Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3000 Inherited Retinal Disease Patients from the United Kingdom

William Woof, Thales A.C. de Guimaraes, Saoud Al-Khuzaei, Malena Daich Varela, Sagnik Sen, Pallavi Bagga, Bernardo Souza Mendes, Mital Shah, Paula Burke, David G. Parry, Siying Lin, Gunjan Naik, Alan Sousa da Silva, Biraja Ghoshal, Bart Liefers, Dun Jack Fu, Michalis Georgiou, Yichen Liu, Quang Nguyen, Yu Fujinami-Yokokawa, Nathaniel Kabiri, Dayyanah Sumodhee, Jennifer Furman, Praveen J. Patel, Ismail Moghul, Juliana Sallum, Samantha R. De Silva, Birgit Lorenz, Frank G. Holz, Kaoru Fujinami, Andrew R Webster, Omar A. Mahroo, Susan M. Downes, Savita Madhusudhan, Konstantinos Balaskas, Michel Michaelides, Nikolas Pontikos
{"title":"Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of More Than 3000 Inherited Retinal Disease Patients from the United Kingdom","authors":"William Woof, Thales A.C. de Guimaraes, Saoud Al-Khuzaei, Malena Daich Varela, Sagnik Sen, Pallavi Bagga, Bernardo Souza Mendes, Mital Shah, Paula Burke, David G. Parry, Siying Lin, Gunjan Naik, Alan Sousa da Silva, Biraja Ghoshal, Bart Liefers, Dun Jack Fu, Michalis Georgiou, Yichen Liu, Quang Nguyen, Yu Fujinami-Yokokawa, Nathaniel Kabiri, Dayyanah Sumodhee, Jennifer Furman, Praveen J. Patel, Ismail Moghul, Juliana Sallum, Samantha R. De Silva, Birgit Lorenz, Frank G. Holz, Kaoru Fujinami, Andrew R Webster, Omar A. Mahroo, Susan M. Downes, Savita Madhusudhan, Konstantinos Balaskas, Michel Michaelides, Nikolas Pontikos","doi":"10.1101/2024.03.24.24304809","DOIUrl":null,"url":null,"abstract":"Purpose: To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients.\nDesign: Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients.\nParticipants: Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019.\nMethods: Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire imaging dataset.\nMain Outcome Measures: Quantitative FAF imaging features including area in mm2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively. Results: A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM, ABCC6, ABCA4, RDH12, and RPE65, with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm2. The five genes with the largest hyper-AF areas were BEST1, CDH23, RDH12, MYO7A, and NR2E3, with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm2 respectively. The five genes with largest ring areas were CDH23, NR2E3, CRX, EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm2. Vessel density was found to be highest in EFEMP1, BEST1, TIMP3, RS1, and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes (RPGR, USH2A, RHO, EYS) found EYS to be the fastest progressor at -0.18 mm2/year.\nConclusions: We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":"117 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv - Ophthalmology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.03.24.24304809","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To quantify relevant fundus autofluorescence (FAF) image features cross-sectionally and longitudinally in a large cohort of inherited retinal diseases (IRDs) patients. Design: Retrospective study of imaging data (55-degree blue-FAF on Heidelberg Spectralis) from patients. Participants: Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone FAF 55-degree imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital (RLH) between 2004 and 2019. Methods: Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF) and hyper-autofluorescence (hyper-AF). Features were manually annotated by six graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an AI model, AIRDetect, which was then applied to the entire imaging dataset. Main Outcome Measures: Quantitative FAF imaging features including area in mm2 and vessel metrics, were analysed cross-sectionally by gene and age, and longitudinally to determine rate of progression. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively. Results: A total of 45,749 FAF images from 3,606 IRD patients from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for disc, hypo-AF, hyper-AF, ring and vessels were respectively 0.86, 0.72, 0.69, 0.68 and 0.65. The five genes with the largest hypo-AF areas were CHM, ABCC6, ABCA4, RDH12, and RPE65, with mean per-patient areas of 41.5, 30.0, 21.9, 21.4, and 15.1 mm2. The five genes with the largest hyper-AF areas were BEST1, CDH23, RDH12, MYO7A, and NR2E3, with mean areas of 0.49, 0.45, 0.44, 0.39, and 0.34 mm2 respectively. The five genes with largest ring areas were CDH23, NR2E3, CRX, EYS and MYO7A, with mean areas of 3.63, 3.32, 2.84, 2.39, and 2.16 mm2. Vessel density was found to be highest in EFEMP1, BEST1, TIMP3, RS1, and PRPH2 (10.6%, 10.3%, 9.8%, 9.7%, 8.9%) and was lower in Retinitis Pigmentosa (RP) and Leber Congenital Amaurosis genes. Longitudinal analysis of decreasing ring area in four RP genes (RPGR, USH2A, RHO, EYS) found EYS to be the fastest progressor at -0.18 mm2/year. Conclusions: We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach.
英国 3000 多名遗传性视网膜疾病患者分子特征队列中眼底自发荧光特征的定量分析
目的:对一大批遗传性视网膜疾病(IRDs)患者的眼底自动荧光(FAF)图像特征进行横向和纵向量化:对患者的成像数据(海德堡Spectralis上的55度蓝色-FAF)进行回顾性研究:2004年至2019年期间在Moorfields眼科医院(MEH)和皇家利物浦医院(RLH)接受55度FAF成像的临床和分子确诊为IRD的患者:定义了五个感兴趣的FAF特征:血管、视盘、白内障周围信号增强环(环)、相对低自荧光(低自荧光)和高自荧光(高自荧光)。由六名分级人员根据定义的分级协议对患者子集的特征进行人工标注,生成用于训练人工智能模型 AIRDetect 的分割掩膜,然后将其应用于整个成像数据集:按基因和年龄横向分析FAF成像的定量特征,包括以平方毫米为单位的面积和血管指标,并纵向确定进展率。AIRDetect 特征分割和检测分别通过 Dice 评分和精确度/召回率进行验证。结果:使用 AIRDetect 自动分割了 3,606 名 MEH IRD 患者的 45,749 张 FAF 图像,涵盖 170 个基因。椎间盘、低AF、高AF、环和血管的模型分级Dice得分分别为0.86、0.72、0.69、0.68和0.65。低AF面积最大的五个基因是CHM、ABCC6、ABCA4、RDH12和RPE65,每个患者的平均面积分别为41.5、30.0、21.9、21.4和15.1平方毫米。超 AF 面积最大的五个基因是 BEST1、CDH23、RDH12、MYO7A 和 NR2E3,平均面积分别为 0.49、0.45、0.44、0.39 和 0.34 平方毫米。环面积最大的五个基因是 CDH23、NR2E3、CRX、EYS 和 MYO7A,平均面积分别为 3.63、3.32、2.84、2.39 和 2.16 平方毫米。发现血管密度在 EFEMP1、BEST1、TIMP3、RS1 和 PRPH2 中最高(10.6%、10.3%、9.8%、9.7%、8.9%),而在视网膜色素变性(RP)和 Leber 先天性无视力基因中较低。对四个 RP 基因(RPGR、USH2A、RHO、EYS)的视网膜色素变性环面积递减进行的纵向分析发现,EYS 的视网膜色素变性环面积递减最快,为-0.18 mm2/年:我们首次采用新型人工智能方法,对不同IRD的FAF特征进行了大规模的横断面和纵向定量分析。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信