[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-363928-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-363928-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-and-radiomics-models-in-patients-with-advanced-non-small-cell-lung-cancer-treated-with-immunotherapy-combined-with-stereotactic-radiotherapy","Deep learning and radiomics models in patients with advanced non-small cell lung cancer treated with immunotherapy combined with stereotactic radiotherapy","","Quantitative imaging is used to predict oncological outcomes. The study evaluates whether radiomics and deep learning predict outcomes in metastatic non-small cell lung cancer using randomized PD-1 inhibitor trials combined with stereotactic ablative body radiotherapy (PEMBRO-RT, NIVORAD, and MDACC). A radiomics random forest shows lower discriminative performance than deep learning for per-lesion progressive disease, while clinical features improve radiomics-based survival models. External validation reduces performance, indicating reduced generalizability and need for methods supporting clinical translation.",{"@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/deep-learning-and-radiomics-models-in-patients-with-advanced-non-small-cell-lung-cancer-treated-with-immunotherapy-combined-with-stereotactic-radiotherapy/363928/",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-and-radiomics-models-in-patients-with-advanced-non-small-cell-lung-cancer-treated-with-immunotherapy-combined-with-stereotactic-radiotherapy/363928.png","ImageObject",300,407,{"name":42,"@type":43},"awa","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","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 is the main goal of the study?","Question",{"text":63,"@type":64},"To determine whether radiomics and deep learning can predict outcomes in metastatic non-small cell lung cancer treated with immunotherapy combined with stereotactic ablative body radiotherapy.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which trials were used to develop and validate the models?",{"text":68,"@type":64},"The radiomics model was developed on PEMBRO-RT, and validation was performed on NIVORAD and MDACC.",{"name":70,"@type":61,"acceptedAnswer":71},"How do radiomics and deep learning compare for predicting per-lesion progression?",{"text":72,"@type":64},"For per-lesion progressive disease, the radiomics random forest shows lower predictive performance than the deep learning model on the development cohort.","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},363928,1791070093,{"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":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,"preview_page_count":33,"preview_urls":145},3985747858093,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDeep learning and radiomics models in patients with advanced non-small cell lung cancer treated with immunotherapy combined with stereotactic radiotherapy  \nG. Kothari1,2􀀍, N. Hardcastle2,3,4, R. Perera5,6, P. Jackson2,3, S. Lee7, J. D. Silver8,  \nM. Gaudreault2,3, J. Li2,6, C. Brown9,10, P. L. R. Mitchell11, T. Kron2,3,4, J. W. Welsh12,  \nW. S. M. E. Theelen13,14 & S. Siva1,2,14  \nQuantitative imaging is an emerging field that may allow prediction of oncological outcomes. We investigate whether radiomics and deep learning can predict outcomes in metastatic non-small cell lung cancer utilizing randomized trials of PD-1 inhibitors + /− stereotactic ablative body radiotherapy:  \nPEMBRO-RT(NCT02492568), NIVORAD(ACTRN12616000352404) and MDACC(NCT02444741) . A random forest model developed on PEMBRO-RT using radiomics features had anAUC of 0.57 for prediction of per-lesion progressive disease on immunotherapy compared to anAUC of 0.92 for a deep learning model. A random forest survival model using radiomics features for overall survival (progression free survival) had a concordance index of 0.63(0.59) and improved to 0.67(0.65) by adding clinical features, including PD-L1 and treatment arm. Validation on NIVORAD and MDACC revealed reduced AUCs. Overall, a deep learning compared to a radiomics model demonstrated excellent predictive value for per-lesion progressive disease for patients on immunotherapy. Models had reduced performance on external validation. Research improving generalizability is required for clinical translation.  \nKeywords Lung cancer, Non-small cell lung cancer, Radiomics, Deep learning, Immunotherapy, Stereotactic ablative body radiotherapy  \nImmunotherapy has profoundly changed the treatment landscape for patients with early stage and metastatic cancers. For patients with metastatic non-small cell lung cancer (NSCLC), immune checkpoint inhibitors (ICI)(including PD-1, PD-L1 and CTLA-4 inhibitors) alone or combined with chemotherapy is considered standard of care for first-line metastatic NSCLC. Durable benefits from ICI, however, are experienced by a minority of patients1, leading to studies exploring strategies to augment the effects of ICI through treatment combinations such as with stereotactic ablative body radiotherapy (SABR)2,3.  \n1Division of Radiation Oncology, Peter MacCallum Cancer Centre, 305 Grattan St, Melbourne, VIC 3000, Australia.  \n2The Sir Peter MacCallum Department of Oncology, University of Melbourne, Melbourne, VIC, Australia.  \n3Department of Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia. 4Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW, Australia. 5School of Electrical, Mechanical and Infrastructure Engineering, University of Melbourne, Melbourne, VIC 3010, Australia. 6Division of Cancer Research, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia. 7Department of Cancer Imaging, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia. 8Statistical Consulting Centre, School of Mathematics and Statistics, University of Melbourne, Melbourne, VIC, Australia. 9Northern Sydney Cancer Centre, Radiation Oncology Unit, Royal North Shore Hospital, St Leonards, Sydney, NSW, Australia. 10National Health and Medical Research Council, Clinical Trials Centre, The University of Sydney, Sydney, NSW, Australia. 11Department of Medical Oncology, Olivia Newton John Cancer Centre, Austin Health, VIC, Australia. 12Department of Thoracic Radiation Oncology, The University of Texas MD Anderson Cancer Center, Houston, TX, USA. 13Department of Thoracic Oncology, Netherlands Cancer Institute, Amsterdam, The Netherlands. 14These authors jointly supervised this work: W. S. M. ETheelen and S. Siva. 􀀍 [email: Gargi.Kothari@petermac.org](email: Gargi.Kothari@petermac.org)  \nPre-clinical and clinical data suggests that radiotherapy can enhance immunity by releasing tumor anti","cbCaiuafIHemNJIE","https://ap.wps.com/l/cbCaiuafIHemNJIE","pdf",1746023,"English","# Study objective and rationale\n## Trials and datasets used for prediction\n## Model comparison: radiomics vs deep learning\n## Survival analysis and added clinical features\n## External validation and generalizability","[{\"question\":\"What is the main goal of the study?\",\"answer\":\"To determine whether radiomics and deep learning can predict outcomes in metastatic non-small cell lung cancer treated with immunotherapy combined with stereotactic ablative body radiotherapy.\"},{\"question\":\"Which trials were used to develop and validate the models?\",\"answer\":\"The radiomics model was developed on PEMBRO-RT, and validation was performed on NIVORAD and MDACC.\"},{\"question\":\"How do radiomics and deep learning compare for predicting per-lesion progression?\",\"answer\":\"For per-lesion progressive disease, the radiomics random forest shows lower predictive performance than the deep learning model on the development cohort.\"}]","Deep learning and radiomics models in patients with advanced non-small cell lung cancer treated with immunotherapy combined with stereotactic radiotherapy | PDF",1790154229,25,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f8f7f986157bf9ce564003fa9010bece.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/4c37f7117d4a099dbc67c7ee20b026f9.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d2d9d910867a886f089f8c1386598124.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c38efd5d29d06572dbbaccd30b8f821e.webp",980,1287]