[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-382838-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-382838-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","deep-learning-for-tumor-margin-identification-in-electromagnetic-imaging","Deep learning for tumor margin identification in electromagnetic imaging","","A novel deep learning method is proposed for tumor margin identification in electromagnetic imaging to support more accurate tumor removal surgery. The approach segments electromagnetic images into tumor and normal regions, formulated from a perspective related to electromagnetic image reconstruction. A recurrent auto-encoder network architecture called DeepTMI is introduced, with performance evaluated on reconstructed images from an experimental tissue-mimicking phantom. Results using SSIM and MSE show substantially improved segmentation over a conventional backpropagation baseline.",{"@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/deep-learning-for-tumor-margin-identification-in-electromagnetic-imaging/382838/",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/deep-learning-for-tumor-margin-identification-in-electromagnetic-imaging/382838.png","ImageObject",300,407,{"name":42,"@type":43},"Cart","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-24",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},"What problem does DeepTMI address in electromagnetic imaging?","Question",{"text":63,"@type":64},"It identifies tumor margins by segmenting electromagnetic images into tumor and normal regions to aid surgeons before or during excision.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is the tumor margin boundary determined in the proposed method?",{"text":68,"@type":64},"The method requires identifying the border between normal and tumor tissue, achieved through learned image segmentation into two regions.",{"name":70,"@type":61,"acceptedAnswer":71},"How was the method evaluated and how did it compare to a baseline?",{"text":72,"@type":64},"Effectiveness was demonstrated by segmenting reconstructed images of an experimental phantom; DeepTMI achieved average SSIM around 0.94 and MSE around 0.04, outperforming the conventional backpropagation method.","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},382838,1790822565,{"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":123,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144},18829141979164,"https://eur-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDeep learning for tumor margin identification in electromagnetic imaging  \nAmir Mirbeik1,2 & Negar Ebadi2,3*  \nIn this work, a novel method for tumor margin identification in electromagnetic imaging is proposed to optimize the tumor removal surgery. This capability will enable the visualization of the border of the cancerous tissue for the surgeon prior or during the excision surgery. To this end, the border between the normal and tumor parts needs to be identified. Therefore, the images need to be segmented into tumor and normal areas. We propose a deep learning technique which divides the electromagnetic images into two regions: tumor and normal, with high accuracy. We formulate deep learning from a perspective relevant to electromagnetic image reconstruction. A recurrent auto-encoder network architecture (termed here DeepTMI) is presented. The effectiveness of the algorithm is demonstrated by segmenting the reconstructed images of an experimental tissue-mimicking phantom. The structure similarity measure (SSIM) and mean-square-error (MSE) average of normalized reconstructed results by the DeepTMI method are about 0.94 and 0.04 respectively, while that average obtained from the conventional backpropagation (BP) method can hardly overcome 0.35 and 0.41 respectively.  \nSurgical resection is the mainstream treatment for solid tumors (tissues that normally do not contain cysts or liquid areas). The resected specimens are sent to pathology for evaluation and subsequently an additional piece of tissue is removed if cancer is observed in the margins ofthe resected pieces. In this procedure, sampling error may be present as less than 2% of the total sample is normally examined microscopically due to tissue processing and sectioning1. Therefore, the presence of tumor at the margins is sometimes underestimated or even missed. On the other hand, often times some normal tissue is unnecessarily removed during surgery. Since lesions generally occur on sun-exposed body parts, for instance the face, minimizing tissue loss is important for improving the quality of life of cancer patients.  \nHowever, the current methods to distinguish malignant from healthy tissue are primarily limited to tactile and visual cues as well as the surgeon’s experience. As a result, a positive surgical margin or the presence of residual tumor may be left behind after resection. It is well-documented that the presence of residual tumor can negatively impact treatment outcomes and survival, as well as pose an economic burden2.  \nImaging techniques would be highly valuable in assisting surgeons to identify tumor margins pre-or intraoperatively to evaluate the remainder of the resected lesion on the body. Several non-invasive imaging tools such as neuro-navigation, magnetic resonance imaging (MRI), ultrasound (US), Raman spectroscopy (RS), and optical fluorescence imaging (FLI) have been developed for this purpose3–14. However, they each have limitations on their uses and provide optimal outcomes only under certain conditions. No imaging tool has been widely adopted in the clinics. There is a definite need for an imaging tool that could visualize tumor profiles with sufficient contrasts throughout the depth of the skin at an affordable cost.  \nIn Ref.15, the authors developed a high-resolution millimeter-wave imaging (HR-MMWI) system for earlystage detection of skin cancer. In-vivo measurements of more than 136 cancerous and benign skin lesions were performed. In particular, the diagnosis of skin lesions with clinical interest, i.e., cancer/precancer versus benign lesions, was concerned. The findings established that real-time millimeter-wave imaging can distinguish between malignant tissues and benign skin lesions with high diagnostic accuracy (97% sensitivity and 98% specificity) . As the next step, the capability of the system in identifying tumor margins pre-or intra-operatively needs ","cbCaieXNd6kLLmK3","https://ap.wps.com/l/cbCaieXNd6kLLmK3","pdf",1561869,"English","# Introduction\n## Motivation and clinical need\n## Limitations of existing approaches\n## Electromagnetic imaging and prior work","[{\"question\":\"What problem does DeepTMI address in electromagnetic imaging?\",\"answer\":\"It identifies tumor margins by segmenting electromagnetic images into tumor and normal regions to aid surgeons before or during excision.\"},{\"question\":\"How is the tumor margin boundary determined in the proposed method?\",\"answer\":\"The method requires identifying the border between normal and tumor tissue, achieved through learned image segmentation into two regions.\"},{\"question\":\"How was the method evaluated and how did it compare to a baseline?\",\"answer\":\"Effectiveness was demonstrated by segmenting reconstructed images of an experimental phantom; DeepTMI achieved average SSIM around 0.94 and MSE around 0.04, outperforming the conventional backpropagation method.\"}]","Deep learning for tumor margin identification in electromagnetic imaging | PDF",1790252625,25]