Article
Computer Science, Artificial Intelligence
Lu Zhang, Li Wang, Dajiang Zhu
Summary: Understanding the relationship between brain structure and function is crucial for uncovering organizational principles of the human brain. This study proposes a method called MGCN-GAN, which combines generative adversarial networks and graph convolutional networks, to infer individual structural connectivity based on functional connectivity. Experimental results demonstrate that the model can generate reliable individual structural connectivity across different individuals.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Neurosciences
Vikram Shenoy Handiru, Alaleh Alivar, Armand Hoxha, Soha Saleh, Easter S. Suviseshamuthu, Guang Yue, Didier Allexandre
Summary: TBI patients exhibited poorer balance performance, reduced brain activation and connectivity during the task, as well as widespread structural damage. Different frequency bands played distinct roles in neural correlates, with theta-band modularity negatively correlating with balance scale and lower beta-band network connectivity associated with white matter integrity reduction.
HUMAN BRAIN MAPPING
(2021)
Article
Neurosciences
Xihe Xie, Chang Cai, Pablo F. Damasceno, Srikantan S. Nagarajan, Ashish Raj
Summary: This study investigates how functional brain networks emerge from the underlying wiring of the brain by introducing signal transmission delays in white matter fibers. The complex Laplacian matrix, dependent on coupling strength and oscillation frequency, can predict canonical functional networks without detailed neural activity modeling. Linear superposition of complex eigenmodes can predict specific functional networks and outperforms real-valued Laplacian in predicting functional networks.
Article
Computer Science, Information Systems
Lujing Wang, Weifeng Yuan, Lu Zeng, Jie Xu, Yujie Mo, Xinxiang Zhao, Liang Peng
Summary: This paper proposes a new graph neural network framework for brain disease diagnosis, achieving diagnosis effectiveness by learning global relationships and selecting the most discriminative brain regions. Experimental results demonstrate the effectiveness of this method.
INFORMATION PROCESSING & MANAGEMENT
(2022)
Article
Neurosciences
Yin Wang, Athanasia Metoki, Yunman Xia, Yinyin Zang, Yong He, Ingrid R. Olson
Summary: This study reveals the brain-wide organization and mechanisms of mentalizing processing, showing the detailed connectomic features of the mentalizing network. It demonstrates that mentalizing unfolds across functionally heterogeneous regions with highly structured fiber tracts and unique hierarchical functional architecture, distinguishing it from other brain networks supporting related functions such as autobiographical memory and moral reasoning.
Article
Multidisciplinary Sciences
Justin Reber, Kai Hwang, Mark Bowren, Joel Bruss, Pratik Mukherjee, Daniel Tranel, Aaron D. Boes
Summary: Lesions disrupting white matter regions with high edge density are more strongly associated with cognitive impairment compared to lesions damaging gray matter regions with high participation coefficient, which helps explain interindividual differences in cognitive outcomes following brain damage.
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2021)
Article
Multidisciplinary Sciences
Meng Cao, Ziyan Wu, Xiaobo Li
Summary: This study developed a MATLAB toolbox called GAT-FD for analyzing task-related brain functional connectivity, functional network topological properties, and their dynamics. It was tested and validated using functional magnetic resonance imaging data and demonstrated effective and quantitative evaluations of functional network properties and dynamics during task performance.
Article
Neurosciences
Sondos Ayyash, Andrew D. Davis, Gesine L. Alders, Glenda MacQueen, Stephen C. Strother, Stefanie Hassel, Mojdeh Zamyadi, Stephen R. Arnott, Jacqueline K. Harris, Raymond W. Lam, Roumen Milev, Daniel J. Mueller, Sidney H. Kennedy, Susan Rotzinger, Benicio N. Frey, Luciano Minuzzi, Geoffrey B. Hall
Summary: There is a growing interest in exploring the data fusion analysis of functional and structural imaging sources. A novel processing pipeline, FATCAT-awFC, was developed to identify connectivity changes in MDD patients compared to healthy individuals, revealing significant differences in specific brain networks. By combining structural and functional data, this method enhances our understanding of the intricate relationship between structural and functional connectivity in depression.
HUMAN BRAIN MAPPING
(2021)
Article
Computer Science, Artificial Intelligence
Ahmed Nebli, Mohammed Amine Gharsallaoui, Zeynep Gurler, Islem Rekik, Alzheimers Dis Neuroimaging Initiative
Summary: Graph neural networks (GNNs) have been widely used in various fields such as computer vision and computer-aided diagnosis, but the reproducibility of the discriminative features identified by GNNs is still a concern, especially in clinical applications. This study proposes a reproducibility-based GNN selection framework to quantify the reproducibility by evaluating the shared discriminative features among different models.
