Retinal vessel segmentation refers to extracting the vessel region with continuous and smooth boundaries from retinal images, which is of great significance in clinical practices. However, due to the weak and blurry edges of targets as well as interference (such as optic cup and disc) in the background, current deep neural network-based methods struggle in extracting features with discriminative semantics while preserving continuous edges. To enforce continuous predictions of weak edges, we propose a level set guided region prototype rectification (LSRPR) framework and a novel level set loss (LS-loss) with learnable and self-guided mechanisms. Specifically, the LSRPR firstly takes features of the last layer from the decoders of a U-Net version as input and rectified the region prototype by an auxiliary self-supervised level set loss, then the pre-trained model is fine-tuned by using supervised level set loss. The LS-loss facilitates the model to generate reliable guidance and enhances the continuous of edges among the decoders of neural network model. The proposed method is simple, yet effective, which can easily be extended to other frameworks. The quantitative and qualitative experimental results on public retinal vessel datasets indicate the effectiveness of the region prototype rectification compared to other SOTA models. Our code is available at Github:https://github.com/tweedlemoon/LSRPR.