Automated Detection of Fundus Photographic Red Lesions in Diabetic Retinopathy

Abstract

Detection of diabetic retinopathy by automated detection of single fundus lesions can be achieved with a performance comparable to that of experienced ophthalmologists. The results warrant further investigation of automated fundus image analysis as a tool for diabetic retinopathy screening.

Detection of Fundus Lesions Using Classifier Selection

“…Meanwhile, the specificity is the ratio of the number of images in which lesions are not detected to the number of images without lesions. This evaluation is also applied in other papers [7], [9]- [11]. Four results are listed in Table 2.…”

“…Larsen et al evaluated that system and the result was 96.7% for sensitivity and 71.4% for specificity [11].…”

Diabetes Care and Treatment Project: A Joslin Telemedicine Initiative

“…[9,10], evaluated the performance of an automated fundus photographic image analysis algorithm in high-sensitivity and/or high specificity classification of patients with diabetes with undiagnosed DR from those without retinopathy. In their study, the data set consisted of 260 diabetic patients of which * 137 presented with DR.…”

“…This final step in the screening process makes this system differ from those previously developed and cited in the literature [9,10]. The screening system implemented a technique that made it unnecessary to detect automatically all MAs and to reject all other segmented objects that resemble MAs in an image.…”

Preventing Diabetic Retinopathy: Red Lesions Detection in Early Stages

“…In (Goldbaum et al, 1990) Mahalanobis distance is used as the classifier criteria, but results were inconclusive. Many other approximations can be found in literature, like mathematical morphology based (Cree et al, 1997;Spencer et al, 1996) or neural network based (Gardner et al, 1996), with results ranging in sensitivity from 85% and specificity of 76% (Hipwell et al, 2000), sensitivity of 77.5% and specificity of 88.7% in (Sinthanayothin et al, 2002) or sensitivity 93.1% and specificity of 71.4% (Larsen et al, 2003), this last obtained using a commercially available automatic red lesion detection system. More recently, García et al (García et al, 2009) developed several techniques to deal with the problem of feature detection for the diabetic retinopathy diagnosis and screening, using neural nets like the multilayer perceptron classifier (García et al, 2008) or a radial basis function fed with the output of a logistic regression process, and obtained values ranging in sensitivity from 86.1% to 92.1% and from 71.4% to 86.4% in positive predicted results.…”