Cho Baek Hwan, Lee Da Young, Park Kyung-Ah, Oh Sei Yeul, Moon Jong Hak, Lee Ga-In, Noh Hoon, Chung Joon Kyo, Kang Min Chae, Chung Myung Jin
Medical AI Research Center, Institute of Smart Healthcare, Samsung Medical Center, Seoul, Korea.
Department of Medical Device Management and Research, SAIHST, Sungkyunkwan University, Seoul, Korea.
BMC Ophthalmol. 2020 Oct 9;20(1):407. doi: 10.1186/s12886-020-01657-w.
It is necessary to consider myopic optic disc tilt as it seriously impacts normal ocular parameters. However, ophthalmologic measurements are within inter-observer variability and time-consuming to get. This study aimed to develop and evaluate deep learning models that automatically recognize a myopic tilted optic disc in fundus photography.
This study used 937 fundus photographs of patients with normal or myopic tilted disc, collected from Samsung Medical Center between April 2016 and December 2018. We developed an automated computer-aided recognition system for optic disc tilt on color fundus photographs via a deep learning algorithm. We preprocessed all images with two image resizing techniques. GoogleNet Inception-v3 architecture was implemented. The performances of the models were compared with the human examiner's results. Activation map visualization was qualitatively analyzed using the generalized visualization technique based on gradient-weighted class activation mapping (Grad-CAM++).
Nine hundred thirty-seven fundus images were collected and annotated from 509 subjects. In total, 397 images from eyes with tilted optic discs and 540 images from eyes with non-tilted optic discs were analyzed. We included both eye data of most included patients and analyzed them separately in this study. For comparison, we conducted training using two aspect ratios: the simple resized dataset and the original aspect ratio (AR) preserving dataset, and the impacts of the augmentations for both datasets were evaluated. The constructed deep learning models for myopic optic disc tilt achieved the best results when simple image-resizing and augmentation were used. The results were associated with an area under the receiver operating characteristic curve (AUC) of 0.978 ± 0.008, an accuracy of 0.960 ± 0.010, sensitivity of 0.937 ± 0.023, and specificity of 0.963 ± 0.015. The heatmaps revealed that the model could effectively identify the locations of the optic discs, the superior retinal vascular arcades, and the retinal maculae.
We developed an automated deep learning-based system to detect optic disc tilt. The model demonstrated excellent agreement with the previous clinical criteria, and the results are promising for developing future programs to adjust and identify the effect of optic disc tilt on ophthalmic measurements.
有必要考虑近视性视盘倾斜，因为它会严重影响正常的眼部参数。然而，眼科测量存在观察者间差异，且获取测量结果耗时。本研究旨在开发并评估能在眼底照片中自动识别近视性倾斜视盘的深度学习模型。
本研究使用了2016年4月至2018年12月期间从三星医疗中心收集的937张正常或近视性倾斜视盘患者的眼底照片。我们通过深度学习算法开发了一种用于彩色眼底照片中视盘倾斜的自动计算机辅助识别系统。我们使用两种图像缩放技术对所有图像进行预处理。采用了谷歌网络Inception-v3架构。将模型的性能与人类检查者的结果进行比较。使用基于梯度加权类激活映射（Grad-CAM++）的广义可视化技术对激活图可视化进行定性分析。
从509名受试者收集并标注了937张眼底图像。总共分析了397张来自倾斜视盘眼睛的图像和540张来自非倾斜视盘眼睛的图像。在本研究中，我们纳入了大多数纳入患者的双眼数据并分别进行分析。为了进行比较，我们使用两种宽高比进行训练：简单缩放数据集和保留原始宽高比（AR）的数据集，并评估了两种数据集增强的影响。当使用简单图像缩放和增强时，构建的用于近视性视盘倾斜的深度学习模型取得了最佳结果。结果显示受试者工作特征曲线下面积（AUC）为0.978±0.008，准确率为0.960±0.010，灵敏度为0.937±0.023，特异性为0.963±0.015。热图显示该模型能够有效地识别视盘、视网膜上血管弓和视网膜黄斑的位置。
我们开发了一种基于深度学习的自动系统来检测视盘倾斜。该模型与先前的临床标准显示出极佳的一致性，其结果对于开发未来程序以调整和识别视盘倾斜对眼科测量的影响很有前景。
