Improved U-Net3+ with stage residual for brain tumor segmentation
Abstract Background For the encoding part of U-Net3+,the ability of brain tumor feature extraction is insufficient, as a result, the features can not be fused well during up-sampling, and the accuracy of segmentation will reduce. Methods In this study, we put forward an improved U-Net3+ segmentation...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-022-00738-0 |
| _version_ | 1819349570471067648 |
|---|---|
| author | Chuanbo Qin Yujie Wu Wenbin Liao Junying Zeng Shufen Liang Xiaozhi Zhang |
| author_facet | Chuanbo Qin Yujie Wu Wenbin Liao Junying Zeng Shufen Liang Xiaozhi Zhang |
| author_sort | Chuanbo Qin |
| collection | DOAJ |
| description | Abstract Background For the encoding part of U-Net3+,the ability of brain tumor feature extraction is insufficient, as a result, the features can not be fused well during up-sampling, and the accuracy of segmentation will reduce. Methods In this study, we put forward an improved U-Net3+ segmentation network based on stage residual. In the encoder part, the encoder based on the stage residual structure is used to solve the vanishing gradient problem caused by the increasing in network depth, and enhances the feature extraction ability of the encoder which is instrumental in full feature fusion when up-sampling in the network. What’s more, we replaced batch normalization (BN) layer with filter response normalization (FRN) layer to eliminate batch size impact on the network. Based on the improved U-Net3+ two-dimensional (2D) model with stage residual, IResUnet3+ three-dimensional (3D) model is constructed. We propose appropriate methods to deal with 3D data, which achieve accurate segmentation of the 3D network. Results The experimental results showed that: the sensitivity of WT, TC, and ET increased by 1.34%, 4.6%, and 8.44%, respectively. And the Dice coefficients of ET and WT were further increased by 3.43% and 1.03%, respectively. To facilitate further research, source code can be found at: https://github.com/YuOnlyLookOne/IResUnet3Plus . Conclusion The improved network has a significant improvement in the segmentation task of the brain tumor BraTS2018 dataset, compared with the classical networks u-net, v-net, resunet and u-net3+, the proposed network has smaller parameters and significantly improved accuracy. |
| first_indexed | 2024-12-24T19:02:37Z |
| format | Article |
| id | doaj.art-347f1aec2718458f8672bce40d380afe |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-12-24T19:02:37Z |
| publishDate | 2022-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-347f1aec2718458f8672bce40d380afe2022-12-21T16:43:09ZengBMCBMC Medical Imaging1471-23422022-01-0122111510.1186/s12880-022-00738-0Improved U-Net3+ with stage residual for brain tumor segmentationChuanbo Qin0Yujie Wu1Wenbin Liao2Junying Zeng3Shufen Liang4Xiaozhi Zhang5Faculty of Intelligent Manufacturing, Wuyi UniversityFaculty of Intelligent Manufacturing, Wuyi UniversityFaculty of Intelligent Manufacturing, Wuyi UniversityFaculty of Intelligent Manufacturing, Wuyi UniversityFaculty of Intelligent Manufacturing, Wuyi UniversitySchool of Electrical Engineering, University of South ChinaAbstract Background For the encoding part of U-Net3+,the ability of brain tumor feature extraction is insufficient, as a result, the features can not be fused well during up-sampling, and the accuracy of segmentation will reduce. Methods In this study, we put forward an improved U-Net3+ segmentation network based on stage residual. In the encoder part, the encoder based on the stage residual structure is used to solve the vanishing gradient problem caused by the increasing in network depth, and enhances the feature extraction ability of the encoder which is instrumental in full feature fusion when up-sampling in the network. What’s more, we replaced batch normalization (BN) layer with filter response normalization (FRN) layer to eliminate batch size impact on the network. Based on the improved U-Net3+ two-dimensional (2D) model with stage residual, IResUnet3+ three-dimensional (3D) model is constructed. We propose appropriate methods to deal with 3D data, which achieve accurate segmentation of the 3D network. Results The experimental results showed that: the sensitivity of WT, TC, and ET increased by 1.34%, 4.6%, and 8.44%, respectively. And the Dice coefficients of ET and WT were further increased by 3.43% and 1.03%, respectively. To facilitate further research, source code can be found at: https://github.com/YuOnlyLookOne/IResUnet3Plus . Conclusion The improved network has a significant improvement in the segmentation task of the brain tumor BraTS2018 dataset, compared with the classical networks u-net, v-net, resunet and u-net3+, the proposed network has smaller parameters and significantly improved accuracy.https://doi.org/10.1186/s12880-022-00738-0Brain tumor segmentationStage ResidualU-Net3+Full-scale connectionFRN |
| spellingShingle | Chuanbo Qin Yujie Wu Wenbin Liao Junying Zeng Shufen Liang Xiaozhi Zhang Improved U-Net3+ with stage residual for brain tumor segmentation BMC Medical Imaging Brain tumor segmentation Stage Residual U-Net3+ Full-scale connection FRN |
| title | Improved U-Net3+ with stage residual for brain tumor segmentation |
| title_full | Improved U-Net3+ with stage residual for brain tumor segmentation |
| title_fullStr | Improved U-Net3+ with stage residual for brain tumor segmentation |
| title_full_unstemmed | Improved U-Net3+ with stage residual for brain tumor segmentation |
| title_short | Improved U-Net3+ with stage residual for brain tumor segmentation |
| title_sort | improved u net3 with stage residual for brain tumor segmentation |
| topic | Brain tumor segmentation Stage Residual U-Net3+ Full-scale connection FRN |
| url | https://doi.org/10.1186/s12880-022-00738-0 |
| work_keys_str_mv | AT chuanboqin improvedunet3withstageresidualforbraintumorsegmentation AT yujiewu improvedunet3withstageresidualforbraintumorsegmentation AT wenbinliao improvedunet3withstageresidualforbraintumorsegmentation AT junyingzeng improvedunet3withstageresidualforbraintumorsegmentation AT shufenliang improvedunet3withstageresidualforbraintumorsegmentation AT xiaozhizhang improvedunet3withstageresidualforbraintumorsegmentation |