Advances in Studying Brain Morphology: The Benefits of Open-Access Data

Madan, Christopher R.

doi:10.3389/fnhum.2017.00405

Cited by 36 publications

(34 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The external gray matter model that was trained on an independent sample showed less accurate prediction of brain age in our data compared to the k-folding based gray matter model. While both datasets were corrected for factors including scanner site, motion, and ICV, such discrepancies indicate that confounding factors including recruitment procedures, scanner equipment and data-processing pipelines may influence prediction accuracy across datasets [56].…”

Section: Discussionmentioning

confidence: 99%

Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study

Lange

Anatürk

Kaufmann

et al. 2020

Preprint

View full text Add to dashboard Cite

Brain age is becoming a widely applied imaging-based biomarker of neural aging and potential proxy for brain integrity and health. We estimated multimodal and modality-specific brain age in the Whitehall II MRI cohort using machine learning and imaging-derived measures of gray matter morphology, diffusion-based white matter microstructure, and resting state functional connectivity. Ten-fold cross validation yielded multimodal and modality-specific brain age estimates for each participant, and additional predictions based on a separate training sample was included for comparison. The results showed equivalent age prediction accuracy between the multimodal model and the gray and white matter models (R 2 of 0.34, 0.31, and 0.31, respectively), while the functional connectivity model showed a lower prediction accuracy (R 2 of 0.01). Cardiovascular risk factors, including high blood pressure, alcohol intake, and stroke risk score, were each associated with more apparent brain aging, with consistent associations across modalities.

show abstract

Section: Discussionmentioning

confidence: 99%

Multimodal brain-age prediction and cardiovascular risk: The Whitehall II MRI sub-study

Lange

Anatürk

Kaufmann

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…To construct this age-prediction model, we used several open-access MRI datasets. The public sharing of MRI data has been quickly growing and a large number of open-access datasets are now available (Biswal et al, 2010;Das et al, 2017;Madan, 2017;Mennes et al, 2013;Poldrack & Gorgolewski, 2014;Poldrack et al, 2017;Shenkin et al, 2017). The use of open-access datasets enabled us to have the large sample sizes needed to have training datasets as well as held-out datasets, as well as demonstrate the generalizability and reproducibility of the presented results, though this was not possible only a few years ago (Dickie et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Predicting age from cortical structure across the lifespan

Madan

Kensinger

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Predicting age from cortical morphology 2 Graphical AbstractSeveral measures of cortical structure differ in relation to age. We examined the cortical granularity of these differences across seven parcellation approaches, from a 1 region (unparcellated cortical ribbon) to 1000 regions (patches with boundaries informed by anatomical landmarks), and three measures: thickness, gyrification, and fractal dimensionality. Rather than merely examining age-related relationships, we examined how these parcellations and measures can be used to predict age.. CC-BY 4.0 International license peer-reviewed) is the author/funder. It is made available under aThe copyright holder for this preprint (which was not . http://dx.doi.org/10.1101/248518 doi: bioRxiv preprint first posted online Jan. 16, 2018; Predicting age from cortical morphology 3 AbstractDespite inter-individual differences in cortical structure, cross-sectional and longitudinal studies have demonstrated a large degree of population-level consistency in age-related differences in brain morphology. The present study assessed how accurately an individual's age could be predicted by estimates of cortical morphology, comparing a variety of structural measures, including thickness, gyrification, and fractal dimensionality. Structural measures were calculated across up to seven different parcellation approaches, ranging from 1 region to 1000 regions. The age-prediction framework was trained using morphological measures obtained from T1-weighted MRI volumes collected from multiple sites, yielding a training dataset of 1056 healthy adults, aged 18-97. Age predictions were calculated using a machine-learning approach that incorporated non-linear differences over the lifespan. In two independent, held-out test samples, age predictions had a median error of 6-7 years. Age predictions were best when using a combination of cortical metrics, both thickness and fractal dimensionality. Overall, the results reveal that age-related differences in brain structure are systematic enough to enable reliable age prediction based on metrics of cortical morphology.

show abstract

“…Bauer et al (2013)) and dementia (e.g., B. C. Dickerson et al (2011)). It is therefore essential to accurately and scientifically characterise such changes by using an array of morphologic measurements, for a better understanding of the natural progression of ageing and disease (Mills et al (2016);Madan (2017)). While many existing brain image analysis tools (e.g., FreeSurfer (Fischl et al (2004); Desikan et al (2006)), BrainSuite (Shattuck and Leahy (2002)), and BrainVISA (Kochunov et al (2012))) automatically compute such data from a 3-dimensional (3D) brain image, they lack the ability to do so for the equivalent manually-traced regions of interest (ROIs).…”

Section: Discussionmentioning

confidence: 99%