DICTIONARY LEARNING BASED IMAGE RECONSTRUCTION

摘要

A computationally efficient dictionary learning-based term is employed in an iterative reconstruction framework to keep more spatial information than two-dimensional dictionary learning and require less computational cost than three-dimensional dictionary learning. In one such implementation, a non-local regularization algorithm is employed in an MBIR context (such as in a low dose CT image reconstruction context) based on dictionary learning in which dictionaries from different directions (e.g., x,y-plane, y,z-plane, x,z-plane) are employed and the sparse coefficients calculated accordingly. In this manner, spatial information from all three directions is retained and computational cost is constrained.

主权项

1. A reconstruction method, comprising:
acquiring a set of projection data from a plurality of views around an imaged volume; performing an iterative reconstruction of the set of projection data by solving an objective function comprising at least a dictionary-based term, wherein the dictionary-based term employs dictionary learning that employs two or more dictionaries each comprising at least some two-dimensional image patches oriented in different directions; and generating a reconstructed image upon completion of the iterative reconstruction.