Liu Lizhuang, Wu Kun, Wang Ke, Han Zhenqi, Qiu Jianxing, Zhan Qiao, Wu Tian, Xu Jinghang, Zeng Zheng
Shanghai Advanced Research Institute, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shanghai, China.
Radiology Department, Peking University First Hospital, Beijing, China.
PeerJ Comput Sci. 2024 Jan 25;10:e1751. doi: 10.7717/peerj-cs.1751. eCollection 2024.
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 SEU-Net by introducing the channel attention mechanism into U-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 U-Net). SEU-Net not only retains the advantages of U-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 SEU-Net has state-of-the-art performance and good robustness in liver occupying lesions segmentation.
肝脏占位性病变会对个人的健康和福祉产生深远影响。为了帮助医生诊断和治疗肝脏中的异常区域，我们通过将通道注意力机制引入U-Net，提出了一种名为SEU-Net的新型网络，用于准确自动地分割肝脏占位性病变。我们设计了带有挤压激励（SE）的残差U块（SE-RSU），即在残差U块（RSU，U-Net的组成单元）的残差连接处添加挤压激励（SE）注意力机制。SEU-Net不仅保留了U-Net在多尺度捕捉上下文信息方面的优势，还能根据通道注意力机制自适应地重新校准通道特征响应，以强调有用的特征信息。此外，我们从北京大学第一医院的临床数据中提出了一个用于肝脏占位性病变分割的新腹部CT数据集（PUFH数据集）。我们在PUFH和肝脏肿瘤分割挑战赛（LiTS）数据集上评估了所提出的方法，并将其与八个深度学习网络进行了比较。实验结果表明，SEU-Net在肝脏占位性病变分割方面具有先进的性能和良好的鲁棒性。
