Machine-learning based exploration of determinants of gray matter volume in the KORA-MRI study.
Ontology highlight
ABSTRACT:
SUBMITTER: Galie F
PROVIDER: S-EPMC7239887 | biostudies-literature | 2020 May
REPOSITORIES: biostudies-literature
Publications
Machine-learning based exploration of determinants of gray matter volume in the KORA-MRI study.
Galiè Franziska F Rospleszcz Susanne S Keeser Daniel D Beller Ebba E Illigens Ben B Lorbeer Roberto R Grosu Sergio S Selder Sonja S Auweter Sigrid S Schlett Christopher L CL Rathmann Wolfgang W Schwettmann Lars L Ladwig Karl-Heinz KH Linseisen Jakob J Peters Annette A Bamberg Fabian F Ertl-Wagner Birgit B Stoecklein Sophia S
Scientific reports 20200520 1
To identify the most important factors that impact brain volume, while accounting for potential collinearity, we used a data-driven machine-learning approach. Gray Matter Volume (GMV) was derived from magnetic resonance imaging (3T, FLAIR) and adjusted for intracranial volume (ICV). 93 potential determinants of GMV from the categories sociodemographics, anthropometric measurements, cardio-metabolic variables, lifestyle factors, medication, sleep, and nutrition were obtained from 293 participants ...[more]
Similar Datasets
Project description:BACKGROUND:Childhood trauma is a significant risk factor for adult psychopathology. Previous investigations have implicated childhood trauma-related structural changes in anterior cingulate, dorsolateral prefrontal and orbitofrontal cortex, and hippocampus. Using a large transdiagnostic community sample, the goal of this investigation was to differentially associate regional gray matter (GM) volume with childhood trauma severity specifically, distinct from adult psychopathology. METHODS:A total of 577 non-treatment-seeking adults (n = 207 men) completed diagnostic, childhood trauma, and structural magnetic resonance imaging assessments with regional GM volume estimated using FreeSurfer. Elastic net analysis was conducted in a nested cross-validation framework, with GM volumes, adult psychopathology, age, education, sex, and magnetic resonance imaging coil type as potential predictors for childhood trauma severity. RESULTS:Elastic net identified age, education, sex, medical condition, adult psychopathology, and 13 GM regions as predictors of childhood trauma severity. GM regions identified included right caudate; left pallidum; bilateral insula and cingulate sulcus; left superior, inferior, and orbital frontal regions; and regions within temporal and parietal lobes and cerebellum. CONCLUSIONS:Results from this large, transdiagnostic sample implicate GM volume in regions central to current neurobiological theories of trauma (e.g., prefrontal cortex) as well as additional regions involved in reward, interoceptive, attentional, and sensory processing (e.g., striatal, insula, and parietal/occipital cortices). Future longitudinal studies examining the functional impact of structural changes in this broader network of regions are needed to clarify the role each may play in longer-term outcomes following trauma.
| S-EPMC6688962 | biostudies-literature
Project description:Imaging biomarkers derived from magnetic resonance imaging (MRI) data are used to quantify normal development, disease, and the effects of disease-modifying therapies. However, motion during image acquisition introduces image artifacts that, in turn, affect derived markers. A systematic effect can be problematic since factors of interest like age, disease, and treatment are often correlated with both a structural change and the amount of head motion in the scanner, confounding the ability to distinguish biology from artifact. Here we evaluate the effect of head motion during image acquisition on morphometric estimates of structures in the human brain using several popular image analysis software packages (FreeSurfer 5.3, VBM8 SPM, and FSL Siena 5.0.7). Within-session repeated T1-weighted MRIs were collected on 12 healthy volunteers while performing different motion tasks, including two still scans. We show that volume and thickness estimates of the cortical gray matter are biased by head motion with an average apparent volume loss of roughly 0.7%/mm/min of subject motion. Effects vary across regions and remain significant after excluding scans that fail a rigorous quality check. In view of these results, the interpretation of reported morphometric effects of movement disorders or other conditions with increased motion tendency may need to be revisited: effects may be overestimated when not controlling for head motion. Furthermore, drug studies with hypnotic, sedative, tranquilizing, or neuromuscular-blocking substances may contain spurious "effects" of reduced atrophy or brain growth simply because they affect motion distinct from true effects of the disease or therapeutic process.
