[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-356460-105":59,"doc-detail-356460-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","adaptive-multi-feature-fusion-architecture-with-optimized-learning-for-high-fidelity-brain-tumor-classification-in-mri","Adaptive multi-feature fusion architecture with optimized learning for high-fidelity brain tumor classification in MRI","","Adaptive multi-feature fusion learning targets accurate early brain tumor grading on MRI, where distinguishing high-grade glioma, low-grade glioma, and healthy tissue remains difficult. A preprocessing stage combines Adaptive Gamma Correction for contrast enhancement with DnCNN denoising. Transfer-learning CNNs extract deep features from three fine-tuned layers, each optimized by a distinct algorithm, then are fused with texture descriptors from GLCM, forming nine CGFF sets. Hybrid descriptors are evaluated with RF, XGBoost, LightGBM, SVM, and a stacked ensemble, validated via Friedman test (p\u003C0.05). Results reach 99.05% accuracy and consistently outperform state-of-the-art metrics.",{"@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":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/adaptive-multi-feature-fusion-architecture-with-optimized-learning-for-high-fidelity-brain-tumor-classification-in-mri/356460/",{"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/adaptive-multi-feature-fusion-architecture-with-optimized-learning-for-high-fidelity-brain-tumor-classification-in-mri/356460.png","ImageObject",300,407,{"name":92,"@type":93},"River Wang","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-23",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What imaging problem does the framework aim to solve in brain tumor classification?","Question",{"text":113,"@type":114},"It targets reliable grading by separating high-grade glioma, low-grade glioma, and healthy tissue using MRI, which is still a major challenge at early stages.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method preprocess MRI images?",{"text":118,"@type":114},"It uses Adaptive Gamma Correction (AGC) to improve contrast adjustment and a Denoising Convolutional Neural Network (DnCNN) to remove noise.",{"name":120,"@type":111,"acceptedAnswer":121},"What features are fused for the final descriptors and how are they evaluated?",{"text":122,"@type":114},"Deep representations from three fine-tuned transfer learning CNN layers are combined with handcrafted GLCM-based texture measures to create nine CNN–GLCM Fused Feature (CGFF) sets, then assessed using RF, XGBoost, LightGBM, SVM, and a stacked ensemble with Friedman statistical testing.","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},356460,1790190736,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"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":56,"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,"preview_page_count":19,"preview_urls":146},1099514067438,"https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nAdaptive multi-feature fusion architecture with optimized learning for high-fidelity brain tumor classification in MRI  \nMohammed Safy1, Mahmoud Khaled Abd-Ellah2, Esraa Salah Bayoumi3,4􀀍 &  \nGerges M. Salama3  \nBrain gliomas represent one of the most aggressive cancers worldwide and remain difficult to diagnose accurately at an early stage. Although computer-aided diagnostic (CAD) approaches have progressed notably in recent years, distinguishing between high-grade glioma (HG-G), low-grade glioma (LGG), and healthy brain tissue on magnetic resonance images is still a major challenge. To address this issue, we propose a multi-stage framework designed to push the boundaries of current classification methods. The framework begins with a preprocessing phase that integrates Adaptive Gamma Correction (AGC) for improved contrast adjustment with a Denoising Convolutional Neural Network (DnCNN) for noise removal. Feature extraction is then carried out from three representative layers across three fine-tuned transfer learning CNNs (TRCNNs), where each model is optimized by a different algorithm. These deep representations are combined with handcrafted texture measures based on the Gray-Level Co-occurrence Matrix (GLCM), producing nine unique CNN–GLCM Fused Feature (CGFF) sets. The resulting hybrid descriptors are evaluated using several strong classifiers such as Random Forest (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Support Vector Machine (SVM), along with a stacked ensemble to reinforce stability and robustness. Performance significance was verified through the Friedman statistical test, with p \u003C 0.05, confirming the reliability of the improvements. The framework achieved 99.05% accuracy, 98.99% recall, 99.52% specificity, 99.08% positive predictive value (PPV), and 99.54% negative predictive value (NPV), consistently surpassed state-of-the-art (SOTA) methods across all reported metrics.  \nKeywords Image enhancement technique, Multi-class gliomas, Tumor classification, CGFF layers, Friedman test  \nThe prompt and precise detection of the brain tumor grade directly influences the patient’s anticipated survival and plays a crucial role in treatment planning and evaluating tumor growth1. Significantly, brain tumors contribute to 85–90% of all central nervous system damage across all medical conditions2. Based on recent data provided by the National Brain Tumor Society (NBTS), one million Americans are living with a brain tumor. By the end of 2023, 94,390 cases of primary brain tumors were recorded, and 18,990 individuals died3. Gliomas are viewed as the most aggressive primary brain tumors within the central nervous system (CNS)4. The World Health Organization (WHO) classifies glioma tumors into two groups: low-grade (LG-G) and high-grade (HGG)5. This classification relies on the microscopic appearance of tumor cells. Examination under the microscope reveals that cells in low-grade gliomas divide slowly. Although non-cancerous, low-grade gliomas can create issues by exerting pressure on normal brain structures. In contrast, high-grade gliomas exhibit more rapid and aggressive growth when compared to low-grade gliomas6.  \nMagnetic resonance imaging (MRI) is an advanced imaging technology known for its ability to offer detailed insights into brain tissue, making it a common choice for automated tumor detection7. MRI, which produces highly accurate images of brain tumor features, may provide patients with alternative therapy options. The high  \n1College of Computing and Information Technology, Arab Academy for Science, Technology and Maritime Transport (AASTMT), Smart Village, B 2401, Giza, Egypt. 2Faculty of Artificial Intelligence, Egyptian Russian University, Cairo 11829, Egypt. 3Department of Electrical Engineering, Faculty of Engineering, Minia University, Minia 61111, Egypt.  \n4Electrical Engineering Depart","cbCaitEIBVHCFYYe","https://ap.wps.com/l/cbCaitEIBVHCFYYe","pdf",4389324,"English","# Introduction\n## Clinical challenge and problem motivation\n## Background on glioma grading\n## Role of MRI and CAD\n## AI, machine learning, and CNNs\n# Proposed methodology\n## Preprocessing with AGC and DnCNN\n## Feature extraction with TRCNN layers\n## Texture features via GLCM and CGFF fusion\n## Classifiers and stacked ensemble\n## Statistical validation and performance results","[{\"question\":\"What imaging problem does the framework aim to solve in brain tumor classification?\",\"answer\":\"It targets reliable grading by separating high-grade glioma, low-grade glioma, and healthy tissue using MRI, which is still a major challenge at early stages.\"},{\"question\":\"How does the proposed method preprocess MRI images?\",\"answer\":\"It uses Adaptive Gamma Correction (AGC) to improve contrast adjustment and a Denoising Convolutional Neural Network (DnCNN) to remove noise.\"},{\"question\":\"What features are fused for the final descriptors and how are they evaluated?\",\"answer\":\"Deep representations from three fine-tuned transfer learning CNN layers are combined with handcrafted GLCM-based texture measures to create nine CNN–GLCM Fused Feature (CGFF) sets, then assessed using RF, XGBoost, LightGBM, SVM, and a stacked ensemble with Friedman statistical testing.\"}]","Adaptive multi-feature fusion architecture with optimized learning for high-fidelity brain tumor classification in MRI | PDF",1790125415,48,[147,151,155,159],{"page_no":8,"url":148,"width":149,"height":150},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0f37399f42cee4af98595ccb5006c522.webp",983,1291,{"page_no":14,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/c2c24204ace9f243b48d07711edc3d1b.webp",982,1290,{"page_no":81,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/363574f37c0e5e9f0e6e688018338535.webp",981,1289,{"page_no":19,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/039c009ed79e8ee93ca4273d67dc6b02.webp",980,1287]