Retinal vessel segmentation is a key step towards the accurate visualization, diagnosis, early treatment and surgery planning of ocular diseases. For the last two decades, a tremendous amount of research has been dedicated in developing automated methods for segmentation of blood vessels from retinal fundus images. Despite the fact, segmentation of retinal vessels still remains a challenging task. In this thesis, in order to detect retinal blood vessels, we first improved the quality of the input images in the pre-processing stage by the histogram equalization, and then in the segmentation step, we used the U-Net neural network. This neural network is specifically designed only for segmentation of medical images, and unlike other convolutional neural networks, it does not require large input for training. As the innovative aspect, the meta-parameters of this neural network, including the batch size and the learning rate, were optimized using the particle swarm optimization algorithm. In the end, we were able to achieve 99.6% accuracy, 93.2% sensitivity and 99.7% specificity.
