Article
Biology
Yibin Wang, Haixia Long, Qianwei Zhou, Tao Bo, Jianwei Zheng
Summary: This study proposes a position-aware graph-convolution-network-based model for the diagnosis of Autism Spectrum Disorder (ASD), with superior accuracy and interpretability. The model utilizes a time-series encoder for feature extraction and a connectivity generator to model the correlation with long-range dependencies. It also adopts a position embedding technique to differentiate brain nodes with different locations and employs a rarefying method for reducing dimensionality complexity. The experiments conducted on Autism Brain Imaging Data Exchange demonstrate state-of-the-art performance and provide potential biomarkers for ASD clinical diagnosis.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Neurosciences
Yueying Chen, Aiping Liu, Xueyang Fu, Jie Wen, Xun Chen
Summary: This paper proposes an invertible dynamic GCN model for identifying ASD and investigating the alterations of connectivity patterns associated with the disease. Experimental results show that the proposed method achieves superior disease classification performance and provides an interpretable deep learning model for brain connectivity analysis.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mingliang Wang, Jiashuang Huang, Mingxia Liu, Daoqiang Zhang
Summary: This study proposes a temporal dynamics learning (TDL) method for network-based brain disease identification using rs-fMRI time-series data. By integrating network feature extraction and classifier training into a unified framework, it addresses the issues of previous studies paying less attention to the evolution of global network structures over time and treating feature extraction and training as separate tasks.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Mathematical & Computational Biology
Md Shale Ahammed, Sijie Niu, Md Rishad Ahmed, Jiwen Dong, Xizhan Gao, Yuehui Chen
Summary: The study highlights how non-invasive whole-brain scans can assist in the diagnosis of neuropsychiatric disorders, such as autism and brain cancer. Using functional Magnetic Resonance Imaging (fMRI) and advanced machine learning methods, the proposed DarkASDNet model showed high accuracy in classifying Autism Spectrum Disorder (ASD) against typical controls.
FRONTIERS IN NEUROINFORMATICS
(2021)
Article
Neurosciences
Rebecca J. Lepping, Walker S. McKinney, Grant C. Magnon, Sarah K. Keedy, Zheng Wang, Stephen A. Coombes, David E. Vaillancourt, John A. Sweeney, Matthew W. Mosconi
Summary: Research indicates that individuals with autism spectrum disorder exhibit increased force variability and reduced entropy during visuomotor behavior, along with greater brain activation and decreased functional connectivity. Additionally, delayed maturation is observed in the functional connectivity between cerebellar-cortical sensorimotor and nonsensorimotor networks.
HUMAN BRAIN MAPPING
(2022)
Article
Neurosciences
Jingcong Li, Fei Wang, Jiahui Pan, Zhenfu Wen
Summary: This paper proposed a functional graph discriminative network (FGDN) for ASD classification, achieving effective differentiation between ASD patients and healthy controls based on pre-built graph templates. The FGDN serves as an effective tool for ASD identification and shows potential as a technique in neuroscience research.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Pediatrics
Min Feng, Juncai Xu
Summary: This study presents an advanced convolutional neural network algorithm for early detection of autism spectrum disorder (ASD) using resting-state functional magnetic resonance imaging (fMRI) in pediatric cohorts. The algorithm achieves unparalleled diagnostic metrics and surpasses existing computational methods. Feature map analyses confirm its hierarchical feature extraction capabilities. The research provides a deep learning framework for computer-assisted ASD screening via fMRI, with transformative implications for early diagnosis and intervention.
Article
Neurosciences
Sarah Barzegari Alamdari, Masoumeh Sadeghi Damavandi, Mojtaba Zarei, Reza Khosrowabadi
Summary: Cognitive functions in individuals with autism spectrum disorder (ASD) are affected by changes in brain functional networks. This study explores the alteration pattern of theory of mind (ToM) and weak central coherence theory in the network level of functional interactions. The findings highlight significant changes in the interaction of various functional networks, supporting the main cognitive theories of ASD.
FRONTIERS IN HUMAN NEUROSCIENCE
(2022)
Article
Neurosciences
Yasuhito Nagai, Eiji Kirino, Shoji Tanaka, Chie Usui, Rie Inami, Reiichi Inoue, Aki Hattori, Wataru Uchida, Koji Kamagata, Shigeki Aoki
Summary: This study evaluated functional connectivity in adult autism spectrum disorder (ASD) patients using rs-fMRI and DKI. The results showed abnormal FC between different brain regions in ASD patients compared to healthy controls. Additionally, DKI data revealed microstructural alterations in the white matter tracts of ASD patients.
