Alzheimer's disease auxiliary diagnosis system, data processing method thereof and terminal

The invention discloses an Alzheimer's disease auxiliary diagnosis system. The system comprises a preprocessing module which carries out preprocessing of an original MRI structure image, obtains a preprocessed image, converts the preprocessed image into an MNI space, obtains a preprocessed image, and carries out resampling of the image at an isotropic resolution; an ROI positioning module which performs rigid registration on the image obtained after preprocessing and a standard brain template to obtain a deformation field of non-rigid registration, and selects a plurality of ROIs on the preprocessed individual image according to the deformation field; and an analysis module which constructs, trains, verifies and tests a deep learning model, calculates the characteristic spectrum and the probability value of each ROI in the plurality of ROI individuals by using the deep learning model, and judges whether a subject is an Alzheimer's disease patient according to the probability values. According to the system, t