SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation

• Published in: PeerJ. Computer science Vol. 10; p. e1751
• Main Authors: Liu, Lizhuang, Wu, Kun, Wang, Ke, Han, Zhenqi, Qiu, Jianxing, Qiao Zhan, Wu, Tian, Xu, Jinghang, Zeng, Zheng
• Format: Journal Article
• Language: English
• Published: San Diego PeerJ, Inc 25.01.2024; PeerJ Inc
• Subjects: Algorithms; Artificial Intelligence; Automation; Bioinformatics; Clustering; Computed tomography; Computer Vision; Datasets; Deep learning; Excitation; Image segmentation; Kappa coefficient; Lesions; Liver; Liver occupying lesion segmentation; Machine learning; SE attention; Semantics; Tumors; U2-Net
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.1751

Liver occupying lesions can profoundly impact an individual’s health and well-being. To assist physicians in the diagnosis and treatment of abnormal areas in the liver, we propose a novel network named SEU2-Net by introducing the channel attention mechanism into U2-Net for accurate and automatic liver occupying lesion segmentation. We design the Residual U-block with Squeeze-and-Excitation (SE-RSU), which is to add the Squeeze-and-Excitation (SE) attention mechanism at the residual connections of the Residual U-blocks (RSU, the component unit of U2-Net). SEU2-Net not only retains the advantages of U2-Net in capturing contextual information at multiple scales, but can also adaptively recalibrate channel feature responses to emphasize useful feature information according to the channel attention mechanism. In addition, we present a new abdominal CT dataset for liver occupying lesion segmentation from Peking University First Hospital’s clinical data (PUFH dataset). We evaluate the proposed method and compare it with eight deep learning networks on the PUFH and the Liver Tumor Segmentation Challenge (LiTS) datasets. The experimental results show that SEU2-Net has state-of-the-art performance and good robustness in liver occupying lesions segmentation.