scholarly journals Musical skills can be decoded from magnetic resonance images

2020 ◽  
Author(s):  
Tuomas Puoliväli ◽  
Tuomo Sipola ◽  
Anja Thiede ◽  
Marina Kliuchko ◽  
Brigitte Bogert ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Brain Structure ◽  
Structural Changes ◽  
Musical Instrument ◽  
Structural Features ◽  
Brain Regions ◽  
Magnetic Resonance Images ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
The Brain

AbstractLearning induces structural changes in the brain. Especially repeated, long-term behaviors, such as extensive training of playing a musical instrument, are likely to produce characteristic features to brain structure. However, it is not clear to what extent such structural features can be extracted from magnetic resonance images of the brain. Here we show that it is possible to predict whether a person is a musician or a non-musician based on the thickness of the cerebral cortex measured at 148 brain regions encompassing the whole cortex. Using a supervised machine learning technique called support vector machines, we achieved significant (κ = 0.321, p < 0.001) agreement between the actual and predicted participant groups of 30 musicians and 85 non-musicians. The areas contributing to the prediction were mostly in the frontal, parietal, and occipital lobes of the left hemisphere. Our results suggest that decoding an acquired skill from magnetic resonance images of brain structure is feasible to some extent. Further, the distribution of the areas that were informative in the classification, which mostly, but not entirely overlapped with earlier findings, implies that decoding-based analyses of structural properties of the brain can reveal novel aspects of musical aptitude.

scholarly journals The Proliferation of Dentate Gyrus Progenitors in the Ferret Hippocampus by Neonatal Exposure to Valproic Acid

2021 ◽  
Vol 15 ◽  
Author(s):  
Kazuhiko Sawada ◽  
Shiori Kamiya ◽  
Ichio Aoki
Keyword(s):  
Valproic Acid ◽  
Cerebral Cortex ◽  
Magnetic Resonance ◽  
Dentate Gyrus ◽  
Structural Changes ◽  
S100 Protein ◽  
Brain Regions ◽  
Autism Spectrum ◽  
Magnetic Resonance Images ◽  
Neonatal Exposure

Prenatal and neonatal exposure to valproic acid (VPA) is associated with human autism spectrum disorder (ASD) and can alter the development of several brain regions, such as the cerebral cortex, cerebellum, and amygdala. Neonatal VPA exposure induces ASD-like behavioral abnormalities in a gyrencephalic mammal, ferret, but it has not been evaluated in brain regions other than the cerebral cortex in this animal. This study aimed to facilitate a comprehensive understanding of brain abnormalities induced by developmental VPA exposure in ferrets. We examined gross structural changes in the hippocampus and tracked proliferative cells by 5-bromo-2-deoxyuridine (BrdU) labeling following VPA administration to ferret infants on postnatal days (PDs) 6 and 7 at 200 μg/g of body weight. Ex vivo short repetition time/time to echo magnetic resonance imaging (MRI) with high spatial resolution at 7-T was obtained from the fixed brain of PD 20 ferrets. The hippocampal volume estimated using MRI-based volumetry was not significantly different between the two groups of ferrets, and optical comparisons on coronal magnetic resonance images revealed no differences in gross structures of the hippocampus between VPA-treated and control ferrets. BrdU-labeled cells were observed throughout the hippocampus of both two groups at PD 20. BrdU-labeled cells were immunopositive for Sox2 (&gt;70%) and almost immunonegative for NeuN, S100 protein, and glial fibrillary acidic protein. BrdU-labeled Sox2-positive progenitors were abundant, particularly in the subgranular layer of the dentate gyrus (DG), and were denser in VPA-treated ferrets. When BrdU-labeled Sox2-positive progenitors were examined at 2 h after the second VPA administration on PD 7, their density in the granular/subgranular layer and hilus of the DG was significantly greater in VPA-treated ferrets compared to controls. The findings suggest that VPA exposure to ferret infants facilitates the proliferation of DG progenitors, supplying excessive progenitors for hippocampal adult neurogenesis to the subgranular layer.

scholarly journals Comparison of machine learning approaches for enhancing Alzheimer’s disease classification

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e10549
Author(s):  
Qi Li ◽  
Mary Qu Yang
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Structural Changes ◽  
Spatial Information ◽  
Neurodegenerative Disorder ◽  
Brain Regions ◽  
Disease Classification ◽  
Support Vector ◽  
The Brain

