GENERATING PSEUDO-CT FROM MR-DATA USING A REGRESSION MODEL BASED ON FEATURES

摘要

FIELD: image forming devices.;SUBSTANCE: invention relates to systems for forming a pseudo-CT image. System includes a processor configured to search and retrieve training data, including at least one MR image and at least one CT image for each of a plurality of training objects. For each training object, the processor can select a plurality of features from each image point of at least one MR image, create a feature vector for each image point based on selected features and select a CT value from each image point of at least one CT image, machine learning method is taught and pseudo-CT image is generated by trained method of machine learning.;EFFECT: high quality of forming a pseudo-CT image.;19 cl, 14 dwg