| S-EPMC4300248 | biostudies-literature
Project description:The myelin content of the cortex changes over the human lifetime and aberrant cortical myelination is associated with diseases such as schizophrenia and multiple sclerosis. Recently magnetic resonance imaging (MRI) techniques have shown potential in differentiating between myeloarchitectonically distinct cortical regions in vivo. Here we introduce a new algorithm for correcting partial volume effects present in mm-scale MRI images which was used to investigate the myelination pattern of the cerebral cortex in 1555 clinically normal subjects using the ratio of T1-weighted (T1w) and T2-weighted (T2w) MRI images. A significant linear cross-sectional age increase in T1w/T2w estimated myelin was detected across an 18 to 35 year age span (highest value of ~ 1%/year compared to mean T1w/T2w myelin value at 18 years). The cortex was divided at mid-thickness and the value of T1w/T2w myelin calculated for the inner and outer layers separately. The increase in T1w/T2w estimated myelin occurs predominantly in the inner layer for most cortical regions. The ratio of the inner and outer layer T1w/T2w myelin was further validated using high-resolution in vivo MRI scans and also a high-resolution MRI scan of a postmortem brain. Additionally, the relationships between cortical thickness, curvature and T1w/T2w estimated myelin were found to be significant, although the relationships varied across the cortex. We discuss these observations as well as limitations of using the T1w/T2w ratio as an estimate of cortical myelin.
| S-EPMC4262571 | biostudies-literature
Project description:BackgroundDespite decades of research, there is continued uncertainty regarding whether autism is associated with a specific profile of gray matter (GM) structure. This inconsistency may stem from the widespread use of voxel-based morphometry (VBM) methods that combine indices of GM density and GM volume. If GM density or volume, but not both, prove different in autism, the traditional VBM approach of combining the two indices may obscure the difference. The present study measures GM density and volume separately to examine whether autism is associated with alterations in GM volume, density, or both.MethodsDifferences in MRI-based GM density and volume were examined in 6-25 year-olds with a diagnosis of autism spectrum disorder (n = 213, 80.8% male, IQ 47-154) and a typically developing (TD) sample (n = 190, 71.6% male, IQ 67-155). High-resolution T1-weighted anatomical images were collected on a single MRI scanner. Regional density and volume were estimated via whole-brain parcellation comprised of 1625 parcels. Parcel-wise analyses were conducted using generalized additive models while controlling the false discovery rate (FDR, q < 0.05). Volume differences in the 68-region Desikan-Killiany atlas derived from Freesurfer were also examined, to establish the generalizability of findings across methods.ResultsNo density differences were observed between the autistic and TD groups, either in individual parcels or whole brain mean density. Increased volume was observed in autism compared to the TD group when controlling for Age, Sex, and IQ, both at the level of the whole brain (total volume) and in 45 parcels (2.8% of total parcels). Parcels with greater volume included inferior, middle, and superior temporal gyrus, inferior and superior frontal gyrus, precuneus, and fusiform gyrus. Converging evidence from a standard Freesurfer pipeline also identified greater volume in a number of overlapping regions.LimitationsThe method for determining "density" is not a direct measure of neuronal density, and this study cannot reveal underlying cellular differences. While this study represents possibly the largest single-site sample of its kind, it is underpowered to detect very small differences.ConclusionsThese results provide compelling evidence that autism is associated with regional GM volumetric differences, which are more prominent than density differences. This underscores the importance of examining volume and density separately, and suggests that direct measures of volume (e.g. region-of-interest or tensor-based morphometry approaches) may be more sensitive to autism-relevant differences in neuroanatomy than concentration/density-based approaches.
