{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:07:55Z","timestamp":1789103275060,"version":"build-2803163510"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Accurate brain tumor classification from Magnetic Resonance Imaging (MRI) remains challenging due to dataset heterogeneity, class imbalance, and limited interpretability, while practical deployment further requires models that balance predictive performance with computational efficiency. In this work, we propose\n                    <jats:italic>NeuroTrustNet<\/jats:italic>\n                    , an integrated multimodal framework that combines complementary convolutional neural network (CNN), Vision Transformer (ViT), and handcrafted radiomic representations through the proposed Adaptive Attention Stacking (AAS) mechanism, enabling sample-specific feature fusion to improve robustness under cross-dataset variability while maintaining deployment-oriented computational efficiency. To evaluate performance under different computational constraints, we consider both high-capacity ensemble models (CNN and ViT ensembles) and lightweight architectures (RapidNet and AdaptoVision) as baseline systems. Experimental results on a large multi-dataset corpus show that while high-capacity ensembles achieve the highest accuracy (up to 96% on an external test set), the proposed NeuroTrustNet maintains competitive performance (94%) while reducing the computational cost of the fusion optimization stage by approximately 80% compared with full end-to-end ensemble training, highlighting its suitability for deployment-oriented medical AI systems operating under computational constraints while maintaining an effective balance between accuracy and efficiency. To further enhance interpretability, we incorporate a\n                    <jats:italic>post-hoc<\/jats:italic>\n                    interpretability component combining visual attribution maps with structured textual summaries derived from model outputs, enabling transparent and human-readable insights without influencing model predictions. The results demonstrate the potential of NeuroTrustNet as a deployment-oriented multimodal decision-support framework, providing a competitive balance between predictive performance, computational efficiency, and interpretability under cross-dataset variability.\n                  <\/jats:p>","DOI":"10.3389\/frai.2026.1900160","type":"journal-article","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:35:37Z","timestamp":1789101337000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["NeuroTrustNet: a cost-effective multimodal ensemble framework for brain tumor classification under cross-dataset variability"],"prefix":"10.3389","volume":"9","author":[{"given":"Ferdaus Ibne","family":"Aziz","sequence":"first","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan","place":["Ulsan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Insoo","family":"Koo","sequence":"additional","affiliation":[{"name":"Department of Electrical, Electronic and Computer Engineering, University of Ulsan","place":["Ulsan, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tumennast","family":"Erdenebold","sequence":"additional","affiliation":[{"name":"AI and Big Data Department, Woosong University","place":["Daejeon, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jubayer A.","family":"Hossain","sequence":"additional","affiliation":[{"name":"Faculty of Nursing and Health Sciences, Nord University","place":["Namsos, Norway"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asle","family":"Fagerstr\u00f8m","sequence":"additional","affiliation":[{"name":"Department of Technology, Kristiania University of Applied Sciences","place":["Bergen, Norway"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Debasish","family":"Ghose","sequence":"additional","affiliation":[{"name":"Department of Technology, Kristiania University of Applied Sciences","place":["Bergen, Norway"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"92","DOI":"10.54756\/IJSAR.2024.24","article-title":"Transfer learning and advanced CNN models for detecting brain tumors using MRI","volume":"4","author":"Abbasi","year":"2024","journal-title":"Int. J. Sci. Appl. Res"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.31557\/APJCP.2023.24.6.2141","article-title":"Brain tumor classification based on improved stacked ensemble deep learning methods","volume":"24","author":"Al-Azzwi","year":"2023","journal-title":"Asian Pac. J. Cancer Prev"},{"key":"B3","first-page":"29","article-title":"Detection of brain tumor using deep learning","volume":"6","author":"Almadhoun","year":"2022","journal-title":"Int. J. Acad. Eng. Res."