Abstract: The present disclosure provides an operating method of a brain imaging neurological abnormality prediction system, which includes steps as follows. The T1-weighted image and the diffusion-weighted image of the patient are acquired; the image process is performed on the T1-weighted image and the diffusion-weighted image to obtain a smoothed brain standard space infarction image; the smoothed brain standard space infarction image is multiplied by and a weighted image for a post-processing to obtain a post-weight image; the post-weight image is inputted to the deep learning cross validation classification model of transfer learning to predict whether the neurological abnormality occurs within a predetermined period after the patient's brain disease.

Abstract: The present disclosure provides an operation method of a PET (positron emission tomography) quantitative localization system, which includes steps as follows. The PET image and the MRI (magnetic resonance imaging) of the patient are acquired; the nonlinear deformation is performed on the MRI and the T1 template to generate deformation information parameters; the AAL (automated anatomical labeling) atlas is deformed to an individual brain space of the patient, so as to generate an individual brain space AAL atlas, where the AAL atlas and the T1 template are in a same space; lateralization indexes of the ROIs of the individual brain space AAL atlas corresponding to the PET image normalized through the gray-scale intensity are calculated; the lateralization indexes are inputted into one or more machine learning models to analyze the result of determining a target.