Himeesh Kumar, Yelena Bagdasarova, Scott Song, Doron G. Hickey, Amy C. Cohn, Mali Okada, Robert P. Finger, Jan H. Terheyden, Ruth E. Hogg, Pierre-Henry Gabrielle, Louis Arnould, Maxime Jannaud, Xavier Hadoux, Peter van Wijngaarden, Carla J. Abbott, Lauren A.B. Hodgson, Roy Schwartz, Adnan Tufail, Emily Y. Chew, Cecilia S. Lee, Erica L. Fletcher, Melanie Bahlo, Brendan R.E. Ansell, Alice Pebay, Robyn H. Guymer, Aaron Y. Lee, Zhichao Wu
{"title":"Deep Learning-Based Detection of Reticular Pseudodrusen in Age-Related Macular Degeneration on Optical Coherence Tomography","authors":"Himeesh Kumar, Yelena Bagdasarova, Scott Song, Doron G. Hickey, Amy C. Cohn, Mali Okada, Robert P. Finger, Jan H. Terheyden, Ruth E. Hogg, Pierre-Henry Gabrielle, Louis Arnould, Maxime Jannaud, Xavier Hadoux, Peter van Wijngaarden, Carla J. Abbott, Lauren A.B. Hodgson, Roy Schwartz, Adnan Tufail, Emily Y. Chew, Cecilia S. Lee, Erica L. Fletcher, Melanie Bahlo, Brendan R.E. Ansell, Alice Pebay, Robyn H. Guymer, Aaron Y. Lee, Zhichao Wu","doi":"10.1101/2024.09.11.24312817","DOIUrl":null,"url":null,"abstract":"Reticular pseudodrusen (RPD) signify a critical phenotype driving vision loss in age-related macular degeneration (AMD). Their detection is paramount in the clinical management of those with AMD, yet they remain challenging to reliably identify. We thus developed a deep learning (DL) model to segment RPD from 9,800 optical coherence tomography B-scans, and this model produced RPD segmentations that had higher agreement with four retinal specialists (Dice similarity coefficient [DSC]=0.76 [95% confidence interval [CI] 0.71-0.81]) than the agreement amongst the specialists (DSC=0.68, 95% CI=0.63-0.73; p<0.001). In five external test datasets consisting of 1,017 eyes from 812 individuals, the DL model detected RPD with a similar level of performance as two retinal specialists (area-under-the-curve of 0.94 [95% CI=0.92-0.97], 0.95 [95% CI=0.92-0.97] and 0.96 [95% CI=0.94-0.98] respectively; p≥0.32). This DL model enables the automatic detection and quantification of RPD with expert-level performance, which we have made publicly available.","PeriodicalId":501390,"journal":{"name":"medRxiv - Ophthalmology","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","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/10.1101/2024.09.11.24312817","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
Reticular pseudodrusen (RPD) signify a critical phenotype driving vision loss in age-related macular degeneration (AMD). Their detection is paramount in the clinical management of those with AMD, yet they remain challenging to reliably identify. We thus developed a deep learning (DL) model to segment RPD from 9,800 optical coherence tomography B-scans, and this model produced RPD segmentations that had higher agreement with four retinal specialists (Dice similarity coefficient [DSC]=0.76 [95% confidence interval [CI] 0.71-0.81]) than the agreement amongst the specialists (DSC=0.68, 95% CI=0.63-0.73; p<0.001). In five external test datasets consisting of 1,017 eyes from 812 individuals, the DL model detected RPD with a similar level of performance as two retinal specialists (area-under-the-curve of 0.94 [95% CI=0.92-0.97], 0.95 [95% CI=0.92-0.97] and 0.96 [95% CI=0.94-0.98] respectively; p≥0.32). This DL model enables the automatic detection and quantification of RPD with expert-level performance, which we have made publicly available.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
