EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

OCT-SelfNet: a self-supervised framework with multi-source datasets for generalized retinal disease detection

Fatema-E Jannat, Sina Gholami, Minhaj Nur Alam, Hamed Tabkhi

Frontiers in Big Data · 29.07.2025 · 8

DOI: 10.3389/fdata.2025.1609124 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Big Data, online erschienen am 29.07.2025. Verfasst von Fatema-E Jannat und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, Charlotte, NC, United States. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NEI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

In the medical AI field, there is a significant gap between advances in AI technology and the challenge of applying locally trained models to diverse patient populations. This is mainly due to the limited availability of labeled medical image data, driven by privacy concerns. To address this, we have developed a self-supervised machine learning framework for detecting eye diseases from optical coherence tomography (OCT) images, aiming to achieve generalized learning while minimizing the need for large labeled datasets.

Methods

Our framework, OCT-SelfNet, effectively addresses the challenge of data scarcity by integrating diverse datasets from multiple sources, ensuring a comprehensive representation of eye diseases. By employing a robust two-phase training strategy self-supervised pre-training with unlabeled data followed by a supervised training stage, we utilized the power of a masked autoencoder built on the SwinV2 backbone.

Results

Extensive experiments were conducted across three datasets with varying encoder backbones, assessing scenarios including the absence of self-supervised pre-training, the absence of data fusion, low data availability, and unseen data to evaluate the efficacy of our methodology. OCT-SelfNet outperformed the baseline model (ResNet-50, ViT) in most cases. Additionally, when tested for cross-dataset generalization, OCT-SelfNet surpassed the performance of the baseline model, further demonstrating its strong generalization ability. An ablation study revealed significant improvements attributable to self-supervised pre-training and data fusion methodologies.

Discussion

Our findings suggest that the OCT-SelfNet framework is highly promising for real-world clinical deployment in detecting eye diseases from OCT images. This demonstrates the effectiveness of our two-phase training approach and the use of a masked autoencoder based on the SwinV2 backbone. Our work bridges the gap between basic research and clinical application, which significantly enhances the framework's domain adaptation and generalization capabilities in detecting eye diseases.

Schlagwörter

Stichwörter der Autor:innen

OCTSwinV2autoencoderclassificationdeep learningself-supervisedtransfer learningtransformer

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, University of North Carolina at Charlotte, Charlotte, NC, United States.

Förderung

  • NEI NIH HHS

Zitieren

APA

Jannat, F. E., Gholami, S., Alam, M. N., & Tabkhi, H. (2025). OCT-SelfNet: a self-supervised framework with multi-source datasets for generalized retinal disease detection. Frontiers in Big Data, 8. https://doi.org/10.3389/fdata.2025.1609124

Vancouver

Jannat FE, Gholami S, Alam MN, Tabkhi H. OCT-SelfNet: a self-supervised framework with multi-source datasets for generalized retinal disease detection. Frontiers in Big Data. 2025;8. doi:10.3389/fdata.2025.1609124

BibTeX
@article{Jannat2025,
  author = {Jannat, Fatema-E and Gholami, Sina and Alam, Minhaj Nur and Tabkhi, Hamed},
  title = {OCT-SelfNet: a self-supervised framework with multi-source datasets for generalized retinal disease detection},
  journal = {Frontiers in Big Data},
  year = {2025},
  volume = {8},
  doi = {10.3389/fdata.2025.1609124}
}
Kostenlos starten →