Research on segmentation of pterygium lesions based on convolutional neural networks
AIM: To study the precise segmentation of pterygium lesions using the convolutional neural networks from artificial intelligence.METHODS: The network structure of Phase-fusion PSPNet for the segmentation of pterygium lesions is proposed based on the PSPNet model structure. In our network, the up-sam...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Press of International Journal of Ophthalmology (IJO PRESS)
2022-06-01
|
| Series: | Guoji Yanke Zazhi |
| Subjects: | |
| Online Access: | http://ies.ijo.cn/cn_publish/2022/6/202206026.pdf |
| _version_ | 1818239754114695168 |
|---|---|
| author | Shao-Jun Zhu Xin-Wen Fang Bo Zheng Mao-Nian Wu Wei-Hua Yang |
| author_facet | Shao-Jun Zhu Xin-Wen Fang Bo Zheng Mao-Nian Wu Wei-Hua Yang |
| author_sort | Shao-Jun Zhu |
| collection | DOAJ |
| description | AIM: To study the precise segmentation of pterygium lesions using the convolutional neural networks from artificial intelligence.METHODS: The network structure of Phase-fusion PSPNet for the segmentation of pterygium lesions is proposed based on the PSPNet model structure. In our network, the up-sampling module is connected behind the pyramid pooling module, which gradually increase the sampling based on the principle of phased increase. Therefore, the information loss is reduced, it is suitable for segmentation tasks with fuzzy edges. The experiments conducted on the dataset provided by the Affiliated Eye Hospital of Nanjing Medical University, which includes 517 ocular surface photographic images of pterygium were divided into training set(330 images), validation set(37 images)and test set(150 images), which the training set and the validation set images are used for training, and the test set images are only used for testing. Comparing results of intelligent segmentation and expert annotation of pterygium lesions.RESULTS: Phase-fusion PSPNet network structure for pterygium mean intersection over union(MIOU)and mean average precision(MPA)were 86.31% and 91.91%, respectively, and pterygium intersection over union(IOU)and average precision(PA)were 77.64% and 86.10%, respectively.CONCLUSION: Convolutional neural networks can segment pterygium lesions with high precision, which is helpful to provide an important reference for doctors' further diagnosis of disease and surgical recommendations, and can also visualize the pterygium intelligent diagnosis. |
| first_indexed | 2024-12-12T13:02:34Z |
| format | Article |
| id | doaj.art-f270eee0476f43719c835b2e78c5c838 |
| institution | Directory Open Access Journal |
| issn | 1672-5123 |
| language | English |
| last_indexed | 2024-12-12T13:02:34Z |
| publishDate | 2022-06-01 |
| publisher | Press of International Journal of Ophthalmology (IJO PRESS) |
| record_format | Article |
| series | Guoji Yanke Zazhi |
| spelling | doaj.art-f270eee0476f43719c835b2e78c5c8382022-12-22T00:23:46ZengPress of International Journal of Ophthalmology (IJO PRESS)Guoji Yanke Zazhi1672-51232022-06-012261016101910.3980/j.issn.1672-5123.2022.6.26202206026Research on segmentation of pterygium lesions based on convolutional neural networksShao-Jun Zhu0Xin-Wen Fang1Bo Zheng2Mao-Nian Wu3Wei-Hua Yang4School of Information Engineering, Huzhou University, Huzhou 313000, Zhejiang Province, China; Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou 313000, Zhejiang Province, ChinaSchool of Information Engineering, Huzhou University, Huzhou 313000, Zhejiang Province, China; Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou 313000, Zhejiang Province, ChinaSchool of Information Engineering, Huzhou University, Huzhou 313000, Zhejiang Province, China; Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou 313000, Zhejiang Province, ChinaSchool of Information Engineering, Huzhou University, Huzhou 313000, Zhejiang Province, China; Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources, Huzhou University, Huzhou 313000, Zhejiang Province, ChinaBig Data Laboratory of Ophthalmic Artificial Intelligence, the Affiliated Eye Hospital of Nanjing Medical University, Nanjing 210029, Jiangsu Province, ChinaAIM: To study the precise segmentation of pterygium lesions using the convolutional neural networks from artificial intelligence.METHODS: The network structure of Phase-fusion PSPNet for the segmentation of pterygium lesions is proposed based on the PSPNet model structure. In our network, the up-sampling module is connected behind the pyramid pooling module, which gradually increase the sampling based on the principle of phased increase. Therefore, the information loss is reduced, it is suitable for segmentation tasks with fuzzy edges. The experiments conducted on the dataset provided by the Affiliated Eye Hospital of Nanjing Medical University, which includes 517 ocular surface photographic images of pterygium were divided into training set(330 images), validation set(37 images)and test set(150 images), which the training set and the validation set images are used for training, and the test set images are only used for testing. Comparing results of intelligent segmentation and expert annotation of pterygium lesions.RESULTS: Phase-fusion PSPNet network structure for pterygium mean intersection over union(MIOU)and mean average precision(MPA)were 86.31% and 91.91%, respectively, and pterygium intersection over union(IOU)and average precision(PA)were 77.64% and 86.10%, respectively.CONCLUSION: Convolutional neural networks can segment pterygium lesions with high precision, which is helpful to provide an important reference for doctors' further diagnosis of disease and surgical recommendations, and can also visualize the pterygium intelligent diagnosis.http://ies.ijo.cn/cn_publish/2022/6/202206026.pdfpterygiumimage segmentationdeep learningconvolutional neural networkspspnet |
| spellingShingle | Shao-Jun Zhu Xin-Wen Fang Bo Zheng Mao-Nian Wu Wei-Hua Yang Research on segmentation of pterygium lesions based on convolutional neural networks Guoji Yanke Zazhi pterygium image segmentation deep learning convolutional neural networks pspnet |
| title | Research on segmentation of pterygium lesions based on convolutional neural networks |
| title_full | Research on segmentation of pterygium lesions based on convolutional neural networks |
| title_fullStr | Research on segmentation of pterygium lesions based on convolutional neural networks |
| title_full_unstemmed | Research on segmentation of pterygium lesions based on convolutional neural networks |
| title_short | Research on segmentation of pterygium lesions based on convolutional neural networks |
| title_sort | research on segmentation of pterygium lesions based on convolutional neural networks |
| topic | pterygium image segmentation deep learning convolutional neural networks pspnet |
| url | http://ies.ijo.cn/cn_publish/2022/6/202206026.pdf |
| work_keys_str_mv | AT shaojunzhu researchonsegmentationofpterygiumlesionsbasedonconvolutionalneuralnetworks AT xinwenfang researchonsegmentationofpterygiumlesionsbasedonconvolutionalneuralnetworks AT bozheng researchonsegmentationofpterygiumlesionsbasedonconvolutionalneuralnetworks AT maonianwu researchonsegmentationofpterygiumlesionsbasedonconvolutionalneuralnetworks AT weihuayang researchonsegmentationofpterygiumlesionsbasedonconvolutionalneuralnetworks |