PDF(Pubmed)
Abstract：
UNASSIGNED: To assess the accuracy of probabilistic deep learning models to discriminate normal eyes and eyes with glaucoma from fundus photographs and visual fields.
UNASSIGNED: Algorithm development for discriminating normal and glaucoma eyes using data from multicenter, cross-sectional, case-control study.
UNASSIGNED: Fundus photograph and visual field data from 1,655 eyes of 929 normal and glaucoma subjects to develop and test deep learning models and an independent group of 196 eyes of 98 normal and glaucoma patients to validate deep learning models.
UNASSIGNED: Accuracy and area under the receiver-operating characteristic curve (AUC).
UNASSIGNED: Fundus photographs and OCT images were carefully examined by clinicians to identify glaucomatous optic neuropathy (GON). When GON was detected by the reader, the finding was further evaluated by another clinician. Three probabilistic deep convolutional neural network (CNN) models were developed using 1,655 fundus photographs, 1,655 visual fields, and 1,655 pairs of fundus photographs and visual fields collected from Compass instruments. Deep learning models were trained and tested using 80% of fundus photographs and visual fields for training set and 20% of the data for testing set. Models were further validated using an independent validation dataset. The performance of the probabilistic deep learning model was compared with that of the corresponding deterministic CNN model.
UNASSIGNED: The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and combined modalities using development dataset were 0.90 (95% confidence interval: 0.89-0.92), 0.89 (0.88-0.91), and 0.94 (0.92-0.96), respectively. The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and both modalities using the independent validation dataset were 0.94 (0.92-0.95), 0.98 (0.98-0.99), and 0.98 (0.98-0.99), respectively. The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and both modalities using an early glaucoma subset were 0.90 (0.88,0.91), 0.74 (0.73,0.75), 0.91 (0.89,0.93), respectively. Eyes that were misclassified had significantly higher uncertainty in likelihood of diagnosis compared to eyes that were classified correctly. The uncertainty level of the correctly classified eyes is much lower in the combined model compared to the model based on visual fields only. The AUCs of the deterministic CNN model using fundus images, visual field, and combined modalities based on the development dataset were 0.87 (0.85,0.90), 0.88 (0.84,0.91), and 0.91 (0.89,0.94), and the AUCs based on the independent validation dataset were 0.91 (0.89,0.93), 0.97 (0.95,0.99), and 0.97 (0.96,0.99), respectively, while the AUCs based on an early glaucoma subset were 0.88 (0.86,0.91), 0.75 (0.73,0.77), and 0.92 (0.89,0.95), respectively.
UNASSIGNED: Probabilistic deep learning models can detect glaucoma from multi-modal data with high accuracy. Our findings suggest that models based on combined visual field and fundus photograph modalities detects glaucoma with higher accuracy. While probabilistic and deterministic CNN models provided similar performance, probabilistic models generate certainty level of the outcome thus providing another level of confidence in decision making.
UNASSIGNED: Algorithm development for discriminating normal and glaucoma eyes using data from multicenter, cross-sectional, case-control study.
UNASSIGNED: Fundus photograph and visual field data from 1,655 eyes of 929 normal and glaucoma subjects to develop and test deep learning models and an independent group of 196 eyes of 98 normal and glaucoma patients to validate deep learning models.
UNASSIGNED: Accuracy and area under the receiver-operating characteristic curve (AUC).
UNASSIGNED: Fundus photographs and OCT images were carefully examined by clinicians to identify glaucomatous optic neuropathy (GON). When GON was detected by the reader, the finding was further evaluated by another clinician. Three probabilistic deep convolutional neural network (CNN) models were developed using 1,655 fundus photographs, 1,655 visual fields, and 1,655 pairs of fundus photographs and visual fields collected from Compass instruments. Deep learning models were trained and tested using 80% of fundus photographs and visual fields for training set and 20% of the data for testing set. Models were further validated using an independent validation dataset. The performance of the probabilistic deep learning model was compared with that of the corresponding deterministic CNN model.
UNASSIGNED: The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and combined modalities using development dataset were 0.90 (95% confidence interval: 0.89-0.92), 0.89 (0.88-0.91), and 0.94 (0.92-0.96), respectively. The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and both modalities using the independent validation dataset were 0.94 (0.92-0.95), 0.98 (0.98-0.99), and 0.98 (0.98-0.99), respectively. The AUC of the deep learning model in detecting glaucoma from fundus photographs, visual fields, and both modalities using an early glaucoma subset were 0.90 (0.88,0.91), 0.74 (0.73,0.75), 0.91 (0.89,0.93), respectively. Eyes that were misclassified had significantly higher uncertainty in likelihood of diagnosis compared to eyes that were classified correctly. The uncertainty level of the correctly classified eyes is much lower in the combined model compared to the model based on visual fields only. The AUCs of the deterministic CNN model using fundus images, visual field, and combined modalities based on the development dataset were 0.87 (0.85,0.90), 0.88 (0.84,0.91), and 0.91 (0.89,0.94), and the AUCs based on the independent validation dataset were 0.91 (0.89,0.93), 0.97 (0.95,0.99), and 0.97 (0.96,0.99), respectively, while the AUCs based on an early glaucoma subset were 0.88 (0.86,0.91), 0.75 (0.73,0.77), and 0.92 (0.89,0.95), respectively.
