NeuroImage
-
Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. ⋯ In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0.56/0.65/0.46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD.
-
In this work a method is described to discern the perfusion territories in the cerebellum that are exclusively supplied by either or both vertebral arteries. In normal vascular anatomy the posterior inferior cerebellar artery (PICA) is supplied exclusively by its ipsilateral vertebral artery. The perfusion territories of the vertebral arteries were determined in 14 healthy subjects by means of a super-selective pseudo-continuous ASL sequence on a 3T MRI scanner. ⋯ The inferior part of the vermis is supplied by the PICA in all subjects. Two subjects were found with interhemispheric blood flow to both tonsils from one PICA without contribution from the contralateral PICA. With the method as presented, clinicians may in the future accurately classify cerebellar infarcts according to affected perfusion territories, which might be helpful in the decision whether a stenosis should be considered symptomatic.
-
Several large imaging-genetics consortia aim to identify genetic variants influencing subcortical brain volumes. We investigated the extent to which genetic variation accounts for the variation in subcortical volumes, including thalamus, amygdala, putamen, caudate nucleus, globus pallidus and nucleus accumbens and obtained the stability of these brain volumes over a five-year period. ⋯ Five-year stability was substantial and higher for larger [e.g., thalamus (.88), putamen (.86), caudate nucleus (.87)] compared to smaller [nucleus accumbens (.45)] subcortical structures. These results provide additional evidence that subcortical structures are promising starting points for identifying genetic variants that influence brain structure.
-
Randomized Controlled Trial
Magnetoencephalographic evidence for the modulation of cortical swallowing processing by transcranial direct current stimulation.
Swallowing is a complex neuromuscular task that is processed within multiple regions of the human brain. Rehabilitative treatment options for dysphagia due to neurological diseases are limited. Because the potential for adaptive cortical changes in compensation of disturbed swallowing is recognized, neuromodulation techniques like transcranial direct current stimulation (tDCS) are currently considered as a treatment option. ⋯ No relevant behavioral effects were observed on swallow response time, but swallow precision improved after left tDCS (p<0.05). Anodal tDCS applied over the swallowing motor cortex of either hemisphere was able to increase bilateral swallow-related cortical network activation in a frequency specific manner. These neuroplastic effects were associated with subtle behavioral gains during complex swallow tasks in healthy individuals suggesting that tDCS deserves further evaluation as a treatment tool for dysphagia.
-
In many neuroscience and clinical studies, accurate measurement of hippocampus is very important to reveal the inter-subject anatomical differences or the subtle intra-subject longitudinal changes due to aging or dementia. Although many automatic segmentation methods have been developed, their performances are still challenged by the poor image contrast of hippocampus in the MR images acquired especially from 1.5 or 3.0 Tesla (T) scanners. With the recent advance of imaging technology, 7.0 T scanner provides much higher image contrast and resolution for hippocampus study. ⋯ Then, under the multi-atlas segmentation framework, multiple sequences of ACM-based classifiers are trained for all atlases to incorporate the anatomical variability. In the application stage, for a new image, its hippocampus segmentation can be achieved by fusing the labeling results from all atlases, each of which is obtained by applying the atlas-specific ACM-based classifiers. Experimental results on twenty 7.0 T images with the voxel size of 0.35×0.35×0.35 mm3 show very promising hippocampus segmentations (in terms of Dice overlap ratio 89.1±0.020), indicating high applicability for the future clinical and neuroscience studies.