Multi-Objective Bio-Inspired Hyperparameter Optimization for Trustworthy Brain Tumor MRI Classification Using Calibration-Aware CNN Models
Artificial Intelligence Systems and Its Applications · 2025
DOI: 10.65917/aisa.v1i2.45 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence Systems and Its Applications, 2025. Verfasst von Kafitra Marna Ibrahim und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Automated brain tumor classification from magnetic resonance imaging (MRI) has become an essential component in advancing computer-aided diagnosis. However, many deep learning approaches prioritize accuracy alone while overlooking two key requirements for real-world medical deployment: the reliability of predicted confidence scores and the computational efficiency required for clinical integration. This study proposes a multi-objective bio-inspired hyperparameter optimization framework to produce convolutional neural network (CNN) models that are accurate, well-calibrated, and computationally efficient. The model is optimized using a Multi-Objective Particle Swarm Optimization (MOPSO) algorithm that jointly minimizes validation error, Expected Calibration Error (ECE), and inference latency. Experiments were conducted on a four-class Brain Tumor MRI dataset, and the optimized configuration achieved a test accuracy of 95 percent, an ECE of 1.48 percent, and a sub-millisecond inference latency of 0.88 milliseconds per sample. Grad-CAM visualizations further confirm that the model’s decisions are guided by clinically relevant tumor regions. The results demonstrate that multi-objective hyperparameter optimization offers a robust pathway for developing trustworthy, efficient, and interpretable artificial intelligence systems for medical imaging applications.
Zitieren
APA
Ibrahim, K. M., & Jayaputra, Z. Z. (2025). Multi-Objective Bio-Inspired Hyperparameter Optimization for Trustworthy Brain Tumor MRI Classification Using Calibration-Aware CNN Models. Artificial Intelligence Systems and Its Applications. https://doi.org/10.65917/aisa.v1i2.45
Vancouver
Ibrahim KM, Jayaputra ZZ. Multi-Objective Bio-Inspired Hyperparameter Optimization for Trustworthy Brain Tumor MRI Classification Using Calibration-Aware CNN Models. Artificial Intelligence Systems and Its Applications. 2025. doi:10.65917/aisa.v1i2.45
BibTeX
@article{Ibrahim2025,
author = {Ibrahim, Kafitra Marna and Jayaputra, Zaky Zaujan},
title = {Multi-Objective Bio-Inspired Hyperparameter Optimization for Trustworthy Brain Tumor MRI Classification Using Calibration-Aware CNN Models},
journal = {Artificial Intelligence Systems and Its Applications},
year = {2025},
doi = {10.65917/aisa.v1i2.45}
}
EUVIMED