U-Net combined with multi-scale attention mechanism for liver segmentation in CT images
Abstract Background The liver is an important organ that undertakes the metabolic function of the human body. Liver cancer has become one of the cancers with the highest mortality. In clinic, it is an important work to extract the liver region accurately before the diagnosis and treatment of liver l...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-10-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-021-01649-w |
| _version_ | 1818937171431653376 |
|---|---|
| author | Jiawei Wu Shengqiang Zhou Songlin Zuo Yiyin Chen Weiqin Sun Jiang Luo Jiantuan Duan Hui Wang Deguang Wang |
| author_facet | Jiawei Wu Shengqiang Zhou Songlin Zuo Yiyin Chen Weiqin Sun Jiang Luo Jiantuan Duan Hui Wang Deguang Wang |
| author_sort | Jiawei Wu |
| collection | DOAJ |
| description | Abstract Background The liver is an important organ that undertakes the metabolic function of the human body. Liver cancer has become one of the cancers with the highest mortality. In clinic, it is an important work to extract the liver region accurately before the diagnosis and treatment of liver lesions. However, manual liver segmentation is a time-consuming and boring process. Not only that, but the segmentation results usually varies from person to person due to different work experience. In order to assist in clinical automatic liver segmentation, this paper proposes a U-shaped network with multi-scale attention mechanism for liver organ segmentation in CT images, which is called MSA-UNet. Our method makes a new design of U-Net encoder, decoder, skip connection, and context transition structure. These structures greatly enhance the feature extraction ability of encoder and the efficiency of decoder to recover spatial location information. We have designed many experiments on publicly available datasets to show the effectiveness of MSA-UNet. Compared with some other advanced segmentation methods, MSA-UNet finally achieved the best segmentation effect, reaching 98.00% dice similarity coefficient (DSC) and 96.08% intersection over union (IOU). |
| first_indexed | 2024-12-20T05:47:43Z |
| format | Article |
| id | doaj.art-5ec0078bc60045c2b84b428004b7ac33 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-12-20T05:47:43Z |
| publishDate | 2021-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-5ec0078bc60045c2b84b428004b7ac332022-12-21T19:51:15ZengBMCBMC Medical Informatics and Decision Making1472-69472021-10-0121111210.1186/s12911-021-01649-wU-Net combined with multi-scale attention mechanism for liver segmentation in CT imagesJiawei Wu0Shengqiang Zhou1Songlin Zuo2Yiyin Chen3Weiqin Sun4Jiang Luo5Jiantuan Duan6Hui Wang7Deguang Wang8School of Medical Imaging, Xuzhou Medical UniversitySchool of Economics and Finance, Xi’an Jiaotong UniversitySchool of the First Clinical Medical, Xuzhou Medical UniversitySchool of the First Clinical Medical, Xuzhou Medical UniversitySchool of Medical Imaging, Xuzhou Medical UniversitySchool of Medical Imaging, Xuzhou Medical UniversitySchool of Economics and Finance, Xi’an Jiaotong UniversitySchool of Medical Imaging, Xuzhou Medical UniversitySchool of Medical Imaging, Xuzhou Medical UniversityAbstract Background The liver is an important organ that undertakes the metabolic function of the human body. Liver cancer has become one of the cancers with the highest mortality. In clinic, it is an important work to extract the liver region accurately before the diagnosis and treatment of liver lesions. However, manual liver segmentation is a time-consuming and boring process. Not only that, but the segmentation results usually varies from person to person due to different work experience. In order to assist in clinical automatic liver segmentation, this paper proposes a U-shaped network with multi-scale attention mechanism for liver organ segmentation in CT images, which is called MSA-UNet. Our method makes a new design of U-Net encoder, decoder, skip connection, and context transition structure. These structures greatly enhance the feature extraction ability of encoder and the efficiency of decoder to recover spatial location information. We have designed many experiments on publicly available datasets to show the effectiveness of MSA-UNet. Compared with some other advanced segmentation methods, MSA-UNet finally achieved the best segmentation effect, reaching 98.00% dice similarity coefficient (DSC) and 96.08% intersection over union (IOU).https://doi.org/10.1186/s12911-021-01649-wDeep learningAttention mechanismMulti-scaleLiver segmentationCT images |
| spellingShingle | Jiawei Wu Shengqiang Zhou Songlin Zuo Yiyin Chen Weiqin Sun Jiang Luo Jiantuan Duan Hui Wang Deguang Wang U-Net combined with multi-scale attention mechanism for liver segmentation in CT images BMC Medical Informatics and Decision Making Deep learning Attention mechanism Multi-scale Liver segmentation CT images |
| title | U-Net combined with multi-scale attention mechanism for liver segmentation in CT images |
| title_full | U-Net combined with multi-scale attention mechanism for liver segmentation in CT images |
| title_fullStr | U-Net combined with multi-scale attention mechanism for liver segmentation in CT images |
| title_full_unstemmed | U-Net combined with multi-scale attention mechanism for liver segmentation in CT images |
| title_short | U-Net combined with multi-scale attention mechanism for liver segmentation in CT images |
| title_sort | u net combined with multi scale attention mechanism for liver segmentation in ct images |
| topic | Deep learning Attention mechanism Multi-scale Liver segmentation CT images |
| url | https://doi.org/10.1186/s12911-021-01649-w |
| work_keys_str_mv | AT jiaweiwu unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT shengqiangzhou unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT songlinzuo unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT yiyinchen unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT weiqinsun unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT jiangluo unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT jiantuanduan unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT huiwang unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages AT deguangwang unetcombinedwithmultiscaleattentionmechanismforliversegmentationinctimages |