Article
Computer Science, Artificial Intelligence
Nan Wang, Dongren Yao, Lizhuang Ma, Mingxia Liu
Summary: The proposed MC-NFE method divides training data into ASD and HC groups, models inter-site heterogeneity within each category, and uses a nested SVD method to extract FC features for ASD detection. Experimental results show that MC-NFE outperforms several state-of-the-art methods in detecting ASD, with discriminative FCs mainly located in the default mode network, salience network, and cerebellum region.
MEDICAL IMAGE ANALYSIS
(2022)
Article
Behavioral Sciences
Pengchen Ren, Qingshang Bi, Wenbin Pang, Meijuan Wang, Qionglin Zhou, Xiaoshan Ye, Ling Li, Le Xiao
Summary: This study used a large sample of rs-fMRI data from ASD patients and TD controls to classify patients into subtypes using a machine learning model. The results showed differences in brain functional connectivity between these subtypes, which helps to reduce the heterogeneity of the disease.
BEHAVIOURAL BRAIN RESEARCH
(2023)
Article
Neurosciences
Carina Freitas, Benjamin A. E. Hunt, Simeon M. Wong, Leanne Ristic, Susan Fragiadakis, Stephanie Chow, Alana Iaboni, Jessica Brian, Latha Soorya, Joyce L. Chen, Russell Schachar, Benjamin T. Dunkley, Margot J. Taylor, Jason P. Lerch, Evdokia Anagnostou
Summary: This study examines the processing of familiar and unfamiliar stimuli in children with Autism Spectrum Disorder (ASD). The results demonstrate atypical processing of unfamiliar songs in ASD, while relatively typical processing of familiar stimuli. This finding suggests that familiarity may play a role in strength-based intervention planning for ASD.
FRONTIERS IN NEUROSCIENCE
(2022)
Article
Neurosciences
Junlin Jing, Benjamin Klugah-Brown, Shiyu Xia, Min Sheng, Bharat B. Biswal
Summary: This study compared the applications of Group information-guided independent component analysis (GIG-ICA) and independent vector analysis (IVA-GL) in neuroimaging research and found similarities and differences in the patterns of functional networks. IVA-GL demonstrated greater sensitivity in networks with higher intersubject variability, while GIG-ICA identified functional networks with distinct modularity patterns.
FRONTIERS IN NEUROSCIENCE
(2023)
Article
Computer Science, Interdisciplinary Applications
Mwiza Kunda, Shuo Zhou, Gaolang Gong, Haiping Lu
Summary: This paper proposes new methods for multi-site autism classification using the ABIDE dataset. By introducing a new measure of functional connectivity and adopting a domain adaptation approach, the classification accuracy can be improved to 73%.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Engineering, Biomedical
Hao Zhu, Jun Wang, Yin-Ping Zhao, Minhua Lu, Jun Shi
Summary: This study proposes a novel contrastive multi-view composite graph convolutional network (CMV-CGCN) for autism spectrum disorder (ASD) classification. The method constructs a pair of graphs based on functional connectivities (FC) and high-order functional connectivities (HOFC) features, sharing phenotypic information in the graph edges. A new contrastive multi-view learning method is proposed based on consistent representation, along with a contribution learning mechanism. Experimental results demonstrate that the proposed method outperforms existing methods on the Autism Brain Imaging Data Exchange (ABIDE) database.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Biochemical Research Methods
Keith W. Jamison, Abhrajeet V. Roy, Sheng He, Stephen A. Engel, Bin He
JOURNAL OF NEUROSCIENCE METHODS
(2015)
Article
Neurosciences
Abhrajeet V. Roy, Keith W. Jamison, Sheng He, Stephen A. Engel, Bin He
Article
Neurosciences
An Thanh Vu, Keith Jamison, Matthew F. Glasser, Stephen M. Smith, Timothy Coalson, Steen Moeller, Edward J. Auerbach, Kamil Ugurbil, Essa Yacoub
