Purpose

: To compare convolutional neural network (CNN) analysis of en face vessel density images to gradient boosting classifier (GBC) analysis of instrument provided, feature-based optical coherence tomography angiography (OCTA) vessel density measurements and OCT RNFL thickness measurements for classifying healthy and glaucomatous eyes.

Design

: Comparison of diagnostic approaches

Methods

: 130 eyes of 80 healthy individuals and 275 eyes of 185 glaucoma patients with optic nerve head (ONH) OCTA and OCT imaging were included. Classification performance of a VGG16 CNN trained and tested on entire en face 4.5 mm x 4.5 mm radial peripapillary capillary OCTA ONH images was compared to performance of separate GBC models trained and tested on standard OCTA and OCT measurements. Five-fold cross-validation was used to test predictions for CNNs and GBCs. Areas under the precision recall curves (AUPRC) were calculated to control for training/test set size imbalance and were compared.

Results

: Adjusted AUPRCs for GBC models were 0.89 (95% CI = 0.82, 0.92) for whole image vessel density GBC, 0.89 (0.83, 0.92) for whole Image capillary density GBC, 0.91 (0.88, 0.93) for combined whole Image vessel and whole image capillary density GBC, and 0.93 (0.91, 095) for RNFL thickness GBC. The adjusted AUPRC using CNN analysis of en face vessel density images was 0.97 (0.95, 0.99) resulting in significantly improved classification compared to GBC OCTA-based results and GBC OCT-based results (P ≤ 0.01 for all comparisons).

Conclusion

: Deep learning en face image analysis improves on feature-based GBC models for classifying healthy and glaucoma eyes.

中文翻译：

---

光学相干断层扫描血管造影测量血管密度的深度学习图像分析改进了健康和青光眼眼睛的分类

目的

：比较正面血管密度图像的卷积神经网络 (CNN) 分析与所提供仪器的梯度增强分类器 (GBC) 分析、基于特征的光学相干断层扫描血管造影 (OCTA) 血管密度测量和 OCT RNFL 厚度测量，用于对健康和健康进行分类青光眼。

设计

: 诊断方法的比较

方法

：包括 80 名健康人的 130 只眼和 185 名青光眼患者的 275 只眼的视神经乳头 (ONH) OCTA 和 OCT 成像。在整个en face 4.5 mm x 4.5 mm 径向毛细血管周围毛细血管 OCTA ONH 图像上训练和测试的VGG16 CNN 的分类性能与在标准 OCTA 和 OCT 测量上训练和测试的单独 GBC 模型的性能进行了比较。五重交叉验证用于测试 CNN 和 GBC 的预测。计算精确召回曲线下的面积 (AUPRC) 以控制训练/测试集大小不平衡并进行比较。

结果

：GBC 模型的调整后 AUPRC 对于整个图像血管密度 GBC 为 0.89（95% CI = 0.82，0.92），对于整个图像毛细管密度 GBC 为 0.89（0.83，0.92），对于组合的整个图像血管和整个图像为 0.91（0.88，0.93）图像毛细血管密度 GBC，RNFL 厚度 GBC 为 0.93（0.91，095）。使用正面血管密度图像的 CNN 分析调整后的 AUPRC为 0.97（0.95，0.99），与基于 GBC OCTA 的结果和基于 GBC OCT 的结果相比，分类得到显着改善（所有比较 P ≤ 0.01）。

结论

：深度学习面部图像分析改进了基于特征的 GBC 模型，用于对健康眼睛和青光眼眼睛进行分类。