[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-417410-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-417410-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","automating-brachial-plexus-scan-wireless-handheld-ultrasound-with-deep-learning-over-ten-locations","Automating Brachial Plexus Scan - Wireless Handheld Ultrasound with Deep Learning over Ten Locations","","Topographical ultrasound supports brachial plexus visualization for regional anesthesia, yet existing AI nerve-localization models are typically trained on high-resolution stationary ultrasound. This limits performance when using convenient low-resolution wireless handheld devices. A two-stage convolutional neural network was developed for low-resolution images, using 60,000 expert-annotated frames from 30 adult patients. Testing showed 99.2% sensitivity and 84.5% specificity for position classification and improved landmark segmentation versus novice physicians, supporting educational training.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/automating-brachial-plexus-scan-wireless-handheld-ultrasound-with-deep-learning-over-ten-locations/417410/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/automating-brachial-plexus-scan-wireless-handheld-ultrasound-with-deep-learning-over-ten-locations/417410.png","ImageObject",300,407,{"name":42,"@type":43},"acoobca","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-28",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does the study address in AI-based brachial plexus localization?","Question",{"text":63,"@type":64},"Existing models are trained on high-resolution stationary ultrasound images, so they do not generalize well to low-resolution wireless handheld devices. The study proposes a segmentation approach suited to handheld imaging.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the model trained and what data were used?",{"text":68,"@type":64},"Thirty adult patients provided consent. A portable high-frequency ultrasound probe acquired B-mode images and video clips at 20 predefined positions, and a training set of 60,000 images with expert annotations was constructed.",{"name":70,"@type":61,"acceptedAnswer":71},"How did the proposed model perform compared with novice physicians?",{"text":72,"@type":64},"For classification of image positions, the model achieved 99.2% sensitivity and 84.5% specificity, versus 81.1% and 59.8% for novices. For segmentation, it produced lower distance error and better shape similarity metrics.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},417410,1790719104,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":4},3985747870733,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","| Original Article |\n| --- |\n|  |\n\nAutomating Brachial Plexus Scan: Wireless Handheld Ultrasound with Deep Learning over Ten Locations  \nMin‑Jie Yang1,2*, Hao‑Kuang Wang1,3, Yi‑Qi Zhang1,4  \n1Department of Neurosurgery, E‑Da Hospital, Kaohsiung, Taiwan, 2Department of Surgery, School of Medicine, National Taiwan University, Taipei, Taiwan, 3Department of Surgery, Institute of Clinical Medicine, National Cheng Kung University, Tainan, Taiwan, 4Department of Surgery, School of Medicine, China Medical University, Taichung, Taiwan  \nAbstract  \nBackground: Topographical ultrasound is gaining traction for brachial plexus visualization due to its value in regional anesthesia. However, existing artificial intelligence models for nerve localization are trained on high‑resolution stationary ultrasound images, limiting their applicability to more convenient, low‑resolution handheld devices. This study addresses this challenge by proposing a novel image segmentation model suitable for low‑resolution images. Methods: Thirty adult patients provided informed consent for participation in this study. A high‑frequency, portable ultrasound probe was used to acquire B‑mode images and video clips at 20 predefined positions. A training dataset of60,000 images was constructed with expert annotations for landmark localization. A two‑stage convolutional neural network architecture was implemented: Stage 1 for image classification and Stage 2 for segmentation with centroid refinement. Four novice physicians underwent testing for comparison. Model performance was evaluated using classification accuracy and segmentation precision metrics. Results: Our model achieved high accuracy in classifying brachial plexus ultrasound image positions (99.2% sensitivity and 84.5% specificity) compared to novice physicians (81.1% sensitivity and 59.8% specificity). In addition, the model demonstrated significantly superior performance in landmark segmentation, with lower median distance error (0.19 mm vs. 4.9 mm) and superior shape similarity metrics (average symmetric surface distance, Hausdorff distance and intersection over union) compared to novice physicians. Conclusion: We present a novel image segmentation model for brachial plexus ultrasound images. The model achieved high classification accuracy and significantly surpassed novice physicians in landmark segmentation. This performance suggests the potential for the model as an educational tool to aid novice physicians in learning brachial plexus anatomy.  \nKeywords: Artificial intelligence‑based nerve identification, brachial plexus, handheld ultrasound, portable device deployment  \nIntroductIon  \nRecent years have witnessed a growing body of research investigating the application of topographical ultrasound for brachial plexus visualization, driven by its recognized clinical utility in regional anesthesia and peripheral nerve blocks.[1‑3] The complex anatomy of the cervical region has spurred the development of artificial intelligence (AI)‑assisted models to facilitate localization of relevant structures, particularly for novice practitioners. However, a key limitation of existing models lies in their training on high‑resolution images acquired with cart‑based ultrasound systems. These models may not generalize well to images obtained using more convenient, portable, wireless handheld devices. The advantages of handheld devices include their compact size, lightweight  \nReceived: 29‑05‑2024 Revised: 26‑07‑2024 Accepted: 29‑08‑2024 Available Online: 17‑03‑2025  \n\n| Access this article online |  |\n| --- | --- |\n| Quick Response Code:\u003Cbr>| Website:\u003Cbr>[https://journals.lww.com/jmut](https://journals.lww.com/jmut) |\n|  | DOI:\u003Cbr>10.4103/jmu.jmu_61_24 |\n\ndesign, and the ability to store acquired images on personal smartphones or tablets. However, these devices typically have fewer channels in micro‑beamforming system, leading to inherently lower image resolution.  \nConventional AI‑assisted image segmentation tasks oft","cbCaihtamO3PWfhY","https://ap.wps.com/l/cbCaihtamO3PWfhY","pdf",6606696,13,"English","# Abstract\n## Background\n## Methods\n## Results\n## Conclusion\n# Introduction\n# Materials and Methods\n## Ethical approval and participant recruitment","[{\"question\":\"What problem does the study address in AI-based brachial plexus localization?\",\"answer\":\"Existing models are trained on high-resolution stationary ultrasound images, so they do not generalize well to low-resolution wireless handheld devices. The study proposes a segmentation approach suited to handheld imaging.\"},{\"question\":\"How was the model trained and what data were used?\",\"answer\":\"Thirty adult patients provided consent. A portable high-frequency ultrasound probe acquired B-mode images and video clips at 20 predefined positions, and a training set of 60,000 images with expert annotations was constructed.\"},{\"question\":\"How did the proposed model perform compared with novice physicians?\",\"answer\":\"For classification of image positions, the model achieved 99.2% sensitivity and 84.5% specificity, versus 81.1% and 59.8% for novices. For segmentation, it produced lower distance error and better shape similarity metrics.\"}]","Automating Brachial Plexus Scan - Wireless Handheld Ultrasound with Deep Learning over Ten Locations | PDF",1790609090,33]