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.3390\/diagnostics13071320","article-title":"Weighted average ensemble deep learning model for stratification of brain tumor in MRI images","volume":"13","author":"Anand","year":"2023","journal-title":"Diagnostics"},{"key":"B5","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/s12539-023-00571-1","article-title":"BMRI-NET: a deep stacked ensemble model for multi-class brain tumor classification from MRI images","volume":"15","author":"Asif","year":"2023","journal-title":"Interdiscipl. Sci.: Comput. Life Sci"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.02371","article-title":"RAPID-Net: accurate pocket identification for binding-site-agnostic docking","author":"Balytskyi","year":"2025","journal-title":"arXiv Preprint arXiv:2502.02371"},{"key":"B7","doi-asserted-by":"publisher","first-page":"111218","DOI":"10.1109\/ACCESS.2024.3425469","article-title":"A transfer learning based approach for brain tumor classification","volume":"12","author":"Bibi","year":"2024","journal-title":"IEEE Access"},{"key":"B8","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1016\/j.inffus.2021.07.011","article-title":"Cost-effective ensemble models selection using deep reinforcement learning","volume":"77","author":"Birman","year":"2021","journal-title":"Inform. Fus"},{"key":"B9","doi-asserted-by":"publisher","first-page":"22099","DOI":"10.1007\/s11042-023-15557-w","article-title":"TumorAwareNet: deep representation learning with attention based sparse convolutional denoising autoencoder for brain tumor recognition","volume":"83","author":"Bodapati","year":"2024","journal-title":"Multimed. Tools Appl"},{"key":"B10","doi-asserted-by":"publisher","first-page":"36453","DOI":"10.1007\/s11042-024-19657-z","article-title":"Developing diverse ensemble architectures for automatic brain tumor classification","volume":"84","author":"Bogacsovics","year":"2025","journal-title":"Multimedia Tools Appl."},{"key":"B11","doi-asserted-by":"publisher","first-page":"122159","DOI":"10.1016\/j.eswa.2023.122159","article-title":"Development of hybrid models based on deep learning and optimized machine learning algorithms for brain tumor multi-classification","volume":"238","author":"Celik","year":"2024","journal-title":"Expert Syst. Appl"},{"key":"B12","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1109\/ICCV48922.2021.00041","article-title":"\u201cCrossViT: cross-attention multi-scale vision transformer for image classification,\u201d","author":"Chen","year":"2021","journal-title":"Proc. IEEE\/CVF int. conf. comput. vis"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1384","DOI":"10.3390\/diagnostics11081384","article-title":"TransMed: transformers advance multi-modal medical image classification","volume":"11","author":"Dai","year":"2021","journal-title":"Diagnostics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3390\/cancers17010121","article-title":"Advanced brain tumor classification in MR images using transfer learning and pre-trained deep CNN models","volume":"17","author":"Disci","year":"2025","journal-title":"Cancers"},{"key":"B15","doi-asserted-by":"publisher","first-page":"221","DOI":"10.3390\/a17060221","article-title":"A hybrid learning-architecture for improved brain tumor recognition","volume":"17","author":"Dixon","year":"2024","journal-title":"Algorithms"},{"key":"B16","doi-asserted-by":"publisher","first-page":"12027","DOI":"10.1007\/s13369-023-08607-w","article-title":"Transfer learning-based deep feature extraction framework using fine-tuned EfficientNet-B7 for multiclass brain tumor classification","volume":"49","author":"Ghosh","year":"2024","journal-title":"Arab. J. Sci. Eng"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1524","DOI":"10.1038\/s41598-024-51867-1","article-title":"NeuroNet19: an explainable deep neural network model for the classification of brain tumors using magnetic resonance imaging data","volume":"14","author":"Haque","year":"2024","journal-title":"Sci. Rep"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv