一种基于深度学习的方法用于在眼底照片上准确鉴别视盘玻璃膜疣和视乳头水肿。
A Deep Learning Approach for Accurate Discrimination Between Optic Disc Drusen and Papilledema on Fundus Photographs.
作者信息
Sathianvichitr Kanchalika, Najjar Raymond P, Zhiqun Tang, Fraser J Alexander, Yau Christine W L, Girard Michael J A, Costello Fiona, Lin Mung Y, Lagrèze Wolf A, Vignal-Clermont Catherine, Fraser Clare L, Hamann Steffen, Newman Nancy J, Biousse Valérie, Milea Dan
机构信息
Singapore Eye Research Institute (KS, RPN, TZ, DM), Singapore, Singapore; Duke-NUS Medical School (RPN, MJAG, DM), National University of Singapore, Singapore, Singapore; Department of Ophthalmology (RPN), Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore; Departments of Clinical Neurological Sciences and Ophthalmology (JAF), Western University, London, Canada; Department of Neuro-Ophthalmology (CWLY, DM), Singapore National Eye Centre, Singapore, Singapore; Ophthalmic Engineering & Innovation Laboratory (MJAG), Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore; Institute for Molecular and Clinical Ophthalmology (MJAG), Basel, Switzerland; Departments of Clinical Neurosciences and Surgery (FC), University of Calgary, Calgary, Canada; Department of Medicine (MYL), Emory University School of Medicine, Atlanta, Georgia; Department of Ophthalmology (MYL, NJN, VB), Emory Eye Center, Emory University School of Medicine, Atlanta, Georgia; Eye Center (WAL), Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany; Save Sight Institute (CLF), Faculty of Health and Medicine, The University of Sydney, New South Wales, Australia; Department of Ophthalmology (SH, DM), Rigshospitalet, University of Copenhagen, Copenhagen, Denmark; Department of Neurology (NJN, VB), Emory University School of Medicine, Atlanta, Georgia; Department of Neurological Surgery (NJN), Emory University School of Medicine, Atlanta, Georgia; and Rothschild Foundation Hospital (CV-C, DM), Paris, France.
出版信息
J Neuroophthalmol. 2024 Dec 1;44(4):454-461. doi: 10.1097/WNO.0000000000002223. Epub 2024 Aug 2.
BACKGROUND
Optic disc drusen (ODD) represent an important differential diagnosis of papilledema caused by intracranial hypertension, but their distinction may be difficult in clinical practice. The aim of this study was to train, validate, and test a dedicated deep learning system (DLS) for binary classification of ODD vs papilledema (including various subgroups within each category), on conventional mydriatic digital ocular fundus photographs collected in a large international multiethnic population.
METHODS
This retrospective study included 4,508 color fundus images in 2,180 patients from 30 neuro-ophthalmology centers (19 countries) participating in the Brain and Optic Nerve Study with Artificial Intelligence (BONSAI) Group. For training and internal validation, we used 857 ODD images and 3,230 papilledema images, in 1,959 patients. External testing was performed on an independent data set (221 patients), including 207 images with ODD (96 visible and 111 buried), provided by 3 centers of the Optic Disc Drusen Studies Consortium, and 214 images of papilledema (92 mild-to-moderate and 122 severe) from a previously validated study.
RESULTS
The DLS could accurately distinguish between all ODD and papilledema (all severities included): area under the receiver operating characteristic curve (AUC) 0.97 (95% confidence interval [CI], 0.96-0.98), accuracy 90.5% (95% CI, 88.0%-92.9%), sensitivity 86.0% (95% CI, 82.1%-90.1%), and specificity 94.9% (95% CI, 92.3%-97.6%). The performance of the DLS remained high for discrimination of buried ODD from mild-to-moderate papilledema: AUC 0.93 (95% CI, 0.90-0.96), accuracy 84.2% (95% CI, 80.2%-88.6%), sensitivity 78.4% (95% CI, 72.2%-84.7%), and specificity 91.3% (95% CI, 87.0%-96.4%).
CONCLUSIONS
A dedicated DLS can accurately distinguish between ODD and papilledema caused by intracranial hypertension, even when considering buried ODD vs mild-to-moderate papilledema.
背景
视盘玻璃膜疣（ODD）是颅内高压所致视乳头水肿的重要鉴别诊断，但在临床实践中可能难以区分。本研究的目的是在一个大型国际多民族人群收集的传统散瞳数字眼底照片上，训练、验证并测试一个用于ODD与视乳头水肿（包括每个类别中的各种亚组）二元分类的专用深度学习系统（DLS）。
方法
这项回顾性研究纳入了来自30个神经眼科中心（19个国家）参与人工智能脑与视神经研究（BONSAI）组的2180例患者的4508张彩色眼底图像。为了训练和内部验证，我们使用了1959例患者的857张ODD图像和3230张视乳头水肿图像。在一个独立数据集（221例患者）上进行外部测试，该数据集包括视盘玻璃膜疣研究联盟3个中心提供地207张ODD图像（96张可见和111张埋藏），以及来自一项先前验证研究的214张视乳头水肿图像（92张轻度至中度和122张重度）。
结果
DLS能够准确区分所有ODD和视乳头水肿（包括所有严重程度）：受试者操作特征曲线下面积（AUC）为0.97（95%置信区间[CI]，0.96 - 0.98），准确率为90.5%（95% CI，88.0% - 92.9%），敏感性为86.0%（95% CI，82.1% - 90.1%），特异性为94.9%（95% CI，92.3% - 97.6%）。对于区分埋藏性ODD与轻度至中度视乳头水肿，DLS的性能仍然很高：AUC为0.93（95% CI，0.90 - 0.96），准确率为84.2%（95% CI，80.2% - 88.6%），敏感性为78.4%（95% CI，72.2% - 84.7%），特异性为91.3%（95% CI，87.0% - 96.4%）。
结论
即使考虑埋藏性ODD与轻度至中度视乳头水肿，专用DLS也能准确区分ODD和颅内高压所致视乳头水肿。
Zotero 插件