Department of Mathematics Education, School of Education, Kyungnam University, 7 Kyugnamdaehak‑ro, Masanhappo‑gu, Changwon, Gyeongsangnam-do, 51767, Republic of Korea.
Department of Ophthalmology, Gyeongsang National University Changwon Hospital, School of Medicine, Gyeongsang National University, 11 Samjeongja-ro, Seongsan-gu, Changwon, Gyeongsangnam-do, 51472, Republic of Korea.
Sci Rep. 2023 Oct 25;13(1):18304. doi: 10.1038/s41598-023-43104-y.
The aim of this study was to predict three visual filed (VF) global indexes, mean deviation (MD), pattern standard deviation (PSD), and visual field index (VFI), from optical coherence tomography (OCT) parameters including Bruch's Membrane Opening-Minimum Rim Width (BMO-MRW) and retinal nerve fiber layer (RNFL) based on a deep-learning model. Subjects consisted of 224 eyes with Glaucoma suspects (GS), 245 eyes with early NTG, 58 eyes with moderate stage of NTG, 36 eyes with PACG, 57 eyes with PEXG, and 99 eyes with POAG. A deep neural network (DNN) algorithm was developed to predict values of VF global indexes such as MD, VFI, and PSD. To evaluate performance of the model, mean absolute error (MAE) was determined. The MAE range of the DNN model on cross validation was 1.9-2.9 (dB) for MD, 1.6-2.0 (dB) for PSD, and 5.0 to 7.0 (%) for VFI. Ranges of Pearson's correlation coefficients were 0.76-0.85, 0.74-0.82, and 0.70-0.81 for MD, PSD, and VFI, respectively. Our deep-learning model might be useful in the management of glaucoma for diagnosis and follow-up, especially in situations when immediate VF results are not available because VF test requires time and space with a subjective nature.
本研究旨在基于深度学习模型，从光学相干断层扫描（OCT）参数中预测 3 个视野（VF）全局指标，包括平均偏差（MD）、模式标准差（PSD）和视野指数（VFI），这些参数包括布鲁赫膜开口最小边缘宽度（BMO-MRW）和视网膜神经纤维层（RNFL）。研究对象包括 224 只青光眼疑似（GS）眼、245 只早期正常眼压性青光眼（NTG）眼、58 只中度 NTG 眼、36 只PACG 眼、57 只 PEXG 眼和 99 只原发性开角型青光眼（POAG）眼。我们开发了一种深度神经网络（DNN）算法来预测 MD、VFI 和 PSD 等 VF 全局指标的值。为了评估模型的性能，我们确定了平均绝对误差（MAE）。在交叉验证中，DNN 模型的 MAE 范围为 MD（1.9-2.9dB）、PSD（1.6-2.0dB）和 VFI（5.0-7.0%）。MD、PSD 和 VFI 的 Pearson 相关系数范围分别为 0.76-0.85、0.74-0.82 和 0.70-0.81。我们的深度学习模型可能有助于青光眼的诊断和随访管理，特别是在无法立即获得 VF 结果的情况下，因为 VF 测试需要时间和空间，并且具有主观性。
