Martin Michl, Bianca S Gerendas, Anastasiia Gruber, Felix Goldbach, Georgios Mylonas, Oliver Leingang, Wolf Bühl, Stefan Sacu, Hrvoje Bogunovic, Amir Sadeghipour, Ursula Schmidt-Erfurth
{"title":"人工智能视网膜液监测在优化条件下对新生血管性年龄相关性黄斑变性与不同眼科保健专业人员人工评估的比较","authors":"Martin Michl, Bianca S Gerendas, Anastasiia Gruber, Felix Goldbach, Georgios Mylonas, Oliver Leingang, Wolf Bühl, Stefan Sacu, Hrvoje Bogunovic, Amir Sadeghipour, Ursula Schmidt-Erfurth","doi":"10.1111/aos.17458","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To investigate whether automated intra- and subretinal fluid (IRF/SRF) volume measurements are equivalent to manual evaluations by eye care professionals from different backgrounds on real-world optical coherence tomography (OCT) images in neovascular age-related macular degeneration (nAMD).</p><p><strong>Methods: </strong>Routine OCT images (Spectralis, Heidelberg Engineering) were obtained during standard-of-care anti-VEGF treatment for nAMD at a tertiary referral centre. IRF/SRF presence and change (increase/decrease/stability) were assessed without time constraints by five retinologists, three ophthalmology residents, three general ophthalmologists, three orthoptists and three certified readers. Fluid volumes were segmented and quantified using a regulatory-approved AI-based tool (Vienna Fluid Monitor, RetInSight, Vienna, Austria). Sensitivity/specificity (Sen/Spe) for grading fluid presence and kappa agreement were calculated for each group. Their performances in distinguishing between IRF/SRF increase and decrease were assessed using AUCs.</p><p><strong>Results: </strong>About 124 follow-up visit pairs of 59 eyes with active nAMD were included. Across all five groups, fluid volumes >5 nL were identified with values of 0.81-0.95 (Sen)/0.70-0.91 (Spe) for IRF and 0.89-0.98 (Sen)/0.74-0.90 (Spe) for SRF. Interpretations of IRF changes between -17 nL and +3 nL and SRF changes between -9.30 nL and +6.50 nL were associated with Sen > 0.80 and Spe > 0.87 among all groups. Agreements between the algorithm and groups in grading IRF/SRF presence ranged from κ = 0.69-0.82/0.73-0.79. The AUC for correctly classifying fluid change was >0.89 across all groups.</p><p><strong>Conclusion: </strong>Eye care professionals with different levels of clinical expertise assessed disease activity on standard OCT images with comparable accuracy. Despite optimizing the methodology and time resources, manual performance did not reach the high level of automated fluid monitoring.</p>","PeriodicalId":6915,"journal":{"name":"Acta Ophthalmologica","volume":" ","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Comparison of AI-based retinal fluid monitoring in neovascular age-related macular degeneration with manual assessment by different eye care professionals under optimized conditions.\",\"authors\":\"Martin Michl, Bianca S Gerendas, Anastasiia Gruber, Felix Goldbach, Georgios Mylonas, Oliver Leingang, Wolf Bühl, Stefan Sacu, Hrvoje Bogunovic, Amir Sadeghipour, Ursula Schmidt-Erfurth\",\"doi\":\"10.1111/aos.17458\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>To investigate whether automated intra- and subretinal fluid (IRF/SRF) volume measurements are equivalent to manual evaluations by eye care professionals from different backgrounds on real-world optical coherence tomography (OCT) images in neovascular age-related macular degeneration (nAMD).</p><p><strong>Methods: </strong>Routine OCT images (Spectralis, Heidelberg Engineering) were obtained during standard-of-care anti-VEGF treatment for nAMD at a tertiary referral centre. IRF/SRF presence and change (increase/decrease/stability) were assessed without time constraints by five retinologists, three ophthalmology residents, three general ophthalmologists, three orthoptists and three certified readers. Fluid volumes were segmented and quantified using a regulatory-approved AI-based tool (Vienna Fluid Monitor, RetInSight, Vienna, Austria). Sensitivity/specificity (Sen/Spe) for grading fluid presence and kappa agreement were calculated for each group. Their performances in distinguishing between IRF/SRF increase and decrease were assessed using AUCs.