{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T04:18:11Z","timestamp":1775017091969,"version":"3.50.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Brain tumors are very dangerous as they cause death. A lot of people die every year because of brain tumors. Therefore, accurate classification and detection in the early stages can help in recovery. Various deep learning techniques have achieved good results in brain tumor classification. The traditional deep learning methods and training the neural network from scratch are time-consuming and can last for weeks of training. Therefore, in this work, we proposed an ensemble approach depending on transfer learning that utilizes pre-trained models of DenseNet121 and InceptionV3 to detect three forms of brain tumors: meningioma, glioma, and pituitary. While developing the ensemble model, some changes were made to the architecture of pre-trained models by replacing their classifiers (fully connected and SoftMax layers) with a new classifier to adopt the recent task. In addition, gradient-weighted class activation maps (Grad-CAM) are an explainable model to verify results and achieve high confidence. The suggested model was validated using a publicly available dataset and achieved 99.02% accuracy, 98.75% precision, 98.98% recall, and a 98.86% F1 score. The suggested approach outperformed others in detecting and classifying brain tumor MRI data, and verifying results using the explainable model achieved a high degree of trust.<\/jats:p>","DOI":"10.1007\/s00521-024-10401-0","type":"journal-article","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:57:06Z","timestamp":1732096626000},"page":"1289-1306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Explainable ensemble deep learning-based model for brain tumor detection and classification"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8065-8977","authenticated-orcid":false,"given":"Khalid M.","family":"Hosny","sequence":"first","affiliation":[]},{"given":"Mahmoud A.","family":"Mohammed","sequence":"additional","affiliation":[]},{"given":"Rania A.","family":"Salama","sequence":"additional","affiliation":[]},{"given":"Ahmed M.","family":"Elshewey","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"issue":"8","key":"10401_CR1","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1016\/j.amjmed.2017.12.039","volume":"131","author":"JR McFaline-Figueroa","year":"2018","unstructured":"McFaline-Figueroa JR, Lee EQ (2018) Brain tumors. Am J Med 131(8):874\u2013882. https:\/\/doi.org\/10.1016\/j.amjmed.2017.12.039","journal-title":"Am J Med"},{"key":"10401_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-23705-8_1","volume":"1405","author":"LM Wang","year":"2023","unstructured":"Wang LM, Englander ZK, Miller ML, Bruce JN (2023) Malignant glioma. Adv Exp Med Biol 1405:1\u201330. https:\/\/doi.org\/10.1007\/978-3-031-23705-8_1","journal-title":"Adv Exp Med Biol"},{"issue":"5","key":"10401_CR3","doi-asserted-by":"publisher","first-page":"381","DOI":"10.3322\/caac.21693","volume":"71","author":"KD Miller","year":"2021","unstructured":"Miller KD, Ostrom QT, Kruchko C, Patil N, Tihan T, Cioffi G, Fuchs HE, Waite KA et al (2021) Brain and other central nervous system tumor statistics. Cancer J Clin 71(5):381\u2013406. https:\/\/doi.org\/10.3322\/caac.21693","journal-title":"Cancer J Clin"},{"issue":"14","key":"10401_CR4","doi-asserted-by":"publisher","first-page":"3565","DOI":"10.3390\/cancers15143565","volume":"15","author":"SM Rezaeijo","year":"2023","unstructured":"Rezaeijo SM, Chegeni N, Baghaei Naeini F, Makris D, Bakas S (2023) Within-modality