[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-430559-105":59,"doc-detail-430559-en":130},{"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":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","predicting-lung-cancer-survival-with-attention-based-ct-slices-combination","Predicting lung cancer survival with attention-based CT slices combination","","Accurate prognosis of Non-Small Cell Lung Cancer (NSCLC) is crucial for improving patient care, yet overall survival prediction has not fully leveraged deep learning advances. This study proposes a novel approach to predict 2-year overall survival from CT scans by combining EfficientNetB0 CT representations with a soft-attention mechanism that selects relevant slices, followed by a risk-assessment network. Validated on the public LUNG1 dataset and a smaller private dataset, the method outperforms benchmark 3D networks and benefits transfer learning in limited data scenarios.",{"@graph":69,"@context":122},[70,84,105],{"@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":35,"@type":76,"position":81},"https://docshare.wps.com/document/healthcare/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/predicting-lung-cancer-survival-with-attention-based-ct-slices-combination/430559/",{"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/predicting-lung-cancer-survival-with-attention-based-ct-slices-combination/430559.png","ImageObject",300,407,{"name":92,"@type":93},"Jacob","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-04","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the study’s main goal in NSCLC prognosis?","Question",{"text":112,"@type":113},"To predict 2-year overall survival (OS) in NSCLC patients using CT scans with an attention-based slice selection strategy.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method use CT information?",{"text":117,"@type":113},"It extracts CT scan representations with EfficientNetB0, applies a soft attention mechanism to identify the most relevant slices, and then feeds them into a risk-assessment network.",{"name":119,"@type":110,"acceptedAnswer":120},"What datasets and comparisons were used to validate performance?",{"text":121,"@type":113},"The method was validated on the public LUNG1 dataset and a smaller private dataset, compared against benchmark 3D networks and variants, and transfer learning was evaluated on the private dataset.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},430559,1790762764,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":34,"category_name":35,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":36,"preview_page_count":4},962084931830,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Paolo et al.  \nHealth Information Science and Systems (2026) 14:20  \n[https://doi.org/10.1007/s13755-025-00404-z](https://doi.org/10.1007/s13755-025-00404-z)  \nHealth Information Science and Systems  \nRESEARCH  \nPredicting lung cancer survival    \nwith attention-based CT slices combination  \nDomenico Paolo1, Carlo Greco5,6, Edy Ippolito5,6, Michele Fiore5,6, Sara Ramella5,6, Paolo Soda1,3* , Matteo Tortora2, Alessandro Bria4 and Rosa Sicilia1  \nAbstract  \nAccurate prognosis of Non-Small Cell Lung Cancer (NSCLC) is crucial for enhancing patient care and treatment outcomes. Despite the advancements in deep learning, the task of overall survival prediction in NSCLC has not fully leveraged these techniques, yet. This study introduces a novel methodology for predicting 2-year overall survival (OS) in NSCLC patients using CT scans. Our approach integrates CT scan representations produced by EfficientNetB0 with a soft attention mechanism to identify the most relevant slices for survival risk prediction, which are then analyzed by a risk-assessment network. To validate our method and ensure reproducibility, we employed the public LUNG1 dataset and a smaller private dataset. Our approach was compared to benchmark 3D networks and two variants of our methodology: on the LUNG1 it outperformed the competitors achieving a mean 􀀞􀀝-index of 0.584 over tenfold crossvalidation. On the LUNG1 we also demonstrated the adaptability of our method with 5 other 2D backbones replacing the EfficientNetB0, confirming that our mechanism of combining 2D slice representations to construct a 3D volume representation is more effective for OS prediction compared to a traditional 3D approach. Finally, we used transfer learning on the private dataset, showing that it can significantly enhance performance in limited data scenarios, increasing the 􀀞􀀝-index by 0.076 compared to model without transfer learning.  \nKeywords: Deep learning, Non-small cell lung cancer, Overall survival, Risk analysis, Soft-attention  \nIntroduction  \nLung cancer remains one of the leading causes of cancerrelated mortality worldwide, making early diagnosis and accurate prognosis critical for improving patient outcomes [1]. Computed tomography (CT) is the standard imaging modality for lung cancer detection and monitoring, providing high-resolution, volumetric information about tumor morphology and surrounding tissues. CT imaging is widely available in clinical practice and offers detailed structural insights that are essential for treatment planning and disease progression assessment.  \nIntegrating artificial intelligence (AI), and in particular deep learning methods, into CT imaging analysis has the potential to further enhance clinical decision-making. Convolutional neural networks (CNNs) have become  \n*Correspondence: [paolo.soda@umu.se](paolo.soda@umu.se)  \n3 Department of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, Umeå, Sweden  \nFull list of author information is available at the end of the article  \nthe backbone of state-of-the-art approaches for medical image analysis, enabling automated detection, segmentation, and characterization of lung lesions [2–4]. The increasing availability of annotated CT datasets has facilitated the development of models capable of assisting radiologists and clinicians in diagnosis and prognosis.  \nDespite these advancements, predicting overall survival (OS) from CT images remains challenging. OS prediction involves estimating the likelihood that a patient will survive over a defined timeframe and requires capturing subtle imaging patterns correlated with patient outcomes. Developing models for OS prediction is difficult due to the high computational demands and extensive data required to process complex medical images like CT scans [5] . These models often exhibit limited generalization capability due to the inherent variability in medical images, particularly when applied across different institutions and e","cbCaiaWmJGV5DH3T","https://ap.wps.com/l/cbCaiaWmJGV5DH3T","pdf",2287162,16,"English","# Abstract\n# Introduction\n## Imaging role in lung cancer prognosis\n## Limits of current OS prediction\n## Proposed attention-based CT approach","[{\"question\":\"What is the study’s main goal in NSCLC prognosis?\",\"answer\":\"To predict 2-year overall survival (OS) in NSCLC patients using CT scans with an attention-based slice selection strategy.\"},{\"question\":\"How does the proposed method use CT information?\",\"answer\":\"It extracts CT scan representations with EfficientNetB0, applies a soft attention mechanism to identify the most relevant slices, and then feeds them into a risk-assessment network.\"},{\"question\":\"What datasets and comparisons were used to validate performance?\",\"answer\":\"The method was validated on the public LUNG1 dataset and a smaller private dataset, compared against benchmark 3D networks and variants, and transfer learning was evaluated on the private dataset.\"}]","Predicting lung cancer survival with attention-based CT slices combination | PDF",1790653151]