Systems and methods for machine learning based physiological motion measurement

Patent metadata

Field	Value
Publication number	US-11710244-B2
Application number	US-201916673817-A
Country	US
Kind code	B2
Filing date	Nov 4, 2019
Priority date	Nov 4, 2019
Publication date	Jul 25, 2023
Grant date	Jul 25, 2023

Abstract

A system for physiological motion measurement is provided. The system may acquire a reference image corresponding to a reference motion phase of an ROI and a target image of the ROI corresponding to a target motion phase, wherein the reference motion phase may be different from the target motion phase. The system may identify one or more feature points relating to the ROI from the reference image, and determine a motion field of the feature points from the reference motion phase to the target motion phase using a motion prediction model. An input of the motion prediction model may include at least the reference image and the target image. The system may further determine a physiological condition of the ROI based on the motion field.

First claim

What is claimed is:

1. A system, comprising:
at least one storage device including a set of instructions for physiological motion measurement; and
at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to direct the system to perform operations including:
acquiring a reference image of a region of interest (ROI) corresponding to a reference motion phase of the ROI and a target image of the ROI corresponding to a target motion phase of the ROI, the target motion phase being different from the reference motion phase;
identifying one or more feature points relating to the ROI from the reference image;
determining, based on the reference image, a first distance between a first feature point and a second feature point of the one or more feature points, the first feature point and the second feature point being in the reference image corresponding to the reference motion phase;
determining a motion field of the first feature point and the second feature point from the reference motion phase to the target motion phase using a motion prediction model, wherein an input of the motion prediction model includes at least the reference image and the target image;
determining, based on the motion field, a second distance between a third feature point in the target image, corresponding to the first feature point, and a fourth feature point in the target image, corresponding to the second feature point; and
determining, based on the first distance and the second distance, a physiological condition of the ROI, wherein the motion prediction model is generated by performing an iteration operation for training a preliminary model using at least one training sample, each of the at least one training sample including a first sample image and a second sample image indicative of a physiological motion of a sample region of interest (ROI), the first sample image corresponding to a first motion phase of the sample ROI, and the second sample image corresponding to a second motion phase of the sample ROI, the iteration operating including one or more iterations, at least one of the one or more iterations including:
for each of the at least one training sample,
generating a first motion field from the first sample image to the second sample image using an updated preliminary model determined in a previous iteration;
generating a predicted second sample image according to the first motion field; and
determining a first difference between the predicted second sample image and the second sample image of the training sample;

determining, based at least in part on the first difference corresponding to each of the at least one training sample, a value of a loss function; and
updating the updated preliminary model to be used in a next iteration based on the value of the loss function.

2. The system of claim 1 , wherein the ROI includes at least one of a heart, a lung, an abdomen, a chest, a stomach of a subject.

3. The system of claim 1 , wherein
the ROI is a heart,
the first feature point relating to the heart in the reference image includes an inner point on an endocardium of the heart, and
the second feature point relating to the heart in the reference image includes a corresponding outer point on an epicardium of the heart.

4. The system of claim 3 , wherein to identify the inner point and the corresponding outer point from the reference image, the at least one processor is further configured to direct the system to perform additional operations including:
segmenting, from the reference image, the endocardium and the epicardium; and
identifying, based on positions of the endocardium and the epicardium, the inner point and the corresponding outer point from the reference image.

5. The system of claim 1 , the ROI comprising a heart, wherein the motion field includes a motion vector of the first feature point and a motion vector of the second feature point, and to determine a physiological condition of the heart, the at least one processor is further configured to direct the system to perform additional operations including:
determining, based on the motion vector of the first feature point, the third feature point in the target image corresponding to the first feature point;
determining, based on the motion vector of the second feature point, the fourth feature point in the target image corresponding to the second feature point;
determining the second distance between the third feature point and the fourth feature point in the target motion phase; and
determining, based on the first distance and the second distance, a strain value relating to the heart.

6. The system of claim 1 , wherein the motion prediction model is trained
according to an unsupervised learning technique.

7. The system of claim 6 , wherein the preliminary model is a generative adversarial network (GAN) model.

8. The system of claim 1 , wherein the motion prediction model is generated by minimizing the loss function.

9. The system of claim 1 , wherein the predicted second sample image is generated by warping the first sample image of the training sample according to the first motion field.

10. The system of claim 1 , wherein the at least one of the one or more iterations further includes:
for each of the at least one training sample,
generating a second motion field from the second sample image to the first sample image using the preliminary model;
determining an opposite motion field of the second motion field; and
determining a second difference between the opposite motion field and the first motion field of the training sample,
wherein the value of the loss function is determined further based on the second difference corresponding to each training sample.

11. The system of claim 10 , wherein the at least one of the one or more iterations further includes:
for each of the at least one training sample,
generating a predicted first sample image by warping the second sample image of the training sample according to the first sample image of the training sample using the preliminary model;
generating a third sample image by warping the predicted first sample image according to the second sample image using the preliminary model;
generating a fourth sample image by warping the predicted second sample image according to the first sample image using the preliminary model; and
determining a third difference between the third sample image and the second sample image and a fourth difference between the fourth sample image and the first sample image,
wherein the value of the loss function is determined further based on the third difference and the fourth difference corresponding to each training sample.

12. A non-transitory computer readable medium, comprising a set of instructions for physiological motion measurement, wherein when executed by at least one processor, the set of instructions direct the at least one processor to effectuate a method, the method comprising:
acquiring a reference image of a region of interest (ROI) corresponding to a reference motion phase of the ROI and a target image of the ROI corresponding to a target motion phase of the ROI, the target motion phase being different from the reference motion phase;
identifying one or more feature points relating to the ROI from the reference image;
determining, based on the reference image, a first distance between a first feature point and a second feature point of the one or more feature points, the first feature point and the second feature point being in the reference image corresponding to the in the reference m

Assignees

• Shanghai United Imaging Intelligence Co Ltd

Inventors

• Sun Shanhui
• Chen Zhang
• Chen Terrence
• Wu Ziyan

Classifications

• G06T12/10

  Image preprocessing, e.g. calibration, positioning of sources or scatter correction · CPC title

• G06T7/248 Primary

  involving reference images or patches · CPC title

• A61B5/1076

  for measuring dimensions inside body cavities, e.g. using catheters (A61B3/1005 takes precedence) · CPC title

• A61B5/1107

  Measuring contraction of parts of the body, e.g. organ or muscle · CPC title

• A61B5/1128

  using image analysis (A61B5/1127 takes precedence) · CPC title