A multimodal visual–language foundation model for computational ophthalmology
Danli Shi, Weiyi Zhang, J. Yang, Siyu Huang, Xiaolan Chen, Pusheng Xu, Kai Jin, Shan C. Lin, Wei Jin, Mayinuer Yusufu, Shunming Liu, Q Zhang, Zongyuan Ge, Xun Xu, Mingguang He
Abstract
Early detection of eye diseases is vital for preventing vision loss. Existing ophthalmic artificial intelligence models focus on single modalities, overlooking multi-view information and struggling with rare diseases due to long-tail distributions. We propose EyeCLIP, a multimodal visual-language foundation model trained on 2.77 million ophthalmology images from 11 modalities with partial clinical text. Our novel pretraining strategy combines self-supervised reconstruction, multimodal image contrastive learning, and image-text contrastive learning to capture shared representations across modalities. EyeCLIP demonstrates robust performance across 14 benchmark datasets, excelling in disease classification, visual question answering, and cross-modal retrieval. It also exhibits strong few-shot and zero-shot capabilities, enabling accurate predictions in real-world, long-tail scenarios. EyeCLIP offers significant potential for detecting both ocular and systemic diseases, and bridging gaps in real-world clinical applications.