# US 2021/0199743 A1 · Methods, systems, and computer readable media for accelerating diffusion magnetic resonance imaging (mri) acquisition via slice-interleaved diffusion encoding

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2021/0199743 A1
- Document ID: US20210199743A1
- Status: Published application
- Kind: A1
- Application number: 17/139,426
- Filed: 2020-12-31
- Published: 2021-07-01
- Earliest claimed: 2019-12-31
- Assignees: The University of North Carolina at Chapel Hill
- Applicants: The University of North Carolina at Chapel Hill
- Inventors: Pew-Thian Yap; Yoonmi Hong; Wei-Tang Chang
- Web page: https://patentgrep.com/patent/US20210199743A1

## CPC

- G01R 33/56341: {Diffusion imaging}
- G01R 33/56545: {caused by finite or discrete sampling, e.g. Gibbs ringing, truncation artefacts, phase aliasing artefacts}
- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- G01R 33/4835: {of multiple slices}
- G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/0475: Generative networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 3/094: Adversarial learning
- G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- A61B 5/0042: {for the brain}
- G06N 3/047: Probabilistic or stochastic networks
- G06T 2210/41: Medical
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A method for accelerating diffusion magnetic resonance imaging (MRI) acquisition via slice interleaved diffusion encoding (SIDE) includes conducting a plurality of simultaneous multislice (SMS) excitations for each of a plurality of SIDE diffusion-weighted volumes to obtain SMS images of an MRI subject at different diffusion orientations, regrouping the images into slice groups with different orientations, generating a plurality of slice-undersampled diffusion weighted volumetric images of the subject, wherein each of the plurality of slice-undersampled diffusion weighted volumetric images is produced by cyclically interleaving the slice groups, such that each slice group is associated with a different diffusion wavevector, and reconstructing a full diffusion-weighted volumetric image of the subject by providing the plurality of slice-undersampled diffusion weighted volumetric images to a neural network trained to produce full diffusion-weighted volumetric versions of diffusion magnetic resonance images from undersampled versions of the diffusion magnetic resonance images.

## Claims

### Claim 1

A method for accelerating diffusion magnetic resonance imaging (MRI) acquisition via slice interleaved diffusion encoding (SIDE), the method comprising:
conducting a plurality of simultaneous multislice (SMS) excitations for each of a plurality of SIDE diffusion-weighted volumes to obtain SMS images of an MRI subject at different diffusion orientations, wherein each SMS excitation captures a plurality of slice images of the MRI subject at one of the different diffusion orientations;
regrouping the images into slice groups with different orientations;
generating a plurality of slice-undersampled diffusion weighted volumetric images of the MRI subject, wherein each of the plurality of slice-undersampled diffusion weighted volumetric images is produced by cyclically interleaving the slice groups, such that each slice group is associated with a different diffusion wavevector; and
reconstructing full diffusion-weighted volumetric images of the MRI subject by providing the plurality of slice-undersampled diffusion weighted volumetric images to a neural network trained to produce full diffusion-weighted volumetric versions of diffusion magnetic resonance images from undersampled versions of the diffusion magnetic resonance images.

### Claim 2 (depends on 1)

The method of claim 1 wherein the plurality of SMS excitations is processed for a period of time equal to a predefined repetition time (TR).

### Claim 3 (depends on 1)

The method of claim 1 wherein cyclically interleaving includes offsetting diffusion wavevectors that sequentially encode the slice groups by an integer factor.

### Claim 4 (depends on 3)

The method of claim 3 wherein the slice groups remain in a same sequence in each encoding cycle and are encoded by the offset diffusion wavevectors in each subsequent encoding cycle.

### Claim 5 (depends on 1)

The method of claim 1 wherein the different orientations of the plurality of SMS excitations are designated using different diffusion wavevectors.

### Claim 6 (depends on 1)

The method of claim 1 wherein each of the SIDE diffusion-weighted volumes contains information resulting from the different diffusion orientations.

### Claim 7 (depends on 1)

The method of claim 1 wherein the neural network is configured to utilize interpolation algorithms to reconstruct the full diffusion-weighted volumetric images.

