PIPO-FAN
In this paper, we propose a novel network architecture for unified multi-scale feature abstraction, which incorporates multi-scale features in a hierarchical fashion at various depths for image segmentation. The 2D network shows very competitive performance compared with other 3D networks in liver CT image segmentation with a single step. We further develop a unified segmentation strategy to train the three separate datasets together and do multi-organ segmentation with these partial datasets. It gives the segmentation network more robustness and accuracy. We'll test the method further in future work.