| S-EPMC8633367 | biostudies-literature
Project description:Background:To evaluate the association of multiparametric and multiregional MRI-features with key molecular characteristics in patients with newly-diagnosed glioblastoma. Methods:Retrospective data evaluation was approved by the local ethics committee of the University of Heidelberg (ethics approval number: S-320/2012) and informed consent was waived. Preoperative MRI-features were correlated with key molecular characteristics within a single-institutional cohort of 152 patients with newly-diagnosed glioblastoma. Preoperative MRI-features (n=31) included multiparametric (anatomical, diffusion-, perfusion-, and susceptibility-weighted images) and multiregional (contrast enhancing and non-enhancing FLAIR-hyperintense) information with (histogram) quantification of tumor volumes, volume ratios, apparent diffusion coefficients, cerebral blood flow / volume (CBF / CBV) and intratumoral susceptibility signals. Molecular characteristics determined with the Illumina Infinium HumanMethylation450 array included global DNA-methylation subgroups (e.g. mesenchymal (MES), RTK I “PGFRA”, RTK II “classic”), MGMT-promoter methylation status and hallmark copy-number-variations (EGFR-, PDGFRA-, MDM4- and CDK4-amplification; PTEN-, CDKN2A-, NF1- and RB1-loss). Univariate analyses (voxel-lesion-symptom-mapping for tumor location, Wilcoxon-test for all other MRI-features) as well as machine-learning models were applied to study the strength of association and discriminative value of MRI-features for predicting underlying molecular characteristics. Results: There was no tumor location predilection for any of the assessed molecular parameters (permutation-adjusted p>0.05 each). Univariate imaging parameter associations were noted for EGFR amplification and CDKN2A loss, both demonstrating increased nrCBV and nrCBF values (performance of these parameters, as assessed by the area under the ROC curve ranged from 63 to 69%, FDR-adjusted p<0.05, respectively). Subjecting all MRI-features to machine-learning-based classification allowed to predict EGFR amplification status and the RTK II “classic” GB subgroup with a moderate, yet significantly greater accuracy (63% for EGFR [p<0.01] and 61% for RTK II [p=0.01]) than the prediction by chance, whereas prediction accuracy for all other molecular parameters was non-significant (p>0.05, all models). Conclusions: In summary, we found univariate associations between established MRI-features and molecular characteristics, however not of sufficient strength to allow the generation of machine-learning classification models for reliable and clinically meaningful prediction of the assessed molecular characteristics in patients with newly-diagnosed glioblastoma.
2016-11-23 | GSE85539 | GEO
Project description:Nicotine modulates prefrontal processing when tested with functional imaging. Previous studies on changes in regional brain volumes in small samples, reporting different life-time exposure to nicotine, identified reduced volume in smokers in prefrontal areas but reported controversial results for other areas. We investigated the association of cigarette smoking and regional gray and white matter volume by using voxel-based morphometry (VBM) for T1-weighted high-resolution magnetic resonance imaging in 315 current-smokers and 659 never-smokers from the representative Study of Health in Pomerania (SHIP). Our study showed that in current-smokers smoking is significantly associated with gray matter volume loss in the prefrontal cortex, the anterior cingulate cortex, the insula, and the olfactory gyrus. White matter volumes were not relevantly reduced in current-smokers. In current-smokers, we found associations of gray matter loss and smoking exposure (pack-years) in the prefrontal cortex, the anterior and middle cingulate cortex, and the superior temporal and angular gyrus, which however did not stand corrections for multiple testing. We confirmed associations between smoking and gray matter differences in the prefrontal cortex, the anterior cingulate cortex and the insula in the general population of Pomerania (Germany). For the first time, we identified differences in brain volumes in the olfactory gyrus. Other cerebral regions did not show significant differences when correcting for multiple comparisons within the whole brain. The regions of structural deficits might be involved in addictive behavior and withdrawal symptoms, whereas further investigations have to show if the observed atrophies were caused by smoking itself or are preexisting differences between smoking and non-smoking individuals.
| S-EPMC4207339 | biostudies-other
Project description:A positive association between brain size and intelligence is firmly established, but whether region-specific anatomical differences contribute to general intelligence remains an open question. Results from voxel-based morphometry (VBM) - one of the most widely used morphometric methods - have remained inconclusive so far. Here, we applied cross-validated machine learning-based predictive modeling to test whether out-of-sample prediction of individual intelligence scores is possible on the basis of voxel-wise gray matter volume. Features were derived from structural magnetic resonance imaging data (N = 308) using (a) a purely data-driven method (principal component analysis) and (b) a domain knowledge-based approach (atlas parcellation). When using relative gray matter (corrected for total brain size), only the atlas-based approach provided significant prediction, while absolute gray matter (uncorrected) allowed for above-chance prediction with both approaches. Importantly, in all significant predictions, the absolute error was relatively high, i.e., greater than ten IQ points, and in the atlas-based models, the predicted IQ scores varied closely around the sample mean. This renders the practical value even of statistically significant prediction results questionable. Analyses based on the gray matter of functional brain networks yielded significant predictions for the fronto-parietal network and the cerebellum. However, the mean absolute errors were not reduced in contrast to the global models, suggesting that general intelligence may be related more to global than region-specific differences in gray matter volume. More generally, our study highlights the importance of predictive statistical analysis approaches for clarifying the neurobiological bases of intelligence and provides important suggestions for future research using predictive modeling.
