MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation
Accurate medical imaging segmentation of the retinal fundus vasculature is essential to assist physicians in diagnosis and treatment. In recent years, convolutional neural networks (CNN) are widely used to classify retinal blood vessel pixels for retinal blood vessel segmentation tasks. However, the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/7/1357 |
| _version_ | 1797415434838867968 |
|---|---|
| author | Yun Jiang Jing Liang Tongtong Cheng Yuan Zhang Xin Lin Jinkun Dong |
| author_facet | Yun Jiang Jing Liang Tongtong Cheng Yuan Zhang Xin Lin Jinkun Dong |
| author_sort | Yun Jiang |
| collection | DOAJ |
| description | Accurate medical imaging segmentation of the retinal fundus vasculature is essential to assist physicians in diagnosis and treatment. In recent years, convolutional neural networks (CNN) are widely used to classify retinal blood vessel pixels for retinal blood vessel segmentation tasks. However, the convolutional block receptive field is limited, simple multiple superpositions tend to cause information loss, and there are limitations in feature extraction as well as vessel segmentation. To address these problems, this paper proposes a new retinal vessel segmentation network based on U-Net, which is called multi-scale cross-position attention network (MCPANet). MCPANet uses multiple scales of input to compensate for image detail information and applies to skip connections between encoding blocks and decoding blocks to ensure information transfer while effectively reducing noise. We propose a cross-position attention module to link the positional relationships between pixels and obtain global contextual information, which enables the model to segment not only the fine capillaries but also clear vessel edges. At the same time, multiple scale pooling operations are used to expand the receptive field and enhance feature extraction. It further reduces pixel classification errors and eases the segmentation difficulty caused by the asymmetry of fundus blood vessel distribution. We trained and validated our proposed model on three publicly available datasets, DRIVE, CHASE, and STARE, which obtained segmentation accuracy of 97.05%, 97.58%, and 97.68%, and Dice of 83.15%, 81.48%, and 85.05%, respectively. The results demonstrate that the proposed method in this paper achieves better results in terms of performance and segmentation results when compared with existing methods. |
| first_indexed | 2024-03-09T05:48:36Z |
| format | Article |
| id | doaj.art-e3bbd384ebd94f10b0f62c038b9ed6ef |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T05:48:36Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-e3bbd384ebd94f10b0f62c038b9ed6ef2023-12-03T12:19:32ZengMDPI AGSymmetry2073-89942022-07-01147135710.3390/sym14071357MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image SegmentationYun Jiang0Jing Liang1Tongtong Cheng2Yuan Zhang3Xin Lin4Jinkun Dong5College of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaCollege of Computer Science and Engineering, Northwest Normal University, Lanzhou 730070, ChinaAccurate medical imaging segmentation of the retinal fundus vasculature is essential to assist physicians in diagnosis and treatment. In recent years, convolutional neural networks (CNN) are widely used to classify retinal blood vessel pixels for retinal blood vessel segmentation tasks. However, the convolutional block receptive field is limited, simple multiple superpositions tend to cause information loss, and there are limitations in feature extraction as well as vessel segmentation. To address these problems, this paper proposes a new retinal vessel segmentation network based on U-Net, which is called multi-scale cross-position attention network (MCPANet). MCPANet uses multiple scales of input to compensate for image detail information and applies to skip connections between encoding blocks and decoding blocks to ensure information transfer while effectively reducing noise. We propose a cross-position attention module to link the positional relationships between pixels and obtain global contextual information, which enables the model to segment not only the fine capillaries but also clear vessel edges. At the same time, multiple scale pooling operations are used to expand the receptive field and enhance feature extraction. It further reduces pixel classification errors and eases the segmentation difficulty caused by the asymmetry of fundus blood vessel distribution. We trained and validated our proposed model on three publicly available datasets, DRIVE, CHASE, and STARE, which obtained segmentation accuracy of 97.05%, 97.58%, and 97.68%, and Dice of 83.15%, 81.48%, and 85.05%, respectively. The results demonstrate that the proposed method in this paper achieves better results in terms of performance and segmentation results when compared with existing methods.https://www.mdpi.com/2073-8994/14/7/1357retinal vessel segmentationconvolutional neural networkattention mechanism |
| spellingShingle | Yun Jiang Jing Liang Tongtong Cheng Yuan Zhang Xin Lin Jinkun Dong MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation Symmetry retinal vessel segmentation convolutional neural network attention mechanism |
| title | MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation |
| title_full | MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation |
| title_fullStr | MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation |
| title_full_unstemmed | MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation |
| title_short | MCPANet: Multiscale Cross-Position Attention Network for Retinal Vessel Image Segmentation |
| title_sort | mcpanet multiscale cross position attention network for retinal vessel image segmentation |
| topic | retinal vessel segmentation convolutional neural network attention mechanism |
| url | https://www.mdpi.com/2073-8994/14/7/1357 |
| work_keys_str_mv | AT yunjiang mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation AT jingliang mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation AT tongtongcheng mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation AT yuanzhang mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation AT xinlin mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation AT jinkundong mcpanetmultiscalecrosspositionattentionnetworkforretinalvesselimagesegmentation |