Article
Neurosciences
Yizhen Pan, Xuan Li, Yuling Liu, Xiaoyan Jia, Shan Wang, Qiuyu Ji, Wenpu Zhao, Bo Yin, Guanghui Bai, Jie Zhang, Lijun Bai
Summary: Mild traumatic brain injury (mTBI) disrupts the integrity of white matter microstructure, affecting brain functional connectivity supporting cognitive function. The current study investigated the alteration pattern of regional SC-FC coupling in acute and chronic mTBI patients and found that the sensorimotor network (SMN) exhibited altered coupling in acute mTBI, while chronic mTBI showed persistent decoupling of the SMN and additional decoupling of the default mode network (DMN). Crucially, the decoupling of the SMN and DMN predicted better cognitive outcomes.
Article
Neurosciences
Francesca Bottino, Martina Lucignani, Luca Pasquini, Michele Mastrogiovanni, Simone Gazzellini, Matteo Ritrovato, Daniela Longo, Lorenzo Figa-Talamanca, Maria Camilla Rossi Espagnet, Antonio Napolitano
Summary: This study investigated the spatial stability of functional connectivity variations induced by parcellation errors. Using subjects from three public online datasets, the study simulated random parcellation variability and evaluated its effects on twenty-seven graph-theoretical measures. The results showed that certain measures had higher spatial stability while others had lower spatial stability. Multivariate analysis demonstrated significant effects of atlas, datasets, and thresholds. Additionally, spatial stability was influenced by threshold, atlas choice, and scanning parameters. The study highlights the importance of paying attention to parcellation-related spatial errors that may affect the reliability of functional connectivity measures.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Neurosciences
Alja Kavcic, Jure Demsar, Dejan Georgiev, Nuska Pecaric Meglic, Aneta Soltirovska Salamon
Summary: Impaired cognitive functioning after perinatal stroke is linked to long-term changes in functional brain networks. We used a 64-channel electroencephalogram to study brain functional connectivity in 12 participants with a history of unilateral perinatal stroke. Results showed evidence of disrupted brain networks in these children, years after the stroke, with the extent of changes influenced by the lesion size. The networks remained more segregated and exhibited higher synchronization at both whole-brain and intrahemispheric levels, with greater interhemispheric connectivity compared to healthy controls.
Article
Neurosciences
Tao Yin, Zhaoxuan He, Peihong Ma, Ruirui Sun, Kunnan Xie, Tianyu Liu, Li Chen, Jingwen Chen, Likai Hou, Yuke Teng, Yuyi Guo, Zilei Tian, Jing Xiong, Fumin Wang, Shenghong Li, Sha Yang, Fang Zeng
Summary: This study identified abnormal brain dynamics in functional constipation patients, which were correlated with symptom severity. Graph-theoretic analysis showed higher sample entropy at nodal efficiency in the anterior insula of FCon patients.
HUMAN BRAIN MAPPING
(2021)
Article
Computer Science, Information Systems
Junzhong Ji, Yating Ren, Minglong Lei
Summary: This study proposes a hypergraph attention network (FC-HAT) for functional brain network classification, which dynamically generates hypergraphs and extracts high-order information using attention mechanisms. Experimental results demonstrate the effectiveness of FC-HAT in cerebral disease classification and the identification of biomarkers associated with cerebral diseases.
INFORMATION SCIENCES
(2022)
Article
Engineering, Biomedical
Xiaoyi Chen, Jing Zhou, Pengfei Ke, Jiayuan Huang, Dongsheng Xiong, Yuanyuan Huang, Guolin Ma, Yuping Ning, Fengchun Wu, Kai Wu
Summary: Recent studies have shown that brain connectivity abnormalities are associated with schizophrenia. However, most previous studies using machine learning methods focused on MRI features of brain regions, ignoring brain connectivity and its network topology. In this study, we used a graph convolutional network (GCN) to classify schizophrenia patients based on both brain region and connectivity features derived from combined functional MRI and connectomics analysis. The results showed that the proposed method significantly improved classification performance compared to traditional machine learning and deep learning methods based on MRI features alone.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Review
Neuroimaging
Inga K. Koerte, Roald Bahr, Peter Filipcik, Jolien Gooijers, Alexander Leemans, Alexander P. Lin, Yorghos Tripodis, Martha E. Shenton, Nir Sochen, Stephan P. Swinnen, Ofer Pasternak
Summary: The study focuses on the impacts of repetitive head impacts on the brain structure and function of youth athletes, as well as potential clinical or behavioral consequences. Through the REPIMPACT Consortium, a multinational research effort aims to comprehensively assess competitive soccer players exposed to repetitive head impacts by providing complex molecular-level data.
