Robust Brain Tumor MRI Classification Through MobileNetV3 Deep Feature Fusion and Principal Component Analysis Enhanced AdaBoost Learning
Abstract
Among the most serious neurological diseases are brain tumors, which pose a challenge to early detection through MRI due to low contrast, tissue heterogeneity, and high-dimensional deep features that make it difficult for traditional classification models to be effective. This study proposes a robust and computationally efficient multi-class classification framework capable of distinguishing four tumor types: glioma, meningioma, pituitary tumor, and no tumor. The primary contributions are: (1) the development of a hybrid feature-learning pipeline that introduces a hybrid feature-learning framework in which a one-level 2D Discrete Wavelet Transform (2D-DWT) is employed as a multi-resolution preprocessing step to enhance MRI slices prior to deep feature extraction using MobileNetV3; (2) the application of Principal Component Analysis (PCA) to compress a 1,024-dimensional deep-feature vector into only 20 principal components, achieving a 99.96% reduction in dimensionality; (3) the use of an optimized AdaBoost ensemble specifically adapted for low-dimensional inputs; and (4) achieving performance that surpasses several published approaches evaluated on the same benchmark dataset. The proposed workflow includes cropping, normalization, and CLAHE enhancement, followed by 2D-DWT to extract LL, LH, HL, and HH sub-band information. The wavelet-refined MRI slices are processed by MobileNetV3 to implicitly encode spectral–textural information into deep semantic representations, which are subsequently reduced using PCA and classified by AdaBoost. Experiments conducted on a public Kaggle brain MRI dataset comprising 7023 images show that MobileNetV3 combined with 2D-DWT achieves an accuracy of 99.56%. When enhanced with PCA and AdaBoost, the full framework attains 99.94% accuracy, 99.95% precision, 99.96% recall, 99.94% F1-score, and 100% AUC, demonstrating remarkable tumor discrimination performance. In summary, the proposed PCA–AdaBoost hybrid framework offers a highly accurate, lightweight, and clinically promising solution for automated brain tumor MRI classification.
Downloads
References
T. A. Shaikh, S. Hakak, T. Rasool, and M. Wasid, "Machine Learning and Artificial Intelligence in Healthcare Systems", Boca Raton, FL, USA: CRC Press, 2023, doi: 10.1201/9781003265436.
S. Alsubai, H. U. Khan, A. Alqahtani, M. Sha, S. Abbas, and U. G. Mohammad “Ensemble deep learning for brain tumor detection”, Frontiers in Computational Neuroscience, Volume 16, pp.1-14, 2022, doi: 10.3389/fncom.2022.1005617.
N. F. Othman and S. W. Kareem, “Brain Tumor Classification Accuracy Using Deep Learning with Real and Synthetic MRI Images,” ZANCO Journal of Pure and Applied Sciences, pp. 126–149, 2025, doi: https://doi.org/10.21271/ZJPAS.37.4.11.
N. Ullah, A. Javed, A. Alhazmi, S. M. Hasnain, A. Tahir, and R. A. Id, “TumorDetNet : A unified deep learning model for brain tumor detection and classification,” PLOS ONE, pp. 1–24, 2023, doi: 10.1371/journal.pone.0291200.
Y. Sankararao, and K. Syed, “EBTSC- Enhanced Brain Tumor Segmentation and Classification Using U-Net ++ and Hybrid deep learning Method,” International Journal of Intelligent Engineering and Systems, Vol. 18, No. 10, pp. 933–948, 2025, doi: 10.22266/ijies2025.1130.59.
B. Ramu, R. B. Tummala, S. Siddamsetti, D. R. S. Victoria, D. Kishore, and N. M. Jyothi, “Accurate Brain Tumor Classification Using GoogLe Net and Extreme Learning Machine ( ELM ) With Multiple Features,” International Journal of Intelligent Engineering and Systems, Vol.18, No.11, 2025, doi: 10.22266/ijies2025.1231.22.
A. B. Abdusalomov, M. Mukhiddinov, and T. K. Whangbo, “Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging,” Cancers, pp. 1-29, 2023, 15, 4172, https://www.mdpi.com/2072-6694/15/16/4172.
H. M. Al-dabbas and M. S. Mahdi, “Classification of Brain Tumor Diseases Using Data Augmentation and Transfer Learning,” Iraqi Journal of Science, Vol. 65, No. 4, pp. 2275–2286, 2024, doi: 10.24996/ijs.2024.65.4.41.
M. M. Zahoor, S. H. Khan, T. J. Alahmadi, and T. Alsahfi, A. S. Al Mazroa, H. A. Sakr, S. Alqahtani, A. Albanyan, and B. K. Alshemaimri, “Brain Tumor MRI Classification Using a Novel Deep Residual,” Biomedicines, pp. 1–19, 2024, doi: 10.3390/biomedicines12071395.
