[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117385-en":3,"doc-seo-117385-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},117385,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Mapping dynamic brain networks with MEG data using machine learning","This thesis develops new methodologies for extracting richer information from non-invasive electrophysiological recordings, centered on temporal structure in brain network activity. It models time-varying functional connectivity (FC) at fast cognitive scales (~100 ms) using generative statistical and deep learning frameworks such as HMM and DyNeMo. The work introduces M-DyNeMo to relax the shared-dynamics assumption between power and FC, and proposes HIVE to capture session-level heterogeneity via embedding “fingerprints,” improving recovery on simulated data and interpreting meaningful variation in real MEG.","Mapping dynamic brain networks with MEG data using machine  \nlearning  \nRukuang Huang  \nsupervised by  \nMark Woolrich  \nand Chetan Gohil  \nJesus College University of Oxford  \nA thesis submitted for the degree of Doctor of Philosophy September 2024  \nAbstract  \nThis thesis mainly concerns the analysis of non-invasive electrophysiological data, focusing on development of new methodologies for extracting more information from existing datasets. The primary object of interest is the temporal structure in brain network activity, in particular, time-varying functional connectivity (FC), which has been linked to cognition, demographics and disease states. Statistical machine learning and deep learning allows researchers to formulate generative models such as the HMM (Hidden Markov Model) and DyNeMo (Dynamic Network Modes) to give estimates of time-varying FC atthe time scales of fast cognition, i.e. on the order of 100 milliseconds, which has been impossible with traditional methods like the sliding window approach. The main contribution of the work in this thesis lies in tackling two of the limitations of these generative models.  \nFirstly, time-varying estimates of power and FC are calculated under the assumption that they share the same dynamics. But there is no principled basis for this assumption. We propose Multi-dynamic Network Modes (M-DyNeMo), an extension to DyNeMo, that allows for the possibility that the power and the FC networks have different dynamics. Using this new method on magnetoencephalography (MEG) data, we show that the dynamics of the power and the FC networks are not strongly coupled. Using a visual perception task MEG dataset, we also show that the power and FC network dynamics are modulated by the task, and that the coupling in their dynamics changes significantly during task. This new method reveals novel insights into evoked responses and ongoing activity that previous methods fail to capture, challenging the assumption that power and FC share the same dynamics.  \nSecondly, existing methods assume the same network, or set of networks, are shared by all recording sessions, i.e. the networks are estimated at the group level. This is an unrealistic assumption as functional brain activity is known to possess significant heterogeneity and these methods do not allow for the discovery of, nor benefit from, subpopulation structure in the data. We propose the use of embedding vectors (c.f. word embedding in Natural Language Processing) to explicitly model individual sessions while inferring networks across a group. This vector is effectively a “fingerprint” for each session, which can cluster  \nsessions with similar functional networks together in a learnt embedding space. We apply this approach to estimate time-varying FC, using the HMM, to model individual sessions in neuroimaging data. We call this approach HIVE (HMM with Integrated Variability Estimation) . Using simulated data, we show that HIVE can recover the true, underlying inter-session variability and show improved performance over existing approaches. Using real MEG data, we show the learnt embedding vectors (session fingerprints) reflect meaningful sources of variation across a population (demographics, scanner types, sites, etc) . This work provides a powerful new technique for modelling individual sessions while leveraging information available across an entire group.  \nOverall, this thesis utilises techniques in statistical machine learning and deep generative models to extract more information from neuroimaging data. This body of work provides ways to gain extra insights in cortical network dynamics from large-scale and diverse datasets. In addition to those in methodology, significant contributions were made to the software package osl-dynamics that allows models to be trained and analysed efficiently and reproducibly.  \nAcknowledgements  \nI would like to express my deepest gratitude to my supervisor Mark Woolrich. Mark always gave guidance, enco","cbCaioxK02672eJO","https://ap.wps.com/l/cbCaioxK02672eJO","pdf",24160859,1,212,"English","en",105,"# Contents\n## Introduction\n## Modelling and learning techniques","[{\"question\":\"What data and main target does the thesis focus on?\",\"answer\":\"The thesis analyzes non-invasive electrophysiological data with a focus on the temporal structure of brain network activity, especially time-varying functional connectivity (FC).\"},{\"question\":\"How does the thesis improve on generative models like DyNeMo?\",\"answer\":\"It introduces Multi-dynamic Network Modes (M-DyNeMo) to allow power and FC to have different dynamics, addressing a key limitation of earlier assumptions.\"},{\"question\":\"How does the thesis handle differences across recording sessions?\",\"answer\":\"It proposes HIVE, which uses embedding vectors as session “fingerprints” to model individual sessions while inferring networks across a group, capturing inter-session variability.\"}]","Mapping dynamic brain networks with MEG data using machine learning | PDF",1785675509,534,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"mapping-dynamic-brain-networks-with-meg-data-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/mapping-dynamic-brain-networks-with-meg-data-using-machine-learning/117385/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What data and main target does the thesis focus on?","Question",{"text":75,"@type":76},"The thesis analyzes non-invasive electrophysiological data with a focus on the temporal structure of brain network activity, especially time-varying functional connectivity (FC).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis improve on generative models like DyNeMo?",{"text":80,"@type":76},"It introduces Multi-dynamic Network Modes (M-DyNeMo) to allow power and FC to have different dynamics, addressing a key limitation of earlier assumptions.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the thesis handle differences across recording sessions?",{"text":84,"@type":76},"It proposes HIVE, which uses embedding vectors as session “fingerprints” to model individual sessions while inferring networks across a group, capturing inter-session variability.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]