In medical sciences, detecting blood vessels in retinal images provides important information for ophthalmologists. The detection of vessels in retinal images is highly significant due to their critical role in eye health evaluation. These vessels are essential for diagnosing diseases, monitoring changes over time, and assessing conditions such as diabetic retinopathy, retinal artery occlusion, and ocular hypertension. To this end, this paper proposes a new algorithm for retinal vessel segmentation. The algorithm utilizes various image processing techniques, especially morphological processing. The innovative aspects of this research include using grayscale images obtained from all three channels of the color image, combining multiple image processing methods, applying Gabor filtering, and proposing a sharpening technique to enhance edges. Additionally, a modified method for background estimation and removal, as well as the use of morphological reconstruction for the final reconstruction and extraction of retinal vessels, are among the research objectives. The efficiency of the proposed algorithms has been evaluated in terms of accuracy, sensitivity, and specificity on the DRIVE and STARE datasets, and the results have been analyzed.
akram asghari govar (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: