CGD-Net: A Hybrid End-to-end Network with gating decoding for Liver Tumor Segmentation from CT Images

Xiaogang Zhu, Tao Liu, Ziqiu Liu, Ouyang Shaobo, Xin Wang, Shu Hu, Feng Ding

Abstract: Liver tumor segmentation plays a crucial role in the diagnosis and treatment of hepatic lesions. However, accurate tumor segmentation remains a challenging task due to the fuzzy boundaries of liver tumors and the uncertainty in shape, size, and location. In this paper, we propose a new end-to-end segmentation network called CGD-Net, which incorporates Transformer and frequency-domain features into a convolutional network, and proposes a new decoder structure to automatically learn from Segmentation of liver tumors in CT images. The proposed CGD-Net consists of a Transformer encoder, a frequency domain information fusion module, a gated decoder and three skip connections. Using the powerful feature extraction capability of the Transformer encoder to extract multi-feature information.CGD(Control Gate Decoder)blocks gradually restore the feature information lost in the encoding process by emphasizing the original information.In order to fully utilize the information of the original image, three skip connections are used to connect each encoder layer and its corresponding decoder layer, and a FEM (Frequency-domain Enhance module)is built in the third skip connection to fuse frequency domain features. Experiments on the LiTS dataset validate that the proposed CGD-Net can effectively segment liver tumors from CT images in an end-to-end manner, with segmentation accuracy exceeding many existing methods.