Intraocular Cytokine Level Prediction from Fundus Images and Optical Coherence Tomography

We aimed to predict intraocular cytokine concentrations using color fundus photographs (CFP) and retinal optical coherence tomography (OCT) with deep learning. We integrated datasets from 10 previous studies on aqueous humor multiplex cytokines assays and conducted a multi-center retrospective analysis.We used data from 139 patients (152 eyes) and 176 aqueous humor samples.

本研究旨在利用彩色眼底照相（CFP）与视网膜光学相干断层扫描（OCT）结合深度学习技术，预测眼内细胞因子浓度。我们整合了此前10项关于房水多重细胞因子检测的研究数据集，并开展了多中心回顾性分析。本研究共纳入139例患者（152只眼）的176份房水样本数据。