Canon Medical Systems Corporation

Toshiba Medical Systems Corporation

Anuj Sharma

Andrew James Wheaton

Samir Dev Sharma

Wayne R Dannels

Masahito Nambu

Sampada Bhave

The present disclosure relates to dividing image data obtained from a scan (e.g. MRI) of an object into two or more sets of data corresponding do unique motion patterns and/or motion sources. Each of the two or more sets of data can be corrected using an appropriate correction technique. One appropriate correction techniques includes generating kernels for each divided imaging dataset using center and adjacent slice information to correct for through-plane and in-plane artifacts.

Motion correction of images corrupted by multiple motion sources

An apparatus for incremental motion correction in medical imaging. The apparatus for motion correction in magnetic resonance imaging includes processing circuitry configured to estimate an intermediate image from a first section of k-space, the first section of the k-space corresponding to acquisition time points within a magnetic resonance scan of a subject, the corresponding acquisition time points within the magnetic resonance scan being associated with shots of the k-space determined to have minimal motion, estimate motion parameters of a second section of the k-space using the estimated intermediate image, combine data from the first section of the k-space with data from the second section of the k-space according to the estimated motion parameters, and reconstruct the combined data of the k-space to generate a final image.

System, apparatus, and method for incremental motion correction in magnetic resonance imaging

A magnetic resonance imaging apparatus according to an embodiment includes a processing circuit. The processing circuit acquires a plurality of echo signals not to be encoded corresponding to a plurality of respective shots about acquisition of a plurality of echo signals having been encoded by magnetic resonance imaging for a subject, compares the echo signals not to be encoded with each other about the shots, and identifies a shot to be removed about generation of a magnetic resonance image about the subject out of the shots based on a comparison result of the echo signals not to be encoded.

Magnetic resonance imaging apparatus, method for identifying body motion-related shot, and computer-readable non-volatile storage medium storing therein body motion-related shot identification program

A synthetically generated noise image is generated from at least one high signal-to-noise ratio target image and at least two zero-mean Gaussian noise images, scaled according to a noise scale. The images are combined in a non-linear manner to produce the synthetically generated noise image which can be used as a training image in a machine learning-based system that 'denoises' images. The process can be repeated for a number of different noise scales to produce a set of training images. In one embodiment, the synthetically generated noise image Iis generated according to:=&#x221a;{square root over ()}where I is the original target image, I=I+pGand I=pG, and where Gand Gare zero-mean Gaussian noise images, and p is the noise scale.

Method and system for training a machine learning-based image denoising system

A deep learning (DL) network is proposed to mitigate artifacts in simultaneous multi-slice (SMS) magnetic resonance imaging (MRI) data. For example, unaliased images generated from SMS aliased images can exhibit leakage artifacts due to inaccuracies in the receive-coil sensitives used during sensitivity encoding (SENSE) processing. To mitigate leakage artifacts, the DL network learns to correct the receive-coil sensitives before SENSE processing, and/or learns to detect and subtract the artifacts from the unaliased images after SENSE processing. The DL network can also be trained to denoise the unaliased images.

Apparatus and method for deep learning to mitigate artifacts arising in simultaneous multi slice (SMS) magnetic resonance imaging (MRI)

Magnetic resonance imaging (MRI) systems and methods determine slice leakage and/or residual aliasing in the image domain in accelerated MRI imaging. Implementations process one slice of MRI image domain data by input to a sensitivity encoding (SENSE) un-aliasing matrix built from predetermined RF signal reception sensitivity maps, thereby producing as matrix output SENSE-decoded MRI image domain data for one pass through image slice and at least one extra slice, and determine inter-slice leakage and/or in-plane residual aliasing based on content of the at least one extra output slice from the SENSE-decoded MRI image domain data.

Determining slice leakage in accelerated magnetic resonance imaging

A magnetic resonance imaging system includes an array radiofrequency coil and processing circuitry operatively linked to the array radiofrequency coil and configured to receive output signals from the array radiofrequency coil commensurate with a simultaneous multi-slice magnetic imaging characterized by simultaneous multi-slice parameters, estimate distorted regions of the image volume using either data obtained via a pre-scan or a pre-computed model, minimize overlap of the distorted regions with image voxels representing tissue to obtain optimized values of the simultaneous multi-slice parameters, configuring and executing the simultaneous multi-slice imaging sequence based on the optimized values of the simultaneous multi-slice parameters, and reconstruct simultaneous multi-slice images with minimized artifacts.

Systems and methods for image artifact reduction in simultaneous multi-slice magnetic resonance imaging

An apparatus and method of detecting a characteristic in an image is performed by obtaining, from an image capturing apparatus, raw signal data formed from a plurality of data samples and including a signal of interest captured by the image capturing apparatus and classifying, using a neural network, samples other than the signal of interest using a classifier having been determined using a first parameter based on information about the sample and a second parameter based on information identifying a position of the sample within the raw image data.

Apparatus, system and method for machine learning spike noise detection

Magnetic resonance imaging (MRI) systems and methods to determine and/or correct slice leakage and/or residual aliasing in the image domain in accelerated MRI imaging. Some implementations process one slice of MRI image domain data by input to a sensitivity encoding (SENSE) un-aliasing matrix built from predetermined RF signal reception sensitivity maps, thereby producing SENSE-decoded MRI image domain data for one pass-through image slice and at least one extra slice, and determine inter-slice leakage and/or in-plane residual aliasing based on content of the at least one extra output slice from the SENSE-decoded MRI image domain data. Some implementations correct slice leakage in reconstructed images by generating a fractional leakage matrix of inter-slice leakage measurements, and by multiplying the inverted fractional leakage matrix with uncorrected reconstructed images.

Correcting residual aliasing in accelerated magnetic resonance imaging

An apparatus and method are provided to correct motion artifacts in magnetic resonance imaging (MRI) data by obtaining magnetic resonance imaging (MRI) data, the MRI data including imaging segments and corresponding navigator segments, each imaging segment sampled over a respective regions of two or more regions of a k-space grid, one of the navigator segments being selected as a reference navigator segment; generating, for each imaging segment of the imaging segments, a respective phase map based on the reference navigator segment and a corresponding navigator segment of the each imaging segment; applying the respective phase maps to the corresponding imaging segments to generate corrected imaging segments; averaging the corrected imaging segments in k-space to generate averaged imaging segments; and reconstructing an MRI image based on the averaged imaging segments.

Growing community of inventors

Vernon Hills, IL, United States of America

Anuj Sharma