Systems and methods for magnetic resonance image reconstruction

A method for magnetic resonance imaging (MRI) implemented on a computing apparatus, the computing apparatus including at least one processor and at least one storage device, the method comprising:

• obtaining k-space data associated with MR signals acquired by an MR scanner, the k-space data corresponding to a first sampling rate;
• generating one or more estimated images based on the k-space data and a target neural network model, the one or more estimated images corresponding to a second sampling rate that exceeds the first sampling rate;
• determining, based on the one or more estimated images, an objective function;
• and
• determining one or more target images based on the objective function by performing a plurality of iterations until a condition is satisfied, wherein the objective function includes a regularization term configured to constrain a difference between the one or more estimated images and one or more candidate images determined in each iteration, the one or more candidate images determined in the last iteration after the condition is satisfied being designated as the one or more target images.

A non-transitory computer-readable medium storing at least one set of instructions, wherein when executed by at least one processor, the at least one set of instructions directs the at least one processor to perform acts of:

• obtaining k-space data associated with MR signals acquired by an MR scanner, the k-space data corresponding to a first sampling rate;
• generating one or more estimated images based on the k-space data and a target neural network model, the one or more estimated images corresponding to a second sampling rate that exceeds the first sampling rate;
• determining, based on the one or more estimated images, an objective function;
• and
• determining one or more target images based on the objective function by performing a plurality of iterations until a condition is satisfied, wherein the objective function includes a regularization term configured to constrain a difference between the one or more estimated images and one or more candidate images determined in each iteration, the one or more candidate images determined in the last iteration after the condition is satisfied being designated as the one or more target images.