Image Analysis for the Assessment of Retinal Vascular Changes
- March 31, 2018
- Posted by: RSIS
- Categories: Electrical and Electronics Engineering, Electronics & Communication Engineering
International Journal of Research and Scientific Innovation (IJRSI) | Volume V, Issue III, March 2018 | ISSN 2321–2705
Image Analysis for the Assessment of Retinal Vascular Changes
Sukumar Fulzele
ME (VLSI and Embedded System)
G.H. Raisoni College of Engineering and Management Wagholi, Pune-412207, India
Abstract—The development of an automatic telemedicine system for computer-aided screening and grading of diabetic retinopathy depends on reliable detection of retinal lesions in fundus images. The main contribution is a new set of texture features called Gabor features that do not require precise segmentation of the regions to be classified. These features represent the evolution of the textures during image flooding and allow to discriminate between lesions and vessel segments. Among several retinal vascular signs, Arteriolar-to-Venular Ratio (AVR) is a well known health biomarker and there is a strong need to develop an automated system for an accurate and reproducible estimation of AVR which requires different image analysis tools. Automatic and accurate blood vessel segmentation system could provide several useful features for diagnosis of various retinal diseases, and reduce the doctor’s workload.We list publicly available databases and appropriate measurement techniques to compare quantitatively the performance of these approaches. Furthermore, we discuss on how the performance of image processing-based systems can be improved by fusing the output of individual detector algorithms. This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. This method uses an ensemble system of bagged and boosted decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. In this paper, we have presented an effective retinal vessel segmentation technique based on supervised classification using an ensemble classifier of boosted and bagged decision trees.
Keywords—Arteriolar-to-Venular Ratio (AVR), hypertension, blood vessel segmentation, cardiovascular diseases, automatic telemedicine system, computer-aided screening.
