This project explores the use of Deep Learning and Computer Vision techniques to enhance blood vessel segmentation in fundus images, a crucial step in ophthalmological diagnostics. Accurate segmentation of retinal blood vessels is essential for detecting diseases such as diabetic retinopathy, glaucoma, and hypertensive retinopathy, where vascular abnormalities serve as early indicators. Our study begins with a comprehensive literature review of existing deep learning models used for blood vessel segmentation. Subsequently, we will implement and evaluate state-of-the-art segmentation methods using publicly available fundus image datasets. The performance of these models will be compared based on segmentation accuracy, computational efficiency, and clinical relevance. By refining deep learning-based segmentation techniques, this project aims to contribute to the improvement of automated ophthalmological diagnostics, making them more reliable and accessible.