MULTI-CONTRAST IMAGE RECONSTRUCTION WITH JOINT BAYESIAN COMPRESSED SENSING

摘要

A method for reconstructing multiple images of a subject depicting multiple different contrast characteristics from medical image data acquired with a medical imaging system is provided. Multiple image data sets are acquired with one or more medical imaging systems and the image data sets used to estimate hyperparameters drawn from a prior distribution, such as a prior distribution of image gradient coefficients. These hyperparameters and the acquired image data sets are utilized to produce a posterior distribution, such as a posterior distribution of image gradients. From this posterior distribution, multiple images with the different contrast characteristics are reconstructed. The medical imaging system may be a magnetic resonance imaging system, an x-ray computed tomography imaging system, an ultrasound system, and so on.