SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation

7 Apr 2020  ·  Changlu Guo, Márton Szemenyei, Yugen Yi, Wenle Wang, Buer Chen, Changqi Fan ·

The precise segmentation of retinal blood vessels is of great significance for early diagnosis of eye-related diseases such as diabetes and hypertension. In this work, we propose a lightweight network named Spatial Attention U-Net (SA-UNet) that does not require thousands of annotated training samples and can be utilized in a data augmentation manner to use the available annotated samples more efficiently. SA-UNet introduces a spatial attention module which infers the attention map along the spatial dimension, and multiplies the attention map by the input feature map for adaptive feature refinement. In addition, the proposed network employs structured dropout convolutional blocks instead of the original convolutional blocks of U-Net to prevent the network from overfitting. We evaluate SA-UNet based on two benchmark retinal datasets: the Vascular Extraction (DRIVE) dataset and the Child Heart and Health Study (CHASE_DB1) dataset. The results show that the proposed SA-UNet achieves state-of-the-art performance on both datasets.The implementation and the trained networks are available on Github1.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Retinal Vessel Segmentation CHASE_DB1 SA-UNet F1 score 0.8153 # 5
AUC 0.9905 # 4
Retinal Vessel Segmentation DRIVE SA-UNet F1 score 0.8263 # 4
AUC 0.9864 # 3
Accuracy 0.9698 # 4