Abstract
Retinal diseases remain among the leading preventable causes of visual impairment worldwide. Automated screening based on fundus image analysis has the potential to expand access to early detection, particularly in underserved populations. This paper presents a reproducible deep learning pipeline for binary retinal disease risk classification from publicly available fundus photographs. We implement and compare a baseline convolutional neural network with a transfer learning approach using a pretrained VGG16 backbone and evaluate generalization on held-out data. To address class imbalance, we apply class weighting and report standard classification metrics including accuracy, precision, recall, F1-score, confusion matrices, and ROC-AUC. The VGG16 transfer learning model achieves 90.8% test accuracy with a weighted F1-score of 0.90, substantially outperforming the baseline CNN (83.1% accuracy). Results indicate that transfer learning improves discrimination compared to a baseline CNN, while also revealing remaining challenges in sensitivity to minority disease cases. We discuss practical limitations related to dataset characteristics, class imbalance, and threshold selection, and provide guidance for reproducibility and future improvements for clinically reliable screening
Abstract (translated)
视网膜疾病仍是全球可预防性视觉障碍的主要病因之一。基于眼底图像分析的自动化筛查有潜力扩大早期检测的可及性，尤其对医疗资源匮乏地区。本研究提出一个可复现的深度学习流程，用于基于公开眼底照片的视网膜疾病风险二分类。我们实现并比较了基线卷积神经网络与采用预训练VGG16骨干网络的迁移学习方法，并在保留测试集上评估泛化能力。为处理类别不平衡，我们应用类别加权策略，并报告准确率、精确率、召回率、F1分数、混淆矩阵及ROC-AUC等标准分类指标。VGG16迁移学习模型在测试集上达到90.8%的准确率与0.90的加权F1分数，显著优于基线CNN（83.1%准确率）。结果表明迁移学习相较于基线CNN提升了判别能力，同时揭示了对少数疾病病例敏感度仍存在的挑战。我们讨论了与数据集特征、类别不平衡及阈值选择相关的实践局限，并为实现临床可靠筛查的可复现性与未来改进提供指导。
URL
https://arxiv.org/abs/2603.23785
