Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model

Abstract A segmentation-free 3D Convolutional Neural Network (3DCNN) model was adopted to estimate Visual Field (VF) in glaucoma cases using Optical Coherence Tomography (OCT) images. This study, conducted at a university hospital, included 6335 participants (12,325 eyes). Two models were trained, o...

Full description

Saved in:
Bibliographic Details
Main Authors: Makoto Koyama, Yuta Ueno, Yoshikazu Ito, Tetsuro Oshika, Masaki Tanito
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-98511-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181164259606528
author Makoto Koyama
Yuta Ueno
Yoshikazu Ito
Tetsuro Oshika
Masaki Tanito
author_facet Makoto Koyama
Yuta Ueno
Yoshikazu Ito
Tetsuro Oshika
Masaki Tanito
author_sort Makoto Koyama
collection DOAJ
description Abstract A segmentation-free 3D Convolutional Neural Network (3DCNN) model was adopted to estimate Visual Field (VF) in glaucoma cases using Optical Coherence Tomography (OCT) images. This study, conducted at a university hospital, included 6335 participants (12,325 eyes). Two models were trained, one on the Glaucoma-Specific Training Group (GTG) and one on the Comprehensive Training Group (CTG) that included various ocular conditions without manual preselection. The CTG showed significantly better performance than the GTG in estimating VF thresholds and Mean Deviation (MD) for both Humphrey Field Analyzer (HFA) 24-2 and HFA10-2 test patterns (p < 0.001). Strong correlations were observed between the estimated and actual VF thresholds for HFA24-2 (Pearson’s r: 0.878) and HFA10-2 (r: 0.903), as well as MD for HFA24-2 (r: 0.911) and HFA10-2 (r: 0.944) in the CTG. The CTG demonstrated lower estimation errors than the GTG and smaller errors in severe cases. The model’s performance remained relatively stable even in advanced glaucoma cases. The model’s ability to learn from a comprehensive dataset without human annotation highlights its potential for large-scale training in the future, potentially improving glaucoma assessment and monitoring in clinical practice. Further validation in external datasets and exploration in different clinical settings are warranted.
format Article
id doaj-art-d1ea22e9146f4ab19006a1f1c51eefbb
institution OA Journals
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d1ea22e9146f4ab19006a1f1c51eefbb2025-08-20T02:17:57ZengNature PortfolioScientific Reports2045-23222025-04-0115111110.1038/s41598-025-98511-0Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network modelMakoto Koyama0Yuta Ueno1Yoshikazu Ito2Tetsuro Oshika3Masaki Tanito4Minamikoyasu Eye ClinicIto Eye ClinicIto Eye ClinicDepartment of Ophthalmology, Faculty of Medicine, University of TsukubaDepartment of Ophthalmology, Shimane University Faculty of MedicineAbstract A segmentation-free 3D Convolutional Neural Network (3DCNN) model was adopted to estimate Visual Field (VF) in glaucoma cases using Optical Coherence Tomography (OCT) images. This study, conducted at a university hospital, included 6335 participants (12,325 eyes). Two models were trained, one on the Glaucoma-Specific Training Group (GTG) and one on the Comprehensive Training Group (CTG) that included various ocular conditions without manual preselection. The CTG showed significantly better performance than the GTG in estimating VF thresholds and Mean Deviation (MD) for both Humphrey Field Analyzer (HFA) 24-2 and HFA10-2 test patterns (p < 0.001). Strong correlations were observed between the estimated and actual VF thresholds for HFA24-2 (Pearson’s r: 0.878) and HFA10-2 (r: 0.903), as well as MD for HFA24-2 (r: 0.911) and HFA10-2 (r: 0.944) in the CTG. The CTG demonstrated lower estimation errors than the GTG and smaller errors in severe cases. The model’s performance remained relatively stable even in advanced glaucoma cases. The model’s ability to learn from a comprehensive dataset without human annotation highlights its potential for large-scale training in the future, potentially improving glaucoma assessment and monitoring in clinical practice. Further validation in external datasets and exploration in different clinical settings are warranted.https://doi.org/10.1038/s41598-025-98511-0
spellingShingle Makoto Koyama
Yuta Ueno
Yoshikazu Ito
Tetsuro Oshika
Masaki Tanito
Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
Scientific Reports
title Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
title_full Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
title_fullStr Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
title_full_unstemmed Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
title_short Automated learning of glaucomatous visual fields from OCT images using a comprehensive, segmentation-free 3D convolutional neural network model
title_sort automated learning of glaucomatous visual fields from oct images using a comprehensive segmentation free 3d convolutional neural network model
url https://doi.org/10.1038/s41598-025-98511-0
work_keys_str_mv AT makotokoyama automatedlearningofglaucomatousvisualfieldsfromoctimagesusingacomprehensivesegmentationfree3dconvolutionalneuralnetworkmodel
AT yutaueno automatedlearningofglaucomatousvisualfieldsfromoctimagesusingacomprehensivesegmentationfree3dconvolutionalneuralnetworkmodel
AT yoshikazuito automatedlearningofglaucomatousvisualfieldsfromoctimagesusingacomprehensivesegmentationfree3dconvolutionalneuralnetworkmodel
AT tetsurooshika automatedlearningofglaucomatousvisualfieldsfromoctimagesusingacomprehensivesegmentationfree3dconvolutionalneuralnetworkmodel
AT masakitanito automatedlearningofglaucomatousvisualfieldsfromoctimagesusingacomprehensivesegmentationfree3dconvolutionalneuralnetworkmodel