Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography
PurposeTo characterize the corneal and epithelial thickness at different stages of keratoconus (KC), using a deep learning based corneal segmentation algorithm for anterior segment optical coherence tomography (AS-OCT).MethodsAn AS-OCT dataset was constructed in this study with 1,430 images from 715...
| 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.2021.804273/full |
| _version_ | 1828137186529116160 |
|---|---|
| author | Yanling Dong Yanling Dong Dongfang Li Dongfang Li Zhen Guo Zhen Guo Yang Liu Ping Lin Ping Lin Bin Lv Chuanfeng Lv Guotong Xie Guotong Xie Guotong Xie Lixin Xie Lixin Xie |
| author_facet | Yanling Dong Yanling Dong Dongfang Li Dongfang Li Zhen Guo Zhen Guo Yang Liu Ping Lin Ping Lin Bin Lv Chuanfeng Lv Guotong Xie Guotong Xie Guotong Xie Lixin Xie Lixin Xie |
| author_sort | Yanling Dong |
| collection | DOAJ |
| description | PurposeTo characterize the corneal and epithelial thickness at different stages of keratoconus (KC), using a deep learning based corneal segmentation algorithm for anterior segment optical coherence tomography (AS-OCT).MethodsAn AS-OCT dataset was constructed in this study with 1,430 images from 715 eyes, which included 118 normal eyes, 134 mild KC, 239 moderate KC, 153 severe KC, and 71 scarring KC. A deep learning based corneal segmentation algorithm was applied to isolate the epithelial and corneal tissues from the background. Based on the segmentation results, the thickness of epithelial and corneal tissues was automatically measured in the center 6 mm area. One-way ANOVA and linear regression were performed in 20 equally divided zones to explore the trend of the thickness changes at different locations with the KC progression. The 95% confidence intervals (CI) of epithelial thickness and corneal thickness in a specific zone were calculated to reveal the difference of thickness distribution among different groups.ResultsOur data showed that the deep learning based corneal segmentation algorithm can achieve accurate tissue segmentation and the error range of measured thickness was less than 4 μm between our method and the results from clinical experts, which is approximately one image pixel. Statistical analyses revealed significant corneal thickness differences in all the divided zones (P < 0.05). The entire corneal thickness grew gradually thinner with the progression of the KC, and their trends were more pronounced around the pupil center with a slight shift toward the temporal and inferior side. Especially the epithelial thicknesses were thinner gradually from a normal eye to severe KC. Due to the formation of the corneal scarring, epithelial thickness had irregular fluctuations in the scarring KC.ConclusionOur study demonstrates that our deep learning method based on AS-OCT images could accurately delineate the corneal tissues and further successfully characterize the epithelial and corneal thickness changes at different stages of the KC progression. |
| first_indexed | 2024-04-11T18:14:37Z |
| format | Article |
| id | doaj.art-ca74e41bb01a4759b9d90ce7cab70f92 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-04-11T18:14:37Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-ca74e41bb01a4759b9d90ce7cab70f922022-12-22T04:09:58ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2022-01-011510.3389/fnins.2021.804273804273Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence TomographyYanling Dong0Yanling Dong1Dongfang Li2Dongfang Li3Zhen Guo4Zhen Guo5Yang Liu6Ping Lin7Ping Lin8Bin Lv9Chuanfeng Lv10Guotong Xie11Guotong Xie12Guotong Xie13Lixin Xie14Lixin Xie15Qingdao Eye Hospital of Shandong First Medical University, Qingdao, ChinaState Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, ChinaQingdao Eye Hospital of Shandong First Medical University, Qingdao, ChinaState Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, ChinaQingdao Eye Hospital of Shandong First Medical University, Qingdao, ChinaState Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, ChinaPing An Technology (Shenzhen) Co. Ltd., Shenzhen, ChinaQingdao Eye Hospital of Shandong First Medical University, Qingdao, ChinaState Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, ChinaPing An Technology (Shenzhen) Co. Ltd., Shenzhen, ChinaPing An Technology (Shenzhen) Co. Ltd., Shenzhen, ChinaPing An Technology (Shenzhen) Co. Ltd., Shenzhen, ChinaPing An Health Cloud Co. Ltd., Shenzhen, ChinaPing An International Smart City Technology Co. Ltd., Shenzhen, ChinaQingdao Eye Hospital of Shandong First Medical University, Qingdao, ChinaState Key Laboratory Cultivation Base, Shandong Provincial Key