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder, accounting for nearly 60% of all dementia cases. The occurrence of the disease has been increasing rapidly in recent years. Presently about 46.8 million individuals suffer from AD worldwide. The current absence of effective treatment to reverse or stop AD progression highlights the importance of disease prevention and early diagnosis. Brain structural Magnetic Resonance Imaging (MRI) has been widely used for AD detection as it can display morphometric differences and cerebral structural changes. In this study, we built three machine learning-based MRI data classifiers to predict AD and infer the brain regions that contribute to disease development and progression. We then systematically compared the three distinct classifiers, which were constructed based on Support Vector Machine (SVM), 3D Very Deep Convolutional Network (VGGNet) and 3D Deep Residual Network (ResNet), respectively. To improve the performance of the deep learning classifiers, we applied a transfer learning strategy. The weights of a pre-trained model were transferred and adopted as the initial weights of our models. Transferring the learned features significantly reduced training time and increased network efficiency. The classification accuracy for AD subjects from elderly control subjects was 90%, 95%, and 95% for the SVM, VGGNet and ResNet classifiers, respectively. Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to show discriminative regions that contributed most to the AD classification by utilizing the learned spatial information of the 3D-VGGNet and 3D-ResNet models. The resulted maps consistently highlighted several disease-associated brain regions, particularly the cerebellum which is a relatively neglected brain region in the present AD study. Overall, our comparisons suggested that the ResNet model provided the best classification performance as well as more accurate localization of disease-associated regions in the brain compared to the other two approaches.

scholarly journals Morphometric and Functional Brain Connectivity Differentiates Chess Masters from Amateur Players

2020 ◽  
Author(s):  
Harish RaviPrakash ◽  
Syed Muhammad Anwar ◽  
Nadia M. Biassou ◽  
Ulas Bagci
Keyword(s):  
Magnetic Resonance ◽  
Functional Connectivity ◽  
Spatial Reasoning ◽  
Medical Condition ◽  
Brain Connectivity ◽  
Magnetic Resonance Images ◽  
Support Vector ◽  
Connectivity Matrix ◽  
Chess Players ◽  
The Brain

ABSTRACTA common task in brain image analysis includes diagnosis of a certain medical condition wherein groups of healthy controls and diseased subjects are analyzed and compared. On the other hand, for two groups of healthy participants with different proficiency in a certain skill, a distinctive analysis of the brain function remains a challenging problem. In this study, we develop new computational tools to explore the functional and anatomical differences that could exist between the brain of healthy individuals identified on the basis of different levels of task experience/proficiency. Towards this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information. In addition, we utilize T1-weighted magnetic resonance imaging to estimate morphometric connectivity (MC) information. We combine functional and anatomical features into a new connectivity matrix, which we term as the functional morphometric similarity connectome (FMSC). Since, both the FC and MC information is susceptible to redundancy, the size of this information is reduced using statistical feature selection. We employ off-the-shelf machine learning classifier, support vector machine, for both single- and multi-modality classifications. From our experiments, we establish that the saliency and ventral attention network of the brain is functionally and anatomically different between two groups of healthy subjects (chess players). We argue that, since chess involves many aspects of higher order cognition such as systematic thinking and spatial reasoning and the identified network is task-positive to cognition tasks requiring a response, our results are valid and supporting the feasibility of the proposed computational pipeline. Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via our novel FMSC algorithm.

scholarly journals Morphometric and Functional Brain Connectivity Differentiates Chess Masters From Amateur Players

2021 ◽  
Vol 15 ◽  
Author(s):  
Harish RaviPrakash ◽  
Syed Muhammad Anwar ◽  
Nadia M. Biassou ◽  
Ulas Bagci
Keyword(s):  
Magnetic Resonance ◽  
Functional Connectivity ◽  
Spatial Reasoning ◽  
Medical Condition ◽  
Brain Connectivity ◽  
Magnetic Resonance Images ◽  
Support Vector ◽  
Connectivity Matrix ◽  
Chess Players ◽  
The Brain

A common task in brain image analysis includes diagnosis of a certain medical condition wherein groups of healthy controls and diseased subjects are analyzed and compared. On the other hand, for two groups of healthy participants with different proficiency in a certain skill, a distinctive analysis of the brain function remains a challenging problem. In this study, we develop new computational tools to explore the functional and anatomical differences that could exist between the brain of healthy individuals identified on the basis of different levels of task experience/proficiency. Toward this end, we look at a dataset of amateur and professional chess players, where we utilize resting-state functional magnetic resonance images to generate functional connectivity (FC) information. In addition, we utilize T1-weighted magnetic resonance imaging to estimate morphometric connectivity (MC) information. We combine functional and anatomical features into a new connectivity matrix, which we term as the functional morphometric similarity connectome (FMSC). Since, both the FC and MC information is susceptible to redundancy, the size of this information is reduced using statistical feature selection. We employ off-the-shelf machine learning classifier, support vector machine, for both single- and multi-modality classifications. From our experiments, we establish that the saliency and ventral attention network of the brain is functionally and anatomically different between two groups of healthy subjects (chess players). We argue that, since chess involves many aspects of higher order cognition such as systematic thinking and spatial reasoning and the identified network is task-positive to cognition tasks requiring a response, our results are valid and supporting the feasibility of the proposed computational pipeline. Moreover, we quantitatively validate an existing neuroscience hypothesis that learning a certain skill could cause a change in the brain (functional connectivity and anatomy) and this can be tested via our novel FMSC algorithm.

