Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of blindness in the working-age population of most developing countries like Pakistan. The increasing number of individuals with diabetes worldwide suggests that DR and DME will continue to be major contributors to vision loss and associated functional impairment for years to come. Early detection of retinopathy in individuals with diabetes is critical in preventing visual loss, but current methods of screening fail to identify a sizable number of high-risk patients.
We need to develop a computer assisted diagnostic system for detecting and grading DME signs using retinal images. The grading scheme integrates methods for: (a) detecting retinal structures (e.g. optic disk and fovea); (b) detecting lesions in the retina (e.g. exudates); (c) analyzing the spatial distribution of DME signs in the retina; and (d) grading the severity of a DME case as absent, mild, moderate or severe.
- Diabetic Macular Edema Grading based on Deep Neural Networks (link)
- Multiscale segmentation of exudates in retinal images using contextual cues and ensemble classification (link)
Retinal image Datasets