[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-626796-105":3,"detail-sidebar-cat-0-en-105":80,"doc-detail-626796-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":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","radiomics-feature-analysis-and-model-research-for-predicting-histopathological-subtypes-of-non-small-cell-lung-cancer-on-ct-images-a-multi-dataset-study","Radiomics feature analysis and model research for predicting histopathological subtypes of non-small cell lung cancer on CT images - A multi-dataset study","","Classifying histopathological subtypes of non-small cell lung cancer is critical for selecting optimal treatments, yet current confirmation relies on invasive biopsy or postoperative examination. This multi-dataset study extracted CT radiomics features and built models to distinguish adenocarcinoma and squamous cell carcinoma with strong generalization. A multi-center cohort of 868 patients and 1409 VOI features supported feature selection and comparative evaluation across training, test, and independent TCGA/lung3 sets.",{"@graph":14,"@context":72},[15,34,55],{"@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/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/radiomics-feature-analysis-and-model-research-for-predicting-histopathological-subtypes-of-non-small-cell-lung-cancer-on-ct-images-a-multi-dataset-study/626796/",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/radiomics-feature-analysis-and-model-research-for-predicting-histopathological-subtypes-of-non-small-cell-lung-cancer-on-ct-images-a-multi-dataset-study/626796.png","ImageObject",300,407,{"name":42,"@type":43},"Indoniesian Boy","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-10","2026-10-20",true,{"@type":52,"interactionType":53,"userInteractionCount":26},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"What problem does the study address?","Question",{"text":62,"@type":63},"It targets non-invasive prediction of histopathological subtypes of non-small cell lung cancer by distinguishing adenocarcinoma from squamous cell carcinoma using CT radiomics features and models.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"How were the CT radiomics features extracted and selected?",{"text":67,"@type":63},"A total of 1409 features were extracted from the tumor VOI, then ℓ2,1-norm minimization was used for feature selection and to analyze feature importance.",{"name":69,"@type":60,"acceptedAnswer":70},"Which model showed the best generalization performance?",{"text":71,"@type":63},"The Bagging-AdaBoost-SVM model achieved the highest AUC and demonstrated stronger generalization across the three test sets, outperforming other ensemble and non-ensemble algorithms.","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},626796,1792683164,{"code":4,"msg":81,"data":82},"success",[83,87,91,95,100,105,109,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":84,"show_sort_weight":85,"slug":86},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":92,"show_sort_weight":93,"slug":94},"Exam",70,"exam",{"id":96,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},5,"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":107,"slug":108},7,40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",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":96,"slug":129},19,"General","general",{"code":4,"msg":81,"data":131},{"doc_id":78,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":106,"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":26,"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":4},962090760608,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Received: 11 June 2021 Revised: 9 January 2023 Accepted: 9 January 2023  \nDOI: 10.1002/mp.16233  \nRESEARCH ARTICLE  \nRadiomics feature analysis and model research for predicting histopathological subtypes of non-small cell lung cancer on CT images: A multi-dataset study  \nFan Song1  Peng Zhang1  \nXiao Song2  Jinkai Li3  \n Youdan Feng1  Guangda Fan1  Fei Liu4  Guanglei Zhang1  \nYangyang Sun1  \n1 Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing, China  \n2 School of Medical Imaging, Shanxi Medical University, Taiyuan, China  \n3 School of General Engineering, Beihang University, Beijing, China  \n4 Beijing Advanced Information & Industrial Technology Research Institute, Beijing Information Science & Technology University, Beijing, China  \nCorrespondence  \nGuanglei Zhang, Beijing Advanced Innovation Center for Biomedical Engineering, School of Biological Science