synthesis and novel radiomic evaluation of brain MRI scans. Cancers 15(14):3565. https:\/\/doi.org\/10.3390\/cancers15143565","journal-title":"Cancers"},{"issue":"4","key":"10401_CR5","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.irbm.2021.06.003","volume":"43","author":"MO Khairandish","year":"2022","unstructured":"Khairandish MO, Sharma M, Jain V, Chatterjee JM, Jhanjhi NZ (2022) A hybrid CNN-SVM threshold segmentation approach for tumor detection and classification of MRI brain images. IRBM 43(4):290\u2013299. https:\/\/doi.org\/10.1016\/j.irbm.2021.06.003","journal-title":"IRBM"},{"key":"10401_CR6","doi-asserted-by":"publisher","first-page":"103226","DOI":"10.1016\/j.bspc.2021.103226","volume":"71","author":"H Zerouaoui","year":"2022","unstructured":"Zerouaoui H, Idri A (2022) Deep hybrid architectures for binary classification of medical breast cancer images. Biomed Signal Process Control 71:103226. https:\/\/doi.org\/10.1016\/j.bspc.2021.103226","journal-title":"Biomed Signal Process Control"},{"issue":"12","key":"10401_CR7","doi-asserted-by":"publisher","first-page":"12388","DOI":"10.3390\/jpm11121388","volume":"11","author":"TV Moga","year":"2021","unstructured":"Moga TV, David C, Popescu A, Lupusoru R, Heredea D, Ghiuchici AM, Foncea C, Burdan A et al (2021) Multiparametric ultrasound approach using a tree-based decision classifier for inconclusive focal liver lesions evaluated by contrast-enhanced ultrasound. J Personal Med 11(12):12388. https:\/\/doi.org\/10.3390\/jpm11121388","journal-title":"J Personal Med"},{"key":"10401_CR8","doi-asserted-by":"publisher","first-page":"105161","DOI":"10.1016\/j.compbiomed.2021.105161","volume":"141","author":"P Dutande","year":"2022","unstructured":"Dutande P, Baid U, Talbar S (2022) Deep residual separable convolutional neural network for lung tumor segmentation. Comput Biol Med 141:105161. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.105161","journal-title":"Comput Biol Med"},{"key":"10401_CR9","doi-asserted-by":"publisher","first-page":"3281998","DOI":"10.1155\/2023\/3281998","volume":"2023","author":"MA Kassem","year":"2023","unstructured":"Kassem MA, Naguib SM, Hamza HM, Fouda MM, Saleh MK, Hosny KM (2023) Explainable transfer learning-based deep learning model for pelvis fracture detection. Int J Intell Syst 2023:3281998. https:\/\/doi.org\/10.1155\/2023\/3281998","journal-title":"Int J Intell Syst"},{"key":"10401_CR10","doi-asserted-by":"publisher","first-page":"5513500","DOI":"10.1155\/2021\/5513500","volume":"2021","author":"A Naseer","year":"2021","unstructured":"Naseer A, Yasir T, Azhar A, Shakeel T, Zafar K (2021) Computer-aided brain tumor diagnosis: performance evaluation of deep learner CNN using augmented brain MRI. Int J Biomed Imaging 2021:5513500. https:\/\/doi.org\/10.1155\/2021\/5513500","journal-title":"Int J Biomed Imaging"},{"issue":"4","key":"10401_CR11","doi-asserted-by":"publisher","first-page":"1607","DOI":"10.1007\/s13347-021-00477-0","volume":"34","author":"WJ von Eschenbach","year":"2021","unstructured":"von Eschenbach WJ (2021) Transparency and the black box problem: why we do not trust ai. Philosop Technol 34(4):1607\u20131622. https:\/\/doi.org\/10.1007\/s13347-021-00477-0","journal-title":"Philosop Technol"},{"issue":"2","key":"10401_CR12","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s00779-023-01730-3","volume":"28","author":"C Zhang","year":"2024","unstructured":"Zhang C, He J, Shang L (2024) An X-ray image classification method with fine-grained features for explainable diagnosis of pneumoconiosis. Pers Ubiquit Comput 