Abstract：
OBJECTIVE: To develop and validate a deep learning model for the segmentation of five retinal biomarkers associated with neovascular age-related macular degeneration (nAMD).
METHODS: 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients.
RESULTS: The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10).
CONCLUSIONS: We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians\' assessments.
METHODS: 300 optical coherence tomography volumes from subject eyes with nAMD were collected. Images were manually segmented for the presence of five crucial nAMD features: intraretinal fluid, subretinal fluid, subretinal hyperreflective material, drusen/drusenoid pigment epithelium detachment (PED) and neovascular PED. A deep learning architecture based on a U-Net was trained to perform automatic segmentation of these retinal biomarkers and evaluated on the sequestered data. The main outcome measures were receiver operating characteristic curves for detection, summarised using the area under the curves (AUCs) both on a per slice and per volume basis, correlation score, enface topography overlap (reported as two-dimensional (2D) correlation score) and Dice coefficients.
RESULTS: The model obtained a mean (±SD) AUC of 0.93 (±0.04) per slice and 0.88 (±0.07) per volume for fluid detection. The correlation score (R2) between automatic and manual segmentation obtained by the model resulted in a mean (±SD) of 0.89 (±0.05). The mean (±SD) 2D correlation score was 0.69 (±0.04). The mean (±SD) Dice score resulted in 0.61 (±0.10).
CONCLUSIONS: We present a fully automated segmentation model for five features related to nAMD that performs at the level of experienced graders. The application of this model will open opportunities for the study of morphological changes and treatment efficacy in real-world settings. Furthermore, it can facilitate structured reporting in the clinic and reduce subjectivity in clinicians\' assessments.
摘要：
目的：开发并验证一种深度学习模型，用于分割与新生血管性年龄相关性黄斑变性（nAMD）相关的五种视网膜生物标志物。
方法：从患有nAMD的受试者眼睛收集300个光学相干断层扫描体积。手动分割图像是否存在五个关键的nAMD特征：视网膜内液体，视网膜下液,视网膜下高反射材料，玻璃疣/玻璃疣样色素上皮脱离（PED）和新生血管PED。基于U-Net的深度学习架构被训练来执行这些视网膜生物标志物的自动分割,并在隔离数据上进行评估。主要结果测量是用于检测的接收器工作特性曲线，使用每个切片和每个体积的曲线下面积（AUC）进行总结，相关性得分，表面地形图重叠(报告为二维(2D)相关评分)和Dice系数。
结果：对于流体检测，模型获得的平均（±SD）AUC为每片0.93（±0.04）和每体积0.88（±0.07）。通过模型获得的自动和手动分割之间的相关性得分（R2）导致0.89（±0.05）的平均值（±SD）。平均(±SD)2D相关评分为0.69(±0.04)。平均（±SD）Dice评分为0.61（±0.10）。
结论：我们为与nAMD相关的五个功能提供了一个全自动分割模型，该模型在有经验的分级者的水平上执行。该模型的应用将为研究现实环境中的形态变化和治疗功效开辟机会。此外，它可以促进临床中的结构化报告，并减少临床医生评估中的主观性。
方法：从患有nAMD的受试者眼睛收集300个光学相干断层扫描体积。手动分割图像是否存在五个关键的nAMD特征：视网膜内液体，视网膜下液,视网膜下高反射材料，玻璃疣/玻璃疣样色素上皮脱离（PED）和新生血管PED。基于U-Net的深度学习架构被训练来执行这些视网膜生物标志物的自动分割,并在隔离数据上进行评估。主要结果测量是用于检测的接收器工作特性曲线，使用每个切片和每个体积的曲线下面积（AUC）进行总结，相关性得分，表面地形图重叠(报告为二维(2D)相关评分)和Dice系数。
结果：对于流体检测，模型获得的平均（±SD）AUC为每片0.93（±0.04）和每体积0.88（±0.07）。通过模型获得的自动和手动分割之间的相关性得分（R2）导致0.89（±0.05）的平均值（±SD）。平均(±SD)2D相关评分为0.69(±0.04)。平均（±SD）Dice评分为0.61（±0.10）。
结论：我们为与nAMD相关的五个功能提供了一个全自动分割模型，该模型在有经验的分级者的水平上执行。该模型的应用将为研究现实环境中的形态变化和治疗功效开辟机会。此外，它可以促进临床中的结构化报告，并减少临床医生评估中的主观性。