S. Srinivasan, D. Francis, S. K. Mathivanan, H. Rajadurai, B. D. Shivahare, and M. A. Shah, “A hybrid deep CNN model for brain tumor image multi ‑ classification,” BMC Med. Imaging, pp. 1–21, 2024, doi: 10.1186/s12880-024-01195-7.
R. Khan, S. Taj, Z. U. Khan, S. U. Khan, J. Khan, T. Arshad, and S. Ayouni “High-precision brain tumor classification from MRI images using an advanced hybrid deep learning method with minimal radiation exposure,” J. Radiat. Res. Appl. Sci., vol. 18, no. 4, p. 101858, 2025, doi: 10.1016/j.jrras.2025.101858.
A. Rahman, M. Hayat, N. Iqbal, F. K. Alarfaj, S. Alkhalaf, and F. Alturise, “Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis,” Scientific Reports, pp. 1–15, 2025, doi: 10.1038/s41598-025-14901-4.
R. N. Asif, M. T. Naseem, M. Ahmad, T. Mazhar, M. A. Khan, M. A. Khan, A. Al-Rasheed, and H. Hamam, “Brain tumor detection empowered with ensemble deep learning approaches from MRI scan images,” Scientific Reports, pp. 1–22, 2025, doi: 10.1038/s41598-025-99576-7.
R. F. Jader, S. W. Kareem, and H. Q. Awla, “Ensemble Deep Learning Technique for Detecting MRI Brain Tumor,” Applied Computational Intelligence and Soft Computing, Vol. 2024, pp. 1-13, 2024, doi: 10.1155/2024/6615468.
M. I. Al-khuzaie and W. A. M. Al-jawher, “Enhancing Medical Image Classification : A Deep Learning Perspective with Multi Wavelet Transform,” Journal port Science Research, Vol. 6, No. 4, pp. 365–373, 2023, doi: 10.36371/port.2023.4.7.
F. M. J. M. Shamrat, S. Azam, A. Karim, R. Islam, Z. Tasnim, P. Ghosh and F. D. Boer, “LungNet22 : A Fine-Tuned Model for Multiclass Classification and Prediction of Lung Disease Using X-ray Images,” and prediction of lung disease using X-ray images”, Journal of Personalized Medicine, Vol. 12, No. 5, pp. 680, 2022, doi: 10.3390/jpm12050680.
S. N. Nia and F. Y. Shih, “Medical X Ray Image Enhancement Using Global Contrast Limited Adaptive Histogram Equalization,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 38, no. 12, Article 2457010, 2024, doi: 10.1142/S0218001424570106.
M. S. Z. Ahmad, N. A. Ab. Aziz, H. S. Lim, A. K. Ghazali, and A. A. Latiff, “Impact of Image Enhancement Using Contrast Limited Adaptive Histogram Equalization (CLAHE), Anisotropic Diffusion, and Histogram Equalization on Spine X Ray Segmentation with U Net, Mask R CNN, and Transfer Learning,” Algorithms, vol. 18, no. 12, Article 796, 2025, doi: 10.3390/a18120796.
M. Mehdizadeh, K. T. Tafti, and P. Soltani, “Evaluation of Histogram Equalization and Contrast Limited Adaptive Histogram Equalization Effect on Image Quality and Fractal Dimensions of Digital Periapical Radiographs,” Oral Radiology, vol. 39, no. 2, pp. 418–424, 2023, doi: 10.1007/s11282-022-00654-7.
V. D. Phan, L. C. Chan, A. H. A. Li, Y. T. Chien, and C. V. Nguyen, “Liver cancer prediction in a viral hepatitis cohort: A deep learning approach,” International Journal of Cancer, 147(10), pp. 2871-2878, 2020, doi: 10.1002/ijc.33245.
B. Sravani and M. S. Kumar, “A Hybrid Deep Ensemble Model for Precise Liver and Tumor Segmentation Using U-Net and W-Net Architectures,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, Vol. 8, No. 2, April 2026, pp: 553-571, 2026, doi: 10.35882/jeeemi.v8i2.1089.
A. A. Abdullah, A. Aldhahab, and H. M. Al Abboodi, “Deep-Ensemble Learning Models for the Detection and Classification of Eye Diseases Based on Engineering Feature Extraction with Efficientb6 and Densnet169,” Int. J. Intell. Eng. Syst., Vol. 17, No. 6, pp. 1001–1022, 2024, doi: 10.22266/ijies2024.1231.75.
S. G. Mallat, “A Theory for Multiresolution Signal Decomposition: The Wavelet Representation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 11, no. 7, pp. 674–693, 1989, doi: 10.1109/34.192463.
