[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-350663-105":59,"doc-detail-350663-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","deep-learning-driven-early-detection-of-lung-cancer-from-ct-images-using-transfer-learning-approaches","Deep learning driven early detection of lung cancer from CT images using transfer learning approaches","","Lung cancer remains a leading cause of cancer-related mortality due to frequent late-stage diagnosis and reduced effectiveness of advanced-stage treatments. This study develops deep-learning methods to automatically classify lung CT images into benign, malignant, and normal categories. A full workflow covers data acquisition, preprocessing, model development, training, validation, and performance evaluation using patient-level splitting to reduce slice leakage. Among six architectures, fully fine-tuned VGG16 achieves the best accuracy and supports Grad-CAM interpretability, suggesting utility for assistive screening pending broader validation.",{"@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/deep-learning-driven-early-detection-of-lung-cancer-from-ct-images-using-transfer-learning-approaches/350663/",{"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/deep-learning-driven-early-detection-of-lung-cancer-from-ct-images-using-transfer-learning-approaches/350663.png","ImageObject",300,407,{"name":92,"@type":93},"kopisore","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-23","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the study address in lung cancer detection?","Question",{"text":112,"@type":113},"The study targets high mortality linked to late-stage diagnosis by improving early and accurate classification of lung CT images.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How is the classification task defined in the proposed approach?",{"text":117,"@type":113},"The model performs multi-class classification, labeling CT images as benign, malignant, or normal.",{"name":119,"@type":110,"acceptedAnswer":120},"Why is patient-level data splitting important in this work?",{"text":121,"@type":113},"Patient-level splitting helps prevent slice-level data leakage, making the evaluation more reliable.","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},350663,1790179352,{"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":14,"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":145},962090880963,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nDeep learning driven early detection of lung cancer from CT images using transfer learning approaches  \nVishwasV. Patange1, Jagadish B. Jadhav2, Sanjay L. Nalbalwar1 & Priyanka V. Deshmukh3  \nLung cancer remains one of the foremost causes of cancer-related mortality worldwide, primarily due to its frequent late-stage diagnosis and the limited efficacy of available treatments at advanced stages. This study seeks to advance early detection through the application of deep learning techniques for the automated classification of lung CT images into benign, malignant, and normal categories. A comprehensive methodological framework was adopted, encompassing data acquisition, preprocessing, model development, training, validation, and performance evaluation, with patientlevel data splitting employed to prevent slice-level data leakage. Among six tested architectures (VGG16, Custom CNN, MobileNetV2, ResNet50, InceptionV3, and EfficientNetB0), the fully fine-tuned VGG16 model optimized via transfer learning and trained on the IQ-OTH/NCCD lung cancer dataset exhibited the strongest overall performance, achieving a mean test accuracy of 89.39% ± 2.10%(test loss 0.329) across three independent runs, and 89.70% ± 2.75% under 5-fold patient-grouped crossvalidation. One-way ANOVA (F = 17.55, p \u003C 0.0001) followed by Tukey’s HSD post-hoc test confirmed that VGG16 significantly outperformed ResNet50 and EfficientNetB0. To enhance interpretability, Grad-CAM visualizations were generated for all three classes, indicating that the model’s attention broadly corresponded to anatomically relevant lung regions. Trained and evaluated on a Google Colab GPU environment, the proposed system demonstrates potential as an assistive tool for automated lung cancer screening, warranting further validation on larger and multi-institutional datasets before clinical application.  \nKeywords Lung cancer, CT scan images, Deep learning, Convolutional neural network (CNN), Transfer learning, VGG16, Grad-CAM  \nAbbreviations  \nAI  \nML  \nDL  \nCNN  \nCT  \nTPUGrad-CAMSVMAUC-ROC  \nArtificial intelligence Machine learning  \nDeep learning Convolutional neural network Computed tomography Tensor processing unit  \nGradient-weighted class activation mapping Support vector machine  \nArea under the receiver operating characteristic curve  \nLung cancer remains one of the most prevalent and lethal cancers globally, consistently ranking among the leading causes of cancer-related deaths. Its high mortality rate primarily results from late-stage detection, when available treatments such as surgery, chemotherapy, and radiotherapy are far less effective. Therefore, early and accurate diagnosis is essential to improving survival outcomes. Traditional diagnostic methods, including chest X-rays, Computed Tomography (CT) scans, and tissue biopsies, face several limitations such as inconsistent  \n1Dr. Babasaheb Ambedkar Technological University, Lonere, India. 2R. C. Patel Institute of Technology, Shirpur, Dhule, India. 3Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Pune, India. email: [priyanka.deshmukh@sitpune.edu.in](priyanka.deshmukh@sitpune.edu.in)  \n[www. nature.com/scientificreports](www. nature.com/scientificreports)  \naccuracy, high cost, limited availability in low-resource settings, and risks related to radiation and invasiveness. These challenges emphasize the necessity for more advanced, precise, and non-invasive diagnostic alternatives.  \nIn recent years, Artificial Intelligence (AI), particularly Machine Learning (ML), has revolutionized medical diagnostics by enabling data-driven disease detection and decision support. ML algorithms are capable of analyzing extensive and complex medical datasets, facilitating predictive analytics and automated diagnosis. By integrating radiological images, genetic data, and clinical histories, these systems extract intrica","cbCaigp8n12949AE","https://ap.wps.com/l/cbCaigp8n12949AE","pdf",2194250,17,"English","# Abstract\n## Early detection goal and problem\n## Model framework and evaluation\n## Best-performing architecture and results\n## Interpretability and practical implications","[{\"question\":\"What problem does the study address in lung cancer detection?\",\"answer\":\"The study targets high mortality linked to late-stage diagnosis by improving early and accurate classification of lung CT images.\"},{\"question\":\"How is the classification task defined in the proposed approach?\",\"answer\":\"The model performs multi-class classification, labeling CT images as benign, malignant, or normal.\"},{\"question\":\"Why is patient-level data splitting important in this work?\",\"answer\":\"Patient-level splitting helps prevent slice-level data leakage, making the evaluation more reliable.\"}]","Deep learning driven early detection of lung cancer from CT images using transfer learning approaches | PDF",1790090470,43]