Attention-guided duplex adversarial U-net for pancreatic segmentation from computed tomography images

Segmenting the organs from computed tomography (CT) images is crucial to early diagnosis and treatment. Pancreas segmentation is especially challenging because the pancreas has a small volume and a large variation in shape.

To mitigate this issue, an attention-guided duplex adversarial U-Net (ADAU-Net) for pancreas segmentation is proposed in this work. First, two adversarial networks are integrated into the baseline U-Net to ensure the obtained prediction maps resemble the ground truths. Then, attention blocks are applied to preserve much contextual information for segmentation. The implementation of the proposed ADAU-Net consists of two steps: 1) backbone segmentor selection scheme is introduced to select an optimal backbone segmentor from three two-dimensional segmentation model variants based on a conventional U-Net and 2) attention blocks are integrated into the backbone segmentor at several locations to enhance the interdependency among pixels for a better segmentation performance, and the optimal structure is selected as a final version.

The experimental results on the National Institutes of Health Pancreas-CT dataset show that our proposed ADAU-Net outperforms the baseline segmentation network by 6.39% in dice similarity coefficient and obtains a competitive performance compared with the-state-of-art methods for pancreas segmentation.

The ADAU-Net achieves satisfactory segmentation results on the public pancreas dataset, indicating that the proposed model can segment pancreas outlines from CT images accurately.