[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-381336-105":59,"doc-detail-381336-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-diagnostic-classification-of-lung-nodules-using-multiple-scale-residual-network","A diagnostic classification of lung nodules using multiple-scale residual network","","Computed tomography (CT) improves diagnostic efficacy and can reduce lung cancer mortality, but benign–malignant discrimination of lung nodules remains difficult. This study develops a multiple-scale residual network (MResNet) to automatically and precisely extract general nodule features and classify nodules using deep learning. MResNet combines ResNet contextual learning with a pyramid pooling module to fuse features across four scales. Results show strong training performance and reliable test-set discrimination, enabling reproducible malignancy risk scoring to support clinicians and radiologists and optimize lung cancer screening management.",{"@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":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/a-diagnostic-classification-of-lung-nodules-using-multiple-scale-residual-network/381336/",{"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-diagnostic-classification-of-lung-nodules-using-multiple-scale-residual-network/381336.png","ImageObject",300,407,{"name":92,"@type":93},"Kyle","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-09-24",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",11,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What problem does the study address in CT-based lung nodule evaluation?","Question",{"text":113,"@type":114},"Distinguishing benign from malignant nodules in CT imaging remains challenging due to subtle differences, even for experienced radiologists.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does MResNet improve nodule feature learning and classification?",{"text":118,"@type":114},"It uses ResNet as a backbone to learn contextual representation and a pyramid pooling module to fuse features across multiple scales for more general nodule characteristics.",{"name":120,"@type":111,"acceptedAnswer":121},"How do the model’s metrics compare between training and testing sets?",{"text":122,"@type":114},"The model achieves very high performance in the training set, while the testing set retains strong discrimination with accuracy, sensitivity, specificity, PPV, NPV, and AUC reported in the study.","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},381336,1790330766,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":34,"category_name":35,"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":105,"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},3985741905716,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nA diagnostic classification of lung nodules using multiple‑scale residual network  \nHongfeng Wang1, Hai Zhu1, Lihua Ding3 & Kaili Yang2*  \nComputed tomography (CT) scans have been shown to be an effective way of improving diagnostic efficacy and reducing lung cancer mortality. However, distinguishing benign from malignant nodules in CT imaging remains challenging. This study aims to develop a multiple‑scale residual network (MResNet) to automatically and precisely extract the general feature of lung nodules, and classify lung nodules based on deep learning. The MResNet aggregates the advantages of residual units and pyramid pooling module (PPM) to learn key features and extract the general feature for lung nodule classification. Specially, the MResNet uses the ResNet as a backbone network to learn contextual information and discriminate feature representation. Meanwhile, the PPM is used to fuse features under four different scales, including the coarse scale and the fine‑grained scale to obtain more general lung features of the CT image. MResNet had an accuracy of 99.12%, a sensitivity of 98.64%, a specificity of 97.87%, a positive predictive value (PPV) of 99.92%, and a negative predictive value (NPV) of 97.87% in the training set. Additionally, its area under the receiver operating characteristic curve (AUC) was 0.9998 (0.99976–0.99991) . MResNet’s accuracy, sensitivity, specificity, PPV, NPV, and AUC in the testing set were 85.23%, 92.79%, 72.89%, 84.56%, 86.34%, and 0.9275 (0.91662–0.93833), respectively. The developed MResNet performed exceptionally well in estimating the malignancy risk of pulmonary nodules found on CT. The model has the potential to provide reliable and reproducible malignancy risk scores for clinicians and radiologists, thereby optimizing lung cancer screening management.  \nThe International Agency for Research on Cancer’s most recent global cancer report showed that lung cancer accounts for 11.4%(second only to breast cancer) of new cancer cases and 18.0%(the highest of all cancers) of new cancer deaths worldwide in 2020, representing a significant disease burden globally1,2. Despite advancementsin surgical, radiotherapeutic, and chemotherapeutic methods, the long-term survival of lung cancer still dismal3. Early diagnosis has been proved to be an effective approach to improve lung cancer outcomes, with 5-year relative survival increasing from 6% for distant-stage disease to 33% for regional stage and 60% for localized-stage disease4. According to the studies of the National Lung Screening Trial (NLST) and the Dutch-Belgian Lung Cancer Screening, screening high-risk individuals with low-dose chest computed tomography (CT) can reduce lung cancer mortality by 20% and 26%, respectively5.  \nDespite the fact that the widespread use of CT has improved the diagnostic efficacy of lung cancer and the treatment outcomes for patients, the vast number of CT images has increased the radiologists’ burden. Currently, the classification of pulmonary nodules in CT is highly dependent on radiologists, but the increase of radiologists is far below the rate of increase in medical imaging data. For instance, the annual growth rate of medical imaging data in the United States is 63%, while the annual growth rate of the number of radiologists is only 2% . Due to the tremendous workload, physicians often become exhausted, which affects their work efficiency and leads to missed examinations and misdiagnosis. Additionally, it can be challenging for even the most skilled radiologist to accurately classify small nodules. Particularly as section thickness decreases, distinguishing pulmonary lesions from adjacent normal vascular structures becomes more difficult. Since it depends solely on the radiologist, nodule classification is subjective and challenging to generalize.  \nTo improve efficiency and reduce the rate of misdiagnosis, numerous investigato","cbCaibV6uzUlQBSq","https://ap.wps.com/l/cbCaibV6uzUlQBSq","pdf",1919465,"English","# Background and challenge\n## Imaging value and clinical burden\n# Proposed method\n## MResNet architecture\n## Multi-scale feature fusion\n# Performance results\n## Training set metrics\n## Testing set metrics\n# Clinical implications\n## Malignancy risk scoring for screening management","[{\"question\":\"What problem does the study address in CT-based lung nodule evaluation?\",\"answer\":\"Distinguishing benign from malignant nodules in CT imaging remains challenging due to subtle differences, even for experienced radiologists.\"},{\"question\":\"How does MResNet improve nodule feature learning and classification?\",\"answer\":\"It uses ResNet as a backbone to learn contextual representation and a pyramid pooling module to fuse features across multiple scales for more general nodule characteristics.\"},{\"question\":\"How do the model’s metrics compare between training and testing sets?\",\"answer\":\"The model achieves very high performance in the training set, while the testing set retains strong discrimination with accuracy, sensitivity, specificity, PPV, NPV, and AUC reported in the study.\"}]","A diagnostic classification of lung nodules using multiple-scale residual network | PDF",1790244873,28]