An End-to-End Multi-Head Attention-Based Deep Learning Model for Enhanced Brain Tumor Detection Using MRI
Received: 26 August 2025 | Revised: 26 September 2025, 13 October 2025, 14 October 2025, 16 October 2025, and 18 October 2025 | Accepted: 21 October 2025 | Online: 6 November 2025
Corresponding author: V. Chanemougavel
Abstract
In recent years, the healthcare field has been significantly transformed by advances in technology, with Artificial Intelligence (AI) playing an important role in this process. AI refers to digital systems that emulate human-like intelligence and are widely applied in healthcare. Brain Tumors (BTs), which result from abnormal cell growth in the central nervous system, pose great difficulties in diagnosis and treatment. An early and precise diagnosis is vital for effective treatment. With the help of Magnetic Resonance Imaging (MRI), Deep Learning (DL) models can recognize and classify BTs, aiding in their rapid and easy detection. For accurate detection of BTs, this study presents an Advanced Brain Tumor Classification by integrating DL Models and Optimization Techniques (ABTC-IDLMOT) in biomedical imaging. The objective was to classify the affected BT region using a fine-tuned multi-head attention-based DL model. Initially, preprocessing employs the Wiener Filter (WF) for noise removal and Otsu's threshold for skull removal. In addition, EfficientNetV2M is utilized for feature extraction. Then, a Convolutional Neural Network-based Multi-Head Attention (CNN-MHA) model is used for BT classification. Finally, RMSProp optimization is used to tune the hyperparameters and improve the classification performance of CNN-MHA. The experimental study uses a benchmark MRI dataset. Performance validation of the ABTC-IDLMOT approach showed an accuracy of 96.65%.
Keywords:
deep learning, brain tumor classification, RMSProp, preprocessing, biomedical imagingDownloads
References
Z. Li and X. Zhou, ''A Global-Local Parallel Dual-Branch Deep Learning Model with Attention-Enhanced Feature Fusion for Brain Tumor MRI Classification.,'' Computers, Materials & Continua, vol. 83, no. 1, Apr. 2025, Art. no. 739. DOI: https://doi.org/10.32604/cmc.2025.059807
R. Vankdothu, M. A. Hameed, and H. Fatima, “A Brain Tumor Identification and Classification Using Deep Learning based on CNN-LSTM Method,” Computers and Electrical Engineering, vol. 101, July 2022, Art. no. 107960. DOI: https://doi.org/10.1016/j.compeleceng.2022.107960
X. Gu, Z. Shen, J. Xue, Y. Fan, and T. Ni, ''Brain Tumor MR Image Classification Using Convolutional Dictionary Learning With Local Constraint,'' Frontiers in Neuroscience, vol. 15, May 2021. DOI: https://doi.org/10.3389/fnins.2021.679847
B. R. Sree et al., ''Brain Tumor Detection and Classification using Magnetic Resonance Imaging and Machine Learning Approaches,'' in 2022 6th International Conference on Computing Methodologies and Communication (ICCMC), Erode, India, Mar. 2022, pp. 1729–1734. DOI: https://doi.org/10.1109/ICCMC53470.2022.9754077
R. Sundarasekar and A. Appathurai, ''Efficient brain tumor detection and classification using magnetic resonance imaging,'' Biomedical Physics & Engineering Express, vol. 7, no. 5, Apr. 2021, Art. no. 055007. DOI: https://doi.org/10.1088/2057-1976/ac0ccc
L. J. Muhammad, I. Badi, A. A. Haruna, I. A. Mohammed, and O. S. Dada, ''Deep Learning Models for Classification of Brain Tumor with Magnetic Resonance Imaging Images Dataset,'' in Computational Intelligence in Oncology: Applications in Diagnosis, Prognosis and Therapeutics of Cancers, K. Raza, Ed. Springer, 2022, pp. 159–176. DOI: https://doi.org/10.1007/978-981-16-9221-5_9
T. Rohini and P. Praveen, ''An Intuitive Approach on Transfer Learning with an IBF+IHP Model for Stroke Classification and Prediction,'' Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19655–19660, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9031
M. Rasool, A. Noorwali, H. Ghandorh, N. A. Ismail, and W. M. S. Yafooz, ''Brain Tumor Classification using Deep Learning: A State-of-the-Art Review,'' Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16586–16594, Oct. 2024. DOI: https://doi.org/10.48084/etasr.8298
M. F. Khan, A. Iftikhar, H. Anwar, and S. A. Ramay, ''Brain Tumor Segmentation and Classification using Optimized Deep Learning,'' Journal of Computing & Biomedical Informatics, vol. 7, no. 01, pp. 632–640, June 2024.
