Glaucoma diagnosis method based on deep learning

The invention discloses a glaucoma diagnosis method based on deep learning, and the method comprises the steps: carrying out the preprocessing of an input original fundus image data set, and obtaining image data which can be recognized and utilized by a model 1; the model 1 is trained, so that the model 1 can accurately segment an optic disc and optic cup region according to the fundus image and output a key feature image showing optic disc and optic cup segmentation; extracting a key feature image of the model 1 in the process of processing the eye fundus image as an input parameter of the model 2, preprocessing image data needing to be input into the model 2, and converting the image data into data in a unified format; after the model 2 receives input data of the model 1, training of the model 2 is carried out, then a target result is output, and the target result is glaucoma or non-glaucoma. 本发明公开了一种基于深度学习的青光眼诊断方法，将输入的原始眼底图像数据集进行预处理，并得到模型1可识别利用的图像数据；训练模型1，使模型1达到根据眼底图像能够准确分割视盘视杯区域并输出展现视盘视杯分割的关键特征图像；提取模型1在处理