BRAIN IMAGING AND BEHAVIOR
(2022)
Article
Neurosciences
Valeria Elisa Contarino, Silvia Siggillino, Andrea Arighi, Elisa Scola, Giorgio Giulio Fumagalli, Giorgio Conte, Emanuela Rotondo, Daniela Galimberti, Anna Margherita Pietroboni, Tiziana Carandini, Alexander Leemans, Anna Maria Bianchi, Fabio Maria Triulzi
Summary: This study investigates the alterations in superficial white matter (SWM) in Alzheimer's disease (AD) and non-AD neurodegenerative dementia (ND), and explores the relationship with cerebrospinal fluid (CSF) biomarkers and clinical data. The findings suggest that widespread SWM alterations occur in both AD and non-AD ND, and AD shows more severe alterations in the parietal SWM. These alterations are strongly linked to both cognitive decline and diagnostic CSF biomarkers.
JOURNAL OF ALZHEIMERS DISEASE
(2022)
Article
Neurosciences
Celine Maes, Koen Cuypers, Ronald Peeters, Stefan Sunaert, Richard A. E. Edden, Jolien Gooijers, Stephan P. Swinnen
Summary: Recent studies emphasize the important role of the principal inhibitory neurotransmitter GABA in motor performance during aging. Behavioral results indicate poorer motor performance in older adults compared to young adults. Moreover, a transient task-related decrease in GABA+ levels was observed during task execution, which was linked to task-related brain activity patterns.
JOURNAL OF NEUROSCIENCE
(2022)
Article
Neurosciences
T. S. Monteiro, B. R. King, C. Seer, D. Mantini, S. P. Swinnen
Summary: Functional changes occur in the aging brain, leading to more restricted brain activity fluctuations in older adults. This study used innovation-driven co-activation patterns (ICAP) to investigate the emergence of various brain networks during rest in adults of different ages. The findings showed that older adults tend to activate fewer network configurations, including multiple functionally distinct brain areas, which may be related to the age-related decreases in performance and motor behavior.
Article
Clinical Neurology
Anouk S. Verschuur, Vivian Boswinkel, Chantal M. W. Tax, Jochen A. C. van Osch, Ingrid M. Nijholt, Cornelis H. Slump, Linda S. de Vries, Gerda van Wezel-Meijler, Alexander Leemans, Martijn F. Boomsma
Summary: This study aimed to apply and evaluate an intensity-based interpolation technique for segmentation of motion-affected neonatal brain MRI. The results showed that interpolation can effectively improve the segmentation of scans with motion artifacts and reduce the percentage of discarded scans.
JOURNAL OF NEUROIMAGING
(2022)
Article
Biophysics
Ernst Christiaanse, Patrik O. O. Wyss, Anke Scheel-Sailer, Angela Frotzler, Dirk Lehnick, Rajeev K. K. Verma, Markus F. F. Berger, Alexander Leemans, Alberto De Luca
Summary: The study investigates the variability and reliability of diffusion kurtosis imaging (DKI) metrics in brain tissues outside white matter using an advanced estimation called mean kurtosis (MK)-Curve. The MK-Curve corrected DKI metrics showed good to excellent agreement in white and gray matter at 3 T, except for two metrics derived from DKI. This study highlights the importance of using a correction method to improve the reliability of DKI metrics.
NMR IN BIOMEDICINE
(2023)
Review
Neurosciences
Shanti Van Malderen, Melina Hehl, Stefanie Verstraelen, Stephan P. Swinnen, Koen Cuypers
Summary: This paper reviews and summarizes the research on the inter- and intra-hemispheric interactions of dual-site transcranial magnetic stimulation (ds-TMS) and discusses its applicability and contributions to motor control. However, there is variability in the experimental context and stimulation parameters, calling for more systematic studies to address these issues.
REVIEWS IN THE NEUROSCIENCES
(2023)
Article
Clinical Neurology
Elena M. Bonke, Amanda Clauwaert, Stefan M. Hillmann, Uta Tacke, Caroline Seer, Eukyung Yhang, Yorghos Tripodis, Stian B. Sandmo, Tim L. T. Wiegand, David Kaufmann, Elisabeth Kaufmann, Sutton B. Richmond, Malo Gaubert, Johanna Seitz-Holland, Alexander Leemans, Stephan P. Swinnen, Roald Bahr, Ofer Pasternak, Florian Heinen, Inga K. Koerte, Michaela V. Bonfert, Jolien Gooijers
Summary: This study investigates the relationship between neurological soft signs (NSS) and postural control in adolescent athletes, and suggests that force plate measures can provide relevant quantitative information in addition to qualitative assessments.
