Detection and Classification of Diabetic Retinopathy From Posterior Pole Images With A Deep Learning Model

This is a prospective study to assess the safety and efficacy of EyeCheckup in screening for DR.

This study was carried out in a single center at Akdeniz University Faculty of Medicine with primary endpoints to determine the sensitivity and specificity of EyeCheckup to diabetic retinopathy in the primary care setting.

Methods and tools to be used in the study:

• Fundus photography with non-mydriatic camera and classification of diabetic retinopathy with artificial intelligence algorithm,
• Evaluation of seven field dilated fundus images by retina specialists and comparison of results for clinical validation of the system.

Clinical and laboratory tests to be performed:

• Fundus photography with a non-mydriatic camera. In this study, no invasive procedure is applied to the patient, the retinal photograph will be taken with a special digital camera called a fundus camera. In patients whose non-mydriatic image cannot be obtained, tropicamide drops will be instilled to dilate the pupil, and then photographs will be taken.
• Pupil dilation will be achieved by instilling Tropicamide drops in both eyes of the patient, and then 4 quadrant photographs of both eyes will be taken with a mydriatic fundus camera.

After exclusions, this study will enroll up to 900 subjects who are diagnosed with diabetes by the endocrinology polyclinic and meet the eligibility criteria. Participants who meet the eligibility criteria will be recruited after obtaining written informed consent from primary health care providers. Subjects will undergo fundus photography per, Food and Drug Administration (FDA) cleared, ophthalmic cameras (product code: HKI). Images will be taken according to a specific EyeCheckup imaging protocol provided to the ophthalmic camera operator and then analyzed by the EyeCheckup device.

The photography protocol consists of two images of the ocular fundus (one optic disc nerve centered, one macula centered), obtained from both eyes of enrolled participants.

After the retinal images taken from ophthalmic cameras (product code: HKI), images are analyzed with EyeCheckup and a scan report is prepared. If it is necessary to enlarge the pupils, eye enlarging eye drops are applied and wait 15-30 minutes. This information is noted. DR is diagnosed by examination by a retina specialist with the captured images. EyeCheckup success rate is calculated by comparing both reports.

Inclusion criteria

• A diagnosis of diabetes mellitus
• Understanding of study and provision of written informed consent
• 18 years of age or older
• No history of any other retinal vascular disease, glaucoma, or other disease that may affect the appearance of the retina or optic disc (refractive error and ocular surface disease are allowed)
• Other than cataract surgery, no history of intraocular surgery, ocular laser treatments for any retinal disease, or ocular injections for diabetic macular edema or proliferative disease No media opacity precluding good retinal photography

Exclusion criteria

• No diagnosis of diabetes mellitus
• Potential subject cannot understand study or informed consent
• A history of retinal vascular disease other than diabetic retinopathy that may affect the appearance of the retina or optic disc
• Previous intraocular surgery including cataract; previous laser to the retina; or previous intraocular injections for the treatment of diabetic retinopathy
• Pregnant women or women with gestational diabetes mellitus
• A media opacity in either eye that is severe enough to preclude good retinal photography
• Permanent vision impairment in one or both eyes
• The participant is contraindicated for imaging with fundus imaging systems used in the study:
• Participant is hypersensitive to light
• Participant recently received photodynamic therapy (PDT)
• Participant uses drugs that cause photosensitivity