PDF(Pubmed)
Abstract：
UNASSIGNED: Deep learning architectures can automatically learn complex features and patterns associated with glaucomatous optic neuropathy (GON). However, developing robust algorithms requires a large number of data sets. We sought to train an adversarial model for generating high-quality optic disc images from a large, diverse data set and then assessed the performance of models on generated synthetic images for detecting GON.
UNASSIGNED: A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models\' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques.
UNASSIGNED: Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model\'s area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image.
UNASSIGNED: Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection.
UNASSIGNED: Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.
UNASSIGNED: A total of 17,060 (6874 glaucomatous and 10,186 healthy) fundus images were used to train deep convolutional generative adversarial networks (DCGANs) for synthesizing disc images for both classes. We then trained two models to detect GON, one solely on these synthetic images and another on a mixed data set (synthetic and real clinical images). Both the models were externally validated on a data set not used for training. The multiple classification metrics were evaluated with 95% confidence intervals. Models\' decision-making processes were assessed using gradient-weighted class activation mapping (Grad-CAM) techniques.
UNASSIGNED: Following receiver operating characteristic curve analysis, an optimal cup-to-disc ratio threshold for detecting GON from the training data was found to be 0.619. DCGANs generated high-quality synthetic disc images for healthy and glaucomatous eyes. When trained on a mixed data set, the model\'s area under the receiver operating characteristic curve attained 99.85% on internal validation and 86.45% on external validation. Grad-CAM saliency maps were primarily centered on the optic nerve head, indicating a more precise and clinically relevant attention area of the fundus image.
UNASSIGNED: Although our model performed well on synthetic data, training on a mixed data set demonstrated better performance and generalization. Integrating synthetic and real clinical images can optimize the performance of a deep learning model in glaucoma detection.
UNASSIGNED: Optimizing deep learning models for glaucoma detection through integrating DCGAN-generated synthetic and real-world clinical data can be improved and generalized in clinical practice.
摘要：
■深度学习架构可以自动学习与青光眼视神经病变（GON）相关的复杂特征和模式。然而,开发健壮的算法需要大量的数据集。我们试图训练一种对抗模型，用于从大型光盘图像中生成高质量的光盘图像，不同的数据集，然后评估模型在生成的合成图像上的性能，以检测GON。
■总共使用17,060（6874个青光眼和10,186个健康）眼底图像来训练深度卷积生成对抗网络（DCGAN），以合成这两类的光盘图像。然后我们训练了两个模型来检测GON，一个仅在这些合成图像上，另一个在混合数据集（合成和真实临床图像）上。两个模型都在未用于训练的数据集上进行了外部验证。采用95%置信区间对多分类指标进行评价。使用梯度加权类激活映射(Grad-CAM)技术评估模型的决策过程。
■在接收器工作特性曲线分析之后，从训练数据中检测GON的最佳杯盘比阈值为0.619.DCGAN为健康和青光眼眼睛生成了高质量的合成圆盘图像。在混合数据集上训练时，模型在接收器工作特征曲线下的面积在内部验证时达到99.85%，在外部验证时达到86.45%。Grad-CAM显著性图主要集中在视神经头,指示眼底图像的更精确和临床相关的注意区域。
■尽管我们的模型在合成数据上表现良好，在混合数据集上的训练表现出更好的性能和泛化。整合合成和真实临床图像可以优化青光眼检测中深度学习模型的性能。
■通过整合DCGAN生成的合成和真实世界的临床数据来优化青光眼检测的深度学习模型，可以在临床实践中得到改进和推广。
■总共使用17,060（6874个青光眼和10,186个健康）眼底图像来训练深度卷积生成对抗网络（DCGAN），以合成这两类的光盘图像。然后我们训练了两个模型来检测GON，一个仅在这些合成图像上，另一个在混合数据集（合成和真实临床图像）上。两个模型都在未用于训练的数据集上进行了外部验证。采用95%置信区间对多分类指标进行评价。使用梯度加权类激活映射(Grad-CAM)技术评估模型的决策过程。
■在接收器工作特性曲线分析之后，从训练数据中检测GON的最佳杯盘比阈值为0.619.DCGAN为健康和青光眼眼睛生成了高质量的合成圆盘图像。在混合数据集上训练时，模型在接收器工作特征曲线下的面积在内部验证时达到99.85%，在外部验证时达到86.45%。Grad-CAM显著性图主要集中在视神经头,指示眼底图像的更精确和临床相关的注意区域。
■尽管我们的模型在合成数据上表现良好，在混合数据集上的训练表现出更好的性能和泛化。整合合成和真实临床图像可以优化青光眼检测中深度学习模型的性能。
■通过整合DCGAN生成的合成和真实世界的临床数据来优化青光眼检测的深度学习模型，可以在临床实践中得到改进和推广。
