Global Journal of Engineering and Technology Research (GJETR) · Research article · Open access
Optimized Deep Convolutional Networks for MRI Brain Tumor Classification and Segmentation: A Systematic Review
Maher Talal Al-Asaady
26 October 2026 · Vol. 2, Issue 10, pp. 624-633
DOI: 10.65150/EP-gjetr/V2E10/2026-04 (registration with Crossref in progress)
Download full text (PDF)Cite this article
What is this article about?
Magnetic Resonance Imaging (MRI) is the primary modality for automated brain tumor detection, classification, and segmentation. While conventional Convolutional Neural Networks (CNNs) form the foundation of medical image analysis, they suffer from high computational overhead, local optima traps during hyperparameter tuning, and localized receptive fields that miss global anatomical context.
Article at a glance
- Published
- 26 October 2026
- Volume / issue / pages
- Vol. 2, Issue 10, pp. 624-633
- ISSN
- 3051-3782 (online) · 3051-3774 (print)
- Licence
- CC BY 4.0 — free to read and reuse with attribution
- Peer review
- Double-blind, at least two independent reviewers
- Publisher
- EP Journals Group
Abstract
Magnetic Resonance Imaging (MRI) is the primary modality for automated brain tumor detection, classification, and segmentation. While conventional Convolutional Neural Networks (CNNs) form the foundation of medical image analysis, they suffer from high computational overhead, local optima traps during hyperparameter tuning, and localized receptive fields that miss global anatomical context. This review systematically evaluates how algorithmic optimizations and hybrid architectures overcome these limitations. Through a multi-stage screening of 1,323 Scopus records published from 2021 to 2027 (including early-access publications), we analyze and compare 20 representative benchmark studies across four domains: (1) bio-inspired meta-heuristics for hyperparameter tuning and feature selection; (2) structural modifications integrating multiscale attention, dual-encoder U-Net and V-Net topologies, and wavelet compression for edge deployment; (3) hybrid frameworks pairing CNN extractors with Support Vector Machines, Long Short-Term Memory networks, Quantum Classifiers, and Graph Convolutional Networks; and (4) fusions of CNNs with Vision Transformers and 3D Mamba state-space models to capture long-range dependencies. Critically, our comparative study shows a complexity-performance compromise: sometimes heavy ensembles and hybrid classifiers fail to perform as well as streamlined architectures because of the saturation of the benchmark studies on the public 2D datasets. Finally, clinical translation will involve prioritizing cross-dataset generalization, linear-scaling efficiency, and quantitatively validated Explainable Artificial Intelligence (XAI).
Keywords: Brain tumor detection, convolutional neural networks, magnetic resonance imaging, meta-heuristic optimization
Cite this article
Maher Talal Al-Asaady (2026). Optimized Deep Convolutional Networks for MRI Brain Tumor Classification and Segmentation: A Systematic Review. Global Journal of Engineering and Technology Research, 2(10), 624-633. https://www.ep-journals.org/articles/optimized-deep-convolutional-networks-for-mri-brain-tumor-classification-and-8b963fc0
@article{Maher2026,
title = {Optimized Deep Convolutional Networks for MRI Brain Tumor Classification and Segmentation: A Systematic Review},
author = {Maher Talal Al-Asaady},
journal = {Global Journal of Engineering and Technology Research},
year = {2026},
volume = {2},
number = {10},
pages = {624-633},
url = {https://www.ep-journals.org/articles/optimized-deep-convolutional-networks-for-mri-brain-tumor-classification-and-8b963fc0}
}Questions about this article
Who wrote this article?
Maher Talal Al-Asaady.
Where and when was it published?
In Global Journal of Engineering and Technology Research, Volume 2, Issue 10, pages 624-633, published by EP Journals Group on 26 October 2026.
Is this article free to read?
Yes. It is open access under a Creative Commons Attribution 4.0 (CC BY 4.0) licence, so anyone can read, share and reuse it with attribution.
What is the DOI of this article?
10.65150/EP-gjetr/V2E10/2026-04. Registration with Crossref is in progress.
How do I cite this article?
APA: Maher Talal Al-Asaady (2026). Optimized Deep Convolutional Networks for MRI Brain Tumor Classification and Segmentation: A Systematic Review. Global Journal of Engineering and Technology Research, 2(10), 624-633. https://www.ep-journals.org/articles/optimized-deep-convolutional-networks-for-mri-brain-tumor-classification-and-8b963fc0
More research from GJETR
- Industry Micro-Credential Infusion in PQF Level 5 Technology Diploma Programs: Opportunities and Challenges
Gamaliel B. Vicente Jr., Alma O. Medio, Redjie D. Arcadio · Oct 2026
- Assessment of Process Mapping, Risk Management, and Iso 9001 Quality Management Standards: Basis for a Technology-Enabled Quality Management Framework
Patrick E. Arendain, Redjie D. Arcadio · Oct 2026
- Integrating Solar-Powered PV Cells And SCR-Controlled Three-Phase Rectifiers to Design A Two-Level DC Grid Architecture
Sadia Sultana Turna, Amzad Ali Sarkar · Oct 2026
- Density Functional Theory Investigation of Defect-Induced Electronic Behavior in Iodine-Deficient Mapbi₃ Perovskites for Solar Cells
Sani Kado, Muhammad Y. Onimisi, Dahiru M. Sanni · Sept 2026
- ParkIQ A Predictive Framework for Urban Parking and Accountable Kerbside Management
Syed Darda Rahman · Sept 2026