EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Comparative Analysis of CNN, ResNet50, and Vision Transformer Architectures for Brain Tumor Classification from MRI Images

Matthieu Kayembe, Franklin Mwamba, Pierre Kafunda, Fiston Oshasha, John Poma

Journal of Applied Informatics and Computing · 10.06.2026 · 10 (3) · 2327-2335

DOI: 10.30871/jaic.v10i3.12699 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 10.06.2026. Verfasst von Matthieu Kayembe und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The classification of brain tumors from Magnetic Resonance Imaging (MRI) is a crucial task in computer-aided medical diagnosis. Recent advances in deep learning have significantly improved performance in this domain. In this work, a comparative analysis of three architectures is conducted: a Convolutional Neural Network (CNN) trained from scratch, a transfer learning-based model using ResNet50, and a Vision Transformer (ViT). The models are evaluated on a multi-class dataset containing four categories: glioma, meningioma, pituitary tumor, and no tumor. Experimental results show that the CNN achieves limited performance with moderate generalization capability. The ResNet50 model reaches high accuracy during training but suffers from severe overfitting, leading to a significant drop in performance on the test set. In contrast, the Vision Transformer achieves the best overall performance, with a test accuracy of 0.76 and a good balance between precision and recall. These results highlight the effectiveness of Transformer-based architectures for complex medical image classification tasks.

Zitieren

APA

Kayembe, M., Mwamba, F., Kafunda, P., Oshasha, F., & Poma, J. (2026). Comparative Analysis of CNN, ResNet50, and Vision Transformer Architectures for Brain Tumor Classification from MRI Images. Journal of Applied Informatics and Computing, 10(3), 2327-2335. https://doi.org/10.30871/jaic.v10i3.12699

Vancouver

Kayembe M, Mwamba F, Kafunda P, Oshasha F, Poma J. Comparative Analysis of CNN, ResNet50, and Vision Transformer Architectures for Brain Tumor Classification from MRI Images. Journal of Applied Informatics and Computing. 2026;10(3):2327-2335. doi:10.30871/jaic.v10i3.12699

BibTeX
@article{Kayembe2026,
  author = {Kayembe, Matthieu and Mwamba, Franklin and Kafunda, Pierre and Oshasha, Fiston and Poma, John},
  title = {Comparative Analysis of CNN, ResNet50, and Vision Transformer Architectures for Brain Tumor Classification from MRI Images},
  journal = {Journal of Applied Informatics and Computing},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {2327--2335},
  doi = {10.30871/jaic.v10i3.12699}
}
Kostenlos starten →