Multi-scale Neural Networks for Retinal Blood Vessels Segmentation

Boheng Zhang, Shenglei Huang, Shaohan Hu

Abstract: Existing supervised approaches didn’t make use of the low-level features which are actually effective to semantic segmentation. And another deficiency is that they didn’t consider the relation between pixels, which means effective features are not extracted. In this paper, we applied semantic segmentation on retinal blood vessel images and proposed a novel convolutional neural network which make sufficient use of low-level features together with high-level features and involves atrous convolution to get multi-scale features which should be considered as effective features. Our model is tested on three standard benchmarks - DRIVE, STARE, and CHASE databases. The results presents that our model significantly outperforms existing approaches in terms of accuracy, sensitivity, specificity, the area under the ROC curve and the highest prediction speed. Our work provides evidence of the power of wide and deep neural networks in retinal blood vessels segmentation task which could be applied on other medical images tasks.

Keywords: deep learning, neural networks, retina image, retinopathy, vessel segmentation

Author Affiliation: Tsinghua University, Shanghai Jiao Tong University, Tsinghua University