M. Geetha, V. Srinadh, J. Janet, and S. Sumathi, ''Hybrid Archimedes Sine Cosine optimization enabled Deep Learning for multilevel brain tumor classification using MRI images,'' Biomedical Signal Processing and Control, vol. 87, Jan. 2024, Art. no. 105419. DOI: https://doi.org/10.1016/j.bspc.2023.105419
S. Singh and V. Saxena, ''Classification and Segmentation of MRI Images of Brain Tumors Using Deep Learning and Hybrid Approach,'' International Journal of Electrical and Computer Engineering Systems, vol. 15, no. 2, pp. 163–172, Feb. 2024. DOI: https://doi.org/10.32985/ijeces.15.2.5
A. Sahu, P. K. Das, I. Paul, and S. Meher, ''A Hybrid Deep Learning Framework for Automatic Detection of Brain Tumours Using Different Modalities,'' IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 9, no. 2, pp. 1216–1225, Apr. 2025. DOI: https://doi.org/10.1109/TETCI.2024.3442889
S. Tabatabaei, K. Rezaee, and M. Zhu, ''Attention transformer mechanism and fusion-based deep learning architecture for MRI brain tumor classification system,'' Biomedical Signal Processing and Control, vol. 86, Sept. 2023, Art. no. 105119. DOI: https://doi.org/10.1016/j.bspc.2023.105119
S. Rajendran et al., ''Automated Segmentation of Brain Tumor MRI Images Using Deep Learning,'' IEEE Access, vol. 11, pp. 64758–64768, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3288017
M. Aamir et al., ''A deep learning approach for brain tumor classification using MRI images,'' Computers and Electrical Engineering, vol. 101, July 2022, Art. no. 108105. DOI: https://doi.org/10.1016/j.compeleceng.2022.108105
P. Κ. Tiwary, P. Johri, A. Katiyar, and M. K. Chhipa, ''Deep Learning-Based MRI Brain Tumor Segmentation With EfficientNet-Enhanced UNet,'' IEEE Access, vol. 13, pp. 54920–54937, 2025. DOI: https://doi.org/10.1109/ACCESS.2025.3554405
K. Deng et al., ''OS-DETR: End-to-end brain tumor detection framework based on orthogonal channel shuffle networks,'' PLOS ONE, vol. 20, no. 5, 2025, Art. no. e0320757. DOI: https://doi.org/10.1371/journal.pone.0320757
H. Zhu, J. Huang, K. Chen, X. Ying, and Y. Qian, ''multiPI-TransBTS: A Multi-Path Learning Framework for Brain Tumor Image Segmentation Based on Multi-Physical Information.'' arXiv, Sept. 18, 2024. DOI: https://doi.org/10.1016/j.compbiomed.2025.110148
V. Sharma, M. Kumar, and A. K. Yadav, ''3D AIR-UNet: attention–inception–residual-based U-Net for brain tumor segmentation from multimodal MRI,'' Neural Computing and Applications, vol. 37, no. 16, pp. 9969–9990, June 2025. DOI: https://doi.org/10.1007/s00521-025-11105-9
M. Moshfegh, M. Nikpour, and M. Mobini, ''Wavelet-based Denoising of Magnetic Resonance Images Using Optimized Exponential Function Thresholding and Wiener Filter,'' International Journal of Engineering, vol. 37, no. 12, pp. 2560–2569, 2024. DOI: https://doi.org/10.5829/ije.2024.37.12c.14
K. Wisaeng and W. Sa-ngiamvibool, ''Brain Tumor Segmentation Using Fuzzy Otsu Threshold Morphological Algorithm.'' IAENG International Journal of Applied Mathematics, vol.53, no. 2, pp .1-12, June 2023.
G. M. S. Himel, M. M. Islam, and M. Rahaman, ''Utilizing EfficientNet for sheep breed identification in low-resolution images,'' Systems and Soft Computing, vol. 6, Dec. 2024, Art. no. 200093. DOI: https://doi.org/10.1016/j.sasc.2024.200093
F. Mehmood, S. Ahmad, and T. K. Whangbo, ''An Efficient Optimization Technique for Training Deep Neural Networks,'' Mathematics, vol. 11, no. 6, Jan. 2023, Art. no. 1360. DOI: https://doi.org/10.3390/math11061360
M. Nickparvar, ''Brain Tumor MRI Dataset.'' Kaggle, Available: https://www.kaggle.com/datasets/masoudnickparvar/brain-tumor-mri-dataset.
Downloads
How to Cite
License
Copyright (c) 2025 V. Chanemougavel, K. Jayanthi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
