Systems and methods for phase unwrapping for dense MRI using deep learning

Patent metadata

Field	Value
Publication number	US-11857288-B2
Application number	US-202117166604-A
Country	US
Kind code	B2
Filing date	Feb 3, 2021
Priority date	Feb 3, 2020
Publication date	Jan 2, 2024
Grant date	Jan 2, 2024

Abstract

A method of cardiac strain analysis uses displacement encoded magnetic resonance image (MRI) data of a heart of the subject and includes generating a phase image for each frame of the displacement encoded MRI data. Phase images include potentially phase-wrapped measured phase values corresponding to pixels of the frame. A convolutional neural network CNN computes a wrapping label map for the phase image, and the wrapping label map includes a respective number of phase wrap cycles present at each pixel in the phase image. Computing an unwrapped phase image includes adding a respective phase correction to each of the potentially-wrapped measured phase values of the phase image, and the phase correction is based on the number of phase wrap cycles present at each pixel. Computing myocardial strain follows by using the unwrapped phase image for strain analysis of the subject.

First claim

What is claimed is:

1. A method of strain analysis of a cardiac region of interest of a subject from displacement encoded magnetic resonance image (MRI) data, the method comprising:
acquiring displacement encoded MRI data corresponding to the cardiac region of interest of the subject;
generating a phase image for each frame of the displacement encoded MRI data, wherein the phase image comprises potentially phase-wrapped measured phase values corresponding to pixels of the frame;
training a convolutional neural network (CNN) to compute a wrapping label map for the phase image, wherein the wrapping label map comprises a number of phase wrap cycles present at each pixel in the phase image;
computing, by the trained CNN, the wrapping label map;
computing an unwrapped phase image by adding a respective phase correction to each of the potentially phase-wrapped measured phase values of the phase image, wherein the phase correction is based on the number of phase wrap cycles present at each pixel; and
computing myocardial strain using the unwrapped phase image for strain analysis of the subject.

2. The method of claim 1 , wherein the strain analysis comprises quantification of global and segmental strain associated with the heart of the subject.

3. The method of claim 1 , wherein the displacement encoded MRI data corresponds to displacement encoded stimulated echo (DENSE) cine frames of MRI image data.

4. The method of claim 1 , wherein a U-Net structured CNN is used to compute the wrapping label map.

5. The method of claim 1 , further comprising at least one additional CNN configured for epicardial and endocardial segmentation, and wherein the at least one additional CNN assigns one of three classes to each pixel, wherein the three classes comprise the blood pool, the myocardium, and the background.

6. The method of claim 1 , wherein computing the wrapping label map comprises labeling each pixel as belonging to one of three classes, the classes comprising no-wrap, −2π wrapped, and +2π wrapped.

7. The method of claim 6 , further comprising displaying a visual representation of the phase image according to the respective class and label.

8. The method of claim 1 , wherein at least one trained CNN is trained at least in part from augmented test data from previously verified test images produced by phase unwrapping the previously verified test image, multiplying a phase unwrapped verified test image by a constant, and phase wrapping a product test image within a range of −π to +π to generate a new wrap test image.

9. The method of claim 1 , further comprising using at least one additional CNN to:
(a) identify the left-ventricular (LV) epicardial and endocardial borders; and
(b) identify the interior right ventricular-LV insertion point.

10. The method of claim 1 , further comprising using at least one additional CNN to generate:
(a) segmentation of the LV myocardium;
(b) identification of the anterior right-ventricular (RV) insertion point into the LV; and
(c) an unwrapped phase image by unwrapping of the potentially-wrapped displacement encoded phase values of the myocardium.

11. The method of claim 10 , further comprising:
(d) computing the spatiotemporal displacement field of the unwrapped phase image.

12. The method of claim 1 , wherein:
the potentially phase-wrapped measured phase values correspond to pixel (i, j) of the frame;
the wrapping label map comprises values of respective wrapping constants k ij for each pixel (i, j) in the phase image;
the respective phase correction for each pixel (i, j) is computed by multiplying each value k ij by 2π; and
the unwrapped phase image is computed by adding the phase correction for each pixel (i, j) to each of the potentially phase-wrapped measured phase values of the phase image.

13. The method of claim 1 , wherein the frames of the displacement encoded MRI data comprise image frames having displacement encoded data generated with multiple cycles of phase wrapping.

14. The method of claim 13 , further comprising using the trained CNN to estimate the number of cycles of wrapping corresponding to the phase image during displacement encoding that produced the displacement encoded MRI data.

15. The method of claim 1 , further comprising converting the unwrapped phase image to a respective displacement array.

16. A system, comprising:
a data acquisition device configured to acquire displacement encoded magnetic resonance image (MRI) data corresponding to a cardiac region of interest of a subject;
a computer-implemented convolutional neural network (CNN);
one or more processors coupled to the data acquisition device and the CNN and configured to cause the system to perform functions that comprise:
generating a phase image for each frame of the displacement encoded MRI data, wherein the phase image comprises potentially phase-wrapped measured phase values corresponding to pixels of the frame;
training a convolutional neural network (CNN) to compute a wrapping label map for the phase image, wherein the wrapping label map comprises a respective number of phase wrap cycles present at each pixel in the phase image;
computing, by the trained CNN, the wrapping label map;
computing an unwrapped phase image by adding a respective phase correction to each of the potentially phase-wrapped measured phase values of the phase image, wherein the phase correction is based on the number of phase wrap cycles present at each pixel; and
computing myocardial strain using the unwrapped phase image for strain analysis of the subject.

17. A non-transitory computer-readable medium storing instructions which, when executed by one or more processors, cause one or more computing devices to perform functions for strain analysis of a cardiac region of interest of a subject from displacement encoded magnetic resonance image (MRI) data, and wherein the performed functions comprise:
acquiring displacement encoded MRI data corresponding to the cardiac region of interest of the subject;
generating a phase image for each frame of the displacement encoded MRI data, wherein the phase image comprises potentially phase-wrapped measured phase values corresponding to pixels of the frame;
training a convolutional neural network (CNN) to compute a wrapping label map for the phase image, wherein the wrapping label map comprises a respective number of phase wrap cycles present at each pixel in the phase image;
computing, by the trained CNN, the wrapping label map;
computing an unwrapped phase image by adding a respective phase correction to each of the potentially phase-wrapped measured phase values of the phase image, wherein the phase correction is based on the number of phase wrap cycles present at each pixel; and
computing myocardial strain using the unwrapped phase image for strain analysis of the subject.

Assignees

• Univ Virginia Patent Foundation

Inventors

• Ghadimi Sona
• Sun Changyu
• Feng Xue
• Meyer Craig H
• Epstein Frederick H

Classifications

• A61B5/055

  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• A61B5/0044 Primary

  for the heart · CPC title

• A61B5/02028

  Determining haemodynamic parameters not otherwise provided for, e.g. cardiac contractility or left ventricular ejection fraction · CPC title