28(2):403\u2013415. https:\/\/doi.org\/10.1007\/s00779-023-01730-3","journal-title":"Pers Ubiquit Comput"},{"issue":"1","key":"10401_CR13","doi-asserted-by":"publisher","first-page":"10415","DOI":"10.1038\/s41598-023-37560-9","volume":"13","author":"T Kim","year":"2023","unstructured":"Kim T, Moon NH, Goh TS, Jung ID (2023) Detection of incomplete atypical femoral fracture on anteroposterior radiographs via explainable artificial intelligence. Sci Rep 13(1):10415. https:\/\/doi.org\/10.1038\/s41598-023-37560-9","journal-title":"Sci Rep"},{"issue":"3","key":"10401_CR14","doi-asserted-by":"publisher","first-page":"561","DOI":"10.3390\/diagnostics13030561","volume":"13","author":"E Ghafourian","year":"2023","unstructured":"Ghafourian E, Samadifam F, Fadavian H, Jerfi Canatalay P, Tajally A, Channumsin S (2023) An ensemble model for the diagnosis of brain tumors through MRIs. Diagnostics 13(3):561. https:\/\/doi.org\/10.3390\/diagnostics13030561","journal-title":"Diagnostics"},{"key":"10401_CR15","unstructured":"Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, Van Leemput K (2014) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34:1993\u20132024, BRATS 2014 Dataset. Available online: https:\/\/www.smir.ch\/BRATS\/Start2014."},{"key":"10401_CR16","unstructured":"Hamada A (2020) Br35H Brain Tumor Detection 2020 Dataset. Available online: https:\/\/www.kaggle.com\/ahmedhamada0\/brain-tumor-detection."},{"issue":"6","key":"10401_CR17","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.3390\/s21062222","volume":"21","author":"J Kang","year":"2021","unstructured":"Kang J, Ullah Z, Gwak J (2021) MRI-based brain tumor classification using ensemble of deep features and machine learning classifiers. Sensors 21(6):2222. https:\/\/doi.org\/10.3390\/s21062222","journal-title":"Sensors"},{"issue":"1","key":"10401_CR18","doi-asserted-by":"publisher","first-page":"312","DOI":"10.3390\/app13010312","volume":"13","author":"AW Reza","year":"2023","unstructured":"Reza AW, Hossain MS, Wardiful M, Farzana M, Ahmad S, Alam F, Nandi RN, Siddique N (2023) A CNN-based strategy to classify MRI-based brain tumors using deep convolutional network. Appl Sci 13(1):312. https:\/\/doi.org\/10.3390\/app13010312","journal-title":"Appl Sci"},{"key":"10401_CR19","unstructured":"Brain Tumor Dataset|Kaggle. Available online: https:\/\/www.kaggle.com\/datasets\/nniisshhaann\/braintumors."},{"key":"10401_CR20","unstructured":"Cheng J (2017) brain tumor dataset. https:\/\/figshare.com\/articles\/dataset\/brain_tumor_dataset\/1512427. Accessed on 6 September 2023."},{"issue":"26","key":"10401_CR21","doi-asserted-by":"publisher","first-page":"37541","DOI":"10.1007\/s11042-022-13545-0","volume":"81","author":"A Verma","year":"2022","unstructured":"Verma A, Singh VP (2022) Design, analysis, and implementation of efficient deep learning frameworks for brain tumor classification. Multimed Tools Appl 81(26):37541\u201337567. https:\/\/doi.org\/10.1007\/s11042-022-13545-0","journal-title":"Multimed Tools Appl"},{"issue":"4","key":"10401_CR22","doi-asserted-by":"publisher","first-page":"955","DOI":"10.3390\/electronics12040955","volume":"12","author":"MA G\u00f3mez-Guzm\u00e1n","year":"2023","unstructured":"G\u00f3mez-Guzm\u00e1n MA, Jim\u00e9nez-Berista\u00edn L, Garc\u00eda-Guerrero EE, L\u00f3pez-Bonilla OR, Tamayo-Perez UJ, Esqueda-Elizondo JJ, Palomino-Vizcaino K, Inzunza-Gonz\u00e1lez E (2023) Classifying brain tumors on magnetic resonance imaging by using convolutional neural networks. Electronics 12(4):955. https:\/\/doi.org\/10.3390\/electronics12040955","journal-title":"Electronics"},{"key":"10401_CR23","unstructured":"Brain Tumor Classification (MRI)|Kaggle. Available online: https:\/\/www.kaggle.com\/sartajbhuvaji\/brain-tumor-classification-mri\/metadata."