PT - JOURNAL ARTICLE AU - Hashimoto, Yohei AU - Asaoka, Ryo AU - Kiwaki, Taichi AU - Sugiura, Hiroki AU - Asano, Shotaro AU - Murata, Hiroshi AU - Fujino, Yuri AU - Matsuura, Masato AU - Miki, Atsuya AU - Mori, Kazuhiko AU - Ikeda, Yoko AU - Kanamoto, Takashi AU - Yamagami, Junkichi AU - Inoue, Kenji AU - Tanito, Masaki AU - Yamanishi, Kenji TI - Deep learning model to predict visual field in central 10° from optical coherence tomography measurement in glaucoma AID - 10.1136/bjophthalmol-2019-315600 DP - 2021 Apr 01 TA - British Journal of Ophthalmology PG - 507--513 VI - 105 IP - 4 4099 - http://bjo.bmj.com/content/105/4/507.short 4100 - http://bjo.bmj.com/content/105/4/507.full SO - Br J Ophthalmol2021 Apr 01; 105 AB - Background/Aim To train and validate the prediction performance of the deep learning (DL) model to predict visual field (VF) in central 10° from spectral domain optical coherence tomography (SD-OCT).Methods This multicentre, cross-sectional study included paired Humphrey field analyser (HFA) 10-2 VF and SD-OCT measurements from 591 eyes of 347 patients with open-angle glaucoma (OAG) or normal subjects for the training data set. We trained a convolutional neural network (CNN) for predicting VF threshold (TH) sensitivity values from the thickness of the three macular layers: retinal nerve fibre layer, ganglion cell layer+inner plexiform layer and outer segment+retinal pigment epithelium. We implemented pattern-based regularisation on top of CNN to avoid overfitting. Using an external testing data set of 160 eyes of 131 patients with OAG, the prediction performance (absolute error (AE) and R2 between predicted and actual TH values) was calculated for (1) mean TH in whole VF and (2) each TH of 68 points. For comparison, we trained support vector machine (SVM) and multiple linear regression (MLR).Results AE of whole VF with CNN was 2.84±2.98 (mean±SD) dB, significantly smaller than those with SVM (5.65±5.12 dB) and MLR (6.96±5.38 dB) (all, p<0.001). Mean of point-wise mean AE with CNN was 5.47±3.05 dB, significantly smaller than those with SVM (7.96±4.63 dB) and MLR (11.71±4.15 dB) (all, p<0.001). R2 with CNN was 0.74 for the mean TH of whole VF, and 0.44±0.24 for the overall 68 points.Conclusion DL model showed considerably accurate prediction of HFA 10-2 VF from SD-OCT.