Laboratory of Ophthalmology, Eye Institute of Shandong First Medical University, Qingdao, ChinaPurposeTo characterize the corneal and epithelial thickness at different stages of keratoconus (KC), using a deep learning based corneal segmentation algorithm for anterior segment optical coherence tomography (AS-OCT).MethodsAn AS-OCT dataset was constructed in this study with 1,430 images from 715 eyes, which included 118 normal eyes, 134 mild KC, 239 moderate KC, 153 severe KC, and 71 scarring KC. A deep learning based corneal segmentation algorithm was applied to isolate the epithelial and corneal tissues from the background. Based on the segmentation results, the thickness of epithelial and corneal tissues was automatically measured in the center 6 mm area. One-way ANOVA and linear regression were performed in 20 equally divided zones to explore the trend of the thickness changes at different locations with the KC progression. The 95% confidence intervals (CI) of epithelial thickness and corneal thickness in a specific zone were calculated to reveal the difference of thickness distribution among different groups.ResultsOur data showed that the deep learning based corneal segmentation algorithm can achieve accurate tissue segmentation and the error range of measured thickness was less than 4 μm between our method and the results from clinical experts, which is approximately one image pixel. Statistical analyses revealed significant corneal thickness differences in all the divided zones (P < 0.05). The entire corneal thickness grew gradually thinner with the progression of the KC, and their trends were more pronounced around the pupil center with a slight shift toward the temporal and inferior side. Especially the epithelial thicknesses were thinner gradually from a normal eye to severe KC. Due to the formation of the corneal scarring, epithelial thickness had irregular fluctuations in the scarring KC.ConclusionOur study demonstrates that our deep learning method based on AS-OCT images could accurately delineate the corneal tissues and further successfully characterize the epithelial and corneal thickness changes at different stages of the KC progression.https://www.frontiersin.org/articles/10.3389/fnins.2021.804273/fullkeratoconuscorneal thicknessanterior segment optical coherence tomographydeep learningsegmentation |
| spellingShingle | Yanling Dong Yanling Dong Dongfang Li Dongfang Li Zhen Guo Zhen Guo Yang Liu Ping Lin Ping Lin Bin Lv Chuanfeng Lv Guotong Xie Guotong Xie Guotong Xie Lixin Xie Lixin Xie Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography Frontiers in Neuroscience keratoconus corneal thickness anterior segment optical coherence tomography deep learning segmentation |
| title | Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography |
| title_full | Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography |
| title_fullStr | Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography |
| title_full_unstemmed | Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography |
| title_short | Dissecting the Profile of Corneal Thickness With Keratoconus Progression Based on Anterior Segment Optical Coherence Tomography |
| title_sort | dissecting the profile of corneal thickness with keratoconus progression based on anterior segment optical coherence tomography |
| topic | keratoconus corneal thickness anterior segment optical coherence tomography deep learning segmentation |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2021.804273/full |
| work_keys_str_mv | AT yanlingdong dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT yanlingdong dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT dongfangli dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT dongfangli dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT zhenguo dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT zhenguo dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT yangliu dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT pinglin dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT pinglin dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT binlv dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT chuanfenglv dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT guotongxie dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT guotongxie dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT guotongxie dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT lixinxie dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography AT lixinxie dissectingtheprofileofcornealthicknesswithkeratoconusprogressionbasedonanteriorsegmentopticalcoherencetomography |