Leveraging the RETFound foundation model for optic disc segmentation in retinal images

📅 2025-08-15
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses optic disc segmentation in retinal images—a fundamental task in medical image analysis—by pioneering the adaptation of the RETFound vision foundation model to medical image segmentation. We propose a lightweight segmentation head coupled with end-to-end fine-tuning, enabling efficient transfer learning with only a small number of annotated samples. Unlike prior work focused on diagnostic applications, this is the first effort to evaluate RETFound’s generalization capability on non-diagnostic downstream vision tasks, demonstrating its potential to replace task-specific architectures. Evaluated on five public datasets, our method achieves a Dice coefficient of approximately 96%, substantially outperforming most existing approaches. It further establishes new state-of-the-art performance in internal validation, cross-domain generalization, and domain adaptation. Collectively, this work introduces a novel paradigm for the general-purpose deployment of medical foundation models.

Technology Category

Application Category

📝 Abstract
RETFound is a well-known foundation model (FM) developed for fundus camera and optical coherence tomography images. It has shown promising performance across multiple datasets in diagnosing diseases, both eye-specific and systemic, from retinal images. However, to our best knowledge, it has not been used for other tasks. We present the first adaptation of RETFound for optic disc segmentation, a ubiquitous and foundational task in retinal image analysis. The resulting segmentation system outperforms state-of-the-art, segmentation-specific baseline networks after training a head with only a very modest number of task-specific examples. We report and discuss results with four public datasets, IDRID, Drishti-GS, RIM-ONE-r3, and REFUGE, and a private dataset, GoDARTS, achieving about 96% Dice consistently across all datasets. Overall, our method obtains excellent performance in internal verification, domain generalization and domain adaptation, and exceeds most of the state-of-the-art baseline results. We discuss the results in the framework of the debate about FMs as alternatives to task-specific architectures. The code is available at: [link to be added after the paper is accepted]
Problem

Research questions and friction points this paper is trying to address.

Adapting RETFound for optic disc segmentation in retinal images
Achieving high accuracy with minimal task-specific training data
Comparing foundation models versus task-specific architectures for segmentation
Innovation

Methods, ideas, or system contributions that make the work stand out.

Adapts RETFound for optic disc segmentation
Achieves 96% Dice across multiple datasets
Outperforms segmentation-specific baseline networks
🔎 Similar Papers
No similar papers found.
Z
Zhenyi Zhao
Computing, School of Science and Engineering, University of Dundee, Dundee, UK
M
Muthu Rama Krishnan Mookiah
Computing, School of Science and Engineering, University of Dundee, Dundee, UK
E
Emanuele Trucco
Computing, School of Science and Engineering, University of Dundee, Dundee, UK