EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Retinal Diseases Classification From OCT Images Using Pretrained Dual-Encoder Architecture

Ngo Quang Huy, Hoang Thai Xuan Khoa, Le Van Vinh

Journal of Technical Education Science · 28.02.2026 · 21 (01) · 91-98

DOI: 10.54644/jte.2026.2062 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Technical Education Science, online erschienen am 28.02.2026. Verfasst von Ngo Quang Huy und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Retinal diseases, such as age-related macular degeneration (AMD), diabetic retinopathy (DR), and glaucoma, are leading causes of irreversible vision loss, making early and accurate diagnosis essential for effective treatment. Optical coherence tomography (OCT) provides high-resolution cross-sectional retinal images that support disease assessment; however, many challenges still remain due to noise and artifacts in images or complex retinal structures. In this study, we propose a dual-encoder framework for retinal disease classification from OCT B-scan images by jointly leveraging two pretrained foundation models: RETFound and MIRAGE. Following standardized preprocessing and resampling, high-quality features extracted from the encoders are combined for the final classification tasks. To mitigate overfitting on limited medical data, the RETFound encoder is frozen during training to preserve general visual features, whereas the MIRAGE encoder is fine-tuned to adapt to specific classification objectives. Extensive experiments conducted on seven public OCT benchmark datasets demonstrate that the proposed method outperforms single-encoder baselines on the majority of benchmarks. The framework achieved an average balanced accuracy (BAcc) of 89.8%, an F1-score of 90.7%, and a Matthews Correlation Coefficient (MCC) of 83.9%. These results confirm the effectiveness of combining complementary pretrained encoders for robust and generalizable retinal disease classification in clinical settings.

Zitieren

APA

Huy, N. Q., Khoa, H. T. X., & Vinh, L. V. (2026). Retinal Diseases Classification From OCT Images Using Pretrained Dual-Encoder Architecture. Journal of Technical Education Science, 21(01), 91-98. https://doi.org/10.54644/jte.2026.2062

Vancouver

Huy NQ, Khoa HTX, Vinh LV. Retinal Diseases Classification From OCT Images Using Pretrained Dual-Encoder Architecture. Journal of Technical Education Science. 2026;21(01):91-98. doi:10.54644/jte.2026.2062

BibTeX
@article{Huy2026,
  author = {Huy, Ngo Quang and Khoa, Hoang Thai Xuan and Vinh, Le Van},
  title = {Retinal Diseases Classification From OCT Images Using Pretrained Dual-Encoder Architecture},
  journal = {Journal of Technical Education Science},
  year = {2026},
  volume = {21},
  number = {01},
  pages = {91--98},
  doi = {10.54644/jte.2026.2062}
}
Kostenlos starten →