SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image
In recent years, cervical spondylosis has become one of the most common chronic diseases and has received much attention from the public. Magnetic resonance imaging (MRI) is the most widely used imaging modality for the diagnosis of degenerative cervical spondylosis. The manual identification and se...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2022.1081441/full |
| _version_ | 1828091851466342400 |
|---|---|
| author | Xiang Zhang Yi Yang Yi-Wei Shen Ping Li Yuan Zhong Jing Zhou Ke-Rui Zhang Chang-Yong Shen Yi Li Meng-Fei Zhang Long-Hai Pan Li-Tai Ma Hao Liu |
| author_facet | Xiang Zhang Yi Yang Yi-Wei Shen Ping Li Yuan Zhong Jing Zhou Ke-Rui Zhang Chang-Yong Shen Yi Li Meng-Fei Zhang Long-Hai Pan Li-Tai Ma Hao Liu |
| author_sort | Xiang Zhang |
| collection | DOAJ |
| description | In recent years, cervical spondylosis has become one of the most common chronic diseases and has received much attention from the public. Magnetic resonance imaging (MRI) is the most widely used imaging modality for the diagnosis of degenerative cervical spondylosis. The manual identification and segmentation of the cervical spine on MRI makes it a laborious, time-consuming, and error-prone process. In this work, we collected a new dataset of 300 patients with a total of 600 cervical spine images in the MRI T2-weighted (T2W) modality for the first time, which included the cervical spine, intervertebral discs, spinal cord, and spinal canal information. A new instance segmentation approach called SeUneter was proposed for cervical spine segmentation. SeUneter expanded the depth of the network structure based on the original U-Net and added a channel attention module to the double convolution of the feature extraction. SeUneter could enhance the semantic information of the segmentation and weaken the characteristic information of non-segmentation to the screen for important feature channels in double convolution. In the meantime, to alleviate the over-fitting of the model under insufficient samples, the Cutout was used to crop the pixel information in the original image at random positions of a fixed size, and the number of training samples in the original data was increased. Prior knowledge of the data was used to optimize the segmentation results by a post-process to improve the segmentation performance. The mean of Intersection Over Union (mIOU) was calculated for the different categories, while the mean of the Dice similarity coefficient (mDSC) and mIOU were calculated to compare the segmentation results of different deep learning models for all categories. Compared with multiple models under the same experimental settings, our proposed SeUneter’s performance was superior to U-Net, AttU-Net, UNet++, DeepLab-v3+, TransUNet, and Swin-Unet on the spinal cord with mIOU of 86.34% and the spinal canal with mIOU of 73.44%. The SeUneter matched or exceeded the performance of the aforementioned segmentation models when segmenting vertebral bodies or intervertebral discs. Among all models, SeUneter achieved the highest mIOU and mDSC of 82.73% and 90.66%, respectively, for the whole cervical spine. |
| first_indexed | 2024-04-11T06:19:34Z |
| format | Article |
| id | doaj.art-56310af04da1420b9570f7d56a32186f |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-11T06:19:34Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-56310af04da1420b9570f7d56a32186f2022-12-22T04:40:49ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-12-011310.3389/fphys.2022.10814411081441SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical imageXiang Zhang0Yi Yang1Yi-Wei Shen2Ping Li3Yuan Zhong4Jing Zhou5Ke-Rui Zhang6Chang-Yong Shen7Yi Li8Meng-Fei Zhang9Long-Hai Pan10Li-Tai MaHao Liu11Department of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaSchool of Computer Science, Southwest Petroleum University, Chengdu, ChinaSchool of Computer Science, Southwest Petroleum University, Chengdu, ChinaSchool of Computer Science, Southwest Petroleum University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaWest China School of Medicine, Sichuan University, Chengdu, ChinaWest China School of Medicine, Sichuan University, Chengdu, ChinaDepartment of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, ChinaIn recent years, cervical spondylosis has become one of the most common chronic diseases and has received much attention from the public. Magnetic resonance imaging (MRI) is the most widely used imaging modality for the diagnosis of degenerative cervical spondylosis. The manual identification and segmentation of the cervical spine on MRI makes it a laborious, time-consuming, and error-prone process. In this work, we collected a new dataset of 300 patients with a total of 600 cervical spine images in the MRI T2-weighted (T2W) modality for the first time, which included the cervical spine, intervertebral discs, spinal cord, and spinal canal information. A new instance segmentation approach called SeUneter was proposed for cervical spine segmentation. SeUneter expanded the depth of the network structure based on the original U-Net and added a channel attention module to the double convolution of the feature extraction. SeUneter could enhance the semantic information of the segmentation and weaken the characteristic information of non-segmentation to the screen for important feature channels in double convolution. In the meantime, to alleviate the over-fitting of the model under insufficient samples, the Cutout was used to crop the pixel information in the original image at random positions of a fixed size, and the number of training samples in the original data was increased. Prior knowledge of the data was used to optimize the segmentation results by a post-process to improve the segmentation performance. The mean of Intersection Over Union (mIOU) was calculated for the different categories, while the mean of the Dice similarity coefficient (mDSC) and mIOU were calculated to compare the segmentation results of different deep learning models for all categories. Compared with multiple models under the same experimental settings, our proposed SeUneter’s performance was superior to U-Net, AttU-Net, UNet++, DeepLab-v3+, TransUNet, and Swin-Unet on the spinal cord with mIOU of 86.34% and the spinal canal with mIOU of 73.44%. The SeUneter matched or exceeded the performance of the aforementioned segmentation models when segmenting vertebral bodies or intervertebral discs. Among all models, SeUneter achieved the highest mIOU and mDSC of 82.73% and 90.66%, respectively, for the whole cervical spine.https://www.frontiersin.org/articles/10.3389/fphys.2022.1081441/fullMRI image segmentationU-Netdata augmentationchannel attentioncervical spine |
| spellingShingle | Xiang Zhang Yi Yang Yi-Wei Shen Ping Li Yuan Zhong Jing Zhou Ke-Rui Zhang Chang-Yong Shen Yi Li Meng-Fei Zhang Long-Hai Pan Li-Tai Ma Hao Liu SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image Frontiers in Physiology MRI image segmentation U-Net data augmentation channel attention cervical spine |
| title | SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image |
| title_full | SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image |
| title_fullStr | SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image |
| title_full_unstemmed | SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image |
| title_short | SeUneter: Channel attentive U-Net for instance segmentation of the cervical spine MRI medical image |
| title_sort | seuneter channel attentive u net for instance segmentation of the cervical spine mri medical image |
| topic | MRI image segmentation U-Net data augmentation channel attention cervical spine |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2022.1081441/full |
| work_keys_str_mv | AT xiangzhang seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT yiyang seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT yiweishen seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT pingli seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT yuanzhong seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT jingzhou seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT keruizhang seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT changyongshen seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT yili seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT mengfeizhang seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT longhaipan seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT litaima seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage AT haoliu seuneterchannelattentiveunetforinstancesegmentationofthecervicalspinemrimedicalimage |