Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images

Objectives To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices.Design A multicentre, platform-based development study using retrospective and cross-sectional data....

Full description

Saved in:
Bibliographic Details
Main Authors: Mingzhi Zhang, Tsz Kin Ng, Yi Zheng, Guihua Zhang, Jian-Wei Lin, Ji Wang, Jie Ji, Peiwen Xie, Yongqun Xiong, Hanfu Wu, Cui Liu, Huishan Zhu, Jinqu Huang, Leixian Lin
Format: Article
Language:English
Published: BMJ Publishing Group 2025-05-01
Series:BMJ Open
Online Access:https://bmjopen.bmj.com/content/15/5/e099167.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850233948623339520
author Mingzhi Zhang
Tsz Kin Ng
Yi Zheng
Guihua Zhang
Jian-Wei Lin
Ji Wang
Jie Ji
Peiwen Xie
Yongqun Xiong
Hanfu Wu
Cui Liu
Huishan Zhu
Jinqu Huang
Leixian Lin
author_facet Mingzhi Zhang
Tsz Kin Ng
Yi Zheng
Guihua Zhang
Jian-Wei Lin
Ji Wang
Jie Ji
Peiwen Xie
Yongqun Xiong
Hanfu Wu
Cui Liu
Huishan Zhu
Jinqu Huang
Leixian Lin
author_sort Mingzhi Zhang
collection DOAJ
description Objectives To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices.Design A multicentre, platform-based development study using retrospective and cross-sectional data. Data were subjected to a two-level grading system by trained graders and a retina specialist, and categorised into three types: no DME, non-centre-involved DME and centre-involved DME (CI-DME). The 3-D convolutional neural networks algorithm was used for DME classification system development. The deep learning (DL) performance was compared with the diabetic retinopathy experts.Setting Data were collected from Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Chaozhou People’s Hospital and The Second Affiliated Hospital of Shantou University Medical College from January 2010 to December 2023.Participants 7790 volumes of 7146 eyes from 4254 patients were annotated, of which 6281 images were used as the development set and 1509 images were used as the external validation set, split based on the centres.Main outcomes Accuracy, F1-score, sensitivity, specificity, area under receiver operating characteristic curve (AUROC) and Cohen’s kappa were calculated to evaluate the performance of the DL algorithm.Results In classifying DME with non-DME, our model achieved an AUROCs of 0.990 (95% CI 0.983 to 0.996) and 0.916 (95% CI 0.902 to 0.930) for hold-out testing dataset and external validation dataset, respectively. To distinguish CI-DME from non-centre-involved-DME, our model achieved AUROCs of 0.859 (95% CI 0.812 to 0.906) and 0.881 (95% CI 0.859 to 0.902), respectively. In addition, our system showed comparable performance (Cohen’s κ: 0.85 and 0.75) to the retina experts (Cohen’s κ: 0.58–0.92 and 0.70–0.71).Conclusions Our DL system achieved high accuracy in multiclassification tasks on DME classification with 3-D OCT images, which can be applied to population-based DME screening.
format Article
id doaj-art-bd930a2797b3488d9225b8d4264e40a7
institution OA Journals
issn 2044-6055
language English
publishDate 2025-05-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open
spelling doaj-art-bd930a2797b3488d9225b8d4264e40a72025-08-20T02:02:47ZengBMJ Publishing GroupBMJ Open2044-60552025-05-0115510.1136/bmjopen-2025-099167Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography imagesMingzhi Zhang0Tsz Kin Ng1Yi Zheng2Guihua Zhang3Jian-Wei Lin4Ji Wang5Jie Ji6Peiwen Xie7Yongqun Xiong8Hanfu Wu9Cui Liu10Huishan Zhu11Jinqu Huang12Leixian Lin13The Chinese University of Hong Kong, Hong Kong, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaShantou University Medical College, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaJoint Shantou International Eye Center of Shantou University and The Chinese University of Hong Kong, Shantou, ChinaObjectives To develop and validate an automated diabetic macular oedema (DME) classification system based on the images from different three-dimensional optical coherence tomography (3-D OCT) devices.Design A multicentre, platform-based development study using retrospective and cross-sectional data. Data were subjected to a two-level grading system by trained graders and a retina specialist, and categorised into three types: no DME, non-centre-involved DME and centre-involved DME (CI-DME). The 3-D convolutional neural networks algorithm was used for DME classification system development. The deep learning (DL) performance was compared with the diabetic retinopathy experts.Setting Data were collected from Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong, Chaozhou People’s Hospital and The Second Affiliated Hospital of Shantou University Medical College from January 2010 to December 2023.Participants 7790 volumes of 7146 eyes from 4254 patients were annotated, of which 6281 images were used as the development set and 1509 images were used as the external validation set, split based on the centres.Main outcomes Accuracy, F1-score, sensitivity, specificity, area under receiver operating characteristic curve (AUROC) and Cohen’s kappa were calculated to evaluate the performance of the DL algorithm.Results In classifying DME with non-DME, our model achieved an AUROCs of 0.990 (95% CI 0.983 to 0.996) and 0.916 (95% CI 0.902 to 0.930) for hold-out testing dataset and external validation dataset, respectively. To distinguish CI-DME from non-centre-involved-DME, our model achieved AUROCs of 0.859 (95% CI 0.812 to 0.906) and 0.881 (95% CI 0.859 to 0.902), respectively. In addition, our system showed comparable performance (Cohen’s κ: 0.85 and 0.75) to the retina experts (Cohen’s κ: 0.58–0.92 and 0.70–0.71).Conclusions Our DL system achieved high accuracy in multiclassification tasks on DME classification with 3-D OCT images, which can be applied to population-based DME screening.https://bmjopen.bmj.com/content/15/5/e099167.full
spellingShingle Mingzhi Zhang
Tsz Kin Ng
Yi Zheng
Guihua Zhang
Jian-Wei Lin
Ji Wang
Jie Ji
Peiwen Xie
Yongqun Xiong
Hanfu Wu
Cui Liu
Huishan Zhu
Jinqu Huang
Leixian Lin
Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
BMJ Open
title Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
title_full Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
title_fullStr Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
title_full_unstemmed Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
title_short Development and validation of a 3-D deep learning system for diabetic macular oedema classification on optical coherence tomography images
title_sort development and validation of a 3 d deep learning system for diabetic macular oedema classification on optical coherence tomography images
url https://bmjopen.bmj.com/content/15/5/e099167.full
work_keys_str_mv AT mingzhizhang developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT tszkinng developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT yizheng developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT guihuazhang developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT jianweilin developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT jiwang developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT jieji developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT peiwenxie developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT yongqunxiong developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT hanfuwu developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT cuiliu developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT huishanzhu developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT jinquhuang developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages
AT leixianlin developmentandvalidationofa3ddeeplearningsystemfordiabeticmacularoedemaclassificationonopticalcoherencetomographyimages