</p><p><strong>Results: </strong>About 124 follow-up visit pairs of 59 eyes with active nAMD were included. Across all five groups, fluid volumes >5 nL were identified with values of 0.81-0.95 (Sen)/0.70-0.91 (Spe) for IRF and 0.89-0.98 (Sen)/0.74-0.90 (Spe) for SRF. Interpretations of IRF changes between -17 nL and +3 nL and SRF changes between -9.30 nL and +6.50 nL were associated with Sen > 0.80 and Spe > 0.87 among all groups. Agreements between the algorithm and groups in grading IRF/SRF presence ranged from κ = 0.69-0.82/0.73-0.79. The AUC for correctly classifying fluid change was >0.89 across all groups.</p><p><strong>Conclusion: </strong>Eye care professionals with different levels of clinical expertise assessed disease activity on standard OCT images with comparable accuracy. Despite optimizing the methodology and time resources, manual performance did not reach the high level of automated fluid monitoring.</p>\",\"PeriodicalId\":6915,\"journal\":{\"name\":\"Acta Ophthalmologica\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2025-02-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Acta Ophthalmologica\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/aos.17458\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"OPHTHALMOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Acta Ophthalmologica","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/aos.17458","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"OPHTHALMOLOGY","Score":null,"Total":0}
Comparison of AI-based retinal fluid monitoring in neovascular age-related macular degeneration with manual assessment by different eye care professionals under optimized conditions.
Purpose: To investigate whether automated intra- and subretinal fluid (IRF/SRF) volume measurements are equivalent to manual evaluations by eye care professionals from different backgrounds on real-world optical coherence tomography (OCT) images in neovascular age-related macular degeneration (nAMD).
Methods: Routine OCT images (Spectralis, Heidelberg Engineering) were obtained during standard-of-care anti-VEGF treatment for nAMD at a tertiary referral centre. IRF/SRF presence and change (increase/decrease/stability) were assessed without time constraints by five retinologists, three ophthalmology residents, three general ophthalmologists, three orthoptists and three certified readers. Fluid volumes were segmented and quantified using a regulatory-approved AI-based tool (Vienna Fluid Monitor, RetInSight, Vienna, Austria). Sensitivity/specificity (Sen/Spe) for grading fluid presence and kappa agreement were calculated for each group. Their performances in distinguishing between IRF/SRF increase and decrease were assessed using AUCs.
Results: About 124 follow-up visit pairs of 59 eyes with active nAMD were included. Across all five groups, fluid volumes >5 nL were identified with values of 0.81-0.95 (Sen)/0.70-0.91 (Spe) for IRF and 0.89-0.98 (Sen)/0.74-0.90 (Spe) for SRF. Interpretations of IRF changes between -17 nL and +3 nL and SRF changes between -9.30 nL and +6.50 nL were associated with Sen > 0.80 and Spe > 0.87 among all groups. Agreements between the algorithm and groups in grading IRF/SRF presence ranged from κ = 0.69-0.82/0.73-0.79. The AUC for correctly classifying fluid change was >0.89 across all groups.
Conclusion: Eye care professionals with different levels of clinical expertise assessed disease activity on standard OCT images with comparable accuracy. Despite optimizing the methodology and time resources, manual performance did not reach the high level of automated fluid monitoring.
期刊介绍：
Acta Ophthalmologica is published on behalf of the Acta Ophthalmologica Scandinavica Foundation and is the official scientific publication of the following societies: The Danish Ophthalmological Society, The Finnish Ophthalmological Society, The Icelandic Ophthalmological Society, The Norwegian Ophthalmological Society and The Swedish Ophthalmological Society, and also the European Association for Vision and Eye Research (EVER).
Acta Ophthalmologica publishes clinical and experimental original articles, reviews, editorials, educational photo essays (Diagnosis and Therapy in Ophthalmology), case reports and case series, letters to the editor and doctoral theses.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
