Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus
Automatic segmentation of the cancerous esophagus in computed tomography (CT) images is a computer-assisted method that can improve the efficiency of the diagnosis and treatment. Due to the diversity of the cancer stage and location, the anatomical structure of the cancerous esophagus is various. Mo...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9178277/ |
| _version_ | 1818349882165952512 |
|---|---|
| author | Donghao Zhou Guoheng Huang Jiajian Li Siyu Zhu Zhuowei Wang Bingo Wing-Kuen Ling Chi-Man Pun Lianglun Cheng Xiuyu Cai Jian Zhou |
| author_facet | Donghao Zhou Guoheng Huang Jiajian Li Siyu Zhu Zhuowei Wang Bingo Wing-Kuen Ling Chi-Man Pun Lianglun Cheng Xiuyu Cai Jian Zhou |
| author_sort | Donghao Zhou |
| collection | DOAJ |
| description | Automatic segmentation of the cancerous esophagus in computed tomography (CT) images is a computer-assisted method that can improve the efficiency of the diagnosis and treatment. Due to the diversity of the cancer stage and location, the anatomical structure of the cancerous esophagus is various. Moreover, the low contrast against surrounding tissues leads to a blurry boundary of the cancerous esophagus. Therefore, existing segmentation networks cannot achieve satisfactory results in automatic segmentation of the cancerous esophagus. In this article, we propose a novel 2.5D segmentation network named Eso-Net for the cancerous esophagus based on an encoder-decoder architecture. A 3D enhancement filter called Multi-Structure Response Filter (MSRF) is designed to extract 3D structural information as prior knowledge. Furthermore, dilated convolutions and residual connections are employed in the convolutional blocks of Eso-Net for multi-scale feature learning. With 3D structural priors, Prior Attention Modules (PAM) are incorporated into the network to facilitate the transmission of relevant spatial information. The experiments are conducted on the dataset from 30 esophageal cancer patients, and we report an 84.839% dice similarity coefficient, an 85.955% precision, an 83.752% sensitivity, and a 2.583mm Hausdorff distance. The experimental results demonstrate that the proposed method outperforms other existing segmentation networks in this task and can effectively assist doctors in the diagnosis and treatment of esophageal cancer. |
| first_indexed | 2024-12-13T18:13:00Z |
| format | Article |
| id | doaj.art-9cd8a31c748f4093b637a4b1a2dcd0f7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T18:13:00Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9cd8a31c748f4093b637a4b1a2dcd0f72022-12-21T23:35:55ZengIEEEIEEE Access2169-35362020-01-01815554815556210.1109/ACCESS.2020.30195189178277Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous EsophagusDonghao Zhou0https://orcid.org/0000-0001-5378-8311Guoheng Huang1https://orcid.org/0000-0002-3640-3229Jiajian Li2Siyu Zhu3Zhuowei Wang4https://orcid.org/0000-0001-6479-5154Bingo Wing-Kuen Ling5https://orcid.org/0000-0002-0633-7224Chi-Man Pun6https://orcid.org/0000-0003-1788-3746Lianglun Cheng7Xiuyu Cai8Jian Zhou9https://orcid.org/0000-0002-6868-9866School of Information Engineering, Guangdong University of Technology, Guangzhou, ChinaSchool of Computers, Guangdong University of Technology, Guangzhou, ChinaSchool of Computers, Guangdong University of Technology, Guangzhou, ChinaDepartment of Medical Imaging, Sun Yat-sen University Cancer Center, Guangzhou, ChinaSchool of Computers, Guangdong University of Technology, Guangzhou, ChinaSchool of Information Engineering, Guangdong University of Technology, Guangzhou, ChinaDepartment of Computer and Information Science, University of Macau, Zhuhai, MacauSchool of Computers, Guangdong University of Technology, Guangzhou, ChinaDepartment of Medical Oncology, Sun Yat-sen University Cancer Center, Guangzhou, ChinaDepartment of Medical Imaging, Sun Yat-sen University Cancer Center, Guangzhou, ChinaAutomatic segmentation of the cancerous esophagus in computed tomography (CT) images is a computer-assisted method that can improve the efficiency of the diagnosis and treatment. Due to the diversity of the cancer stage and location, the anatomical structure of the cancerous esophagus is various. Moreover, the low contrast against surrounding tissues leads to a blurry boundary of the cancerous esophagus. Therefore, existing segmentation networks cannot achieve satisfactory results in automatic segmentation of the cancerous esophagus. In this article, we propose a novel 2.5D segmentation network named Eso-Net for the cancerous esophagus based on an encoder-decoder architecture. A 3D enhancement filter called Multi-Structure Response Filter (MSRF) is designed to extract 3D structural information as prior knowledge. Furthermore, dilated convolutions and residual connections are employed in the convolutional blocks of Eso-Net for multi-scale feature learning. With 3D structural priors, Prior Attention Modules (PAM) are incorporated into the network to facilitate the transmission of relevant spatial information. The experiments are conducted on the dataset from 30 esophageal cancer patients, and we report an 84.839% dice similarity coefficient, an 85.955% precision, an 83.752% sensitivity, and a 2.583mm Hausdorff distance. The experimental results demonstrate that the proposed method outperforms other existing segmentation networks in this task and can effectively assist doctors in the diagnosis and treatment of esophageal cancer.https://ieeexplore.ieee.org/document/9178277/Esophageal cancermedical image segmentationdeep learningattention mechanismenhancement filter |
| spellingShingle | Donghao Zhou Guoheng Huang Jiajian Li Siyu Zhu Zhuowei Wang Bingo Wing-Kuen Ling Chi-Man Pun Lianglun Cheng Xiuyu Cai Jian Zhou Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus IEEE Access Esophageal cancer medical image segmentation deep learning attention mechanism enhancement filter |
| title | Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus |
| title_full | Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus |
| title_fullStr | Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus |
| title_full_unstemmed | Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus |
| title_short | Eso-Net: A Novel 2.5D Segmentation Network With the Multi-Structure Response Filter for the Cancerous Esophagus |
| title_sort | eso net a novel 2 5d segmentation network with the multi structure response filter for the cancerous esophagus |
| topic | Esophageal cancer medical image segmentation deep learning attention mechanism enhancement filter |
| url | https://ieeexplore.ieee.org/document/9178277/ |
| work_keys_str_mv | AT donghaozhou esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT guohenghuang esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT jiajianli esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT siyuzhu esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT zhuoweiwang esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT bingowingkuenling esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT chimanpun esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT liangluncheng esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT xiuyucai esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus AT jianzhou esonetanovel25dsegmentationnetworkwiththemultistructureresponsefilterforthecancerousesophagus |