{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:38:55Z","timestamp":1787027935719,"version":"build-2736575974"},"reference-count":32,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EDA Hospital","award":["EDCHT114001"],"award-info":[{"award-number":["EDCHT114001"]}]},{"name":"EDA Hospital","award":["NSTC 113-2221-E-214-007"],"award-info":[{"award-number":["NSTC 113-2221-E-214-007"]}]},{"name":"National Science and Technology Council, Taiwan","award":["EDCHT114001"],"award-info":[{"award-number":["EDCHT114001"]}]},{"name":"National Science and Technology Council, Taiwan","award":["NSTC 113-2221-E-214-007"],"award-info":[{"award-number":["NSTC 113-2221-E-214-007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Accurate classification of brain tumors is critical for treatment planning and prognosis. While deep convolutional neural networks (CNNs) have shown promise in medical imaging, few studies have systematically compared multiple architectures or integrated ensemble strategies to improve diagnostic performance. This study aimed to evaluate various CNN models and optimize classification performance using a majority voting ensemble approach on T1-weighted MRI brain images. Methods: Seven pretrained CNN architectures were fine-tuned to classify four categories: glioblastoma, meningioma, pituitary adenoma, and no tumor. Each model was trained using two optimizers (SGDM and ADAM) and evaluated on a public dataset split into training (70%), validation (10%), and testing (20%) subsets, and further validated on an independent external dataset to assess generalizability. A majority voting ensemble was constructed by aggregating predictions from all 14 trained models. Performance was assessed using accuracy, Kappa coefficient, true positive rate, precision, confusion matrix, and ROC curves. Results: Among individual models, GoogLeNet and Inception-v3 with ADAM achieved the highest classification accuracy (0.987). However, the ensemble approach outperformed all standalone models, achieving an accuracy of 0.998, a Kappa coefficient of 0.997, and AUC values above 0.997 for all tumor classes. The ensemble demonstrated improved sensitivity, precision, and overall robustness. Conclusions: The majority voting ensemble of diverse CNN architectures significantly enhanced the performance of MRI-based brain tumor classification, surpassing that of any single model. These findings underscore the value of model diversity and ensemble learning in building reliable AI-driven diagnostic tools for neuro-oncology.<\/jats:p>","DOI":"10.3390\/diagnostics15141782","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T08:04:41Z","timestamp":1752566681000},"page":"1782","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Majority Voting Ensemble of Deep CNNs for Robust MRI-Based Brain Tumor Classification"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4661-0248","authenticated-orcid":false,"given":"Kuo-Ying","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Radiology, E-DA Cancer Hospital, I-Shou University, No. 21, Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung 82445, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1881-3504","authenticated-orcid":false,"given":"Nan-Han","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Radiology, E-DA Cancer Hospital, I-Shou University, No. 21, Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung 82445, Taiwan"},{"name":"School of Medicine, College of Medicine, I-Shou University, No. 8, Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung 82445, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3808-9998","authenticated-orcid":false,"given":"Yung-Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiological Science, I-Shou University, No. 8, Yida Road, Jiao-Su Village, Yan-Chao District, Kaohsiung 82445, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akari","family":"Matsushima","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Tokyo 173-8605, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Koharu","family":"Kimura","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Tokyo 173-8605, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takahide","family":"Okamoto","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Tokyo 173-8605, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai-Been","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiological Technology, Teikyo University, Tokyo 173-8605, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"AlTahhan, F.E., Khouqeer, G.A., Saadi, S., Elgarayhi, A., and Sallah, M. (2023). Refined automatic brain tumor classification using hybrid convolutional neural networks for MRI scans. Diagnostics, 13.","DOI":"10.3390\/diagnostics13050864"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Albalawi, E., Thakur, A., Dorai, D.R., Bhatia Khan, S., Mahesh, T.R., Almusharraf, A., Aurangzeb, K., and Anwar, M.S. (2024). Enhancing brain tumor classification in MRI scans with a multi-layer customized convolutional neural network approach. Front. Comput. Neurosci., 18.","DOI":"10.3389\/fncom.2024.1418546"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Nahiduzzaman, M., Abdulrazak, L.F., Kibria, H.B., Khandakar, A., Ayari, M.A., Ahamed, M.F., Ahsan, M., Haider, J., Moni, M.A., and Kowalski, M. (2025). A hybrid explainable model based on advanced machine learning and deep learning models for classifying brain tumors using MRI images. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-85874-7"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hassan, E., and Ghadiri, H. (2025). Advancing brain tumor classification: A robust framework using EfficientNetV2 transfer learning and statistical analysis. Comput. Biol. Med., 185.","DOI":"10.1016\/j.compbiomed.2024.109542"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"e270323214998","DOI":"10.2174\/1573405620666230327124902","article-title":"Classification of brain tumours in MRI images using a convolutional neural network","volume":"20","author":"Gupta","year":"2024","journal-title":"Curr. Med. