Biology subjects

Borgwardt, S.

Publications and source records attributed to Borgwardt, S..

22 records · Page 2Linked to original sources

bioRxiv2019

Caffeine-dependent changes of sleep-wake regulation: evidence for adaptation after repeated intake

To enhance wakefulness, daily consumption of caffeine in the morning and afternoon is highly common. However, it is unknown whether such a regular intake pattern affects timing and quality of wakefulness, as regulated by an interplay of circadian and sleep-homeostatic mechanisms. Thus, we investigated the effects of daily caffeine intake and its withdrawal on circadian rhythms and wake-promotion in 20 male young habitual caffeine consumers. We applied a double-blind, within-subject design with a caffeine (150 mg, 3 x daily), a placebo, and a withdrawal condition each lasting ten days. Starting on day nine of treatment, salivary melatonin and cortisol, evening nap sleep, as well as sleepiness and vigilance performance throughout day and night were quantified during 43 h under controlled laboratory conditions. Neither the time course of melatonin (i.e., onset, amplitude, or area under the curve) nor the time course of cortisol were significantly affected by caffeine intake or its withdrawal. During withdrawal, however, volunteers reported increased sleepiness, showed more attentional lapses, as well as polysomnography-derived markers of elevated sleep propensity in the late evening compared to both, placebo and caffeine conditions. Thus, the typical timing of habitual caffeine intake in humans may not necessarily shift circadian phase nor lead to clear-cut benefits in alertness. The time-of-day independent effects of caffeine withdrawal suggest an adaptation to the substance, presumably in the homeostatic aspect of sleep-wake regulation.

neuroscience↗

bioRxiv2018

Deep Learning for Quality Control of Subcortical Brain 3D Shape Models

We present several deep learning models for assessing the morphometric fidelity of deep grey matter region models extracted from brain MRI. We test three different convolutional neural net architectures (VGGNet, ResNet and Inception) over 2D maps of geometric features. Further, we present a novel geometry feature augmentation technique based on parametric spherical mapping. Finally, we present an approach for model decision visualization, allowing human raters to see the areas of subcortical shapes most likely to be deemed of failing quality by the machine. Our training data is comprised of 5200 subjects from the ENIGMA Schizophrenia MRI cohorts, and our test dataset contains 1500 subjects from the ENIGMA Major Depressive Disorder cohorts. Our final models reduce human rater time by 46-70%. ResNet outperforms VGGNet and Inception for all of our predictive tasks.

neuroscience↗

bioRxiv2018

Genetics of brain age suggest an overlap with common brain disorders

Numerous genetic and environmental factors contribute to psychiatric disorders and other brain disorders. Common risk factors likely converge on biological pathways regulating the optimization of brain structure and function across the lifespan. Here, using structural magnetic resonance imaging and machine learning, we estimated the gap between brain age and chronological age in 36,891 individuals aged 3 to 96 years, including individuals with different brain disorders. We show that several disorders are associated with accentuated brain aging, with strongest effects in schizophrenia, multiple sclerosis and dementia, and document differential regional patterns of brain age gaps between disorders. In 16,269 healthy adult individuals, we show that brain age gap is heritable with a polygenic architecture overlapping those observed in common brain disorders. Our results identify brain age gap as a genetically modulated trait that offers a window into shared and distinct mechanisms in different brain disorders.

neuroscience↗

bioRxiv2017

Machine Learning for Large-Scale Quality Control of 3D Shape Models in Neuroimaging

As very large studies of complex neuroimaging phenotypes become more common, human quality assessment of MRI-derived data remains one of the last major bottlenecks. Few attempts have so far been made to address this issue with machine learning. In this work, we optimize predictive models of quality for meshes representing deep brain structure shapes. We use standard vertex-wise and global shape features computed homologously across 19 cohorts and over 7500 human-rated subjects, training kernelized Support Vector Machine and Gradient Boosted Decision Trees classifiers to detect meshes of failing quality. Our models generalize across datasets and diseases, reducing human workload by 30-70%, or equivalently hundreds of human rater hours for datasets of comparable size, with recall rates approaching inter-rater reliability.

neuroscience↗