Self ensembling techniques for generating magnetic resonance images from spatial frequency data

At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method for generating magnetic resonance (MR) images of a subject from MR data obtained by a magnetic resonance imaging (MRI) system, the method comprising:

• generating a first set of one or more MR images from first input MR data obtained by imaging the subject using the MRI system;
• generating a second set of one or more MR images from second input MR data obtained by imaging the subject using the MRI system;
• aligning the first set of one or more MR images and the second set of one or more MR images using a neural network model to obtain aligned first and second sets of one or more MR images, the neural network model comprising a first neural network and a second neural network, the aligning comprising:
• estimating, using the first neural network, a first transformation between the first set of one or more MR images and the second set of one or more MR images;
• generating a first updated set of one or more MR images from the second set of one or more MR images using the first transformation;
• estimating, using the second neural network, a second transformation between the first set of one or more MR images and the first updated set of one or more MR images;
• and
• aligning the first set of one or more MR images and the second set of one or more MR images at least in part by using the first transformation and the second transformation;
• combining the aligned first and second sets of one or more MR images to obtain a combined set of one or more MR images;
• and
• outputting the combined set of one or more MR images.

A magnetic resonance imaging (MRI) system, comprising:

• a magnetics system having a plurality of magnetics components to produce magnetic fields for performing MRI;
• and
• at least one processor configured to perform:
• generating a first set of one or more MR images from first input MR data obtained by imaging a subject using the MRI system;
• generating a second set of one or more MR images from second input MR data obtained by imaging the subject using the MRI system;
• aligning the first set of one or more MR images and the second set of one or more MR images using a neural network model to obtain aligned first and second sets of one or more MR images, the neural network model comprising a first neural network and a second neural network, the aligning comprising:
• estimating, using the first neural network, a first transformation between the first set of one or more MR images and the second set of one or more MR images;
• generating a first updated set of one or more MR images from the second set of one or more MR images using the first transformation;
• estimating, using the second neural network, a second transformation between the first set of one or more MR images and the first updated set of one or more MR images;
• and
• aligning the first set of one or more MR images and the second set of one or more MR images at least in part by using the first transformation and the second transformation;
• combining the aligned first and second sets of one or more MR images to obtain a combined set of one or more MR images;
• and
• outputting the combined set of one or more MR images.