Structural Changes in the Brain in Depression and Relationship to Symptom Recurrence

CNS Spectrums ◽  
2002 ◽  
Vol 7 (2) ◽  
pp. 129-139 ◽  
Author(s):  
J. Douglas Bremner
Keyword(s):  
Frontal Cortex ◽  
Brain Structure ◽  
Structural Changes ◽  
Late Onset ◽  
Public Health Problem ◽  
White Matter Lesions ◽  
Brain Regions ◽  
Important Public Health Problem ◽  
Symptoms Of Depression ◽  
The Brain

ABSTRACTDepression is an important public health problem affecting about 15% of the general population; however, little is known about possible changes in the brain that might underlie the disorder. Neuroimaging has been a powerful tool to map actual changes in the brain structure of depressed patients that might be directly related to their symptoms of depression. Some imaging studies of brain structure have shown smaller hippocampal volume with the chronicity of depression correlating to a reduction in volume. Although the meaning of these findings is unclear, other studies have shown increased amygdala volume. Studies have found reductions in volume of the frontal cortex, with some studies showing specific reductions in subregions of the frontal cortex, including the orbitofrontal cortex. Findings of an increase in white matter lesions in elderly patients with depression have been replicated and correlated with late-onset depression, as well as impairments in social and cognitive function. These findings point to alterations in a circuit of brain regions hypothesized to include the frontal cortex, hippocampus, amygdala, striatum, and thalamus, that underlie symptoms of depression.

Semiautomatic brain region extraction: a method of parcellating brain regions from structural magnetic resonance images

NeuroImage ◽  
2004 ◽  
Vol 22 (4) ◽  
pp. 1492-1502 ◽  
Author(s):  
L.A Dade ◽  
F.Q Gao ◽  
N Kovacevic ◽  
P Roy ◽  
C Rockel ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
Brain Region ◽  
Brain Regions ◽  
Magnetic Resonance Images ◽  
Region Extraction

scholarly journals Applying 3DPCANet and Functional Magnetic Resonance Imaging to Aided Diagnosis of Alzheimer’s Disease

2021 ◽  
Author(s):  
Yu Wang ◽  
Hongfei Jia ◽  
Yifan Duan ◽  
Hongbing Xiao
Keyword(s):  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Magnetic Resonance ◽  
Functional Magnetic Resonance Imaging ◽  
Brain Regions ◽  
Support Vector ◽  
Functional Magnetic Resonance ◽  
Resonance Imaging ◽  
Public Data

Abstract Alzheimer's disease (AD) is a progressive neurodegenerative disease, which changes the structure of brain regions by some hidden causes. In this paper for assisting doctors to make correct judgments, an improved 3DPCANet method is proposed to classify AD by combining the mean (mALFF) of the whole brain. The main idea includes that firstly, the functional magnetic resonance imaging (fMRI) data is pre-processed, and mALFF is calculated to get the corresponding matrix. Then the features of mALFF images are extracted via the improved 3DPCANet network. Finally, AD patients with different stages are classified using support vector machine (SVM). Experiments results based on public data from the Alzheimer’s disease neuroimaging initiative (ADNI) show that the proposed approach has better performance compared with state-of-the-art methods. The accuracies of AD vs. significant memory concern (SMC), SMC vs. late mild cognitive impairment (LMCI), and normal control (NC) vs. SMC reach respectively 92.42%, 91.80%, and 89.50%, which testifies the feasibility and effectiveness of the proposed method.

scholarly journals Experience, but not age, is associated with volumetric mushroom body expansion in solitary alkali bees

2021 ◽  
pp. jeb.238899
Author(s):  
Mallory A. Hagadorn ◽  
Makenna M. Johnson ◽  
Adam R. Smith ◽  
Marc A. Seid ◽  
Karen M. Kapheim
Keyword(s):  
Structural Changes ◽  
Evolutionary Relationship ◽  
Brain Regions ◽  
Mushroom Bodies ◽  
Order Processing ◽  
Social Species ◽  
Evolution Of Sociality ◽  
Foraging Experience ◽  
Brain Changes ◽  
The Brain

In social insects, changes in behavior are often accompanied by structural changes in the brain. This neuroplasticity may come with experience (experience-dependent) or age (experience-expectant). Yet, the evolutionary relationship between neuroplasticity and sociality is unclear, because we know little about neuroplasticity in the solitary relatives of social species. We used confocal microscopy to measure brain changes in response to age and experience in a solitary halictid bee (Nomia melanderi). First, we compared the volume of individual brain regions among newly-emerged females, laboratory females deprived of reproductive and foraging experience, and free-flying, nesting females. Experience, but not age, led to significant expansion of the mushroom bodies—higher-order processing centers associated with learning and memory. Next, we investigated how social experience influences neuroplasticity by comparing the brains of females kept in the laboratory either alone or paired with another female. Paired females had significantly larger olfactory regions of the mushroom bodies. Together, these experimental results indicate that experience-dependent neuroplasticity is common to both solitary and social taxa, whereas experience-expectant neuroplasticity may be an adaptation to life in a social colony. Further, neuroplasticity in response to social chemical signals may have facilitated the evolution of sociality.

Sign in / Sign up

Export Citation Format

Share Document