Retinal vessel segmentation via deep learning network and fully-connected conditional random fields

Abstract

Vessel segmentation is a key step for various medical applications. This paper introduces the deep learning architecture to improve the performance of retinal vessel segmentation. Deep learning architecture has been demonstrated having the powerful ability in automatically learning the rich hierarchical representations. In this paper, we formulate the vessel segmentation to a boundary detection problem, and utilize the fully convolutional neural networks (CNNs) to generate a vessel probability map. Our vessel probability map distinguishes the vessels and background in the inadequate contrast region, and has robustness to the pathological regions in the fundus image. Moreover, a fully-connected Conditional Random Fields (CRFs) is also employed to combine the discriminative vessel probability map and long-range interactions between pixels. Finally, a binary vessel segmentation result is obtained by our method. We show that our proposed method achieve a state-of-the-art vessel segmentation performance on the DRIVE and STARE datasets.