[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-455744-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-455744-en":130},{"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","reconstruction-of-heart-related-imaging-from-lung-electrical-impedance-tomography-using-semi-siamese-u-net","Reconstruction of Heart-related Imaging from Lung Electrical Impedance Tomography Using Semi-Siamese U-Net","","Electrical Impedance Tomography (EIT) enables bedside ventilation monitoring, yet cardiac-related reconstruction is hindered by lung impedance dominance. This research proposes a semi-Siamese U-Net to recover heart-related impedance imaging from lung EIT signals. A shared encoder with two decoders segments lung and heart regions independently, trained on FEM-based simulations and evaluated on real human EIT data with a weighted loss emphasizing cardiac features. Results show Dice >0.99 and MAE \u003C0.1% on simulations, and effective lung-heart separation on real frames without extra fine-tuning.",{"@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/reconstruction-of-heart-related-imaging-from-lung-electrical-impedance-tomography-using-semi-siamese-u-net/455744/",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/reconstruction-of-heart-related-imaging-from-lung-electrical-impedance-tomography-using-semi-siamese-u-net/455744.png","ImageObject",300,407,{"name":42,"@type":43},"Ophelia","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is reconstructing heart-related signals from lung EIT challenging?","Question",{"text":63,"@type":64},"Heart-related reconstruction is limited because lung impedance changes dominate the EIT signals. This dominance makes it harder to recover cardiac information from the mixed measurements.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How does the semi-Siamese U-Net improve lung-heart reconstruction?",{"text":68,"@type":64},"The model uses a shared encoder and two decoders to segment lung and heart regions independently. A weighted binary cross-entropy loss emphasizes learning cardiac-related features.",{"name":70,"@type":61,"acceptedAnswer":71},"What were the reported performance and validation outcomes?",{"text":72,"@type":64},"On FEM-based simulation data, the method achieved a Dice coefficient greater than 0.99 and MAE below 0.1%. It also separated lung and heart regions on real human EIT frames without additional fine-tuning, indicating strong generalization.","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},455744,1791177019,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":107,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},7971461741311,"https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826","[1573-4056/25](1573-4056/25 Send Orders for Reprints to reprints@benthamscience.net)[ Send Orders for Reprints to](1573-4056/25 Send Orders for Reprints to reprints@benthamscience.net)[ ](1573-4056/25 Send Orders for Reprints to reprints@benthamscience.net)[reprints@benthamscience.net](1573-4056/25 Send Orders for Reprints to reprints@benthamscience.net)  \n1  \nCurrent Medical Imaging  \nContent list available at: [https://benthamscience.com/journals/cmir](https://benthamscience.com/journals/cmir)  \nRESEARCH ARTICLE  \nReconstruction of Heart-related Imaging from Lung Electrical Impedance Tomography Using Semi-Siamese U-Net  \nYen-Fen Ko1,*, Yue-Der Lin2 and Po-lan Su3  \n1Department of Biomedical Engineering, College of Biomedical Engineering, China Medical University, Taichung, Taiwan 2Department of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan  \n3Department of Internal Medicine, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, Tainan, Taiwan  \nAbstract:  \nIntroduction:  \nElectrical Impedance Tomography (EIT) is widely used for bedside ventilation monitoring but is limited in reconstructing cardiac-related signals due to the dominance of lung impedance changes. This study aims to reconstruct heart-related impedance imaging from lung EIT using a novel semi-Siamese U-Net architecture.  \nMethods:  \nA deep learning model was developed with a shared encoder and two decoders designed to segment lung and heart regions independently. The model was trained and validated on FEM-based EIT simulations and tested on real human EIT data. A weighted binary cross-entropy loss was applied to emphasize cardiac-related learning.  \nResults:  \nThe model achieved a Dice coefficient >0.99 and MAE \u003C0.1% on simulation data. It successfully separated lung and heart regions on human EIT frames without additional fine-tuning, demonstrating strong generalization capacity.  \nDiscussion:  \nThese findings reveal that the semi-Siamese U-Net can overcome signal dominance and improve cardiac-related EIT reconstruction. However, promising results are currently limited to qualitative evaluation of real data and simulation-based training.  \nConclusion:  \nThe proposed method offers a potential pathway for simultaneous lung-heart monitoring in ICU settings. Future work will focus on clinical validation and real-time implementation.  \nKeywords: Electrical impedance tomography, Semi-Siamese U-Net, Lung imaging, Heart imaging, ICU settings, PEEP, ARDS.  \n\n| Article History | Received: April 24, 2025 | Revised: May 27, 2025 | Accepted: June 02, 2025 |\n| --- | --- | --- | --- |\n\n1. INTRODUCTION  \nLung Electrical Impedance Tomography (EIT) is a technique that has rapidly developed in the recent decade and is based on applying alternating micro-currents at 20-50 Hz using a set of electrodes positioned around the chest of the subject.  \n* Address correspondence to this author at the Department of Biomedical Engineering, College of Biomedical Engineering, China Medical University, No.91, Xueshi Road, North District 404, Taichung City, Taiwan;  \nTel: +8869 33449872; [E-mails: kklven@gmail.com](E-mails: kklven@gmail.com), [yfko@cmu.edu.tw](yfko@cmu.edu.tw)  \nLung EIT is particularly useful in monitoring the functioning of the lungs because lung tissue conductivity is much lower than most tissues ofthe organs in the thorax. This leads to high absolute contrast of lung EIT imaging [1] . In clinical practice, Electrical Impedance Tomography (EIT) is typically performed non-invasively using a rubber electrode belt equipped with 16 electrodes, which is placed around the patient's chest. The system operates by applying small alternating electrical currents through the electrodes and measuring the resulting  \nDOI: 10.2174/0115734056408077250610070821, 2025, 21, e15734056408077  \nvoltage differences. These data are then used to reconstruct real-time images of impedance changes within the thorax, primarily reflecting ven","cbCaibzzZD8ThVJM","https://ap.wps.com/l/cbCaibzzZD8ThVJM","pdf",11088376,13,"English","# Abstract\n# Introduction\n## Electrical Impedance Tomography for bedside ventilation monitoring\n## Clinical relevance of PEEP and ARDS\n## Ventilation–perfusion and perfusion role\n# Methods\n## Semi-Siamese U-Net architecture and training strategy\n## Weighted loss for heart-related learning\n# Results\n## Dice and MAE performance on simulation data\n## Generalization on real human EIT frames\n# Discussion\n## Overcoming signal dominance and reconstruction improvement\n# Conclusion\n## Potential for ICU lung-heart monitoring\n## Future clinical validation and real-time implementation","[{\"question\":\"Why is reconstructing heart-related signals from lung EIT challenging?\",\"answer\":\"Heart-related reconstruction is limited because lung impedance changes dominate the EIT signals. This dominance makes it harder to recover cardiac information from the mixed measurements.\"},{\"question\":\"How does the semi-Siamese U-Net improve lung-heart reconstruction?\",\"answer\":\"The model uses a shared encoder and two decoders to segment lung and heart regions independently. A weighted binary cross-entropy loss emphasizes learning cardiac-related features.\"},{\"question\":\"What were the reported performance and validation outcomes?\",\"answer\":\"On FEM-based simulation data, the method achieved a Dice coefficient greater than 0.99 and MAE below 0.1%. It also separated lung and heart regions on real human EIT frames without additional fine-tuning, indicating strong generalization.\"}]","Reconstruction of Heart-related Imaging from Lung Electrical Impedance Tomography Using Semi-Siamese U-Net | PDF",1790744140,33]