[ Diabetes Type 2 ]

Is digital image compression acceptable within diabetic retinopathy screening? – PubMed


Microaneurysms detection is an important task in computer aided diagnosis of diabetic retinopathy. We studied and implemented a few illumination correction and contrast enhancement techniques on color retinal images to find out the best technique for optimum image enhancement. In: Proc. Using three dimensional vascular image (Doppler OCA) and three dimensional intensity OCT image at macula and optic disc, we evaluated three dimensional vascular architecture at proliferative membrane. A non-mydriatic retinal camera with TRIAD, our ocular telehealth network, was installed in the Family Medicine Center. The sensitivity and specificity for determining diabetic retinopathy was 68.57% (95%CI 57.00-78.20) and 92.25% (95%CI 87.00-95.50), respectively. The longitudinal images were aligned using condition number theory based registration in the vesselness transform domain.

A high rate of poor quality photographs and low sensitivity limited the use of NMDI as a perfect screening system, particularly in dark iris population with diabetes as seen in Indian eyes. Two months later, two graders independently graded the nonmydriatic images in a blinded fashion according to the ETDRS scale; a third observer adjudicated the rare instances of interreader disagreement. Jayabhaskar Rao, Diabetalogist, Nandalur, A.P. Cited by links are available to subscribers only. IPRI’s international network of Key Opinion Leaders in Diabetes has confirmed this interest. Primary care doctors face significant incentives to adopt the new model. E.g., it seemed like the NN overfit for the 0,1,2 vs 3,4 case based on the training / validation difference, and leaving that one out of the final regression problem resulted in a slightly better score.

Tags: , ,