Using a modified U-net model to improve Retinal Vessel Segmentation

Abstract

AI applications in healthcare have broad and exciting prospects, especially in medical image segmentation where AI has proved it can do a better job than human beings in specific tasks. In this project, we apply a U-net model to complete the retinal vessel segmentation task and compare the results with the morphology method which is a classical automatic segmentation technique. Besides, we also make an attempt at data enhancement in morphology methods to explore the importance of data preprocessing in digital image processing. The result shows that the U-net model produces better outcomes than the morphology method according to most of the evaluation criteria. However, data enhancement in morphology does not show significant differences from the original.