Department of Mathematics Education, School of Education, Kyungnam University, Changwon, Republic of Korea.
Department of Ophthalmology, Gyeongsang National University Changwon Hospital, Gyeongsang National University, School of Medicine, 11 Samjeongja-ro, Seongsan-gu, Changwon, Gyeongsangnam-do, 51472, Republic of Korea.
Sci Rep. 2020 Nov 4;10(1):19042. doi: 10.1038/s41598-020-76154-7.
We aimed to classify early normal-tension glaucoma (NTG) and glaucoma suspect (GS) using Bruch's membrane opening-minimum rim width (BMO-MRW), peripapillary retinal nerve fiber layer (RNFL), and the color classification of RNFL based on a deep-learning model. Discriminating early-stage glaucoma and GS is challenging and a deep-learning model may be helpful to clinicians. NTG accounts for an average 77% of open-angle glaucoma in Asians. BMO-MRW is a new structural parameter that has advantages in assessing neuroretinal rim tissue more accurately than conventional parameters. A dataset consisted of 229 eyes out of 277 GS and 168 eyes of 285 patients with early NTG. A deep-learning algorithm was developed to discriminate between GS and early NTG using a training set, and its accuracy was validated in the testing dataset using the area under the curve (AUC) of the receiver operating characteristic curve (ROC). The deep neural network model (DNN) achieved highest diagnostic performance, with an AUC of 0.966 (95%confidence interval 0.929-1.000) in classifying either GS or early NTG, while AUCs of 0.927-0.947 were obtained by other machine-learning models. The performance of the DNN model considering all three OCT-based parameters was the highest (AUC 0.966) compared to the combinations of just two parameters. As a single parameter, BMO-MRW (0.959) performed better than RNFL alone (0.914).
我们旨在使用基于深度学习的模型，通过脉络膜开口最小边缘宽度（BMO-MRW）、视盘周围视网膜神经纤维层（RNFL）和基于颜色的 RNFL 分类，来区分早期正常眼压性青光眼（NTG）和青光眼疑似患者（GS）。区分早期青光眼和 GS 具有一定难度，深度学习模型可能对临床医生有所帮助。在亚洲人中，NTG 占开角型青光眼的平均 77%。BMO-MRW 是一种新的结构参数，在评估神经视网膜边缘组织方面比传统参数具有优势。该数据集由 277 例 GS 中的 229 只眼和 285 例早期 NTG 患者中的 168 只眼组成。通过训练集开发了一种深度学习算法，以区分 GS 和早期 NTG，然后使用受试者工作特征曲线（ROC）下的面积（AUC）在测试集中验证其准确性。深度神经网络模型（DNN）在区分 GS 或早期 NTG 方面的诊断性能最高，AUC 为 0.966（95%置信区间 0.929-1.000），而其他机器学习模型的 AUC 为 0.927-0.947。与仅考虑两个参数的组合相比，同时考虑所有三个 OCT 基于参数的 DNN 模型的性能最高（AUC 为 0.966）。作为单一参数，BMO-MRW（0.959）的表现优于单独的 RNFL（0.914）。
