Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images
Corneal ulcer is a common leading cause of corneal blindness. It is difficult to accurately segment corneal ulcers due to the following problems: large differences in the pathological shapes between point-flaky and flaky corneal ulcers, blurred boundary, noise interference, and the lack of sufficien...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2021.793377/full |
| _version_ | 1819003783942766592 |
|---|---|
| author | Tingting Wang Meng Wang Weifang Zhu Lianyu Wang Zhongyue Chen Yuanyuan Peng Fei Shi Yi Zhou Chenpu Yao Xinjian Chen Xinjian Chen |
| author_facet | Tingting Wang Meng Wang Weifang Zhu Lianyu Wang Zhongyue Chen Yuanyuan Peng Fei Shi Yi Zhou Chenpu Yao Xinjian Chen Xinjian Chen |
| author_sort | Tingting Wang |
| collection | DOAJ |
| description | Corneal ulcer is a common leading cause of corneal blindness. It is difficult to accurately segment corneal ulcers due to the following problems: large differences in the pathological shapes between point-flaky and flaky corneal ulcers, blurred boundary, noise interference, and the lack of sufficient slit-lamp images with ground truth. To address these problems, in this paper, we proposed a novel semi-supervised multi-scale self-transformer generative adversarial network (Semi-MsST-GAN) that can leverage unlabeled images to improve the performance of corneal ulcer segmentation in fluorescein staining of slit-lamp images. Firstly, to improve the performance of segmenting the corneal ulcer regions with complex pathological features, we proposed a novel multi-scale self-transformer network (MsSTNet) as the MsST-GAN generator, which can guide the model to aggregate the low-level weak semantic features with the high-level strong semantic information and adaptively learn the spatial correlation in feature maps. Then, to further improve the segmentation performance by leveraging unlabeled data, the semi-supervised approach based on the proposed MsST-GAN was explored to solve the problem of the lack of slit-lamp images with corresponding ground truth. The proposed Semi-MsST-GAN was comprehensively evaluated on the public SUSTech-SYSU dataset, which contains 354 labeled and 358 unlabeled fluorescein staining slit-lamp images. The results showed that, compared with other state-of-the-art methods, our proposed method achieves better performance with comparable efficiency. |
| first_indexed | 2024-12-20T23:26:30Z |
| format | Article |
| id | doaj.art-ef48931f70b74f15b7a0454820d6d190 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-20T23:26:30Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-ef48931f70b74f15b7a0454820d6d1902022-12-21T19:23:24ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-01-011510.3389/fnins.2021.793377793377Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp ImagesTingting Wang0Meng Wang1Weifang Zhu2Lianyu Wang3Zhongyue Chen4Yuanyuan Peng5Fei Shi6Yi Zhou7Chenpu Yao8Xinjian Chen9Xinjian Chen10Medical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaMedical Image Processing, Analysis and Visualization (MIPAV) Laboratory, The School of Electronics and Information Engineering, Soochow University, Suzhou, ChinaThe State Key Laboratory of Radiation Medicine and Protection, Soochow University, Suzhou, ChinaCorneal ulcer is a common leading cause of corneal blindness. It is difficult to accurately segment corneal ulcers due to the following problems: large differences in the pathological shapes between point-flaky and flaky corneal ulcers, blurred boundary, noise interference, and the lack of sufficient slit-lamp images with ground truth. To address these problems, in this paper, we proposed a novel semi-supervised multi-scale self-transformer generative adversarial network (Semi-MsST-GAN) that can leverage unlabeled images to improve the performance of corneal ulcer segmentation in fluorescein staining of slit-lamp images. Firstly, to improve the performance of segmenting the corneal ulcer regions with complex pathological features, we proposed a novel multi-scale self-transformer network (MsSTNet) as the MsST-GAN generator, which can guide the model to aggregate the low-level weak semantic features with the high-level strong semantic information and adaptively learn the spatial correlation in feature maps. Then, to further improve the segmentation performance by leveraging unlabeled data, the semi-supervised approach based on the proposed MsST-GAN was explored to solve the problem of the lack of slit-lamp images with corresponding ground truth. The proposed Semi-MsST-GAN was comprehensively evaluated on the public SUSTech-SYSU dataset, which contains 354 labeled and 358 unlabeled fluorescein staining slit-lamp images. The results showed that, compared with other state-of-the-art methods, our proposed method achieves better performance with comparable efficiency.https://www.frontiersin.org/articles/10.3389/fnins.2021.793377/fullcorneal ulcerGANslit-lamp imagesemi-supervisiondeep learning |
| spellingShingle | Tingting Wang Meng Wang Weifang Zhu Lianyu Wang Zhongyue Chen Yuanyuan Peng Fei Shi Yi Zhou Chenpu Yao Xinjian Chen Xinjian Chen Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images Frontiers in Neuroscience corneal ulcer GAN slit-lamp image semi-supervision deep learning |
| title | Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images |
| title_full | Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images |
| title_fullStr | Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images |
| title_full_unstemmed | Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images |
| title_short | Semi-MsST-GAN: A Semi-Supervised Segmentation Method for Corneal Ulcer Segmentation in Slit-Lamp Images |
| title_sort | semi msst gan a semi supervised segmentation method for corneal ulcer segmentation in slit lamp images |
| topic | corneal ulcer GAN slit-lamp image semi-supervision deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.793377/full |
| work_keys_str_mv | AT tingtingwang semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT mengwang semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT weifangzhu semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT lianyuwang semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT zhongyuechen semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT yuanyuanpeng semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT feishi semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT yizhou semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT chenpuyao semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT xinjianchen semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages AT xinjianchen semimsstganasemisupervisedsegmentationmethodforcornealulcersegmentationinslitlampimages |