Article
Neurosciences
Michael P. Harms, Leah H. Somerville, Beau M. Ances, Jesper Andersson, Deanna M. Barch, Matteo Bastiani, Susan Y. Bookheimer, Timothy B. Brown, Randy L. Buckner, Gregory C. Burgess, Timothy S. Coalson, Michael A. Chappell, Mirella Dapretto, Gwena Elle Douaud, Bruce Fischl, Matthew F. Glasser, Douglas N. Greve, Cynthia Hodge, Keith W. Jamison, Saad Jbabdi, Sridhar Kandala, Xiufeng Li, Ross W. Mair, Silvia Mangia, Daniel Marcus, Daniele Mascali, Steen Moeller, Thomas E. Nichols, Emma C. Robinson, David H. Salat, Stephen M. Smith, Stamatios N. Sotiropoulos, Melissa Terpstra, Kathleen M. Thomas, M. Dylan Tisdall, Kamil Ugurbil, Andre van der Kouwe, Roger P. Woods, Lilla Zollei, David C. Van Essen, Essa Yacoub
Article
Neurosciences
Peng Zhang, Keith Jamison, Stephen Engel, Bin He, Sheng He
Article
Ophthalmology
Noah C. Benson, Keith W. Jamison, Michael J. Arcaro, An T. Vu, Matthew F. Glasser, Timothy S. Coalson, David C. Van Essen, Essa Yacoub, Kamil Ugurbil, Jonathan Winawer, Kendrick Kay
Article
Neurosciences
Kendrick Kay, Keith W. Jamison, Luca Vizioli, Ruyuan Zhang, Eshed Margalit, Kamil Ugurbil
Article
Neurosciences
Amy F. Kuceyeski, Keith W. Jamison, Julia P. Owen, Ashish Raj, Pratik Mukherjee
HUMAN BRAIN MAPPING
(2019)
Review
Radiology, Nuclear Medicine & Medical Imaging
Meenakshi Khosla, Keith Jamison, Gia H. Ngo, Amy Kuceyeski, Mert R. Sabuncu
MAGNETIC RESONANCE IMAGING
(2019)
Article
Neurosciences
Eshed Margalit, Keith W. Jamison, Kevin S. Weiner, Luca Vizioli, Ru-Yuan Zhang, Kendrick N. Kay, Kalanit Grill-Spector
JOURNAL OF NEUROSCIENCE
(2020)
Article
Biochemical Research Methods
Kendrick Kay, Keith W. Jamison, Ru-Yuan Zhang, Kamil Ugurbil
Article
Neurosciences
Elvisha Dhamala, Keith W. Jamison, Abhishek Jaywant, Sarah Dennis, Amy Kuceyeski
Summary: White matter pathways play a crucial role in facilitating neuronal coactivation patterns in the brain. This study integrates neuroimaging, connectomics, and machine learning methods to explore the relationship between functional and structural brain connectivity with cognition. The results suggest that functional connectivity is more predictive of cognitive scores than structural connectivity, and that distinct functional and structural connections are associated with crystallised and fluid cognitive abilities.
HUMAN BRAIN MAPPING
(2021)
Article
Neurosciences
Elvisha Dhamala, Keith W. Jamison, Abhishek Jaywant, Amy Kuceyeski
Summary: The study reveals that there are shared neurobiological features in the functional connectome underlying crystallised and fluid abilities between males and females, although there are still certain differences between genders.
HUMAN BRAIN MAPPING
(2022)
Article
Multidisciplinary Sciences
Meenakshi Khosla, Gia H. Ngo, Keith Jamison, Amy Kuceyeski, Mert R. Sabuncu
Summary: The study demonstrates that group-level models of neural activity built using movie-watching data can achieve remarkable prediction performance across large areas of the cortex, even beyond sensory-specific areas. These encoding models not only learn high-level concepts that generalize to task-bound paradigms, but also show great potential as powerful tools for studying brain function.
Article
Neurosciences
Jose Sanchez-Bornot, Roberto C. Sotero, J. A. Scott Kelso, Ozguer Simsek, Damien Coyle
Summary: This study proposes a multi-penalized state-space model for analyzing unobserved dynamics, using a data-driven regularization method. Novel algorithms are developed to solve the model, and a cross-validation method is introduced to evaluate regularization parameters. The effectiveness of this method is validated through simulations and real data analysis, enabling a more accurate exploration of cognitive brain functions.