JOURNAL OF THE NEUROLOGICAL SCIENCES
(2023)
Article
Neurosciences
Geraldine Rodriguez-Nieto, Caroline Seer, Justina Sidlauskaite, Lore Vleugels, Anke Van Roy, Robert Hardwick, Stephan Swinnen
Summary: This study comprehensively investigates the neural networks of executive functions and synthesizes the convergences and divergences among the most frequently used executive paradigms. It reveals that a fronto-parietal network is shared by the three main executive domains and identifies the distinctive components of each domain. The study also detects heterogeneity among paradigms within the same domain and provides insights into the neural signatures associated with specific memory modules. Overall, it contributes to a better understanding of executive processes and has implications for clinical applications.
Article
Neurosciences
Geraldine Rodriguez-Nieto, Oron Levin, Lize Hermans, Akila Weerasekera, Anca Croitor Sava, Astrid Haghebaert, Astrid Huybrechts, Koen Cuypers, Dante Mantini, Uwe Himmelreich, Stephan P. Swinnen
Summary: Aging is associated with structural and metabolic changes in the brain. Previous research has focused on individual brain regions, but the relationship among metabolites across the brain has been less studied. Using 1H-MRS, this study investigated the relationship among metabolite concentrations in different brain regions in young and older adults. The results showed age-related differences in metabolite concentrations and revealed associative patterns between metabolites across brain regions, which differed between age groups.
Article
Multidisciplinary Sciences
Antonio Jimenez-Marin, Nele De Bruyn, Jolien Gooijers, Alberto Llera, Sarah Meyer, Kaat Alaerts, Geert Verheyden, Stephan P. Swinnen, Jesus M. Cortes
Summary: This study extends lesion network mapping (LNM) by using a multimodal strategy, combining functional and structural networks, to predict sensorimotor behavior in stroke patients. The results show that functional networks contribute more than structural networks in predicting sensorimotor behavior, and the performance of structural networks depends on lesion size correction.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Eric Cito Becman, Larissa Driemeier, Oron Levin, Stephan Swinnen, Arturo Forner-Cordero
Summary: This study investigates the impact of training and testing condition differences on the predictions of a convolutional neural network (CNN) for myoelectric simultaneous and proportional control (SPC). A dataset of electromyogram (EMG) signals and joint angular accelerations recorded during a star drawing task was utilized. CNNs were trained using specific combinations of motion amplitude and frequency and tested under different combinations. The predictive performance was evaluated using normalized root mean squared error (NRMSE), correlation, and linear regression slope. The results showed that the predictive performance declined differently depending on the increase or decrease of confounding factors. Correlation decreased as the factors decreased, while slope deteriorated when the factors increased. NRMSE worsened in both increasing and decreasing factor scenarios. The study suggests that differences in EMG signal-to-noise ratio (SNR) between training and testing may affect the noise robustness of the CNNs' learned internal features, leading to worse correlations. Additionally, the inability of the networks to predict accelerations outside the training range may contribute to slope deterioration. These findings provide opportunities for developing strategies to mitigate the negative impact of confounding factors on myoelectric SPC devices.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Radiology, Nuclear Medicine & Medical Imaging
Andrey Zhylka, Alexander Leemans, Josien P. W. Pluim, Alberto De Luca
Summary: Multi-level Fiber Tractography (MLFT) is a novel algorithm that reconstructs fiber pathways by progressively considering previously unused fiber orientations. It has been evaluated on synthetic and in vivo data and shown to achieve a comparable radial extent of reconstruction to conventional methods while preserving topography better.
MAGNETIC RESONANCE MATERIALS IN PHYSICS BIOLOGY AND MEDICINE
(2023)
Article
Cell Biology
Caroline Seer, Hamed Zivari Adab, Justina Sidlauskaite, Thijs Dhollander, Sima Chalavi, Jolien Gooijers, Stefan Sunaert, Stephan P. Swinnen
Summary: The study found that white matter connectivity in the corpus callosum (CC) is associated with cognitive and motor performance in older adults, with executive functioning partially explaining the relationship between prefrontal transcallosal pathways and motor control.
Article
Neuroimaging
Joanne P. M. Kenney, Laura Milena Rueda-Delgado, Erik O. Hanlon, Lee Jollans, Ian Kelleher, Colm Healy, Niamh Dooley, Conor McCandless, Thomas Frodl, Alexander Leemans, Catherine Lebel, Robert Whelan, Mary Cannon
Summary: Accurate markers of psychiatric illness are important for predicting disease course. This study used machine learning to investigate neuroanatomical markers of subclinical psychotic experiences (PEs) in early and later adolescence. Neuroimaging data classified adolescents with PEs at 11-13 years and 18-20 years, but not at 14-16 years. Left frontal regions were top classifiers for 11-13 years-old adolescents with PEs, while those with future PEs at 18-20 years were best distinguished based on specific brain regions.
NEUROIMAGE-CLINICAL
(2022)
