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...

Full description

Saved in:
Bibliographic Details
Main Authors: Je Moon Yoon, Ji Young Lim, Hoon Noh, Seung Wan Nam, Jee-Hyong Lee, Don-Il Ham
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