Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network
Due to the limitations of traditional retinal blood vessel segmentation algorithms in feature extraction, vessel breakage often occurs at the end. To address this issue, a retinal vessel segmentation algorithm based on a modified U-shaped network is proposed in this paper. This algorithm can extract...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/465 |
| _version_ | 1827384839443054592 |
|---|---|
| author | Xialan He Ting Wang Wankou Yang |
| author_facet | Xialan He Ting Wang Wankou Yang |
| author_sort | Xialan He |
| collection | DOAJ |
| description | Due to the limitations of traditional retinal blood vessel segmentation algorithms in feature extraction, vessel breakage often occurs at the end. To address this issue, a retinal vessel segmentation algorithm based on a modified U-shaped network is proposed in this paper. This algorithm can extract multi-scale vascular features and perform segmentation in an end-to-end manner. First, in order to improve the low contrast of the original image, pre-processing methods are employed. Second, a multi-scale residual convolution module is employed to extract image features of different granularities, while residual learning improves feature utilization efficiency and reduces information loss. In addition, a selective kernel unit is incorporated into the skip connections to obtain multi-scale features with varying receptive field sizes achieved through soft attention. Subsequently, to further extract vascular features and improve processing speed, a residual attention module is constructed at the decoder stage. Finally, a weighted joint loss function is implemented to address the imbalance between positive and negative samples. The experimental results on the DRIVE, STARE, and CHASE_DB1 datasets demonstrate that MU-Net exhibits better sensitivity and a higher Matthew’s correlation coefficient (0.8197, 0.8051; STARE: 0.8264, 0.7987; CHASE_DB1: 0.8313, 0.7960) compared to several state-of-the-art methods. |
| first_indexed | 2024-03-08T15:11:04Z |
| format | Article |
| id | doaj.art-3f0aab944db34da4a013ad449a2066b8 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:04Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-3f0aab944db34da4a013ad449a2066b82024-01-10T14:52:14ZengMDPI AGApplied Sciences2076-34172024-01-0114146510.3390/app14010465Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped NetworkXialan He0Ting Wang1Wankou Yang2College of Information Science and Technology & College of Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Information Science and Technology & College of Artificial Intelligence, Nanjing Forestry University, Nanjing 210037, ChinaCollege of Automation, Southeast University, Nanjing 210096, ChinaDue to the limitations of traditional retinal blood vessel segmentation algorithms in feature extraction, vessel breakage often occurs at the end. To address this issue, a retinal vessel segmentation algorithm based on a modified U-shaped network is proposed in this paper. This algorithm can extract multi-scale vascular features and perform segmentation in an end-to-end manner. First, in order to improve the low contrast of the original image, pre-processing methods are employed. Second, a multi-scale residual convolution module is employed to extract image features of different granularities, while residual learning improves feature utilization efficiency and reduces information loss. In addition, a selective kernel unit is incorporated into the skip connections to obtain multi-scale features with varying receptive field sizes achieved through soft attention. Subsequently, to further extract vascular features and improve processing speed, a residual attention module is constructed at the decoder stage. Finally, a weighted joint loss function is implemented to address the imbalance between positive and negative samples. The experimental results on the DRIVE, STARE, and CHASE_DB1 datasets demonstrate that MU-Net exhibits better sensitivity and a higher Matthew’s correlation coefficient (0.8197, 0.8051; STARE: 0.8264, 0.7987; CHASE_DB1: 0.8313, 0.7960) compared to several state-of-the-art methods.https://www.mdpi.com/2076-3417/14/1/465deep learningretinal vessel segmentationmulti-scale informationselective kernelattention mechanisms |
| spellingShingle | Xialan He Ting Wang Wankou Yang Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network Applied Sciences deep learning retinal vessel segmentation multi-scale information selective kernel attention mechanisms |
| title | Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network |
| title_full | Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network |
| title_fullStr | Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network |
| title_full_unstemmed | Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network |
| title_short | Research on Retinal Vessel Segmentation Algorithm Based on a Modified U-Shaped Network |
| title_sort | research on retinal vessel segmentation algorithm based on a modified u shaped network |
| topic | deep learning retinal vessel segmentation multi-scale information selective kernel attention mechanisms |
| url | https://www.mdpi.com/2076-3417/14/1/465 |
| work_keys_str_mv | AT xialanhe researchonretinalvesselsegmentationalgorithmbasedonamodifiedushapednetwork AT tingwang researchonretinalvesselsegmentationalgorithmbasedonamodifiedushapednetwork AT wankouyang researchonretinalvesselsegmentationalgorithmbasedonamodifiedushapednetwork |