Abstract: Systems and methods for estimating navigator maps for multi-shot phase-navigated image reconstruction are provided. The techniques described herein include acquiring a reference image of a subject, calculating, for a multi-shot MR image of the subject, a navigator map using the reference image, and reconstructing the multi-shot MR image by applying the navigator maps to segments of the multi-shot MR image. The MR image and the reference image may be, for example, a T1-weighted image, a T2-weighted image, a fluid-attenuated inversion recovery (FLAIR) image, DWI image, a water separated image, fat separated image, a fat suppressed image, a phase contrasted image, or a blood contrasted image. The reference image may be a different type, and/or acquired from the same or a different sequence than the MR image. The navigator maps may correct for shot-varying motion-induced phase differences in the multi-shot MR image.

Abstract: A combined physics-based and machine learning framework is used for reconstructing images from k-space data, in which motion artifacts are significantly reduced in the reconstructed images. In general, model-based retrospective motion correction techniques are accelerated using fast machine learning (“ML”) steps, which may be implemented using a trained neural network such as a convolutional neural network. In this way, the confidence of a classical physics-based reconstruction is obtained with the computational benefits of an ML-based network.

Abstract: A combined physics-based and machine learning framework is used for reconstructing images from k-space data, in which motion artifacts are significantly reduced in the reconstructed images. In general, model-based retrospective motion correction techniques are accelerated using fast machine learning (“ML”) steps, which may be implemented using a trained neural network such as a convolutional neural network. In this way, the confidence of a classical physics-based reconstruction is obtained with the computational benefits of an ML-based network.

Abstract: The disclosure relates to a computer implemented method for magnetic resonance imaging. The method includes: receiving at least a first and a second subset of k-space data as radio frequency signals emitted from excited hydrogen atoms of a subject; sampling the first and second subset of k-space data; choosing the first subset of k-space data as a base subset of k-space data; estimating motion parameters of the second subset of k-space data against the base subset of k-space data; and correcting the second subset of k-space data based on the estimated motion parameters of the second subset of k-space data. The motion parameters of the second subset of k-space data are parameters of a non-linear motion estimating function representing a motion of the subject between receiving the first subset of k-space data and receiving the second subset of k-space data.

Abstract: Described here are systems and methods for retrospectively estimating and correcting for rigid-body motion by using a joint optimization technique to jointly solve for motion parameters and the underlying image. This method is implemented for magnetic resonance imaging (“MRI”), but can also be adapted for other imaging modalities.

Abstract: The disclosure relates to a computer implemented method for magnetic resonance imaging. The method includes: receiving at least a first and a second subset of k-space data as radio frequency signals emitted from excited hydrogen atoms of a subject; sampling the first and second subset of k-space data; choosing the first subset of k-space data as a base subset of k-space data; estimating motion parameters of the second subset of k-space data against the base subset of k-space data; and correcting the second subset of k-space data based on the estimated motion parameters of the second subset of k-space data. The motion parameters of the second subset of k-space data are parameters of a non-linear motion estimating function representing a motion of the subject between receiving the first subset of k-space data and receiving the second subset of k-space data.

Abstract: Described here are systems and methods for retrospectively estimating and correcting for rigid-body motion by using a joint optimization technique to jointly solve for motion parameters and the underlying image. This method is implemented for magnetic resonance imaging (“MRI”), but can also be adapted for other imaging modalities.