A Contour-Aware Feature-Merged Network for Liver Segmentation Based on Shape Prior Knowledge

Abstract One primary challenge in liver segmentation is the fuzzy edge contour. Recently, fully convolutional neural networks (FCNs) have been widely used in liver segmentation because of their adequate feature extraction. Nevertheless, the context among liver slices has been ignored by the FCN. To address this issue, we propose a bidirectional convolutional long short term memory (BiConvLSTM) to explore contextual information. Furthermore, the global contextual information of BiConvLSTM and the local contextual information of an attention gate (AG) is fused into a BiConvLSTM-AG module. The AG is utilized to fuse high-dimensional information from BiConvLSTM to remove irrelevant features. Besides, the Shape-Net network is proposed to extend the liver shape pattern using latent space information, which reduces the interference of fuzzy boundaries. Finally, the improved active contour loss function with L2 norm is added as a feature constraint. Experimental results on public benchmark datasets show that the proposed method slightly outperforms other newly published methods and achieves good performance for liver segmentation.