Automated detection of exudates for diabetic retinopathy screening

Abstract

Automated image analysis is being widely sought to reduce the workload required for grading images resulting from diabetic retinopathy screening programmes. The recognition of exudates in retinal images is an important goal for automated analysis since these are one of the indicators that the disease has progressed to a stage requiring referral to an ophthalmologist. Candidate exudates were detected using a multi-scale morphological process. Based on local properties, the likelihoods of a candidate being a member of classes exudate, drusen or background were determined. This leads to a likelihood of the image containing exudates which can be thresholded to create a binary decision. Compared to a clinical reference standard, images containing exudates were detected with sensitivity 95.0% and specificity 84.6% in a test set of 13,219 images of which 300 contained exudates. Depending on requirements, this method could form part of an automated system to detect images showing either any diabetic retinopathy or referable diabetic retinopathy.

Improving the economic value of photographic screening for optical coherence tomography-detectable macular oedema: a prospective, multicentre, UK study

“…For BHs and exudates, the non-specific filter was applied at multiple scales and the results combined. 52,54 Dark objects were detected for BHs and bright objects were detected for exudates. The second stage of lesion detection performed more detailed analysis of the candidate lesions, measuring such features as their area, contrast and, for the dark lesions, the likelihood of it lying on a vessel.…”

Points of Interest and Visual Dictionaries for Automatic Retinal Lesion Detection

“…Automated bright lesion detection has resulted in highly accurate classification and has been discussed recently by [9], [10], [11]. For automated red lesion detection similar high sensitivity and specificity has been reported.…”

Automatic detection of retinal exudates in fundus images of diabetic retinopathy patients

“…While the results of our algorithm showed higher performance in comparison to the abovementioned value. 10 In a similar study by Fleming et al, 11 they reported the sensitivity of 95.0% and the specificity of 84.6% for their applied method including morphological segmentation and dynamic thresholding using maximum likelihood estimation. The sensitivity of our technique was relatively lower than their results while our specificity was considerably higher than their reported value.…”