Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification
JISKA (Jurnal Informatika Sunan Kalijaga) · 25.01.2026 · 11 (1) · 127-142
DOI: 10.14421/jiska.5860 ↗Kurz gefasst
Fachartikel in der Zeitschrift JISKA (Jurnal Informatika Sunan Kalijaga), online erschienen am 25.01.2026. Verfasst von Ahmad Fauzi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The automated categorization of brain cancers from MRI is essential for improving diagnostic precision. Traditional Convolutional Neural Networks (CNNs) are proficient in local feature extraction but are constrained in their ability to capture long-range spatial relationships, hence impairing performance on intricate malignancies. We propose a hybrid parallel architecture that merges a CNN with a Vision Transformer (ViT) to combine local and global feature modeling. We assessed our dual-branch model in comparison to a conventional CNN baseline using a curated dataset of 15,000 MRI images categorized into three classes: glioma, meningioma, and pituitary. The hybrid model exhibited enhanced performance, attaining 98.40% accuracy and 0.0783 loss, in contrast to the baseline's 97.40% accuracy and 0.1187 loss. The substantial decrease in misclassifications was validated by additional metrics, such as enhanced recall for the meningioma category. The integration of local and global variables produces a more precise, stable, and generalizable classification framework, demonstrating significant potential as a basis for dependable AI-driven Clinical Decision Support Systems (CDSS) in neuroradiology.
Zitieren
APA
Fauzi, A., Fuadi, A. L., & Yunial, A. H. (2026). Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification. JISKA (Jurnal Informatika Sunan Kalijaga), 11(1), 127-142. https://doi.org/10.14421/jiska.5860
Vancouver
Fauzi A, Fuadi AL, Yunial AH. Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification. JISKA (Jurnal Informatika Sunan Kalijaga). 2026;11(1):127-142. doi:10.14421/jiska.5860
BibTeX
@article{Fauzi2026,
author = {Fauzi, Ahmad and Fuadi, Achmad Lutfi and Yunial, Agus Heri},
title = {Comparative Analysis of Hybrid CNN-ViT and CNN for Brain Tumor Classification},
journal = {JISKA (Jurnal Informatika Sunan Kalijaga)},
year = {2026},
volume = {11},
number = {1},
pages = {127--142},
doi = {10.14421/jiska.5860}
}
EUVIMED