[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-368873-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-368873-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","an-interpretable-hybrid-deep-learning-framework-for-gastric-cancer-diagnosis-using-histopathological-imaging","An interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging","","Increasing incidence and complex interpretation of gastric histopathological images create major barriers to accurate, timely diagnosis. Manual assessment is subjective and time-consuming, driving demand for reliable automation in digital pathology. This study proposes a hybrid deep learning framework that combines CNN feature extraction with Transformer-based global context modeling. It is trained and validated on three public datasets (GasHisSDB, TCGA-STAD, NCT-CRC-HE-100 K), using stain normalization and standard patch augmentation. Fivefold cross-validation reports accuracy, macro F1, and AUC, while Grad-CAM provides interpretability and highlights regions consistent with expert annotations.",{"@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/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/an-interpretable-hybrid-deep-learning-framework-for-gastric-cancer-diagnosis-using-histopathological-imaging/368873/",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/an-interpretable-hybrid-deep-learning-framework-for-gastric-cancer-diagnosis-using-histopathological-imaging/368873.png","ImageObject",300,407,{"name":42,"@type":43},"Ben ","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-03","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is gastric cancer diagnosis challenging with histopathological images?","Question",{"text":63,"@type":64},"The complexity of interpreting histopathological images and the subtlety of early symptoms make manual assessment difficult. This can lead to subjectivity, workload, and delayed or advanced-stage diagnoses.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What is the proposed hybrid deep learning approach in this study?",{"text":68,"@type":64},"The framework combines a CNN backbone for local spatial feature extraction with a Transformer encoder to capture global context. This hybrid design aims to improve representation across tissue subtypes and staining variations.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the study evaluate performance and interpretability?",{"text":72,"@type":64},"Performance is assessed using fivefold cross-validation with metrics such as accuracy, F1-score, and AUC. Grad-CAM visualizations are used to provide interpretability by highlighting biologically relevant regions aligned with expert annotations.","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},368873,1790764833,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,110,115,120,123,127],{"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":29,"show_sort_weight":108,"slug":109},7,40,"healthcare",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},8,"Research & Report",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":107,"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":118,"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":104},2336478951081,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nAn interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging  \nTengfei Ren1, Vijay Govindarajan2, Sami Bourouis3, Xiangkun Wang4 & Shanbao Ke5􀀍  \nThe increasing incidence of gastric cancer and the complexity of histopathological image interpretation present significant challenges for accurate and timely diagnosis. Manual assessments are often subjective and time-intensive, leading to a growing demand for reliable, automated diagnostic tools in digital pathology. This study proposes a hybrid deep learning approach combining convolutional neural networks (CNNs) and Transformer-based architectures to classify gastric histopathological images with high precision. The model is designed to enhance feature representation and spatial contextual understanding, particularly across diverse tissue subtypes and staining variations. Three publicly available datasets—GasHisSDB, TCGA-STAD, and NCT-CRC-HE-100 K—were utilized to train and evaluate the model. Image patches were preprocessed through stain normalization, augmented using standard techniques, and fed into the hybrid model. The CNN backbone extracts local spatial features, while the Transformer encoder captures global context. Performance was assessed using fivefold crossvalidation and evaluated through accuracy, F1-score, AUC, and Grad-CAM-based interpretability. The proposed model achieved a 99.2% accuracy on the GasHisSDB dataset, with a macro F1-score of 0.991 andAUC of 0.996. External validation on TCGA-STAD and NCT-CRC-HE-100 K further confirmed the model’s robustness. Grad-CAM visualizations highlighted biologically relevant regions, demonstrating interpretability and alignment with expert annotations. This hybrid deep learning framework offers a reliable, interpretable, and generalizable tool for gastric cancer diagnosis. Its superior performance and explainability highlight its clinical potential for deployment in digital pathology workflows.  \nKeywords Gastric cancer classification, Histopathological image analysis, Deep learning, CNN-transformer hybrid model, Medical image interpretation, Grad-CAM explainability, Multi-dataset validation  \nBackground and motivation  \nGastric cancer remains one of the leading causes of cancer-related deaths worldwide, with particularly high prevalence in East Asia and parts of Eastern Europe1. However, early detection is the key to a good prognosis, although treatment has advanced considerably. Unfortunately, manual diagnosis is capable of detecting only a limited number of cases at an early stage, which are often diagnosed at an advanced stage because of the subtle nature of the early symptoms2. The gold standard to confirm malignancy is histopathology of gastric biopsy samples. Nevertheless, this process is labor-intensive and may be subject to interobserver variability of pathologists, particularly in the context of high-throughput clinical environments3. Since digital pathology is expanding, computer-aided diagnostic (CAD) systems that help interpret histological slides are receiving increasing interest. Convolutional neural networks (CNNs) have demonstrated great promise in medical image analysis, including cancer detection, classification, and segmentation4,5. These models can automatically extract the relevant features from the images without the need for manual intervention or domain-specific engineering. In the past few years, vision tasks have witnessed the rise of transformer-based models that provide better global  \n1Department of Hemangioma, Henan Provincial People’s Hospital, Zhengzhou University People’s Hospital, Henan University People’s Hospital, Zhengzhou 450000, China. 2Distribution and Supply Technology, Expedia Group, Seattle, WA 98119, USA. 3Department of Information Technology, College of Computers and Information Technology, Taif University, P. O. Box 11099, 21944 Taif, Saudi Arabia. 4Depar","cbCaiuLsc2NXCMXL","https://ap.wps.com/l/cbCaiuLsc2NXCMXL","pdf",4510587,"English","# Background and motivation\n# Problem statement","[{\"question\":\"Why is gastric cancer diagnosis challenging with histopathological images?\",\"answer\":\"The complexity of interpreting histopathological images and the subtlety of early symptoms make manual assessment difficult. This can lead to subjectivity, workload, and delayed or advanced-stage diagnoses.\"},{\"question\":\"What is the proposed hybrid deep learning approach in this study?\",\"answer\":\"The framework combines a CNN backbone for local spatial feature extraction with a Transformer encoder to capture global context. This hybrid design aims to improve representation across tissue subtypes and staining variations.\"},{\"question\":\"How does the study evaluate performance and interpretability?\",\"answer\":\"Performance is assessed using fivefold cross-validation with metrics such as accuracy, F1-score, and AUC. Grad-CAM visualizations are used to provide interpretability by highlighting biologically relevant regions aligned with expert annotations.\"}]","An interpretable hybrid deep learning framework for gastric cancer diagnosis using histopathological imaging | PDF",1790179022]