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kusuma, P.V., and Reddy, S.C.M. (2025). Brain tumor segmentation and classification using MRI: Modified segnet model and hybrid deep learning architecture with improved texture features. Comput. Biol. Chem., 117.","DOI":"10.1016\/j.compbiolchem.2025.108381"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Disci, R., Gurcan, F., and Soylu, A. (2025). Advanced brain tumor classification in MR images using transfer learning and pre-trained deep CNN models. Cancers, 17.","DOI":"10.3390\/cancers17010121"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ali, R.R., Yaacob, N.M., Alqaryouti, M.H., Sadeq, A.E., Doheir, M., Iqtait, M., Rachmawanto, E.H., Sari, C.A., and Yaacob, S.S. (2025). Learning architecture for brain tumor classification based on deep convolutional neural network: Classic and ResNet50. Diagnostics, 15.","DOI":"10.3390\/diagnostics15050624"},{"key":"ref_9","doi-asserted-by":"crossref","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":"Nazarov","year":"2023","journal-title":"Asian Pac. J. Cancer Prev."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Aurna, N.F., Yousuf, M.A., Taher, K.A., Azad, A.K.M., and Moni, M.A. (2022). A classification of MRI brain tumor based on two stage feature level ensemble of deep CNN models. Comput. Biol. Med., 146.","DOI":"10.1016\/j.compbiomed.2022.105539"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_13","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th In-ternational Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2018, January 18\u201323). MobileNetV2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2016, January 27\u201330). Rethinking the Inception architecture for computer vision. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Iqbal, S., Qureshi, A.N., Alhussein, M., Aurangzeb, K., Choudhry, I.A., and Anwar, M.S. (2024). Hybrid deep spatial and statistical feature fusion for accurate MRI brain tumor classification. Front. Comput. Neurosci., 18.","DOI":"10.3389\/fncom.2024.1423051"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Elhadidy, M.S., Elgohr, A.T., El-Geneedy, M., Akram, S., and Kasem, H.M. (2025). Comparative analysis for accurate multi-classification of brain tumor based on significant deep learning models. Comput. Biol. Med., 188.","DOI":"10.1016\/j.compbiomed.2025.109872"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Abirami, S., Ramesh, K., and Lalitha VaniSree, K. (2025). Classification and pixel change detection of brain tumor using Adam Kooka-burra optimization-based Shepard convolutional neural network. NMR Biomed., 38.","DOI":"10.1002\/nbm.5307"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Alsubai, S., Khan, H.U., Alqahtani, A., Sha, M., Abbas, S., and Mohammad, U.G. (2022). Ensemble deep learning for brain tumor detection. Front. Comput. Neurosci., 16.","DOI":"10.3389\/fncom.2022.1005617"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tandel, G.S., Tiwari, A., and Kakde, O.G. (2025). Multi-class brain tumor grades classification using a deep learning-based majority voting algorithm and its validation using explainable-AI. J. Imaging Inform. Med.","DOI":"10.1007\/s10278-024-01368-4"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ait Amou, M., Xia, K., Kamhi, S., and Mouhafid, M. (2022). A novel MRI diagnosis method for brain tumor classification based on CNN and Bayesian optimization. Healthcare, 10.","DOI":"10.3390\/healthcare10030494"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1007\/s10278-022-00752-2","article-title":"Hybrid optimization algorithm enabled deep learning approach brain tumor segmentation and classification using MRI","volume":"36","author":"Deepa","year":"2023","journal-title":"J. Digit. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Amoury, S.E., Smili, Y., and Fakhri, Y. (2025). Design of an optimal convolutional neural network architecture for MRI brain tumor classification by exploiting particle swarm optimization. J. Imaging, 11.","DOI":"10.3390\/jimaging11020031"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e20200011","DOI":"10.1590\/1678-9199-jvatitd-2020-0011","article-title":"Inflammatory lesions and brain tumors: Is it possible to differentiate them based on texture features in magnetic resonance imaging?","volume":"26","author":"Alves","year":"2020","journal-title":"J. Venom. Anim. Toxins Incl. Trop. Dis."},{"key":"ref_25","first-page":"e80084","article-title":"Employing squeeze-and-excitation architecture in a fine-tuned convolutional neural network for magnetic resonance imaging tumor classification","volume":"17","author":"Huang","year":"2025","journal-title":"Cureus"},{"key":"ref_26","first-page":"1","article-title":"Hybrid fruit bee optimization algorithm-based deep convolution neural network for brain tumour classification using MRI images","volume":"28","author":"Jarria","year":"2025","journal-title":"Network"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102498","DOI":"10.1016\/j.compmedimag.2025.102498","article-title":"A novel generative model for brain tumor detection using magnetic resonance imaging","volume":"121","author":"Marques","year":"2025","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chandraprabha, K., Ganesan, L., and Baskaran, K. (2025). A novel approach for the detection of brain tumor and its classification via end-to-end vision transformer\u2014CNN architecture. Front. Oncol., 15.","DOI":"10.3389\/fonc.2025.1508451"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Afzal, S., Rauf, M., Ashraf, S., Bin Md Ayob, S., and Ahmad Arfeen, Z. (2025). CART-ANOVA-based transfer learning approach for seven distinct tumor classification schemes with generalization capability. Diagnostics, 15.","DOI":"10.3390\/diagnostics15030378"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hsu, W.W., Guo, J.M., Pei, L., Chiang, L.A., Li, Y.F., Hsiao, J.C., Colen, R., and Liu, P. (2022). A weakly supervised deep learning-based method for glioma subtype classification using WSI and mpMRIs. Sci. Rep., 12.","DOI":"10.1038\/s41598-022-09985-1"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"\u00d6zkaraca, O., Ba\u011fr\u0131a\u00e7\u0131k, O.\u0130., G\u00fcr\u00fcler, H., Khan, F., Hussain, J., Khan, J., and Laila, U.E. (2023). Multiple brain tumor classification with dense CNN architecture using brain MRI images. Life, 13.","DOI":"10.3390\/life13020349"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3596","DOI":"10.1038\/s41598-025-86752-y","article-title":"Dilated SE-DenseNet for brain tumor MRI classification","volume":"15","author":"Mao","year":"2025","journal-title":"Sci Rep."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/14\/1782\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:09:46Z","timestamp":1760033386000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/14\/1782"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":32,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["diagnostics15141782"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15141782","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]}}}