[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-331457-105":59,"doc-detail-331457-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","enhanced-wgan-model-for-diagnosing-laryngeal-carcinoma-research-article","Enhanced WGAN Model for Diagnosing Laryngeal Carcinoma - Research Article","","This study modifies the U-Net architecture for pixel-based segmentation to automatically classify lesions in laryngeal endoscopic images. The enhanced U-Net uses a five-level encoder-decoder structure with an autoencoder layer to extract latent image representations. A WGAN is introduced to mitigate mode collapse and gradient explosion commonly observed in traditional GANs. Using 8171 polygon-labeled images in seven colors, evaluation via F1 score and intersection over union shows cancer detection with notably high accuracy and an overall 99% performance, supporting earlier diagnosis and reduced diagnostic error.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/enhanced-wgan-model-for-diagnosing-laryngeal-carcinoma-research-article/331457/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/enhanced-wgan-model-for-diagnosing-laryngeal-carcinoma-research-article/331457.png","ImageObject",300,407,{"name":92,"@type":93},"Sage","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the enhanced U-Net + WGAN approach target in laryngeal endoscopy?","Question",{"text":113,"@type":114},"It targets accurate pixel-level segmentation and lesion classification in laryngeal endoscopic images while improving model stability by addressing common GAN training issues such as mode collapse and gradient explosion.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How is the dataset prepared for training and evaluation?",{"text":118,"@type":114},"The dataset contains 8171 endoscopic images labeled with polygons in seven colors, and the model is evaluated using metrics including F1 score and intersection over union (IoU).",{"name":120,"@type":111,"acceptedAnswer":121},"What detection performance does the model achieve?",{"text":122,"@type":114},"The model reports strong results for malignant tumors and an overall accuracy rate of 99%, with benign tumors showing comparatively lower accuracy.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},331457,1790108194,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},687197207057,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","cancers   \nArticle  \nEnhanced WGAN Model for Diagnosing Laryngeal Carcinoma  \nSungjin Kim 1, Yongjun Chang 1, Sungjun An 1, Deokseok Kim 2, Jaegu Cho 3, Kyungho Oh 3, Seungkuk Baek 3 and Bo K. Choi 2, *  \nCitation: Kim, S.; Chang, Y.; An, S.; Kim, D.; Cho, J.; Oh, K.; Baek, S.; Choi, B.K. Enhanced WGAN Model for Diagnosing Laryngeal Carcinoma. Cancers 2024, 16, 3482. [https://](https://)[ ](https://)[doi.org/10.3390/cancers16203482](doi.org/10.3390/cancers16203482)  \nAcademic Editor: Michiel Wilhelmus Maria van den Brekel  \nReceived: 2 September 2024  \nRevised: 3 October 2024  \nAccepted: 9 October 2024  \nPublished: 14 October 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Department of Artificial Intelligence, Cheju Halla University, Jeju 63092, Republic of Korea; [r3dzon3@chu.ac.kr](r3dzon3@chu.ac.kr) (S.K.); [yongnjin@chu.ac.kr](yongnjin@chu.ac.kr) (Y.C.); [sjan2020@chu.ac.kr](sjan2020@chu.ac.kr) (S.A.)  \n2 Research Lab, MTEG, Seoul 03920, Republic of Korea; [laurent@mteg.co.kr](laurent@mteg.co.kr)  \n3 Department of Otolaryngology-Head and Neck Surgery, Korea University College of Medicine, Seoul 02841, Republic of Korea; [jgcho@korea.ac.kr](jgcho@korea.ac.kr) (J.C.); [ohkyungho@korea.ac.kr](ohkyungho@korea.ac.kr) (K.O.); [mdbsk@korea.ac.kr](mdbsk@korea.ac.kr) (S.B.)  \n* [Correspondence: bo@mteg.co.kr](Correspondence: bo@mteg.co.kr)  \nSimple Summary: This study aimed to enhance the accuracy of detecting laryngeal carcinoma using a modified AI model based on U-Net. The model was designed to automatically identify lesions in endoscopic images. Researchers addressed issues such as mode collapse and gradient explosion to ensure stable performance, achieving 99% accuracy in detecting malignancies. The study found that malignant tumors were detected more reliably than benign ones. This technology could help reduce human error in diagnoses, allowing for earlier detection and treatment. Furthermore, it has the potential to be applied in other medical fields, benefiting overall healthcare.  \nAbstract: This study modifies the U-Net architecture for pixel-based segmentation to automatically classify lesions in laryngeal endoscopic images. The advanced U-Net incorporates five-level encoders and decoders, with an autoencoder layer to derive latent vectors representing the image characteristics. To enhance performance, a WGAN was implemented to address common issues such as mode collapse and gradient explosion found in traditional GANs. The dataset consisted of 8171 images labeled with polygons in seven colors. Evaluation metrics, including the F1 score and intersection over union, revealed that benign tumors were detected with lower accuracy compared to other lesions, while cancers achieved notably high accuracy. The model demonstrated an overall accuracy rate of 99% . This enhanced U-Net model shows strong potential in improving cancer detection, reducing diagnostic errors, and enhancing early diagnosis in medical applications.  \nKeywords: image segmentation; laryngeal cancer; laryngoscope video; U-Net; WGAN  \n1. Introduction  \nThe larynx is essential for speech, breathing, and safeguarding the airway during swallowing. However, laryngopharyngeal cancer (LPC), including the laryngeal and hypopharyngeal cancers, is the second most prevalent malignancy in the head and neck region, responsible for over 130,000 deaths in 2020 [1] . Due to its poor prognosis, early detection and diagnosis are vital for effective treatment through diagnostic tools such as endoscopy. However, diagnosis is difficult for physicians until enough training and experience are accumulated. Besides, human visual observation of laryngeal lesions varies,","cbCaitNhWp1ERZSH","https://ap.wps.com/l/cbCaitNhWp1ERZSH","pdf",2550497,15,"English","# Introduction\n## Laryngeal cancer background and need for early diagnosis\n## Challenges in AI-based diagnosis (visual variability and open-set classification)\n# Related work and medical imaging context\n## Medical imaging modalities and deep learning approaches","[{\"question\":\"What problem does the enhanced U-Net + WGAN approach target in laryngeal endoscopy?\",\"answer\":\"It targets accurate pixel-level segmentation and lesion classification in laryngeal endoscopic images while improving model stability by addressing common GAN training issues such as mode collapse and gradient explosion.\"},{\"question\":\"How is the dataset prepared for training and evaluation?\",\"answer\":\"The dataset contains 8171 endoscopic images labeled with polygons in seven colors, and the model is evaluated using metrics including F1 score and intersection over union (IoU).\"},{\"question\":\"What detection performance does the model achieve?\",\"answer\":\"The model reports strong results for malignant tumors and an overall accuracy rate of 99%, with benign tumors showing comparatively lower accuracy.\"}]","Enhanced WGAN Model for Diagnosing Laryngeal Carcinoma - Research Article | PDF",1789993316,38]