| S-EPMC7473979 | biostudies-literature
Project description:To identify the most important parameters associated with cerebral white matter hyperintensities (WMH), in consideration of potential collinearity, we used a data-driven machine-learning approach. We analysed two independent cohorts (KORA and SHIP). WMH volumes were derived from cMRI-images (FLAIR). 90 (KORA) and 34 (SHIP) potential determinants of WMH including measures of diabetes, blood-pressure, medication-intake, sociodemographics, life-style factors, somatic/depressive-symptoms and sleep were collected. Elastic net regression was used to identify relevant predictor covariates associated with WMH volume. The ten most frequently selected variables in KORA were subsequently examined for robustness in SHIP. The final KORA sample consisted of 370 participants (58% male; age 55.7 ± 9.1 years), the SHIP sample comprised 854 participants (38% male; age 53.9 ± 9.3 years). The most often selected and highly replicable parameters associated with WMH volume were in descending order age, hypertension, components of the social environment (i.e. widowed, living alone) and prediabetes. A systematic machine-learning based analysis of two independent, population-based cohorts showed, that besides age and hypertension, prediabetes and components of the social environment might play important roles in the development of WMH. Our results enable personal risk assessment for the development of WMH and inform prevention strategies tailored to the individual patient.
| S-EPMC7840689 | biostudies-literature
Project description:Accelerated gait decline in aging is associated with many adverse outcomes, including an increased risk for falls, cognitive decline, and dementia. Yet, the brain structures associated with gait speed, and how they relate to specific cognitive domains, are not well-understood. We examined structural brain correlates of gait speed, and how they relate to processing speed, executive function, and episodic memory in three non-demented and community-dwelling older adult cohorts (Overall N = 352), using voxel-based morphometry and multivariate covariance-based statistics. In all three cohorts, we identified gray matter volume covariance patterns associated with gait speed that included brain stem, precuneus, fusiform, motor, supplementary motor, and prefrontal (particularly ventrolateral prefrontal) cortex regions. Greater expression of these gray matter volume covariance patterns linked to gait speed were associated with better processing speed in all three cohorts, and with better executive function in one cohort. These gray matter covariance patterns linked to gait speed were not associated with episodic memory in any of the cohorts. These findings suggest that gait speed, processing speed (and to some extent executive functions) rely on shared neural systems that are subject to age-related and dementia-related change. The implications of these findings are discussed within the context of the development of interventions to compensate for age-related gait and cognitive decline.
| S-EPMC6177326 | biostudies-literature
Project description:ObjectiveChefs exert expert motor and cognitive performances on a daily basis. Neuroimaging has clearly shown that that long-term skill learning (i.e., athletes, musicians, chess player or sommeliers) induces plastic changes in the brain thus enabling tasks to be performed faster and more accurately. How a chef's expertise is embodied in a specific neural network has never been investigated.MethodsEleven Italian head chefs with long-term brigade management expertise and 11 demographically-/ psychologically- matched non-experts underwent morphological evaluations.ResultsVoxel-based analysis performed with SUIT, as well as, automated volumetric measurement assessed with Freesurfer, revealed increased gray matter volume in the cerebellum in chefs compared to non-experts. The most significant changes were detected in the anterior vermis and the posterior cerebellar lobule. The magnitude of the brigade staff and the higher performance in the Tower of London test correlated with these specific gray matter increases, respectively.ConclusionsWe found that chefs are characterized by an anatomical variability involving the cerebellum. This confirms the role of this region in the development of similar expert brains characterized by learning dexterous skills, such as pianists, rock climbers and basketball players. However, the nature of the cellular events underlying the detected morphological differences remains an open question.
| S-EPMC5300254 | biostudies-literature