Development of a hybrid framework to characterize red lesions for early detection of diabetic retinopathy

Abstract

<p>Diabetic retinopathy (DR) is one of the driving reasons for visual deficiency, affecting people globally. Currently, the ophthalmologists need to inspect enormous number of images with a specific end goal to perform mass screening of Diabetic retinopathy. In this paper, an efficient Computer aided system based on a Hybrid framework is proposed for the early diagnosis of DR by extracting the early DR lesions such as microaneurysms and hemorrhages. The development of such a screening system would decrease the workload of the ophthalmologists, as they now need to look at those retinal images that are analyzed by the system, as irregularities. The retinal images obtained from standard retinal databases and Hospitals are pre-processed followed by the detection and elimination of blood vessels, optic disk and exudates. Quick propagation Neural Network is used for training and testing of the retinal fundus images since it has the fastest execution time. Linear Classification and Multi class classification of retinal fundus images are performed for the classification and grading of retinal fundus images into normal and abnormal using Alyuda Neuro-Intelligence software. A patient database is created using MySQL to store the required details of the patient and a graphical user interface is developed for an efficient usage of the system. The execution time of the system is found to be 7-9 seconds and is tested on 270 retinal fundus images. The precision and accuracy of the algorithm is 92.5% and 93.9%, respectively.</p>

Modelling on-demand preprocessing framework towards practical approach in clinical analysis of diabetic retinopathy

“…There isa range of preprocessing approaches given in the literature for enhancing the quality of the fundus images. Gamma correction and histogram-based techniques are extensively adopted to improve fundus images' visual characteristics due to their admirable performance [9], [10]. Although there is various availability of preprocessing medical objects, there is less evidence of performing effective preprocessing towards the retina.…”

Ultra low bitrate retinal image compression using integer lifting scheme and subband encoder

“…The retina is the lining of the eye and its function lies in the sense of light coming to the eye, consisting of large blood vessels (BV) (veins) and BV accurate (arteries) easy to damage, and that high blood sugar for a long time can damage these vessels. These changes in the lining of BV increase their permeability [1], [2]. At first, some of these vessels develop and weaken, and these vessels get clogged and do not allow enough blood to pass through them.…”

Design and simulation of interdigitated electrode for Graphene-SnO2 sensor on acetone gas

“…Acetone is one of the common type of VOCs from ketone family [3] and it is present in exhaled breath and used as a biomarker in breath for diabetes mellitus [4]. Diabetes mellitus is a chronic metabolic disorder that arises from insulin deficiency [5][6][7] that elevates blood glucose levels and is one of the major causes of death. Worldwide, it is estimated that 382 million adults are having diabetes and expected to further increase more than 592millions by 2035 [8].…”