EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NeuroFusion-ViT: A Hybrid CNN–EVA Transformer Model with Cross-Attention Fusion for MRI-Based Alzheimer’s Stage Classification

Derya Öztürk Söylemez iD, Sevinç Ay Doğru iD

Diagnostics · 03.03.2026 · 16 (5) · 754

DOI: 10.3390/diagnostics16050754 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 03.03.2026. Verfasst von Derya Öztürk Söylemez und 1 weiteren Autor:innen. Beteiligte Einrichtung: Vocational School of Health Services, Sinop University, Sinop 57000, Turkey. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Alzheimer’s disease is the most common type of dementia and a progressive neurodegenerative disease that begins with neuronal damage and leads to a reduction in brain tissue. Currently, there is no cure for this disease, and existing approaches focus on alleviating symptoms.

Methods

This study proposes NeuroFusion-ViT, a highly accurate and computationally efficient hybrid deep learning model for early-stage detection of Alzheimer’s disease. The model combines an EVA-02-based Vision Transformer (ViT) with the ConvNeXt-Small CNN architecture, providing powerful representation learning that can process both global context and local details. The proposed Gated Cross-Attention Fusion (G-CAF) mechanism dynamically combines two different features, offering high discriminative power and model stability.

Results

In experiments conducted on the OASIS MRI dataset, the model achieved 99.86% accuracy, 0.9989 Macro F1, and 0.999 ROC-AUC values, demonstrating clear superiority over single-modal and hybrid models described in the literature. Furthermore, 5-fold cross-validation results also support the model’s high generalizability. Ablation studies showed that each of the components—cross-attention, gate mechanism, Dual LayerNorm, and FFN-Dropout—made a meaningful contribution to performance.

Conclusions

The results demonstrate that the NeuroFusion-ViT architecture offers a reliable, stable, and clinically applicable solution for Alzheimer’s stage classification.

Schlagwörter

Stichwörter der Autor:innen

AlzheimerMRIvision transformers

Autor:innen und Institutionen

  • Vocational School of Health Services, Sinop University, Sinop 57000, Turkey.
  • Department of Software Engineering, Firat University, Elazig 23000, Turkey.

ORCID-Profile: Derya Öztürk Söylemez, Sevinç Ay Doğru

Zitieren

APA

Öztürk Söylemez, D., & Ay Doğru, S. (2026). NeuroFusion-ViT: A Hybrid CNN–EVA Transformer Model with Cross-Attention Fusion for MRI-Based Alzheimer’s Stage Classification. Diagnostics, 16(5), 754. https://doi.org/10.3390/diagnostics16050754

Vancouver

Öztürk Söylemez D, Ay Doğru S. NeuroFusion-ViT: A Hybrid CNN–EVA Transformer Model with Cross-Attention Fusion for MRI-Based Alzheimer’s Stage Classification. Diagnostics. 2026;16(5):754. doi:10.3390/diagnostics16050754

BibTeX
@article{ztrkSylemez2026,
  author = {Öztürk Söylemez, Derya and Ay Doğru, Sevinç},
  title = {NeuroFusion-ViT: A Hybrid CNN–EVA Transformer Model with Cross-Attention Fusion for MRI-Based Alzheimer’s Stage Classification},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {5},
  pages = {754},
  doi = {10.3390/diagnostics16050754}
}
Kostenlos starten →