I. Daubechies, “Orthonormal Bases of Compactly Supported Wavelets,” Communications on Pure and Applied Mathematics, vol. 41, no. 7, pp. 909–996, 1988, doi: 10.1002/cpa.3160410705.
A. Aldhahab and W. B. Mikhael, “Face Recognition Employing DMWT Followed by FastICA,” Circuits, Syst. Signal Process., 2017, doi: 10.1007/s00034-017-0653-z.
A. G. Howard, M. Zhu and B. Chen, “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv preprint arXiv:1704.04861, 2017.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), pp. 4510–4520, 2018, doi: 10.1109/CVPR.2018.00474.
A. W. Al-funjan, H. M. Al Abboodi, N. A. Hamza, W. M. S. Abedi, and A. H. Abdullah, “A Lightweight Deep Learning-Based Ocular Disease Prediction Model Using Squeeze-and-Excitation Network Architecture with MobileNet Feature Extraction,” Int. J. Intell. Eng. Syst., Vol. 17, No. 4, pp. 243–262, 2024, doi: 10.22266/IJIES2024.0831.19.
A. Tharwat, “Principal component analysis - a tutorial,” Int. J. Appl. Pattern Recognit., Vol. 3, No. 3, pp. 197-240, 2016.
A. A. Abdullah, A. Aldhahab, and H. M. Al Abboodi, “Eye Disease Classification Based on Hybrid Deep Features with Principal Component Analysis and Blending Ensemble Learning,” Int. J. Intell. Eng. Syst., Vol. 18, No. 6, pp. 179–198, 2025, doi: 10.22266/ijies2025.0731.12.
M. Kuhn and K. Johnson, “Applied Predictive Modeling,” New York: Springer, Vol. 26, pp.1-13, 2013, doi: 10.1007/978-1-4614-6849-3.
F. WANG, Z. LI, F. HE, R. WANG, W. YU, and F. NIE, “Feature Learning Viewpoint of Adaboost and a New Algorithm,” IEEE Access, vol. 7, pp. 149890–149899, 2019, doi: 10.1109/ACCESS.2019.2947359.
Y. Freund and R. E. Schapire, “A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting,” J. Comput. Syst. Sci., Vol. 55, No. 1, pp. 119_139, Aug. 1997, doi: 10.1006/jcss.1997.1504.
P. Wu and H. Zhao, “Some Analysis and Research of the AdaBoost Algorithm,” International Conference on Intelligent Computing and Information Science. Berlin, Germany: Springer, pp. 1–5, 2011, doi: 10.1007/978-3-642-18129-0_1.
A. A. Abdullah, A. Aldhahab, and H. M. Al Abboodi, “Detection and Classification of Eye Diseases using Hybrid Deep Features with Decision Tree Algorithm,” 3rd Int. Conf. Adv. Eng. Sci. Technol. AEST 2024, vol. 2024, pp. 1–6, 2024, doi: 10.1109/AEST63017.2024.10960200.
S. Bala, K. Arora, R. Jeevitha, R. Chowdhury, P. Kumar, and S. N. C, “A Novel Encoder Decoder Architecture with Vision Transformer for Medical Image Segmentation,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, Vol. 7, No. 1, pp. 176–186, 2025, doi: 10.35882/jeeemi.v7i1.571.
M. K. Ismael, S. T. Bahar, and A. A. Abdullah, “Harmonic Elimination Method for Permanent Magnet Synchronous Motor Utilizing Active Disturbance Rejection Control,” Proceedings of Engineering and Technology Innovation, vol. 30, pp. 11–23, 2025, doi: https://doi.org/10.46604/peti.2024.14386.
A. C. Kemila, W. Fawwaz, and A. Maki, “Parameter Optimization of Support Vector Machine using River Formation Dynamic on Brain Tumor Classification,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, Vol. 5, No. 3, pp. 177–184, 2023, doi: 10.35882/jeemi.v5i3.312.
A. A. Abdullah, and M. Q. Hatem, “AUDIO TRANSMISSION THROUGH LI-FI,” International Journal of Civil Engineering and Technology, Vol. 9, No. 7, pp. 853–859, 2018, http://iaeme.com/Home/issue/IJCIET?Volume=9&Issue=7.
M. Gangappa, D. Manju, M. G. Krishnna, M. S. M. Reddy, M.Sathish, S. Shahabaaz, A. Shanthan, and M. Chaitanya, “Quantum-Enhanced Brain Tumor Detection and Progression Prediction Using MRI Imaging,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, Vol. 7, No. 2, pp. 493–507, 2025. doi: 10.35882/jeeemi.v7i2.720.
Copyright (c) 2026 Ahmed Aizaldeen Abdullah, Hadeel Safaa Hussein, Laith Ali Abdul Rahaim
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
