Retinal blood vessel segmentation based on the gabor filter and optimized top-hat morphology

Retinal fundus images, specifically the morphology of blood vessels, are valuable diagnostic tools for diseases such as hypertension, diabetic retinopathy, and glaucoma. Modern ophthalmic diagnostic methods rely on the results of analyses of retinal images, and the quality of these analyses depends on the precision with which blood vessels in the retina are segmented. Retinal blood vessel segmentation methods all rely on a process known as contrast enhancement. Having uniform contrast throughout the image is crucial to the accuracy of the segmentation. An essential step in Computer-Aided Diagnosis (CAD) for many eye conditions is the automatic segmentation of retinal blood vessels. Medical analysis and disease diagnosis rely on segmenting thin and thick retinal vessels. This article proposes a new method for accurate vessel segmentation to overcome the difficulties already described in the literature. However, the proposed method is based on the Gabor filter and optimized top-hat morphology techniques. The proposed method is divided into three main stages, image pre-processing, segmentation, and post-processing. A common and public dataset, DRIVE, is employed to evaluate our proposed method. In addition, three metrics are utilized to evaluate the proposed method: accuracy, sensitivity, and specificity. As a result, compared to the state-of-the-art method, the proposed method resulted in significantly improved segmentation accuracy, achieving an accuracy of 96.55%, a sensitivity of 79.36%, and a specificity of 98.20% for the training set. Also, the final results of the proposed method achieved 95.95%, 74.24%, and 98.05% for the testing set’s accuracy, sensitivity, and specificity, respectively.