Title :
Supervised pixel classification into arteries and veins of retinal images
Author :
Chhabra, Smriti ; Bhushan, Bharat
Author_Institution :
Electr. Eng. Dept., Delhi Technol. Univ., New Delhi, India
Abstract :
With the emerging computation techniques in the field of medical science such as in Ophthalmology; it is often required an automated technique for identification of pathological condition such as diabetic retinopathy which might cause serious problems like blindness. Retinal diseases are often characterized by modification in retinal vessels. Retinal blood vessels observed with fundus imaging provides important indicators not only for clinical diagnosis and treatment of eye diseases but also for systemic diseases such as diabetes, hypertension etc. which manifest themselves in the retina. Quantitative structural analysis of the retinal vasculature not only helps in the diagnosis of retinopathies but also provides potential biomarkers of systemic diseases. Such as arteriole to venule width ratio (AVR) is a parameter indicative of microvascular health and systemic disease. In this paper we performed retinal vessel´s pixel classification into arterioles and venules using Neural Network on DRIVE database. Two types of feed-forward Neural Network are used: Back Propagation Network (BPN) and Probabilistic Neural Network (PNN). BPN gives 83.9% and where as PNN gives 85.1% pixel classification on 20 images. The ROC curve for BPN and PNN has value 0.83 and 0.87 respectively for the DRIVE dataset.
Keywords :
adaptive optics; backpropagation; biomedical optical imaging; blood vessels; diseases; eye; feature extraction; image classification; medical image processing; neural nets; patient treatment; retinal recognition; vision defects; AVR parameter indicator; BPN ROC curve; DRIVE database; DRIVE dataset; PNN ROC curve; arteriole pixel classification; arteriole-to-venule width ratio; automated identification technique; back propagation network; blindness; clinical diagnosis indicators; diabetes treatment; diabetic retinopathy; emerging computation techniques; eye disease treatment; feed-forward neural network; fundus imaging; hypertension treatment; medical science field; microvascular health indicator; ophthalmology; pathological condition identification; pixel image classification; potential systemic disease biomarkers; probabilistic neural network; quantitative retinal vasculature analysis; quantitative structural analysis; retinal blood vessels; retinal disease characterization; retinal images; retinal vessel modification; retinal vessel pixel classification; retinopathy diagnosis; supervised pixel classification; systemic disease indicator; systemic disease treatment; venule pixel classification; Arteries; Biomedical imaging; Feature extraction; Image edge detection; Neural networks; Retina; Veins; Retinal images; arteries; classification; neural network; veins;
Conference_Titel :
Computational Intelligence on Power, Energy and Controls with their impact on Humanity (CIPECH), 2014 Innovative Applications of
Conference_Location :
Ghaziabad
DOI :
10.1109/CIPECH.2014.7019098