Morphological and Otsu’s Thresholding-Based Retinal Blood Vessel Segmentation for Detection of Retinopathy

Abstract

Retinal blood vessel segmentation is crucial as it is the earliest process in measuring various indicators of retinopathy sign such as arterial-venous nicking, and focal arteriolar and generalized arteriolar narrowing. The segmentation can be clinically used if its accuracy is close to 100%. In this study, a new method of segmentation is developed for extraction of retinal blood vessel. In this paper, we present a new automated method to extract blood vessels in retinal fundus images. The proposed method comprises of two main parts and a few subcomponents which include pre-processing and segmentation. The main focus for the segmentation part is two morphological reconstructions which are the morphological reconstructions followed by the morphological top-hat transform. Then the technique to classify the vessel pixels and background pixels is Otsu’s Thresholding. The image database used in this study is the High Resolution Fundus Image Database (HRFID). The developed segmentation method accuracies are 95.17%, 92.06% and 94.71% when tested on dataset of healthy, diabetic retinopathy (DR) and glaucoma patients respectively. Overall, the performance of the proposed method is comparable with existing methods with overall accuracies were more than 90 % for all three different categories: healthy, DR and glaucoma.

Retinal image blood vessel extraction and quantification with Euclidean distance transform approach

“…The obtained performance of the proposed algorithm was compared with the human observers and the other existing vessel diameter quantification method (see Table 3). In the stage of segmentation it was observed that for the noisy and high‐resolution images, the applied thresholding‐based ISODATA [28] segmentation method provided more accurate results in comparison with other existing segmentation methods such as the morphological and Otsu's thresholding method [6]. The resultants of the proposed algorithm appeared as pixel values with a decimal point because these were calculated as the mean of pixel values.…”

“…Y K3 ), … and (X Kn , Y Kn ) are the coordinates of K 1 , K 2 , K 3 , … Kn pixels. Then the mean ED, the radius of the ROI can be computed following (6) (see (6)) . Fig.…”

“…Digital image processing is being used extensively in the researches of biomedical engineering and disease diagnosis, treatment planning and supervising, and state monitoring of the respective disease [2]. Due to the simple and non-invasive visualisation of the microvasculature of the human retina, fundus eye image can be analysed to extract the remarkable features of the retinal microvasculature that can be used to predict some dangerous cardiovascular diseases such as diabetes, hypertension, and stroke [3][4][5][6].…”

Contrast enhancement for improved blood vessels retinal segmentation using top-hat transformation and otsu thresholding

“…The process was dependent on the threshold value (U) to fix which areas were included into foreground and which areas were included into background. To create a binary image, the image binarization process was as followed [27]:…”