Abstract
BACKGROUND: Deep learning faces a significant bottleneck in medical image analysis due to its reliance on large-scale, expert-annotated datasets. This challenge is acute in ophthalmology, particularly for detecting early-stage diseases like mild Diabetic Retinopathy (DR1), where subtle lesions and a scarcity of annotations limit supervised learning approaches. METHODS: We propose a generalizable eye disease detection framework based on Zero-shot Learning (ZSL) that mimics clinical reasoning. Using the LCFP-14M dataset, a large-scale fundus image resource we present in this work, our method first identifies disease correlations via a Siamese network. It then transfers knowledge by segmenting DR1-specific lesions from a highly correlated source disease and employs a ResNet-Agglomerative clustering pipeline to enable unsupervised detection of DR1 without using any labeled DR1 cases. RESULTS: Here we show that the proposed framework enables effective DR1 detection without annotated DR1 data. The model achieves an accuracy of 0.8337, precision of 0.8700, recall of 0.7456, F1 score of 0.8030, and ROC-AUC of 0.9226, outperforming most supervised baselines on external test datasets. CONCLUSIONS: Our findings demonstrate that ZSL can simulate clinical diagnostic logic and generalize to unseen eye diseases, offering a promising approach for automated screening where labeled data are scarce.