and Medical Engineering, Beihang University, Beijing 100191, China. [Email:](Email: guangleizhang@buaa.edu.cn)[ guangleizhang@buaa.edu.cn](Email: guangleizhang@buaa.edu.cn)  \nFunding information  \nBeijing Natural Science Foundation, Grant/Award Number: 7202102; National Natural Science Foundation of China, Grant/Award Number: 61871022; Fundamental Research Funds for Central Universities; 111 Project, Grant/Award Number: B13003  \nAbstract  \nPurpose: Classifying the subtypes of non-small cell lung cancer (NSCLC) is essential for clinically adopting optimal treatment strategies and improving clinical outcomes, but the histological subtypes are confirmed by invasive biopsy or post-operative examination at present. Based on multi-center data, this study aimed to analyze the importance of extracted CT radiomics features and develop the model with good generalization performance for precisely distinguishing major NSCLC subtypes:adenocarcinoma (ADC) and squamous cell carcinoma (SCC) .  \nMethods: We collected a multi-center CT dataset with 868 patients from eight international databases on the cancer imaging archive (TCIA) . Among them, patients from five databases were mixed and split to training and test sets (560:140). The remaining three databases were used as independent test sets: TCGA set (n = 97) and lung3 set (n = 71) . A total of 1409 features containing shape, intensity, and texture information were extracted from tumor volume of interest (VOI), then the ℓ2,1-norm minimization was used for feature selection and the importance of selected features was analyzed. Next, the prediction and generalization performance of 130 radiomics models (10 common algorithmsand 120 heterogeneous ensemble combinations) were compared by the average AUC value on three test sets. Finally, predictive results of the optimal model were shown.  \nResults: After feature selection, 401 features were obtained. Features of intensity, texture GLCM, GLRLM, and GLSZM had higher classification weight coefficients than other features (shape, texture GLDM, and NGTDM), and the filtered image features exhibited significant importance than original image features (p-value = 0 .0210) . Moreover,five ensemble learning algorithms (Bagging, AdaBoost, RF, XGBoost, GBDT) had better generalization performance (p-value = 0.00418) than other non-ensemble algorithms (MLP, LR, GNB, SVM, KNN) . The Bagging-AdaBoost-SVM model had the highest AUC value (0 .815 ± 0.010) on three test sets. It obtained AUC values of 0 .819, 0 .823, and 0.804 on test set, TCGA set and lung3 set, respectively.  \nConclusion: Our multi-dataset study showed that intensity features, texture features (GLCM, GLRLM, and GLSZM) and filtered image features were more important for distinguishing ADCs from SCCs. The method of  \nFan Song and Xiao Song contributed equally to this work.  \nMed Phys. 2023;50:4351–[4365.](4365. wileyonlinelibrary.com/journal/mp)[ wileyonlinelibrary.com/journal/mp](4365. wileyonlinelibrary.com/journal/mp) © 2023 American Association of Physicist","cbCaiqJdrDjm8XxN","https://ap.wps.com/l/cbCaiqJdrDjm8XxN","pdf",1896915,15,"English","# Abstract\n# Introduction\n## Clinical need and limitations of invasive diagnosis\n# Methods\n## Multi-center CT dataset and preprocessing\n## Radiomics feature extraction and selection\n## Model training and evaluation across datasets\n# Results\n## Selected features and discriminative feature groups\n## Ensemble vs non-ensemble model performance\n# Conclusion\n## Key predictive features and generalization value","[{\"question\":\"What problem does the study address?\",\"answer\":\"It targets non-invasive prediction of histopathological subtypes of non-small cell lung cancer by distinguishing adenocarcinoma from squamous cell carcinoma using CT radiomics features and models.\"},{\"question\":\"How were the CT radiomics features extracted and selected?\",\"answer\":\"A total of 1409 features were extracted from the tumor VOI, then ℓ2,1-norm minimization was used for feature selection and to analyze feature importance.\"},{\"question\":\"Which model showed the best generalization performance?\",\"answer\":\"The Bagging-AdaBoost-SVM model achieved the highest AUC and demonstrated stronger generalization across the three test sets, outperforming other ensemble and non-ensemble algorithms.\"}]","Radiomics feature analysis and model research for predicting histopathological subtypes of non-small cell lung cancer on CT images - A multi-dataset study | PDF",1792540643,38]