Background/aims To design a deep learning (DL) model for the detection of glaucoma progression with a longitudinal series of macular optical coherence tomography angiography (OCTA) images. Methods 202 eyes of 134 patients with open-angle glaucoma with ≥4 OCTA visits were followed for an average of 3.5 years. Glaucoma progression was defined as having a statistically significant negative 24-2 visual field (VF) mean deviation (MD) rate. The baseline and final macular OCTA images were aligned according to centre of fovea avascular zone automatically, by checking the highest value of correlation between the two images. A customised convolutional neural network (CNN) was designed for classification. A comparison of the CNN to logistic regression model for whole image vessel density (wiVD) loss on detection of glaucoma progression was performed. The performance of the model was defined based on the confusion matrix of the validation dataset and the area under receiver operating characteristics (AUC). Results The average (95% CI) baseline VF MD was −3.4 (−4.1 to −2.7) dB. 28 (14%) eyes demonstrated glaucoma progression. The AUC (95% CI) of the DL model for the detection of glaucoma progression was 0.81 (0.59 to 0.93). The sensitivity, specificity and accuracy (95% CI) of DL model were 67% (34% to 78%), 83% (42% to 97%) and 80% (52% to 95%), respectively. The AUC (95% CI) for the detection of glaucoma progression based on the logistic regression model was lower than the DL model (0.69 (0.50 to 0.88)). Conclusion The optimised DL model detected glaucoma progression based on longitudinal macular OCTA images showed good performance. With external validation, it could enhance detection of glaucoma progression. Trial registration number [NCT00221897][1]. Data are available upon reasonable request. The datasets generated and/or analysed during the current study are available from the corresponding author on reasonable request. [1]: /lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT00221897&atom=%2Fbjophthalmol%2Fearly%2F2024%2F08%2F07%2Fbjo-2023-324528.atom

中文翻译：

---

使用深度学习模型检测纵向系列正面黄斑光学相干断层扫描血管造影图像上的青光眼进展


背景/目标设计一个深度学习（DL）模型，用于通过一系列纵向黄斑光学相干断层扫描血管造影（OCTA）图像检测青光眼进展。方法对134例OCTA就诊次数≥4次的开角型青光眼患者的202只眼进行平均3.5年的随访。青光眼进展定义为具有统计显着性负24-2视野（VF）平均偏差（MD）率。通过检查两幅图像之间相关性的最高值，根据中央凹无血管区中心自动对齐基线和最终黄斑 OCTA 图像。设计了定制的卷积神经网络（CNN）用于分类。对 CNN 与逻辑回归模型在检测青光眼进展时的整个图像血管密度 (wiVD) 损失进行了比较。模型的性能是根据验证数据集的混淆矩阵和接收者操作特征（AUC）下的面积来定义的。结果 平均 (95% CI) 基线 VF MD 为 -3.4（-4.1 至 -2.7）dB。 28 只 (14%) 眼睛出现青光眼进展。 DL 模型检测青光眼进展的 AUC (95% CI) 为 0.81（0.59 至 0.93）。 DL模型的敏感性、特异性和准确性（95% CI）分别为67%（34%至78%）、83%（42%至97%）和80%（52%至95%）。基于逻辑回归模型检测青光眼进展的 AUC (95% CI) 低于 DL 模型 (0.69 (0.50 至 0.88))。结论 优化后的基于纵向黄斑OCTA图像检测青光眼进展的DL模型表现出良好的性能。通过外部验证，它可以增强对青光眼进展的检测。试用注册号[NCT00221897][1]。 数据可根据合理要求提供。当前研究期间生成和/或分析的数据集可根据合理要求从相应作者处获得。 [1]：/lookup/external-ref?link_type=CLINTRIALGOV&access_num=NCT00221897&atom=%2Fbjophamol%2Fearly%2F2024%2F08%2F07%2Fbjo-2023-324528。原子