METHOD FOR GENERATING PREDICTIVE MODEL BASED ON INTRA-SUBJECT AND INTER-SUBJECT VARIABILITY USING STRUCTURAL MRI

摘要

Disclosed are a method and apparatus for generating a predictive model based on intra- and inter-subject variability using structural magnetic resonance imaging. This method is a method in which a predictive model generating apparatus generates a predictive model using structural magnetic resonance imaging (MRI). First, a structural process of obtaining an anatomical measurement value for each subject is performed using a plurality of scan data for a plurality of subjects obtained through a plurality of structural MRI scans for each subject. Next, analysis of variance (ANOVA) that confirms intra-subject variability and inter-subject variability using anatomical measurements obtained for each of the plurality of subjects carry out Then, a predictive machine learning model is used for the feature region identified by the within-subject variability and the inter-subject variability to generate a corresponding predictive model.