[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-330192-105":59,"doc-detail-330192-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","a-3d-lung-lesion-variational-autoencoder","A 3D lung lesion variational autoencoder","","A 3D beta variational autoencoder (beta-VAE) is developed to reconstruct lung nodule images from unlabeled CT datasets and to learn lesion-relevant representations for downstream prediction. The approach addresses limitations of conventional radiomics and label-dependent supervised CNNs by using unsupervised reconstruction and embedding learning. Reconstructions achieve high fidelity, latent embeddings correlate with lesion size, and the model can synthesize lesions with varying sizes. It also predicts clinical endpoints such as pathological N stage and KRAS mutation status on a radiogenomics dataset.",{"@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/a-3d-lung-lesion-variational-autoencoder/330192/",{"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/a-3d-lung-lesion-variational-autoencoder/330192.png","ImageObject",300,407,{"name":92,"@type":93},"Anda","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-28","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 3D beta-VAE address in lung cancer imaging analysis?","Question",{"text":113,"@type":114},"Conventional radiomics is limited by fixed, less adaptable features, and supervised CNNs often require labeled data. The beta-VAE reconstructs and encodes lung nodules from unlabeled CT to support multiple tasks.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the model learn lesion information from CT scans?",{"text":118,"@type":114},"The autoencoder reconstructs 3D lung nodule volumes and embeds lesion characteristics into a latent space. Lesion size shows a significant correlation with the learned embeddings.",{"name":120,"@type":111,"acceptedAnswer":121},"What clinical outcomes can the beta-VAE help predict?",{"text":122,"@type":114},"The model can predict clinical endpoints including pathological N stage and KRAS mutation status, and it performs competitively compared with other methods on the referenced radiogenomics dataset.","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},330192,1790083672,{"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},962075006959,"https://ap-avatar.wpscdn.com/avatar/e0002397efbe92a78e?_k=1776741047341049297","Article  \nA 3D lung lesion variational autoencoder  \nGraphical abstract Authors  \n\n| The Training of the beta-Variational AutoEncoder Image Reconstruction: SSIM = 0.77\u003Cbr>beta-VAE Training Pipeline\u003Cbr>\u003Cbr>3D Lung Lesion Volume\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>Standard Mean\u003Cbr>Deviation\u003Cbr>Re para met ri zat ion\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>Latent  Feature\u003Cbr>\u003Cbr>\u003Cbr>Bottleneck layer\u003Cbr>\u003Cbr>Reconstructed 3D Volume\u003Cbr>\u003Cbr>\u003Cbr>Original Image Reconstructed Image\u003Cbr>Latent Embedding Extracted by beta-VAE Encoding Lesion Characteristics Like Size Synthetic Image by Manipulating Size Difference Vector |\n| --- |\n| \u003Cbr>|\n| \u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>\u003Cbr>Standard Deviation\u003Cbr>\u003Cbr>\u003Cbr>Binary Prediction |\n\nYiheng Li, Christoph Y. Sad´ee, Francisco Carrillo-Perez,  \nHeather M. Selby, Alexander H. Thieme, Olivier Gevaert  \nCorrespondence  \n[ogevaert@stanford.edu](ogevaert@stanford.edu)  \nIn brief  \nIn this study, Li et al. present a 3D beta variational autoencoder (beta-VAE) that reconstructs lung nodule images from CT scans and predicts key clinical outcomesin lung cancer. The model paves the way for enhanced patient outcome prediction.  \nHighlights  \nd A 3D beta-VAE reconstructs lung lesion volumes with high accuracy  \nd The model encodes lesion size in its latent embeddingsd The beta-VAE synthesizes varying lesion size effectively d It predicts clinical endpoints like N stage and KRAS mutations  \nLi et al., 2024, Cell Reports Methods 4, 100695 February 26, 2024 ª 2024 The Authors.  \n[https://doi.org/10.1016/j.crmeth.2024.100695](https://doi.org/10.1016/j.crmeth.2024.100695)  \nll  \nll  \nOPEN ACCESS  \nArticle  \nA 3D lung lesion variational autoencoder  \nYiheng Li,1,4 Christoph Y. Sad´ee,1 Francisco Carrillo-Perez,1,2 Heather M. Selby,1 Alexander H. Thieme,1 and Olivier Gevaert1,3,*  \n1Stanford Center for Biomedical Informatics Research (BMIR), Department of Medicine, Stanford University, Stanford, CA 94305, USA  \n2Department of Architecture and Computer Technology (ATC), University of Granada, C. Periodista Daniel Saucedo Aranda, s/n, Granada, 18014 Granada, Spain  \n3Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA  \n4Lead contact  \n*Correspondence: [ogevaert@stanford.edu](ogevaert@stanford.edu)[ ](ogevaert@stanford.edu)[https://doi.org/10.1016/j.crmeth.2024.100695](https://doi.org/10.1016/j.crmeth.2024.100695)  \nMOTIVATION Conventional radiomics approaches are hindered by their predefined nature and a lack of adaptability to different applications. Furthermore, the supervised convolutional neural network model (CNN) often used relies heavily on labeled data. Here, we developed a 3D beta variational autoencoder (beta-VAE) to advance lung cancer imaging analysis that efficiently reconstructs and encodes lung nodule images from unlabeled CT datasets. This unsupervised model can capture features relevant for multiple downstream tasks and has potential as a pretrained model for predicting patient outcomes in medical imaging.  \nSUMMARY  \nIn this study, we develop a 3D beta variational autoencoder (beta-VAE) to advance lung cancer imaging analysis, countering the constraints of conventional radiomics methods. The autoencoder extracts information from public lung computed tomography (CT) datasets without additional labels. It reconstructs 3D lung nodule images with high quality (structural similarity: 0.774, peak signal-to-noise ratio: 26.1, and meansquared error: 0.0008) . The model effectively encodes lesion sizes in its latent embeddings, with a significant correlation with lesion size found after applying uniform manifold approximation and projection (UMAP) for dimensionality reduction. Additionally, the beta-VAE can synthesize new lesions of varying sizes by manipulating the latent features. The model can predict multiple clinical endpoints, including pathological N stage or KRAS mutation status, on the Stanford radiogenomics lung cancer dataset. Comparisons with other methods show that the beta-VAE performs equally well in these tasks,","cbCain0yEa3e5rCL","https://ap.wps.com/l/cbCain0yEa3e5rCL","pdf",4518854,15,"English","# Motivation\n# Summary\n# Introduction","[{\"question\":\"What problem does the 3D beta-VAE address in lung cancer imaging analysis?\",\"answer\":\"Conventional radiomics is limited by fixed, less adaptable features, and supervised CNNs often require labeled data. The beta-VAE reconstructs and encodes lung nodules from unlabeled CT to support multiple tasks.\"},{\"question\":\"How does the model learn lesion information from CT scans?\",\"answer\":\"The autoencoder reconstructs 3D lung nodule volumes and embeds lesion characteristics into a latent space. Lesion size shows a significant correlation with the learned embeddings.\"},{\"question\":\"What clinical outcomes can the beta-VAE help predict?\",\"answer\":\"The model can predict clinical endpoints including pathological N stage and KRAS mutation status, and it performs competitively compared with other methods on the referenced radiogenomics dataset.\"}]","A 3D lung lesion variational autoencoder | PDF",1789987595,38]