SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation
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 liv...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-1751.pdf |
| _version_ | 1797341772865601536 |
|---|---|
| author | Lizhuang Liu Kun Wu Ke Wang Zhenqi Han Jianxing Qiu Qiao Zhan Tian Wu Jinghang Xu Zheng Zeng |
| author_facet | Lizhuang Liu Kun Wu Ke Wang Zhenqi Han Jianxing Qiu Qiao Zhan Tian Wu Jinghang Xu Zheng Zeng |
| author_sort | Lizhuang Liu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T10:23:01Z |
| format | Article |
| id | doaj.art-c74c3529302845089b4a320cbe4b7d10 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-03-08T10:23:01Z |
| publishDate | 2024-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-c74c3529302845089b4a320cbe4b7d102024-01-27T15:05:13ZengPeerJ Inc.PeerJ Computer Science2376-59922024-01-0110e175110.7717/peerj-cs.1751SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentationLizhuang Liu0Kun Wu1Ke Wang2Zhenqi Han3Jianxing Qiu4Qiao Zhan5Tian Wu6Jinghang Xu7Zheng Zeng8Shanghai Advanced Research Institute, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shanghai, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shanghai, ChinaRadiology Department, Peking University First Hospital, Beijing, ChinaShanghai Advanced Research Institute, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Shanghai, ChinaRadiology Department, Peking University First Hospital, Beijing, ChinaDepartment of Infectious Diseases, The First Affiliated Hospital of Nanjing Medical University, Nanjing, ChinaDepartment of Infectious Diseases, Peking University First Hospital, Beijing, ChinaDepartment of Infectious Diseases, Peking University First Hospital, Beijing, ChinaDepartment of Infectious Diseases, Peking University First Hospital, Beijing, ChinaLiver 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.https://peerj.com/articles/cs-1751.pdfDeep learningLiver occupying lesion segmentationCTSE attentionU2-Net |
| spellingShingle | Lizhuang Liu Kun Wu Ke Wang Zhenqi Han Jianxing Qiu Qiao Zhan Tian Wu Jinghang Xu Zheng Zeng SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation PeerJ Computer Science Deep learning Liver occupying lesion segmentation CT SE attention U2-Net |
| title | SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation |
| title_full | SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation |
| title_fullStr | SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation |
| title_full_unstemmed | SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation |
| title_short | SEU2-Net: multi-scale U2-Net with SE attention mechanism for liver occupying lesion CT image segmentation |
| title_sort | seu2 net multi scale u2 net with se attention mechanism for liver occupying lesion ct image segmentation |
| topic | Deep learning Liver occupying lesion segmentation CT SE attention U2-Net |
| url | https://peerj.com/articles/cs-1751.pdf |
| work_keys_str_mv | AT lizhuangliu seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT kunwu seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT kewang seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT zhenqihan seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT jianxingqiu seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT qiaozhan seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT tianwu seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT jinghangxu seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation AT zhengzeng seu2netmultiscaleu2netwithseattentionmechanismforliveroccupyinglesionctimagesegmentation |