摘要：Visual field assessment is recognized as the important criterion of glaucomatous damage judgement; however, it can show large test–retest variability. We developed a deep learning (DL) algorithm that quantitatively predicts mean deviation (MD) of standard automated perimetry (SAP) from monoscopic optic disc photographs (ODPs). A total of 1200 image pairs (ODPs and SAP results) for 563 eyes of 327 participants were enrolled. A DL model was built by combining a pre-trained DL network and subsequently trained fully connected layers. The correlation coefficient and mean absolute error (MAE) between the predicted and measured MDs were calculated. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the detection ability for glaucomatous visual field (VF) loss. The data were split into training/validation (1000 images) and testing (200 images) sets to evaluate the performance of the algorithm. The predicted MD showed a strong correlation and good agreement with the actual MD (correlation coefficient = 0.755; R2 = 57.0%; MAE = 1.94 dB). The model also accurately predicted the presence of glaucomatous VF loss (AUC 0.953). The DL algorithm showed great feasibility for prediction of MD and detection of glaucomatous functional loss from ODPs.
其他摘要：Abstract Visual field assessment is recognized as the important criterion of glaucomatous damage judgement; however, it can show large test–retest variability. We developed a deep learning (DL) algorithm that quantitatively predicts mean deviation (MD) of standard automated perimetry (SAP) from monoscopic optic disc photographs (ODPs). A total of 1200 image pairs (ODPs and SAP results) for 563 eyes of 327 participants were enrolled. A DL model was built by combining a pre-trained DL network and subsequently trained fully connected layers. The correlation coefficient and mean absolute error (MAE) between the predicted and measured MDs were calculated. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the detection ability for glaucomatous visual field (VF) loss. The data were split into training/validation (1000 images) and testing (200 images) sets to evaluate the performance of the algorithm. The predicted MD showed a strong correlation and good agreement with the actual MD (correlation coefficient = 0.755; R 2 = 57.0%; MAE = 1.94 dB). The model also accurately predicted the presence of glaucomatous VF loss (AUC 0.953). The DL algorithm showed great feasibility for prediction of MD and detection of glaucomatous functional loss from ODPs.
