SYSTEM AND METHOD FOR CORRECTING GRADIENT MAGNETIC FIELD ERROR, BY MAGNETIC RESONANCE IMAGING DEVICE ON BASIS OF MACHINE LEARNING

摘要

The present invention relates to a system and method for correcting a gradient magnetic field error, by a magnetic resonance imaging device on the basis of machine learning. According to a specific example of the present invention, a model about distortion of an image reconstructed with a k-space trajectory derived from a gradient magnetic field is constructed, a k-space trajectory error is predicted on the basis of the result of machine learning using the constructed model, the k-space trajectory is corrected by reflecting the prediction result, and the image is reconstructed with the corrected k-space trajectory, and, thus, additional acquisition of data needed to restore the previously distorted reconstructed image and performing of an image characteristic analysis algorithm can be omitted, thereby increasing accuracy with respect to the corrected k-space trajectory and reducing a cost and calculation complexity caused by adding a monitoring device in terms of hardware.