EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparative analysis of lightweight CNN, vision transformer and hybrid architectures for lung histopathological image classification

Doğu Manalı, Hasan Demirel

The Journal of Supercomputing · 22.06.2026 · 82 (9)

DOI: 10.1007/s11227-026-08653-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Supercomputing, online erschienen am 22.06.2026. Verfasst von Doğu Manalı und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Eastern Mediterranean University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents a comprehensive comparative analysis of 10 state-of-the-art lightweight deep learning architectures for lung histopathological image classification, encompassing Convolutional Neural Networks, Vision Transformers, and hybrid CNN–Transformer models. All architectures were evaluated under identical and fully deterministic experimental conditions on a balanced dataset of 15,000 images representing Lung Adenocarcinoma, Lung Squamous Cell Carcinoma, and benign lung tissue. Two different experimental settings were used to assess the performance of each model: training without data augmentation and training with augmentation techniques. Performance was assessed using Accuracy, F1-score, AUC, Sensitivity, Specificity, final training loss, average epoch time, inference time, and memory consumption. Among all evaluated models, the CNN-based GhostNet-100 achieved the highest overall performance in both experimental settings. Without data augmentation, it reached 99.95% accuracy and a 99.95% F1-score, while with data augmentation it achieved 99.96% accuracy and a 99.96% F1-score. Hybrid architectures such as LeViT-128S also demonstrated competitive performance, whereas lightweight Vision Transformers, including ViT-Tiny and EVA-Tiny, exhibited comparatively lower performance across both settings. Overall, the findings demonstrate that GhostNet-100 provides the optimal balance between predictive accuracy and computational efficiency under the controlled experimental conditions of this study, suggesting its potential as a candidate architecture for future clinical decision-support applications pending prospective clinical validation.

Förderung

  • Eastern Mediterranean University

Zitieren

APA

Manalı, D., & Demirel, H. (2026). Comparative analysis of lightweight CNN, vision transformer and hybrid architectures for lung histopathological image classification. The Journal of Supercomputing, 82(9). https://doi.org/10.1007/s11227-026-08653-9

Vancouver

Manalı D, Demirel H. Comparative analysis of lightweight CNN, vision transformer and hybrid architectures for lung histopathological image classification. The Journal of Supercomputing. 2026;82(9). doi:10.1007/s11227-026-08653-9

BibTeX
@article{Manal2026,
  author = {Manalı, Doğu and Demirel, Hasan},
  title = {Comparative analysis of lightweight CNN, vision transformer and hybrid architectures for lung histopathological image classification},
  journal = {The Journal of Supercomputing},
  year = {2026},
  volume = {82},
  number = {9},
  doi = {10.1007/s11227-026-08653-9}
}
Kostenlos starten →