Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images
Abstract Background This study aims to develop a deep learning-based algorithm dedicated to the automated classification of choroidal layers in en face swept-source optical coherence tomography (SS-OCT) images of the eye. Methods A cohort of 117 healthy subjects (117 eyes), underwent SS-OCT volume s...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | BMC Ophthalmology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12886-025-04170-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849766582419456000 |
|---|---|
| author | Je Moon Yoon Ji Young Lim Hoon Noh Seung Wan Nam Jee-Hyong Lee Don-Il Ham |
| author_facet | Je Moon Yoon Ji Young Lim Hoon Noh Seung Wan Nam Jee-Hyong Lee Don-Il Ham |
| author_sort | Je Moon Yoon |
| collection | DOAJ |
| description | Abstract Background This study aims to develop a deep learning-based algorithm dedicated to the automated classification of choroidal layers in en face swept-source optical coherence tomography (SS-OCT) images of the eye. Methods A cohort of 117 healthy subjects (117 eyes), underwent SS-OCT volume scans covering a 12 × 9 mm range. En face SS-OCT images of the choroid were acquired at 2.6 μm intervals from Bruch’s membrane to the chorioscleral border. The images were classified into 5 layers using landmarks, such as the start of the choriocapillaris, the start of Sattler’s layer, and the start and end of Haller’s layer. The dataset consisted of 16,025 en face SS-OCT images, and model performance was evaluated using 5-fold cross validation. Results We developed the deep learning system based on ResNet, incorporating boundary-enhancing undersampling and subclass ensemble techniques. The developed algorithm successfully classified choroidal layers with a balanced accuracy of 84.30% and 92.61% within error ranges of 0 μm and 5.2 μm, respectively. Conclusions Automated stratification of choroidal layers from en face SS-OCT images can be achieved accurately through deep learning. |
| format | Article |
| id | doaj-art-68f8328cfa7e4fe2919f90694e744d6c |
| institution | DOAJ |
| issn | 1471-2415 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Ophthalmology |
| spelling | doaj-art-68f8328cfa7e4fe2919f90694e744d6c2025-08-20T03:04:31ZengBMCBMC Ophthalmology1471-24152025-07-0125111110.1186/s12886-025-04170-0Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography imagesJe Moon Yoon0Ji Young Lim1Hoon Noh2Seung Wan Nam3Jee-Hyong Lee4Don-Il Ham5Department of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of MedicineDepartment of Artificial Intelligent, Sungkyunkwan UniversityHangil Eye HospitalGood Morning Light Eye ClinicDepartment of Artificial Intelligent, Sungkyunkwan UniversityDepartment of Ophthalmology, Samsung Medical Center, Sungkyunkwan University School of MedicineAbstract Background This study aims to develop a deep learning-based algorithm dedicated to the automated classification of choroidal layers in en face swept-source optical coherence tomography (SS-OCT) images of the eye. Methods A cohort of 117 healthy subjects (117 eyes), underwent SS-OCT volume scans covering a 12 × 9 mm range. En face SS-OCT images of the choroid were acquired at 2.6 μm intervals from Bruch’s membrane to the chorioscleral border. The images were classified into 5 layers using landmarks, such as the start of the choriocapillaris, the start of Sattler’s layer, and the start and end of Haller’s layer. The dataset consisted of 16,025 en face SS-OCT images, and model performance was evaluated using 5-fold cross validation. Results We developed the deep learning system based on ResNet, incorporating boundary-enhancing undersampling and subclass ensemble techniques. The developed algorithm successfully classified choroidal layers with a balanced accuracy of 84.30% and 92.61% within error ranges of 0 μm and 5.2 μm, respectively. Conclusions Automated stratification of choroidal layers from en face SS-OCT images can be achieved accurately through deep learning.https://doi.org/10.1186/s12886-025-04170-0Deep learningArtificial intelligenceChoroidSwept-source optical coherence tomography |
| spellingShingle | Je Moon Yoon Ji Young Lim Hoon Noh Seung Wan Nam Jee-Hyong Lee Don-Il Ham Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images BMC Ophthalmology Deep learning Artificial intelligence Choroid Swept-source optical coherence tomography |
| title | Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images |
| title_full | Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images |
| title_fullStr | Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images |
| title_full_unstemmed | Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images |
| title_short | Deep learning-based automated classification of choroidal layers in en face swept-source optical coherence tomography images |
| title_sort | deep learning based automated classification of choroidal layers in en face swept source optical coherence tomography images |
| topic | Deep learning Artificial intelligence Choroid Swept-source optical coherence tomography |
| url | https://doi.org/10.1186/s12886-025-04170-0 |
| work_keys_str_mv | AT jemoonyoon deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages AT jiyounglim deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages AT hoonnoh deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages AT seungwannam deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages AT jeehyonglee deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages AT donilham deeplearningbasedautomatedclassificationofchoroidallayersinenfacesweptsourceopticalcoherencetomographyimages |