[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-359193-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-359193-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","multi-institutional-deep-learning-for-gtv-segmentation-and-survival-prediction-in-nasopharyngeal-carcinoma-research-article","Multi-institutional deep learning for GTV segmentation and survival prediction in nasopharyngeal carcinoma - Research Article","","Purpose: develop an automated workflow for gross tumor volume (GTV) segmentation on radiotherapy planning CT images for nasopharyngeal carcinoma (NPC) and assess 5-year disease-free survival (DFS) predictive ability using radiomics, clinical, and combined features. Methods: 75 contrast-enhanced planning CTs were used to train SwinUNETR, UNETR, and nnU-Net with five-fold cross-validation, with 120 additional SeGrap2023 scans added for diverse cohorts. DFS used 1059 slice-wise radiomic features with LASSO-based selection and machine learning modeling. Results and conclusions emphasize improved segmentation robustness under multi-institutional training and stronger DFS prediction with integrated feature sets.",{"@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/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/multi-institutional-deep-learning-for-gtv-segmentation-and-survival-prediction-in-nasopharyngeal-carcinoma-research-article/359193/",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/multi-institutional-deep-learning-for-gtv-segmentation-and-survival-prediction-in-nasopharyngeal-carcinoma-research-article/359193.png","ImageObject",300,407,{"name":42,"@type":43},"Mia  ","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-23",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 was the main goal of the study for NPC patients?","Question",{"text":63,"@type":64},"To build an automated workflow for GTV segmentation on radiotherapy planning CT and to evaluate how well radiomics, clinical, and combined features predict 5-year DFS.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which deep learning models were trained for GTV segmentation and how was performance evaluated?",{"text":68,"@type":64},"SwinUNETR, UNETR, and nnU-Net were trained with five-fold cross-validation; segmentation performance was quantified using the Dice similarity coefficient (DSC), with internal and external testing across cohorts.",{"name":70,"@type":61,"acceptedAnswer":71},"How did domain shift affect segmentation accuracy in the external test set?",{"text":72,"@type":64},"nnU-Net achieved strong DSC on SeGrap2023-trained internal validation, but DSC dropped markedly (to around 0.36) when Acibadem cohort data were used for an external test set, indicating a significant domain shift.","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},359193,1790193294,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"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":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},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":55,"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":33,"preview_urls":146},687207024478,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Yuce etal. BMC Medical Imaging (2026) 26:154 [https://doi.org/10.1186/s12880-026-02195-5](https://doi.org/10.1186/s12880-026-02195-5)  \nBMC Medical Imaging  \nRESEARCH Open Access  \nMulti-institutional deep learning for GTV segmentation and survival prediction in nasopharyngeal carcinoma  \nMurat Yuce1,6*, Sinem B. Erdogan2, Ata Akin2, Enis Ozyar3, Gorkem Gungor3, Bora Guvendiren2, BukemTanoren4 and Seda Nilgun Dumlu5*  \nAbstract  \nPurpose To develop an automated workflow for gross tumor volume (GTV) segmentation in radiotherapy planning CT images of nasopharyngeal carcinoma (NPC) patients and to evaluate the 5-year Disease-Free Survival (DFS) predictive performance of radiomics, clinical and combined features.  \nMethods and materials Contrast-enhanced planning CTs of 75 NPC patients were collected. SwinUNETR, UNETRand nnU-Net models were trained with five-fold cross-validation; performance was quantified by Dice similarity coefficient (DSC) . Additional 120 scans from SeGrap2023 were incorporated to assess the model performanceson diverse cohorts. For DFS prediction, 1059 slice-wise radiomic features were extracted. Feature selection used univariate filtering, correlation thresholding and LASSO, followed by machine-learning modelling with radiomic, clinical and combined inputs.  \nResults The highest 5-fold cross-validation DSC performance was achieved by nnU-Net (DSC = 0 . 79) when trained and internally validated only on the SeGrap2023 dataset. However, DSC dropped to 0.36 when Acibadem cohort data were utilized for external test set, suggesting a significant effect of the domain shift. When the Acibadem and SeGrap2023 datasets were combined, nnU-Net achieved an average DSC of 0.73 in 5-fold cross-validation and 0.69 on subset of Acibadem internal test cases. In predicting 5-year DFS, a Logistic Regression model using combined radiomic and clinical features provided the highest AUC score (0 . 79), outperforming clinical-only (AUC = 0 . 59) and radiomics-only (AUC = 0 . 63) feature sets.  \nConclusions Multi-institutional training mitigates domain shift and boosts segmentation robustness. In addition, integrating radiomics with clinical data enhances DFS prediction in NPC. Advanced deep-learning and machinelearning pipelines can refine radiotherapy planning and prognostication, supporting personalized management and improved outcomes.  \nKeywords Nasopharyngeal carcinoma, Radiomics, Deep learning, Segmentation, Gross tumor volume  \n*Correspondence:  \nMurat Yuce [murat.yuce@mssm.edu](murat.yuce@mssm.edu)[ ](murat.yuce@mssm.edu)Seda Nilgun Dumlu [Seda.Dumlu@acibadem.edu.tr](Seda.Dumlu@acibadem.edu.tr)  \nFull list of author information is available at the end of the article  \n© The Author(s) 2026. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit [http://creati](http://creati)[vecommons.org/licenses/by-nc-nd/4.0/](vecommons.org/licenses/by-nc-nd/4.0/.)[.](vecommons.org/licenses/by-nc-nd/4.0/.)  \nYuce et al. BMC Medical Imaging (2026) 26:154  \nIntroduction  \nNasopharyngeal cancer (NPC) is an uncommon tumor, accounting for 87,000 ","cbCaitdRrMsEhnbT","https://ap.wps.com/l/cbCaitdRrMsEhnbT","pdf",2337950,11,"English","# Abstract\n# Purpose\n# Methods and materials\n## Segmentation models and validation\n## DFS prediction pipeline\n# Results\n# Conclusions\n# Keywords\n# Introduction\n## Epidemiology and treatment context\n## Segmentation challenges\n## Related deep learning background","[{\"question\":\"What was the main goal of the study for NPC patients?\",\"answer\":\"To build an automated workflow for GTV segmentation on radiotherapy planning CT and to evaluate how well radiomics, clinical, and combined features predict 5-year DFS.\"},{\"question\":\"Which deep learning models were trained for GTV segmentation and how was performance evaluated?\",\"answer\":\"SwinUNETR, UNETR, and nnU-Net were trained with five-fold cross-validation; segmentation performance was quantified using the Dice similarity coefficient (DSC), with internal and external testing across cohorts.\"},{\"question\":\"How did domain shift affect segmentation accuracy in the external test set?\",\"answer\":\"nnU-Net achieved strong DSC on SeGrap2023-trained internal validation, but DSC dropped markedly (to around 0.36) when Acibadem cohort data were used for an external test set, indicating a significant domain shift.\"}]","Multi-institutional deep learning for GTV segmentation and survival prediction in nasopharyngeal carcinoma - Research Article | PDF",1790136386,28,[147,151,155,159],{"page_no":22,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/74ec4c31092c197386dfb1e0d4f2057b.webp",983,1310,{"page_no":26,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3daa9735b94bf8c1afc12647d811651e.webp",982,1309,{"page_no":30,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/a49c948ec72f2490e45bd6b9f85a1b40.webp",981,1308,{"page_no":33,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7a1efa3131f97524bc2a0d3e2bbcb0cf.webp",980,1306]