Diabetic Retinopathy Image Quality Assessment, Detection, Screening and Referral
Resumo
Diabetic Retinopathy (DR), a common complication caused by diabetes, manifests through different lesions that can result in blindness if not be discovered in time. In this work, we present a general framework whose objective is to automate the eye-fundus image analysis. The work comprises four steps: image quality assessment, DR-related lesion detection, screening, and referral. In each step, we provide satisfactory results, comparable to the State of the Art and, in many cases, surpassing it, especially when dealing with hardto- detect lesions. An important advance in our work is the validation protocol, the cross-dataset, which is closer to real situations. Furthermore, we proposed a Bag-of-Visual-Words representation highly suitable to retinal image analysis.
Referências
Jelinek, H. F., Pires, R., Padilha, R., Goldenstein, S., Wainer, J., and Rocha, A. (2013). Quality control and multi-lesion detection in automated retinopathy classification using a visual words dictionary. In Intl. Conference of the IEEE Engineering in Medicine and Biology Society.
Pires, R., Jelinek, H., Wainer, J., Valle, E., and Anderson, R. Advancing bag-of-visualwords representations for lesion classification in retinal images. PLoS ONE, (In Press).
Pires, R., Jelinek, H. F., Wainer, J., Goldenstein, S., Valle, E., and Rocha, A. (2013). Assessing the need for referral in automatic diabetic retinopathy detection. IEEE Transactions on Biomedical Engineering, 60(12):3391–3398.
Pires, R., Jelinek, H. F., Wainer, J., and Rocha, A. (2012). Retinal image quality analysis for automatic diabetic retinopathy detection. In Intl. Conference on Graphics, Patterns and Images, pages 229–236.
