Using Deep Learning to Segment Retinal Vascular Leakage and Occlusion in Retinal Vasculitis.

IF 2.6 4区医学 Q2 OPHTHALMOLOGY Ocular Immunology and Inflammation Pub Date : 2024-12-01 Epub Date: 2024-01-23 DOI:10.1080/09273948.2024.2305185

Dhanach Dhirachaikulpanich, Jianyang Xie, Xiuju Chen, Xiaoxin Li, Savita Madhusudhan, Yalin Zheng, Nicholas A V Beare

{"title":"Using Deep Learning to Segment Retinal Vascular Leakage and Occlusion in Retinal Vasculitis.","authors":"Dhanach Dhirachaikulpanich, Jianyang Xie, Xiuju Chen, Xiaoxin Li, Savita Madhusudhan, Yalin Zheng, Nicholas A V Beare","doi":"10.1080/09273948.2024.2305185","DOIUrl":null,"url":null,"abstract":"Purpose: Retinal vasculitis (RV) is characterised by retinal vascular leakage, occlusion or both on fluorescein angiography (FA). There is no standard scheme available to segment RV features. We aimed to develop a deep learning model to segment both vascular leakage and occlusion in RV.Methods: Four hundred and sixty-three FA images from 82 patients with retinal vasculitis were used to develop a deep learning model, in 60:20:20 ratio for training:validation:testing. Parameters, including deep learning architectures (DeeplabV3+, UNet++ and UNet), were altered to find the best binary segmentation model separately for retinal vascular leakage and occlusion, using a Dice score to determine the reliability of each model.Results: Our best model for vascular leakage had a Dice score of 0.6279 (95% confidence interval (CI) 0.5584-0.6974). For occlusion, the best model achieved a Dice score of 0.6992 (95% CI 0.6109-0.7874).Conclusion: Our RV segmentation models could perform reliable segmentation for retinal vascular leakage and occlusion in FAs of RV patients.","PeriodicalId":19406,"journal":{"name":"Ocular Immunology and Inflammation","volume":" ","pages":"2291-2298"},"PeriodicalIF":2.6000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ocular Immunology and Inflammation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1080/09273948.2024.2305185","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/23 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose: Retinal vasculitis (RV) is characterised by retinal vascular leakage, occlusion or both on fluorescein angiography (FA). There is no standard scheme available to segment RV features. We aimed to develop a deep learning model to segment both vascular leakage and occlusion in RV.

Methods: Four hundred and sixty-three FA images from 82 patients with retinal vasculitis were used to develop a deep learning model, in 60:20:20 ratio for training:validation:testing. Parameters, including deep learning architectures (DeeplabV3+, UNet++ and UNet), were altered to find the best binary segmentation model separately for retinal vascular leakage and occlusion, using a Dice score to determine the reliability of each model.

Results: Our best model for vascular leakage had a Dice score of 0.6279 (95% confidence interval (CI) 0.5584-0.6974). For occlusion, the best model achieved a Dice score of 0.6992 (95% CI 0.6109-0.7874).

Conclusion: Our RV segmentation models could perform reliable segmentation for retinal vascular leakage and occlusion in FAs of RV patients.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用深度学习对视网膜血管炎中的视网膜血管渗漏和闭塞进行分段。

目的：视网膜血管炎（RV视网膜血管炎（RV）的特征是荧光素血管造影（FA）显示视网膜血管渗漏、闭塞或两者兼有。目前还没有分割视网膜血管炎特征的标准方案。我们的目标是开发一种深度学习模型，用于分割 RV 中的血管渗漏和闭塞：我们使用了 82 名视网膜血管炎患者的 463 张 FA 图像来开发深度学习模型，训练：验证：测试的比例为 60:20:20。改变包括深度学习架构（DeeplabV3+、UNet++ 和 UNet）在内的参数，分别为视网膜血管渗漏和闭塞找到最佳二元分割模型，并使用 Dice 分数确定每个模型的可靠性：结果：血管渗漏的最佳模型 Dice 得分为 0.6279（95% 置信区间 (CI) 0.5584-0.6974）。对于闭塞，最佳模型的 Dice 得分为 0.6992（95% 置信区间为 0.6109-0.7874）：结论：我们的 RV 分割模型可以对 RV 患者 FA 中的视网膜血管渗漏和闭塞进行可靠的分割。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Ocular Immunology and Inflammation 医学-眼科学

CiteScore

6.20

自引率

15.20%

发文量

285

审稿时长

6-12 weeks

期刊介绍： Ocular Immunology & Inflammation ranks 18 out of 59 in the Ophthalmology Category.Ocular Immunology and Inflammation is a peer-reviewed, scientific publication that welcomes the submission of original, previously unpublished manuscripts directed to ophthalmologists and vision scientists. Published bimonthly, the journal provides an international medium for basic and clinical research reports on the ocular inflammatory response and its control by the immune system. The journal publishes original research papers, case reports, reviews, letters to the editor, meeting abstracts, and invited editorials.