Preprint arXiv:1704.04861"},{"key":"B19","doi-asserted-by":"publisher","first-page":"710","DOI":"10.3390\/electronics14040710","article-title":"Improved EfficientNet architecture for multi-grade brain tumor detection","volume":"14","author":"Ishaq","year":"2025","journal-title":"Electronics"},{"key":"B20","doi-asserted-by":"publisher","first-page":"100270","DOI":"10.1016\/j.health.2023.100270","article-title":"Transfer learning architectures with fine-tuning for brain tumor classification using magnetic resonance imaging","volume":"4","author":"Islam","year":"2023","journal-title":"Healthc. Anal"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.12874","article-title":"Residual vision transformer (ResViT) based self-supervised learning model for brain tumor classification","author":"Karagoz","year":"2024","journal-title":"arXiv:2411.12874"},{"key":"B22","unstructured":"Kumar\n              P.\n            \n          \n          Brain MRI Dataset\n          \n          2024"},{"key":"B23","doi-asserted-by":"publisher","first-page":"40204","DOI":"10.1109\/ACCESS.2024.3377105","article-title":"Improved classification of different brain tumors in MRI scans using patterned-gridmask","volume":"12","author":"Lee","year":"2024","journal-title":"IEEE Access"},{"key":"B24","doi-asserted-by":"publisher","first-page":"102995","DOI":"10.1016\/j.inffus.2025.102995","article-title":"Vision-language models in medical image analysis: from simple fusion to general large models","volume":"118","author":"Li","year":"2025","journal-title":"Inform. Fus"},{"key":"B25","doi-asserted-by":"publisher","first-page":"468","DOI":"10.3390\/photonics10040468","article-title":"A lightweight Swin Transformer-based pipeline for optical coherence tomography image denoising in skin application","volume":"10","author":"Liao","year":"2023","journal-title":"Photonics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"100868","DOI":"10.1016\/j.bj.2025.100868","article-title":"Roles and potential of large language models in healthcare: a comprehensive review","volume":"48","author":"Lin","year":"2025","journal-title":"Biomed. J"},{"key":"B27","doi-asserted-by":"publisher","first-page":"107165","DOI":"10.1016\/j.crad.2025.107165","article-title":"Radiomics in clinical radiology: advances, challenges, and future directions","volume":"92","author":"Linton-Reid","year":"2025","journal-title":"Clin. Radiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-024-06758-7","article-title":"ConvBiFuseNet: a parallel fusion model with routing attention for MRI brain tumor classification","volume":"81","author":"Liu","year":"2025","journal-title":"J. Supercomput"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1002\/cbf.3870","article-title":"Brain cancer classification based on multistage ensemble generative adversarial network and convolutional neural network","volume":"41","author":"Melekoodappattu","year":"2023","journal-title":"Cell Biochem. Funct"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1038\/s41598-025-85874-7","article-title":"A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images","volume":"15","author":"Nahiduzzaman","year":"2025","journal-title":"Sci. Rep"},{"key":"B31","doi-asserted-by":"publisher","first-page":"129213","DOI":"10.1016\/j.neucom.2024.129213","article-title":"Brainformer: mimic human visual brain functions to machine vision models via fMRI","volume":"620","author":"Nguyen","year":"2024","journal-title":"Neurocomputing"},{"key":"B32","unstructured":"Nickparvar\n              M.\n            \n          \n          Brain Tumor MRI Dataset\n          \n          2024"},{"key":"B33","doi-asserted-by":"publisher","first-page":"2468","DOI":"10.1016\/j.procs.2023.01.222","article-title":"Ensemble of deep learning models for brain tumor detection","volume":"218","author":"Patil","year":"2023","journal-title":"Proc. Comput. Sci"},{"key":"B34","doi-asserted-by":"publisher","first-page":"200389","DOI":"10.1016\/j.sasc.2025.200389","article-title":"\u201cA deep learning framework for brain tumor detection using CNNs and transfer learning on MRI scans","volume":"7","author":"Prabhas","year":"2025","journal-title":"Syst. Soft Comput"},{"key":"B35","doi-asserted-by":"publisher","first-page":"109790","DOI":"10.1016\/j.patcog.2023.109790","article-title":"Knowledge