 The study aimed to develop and evaluate an unsupervised anomaly detection model for detecting ocular diseases on the basis of color fundus images, achieving high sensitivity and specificity in detecting abnormal fundus images and six common ocular diseases, which implies that this model might be an efficient and economical tool for optimizing current clinical pathways for ophthalmologists. This article was authored by Yong Han, Wei Mingli, Meng Meng Lu, and others.