基于人工智能模型量化视网膜血管特征参数预测子痫前期的可行性研究

周天凡, 邵飞雪, 万盛, 周晨晨, 周思锦, 花晓琳

Feasibility study on quantifying retinal vascular features for predicting preeclampsia based on artificial intelligence models

ZHOU Tianfan, SHAO Feixue, WAN Sheng, ZHOU Chenchen, ZHOU Sijin, HUA Xiaolin

图1 典型眼底图像和视网膜血管分割示意图 Note： A?C. Typical fundus images of the unaffected group (A), GH group (B) and PE group (C). D?F. Schematic diagrams of segmentation of retinal blood vessels of the unaffected group (D), GH group (E) and PE group (F). The red lines represent the retinal arteries, while the blue lines represent the retinal veins.

Fig 1 Typical fundus images and schematic diagrams of segmentation of retinal blood vessels of the three groups