Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation
Currently, glaucoma has become an important cause of blindness. At present, although glaucoma cannot be cured, early treatment can prevent it from getting worse. A reliable way to detect glaucoma is to segment the optic disc and cup and then measure the cup-to-disc ratio (CDR). Many deep neural netw...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8748 |
| _version_ | 1797464054618390528 |
|---|---|
| author | Fengming Zhang Shuiwang Li Jianzhi Deng |
| author_facet | Fengming Zhang Shuiwang Li Jianzhi Deng |
| author_sort | Fengming Zhang |
| collection | DOAJ |
| description | Currently, glaucoma has become an important cause of blindness. At present, although glaucoma cannot be cured, early treatment can prevent it from getting worse. A reliable way to detect glaucoma is to segment the optic disc and cup and then measure the cup-to-disc ratio (CDR). Many deep neural network models have been developed to autonomously segment the optic disc and the optic cup to help in diagnosis. However, their performance degrades when subjected to domain shift. While many domain-adaptation methods have been exploited to address this problem, they are apt to produce malformed segmentation results. In this study, it is suggested that the segmentation network be adjusted using a constrained formulation that embeds prior knowledge about the shape of the segmentation areas that is domain-invariant. Based on IOSUDA (i.e., Input and Output Space Unsupervised Domain Adaptation), a novel unsupervised joint optic cup-to-disc segmentation framework with shape constraints is proposed, called SCUDA (short for Shape-Constrained Unsupervised Domain Adaptation). A shape constrained loss function is novelly proposed in this paper which utilizes domain-invariant prior knowledge concerning the segmentation region of the joint optic cup–optical disc of fundus images to constrain the segmentation result during network training. In addition, a convolutional triple attention module is designed to improve the segmentation network, which captures cross-dimensional interactions and provides a rich feature representation to improve the segmentation accuracy. Experiments on the RIM-ONE_r3 and Drishti-GS datasets demonstrate that the algorithm outperforms existing approaches for segmenting optic discs and cups. |
| first_indexed | 2024-03-09T18:01:31Z |
| format | Article |
| id | doaj.art-e668d21359144a309aaf3e87c768798c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:01:31Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e668d21359144a309aaf3e87c768798c2023-11-24T09:55:09ZengMDPI AGSensors1424-82202022-11-012222874810.3390/s22228748Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup SegmentationFengming Zhang0Shuiwang Li1Jianzhi Deng2Guangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaGuangxi Key Laboratory of Embedded Technology and Intelligent Information Processing, College of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaCurrently, glaucoma has become an important cause of blindness. At present, although glaucoma cannot be cured, early treatment can prevent it from getting worse. A reliable way to detect glaucoma is to segment the optic disc and cup and then measure the cup-to-disc ratio (CDR). Many deep neural network models have been developed to autonomously segment the optic disc and the optic cup to help in diagnosis. However, their performance degrades when subjected to domain shift. While many domain-adaptation methods have been exploited to address this problem, they are apt to produce malformed segmentation results. In this study, it is suggested that the segmentation network be adjusted using a constrained formulation that embeds prior knowledge about the shape of the segmentation areas that is domain-invariant. Based on IOSUDA (i.e., Input and Output Space Unsupervised Domain Adaptation), a novel unsupervised joint optic cup-to-disc segmentation framework with shape constraints is proposed, called SCUDA (short for Shape-Constrained Unsupervised Domain Adaptation). A shape constrained loss function is novelly proposed in this paper which utilizes domain-invariant prior knowledge concerning the segmentation region of the joint optic cup–optical disc of fundus images to constrain the segmentation result during network training. In addition, a convolutional triple attention module is designed to improve the segmentation network, which captures cross-dimensional interactions and provides a rich feature representation to improve the segmentation accuracy. Experiments on the RIM-ONE_r3 and Drishti-GS datasets demonstrate that the algorithm outperforms existing approaches for segmenting optic discs and cups.https://www.mdpi.com/1424-8220/22/22/8748unsupervisedshape constraintattention |
| spellingShingle | Fengming Zhang Shuiwang Li Jianzhi Deng Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation Sensors unsupervised shape constraint attention |
| title | Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation |
| title_full | Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation |
| title_fullStr | Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation |
| title_full_unstemmed | Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation |
| title_short | Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation |
| title_sort | unsupervised domain adaptation with shape constraint and triple attention for joint optic disc and cup segmentation |
| topic | unsupervised shape constraint attention |
| url | https://www.mdpi.com/1424-8220/22/22/8748 |
| work_keys_str_mv | AT fengmingzhang unsuperviseddomainadaptationwithshapeconstraintandtripleattentionforjointopticdiscandcupsegmentation AT shuiwangli unsuperviseddomainadaptationwithshapeconstraintandtripleattentionforjointopticdiscandcupsegmentation AT jianzhideng unsuperviseddomainadaptationwithshapeconstraintandtripleattentionforjointopticdiscandcupsegmentation |