A deep learning-based screening system that examines retinal fundus photographs for various eye conditions, including diabetic retinopathy, age-related macular degeneration (AMD) and glaucoma.
It has been validated on nearly half a million retinal images, with the findings published in JAMA.
Trials are currently ongoing for SELENA+ to become the first nationally-adopted automated screening solution. For commercialization opportunities, please contact EyRIS.
An integrated platform for retinal vessel assessment that allows the automatic extraction and quantitative measurement of vascular structure. Parameters found include
vessel caliber, fractal dimension, tortuosity and bifurcation, which have been found to be useful in estimating the risk of diseases such as stroke, heart disease, hypertension and diabetes.
Continually refined over more than a decade, SIVA has been utilized by many research groups worldwide.
The Clinical History Extractor for Syndromic Surveillance is a collaboration with the Saw Swee Hock School of Public Health,
and comprises a natural language processing algorithm for free-text medical records.