### Claim 8

A system for accelerating diffusion magnetic resonance imaging (MRI) acquisition via slice interleaved diffusion encoding (SIDE), the system comprising:
at least one computing platform including at least one processor; and
a diffusion MRI acquisition acceleration engine executable by the at least one processor for:
conducting a plurality of simultaneous multislice (SMS) excitations for each of a plurality of SIDE diffusion-weighted volumes to obtain SMS images of an MRI subject at different diffusion orientations, wherein each SMS excitation captures a plurality of slice images of the MRI subject at one of the different diffusion orientations;
regrouping the images into slice groups with different orientations;
generating a plurality of slice-undersampled diffusion weighted volumetric images of the MRI subject, wherein each of the plurality of slice-undersampled diffusion weighted volumetric images is produced by cyclically interleaving the slice groups, such that each slice group is associated with a different diffusion wavevector; and
reconstructing full diffusion-weighted volumetric images of the MRI subject by providing the plurality of slice-undersampled diffusion weighted volumetric images to a neural network trained to produce full diffusion-weighted volumetric versions of diffusion magnetic resonance images from undersampled versions of the diffusion magnetic resonance images.

### Claim 9 (depends on 8)

The system of claim 8 wherein each of the plurality of slice-undersampled diffusion weighted volumes is processed for a period of time equal to a predefined repetition time (TR).

### Claim 10 (depends on 8)

The system of claim 8 wherein cyclically interleaving includes offsetting diffusion wavevectors that sequentially encode the slice groups by an integer factor.

### Claim 11 (depends on 10)

The system of claim 10 wherein the slice groups remain in a same sequence in each encoding cycle and are encoded by the offset diffusion wavevectors in each subsequent encoding cycle.

### Claim 12 (depends on 8)

The system of claim 8 wherein the different orientations of the plurality of SMS excitations are designated using different diffusion wavevectors.

### Claim 13 (depends on 8)

The system of claim 8 wherein each of the SIDE diffusion-weighted volumes contains information resulting from the different orientations.

### Claim 14 (depends on 8)

The system of claim 8 wherein the neural network is configured to utilize interpolation algorithms to reconstruct the full diffusion-weighted volumetric image.

### Claim 15

A non-transitory computer readable medium having stored thereon executable instructions that when executed by at least one processor of at least computer cause the at least one computer to perform steps comprising:
conducting a plurality of simultaneous multislice (SMS) excitations for each of a plurality of slice interleaved diffusion encoding (SIDE) diffusion-weighted volumes to obtain SMS images of an MRI subject at different orientations, wherein each SMS excitation captures a plurality of slice images of the MRI subject at one of the different diffusion orientations;
regrouping the images into slice groups with different orientations;
generating a plurality of slice-undersampled diffusion weighted volumetric images of the MRI subject, wherein each of the plurality of slice-undersampled diffusion weighted volumetric images is produced by cyclically interleaving the slice groups, such that each slice group is associated with a different diffusion wavevector; and
reconstructing full diffusion-weighted volumetric images of the MRI subject by providing the plurality of slice-undersampled diffusion weighted volumetric images to a neural network trained to produce full diffusion-weighted volumetric versions of diffusion magnetic resonance images from undersampled versions of the diffusion magnetic resonance images.

### Claim 16 (depends on 15)

The non-transitory computer readable medium of claim 15 wherein each of the plurality of SMS excitations is processed for a period of time equal to a predefined repetition time (TR).

### Claim 17 (depends on 15)

The non-transitory computer readable medium of claim 15 wherein cyclically interleaving includes offsetting diffusion wavevectors that sequentially encode the slice groups by an integer factor.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17 wherein the slice groups remain in a same sequence in each encoding cycle and are encoded by the offset diffusion wavevectors in each subsequent encoding cycle.

### Claim 19 (depends on 15)

The non-transitory computer readable medium of claim 15 wherein the different orientations of the plurality of SMS excitations are designated using different diffusion wavevectors.

### Claim 20 (depends on 15)

The non-transitory computer readable medium of claim 15 wherein each of the SIDE diffusion-weighted volumes contains information resulting from the different orientations.
