AA-WGAN: Attention augmented Wasserstein generative adversarial network with application to fundus retinal vessel segmentation

In this paper, a novel attention augmented Wasserstein generative adversarial network (AA-WGAN) is proposed for fundus retinal vessel segmentation, where a U-shaped network with attention augmented convolution and squeeze-excitation module is designed to serve as the generator. In particular, the complex vascular structures make some tiny vessels hard to segment, while the proposed AA-WGAN can effectively handle such imperfect data property, which is competent in capturing the dependency among pixels in the whole image to highlight the regions of interests via the applied attention augmented convolution. By applying the squeeze-excitation module, the generator is able to pay attention to the important channels of the feature maps, and the useless information can be suppressed as well. In addition, gradient penalty method is adopted in the WGAN backbone to alleviate the phenomenon of generating large amounts of repeated images due to excessive concentration on accuracy. The proposed model is comprehensively evaluated on three datasets DRIVE, STARE, and CHASE_DB1, and the results show that the proposed AA-WGAN is a competitive vessel segmentation model as compared with several other advanced models, which obtains the accuracy of 96.51%, 97.19% and 96.94% on each dataset, respectively. The effectiveness of the applied important components is validated by ablation study, which also endows the proposed AA-WGAN with considerable generalization ability.

Automated summary

In this paper, a novel attention augmented Wasserstein generative adversarial network (AA-WGAN) is proposed for fundus retinal vessel segmentation. The proposed AA-WGAN can effectively handle the imperfect data property of segmenting tiny vessels, highlight regions of interests via attention augmented convolution, and suppress useless information through the squeeze-excitation module. The comprehensive evaluation on three datasets confirms the competitiveness of the proposed AA-WGAN, with accuracy of 96.51%, 97.19%, and 96.94% achieved on DRIVE, STARE, and CHASE_DB1 datasets respectively. The effectiveness of important components is validated by ablation study, demonstrating considerable generalization ability of the proposed AA-WGAN.