Balanced Few-Shot Episodic Learning for Accurate Retinal Disease Diagnosis

TL;DR

This paper introduces a balanced few-shot episodic learning framework for retinal disease diagnosis that improves accuracy and fairness across disease categories with limited data, using balanced sampling, targeted augmentation, and a pretrained ResNet-50 encoder.

Contribution

It proposes a novel balanced few-shot learning approach tailored for retinal disease classification, combining balanced episodic sampling, augmentation, and a pretrained encoder to handle data imbalance.

Findings

Significant accuracy improvements over baseline methods.

Reduced bias toward majority classes in disease diagnosis.

Enhanced minority class detection through targeted augmentation.

Abstract

Automated retinal disease diagnosis is vital given the rising prevalence of conditions such as diabetic retinopathy and macular degeneration. Conventional deep learning approaches require large annotated datasets, which are costly and often imbalanced across disease categories, limiting their reliability in practice. Few-shot learning (FSL) addresses this challenge by enabling models to generalize from only a few labeled samples per class. In this study,we propose a balanced few-shot episodic learning framework tailored to the Retinal Fundus Multi-Disease Image Dataset (RFMiD). Focusing on the ten most represented classes, which still show substantial imbalance between majority diseases (e.g., Diabetic Retinopathy, Macular Hole) and minority ones (e.g., Optic Disc Edema, Branch Retinal Vein Occlusion), our method integrates three key components: (i) balanced episodic sampling, ensuring equal participation of all classes in each 5-way 5-shot episode; (ii) targeted augmentation, including Contrast Limited Adaptive Histogram Equalization (CLAHE) and color/geometry transformations, to improve minority-class diversity; and (iii) a ResNet-50 encoder pretrained on ImageNet, selected for its superior ability to capture fine-grained retinal features. Prototypes are computed in the embedding space and classification is performed with cosine similarity for improved stability. Trained on 100 episodes and evaluated on 1,000 test episodes, our framework achieves substantial accuracy gains and reduces bias toward majority classes, with notable improvements for underrepresented diseases. These results demonstrate that dataset-aware few-shot pipelines, combined with balanced sampling and CLAHE-enhanced preprocessing, can deliver more robust and clinically fair retinal disease diagnosis under data-constrained conditions.