},{"issue":"4","key":"10401_CR24","doi-asserted-by":"publisher","first-page":"668","DOI":"10.3390\/diagnostics13040668","volume":"13","author":"S Athisayamani","year":"2023","unstructured":"Athisayamani S, Antonyswamy RS, Sarveshwaran V, Almeshari M, Alzamil Y, Ravi V (2023) Feature extraction using a residual deep convolutional neural network (ResNet-152) and optimized feature dimension reduction for MRI brain tumor classification. Diagnostics 13(4):668. https:\/\/doi.org\/10.3390\/diagnostics13040668","journal-title":"Diagnostics"},{"issue":"1","key":"10401_CR25","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1007\/s11063-020-10398-2","volume":"53","author":"W Ayadi","year":"2021","unstructured":"Ayadi W, Elhamzi W, Charfi I, Atri M (2021) Deep CNN for brain tumor classification. Neural Process Lett 53(1):671\u2013700. https:\/\/doi.org\/10.1007\/s11063-020-10398-2","journal-title":"Neural Process Lett"},{"issue":"9","key":"10401_CR26","doi-asserted-by":"publisher","first-page":"13429","DOI":"10.1007\/s11042-020-10335-4","volume":"80","author":"RL Kumar","year":"2021","unstructured":"Kumar RL, Kakarla J, Isunuri BV, Singh M (2021) Multi-class brain tumor classification using residual network and global average pooling. Multimed Tools Appl 80(9):13429\u201313438. https:\/\/doi.org\/10.1007\/s11042-020-10335-4","journal-title":"Multimed Tools Appl"},{"issue":"1","key":"10401_CR27","doi-asserted-by":"publisher","first-page":"372","DOI":"10.3390\/s22010372","volume":"22","author":"MF Alanazi","year":"2022","unstructured":"Alanazi MF, Ali MU, Hussain SJ, Zafar A, Mohatram M, Irfan M, AlRuwaili R, Alruwaili M, Ali NH, Albarrak AM (2022) Brain tumor\/mass classification framework using magnetic-resonance-imaging-based isolated and developed transfer deep-learning model. Sensors 22(1):372. https:\/\/doi.org\/10.3390\/s22010372","journal-title":"Sensors"},{"issue":"21","key":"10401_CR28","doi-asserted-by":"publisher","first-page":"3457","DOI":"10.3390\/electronics11213457","volume":"11","author":"GA Amran","year":"2022","unstructured":"Amran GA, Alsharam MS, Blajam AOA, Hasan AA, Alfaifi MY, Amran MH, Gumaei A, Eldin SM (2022) Brain tumor classification and detection using hybrid deep tumor network. Electronics 11(21):3457. https:\/\/doi.org\/10.3390\/electronics11213457","journal-title":"Electronics"},{"key":"10401_CR29","doi-asserted-by":"publisher","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical evaluation of rectified activations in convolutional network. arXiv preprintarXiv:1505.00853https:\/\/doi.org\/10.48550\/arXiv.1505.00853","DOI":"10.48550\/arXiv.1505.00853"},{"key":"10401_CR30","doi-asserted-by":"publisher","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp 4700\u20134708. https:\/\/doi.org\/10.48550\/arXiv.1608.06993","DOI":"10.48550\/arXiv.1608.06993"},{"key":"10401_CR31","doi-asserted-by":"publisher","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826. https:\/\/doi.org\/10.48550\/arXiv.1512.00567","DOI":"10.48550\/arXiv.1512.00567"},{"issue":"2","key":"10401_CR32","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2020) Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vision 128(2):336\u2013359. https:\/\/doi.org\/10.1007\/s11263-019-01228-7","journal-title":"Int J Comput Vision"},{"issue":"10","key":"10401_CR33","doi-asserted-by":"publisher","first-page":"e0140381","DOI":"10.1371\/journal.pone.0140381","volume":"10","author":"J