An ultrasound foundation model detected eye disease with 98.3% screening sensitivity
An ultrasound foundation model for the stratification of vision impairment and eye cancer risk.
Zicheng Zhou … Xuejun Qian
NPJ digital medicine · 2026
Background
The prevalence of vision disorders and eye cancer risk, driven by global population aging, necessitates precise ophthalmological disease screening, yet standardized and robust approaches for risk stratification remain absent.
98.3%
Results
98.3%
share of eyes with disease the AI correctly caught; higher means fewer missed
n = 215,356 image
More results
Here, we present SonoEye, a vision-language ultrasound foundation model for eye disease risk stratification, pre-trained on 215,356 image-text pairs from 70,452 patients using contrastive learning and fine-tuned with consensus-confirmed patient-level labels.
More results
We established the Eye Reporting and Data System (Eye-RADS), a 4-tier risk stratification framework (normal, low-vision risk, high-vision risk, and tumor risk), demonstrating excellent Cohen's kappa agreement across internal (0.808) and external (0.677-0.685) test cohorts.
“
Conclusion
Through image-text alignment, SonoEye generates structured clinical reports with interpretable attention-based visualizations, advancing automated vision risk stratification, particularly for aging populations in resource-limited settings.