SEResU-Net for Multimodal Brain Tumor Segmentation
Glioma is the most common type of brain tumor, and it has a high mortality rate. Accurate tumor segmentation based on magnetic resonance imaging (MRI) is of great significance for the diagnosis and treatment of brain tumors. Recently, the automatic segmentation of brain tumors based on U-Net has gai...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9917504/ |
| _version_ | 1811233482820550656 |
|---|---|
| author | Chengdong Yan Jurong Ding Hui Zhang Ke Tong Bo Hua Shaolong Shi |
| author_facet | Chengdong Yan Jurong Ding Hui Zhang Ke Tong Bo Hua Shaolong Shi |
| author_sort | Chengdong Yan |
| collection | DOAJ |
| description | Glioma is the most common type of brain tumor, and it has a high mortality rate. Accurate tumor segmentation based on magnetic resonance imaging (MRI) is of great significance for the diagnosis and treatment of brain tumors. Recently, the automatic segmentation of brain tumors based on U-Net has gained considerable attention. However, brain tumor segmentation is a challenging task due to the structural variations and inhomogeneous intensity of tumors. Existing brain tumor segmentation studies have shown that the problems of insufficient down-sampling feature extraction and loss of up-sampling information arise when using U-Net to segment brain tumors. In this study, we proposed an improved U-Net model, SEResU-Net, which combines the deep residual network and the Squeeze-and-Excitation Network. The deep residual network solves the problem of network degradation so that SEResU-Net can extract more feature information. The Squeeze-and-Excitation Network avoids information loss and enables the network to focus on the useful feature map, which solves the problem of insufficient segmentation accuracy of small-scale brain tumors. Furthermore, a fusion loss function combining Dice loss and cross-entropy loss was proposed to solve the problems of network convergence and data imbalance. The performance of SEResU-Net was evaluated on the dataset of BraTS2018 and BraTS2019. Experimental results revealed that the mean Dice similarity coefficients of SEResU-Net were 0.9373, 0.9108, and 0.8758 for the whole tumor, the tumor core, and the enhanced tumor, which were 7.10%, 11.88%, and 15.33% greater than those of the U-Net benchmark network, respectively. Our findings demonstrate that the proposed SEResU-Net has a competitive effect in segmenting multimodal brain tumors. |
| first_indexed | 2024-04-12T11:20:46Z |
| format | Article |
| id | doaj.art-273c7bf0c5ea4556a8b92290c311df91 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T11:20:46Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-273c7bf0c5ea4556a8b92290c311df912022-12-22T03:35:22ZengIEEEIEEE Access2169-35362022-01-011011703311704410.1109/ACCESS.2022.32143099917504SEResU-Net for Multimodal Brain Tumor SegmentationChengdong Yan0Jurong Ding1https://orcid.org/0000-0001-6708-5131Hui Zhang2Ke Tong3Bo Hua4Shaolong Shi5https://orcid.org/0000-0002-1926-8141School of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, ChinaSchool of Automation and Information Engineering, Sichuan University of Science and Engineering, Zigong, ChinaYangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China, Quzhou, ChinaGlioma is the most common type of brain tumor, and it has a high mortality rate. Accurate tumor segmentation based on magnetic resonance imaging (MRI) is of great significance for the diagnosis and treatment of brain tumors. Recently, the automatic segmentation of brain tumors based on U-Net has gained considerable attention. However, brain tumor segmentation is a challenging task due to the structural variations and inhomogeneous intensity of tumors. Existing brain tumor segmentation studies have shown that the problems of insufficient down-sampling feature extraction and loss of up-sampling information arise when using U-Net to segment brain tumors. In this study, we proposed an improved U-Net model, SEResU-Net, which combines the deep residual network and the Squeeze-and-Excitation Network. The deep residual network solves the problem of network degradation so that SEResU-Net can extract more feature information. The Squeeze-and-Excitation Network avoids information loss and enables the network to focus on the useful feature map, which solves the problem of insufficient segmentation accuracy of small-scale brain tumors. Furthermore, a fusion loss function combining Dice loss and cross-entropy loss was proposed to solve the problems of network convergence and data imbalance. The performance of SEResU-Net was evaluated on the dataset of BraTS2018 and BraTS2019. Experimental results revealed that the mean Dice similarity coefficients of SEResU-Net were 0.9373, 0.9108, and 0.8758 for the whole tumor, the tumor core, and the enhanced tumor, which were 7.10%, 11.88%, and 15.33% greater than those of the U-Net benchmark network, respectively. Our findings demonstrate that the proposed SEResU-Net has a competitive effect in segmenting multimodal brain tumors.https://ieeexplore.ieee.org/document/9917504/MRIbrain tumor segmentationdeep learningU-Netresidual networksqueeze-and-excitation network |
| spellingShingle | Chengdong Yan Jurong Ding Hui Zhang Ke Tong Bo Hua Shaolong Shi SEResU-Net for Multimodal Brain Tumor Segmentation IEEE Access MRI brain tumor segmentation deep learning U-Net residual network squeeze-and-excitation network |
| title | SEResU-Net for Multimodal Brain Tumor Segmentation |
| title_full | SEResU-Net for Multimodal Brain Tumor Segmentation |
| title_fullStr | SEResU-Net for Multimodal Brain Tumor Segmentation |
| title_full_unstemmed | SEResU-Net for Multimodal Brain Tumor Segmentation |
| title_short | SEResU-Net for Multimodal Brain Tumor Segmentation |
| title_sort | seresu net for multimodal brain tumor segmentation |
| topic | MRI brain tumor segmentation deep learning U-Net residual network squeeze-and-excitation network |
| url | https://ieeexplore.ieee.org/document/9917504/ |
| work_keys_str_mv | AT chengdongyan seresunetformultimodalbraintumorsegmentation AT jurongding seresunetformultimodalbraintumorsegmentation AT huizhang seresunetformultimodalbraintumorsegmentation AT ketong seresunetformultimodalbraintumorsegmentation AT bohua seresunetformultimodalbraintumorsegmentation AT shaolongshi seresunetformultimodalbraintumorsegmentation |