Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification

Abstract

address:Roshan.Welikala@kingston.ac.uk (R.A. Welikala). Abstract:Proliferative diabetic retinopathy (PDR) is a condition that carries a high risk of severe visual impairment. The hallmark of PDR is neovascularisation, the growth of abnormal new vessels. This paper describes an automated method for the detection of new vessels in retinal images.Two vessel segmentation approaches are applied, using the standard line operator and a novel modified line operator. The latter is designed to reduce false responses to non-vessel edges.Both generated binary vessel maps hold vital information which must be processed separately. This is achieved with a dual classification system. Local morphology features are measured from each binary vessel map to produce two separate feature sets. Independent classification © 2014, Elsevier. Licensed under the Creative Commons Attribution-NonCommercialNoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/ is performed for each feature set using a support vector machine (SVM) classifier. The system then combines these individual classification outcomes to produce a final decision. Sensitivity and specificity results using a dataset of 60 images are 0.862 and 0.944 respectively on a per patch basis and 1.00 and 0.90 respectively on a per image basis.

Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy

“…The system produced a final decision by combining the two individual classification outcomes in which regions of the retina were labelled as new vessels or non-new vessels. This section describes a very concise overview, for a full explanation with all parameters listed see [55]. The line operator was used in the proposed method to perform vessel segmentation.…”

“…This included measures that separately took into account the left and right side of the neighbourhood. For full details and equations see [55].…”

“…The contribution of [55] was the novel application of a dual classification approach to independently process the binary maps from two different vessel segmentation methods with the aim to detect new vessels and reduce false responses caused by other retinal features. This included a novel modified line operator, based on double sided thresholding, designed to segment vessels whilst reducing false responses to non-vessel edges.…”

“…The main contribution of the proposed method is the exploration of features suitable for the classification of proliferative diabetic retinopathy combined with the dual classification approach [55]. This is achieved by expanding the feature vector which now includes morphology, gradient and © 2015, Elsevier.…”

River Detection in Remotely Sensed Imagery Using Gabor Filtering and Path Opening

“…The main idea is to ease the river detection process by both reducing noise and enhancing the dark curvilinear features (possible cracks). A 3 × 3 mean filter was first applied to reduce salt and pepper noise [41].…”