Department of Ophthalmology, University of Tokyo Graduate School of Medicine, Tokyo, Japan
Department of Ophthalmology, University of Tokyo Graduate School of Medicine, Tokyo, Japan.
Br J Ophthalmol. 2020 Dec;104(12):1697-1703. doi: 10.1136/bjophthalmol-2019-315027. Epub 2020 Feb 28.
To investigate the usefulness of data augmentation in visual field (VF) trend analyses in patients with glaucoma.
This study included 6380 VFs from 638 eyes of 417 patients with open-angle glaucoma. Various affine transformations were applied to augment the VF data: (1) rotation, (2) scaling, (3) vertical and horizontal shift and (4) a combination of these different transformations. Using pointwise linear regression (PLR), the total deviation (TD) values of a patient's 10th VF were predicted using TD values from shorter VF series (from first to third VFs (VF1-3) to first to ninth VFs (VF1-9)) with and without VF data augmentation, and the root mean squared error (RMSE) was calculated.
With PLR, mean RMSE without VF augmentation averaged from 3.95 (VF1-3) to 19.01 (VF1-9) dB. The RMSE was significantly improved by applying the different transformations: (1) rotation (from VF1-3 to VF1-7), (2) scaling (from VF1-3 to VF1-6), (3) vertical and horizontal shifts (from VF1-3 to VF1-4) and (iv) a combination of these (from VF1-3 to VF1-7). Progression rates in VF1-10 had better agreement with those in shorter VF series when a combination of affine transformation was applied. The differences in rates were between 1.9 (VF1-3) and 0.39 (VF1-9) dB if augmentation was used, which was significantly smaller than that observed when augmentation was not applied (from 2.6 with VF1-3 to 0.26 dB with VF1-9).
It is useful to apply VF data augmentation techniques when predicting future VF progression in glaucoma using PLR, especially with short VF series.
探讨数据扩充在青光眼患者视野（VF）趋势分析中的作用。
本研究纳入了 417 例开角型青光眼患者的 638 只眼中的 6380 个 VF。应用各种仿射变换来扩充 VF 数据：（1）旋转，（2）缩放，（3）垂直和水平移动，（4）这些不同变换的组合。使用逐点线性回归（PLR），在不进行 VF 数据扩充和进行 VF 数据扩充的情况下，根据从第一个到第三个 VF（VF1-3）到第一个到第九个 VF（VF1-9）的较短 VF 系列中的 TD 值，预测患者第 10 个 VF 的总偏差（TD）值，并计算均方根误差（RMSE）。
PLR 分析显示，不进行 VF 扩充时，平均 RMSE 从 3.95（VF1-3）到 19.01（VF1-9）dB。应用不同变换可显著提高 RMSE：（1）旋转（从 VF1-3 到 VF1-7），（2）缩放（从 VF1-3 到 VF1-6），（3）垂直和水平移动（从 VF1-3 到 VF1-4），（4）这些变换的组合（从 VF1-3 到 VF1-7）。应用仿射变换组合时，VF1-10 的进展率与较短 VF 系列的进展率具有更好的一致性。如果应用扩充，速率差异在 1.9（VF1-3）和 0.39（VF1-9）dB 之间，如果不应用扩充，则速率差异在 2.6（VF1-3）和 0.26dB（VF1-9）之间。
在使用 PLR 预测青光眼未来 VF 进展时，应用 VF 数据扩充技术非常有用，尤其是在 VF 较短的情况下。
