Ali SERENER, Sertan SERTE

Geographic variation and ethnicity in diabetic retinopathy detection via deep learning

ISSN: 1300-0632
Yayın Aralığı: 6
Yayıncı: TÜBİTAK

The prevalence of diabetes is on the rise steadily around the globe. Diabetic retinopathy (DR) is a resultof damage to the blood vessels in the retina due to diabetes and its fast treatment is crucial for preventing possibleblindness. The diagnosis of DR is done mostly using a comprehensive eye exam, where the eye is dilated for betterinspection. Analysis by an ophthalmologist is prone to human error and thus automatic and highly accurate detection ofDR is preferred for an earlier and better diagnosis. It is important, however, that automatic detection be accurate for alldata collected from patients of different geographic and ethnic backgrounds. In this paper, the automatic detection of DRwith a deep learning algorithm is analyzed when geographic and ethnic information of the patients is also integrated intothe architecture. It is shown that robust and generalizable DR detection performance is linearly related to the correlationof geographic and ethnic patient information between the training and the testing datasets. The deep learning modelcreated eliminates geographic variation in the detection and works for patients of all ethnicities.

PDF