Cheng","year":"2015","unstructured":"Cheng J, Huang W, Cao S, Yang R, Yang W, Yun Z, Wang Z, Feng Q (2015) Enhanced performance of brain tumor classification via tumor region augmentation and partition. PLOS ONE 10(10):e0140381. https:\/\/doi.org\/10.1371\/journal.pone.0140381","journal-title":"PLOS ONE"},{"issue":"6","key":"10401_CR34","doi-asserted-by":"publisher","first-page":"e0157112","DOI":"10.1371\/journal.pone.0157112","volume":"11","author":"J Cheng","year":"2016","unstructured":"Cheng J, Yang W, Huang M, Huang W, Jiang J, Zhou Y, Yang R, Zhao J et al (2016) Retrieval of brain tumors by adaptive spatial pooling and fisher vector representation. PLOS ONE 11(6):e0157112. https:\/\/doi.org\/10.1371\/journal.pone.0157112","journal-title":"PLOS ONE"},{"issue":"1","key":"10401_CR35","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"issue":"3","key":"10401_CR36","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang C, Bengio S, Hardt M, Recht B, Vinyals O (2021) Understanding deep learning (still) requires rethinking generalization. Commun ACM 64(3):107\u2013115. https:\/\/doi.org\/10.1145\/3446776","journal-title":"Commun ACM"},{"key":"10401_CR37","doi-asserted-by":"publisher","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980. https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"10401_CR38","doi-asserted-by":"publisher","unstructured":"Grandini M, Bagli E, Visani G (2020) Metrics for multi-class classification: an overview. arXiv preprint arXiv:2008.05756. https:\/\/doi.org\/10.48550\/arXiv.2008.05756.","DOI":"10.48550\/arXiv.2008.05756."},{"issue":"4","key":"10401_CR39","doi-asserted-by":"publisher","first-page":"602","DOI":"10.3390\/brainsci13040602","volume":"13","author":"Z Rasheed","year":"2023","unstructured":"Rasheed Z, Ma Y-K, Ullah I, al Shloul T, bin Tufail A, Ghadi YY, Khan MZ, Mohamed HG (2023) Automated classification of brain tumors from magnetic resonance imaging using deep learning. Brain Sci 13(4):602. https:\/\/doi.org\/10.3390\/brainsci13040602","journal-title":"Brain Sci"},{"issue":"15","key":"10401_CR40","doi-asserted-by":"publisher","first-page":"9075","DOI":"10.1007\/s00521-020-05671-3","volume":"33","author":"AM Alhassan","year":"2021","unstructured":"Alhassan AM, Zainon WMNW (2021) Brain tumor classification in magnetic resonance image using hard swish-based RELU activation function-convolutional neural network. Neural Comput Appl 33(15):9075\u20139087. https:\/\/doi.org\/10.1007\/s00521-020-05671-3","journal-title":"Neural Comput Appl"},{"issue":"3","key":"10401_CR41","doi-asserted-by":"publisher","first-page":"679","DOI":"10.3390\/pr11030679","volume":"11","author":"PP Malla","year":"2023","unstructured":"Malla PP, Sahu S, Alutaibi AI (2023) Classification of tumor in brain MR images using deep convolutional neural network and global average pooling. Processes 11(3):679. https:\/\/doi.org\/10.3390\/pr11030679","journal-title":"Processes"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10401-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10401-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10401-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T04:33:08Z","timestamp":1737693188000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10401-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10401"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10401-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"17 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article contains no studies with human participants performed by any authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}