OCT image-based Alzheimer's disease risk prediction method and system and medium

The invention relates to an OCT image-based Alzheimer's disease risk prediction method and system and a medium. The OCT image-based Alzheimer's disease risk prediction method comprises the following steps that a fundus OCT image is input into a trained retina segmentation model to obtain a segmentation mask of a retina region; a fundus OCT image is input into a trained choroid segmentation model to obtain a segmentation mask of a choroid region; the position of a macular central recess is detected; the distance between the upper and lower boundaries of the retina segmentation mask and the choroid segmentation mask at the macular central recess is calculated to obtain the retina thickness and the choroid thickness at the corresponding positions; and the omentum thickness, the choroid thickness and the age and gender information of the person taking the fundus OCT image are input into an optimized multi-index Logistic regression model to obtain the disease risk level of the Alzheimer's disease. The retina and c