Diagnostic Image Analysis Group, Department of Radiology, Radboud University Medical Center, Nijmegen, The Netherlands; Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands.
Department of Ophthalmology, Erasmus University Medical Center, Rotterdam, The Netherlands; Department of Epidemiology, Erasmus University Medical Center, Rotterdam, The Netherlands.
Ophthalmology. 2020 Aug;127(8):1086-1096. doi: 10.1016/j.ophtha.2020.02.009. Epub 2020 Feb 15.
To develop and validate a deep learning model for the automatic segmentation of geographic atrophy (GA) using color fundus images (CFIs) and its application to study the growth rate of GA.
Prospective, multicenter, natural history study with up to 15 years of follow-up.
Four hundred nine CFIs of 238 eyes with GA from the Rotterdam Study (RS) and Blue Mountain Eye Study (BMES) for model development, and 3589 CFIs of 376 eyes from the Age-Related Eye Disease Study (AREDS) for analysis of GA growth rate.
A deep learning model based on an ensemble of encoder-decoder architectures was implemented and optimized for the segmentation of GA in CFIs. Four experienced graders delineated, in consensus, GA in CFIs from the RS and BMES. These manual delineations were used to evaluate the segmentation model using 5-fold cross-validation. The model was applied further to CFIs from the AREDS to study the growth rate of GA. Linear regression analysis was used to study associations between structural biomarkers at baseline and the GA growth rate. A general estimate of the progression of GA area over time was made by combining growth rates of all eyes with GA from the AREDS set.
Automatically segmented GA and GA growth rate.
The model obtained an average Dice coefficient of 0.72±0.26 on the BMES and RS set while comparing the automatically segmented GA area with the graders' manual delineations. An intraclass correlation coefficient of 0.83 was reached between the automatically estimated GA area and the graders' consensus measures. Nine automatically calculated structural biomarkers (area, filled area, convex area, convex solidity, eccentricity, roundness, foveal involvement, perimeter, and circularity) were significantly associated with growth rate. Combining all growth rates indicated that GA area grows quadratically up to an area of approximately 12 mm, after which growth rate stabilizes or decreases.
The deep learning model allowed for fully automatic and robust segmentation of GA on CFIs. These segmentations can be used to extract structural characteristics of GA that predict its growth rate.
开发并验证一种基于彩色眼底图像（CFIs）的深度学习模型，用于自动分割地理萎缩（GA），并将其应用于研究 GA 的增长率。
前瞻性、多中心、随访时间长达 15 年的自然史研究。
来自 Rotterdam 研究（RS）和 Blue Mountain 眼研究（BMES）的 238 只眼的 409 张 CFIs 用于模型开发，来自 Age-Related Eye Disease Study（AREDS）的 376 只眼的 3589 张 CFIs 用于分析 GA 增长率。
实现并优化了一种基于编码器-解码器体系结构的深度学习模型，用于 CFIs 中 GA 的分割。四名有经验的分级员在共识的基础上对 RS 和 BMES 的 CFIs 中的 GA 进行了描绘。使用 5 折交叉验证评估分割模型。该模型进一步应用于 AREDS 的 CFIs，以研究 GA 的增长率。线性回归分析用于研究基线时结构生物标志物与 GA 增长率之间的关联。通过结合 AREDS 中所有患有 GA 的眼睛的增长率，对 GA 面积随时间的进展进行了总体估计。
自动分割的 GA 和 GA 增长率。
与分级员的手动描绘相比，该模型在 BMES 和 RS 数据集上获得了平均 Dice 系数 0.72±0.26。自动估计的 GA 区域与分级员共识测量之间的组内相关系数达到 0.83。九个自动计算的结构生物标志物（面积、填充面积、凸面积、凸度、偏心度、圆度、黄斑受累、周长和圆形度）与增长率显著相关。结合所有增长率表明，GA 面积在达到约 12mm 的面积之前呈二次增长，之后增长率稳定或下降。
深度学习模型允许对 CFIs 上的 GA 进行全自动和稳健的分割。这些分割可用于提取预测 GA 增长率的 GA 的结构特征。
