[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-343887-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-343887-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","interpretable-survival-network-for-progression-risk-analysis-of-multimodality-imaging-biomarkers-in-poor-prognosis-head-and-neck-cancers-study","Interpretable survival network for progression risk analysis of multimodality imaging biomarkers in poor-prognosis head and neck cancers - study","","Interpretable survival network for progression risk analysis of multimodality imaging biomarkers in poor-prognosis head and neck cancers uses multi-time point, multi-modality quantitative imaging biomarkers together with clinical factors to predict local and distant failures in patients with poor-prognosis head and neck cancers. Ninety-three patients in a phase II adaptive radiation dose escalation trial underwent FDG-PET and multiparametric MRI before radiotherapy and at the 10th fraction. Expected Gradients and Expected Hessian assess feature attributions and interactions. Rigorous cross-validation yields a c-index of 0.758 for local failure and 0.695 for distant failure, supporting more personalized intensified treatment decisions.",{"@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/interpretable-survival-network-for-progression-risk-analysis-of-multimodality-imaging-biomarkers-in-poor-prognosis-head-and-neck-cancers-study/343887/",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/interpretable-survival-network-for-progression-risk-analysis-of-multimodality-imaging-biomarkers-in-poor-prognosis-head-and-neck-cancers-study/343887.png","ImageObject",300,407,{"name":42,"@type":43},"Seraphina","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-05","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",6,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"研究使用哪些成像模态和时间点来预测局部与远处失败？","Question",{"text":63,"@type":64},"研究结合多时间点与多模态成像。在放疗前以及放疗过程第10次分割（约2周）采集FDG-PET与多参数MRI，并与临床因素共同建模以预测局部（LF）与远处（DF）失败。","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"如何评估模型的可解释性与特征贡献？",{"text":68,"@type":64},"通过Expected Gradients（EG）与Expected Hessian（EH）评估特征归因与特征间交互，从而理解关键影像生物标志物及其复杂因子关系。",{"name":70,"@type":61,"acceptedAnswer":71},"局部失败与远处失败预测模型的效果如何？",{"text":72,"@type":64},"局部失败预测模型在加入如p16状态与放疗增量等生物标志物后达到ac-index 0.758；远处失败预测模型的c-index为0.695。","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},343887,1790212068,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,105,110,114,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},7,"Healthcare",40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},8,30,"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":111,"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":115,"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,"preview_page_count":33,"preview_urls":145},962075114101,"https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nInterpretable survival network for progression risk analysis of multimodality imaging biomarkers in poor-prognosis head and neck cancers  \nLise Wei􀀍, Madhava P. Aryal, Choonik Lee, Jennifer L. Shah, Michelle L. Mierzwa & Yue Cao  \nThis study explores the predictive utility of multi-time point, multi-modality quantitative imaging biomarkers (QIBs) and clinical factors in patients with poor-prognosis head and neck cancers (HNCs) using interpretable machine learning. We examined 93 patients with p16 + oropharyngeal squamous cell carcinoma or locally advanced p16-HNCs enrolled in a phase II adaptive radiation dose escalation trial. FDG-PET and multiparametric MRI scans were conducted before radiation therapy and atthe 10th fraction (2 weeks). A survival network analyzed MRI and PET-derived biomarkers such as gross tumor volume (GTV), blood volume (BV), and metabolic tumor volume (MTV50), along with clinical factors to predict local (LF) and distant failures (DF) . Feature attributions and interactions were assessed using Expected Gradients (EG) and Expected Hessian (EH). Through rigorous cross-validation, the model for predicting LF, incorporating biomarkers like p16 status and radiation boost, achieved ac-index of 0.758. Similarly, the DF prediction model showed a c-index of 0.695. The analysis of feature attributions and interactions enhanced understanding of important features and complex factor interplays, potentially guiding more personalized and intensified treatment approaches for HNC patients.  \nKeywords HNCs, Functional imaging biomarker, Interpretable machine learning  \nHead and neck squamous cell carcinomas (HNSCCs) is the sixth most common cancer worldwide, with a 30% increase expected by 20301, and primarily linked to usage of tobacco and alcohol, and human papillomavirus (HPV) infection2. The patients with HPV-associated oropharyngeal squamous cell carcinoma (OPSCC) typically exhibit a more favorable prognosis than those with non-HPV one2. Furthermore, the patients with early stage HPV-associated OPSCC have an excellent prognosis with “standard chemoradiation therapy (CRT)”3. However, up to 20% of the patients are present with advanced stage III of HPV-associated OPSCC and have high recurrence and metastasis rates. The locoregional recurrence rate is as high as 50% during the first 2 years after diagnosis in the patients with advanced HNSCCs including HPV-associated stage III OPSCC and non-HPV related HNSCCs4. The response-based adaptive intensification of CRT could improve locoregional control in the patients with local advanced poor prognosis HNSCCs.  \nMulti-modality imaging serves as a crucial tool for response assessment and for prediction of patient outcomes. Several studies of MRI and PET were carried out to explore predictive imaging biomarkers for locoregional and distant progression of HNSCC5–19. However, most of these studies are limited by their reliance on a single imaging modality and at a single time point, which could miss complementary information from different modalities, which could be particularly important in locally advanced diseases, as well as temporal dynamic responses ofthe cancer. In addition, conventional statistical methods used in most of the studies could miss interactive information from different predictors. Furthermore, characteristics and behaviors of imaging biomarkers could be substantially different between high and low risk patients for locoregional and distant progression, which are not differentiated in most of the early studies. All these together could weaken the predictive power of the model. Recently, there has been considerable growth in the use of machine learning (ML) techniques for analyzing imaging and/or clinical data in HNSCC20–24. A cox model is commonly used for multivariate time-to-event analysis, which is a semiparametric model that can calculate partial likelihood without  \nDepartme","cbCaieZaePiJkMxk","https://ap.wps.com/l/cbCaieZaePiJkMxk","pdf",1664748,"English","# Methods\n## Patients and treatment\n# Modeling approach\n## Survival network design\n## Feature attribution and interaction analysis\n# Results\n## Local failure prediction performance\n## Distant failure prediction performance\n# Discussion","[{\"question\":\"研究使用哪些成像模态和时间点来预测局部与远处失败？\",\"answer\":\"研究结合多时间点与多模态成像。在放疗前以及放疗过程第10次分割（约2周）采集FDG-PET与多参数MRI，并与临床因素共同建模以预测局部（LF）与远处（DF）失败。\"},{\"question\":\"如何评估模型的可解释性与特征贡献？\",\"answer\":\"通过Expected Gradients（EG）与Expected Hessian（EH）评估特征归因与特征间交互，从而理解关键影像生物标志物及其复杂因子关系。\"},{\"question\":\"局部失败与远处失败预测模型的效果如何？\",\"answer\":\"局部失败预测模型在加入如p16状态与放疗增量等生物标志物后达到ac-index 0.758；远处失败预测模型的c-index为0.695。\"}]","Interpretable survival network for progression risk analysis of multimodality imaging biomarkers in poor-prognosis head and neck cancers - study | PDF",1790052391,23,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/eb7ce2852266795a23607f8bda9197c6.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/dc1ad2789b68ee1a97b0f8042cf9c2bd.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f938b9e137f3ab26a32825587d4aee27.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5602a9ed621603281173d67f0a6cc113.webp",980,1287]