Block Expanded DINORET: Adapting Natural Domain Foundation Models for Retinal Imaging Without Catastrophic Forgetting

TL;DR

This paper introduces DINORET and BE DINORET, two self-supervised vision models adapted for retinal imaging, employing block expansion to improve domain adaptation and prevent catastrophic forgetting, with superior data efficiency and performance.

Contribution

The study proposes a novel block expansion method for domain adaptation and demonstrates effective fine-tuning of foundation models for retinal imaging without catastrophic forgetting.

Findings

Block expansion mitigates catastrophic forgetting.

DINORET models outperform RETFound in data efficiency.

Models achieve competitive accuracy on retinal tasks.

Abstract

Integrating deep learning into medical imaging is poised to greatly advance diagnostic methods but it faces challenges with generalizability. Foundation models, based on self-supervised learning, address these issues and improve data efficiency. Natural domain foundation models show promise for medical imaging, but systematic research evaluating domain adaptation, especially using self-supervised learning and parameter-efficient fine-tuning, remains underexplored. Additionally, little research addresses the issue of catastrophic forgetting during fine-tuning of foundation models. We adapted the DINOv2 vision transformer for retinal imaging classification tasks using self-supervised learning and generated two novel foundation models termed DINORET and BE DINORET. Publicly available color fundus photographs were employed for model development and subsequent fine-tuning for diabetic retinopathy staging and glaucoma detection. We introduced block expansion as a novel domain adaptation strategy and assessed the models for catastrophic forgetting. Models were benchmarked to RETFound, a state-of-the-art foundation model in ophthalmology. DINORET and BE DINORET demonstrated competitive performance on retinal imaging tasks, with the block expanded model achieving the highest scores on most datasets. Block expansion successfully mitigated catastrophic forgetting. Our few-shot learning studies indicated that DINORET and BE DINORET outperform RETFound in terms of data-efficiency. This study highlights the potential of adapting natural domain vision models to retinal imaging using self-supervised learning and block expansion. BE DINORET offers robust performance without sacrificing previously acquired capabilities. Our findings suggest that these methods could enable healthcare institutions to develop tailored vision models for their patient populations, enhancing global healthcare inclusivity.