[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-370068-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-370068-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":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","lbnet-an-optimized-lightweight-cnn-for-mammographic-breast-cancer-classification-with-xai-based-interpretability","LBNet - an optimized lightweight CNN for mammographic breast cancer classification with XAI-based interpretability","","LBNet proposes an optimized lightweight, interpretable convolutional neural network for mammographic breast cancer classification aimed at overcoming computational complexity, limited generalizability, and low interpretability in existing deep learning models. The network uses five convolutional layers with ReLU, batch normalization, and max-pooling, totaling 2.4 million trainable parameters. Trained on the RSNA dataset with Adam optimization and fivefold cross-validation, it reaches 97.28% accuracy, with strong precision/recall for both cancer and non-cancer cases. External validation achieves 99.54% on CBIS-DDSM and 98.50% on MIAS, and interpretability is enhanced using SHAP and Grad-CAM.",{"@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/lbnet-an-optimized-lightweight-cnn-for-mammographic-breast-cancer-classification-with-xai-based-interpretability/370068/",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/lbnet-an-optimized-lightweight-cnn-for-mammographic-breast-cancer-classification-with-xai-based-interpretability/370068.png","ImageObject",300,407,{"name":42,"@type":43},"hdkawk","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-21","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What problem does LBNet address in mammographic breast cancer classification?","Question",{"text":63,"@type":64},"LBNet targets high computational complexity, limited generalizability across datasets, and insufficient interpretability in existing models, especially for resource-constrained settings.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How is LBNet designed and what are its key architectural components?",{"text":68,"@type":64},"LBNet is a lightweight CNN with five convolutional layers using ReLU activation, batch normalization, and max-pooling, with 2.4 million trainable parameters.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the study validate LBNet’s performance and generalizability?",{"text":72,"@type":64},"LBNet is trained on the RSNA dataset with Adam optimizer and fivefold cross-validation, then validated on external datasets (CBIS-DDSM and MIAS), achieving high accuracy on both.","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},370068,1790395723,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,119,122,126],{"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":55,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},"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":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":112,"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":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":127,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},3985747859855,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nLBNet: an optimized lightweight CNN for mammographic breast cancer classification with XAIbased interpretability  \nJalal Ahmmed1, Faruk Ahmed2, Md Alamgir Kabir1􀀍, Md TaimurAhad3, MehreenAfsar Jadoon4, Atiq ur Rehman5􀀍 & Amine Bermak5  \nBreast cancer represents a major worldwide health burden, marked by high incidence and mortality rates across diverse socioeconomic populations. While deep learning has enabled advances in automated mammographic analysis, existing models often suffer from high computational complexity. They also face limited generalizability and a lack of interpretability. To overcome these challenges, this research introduces LBNet, a lightweight and interpretable convolutional neural network (CNN) built for accurate and efficient breast cancer detection, particularly in resource-constrained settings. With only 2.4 million trainable parameters, LBNet consists of five convolutional layers, leveraging ReLU activation, batch normalization, and max-pooling to optimize feature extraction while maintaining computational efficiency. LBNet was trained on the RSNA dataset using the Adam optimizer and fivefold cross-validation. It achieved 97.28% accuracy. For cancer cases, precision was 99% and recall was 96%. For non-cancer cases, precision was 96% and recall was 99% . In comparison, baseline models such asVGG19, SE-ResNet152, and ResNet152V2 yielded lower accuracies of 87.54%, 87.50%, and 85.24%, respectively, while transfer learning approaches peaked at 87.37% accuracy. LBNet’s generalizability was validated in external datasets, achieving 99.54% accuracy on CBIS-DDSM and 98.50% on MIAS. To enhance clinical trust, this work integrated SHAP (SHapley Additive exPlanations) and Grad-CAM (Gradient-weighted Class Activation Mapping). These methods effectively highlighted diagnostically relevant regions in mammograms. This improved prediction transparency. LBNet demonstrates strong potential as an accurate, efficient, and interpretable solution for breast cancer screening, and future studies could explore its extension to multi-view mammography and real-time clinical deployment.  \nKeywords Breast cancer, Mammography, Lightweight CNN, Explainable AI, SHAP, Grad-CAM, Transfer learning  \nBreast cancer remains one of the foremost global health concerns, significantly contributing to cancer incidence and mortality across both industrialized and developing nations1. According to the World Health Organization (WHO), approximately one in every ten newly diagnosed cancers worldwide is breast cancer, making it the most frequently diagnosed cancer among women2. Recent WHO and International Agency for Research on Cancer (IARC) reports indicate that around 2.3 million women were diagnosed with breast cancer in 2022. This led to nearly 670,000 deaths globally3. Moreover, IARC projects that by 2050, the global burden could rise to about 3.2 million new cases. It may also reach 1.1 million deaths annually if current trends continue4. In the United States alone, approximately 316,950 new invasive cases and 42,170 deaths are anticipated in 20255. Therefore, early detection is vital, as breast cancer often manifests through symptoms such as palpable lumps or skin texture changes, which are primarily identified through imaging techniques like mammography6 (Fig. 1) .  \nTraditional computer-aided diagnosis (CAD) systems, introduced in the 1990s, relied on hand-crafted features such as texture and shape, combined with classical classifiers like SVMs and decision trees7. These systems achieved moderate sensitivity in detecting masses and microcalcifications but suffered from high false-  \n1Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.  \n2Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh, Bangladesh.  \n3Department of Management Information Systems, Independent University, Dh","cbCaioNSFgR4IhZ2","https://ap.wps.com/l/cbCaioNSFgR4IhZ2","pdf",4386188,"English","# Background and motivation\n## Global burden of breast cancer and need for early detection\n## CAD and evolution to deep learning\n# Related work\n## CNN architectures and transfer learning approaches\n## Limitations for clinical deployment\n# Proposed method: LBNet\n## Lightweight design and architecture components\n## Training strategy and evaluation results\n## XAI-based interpretability with SHAP and Grad-CAM\n# Validation and future directions","[{\"question\":\"What problem does LBNet address in mammographic breast cancer classification?\",\"answer\":\"LBNet targets high computational complexity, limited generalizability across datasets, and insufficient interpretability in existing models, especially for resource-constrained settings.\"},{\"question\":\"How is LBNet designed and what are its key architectural components?\",\"answer\":\"LBNet is a lightweight CNN with five convolutional layers using ReLU activation, batch normalization, and max-pooling, with 2.4 million trainable parameters.\"},{\"question\":\"How does the study validate LBNet’s performance and generalizability?\",\"answer\":\"LBNet is trained on the RSNA dataset with Adam optimizer and fivefold cross-validation, then validated on external datasets (CBIS-DDSM and MIAS), achieving high accuracy on both.\"}]","LBNet - an optimized lightweight CNN for mammographic breast cancer classification with XAI-based interpretability | PDF",1790186569,48,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/f345a9af277144f50844e1638ec7f49b.webp",983,1291,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/559da8610d77401c92b69ad1ba657890.webp",982,1290,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/53743418e6ac8245a8fee79699d9adea.webp",981,1289,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9b6975dc44aa3ccd7e51dbdbe20ce576.webp",980,1287]