Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images

Purpose To develop an artificial intelligence algorithm to automatically identify the anterior segment structures and assess multiple parameters of primary angle closure disease (PACD) in ultrasound biomicroscopy (UBM) images.Design Development and validation of an artificial intelligence algorithm...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingzhi Sun, Guotong Xie, Kun Lv, Xiaoyue Zhang, Bin Lv, Yuan Ni, Yao Ma, Fangting Li, Kangyi Yang, Jiayin Qin, Huijuan Wu
Format: Article
Language:English
Published: BMJ Publishing Group 2025-01-01
Series:BMJ Open Ophthalmology
Online Access:https://bmjophth.bmj.com/content/10/1/e001600.full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850096398960164864
author Xingzhi Sun
Guotong Xie
Kun Lv
Xiaoyue Zhang
Bin Lv
Yuan Ni
Yao Ma
Fangting Li
Kangyi Yang
Jiayin Qin
Huijuan Wu
author_facet Xingzhi Sun
Guotong Xie
Kun Lv
Xiaoyue Zhang
Bin Lv
Yuan Ni
Yao Ma
Fangting Li
Kangyi Yang
Jiayin Qin
Huijuan Wu
author_sort Xingzhi Sun
collection DOAJ
description Purpose To develop an artificial intelligence algorithm to automatically identify the anterior segment structures and assess multiple parameters of primary angle closure disease (PACD) in ultrasound biomicroscopy (UBM) images.Design Development and validation of an artificial intelligence algorithm for UBM images.Methods:2339 UBM images from 592 subjects were collected for algorithm development. A multitissue segmentation model based on deep learning was developed for automatic identification of anterior segments and localisation of scleral spur. Then, measurement of the typical angle parameters was performed from the predicted results, including angle-opening distance at 500 µm (AOD 500), trabecular–ciliary angle (TCA) and iris area. We then collected 222 UBM images from 45 subjects in two centres for model validation.Results The multitissue identification model established in this study reached mean Intersection over Union (IoU) of 0.98, 0.98 and 0.98 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 1.07 pixels on scleral spur localisation. Our model got a mean IoU of 0.98, 0.98 and 0.99 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 0.49 pixels on scleral spur localisation in open-angle images and received 0.98, 0.98, 0.978 and 1.42 pixels respectively in angle-closure images. The mean differences between automatic and manual measurement of the angle parameters were 3.07 μm of AOD, 3.34 degrees of TCA and 0.05 mm2 of iris area.Conclusions The automatic method of multitissue identification for PACD eyes developed was feasible, and the automatic measurement of angle parameters was reliable.
format Article
id doaj-art-67f3e8f3cf7e43579ff66fc116dad53d
institution DOAJ
issn 2397-3269
language English
publishDate 2025-01-01
publisher BMJ Publishing Group
record_format Article
series BMJ Open Ophthalmology
spelling doaj-art-67f3e8f3cf7e43579ff66fc116dad53d2025-08-20T02:41:14ZengBMJ Publishing GroupBMJ Open Ophthalmology2397-32692025-01-0110110.1136/bmjophth-2023-001600Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy imagesXingzhi Sun0Guotong Xie1Kun Lv2Xiaoyue Zhang3Bin Lv4Yuan Ni5Yao Ma6Fangting Li7Kangyi Yang8Jiayin Qin9Huijuan Wu10Ping An Technology, Shenzhen, ChinaPing An Technology, Shenzhen, ChinaDepartment of Ophthalmology, Peking University People`s Hospital, Beijing, ChinaPing An Technology, Shenzhen, ChinaPing An Insurance Group Company of China Ltd, Shenzhen, ChinaPing An Insurance Group Company of China Ltd, Shenzhen, ChinaBeijing Key Laboratory of Ocular Disease and Optometry Science, Peking University People`s Hospital, Beijing, ChinaDepartment of Ophthalmology, Peking University People`s Hospital, Beijing, ChinaDepartment of Ophthalmology, Peking University People`s Hospital, Beijing, ChinaDepartment of Ophthalmology, Peking University International Hospital, Beijing, ChinaDepartment of Ophthalmology, Peking University People`s Hospital, Beijing, ChinaPurpose To develop an artificial intelligence algorithm to automatically identify the anterior segment structures and assess multiple parameters of primary angle closure disease (PACD) in ultrasound biomicroscopy (UBM) images.Design Development and validation of an artificial intelligence algorithm for UBM images.Methods:2339 UBM images from 592 subjects were collected for algorithm development. A multitissue segmentation model based on deep learning was developed for automatic identification of anterior segments and localisation of scleral spur. Then, measurement of the typical angle parameters was performed from the predicted results, including angle-opening distance at 500 µm (AOD 500), trabecular–ciliary angle (TCA) and iris area. We then collected 222 UBM images from 45 subjects in two centres for model validation.Results The multitissue identification model established in this study reached mean Intersection over Union (IoU) of 0.98, 0.98 and 0.98 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 1.07 pixels on scleral spur localisation. Our model got a mean IoU of 0.98, 0.98 and 0.99 on cornea segmentation, iris segmentation and ciliary body segmentation and a mean error distance of 0.49 pixels on scleral spur localisation in open-angle images and received 0.98, 0.98, 0.978 and 1.42 pixels respectively in angle-closure images. The mean differences between automatic and manual measurement of the angle parameters were 3.07 μm of AOD, 3.34 degrees of TCA and 0.05 mm2 of iris area.Conclusions The automatic method of multitissue identification for PACD eyes developed was feasible, and the automatic measurement of angle parameters was reliable.https://bmjophth.bmj.com/content/10/1/e001600.full
spellingShingle Xingzhi Sun
Guotong Xie
Kun Lv
Xiaoyue Zhang
Bin Lv
Yuan Ni
Yao Ma
Fangting Li
Kangyi Yang
Jiayin Qin
Huijuan Wu
Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
BMJ Open Ophthalmology
title Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
title_full Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
title_fullStr Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
title_full_unstemmed Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
title_short Deep learning-based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
title_sort deep learning based anterior segment identification and parameter assessment of primary angle closure disease in ultrasound biomicroscopy images
url https://bmjophth.bmj.com/content/10/1/e001600.full
work_keys_str_mv AT xingzhisun deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT guotongxie deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT kunlv deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT xiaoyuezhang deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT binlv deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT yuanni deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT yaoma deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT fangtingli deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT kangyiyang deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT jiayinqin deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages
AT huijuanwu deeplearningbasedanteriorsegmentidentificationandparameterassessmentofprimaryangleclosurediseaseinultrasoundbiomicroscopyimages