Cerebral paralysis early prediction method and system based on brain MRI image and machine learning

The embodiment of the invention relates to the technical field of image processing and artificial intelligence, in particular to a cerebral palsy early prediction method and system based on brain MRI images and machine learning, and the method comprises the following steps: firstly, based on a brain MRI data set, determining a plurality of key brain regions highly related to cerebral palsy; reconstructing the MRI data of different layer thicknesses in the brain MRI data set into thin-layer MRI data; secondly, preprocessing an image in the thin-layer MRI data to obtain image data; segmenting the key brain region to obtain a segmented key brain region; in the segmented key brain region range, feature extraction and screening are carried out on radiomics features of the brain MRI data set in sequence, and important features are obtained; and finally, inputting the important features into a machine learning model, and performing disease classification based on a classification label to obtain a classification res