Abstract

AbstractDiabetic retinopathy (DR) is one of the leading causes of adult blindness in working age population worldwide due to its late diagnosis and treatment. In effort to early detect DR, before visual loss, international guidelines for DR screening recommend an annual fundus examination for all diabetic patients. A variety of techniques can be used to detect and classify DR, including direct and indirect ophthalmoscopy, stereoscopic color film fundus photography, mydriatic and nonmydriatic (NM) digital color and monocromatic photography. Although ophthalmoscopy is the most commonly used technique to screen for DR, it has poor sensitivity when performed by nonophthalmologists in nonmydriatic conditions. The sensitivity of direct ophthalmoscopy in detecting proliferative DR is about 50% when performed by non‐ophtahlmologists in NM conditions. Seven‐field stereoscopic color fundus photographies have been considered as reference standard for diagnosing DR in randomized clinical trials. But this method is time consuming with uncertain practicity for widespread screening programs. Several studies have reported sensitivity and specificity in detecting DR and diabetic macular edema (DME) using limited number of fundus fields, proposing an alternative method for diabetic retinopathy evaluation to the ETDRS 7 fields. Recently introduced telemedicine screening programs based on digital images have the potential to allow for increased detection of DR, resulting in timely treatment and preservation of vision. Also important cost savings have been reported with DR screening, either by manual (human) or automatic (computer‐based) grading. Therefore, there is a critical need for a sensitive, specificic and cost‐effective screening method.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call