Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning
Abstract Macular OCT angiography (OCTA) measurements have been reported to be useful for glaucoma diagnostics. However, research on highly myopic glaucoma is lacking, and the diagnostic value of macular OCTA measurements versus OCT parameters remains inconclusive. We aimed to evaluate the diagnostic...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-32164-9 |
| _version_ | 1797853795841998848 |
|---|---|
| author | Yun Jeong Lee Sukkyu Sun Young Kook Kim Jin Wook Jeoung Ki Ho Park |
| author_facet | Yun Jeong Lee Sukkyu Sun Young Kook Kim Jin Wook Jeoung Ki Ho Park |
| author_sort | Yun Jeong Lee |
| collection | DOAJ |
| description | Abstract Macular OCT angiography (OCTA) measurements have been reported to be useful for glaucoma diagnostics. However, research on highly myopic glaucoma is lacking, and the diagnostic value of macular OCTA measurements versus OCT parameters remains inconclusive. We aimed to evaluate the diagnostic ability of the macular microvasculature assessed with OCTA for highly myopic glaucoma and to compare it with that of macular thickness parameters, using deep learning (DL). A DL model was trained, validated and tested using 260 pairs of macular OCTA and OCT images from 260 eyes (203 eyes with highly myopic glaucoma, 57 eyes with healthy high myopia). The DL model achieved an AUC of 0.946 with the OCTA superficial capillary plexus (SCP) images, which was comparable to that with the OCT GCL+ (ganglion cell layer + inner plexiform layer; AUC, 0.982; P = 0.268) or OCT GCL++ (retinal nerve fiber layer + ganglion cell layer + inner plexiform layer) images (AUC, 0.997; P = 0.101), and significantly superior to that with the OCTA deep capillary plexus images (AUC, 0.779; P = 0.028). The DL model with macular OCTA SCP images demonstrated excellent and comparable diagnostic ability to that with macular OCT images in highly myopic glaucoma, which suggests macular OCTA microvasculature could serve as a potential biomarker for glaucoma diagnosis in high myopia. |
| first_indexed | 2024-04-09T19:56:38Z |
| format | Article |
| id | doaj.art-9350823b78f748f4bd6a3ad46b572da3 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T19:56:38Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-9350823b78f748f4bd6a3ad46b572da32023-04-03T05:27:55ZengNature PortfolioScientific Reports2045-23222023-03-0113111010.1038/s41598-023-32164-9Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learningYun Jeong Lee0Sukkyu Sun1Young Kook Kim2Jin Wook Jeoung3Ki Ho Park4Department of Ophthalmology, Seoul National University Hospital, Seoul National University College of MedicineBiomedical Research Institute, Seoul National University HospitalDepartment of Ophthalmology, Seoul National University Hospital, Seoul National University College of MedicineDepartment of Ophthalmology, Seoul National University Hospital, Seoul National University College of MedicineDepartment of Ophthalmology, Seoul National University Hospital, Seoul National University College of MedicineAbstract Macular OCT angiography (OCTA) measurements have been reported to be useful for glaucoma diagnostics. However, research on highly myopic glaucoma is lacking, and the diagnostic value of macular OCTA measurements versus OCT parameters remains inconclusive. We aimed to evaluate the diagnostic ability of the macular microvasculature assessed with OCTA for highly myopic glaucoma and to compare it with that of macular thickness parameters, using deep learning (DL). A DL model was trained, validated and tested using 260 pairs of macular OCTA and OCT images from 260 eyes (203 eyes with highly myopic glaucoma, 57 eyes with healthy high myopia). The DL model achieved an AUC of 0.946 with the OCTA superficial capillary plexus (SCP) images, which was comparable to that with the OCT GCL+ (ganglion cell layer + inner plexiform layer; AUC, 0.982; P = 0.268) or OCT GCL++ (retinal nerve fiber layer + ganglion cell layer + inner plexiform layer) images (AUC, 0.997; P = 0.101), and significantly superior to that with the OCTA deep capillary plexus images (AUC, 0.779; P = 0.028). The DL model with macular OCTA SCP images demonstrated excellent and comparable diagnostic ability to that with macular OCT images in highly myopic glaucoma, which suggests macular OCTA microvasculature could serve as a potential biomarker for glaucoma diagnosis in high myopia.https://doi.org/10.1038/s41598-023-32164-9 |
| spellingShingle | Yun Jeong Lee Sukkyu Sun Young Kook Kim Jin Wook Jeoung Ki Ho Park Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning Scientific Reports |
| title | Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning |
| title_full | Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning |
| title_fullStr | Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning |
| title_full_unstemmed | Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning |
| title_short | Diagnostic ability of macular microvasculature with swept-source OCT angiography for highly myopic glaucoma using deep learning |
| title_sort | diagnostic ability of macular microvasculature with swept source oct angiography for highly myopic glaucoma using deep learning |
| url | https://doi.org/10.1038/s41598-023-32164-9 |
| work_keys_str_mv | AT yunjeonglee diagnosticabilityofmacularmicrovasculaturewithsweptsourceoctangiographyforhighlymyopicglaucomausingdeeplearning AT sukkyusun diagnosticabilityofmacularmicrovasculaturewithsweptsourceoctangiographyforhighlymyopicglaucomausingdeeplearning AT youngkookkim diagnosticabilityofmacularmicrovasculaturewithsweptsourceoctangiographyforhighlymyopicglaucomausingdeeplearning AT jinwookjeoung diagnosticabilityofmacularmicrovasculaturewithsweptsourceoctangiographyforhighlymyopicglaucomausingdeeplearning AT kihopark diagnosticabilityofmacularmicrovasculaturewithsweptsourceoctangiographyforhighlymyopicglaucomausingdeeplearning |