[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-355095-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-355095-en":131},{"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","clinical-validation-of-lightweight-cnn-architectures-for-reliable-multi-class-classification-of-lung-cancer-using-histopathological-imaging-techniques","Clinical validation of lightweight CNN architectures for reliable multi-class classification of lung cancer using histopathological imaging techniques","","Lung cancer classification from histopathological imaging underpins earlier diagnosis and better survival outcomes, yet high-performing models can be too costly for real clinical deployment. This study validates lightweight convolutional neural network (CNN) variants for reliable multi-class lung cancer classification. Four architectures are trained and compared using data augmentation, class balancing via computed class weights, and macro-F1 early stopping with accuracy/loss/F1 curves and confusion matrices. The best model is tested across multiple random seeds with paired McNemar’s tests, demonstrating strong generalization and reduced computational cost, supporting extensible clinical decision support.",{"@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/clinical-validation-of-lightweight-cnn-architectures-for-reliable-multi-class-classification-of-lung-cancer-using-histopathological-imaging-techniques/355095/",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/clinical-validation-of-lightweight-cnn-architectures-for-reliable-multi-class-classification-of-lung-cancer-using-histopathological-imaging-techniques/355095.png","ImageObject",300,407,{"name":42,"@type":43},"Oliver","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-22",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",15,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"How was model performance compared across the lightweight CNN variants?","Question",{"text":63,"@type":64},"Four CNN architectures were evaluated in a unified framework using data augmentation, computed class weights for class balancing, and macro-F1-based early stopping. Performance was monitored with accuracy/loss/F1 curves and confusion matrices on validation and test datasets.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which lung cancer classes were used for the multi-class classification task?",{"text":68,"@type":64},"The models were trained on three histopathological classes: Lung Benign Tissue, Lung Adenocarcinoma, and Lung Squamous Cell Carcinoma.",{"name":70,"@type":61,"acceptedAnswer":71},"How did the study assess robustness and statistical significance of the best model?",{"text":72,"@type":64},"The top-performing model was evaluated across multiple random seeds, and paired McNemar’s tests were applied against competing variants to establish statistical significance.","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},355095,1790257918,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"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":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":33,"preview_urls":147},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nClinical validation of lightweight CNN architectures for reliable multi-class classification of lung cancer using histopathological imaging techniques  \nAli Raza1􀀍, Fareeha Hanif2 & Heba Abdelgader Mohammed3  \nLung cancer remains one of the leading causes of cancer-related mortality worldwide, and accurate early diagnosis plays a critical role in improving patient survival. In this study, a comparative analysis of multiple lightweight Convolutional Neural Network (CNN) variants is presented for multi-class lung cancer classification using histopathological images. Four CNN architectures were designed to systematically explore the trade-off between model complexity and classification performance. Each variant was trained and evaluated within a unified experimental framework incorporating data augmentation, class balancing via computed class weights, and a custom macro-F1-based early stopping callback to ensure stable and fair performance comparison. The models were trained on three histopathological classes, Lung Benign Tissue, Lung Adenocarcinoma, and Lung Squamous Cell Carcinoma. The training process involved automated generation of accuracy, loss, and validation F1 curves, along with confusion matrices for both validation and test datasets. To assess robustness, the best-performing model was evaluated across multiple random seeds and statistical significance was established using paired McNemar’s tests against competing variants. Among the proposed variants, one model (Lite-V2) achieved superior macro-F1 performance and demonstrated strong generalization capability on unseen test data, confirming the effectiveness of lightweight CNNs in achieving high accuracy with reduced computational cost. This work highlights the potential of custom lightweight CNN architectures for efficient and reliable lung cancer classification, offering a reproducible framework that can be extended to larger datasets or adapted for clinical diagnostic applications.  \nKeywords Lung cancer classification, Histopathological images, Lightweight CNN, Digital pathology, Multiclass classification, Computational pathology, Model optimization  \nLung cancer is one of the most prevalent and deadly cancers worldwide. Accurate diagnosis from histopathological images is critical, as different subtypes like adenocarcinoma, squamous cell carcinoma, and small cell carcinoma require distinct treatment plans. Traditionally, this analysis is performed manually by pathologists, a process that can be time-consuming and subjective. Recent advances in deep learning, particularly Convolutional Neural Networks (CNNs), have shown great potential for automating the classification of medical images. Standard deep learning models like VGG and ResNet, while accurate, are computationally very expensive. Their large size and high processing demands make them difficult to deploy in real-world clinical settings with limited resources. To address this challenge, lightweight CNN variants such as MobileNet, EfficientNet, and ShuffleNet have been developed. These models are specifically designed to be efficient, using fewer parameters and computations while maintaining high accuracy. his paper presents a comprehensive evaluation of these lightweight CNN architectures for the multi-class classification of lung cancer from histopathological images. Our goal is to identify models that offer the best balance between classification performance and computational efficiency, making automated diagnosis more feasible for practical clinical use.  \n1Department of Mathematics, University of the Punjab, Lahore, Pakistan. 2Department of Mathematics, University of Education, Vehari Campus, Vehari, Pakistan. 3Technical and Engineering Specialties Unit, Applied College, King Khalid University, Mohyel Asser, Kingdom of Saudi Arabia. 􀀍 email: [alirazaray71@gmail.com](alirazaray71@gmail.com); [alleerazza786@gmail.com](alleerazza","cbCaikeQEWAlcmF7","https://ap.wps.com/l/cbCaikeQEWAlcmF7","pdf",4773521,28,"English","# Background\n## Clinical need and diagnostic workflow\n## Digital histopathology and deep learning context\n# Methods\n## Lightweight CNN variants and experimental framework\n## Training, class balancing, and early stopping\n## Evaluation metrics and robustness testing\n# Results and significance\n## Macro-F1 performance and generalization\n## Statistical comparison and implications","[{\"question\":\"How was model performance compared across the lightweight CNN variants?\",\"answer\":\"Four CNN architectures were evaluated in a unified framework using data augmentation, computed class weights for class balancing, and macro-F1-based early stopping. Performance was monitored with accuracy/loss/F1 curves and confusion matrices on validation and test datasets.\"},{\"question\":\"Which lung cancer classes were used for the multi-class classification task?\",\"answer\":\"The models were trained on three histopathological classes: Lung Benign Tissue, Lung Adenocarcinoma, and Lung Squamous Cell Carcinoma.\"},{\"question\":\"How did the study assess robustness and statistical significance of the best model?\",\"answer\":\"The top-performing model was evaluated across multiple random seeds, and paired McNemar’s tests were applied against competing variants to establish statistical significance.\"}]","Clinical validation of lightweight CNN architectures for reliable multi-class classification of lung cancer using histopathological imaging techniques | PDF",1790115962,71,[148,152,156,160],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ca23e404ce2a87b33ba9e21beb8b6d69.webp",983,1291,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/7c6836b380615eabc10af198fbaa51ca.webp",982,1290,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5c965f96cad59af58ed9fc6bda5ed194.webp",981,1289,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/ac96ebb35ccba59abb88f39bc15e3623.webp",980,1287]