DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network
To address the problems of under-segmentation and over-segmentation of small organs in medical image segmentation. We present a novel medical image segmentation network model with Depth Separable Gating Transformer and a Three-branch Attention module (DSGA-Net). Firstly, the model adds a Depth Separ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S131915782300099X |
| _version_ | 1797817501112860672 |
|---|---|
| author | Junding Sun Jiuqiang Zhao Xiaosheng Wu Chaosheng Tang Shuihua Wang Yudong Zhang |
| author_facet | Junding Sun Jiuqiang Zhao Xiaosheng Wu Chaosheng Tang Shuihua Wang Yudong Zhang |
| author_sort | Junding Sun |
| collection | DOAJ |
| description | To address the problems of under-segmentation and over-segmentation of small organs in medical image segmentation. We present a novel medical image segmentation network model with Depth Separable Gating Transformer and a Three-branch Attention module (DSGA-Net). Firstly, the model adds a Depth Separable Gated Visual Transformer (DSG-ViT) module into its Encoder to enhance (i) the contextual links among global, local, and channels and (ii) the sensitivity to location information. Secondly, a Mixed Three-branch Attention (MTA) module is proposed to increase the number of features in the up-sampling process. Meanwhile, the loss of feature information is reduced when restoring the feature image to the original image size. By validating Synapse, BraTs2020, and ACDC public datasets, the Dice Similarity Coefficient (DSC) of the results of DSGA-Net reached 81.24%,85.82%, and 91.34%, respectively. Moreover, the Hausdorff Score (HD) decreased to 20.91% and 5.27% on the Synapse and BraTs2020. There are 10.78% and 0.69% decreases compared to the Baseline TransUNet. The experimental results indicate that DSGA-Net achieves better segmentation than most advanced methods. |
| first_indexed | 2024-03-13T08:54:23Z |
| format | Article |
| id | doaj.art-7b48fde19a1b4168934464aad2302ab9 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-13T08:54:23Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-7b48fde19a1b4168934464aad2302ab92023-05-29T04:03:46ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-05-01355101553DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation networkJunding Sun0Jiuqiang Zhao1Xiaosheng Wu2Chaosheng Tang3Shuihua Wang4Yudong Zhang5School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR ChinaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR China; School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK; Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaSchool of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, PR China; School of Computing and Mathematical Sciences, University of Leicester, Leicester LE1 7RH, UK; Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia; Corresponding author.To address the problems of under-segmentation and over-segmentation of small organs in medical image segmentation. We present a novel medical image segmentation network model with Depth Separable Gating Transformer and a Three-branch Attention module (DSGA-Net). Firstly, the model adds a Depth Separable Gated Visual Transformer (DSG-ViT) module into its Encoder to enhance (i) the contextual links among global, local, and channels and (ii) the sensitivity to location information. Secondly, a Mixed Three-branch Attention (MTA) module is proposed to increase the number of features in the up-sampling process. Meanwhile, the loss of feature information is reduced when restoring the feature image to the original image size. By validating Synapse, BraTs2020, and ACDC public datasets, the Dice Similarity Coefficient (DSC) of the results of DSGA-Net reached 81.24%,85.82%, and 91.34%, respectively. Moreover, the Hausdorff Score (HD) decreased to 20.91% and 5.27% on the Synapse and BraTs2020. There are 10.78% and 0.69% decreases compared to the Baseline TransUNet. The experimental results indicate that DSGA-Net achieves better segmentation than most advanced methods.http://www.sciencedirect.com/science/article/pii/S131915782300099XMedical image segmentationTransformerGated attention mechanismDepth separable |
| spellingShingle | Junding Sun Jiuqiang Zhao Xiaosheng Wu Chaosheng Tang Shuihua Wang Yudong Zhang DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network Journal of King Saud University: Computer and Information Sciences Medical image segmentation Transformer Gated attention mechanism Depth separable |
| title | DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network |
| title_full | DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network |
| title_fullStr | DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network |
| title_full_unstemmed | DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network |
| title_short | DSGA-Net: Deeply separable gated transformer and attention strategy for medical image segmentation network |
| title_sort | dsga net deeply separable gated transformer and attention strategy for medical image segmentation network |
| topic | Medical image segmentation Transformer Gated attention mechanism Depth separable |
| url | http://www.sciencedirect.com/science/article/pii/S131915782300099X |
| work_keys_str_mv | AT jundingsun dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork AT jiuqiangzhao dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork AT xiaoshengwu dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork AT chaoshengtang dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork AT shuihuawang dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork AT yudongzhang dsganetdeeplyseparablegatedtransformerandattentionstrategyformedicalimagesegmentationnetwork |