MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image
Purpose: Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal imag...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-02-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023298?viewType=HTML |
| _version_ | 1811162800013180928 |
|---|---|
| author | Jinke Wang Lubiao Zhou Zhongzheng Yuan Haiying Wang Changfa Shi |
| author_facet | Jinke Wang Lubiao Zhou Zhongzheng Yuan Haiying Wang Changfa Shi |
| author_sort | Jinke Wang |
| collection | DOAJ |
| description | Purpose:
Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties.
Method:
This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information.
Results:
We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively.
Conclusions:
Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases. |
| first_indexed | 2024-04-10T06:35:00Z |
| format | Article |
| id | doaj.art-478f2b5e95c643dbbbe7edaac208e46d |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-04-10T06:35:00Z |
| publishDate | 2023-02-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-478f2b5e95c643dbbbe7edaac208e46d2023-03-01T01:16:47ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-02-012046912693110.3934/mbe.2023298MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus imageJinke Wang0Lubiao Zhou1Zhongzheng Yuan 2Haiying Wang3Changfa Shi41. Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China 2. School of Automation, Harbin University of Science and Technology, Harbin 150080, China2. School of Automation, Harbin University of Science and Technology, Harbin 150080, China1. Department of Software Engineering, Harbin University of Science and Technology, Rongcheng 264300, China2. School of Automation, Harbin University of Science and Technology, Harbin 150080, China3. Mobile E-business Collaborative Innovation Center of Hunan Province, Hunan University of Technology and Business, Changsha 410205, ChinaPurpose: Accurate retinal vessel segmentation is of great value in the auxiliary screening of various diseases. However, due to the low contrast between the ends of the branches of the fundus blood vessels and the background, and the variable morphology of the optic disc and cup in the retinal image, the task of high-precision retinal blood vessel segmentation still faces difficulties. Method: This paper proposes a multi-scale integrated context network, MIC-Net, which fully fuses the encoder-decoder features, and extracts multi-scale information. First, a hybrid stride sampling (HSS) block was designed in the encoder to minimize the loss of helpful information caused by the downsampling operation. Second, a dense hybrid dilated convolution (DHDC) was employed in the connection layer. On the premise of preserving feature resolution, it can perceive richer contextual information. Third, a squeeze-and-excitation with residual connections (SERC) was introduced in the decoder to adjust the channel attention adaptively. Finally, we utilized a multi-layer feature fusion mechanism in the skip connection part, which enables the network to consider both low-level details and high-level semantic information. Results: We evaluated the proposed method on three public datasets DRIVE, STARE and CHASE. In the experimental results, the Area under the receiver operating characteristic (ROC) and the accuracy rate (Acc) achieved high performances of 98.62%/97.02%, 98.60%/97.76% and 98.73%/97.38%, respectively. Conclusions: Experimental results show that the proposed method can obtain comparable segmentation performance compared with the state-of-the-art (SOTA) methods. Specifically, the proposed method can effectively reduce the small blood vessel segmentation error, thus proving it a promising tool for auxiliary diagnosis of ophthalmic diseases.https://www.aimspress.com/article/doi/10.3934/mbe.2023298?viewType=HTMLretinal vessel segmentationfundus imagemulti-scaledeep learning |
| spellingShingle | Jinke Wang Lubiao Zhou Zhongzheng Yuan Haiying Wang Changfa Shi MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image Mathematical Biosciences and Engineering retinal vessel segmentation fundus image multi-scale deep learning |
| title | MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image |
| title_full | MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image |
| title_fullStr | MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image |
| title_full_unstemmed | MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image |
| title_short | MIC-Net: multi-scale integrated context network for automatic retinal vessel segmentation in fundus image |
| title_sort | mic net multi scale integrated context network for automatic retinal vessel segmentation in fundus image |
| topic | retinal vessel segmentation fundus image multi-scale deep learning |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023298?viewType=HTML |
| work_keys_str_mv | AT jinkewang micnetmultiscaleintegratedcontextnetworkforautomaticretinalvesselsegmentationinfundusimage AT lubiaozhou micnetmultiscaleintegratedcontextnetworkforautomaticretinalvesselsegmentationinfundusimage AT zhongzhengyuan micnetmultiscaleintegratedcontextnetworkforautomaticretinalvesselsegmentationinfundusimage AT haiyingwang micnetmultiscaleintegratedcontextnetworkforautomaticretinalvesselsegmentationinfundusimage AT changfashi micnetmultiscaleintegratedcontextnetworkforautomaticretinalvesselsegmentationinfundusimage |