Mobile‐aided screening system for proliferative diabetic retinopathy
Résumé
NeoVascularization (NV) occurs in the Proliferative Diabetic Retinopathy (PDR) stage, where the development progress of new vessels presents a high risk for severe vision loss and blindness. Therefore, early NV detection is primordial to preserve patient's vision. Several automated methods have been proposed to detect the NV on retinograph-captured fundus images. However, their employment is constrained by the reduced ophthalmologist per person ratio and the expensive equipment required for image capturing. This paper presents a novel method for NV detection in smartphone-captured fundus images. The implementation of the method on a smartphone device having an optical lens for fundus capturing leads to a Mobiles-Aided-Screening system of PDR (MAS-PDR). The challenge is to ensure accurate and robust detection even with the moderate quality of fundus image, with a reduced execution time. Within this objective, we identify the major criteria of neovascularized vessels which are tortuosity, width, bifurcation and density. Our main contribution consists in proposing a sharp feature to reflect each criterion on reduced computational complexity processing. Therefore, the feature set is provided to a random forest classifier in order to deduce whether the fundus image is in the PDR stage. A dataset raised from publicly databases is used on a 10-cross validation process where average accuracy of 98.69%, sensitivity of 97.73% and a specificity of 99.12% are achieved. To evaluate the method robustness, the same experimentation is repeated after applying motion blur filters to the fundus image dataset, where 98.91% accuracy, 96.75% sensitivity, and 100% specificity are deduced. Moreover, NV screening is performed under three seconds when executed in smartphone devices demonstrating the appropriateness of our suggested method to MAS-PDR.
Fichier principal
MAS_PDR Mobile_Aided Screening System for Proliferative Diabetic Retinopathy.pdf (2.23 Mo)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)