.005), especially the right PB (p = 0.002) at baseline. The Random Forest analysis correctly classified 77% of cognitively improved and not improved AD patients. Concerning the NPI, LR model on ΔNPI (Improved vs. Not Improved) showed a predictive role of sex (p = 0.002), NPI (p = 0.005), PB index (p = 0.006), and FB index (p = 0.039) at baseline. The Random Forest reported a classification accuracy of 86%. Our data indicate that cognitive and behavioral status alone are not sufficient to identify best responders to a multidomain rehabilitation treatment. Increased neural reserve, especially in the parietal areas, is also relevant for the compensatory mechanisms activated by rehabilitative treatment. These data are relevant to support clinical decision by identifying target patients with high probability of success after rehabilitative programs on cognitive and behavioral functioning.

Dataset Information

Development of a Bayesian multimodal model to detect biomarkers in neuroimaging studies.

Publications

Development of a Bayesian multimodal model to detect biomarkers in neuroimaging studies.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets