[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122069-en":3,"doc-seo-122069-105":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},122069,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Language task-based fMRI analysis using machine learning and deep learning - Research study","Task-based language fMRI provides a non-invasive way to identify brain regions supporting language, informing planning for neurosurgical resection near eloquent cortex. This study evaluates multiple machine learning and deep learning approaches to classify voxel-wise fMRI time series using seven language task paradigms from 26 participants. Results compare overall brain performance, using AUC, Dice coefficient, and Euclidean distance between activation peaks, showing that general machine learning and interval-based methods are most promising for localizing language-related activations. The findings support language mapping from less structured paradigms.","TYPE Original Research PUBLISHED 27 November 2024 DOI 10.3389/fradi.2024.1495181  \nEDITED BY  \nCheng Chen,  \nThe Chinese University of Hong Kong, China  \nREVIEWED BY  \nYanfu Zhang,  \nUniversity of Pittsburgh, United States Ke Liu,  \nBeijing Normal University, China  \n*CORRESPONDENCE  \nViktor Vegh  \n [v.vegh@uq.edu.au](v.vegh@uq.edu.au)  \nRECEIVED 12 September 2024  \nACCEPTED 12 November 2024  \nPUBLISHED 27 November 2024  \nCITATION  \nKuan E, Vegh V, Phamnguyen J, O ’ Brien K, Hammond A and Reutens D (2024) Language task-based fMRI analysis using machine learning and deep learning.  \nFront. Radiol. 4:1495181 .  \ndoi: 10.3389/fradi.2024.1495181  \nCOPYRIGHT  \n© 2024 Kuan, Vegh, Phamnguyen, O ’ Brien, Hammond and Reutens. This is an openaccess article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nLanguage task-based fMRI analysis using machine learning and deep learning  \nElaine Kuan1,2,3, Viktor Vegh1,2,3*, John Phamnguyen1,3,4,  \nKieran O’ Brien5, Amanda Hammond5 and David Reutens1,2,3,4  \n1Centre for Advanced Imaging, The University of Queensland, Brisbane, QLD, Australia, 2ARC Training Centre for Innovation in Biomedical Imaging Technology, The University of Queensland, Brisbane, QLD, Australia, 3Australia Institute for Bioengineering and Nanotechnology, The University of Queensland, Brisbane, QLD, Australia, 4Neurology Department, Royal Brisbane and Women’s Hospital, Brisbane, QLD, Australia, 5Siemens Healthineers, Siemens Healthcare Pty Ltd, Brisbane, QLD, Australia  \nIntroduction: Task-based language fMRI is a non-invasive method of identifying brain regions subserving language that is used to plan neurosurgical resections which potentially encroach on eloquent regions. The use of unstructured fMRI paradigms, such as naturalistic fMRI, to map language is of increasing interest. Their analysis necessitates the use of alternative methods such as machine learning (ML) and deep learning (DL) because task regressors may be difficult to define in these paradigms.  \nMethods: Using task-based language fMRI as a starting point, this study investigates the use of different categories of ML and DL algorithms to identify brain regions subserving language. Data comprising of seven task-based language fMRI paradigms were collected from 26 individuals, and ML and DL models were trained to classify voxel-wise fMRI time series.  \nResults: The general machine learning and the interval-based methods were the most promising in identifying language areas using fMRI time series classification. The geneal machine learning method achieved a mean whole-brain Area Under the Receiver Operating Characteristic Curve (AUC) of 0 .97 + 0. 03, mean Dice coefficient of 0 .6 + 0.34 and mean Euclidean distance of 2 .7 + 2.4mm between activation peaks across the evaluated regions of interest. The intervalbased method achieved a mean whole-brain AUC of 0 .96 + 0. 03, mean Dice coefficient of 0 .61 + 0.33 and mean Euclidean distance of 3 .3 + 2.7mm between activation peaks across the evaluated regions of interest.  \nDiscussion: This study demonstrates the utility of different ML and DL methods in classifying task-based language fMRI time series. A potential application of these methods is the identification of language activation from unstructured paradigms.  \nKEYWORDS  \ntask-based fMRI, language, time series, brain activation, machine learning, deep learning  \n1 Introduction  \nIndividual variation in functional representation in the cerebral cortex (1, 2) and the potential for re-organisation in the setting of neurological disorders (3, 4) make it crucial to accurately localise eloquent areas of the ","cbCaivbviIHeB7BS","https://ap.wps.com/l/cbCaivbviIHeB7BS","pdf",14950979,1,15,"English","en",105,"# Introduction\n## Background and clinical relevance\n## Limits of task-based paradigms\n## Rationale for ML and DL\n# Methods\n## Data and task paradigms\n## ML and DL modeling approach\n# Results\n## Performance metrics and comparison\n# Discussion\n## Utility and potential applications","[{\"question\":\"What problem does the study address in language fMRI analysis?\",\"answer\":\"The study targets how to analyze task-based language fMRI data by using machine learning and deep learning, particularly when task regressors are hard to define, such as in unstructured paradigms.\"},{\"question\":\"How were the machine learning and deep learning models trained?\",\"answer\":\"Voxel-wise fMRI time series were used, with models trained on data from seven task-based language fMRI paradigms collected from 26 individuals.\"},{\"question\":\"Which approaches performed best for identifying language areas?\",\"answer\":\"General machine learning and interval-based methods were most promising, achieving high whole-brain AUC values and strong agreement metrics between activation peaks across evaluated regions of interest.\"}]","Language task-based fMRI analysis using machine learning and deep learning - Research study | PDF",1785808678,38,{"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},"language-task-based-fmri-analysis-using-machine-learning-and-deep-learning-research-study","",{"@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/language-task-based-fmri-analysis-using-machine-learning-and-deep-learning-research-study/122069/",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","2026-08-04",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 problem does the study address in language fMRI analysis?","Question",{"text":75,"@type":76},"The study targets how to analyze task-based language fMRI data by using machine learning and deep learning, particularly when task regressors are hard to define, such as in unstructured paradigms.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the machine learning and deep learning models trained?",{"text":80,"@type":76},"Voxel-wise fMRI time series were used, with models trained on data from seven task-based language fMRI paradigms collected from 26 individuals.",{"name":82,"@type":73,"acceptedAnswer":83},"Which approaches performed best for identifying language areas?",{"text":84,"@type":76},"General machine learning and interval-based methods were most promising, achieving high whole-brain AUC values and strong agreement metrics between activation peaks across evaluated regions of interest.","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"]