UNASSIGNED: Probabilistic deep learning models can detect glaucoma from multi-modal data with high accuracy. Our findings suggest that models based on combined visual field and fundus photograph modalities detects glaucoma with higher accuracy. While probabilistic and deterministic CNN models provided similar performance, probabilistic models generate certainty level of the outcome thus providing another level of confidence in decision making.
摘要：
UNASSIGNED：评估概率深度学习模型从眼底照片和视野中区分正常眼睛和青光眼的准确性。
UNASSIGNED：使用多中心数据区分正常和青光眼眼睛的算法开发，横截面,病例对照研究。
UNASSIGNED：来自929名正常和青光眼受试者的1,655只眼的眼底照片和视野数据，以开发和测试深度学习模型，以及98名正常和青光眼患者的196只眼的独立小组，以验证深度学习模型。
UNASSIGNED：准确性和接收器-工作特征曲线（AUC）下的面积。
未经证实：临床医生仔细检查眼底照片和OCT图像，以确定青光眼视神经病变（GON）。当阅读器检测到GON时，该发现由另一名临床医生进一步评估.使用1655张眼底照片开发了三个概率深度卷积神经网络(CNN)模型，1655个视野，以及从指南针仪器收集的1655对眼底照片和视野。深度学习模型的训练和测试使用80%的眼底照片和视野用于训练集，20%的数据用于测试集。使用独立的验证数据集进一步验证模型。将概率深度学习模型的性能与相应的确定性CNN模型的性能进行了比较。
UNASSIGNED：从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用开发数据集的组合模式为0.90(95%置信区间：0.89-0.92)，0.89（0.88-0.91），和0.94（0.92-0.96），分别。从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用独立验证数据集的两种模式均为0.94（0.92-0.95），0.98（0.98-0.99），和0.98（0.98-0.99），分别。从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用早期青光眼子集的两种模式均为0.90（0.88,0.91），0.74（0.73,0.75），0.91（0.89,0.93），分别。与正确分类的眼睛相比，错误分类的眼睛在诊断可能性上的不确定性明显更高。与仅基于视野的模型相比,在组合模型中正确分类的眼睛的不确定性水平低得多。使用眼底图像的确定性CNN模型的AUC，视野,基于开发数据集的组合模式为0.87(0.85,0.90)，0.88（0.84,0.91），和0.91(0.89,0.94)，基于独立验证数据集的AUC为0.91(0.89,0.93)，0.97（0.95,0.99），和0.97(0.96,0.99)，分别,而基于早期青光眼子集的AUC为0.88(0.86,0.91)，0.75(0.73,0.77)，和0.92(0.89,0.95)，分别。
UNASSIGNED：概率深度学习模型可以从多模态数据中高精度地检测青光眼。我们的发现表明，基于组合视野和眼底照片模式的模型可以更高的准确性检测青光眼。虽然概率和确定性CNN模型提供了相似的性能，概率模型生成结果的确定性水平，从而提供决策的另一个信心水平。
UNASSIGNED：使用多中心数据区分正常和青光眼眼睛的算法开发，横截面,病例对照研究。
UNASSIGNED：来自929名正常和青光眼受试者的1,655只眼的眼底照片和视野数据，以开发和测试深度学习模型，以及98名正常和青光眼患者的196只眼的独立小组，以验证深度学习模型。
UNASSIGNED：准确性和接收器-工作特征曲线（AUC）下的面积。
未经证实：临床医生仔细检查眼底照片和OCT图像，以确定青光眼视神经病变（GON）。当阅读器检测到GON时，该发现由另一名临床医生进一步评估.使用1655张眼底照片开发了三个概率深度卷积神经网络(CNN)模型，1655个视野，以及从指南针仪器收集的1655对眼底照片和视野。深度学习模型的训练和测试使用80%的眼底照片和视野用于训练集，20%的数据用于测试集。使用独立的验证数据集进一步验证模型。将概率深度学习模型的性能与相应的确定性CNN模型的性能进行了比较。
UNASSIGNED：从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用开发数据集的组合模式为0.90(95%置信区间：0.89-0.92)，0.89（0.88-0.91），和0.94（0.92-0.96），分别。从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用独立验证数据集的两种模式均为0.94（0.92-0.95），0.98（0.98-0.99），和0.98（0.98-0.99），分别。从眼底照片中检测青光眼的深度学习模型的AUC，视野,使用早期青光眼子集的两种模式均为0.90（0.88,0.91），0.74（0.73,0.75），0.91（0.89,0.93），分别。与正确分类的眼睛相比，错误分类的眼睛在诊断可能性上的不确定性明显更高。与仅基于视野的模型相比,在组合模型中正确分类的眼睛的不确定性水平低得多。使用眼底图像的确定性CNN模型的AUC，视野,基于开发数据集的组合模式为0.87(0.85,0.90)，0.88（0.84,0.91），和0.91(0.89,0.94)，基于独立验证数据集的AUC为0.91(0.89,0.93)，0.97（0.95,0.99），和0.97(0.96,0.99)，分别,而基于早期青光眼子集的AUC为0.88(0.86,0.91)，0.75(0.73,0.77)，和0.92(0.89,0.95)，分别。
UNASSIGNED：概率深度学习模型可以从多模态数据中高精度地检测青光眼。我们的发现表明，基于组合视野和眼底照片模式的模型可以更高的准确性检测青光眼。虽然概率和确定性CNN模型提供了相似的性能，概率模型生成结果的确定性水平，从而提供决策的另一个信心水平。
