VisionCLIP: An Med-AIGC based Ethical Language-Image Foundation Model for Generalizable Retina Image Analysis
This addresses data scarcity and privacy issues in medical AI for retina analysis, though it is incremental as it adapts existing synthetic data and foundation model approaches to this domain.
The paper tackles the challenge of limited annotated medical data and patient privacy by using 1 million synthetic fundus images with text descriptions to train VisionCLIP, a foundation model for retina image analysis, which achieves competitive zero-shot performance on three external datasets compared to models pre-trained on real data.
Generalist foundation model has ushered in newfound capabilities in medical domain. However, the contradiction between the growing demand for high-quality annotated data with patient privacy continues to intensify. The utilization of medical artificial intelligence generated content (Med-AIGC) as an inexhaustible resource repository arises as a potential solution to address the aforementioned challenge. Here we harness 1 million open-source synthetic fundus images paired with natural language descriptions, to curate an ethical language-image foundation model for retina image analysis named VisionCLIP. VisionCLIP achieves competitive performance on three external datasets compared with the existing method pre-trained on real-world data in a zero-shot fashion. The employment of artificially synthetic images alongside corresponding textual data for training enables the medical foundation model to successfully assimilate knowledge of disease symptomatology, thereby circumventing potential breaches of patient confidentiality.