The Science

Automatic Retinal Imaging and Analysis (ARIA)

Retinal vessels are the only visible vessels and accessible by simple fundus photography. Retinal vessels have the same embryo origin and histological structure with cerebral vessels. It provides us a convenient way to assess the cardiovascular condition and reflects pathological change caused by diabetes and hypertension.

Cardiovascular disease and stroke are the second most frequent cause of death worldwide. Ischemic strokes are caused by interruption of the blood flow, while hemorrhagic strokes result from the rupture of a blood vessel or an abnormal vascular structure. About 87% of strokes are ischemic. Currently, there is no effective screening method for stroke. Methods to assess the risk of stroke include ultrasound, computed tomography angiography (CTA), and magnetic resonance angiography (MRA). Ultrasound can be used to evaluate the vascular stenosis and assess blood flow velocity in the carotid artery. CTA and MRA can be used to detect large cerebrovascular abnormalities, but these techniques have relatively high cost and also invasive.

Automatic Retinal Imaging and Analysis (ARIA) is an innovative, data driven technology that BTI intends to employ as a diagnostic device for monitoring Metabolic Syndrome and risk of stroke in general.

ARIA may be used for screening of cardiovascular risk such as stroke, and also indicated for diabetic retinopathy and age-related macular degeneration screening. ARIA is an algorithm, big data driven approach built on an internet platform, under development for screening. It is easy to use and fast, non-invasive, automatic, accurate assessment, suitable for repeated use and supported.

ARIA research exhibits sensitive and specificity for CV risk that is suitable for repeated use and may be used to calculate the 5-year probability of stroke based on a single retinal image versus the risk equation based on blood HbA1C. ARIA incorporation with BTI Technology is anticipated to be introduced in fall 2018 for community application.