EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures

Weijie Zhang, Veronika Belcheva, Tatiana Ermakova

Computers · 12.05.2025 · 14 (5) · 187

DOI: 10.3390/computers14050187 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 12.05.2025. Verfasst von Weijie Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diabetic retinopathy (DR) is a leading cause of vision impairment worldwide, requiring early detection for effective treatment. Deep learning models have been widely used for automated DR classification, with Convolutional Neural Networks (CNNs) being the most established approach. Recently, Vision Transformers (ViTs) have shown promise, but a direct comparison of their performance and interpretability remains limited. Additionally, hybrid models that combine CNN and transformer-based architectures have not been extensively studied. This work systematically evaluates CNNs (ResNet-50), ViTs (Vision Transformer and SwinV2-Tiny), and hybrid models (Convolutional Vision Transformer, LeViT-256, and CvT-13) on DR classification using publicly available retinal image datasets. The models are assessed based on classification accuracy and interpretability, applying Grad-CAM and Attention-Rollout to analyze decision-making patterns. Results indicate that hybrid models outperform both standalone CNNs and ViTs, achieving a better balance between local feature extraction and global context awareness. The best-performing model (CvT-13) achieved a Quadratic Weighted Kappa (QWK) score of 0.84 and an AUC of 0.93 on the test set. Interpretability analysis shows that CNNs focus on fine-grained lesion details, while ViTs exhibit broader but less localized attention. These findings provide valuable insights for optimizing deep learning models in medical imaging, supporting the development of clinically viable AI-driven DR screening systems.

Zitieren

APA

Zhang, W., Belcheva, V., & Ermakova, T. (2025). Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures. Computers, 14(5), 187. https://doi.org/10.3390/computers14050187

Vancouver

Zhang W, Belcheva V, Ermakova T. Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures. Computers. 2025;14(5):187. doi:10.3390/computers14050187

BibTeX
@article{Zhang2025,
  author = {Zhang, Weijie and Belcheva, Veronika and Ermakova, Tatiana},
  title = {Interpretable Deep Learning for Diabetic Retinopathy: A Comparative Study of CNN, ViT, and Hybrid Architectures},
  journal = {Computers},
  year = {2025},
  volume = {14},
  number = {5},
  pages = {187},
  doi = {10.3390/computers14050187}
}
Kostenlos starten →