transfer evolutionary search for lightweight neural architecture with dynamic inference","volume":"143","author":"Qian","year":"2023","journal-title":"Pattern Recognit"},{"key":"B36","doi-asserted-by":"publisher","first-page":"104025","DOI":"10.1016\/j.rineng.2025.104025","article-title":"SAlexNet: superimposed AlexNet using residual attention mechanism for accurate and efficient automatic primary brain tumor detection and classification","volume":"25","author":"Qureshi","year":"2025","journal-title":"Results in Engineering"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e0334430","DOI":"10.1371\/journal.pone.0334430","article-title":"Advanced deep learning-based brain tumor classification using a novel customized CNN and optimized residual network","volume":"20","author":"Rasheed","year":"2025","journal-title":"PLoS ONE"},{"key":"B38","doi-asserted-by":"publisher","first-page":"602","DOI":"10.3390\/brainsci13040602","article-title":"Automated classification of brain tumors from magnetic resonance imaging using deep learning","volume":"13","author":"Rasheed","year":"2023","journal-title":"Brain Sci"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1400341","DOI":"10.3389\/fonc.2024.1400341","article-title":"A fine-tuned vision transformer based enhanced multi-class brain tumor classification using MRI scan imagery","volume":"14","author":"Reddy","year":"2024","journal-title":"Front. Oncol"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.12652","article-title":"AdaptoVision: a multi-resolution image recognition model for robust and scalable classification","author":"Sabrin","year":"2025","journal-title":"arXiv Preprint arXiv:2504.12652"},{"key":"B41","doi-asserted-by":"publisher","first-page":"5930","DOI":"10.3390\/su15075930","article-title":"A study of CNN and transfer learning in medical imaging: advantages, challenges, future scope","volume":"15","author":"Salehi","year":"2023","journal-title":"Sustainability"},{"key":"B42","unstructured":"Brain Tumor Classification (MRI)\n          \n          2024"},{"key":"B43","unstructured":"Sherif\n              M. M.\n            \n          \n          Brain Tumor Dataset\n          \n          2024"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1905.11946","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019","journal-title":"arXiv Preprint arXiv:1905.11946"},{"key":"B45","doi-asserted-by":"publisher","first-page":"97","DOI":"10.3390\/bdcc8090097","article-title":"DaSAM: Disease and spatial attention module-based explainable model for brain tumor detection","volume":"8","author":"Tehsin","year":"2024","journal-title":"Big Data Cogn. Comput"},{"key":"B46","doi-asserted-by":"publisher","first-page":"109183","DOI":"10.1016\/j.compbiomed.2024.109183","article-title":"Multimodal brain tumor segmentation and classification from MRI scans based on optimized DeepLabV3+ and interpreted networks information fusion empowered with explainable AI","volume":"182","author":"Ullah","year":"2024","journal-title":"Comput. Biol. Med"},{"key":"B47","doi-asserted-by":"publisher","first-page":"127216","DOI":"10.1016\/j.neucom.2023.127216","article-title":"RanMerFormer: randomized vision transformer with token merging for brain tumor classification.","volume":"573","author":"Wang","year":"2024","journal-title":"Neurocomputing"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.01083","article-title":"ShuffleNet: an extremely efficient convolutional neural network for mobile devices","author":"Zhang","year":"2017","journal-title":"arXiv Preprint arXiv:1707.01083"},{"key":"B49","doi-asserted-by":"publisher","first-page":"109204","DOI":"10.1016\/j.compbiomed.2024.109204","article-title":"Lightweight medical image segmentation network with multi-scale feature-guided fusion","volume":"182","author":"Zhu","year":"2024","journal-title":"Comput. Biol. Med"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1900160\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T04:35:43Z","timestamp":1789101343000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1900160\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,11]]},"references-count":49,"alternative-id":["10.3389\/frai.2026.1900160"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1900160","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,11]]},"article-number":"1900160"}}