Optimization-Driven Hybrid Machine Learning Framework for Brain Tumor Classification in MRI with Metaheuristic Feature Selection
Diagnostics · 09.03.2026 · 16 (5) · 819
DOI: 10.3390/diagnostics16050819 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 09.03.2026. Verfasst von Yasin Özkan und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Technologies, Zonguldak Bülent Ecevit University, Zonguldak 67100, Türkiye. Die Arbeit wurde bisher 37-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: Brain tumors are among the most severe neurological disorders, and their variability in size, morphology, and anatomical location complicates early and accurate diagnosis. Although magnetic resonance imaging (MRI) is the most reliable non-invasive modality for tumor detection, manual interpretation remains time-consuming, subjective, and susceptible to human error. This study aims to develop an optimization-driven hybrid machine learning framework for accurate and computationally efficient automatic brain tumor classification.
Methods
The dataset includes 834 MRI images (583-training, 123-validation, 128-independent test). Because YOLOv11 detects tumor and non-tumor regions separately, the sample size doubled during region-based analysis, and all subsequent stages were conducted at the regions of interest (ROI) level. On the independent test set, YOLOv11 achieved 98.87% mAP@50, 98.54% precision, and 98.21% recall. The proposed framework combines automated tumor localization with image standardization using Gaussian noise reduction and bilinear interpolation. From the processed MR images, 39 entropy-based features were extracted. To enhance diagnostic performance and eliminate redundant information, the superb fairy-wren optimization algorithm (SFOA) was applied for feature selection and compared with particle swarm optimization (PSO), Harris hawk optimization (HHO), and puma optimization (PO). Final classification was primarily performed using k-nearest neighbors (kNN), while support vector machines (SVM) were used for comparative evaluation.
Results
SFOA reduced the feature dimensionality from 39 to 5 features while achieving 99.20% classification accuracy on the independent test set. In comparison, PSO selected 10 features, HHO selected 6 features and PO selected 10 features, all achieving 98.45% accuracy. The best performance obtained with SVM was 98.45% accuracy (HHO-SVM), which remained lower than the 99.20% achieved by the proposed SFOA-kNN model.
Conclusions
The results indicate that combining entropy-based feature extraction with SFOA-driven feature selection and kNN classification significantly enhances diagnostic accuracy while reducing computational complexity, highlighting the strong potential of the proposed framework for integration into computer-aided diagnosis systems to support clinical decision-making.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Technologies, Zonguldak Bülent Ecevit University, Zonguldak 67100, Türkiye.
- Department of Electrical Electronics Engineering, Zonguldak Bülent Ecevit University, Zonguldak 67100, Türkiye.
ORCID-Profile: Yasin Özkan, Aytaç Altan
Zitieren
APA
Özkan, Y., Özçelik, Y. B., & Altan, A. (2026). Optimization-Driven Hybrid Machine Learning Framework for Brain Tumor Classification in MRI with Metaheuristic Feature Selection. Diagnostics, 16(5), 819. https://doi.org/10.3390/diagnostics16050819
Vancouver
Özkan Y, Özçelik YB, Altan A. Optimization-Driven Hybrid Machine Learning Framework for Brain Tumor Classification in MRI with Metaheuristic Feature Selection. Diagnostics. 2026;16(5):819. doi:10.3390/diagnostics16050819
BibTeX
@article{zkan2026,
author = {Özkan, Yasin and Özçelik, Yusuf Bahri and Altan, Aytaç},
title = {Optimization-Driven Hybrid Machine Learning Framework for Brain Tumor Classification in MRI with Metaheuristic Feature Selection},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {5},
pages = {819},
doi = {10.3390/diagnostics16050819}
}
EUVIMED