Motion detection associated with a body part

Patent metadata

Field	Value
Publication number	US-12591982-B2
Application number	US-202318195009-A
Country	US
Kind code	B2
Filing date	May 9, 2023
Priority date	May 9, 2023
Publication date	Mar 31, 2026
Grant date	Mar 31, 2026

Abstract

Detecting motions associated with a body part of a patient may include using an image sensor installed inside a medical scanner to capture first and second images of the patient inside the medical scanner, wherein the first image may depict the patient in a first state and the second image may depict the patient in a second state. A first area, in the first image, that corresponds to the body part of the patient may be identified and a second area, in the second image, that corresponds to the body part may also be identified so that a first plurality of features may be extracted from the first area of the first image and a second plurality of features may be extracted from the second area of the second image. A motion associated with the body part of the patient may be determined based on the first and second pluralities of features.

First claim

The invention claimed is:

1 . An apparatus, comprising:
at least one processor configured to: obtain, from a color image sensor installed inside a medical scanner, a first color image of a patient inside the medical scanner and a second color image of the patient inside the medical scanner, wherein the first color image depicts the patient in a first state and the second color image depicts the patient in a second state; identify, using a first machine learning (ML) model, a first area in the first color image that corresponds to a body part of the patient; identify, using the first ML model, a second area in the second color image that corresponds to the body part of the patient; extract a first plurality of features from the first area of the first color image and a second plurality of features from the second area of the second color image; determine a preliminary motion of the body part based on the first plurality of features and the second plurality of features; calculate a movement of the medical scanner between a time when the patient is in the first state and a time when the patient is in the second state; and determine a motion of the body part of the patient by subtracting the calculated movement of the medical scanner from the preliminary motion of the body part.

2 . The apparatus of claim 1 , wherein the medical scanner includes a computed tomography (CT) scanner or a magnetic resonance imaging (MRI) scanner.

3 . The apparatus of claim 1 , wherein the at least one processor is further configured to obtain one or more images of the medical scanner and calculate the movement of the medical scanner based on the one or more obtained images.

4 . The apparatus of claim 1 , wherein the at least one processor is further configured to receive information regarding the movement of the medical scanner from the medical scanner and calculate the movement of the medical scanner based on the received information.

5 . The apparatus of claim 1 , wherein the at least one processor is configured to determine the preliminary motion of the body part in multiple dimensions and subtract the movement of the medical scanner from at least one of the multiple dimensions.

6 . The apparatus of claim 1 , wherein the at least one processor being configured to determine the preliminary motion of the body part of the patient based on the first plurality of features and the second plurality of features comprises the at least one processor being configured to determine corresponding features from the first plurality of features and the second plurality of features, and determine the preliminary motion of the body part of the patient based on differences between the corresponding features.

7 . The apparatus of claim 6 , wherein the at least one processor being configured to determine the corresponding features from the first plurality of features and the second plurality of features comprises the at least one processor being configured to identify corresponding pixels in the first area of the first color image and the second area of the second color image that are associated with the body part of the patient, and determine the corresponding features from the first plurality of features and the second plurality of features by selecting respective features from the first plurality of features and the second plurality of features that are associated with the identified pixels.

8 . The apparatus of claim 1 , wherein the at least one processor is further configured to extract the first plurality of features from the first area of the first color image and the second plurality of features from the second area of the second color image using the first ML model or a second ML model.

9 . A method for determining a motion associated with a body part of a patient, the method comprising:
obtaining, from a color image sensor installed inside a medical scanner, a first color image of the patient inside the medical scanner and a second color image of the patient inside the medical scanner, wherein the first color image depicts the patient in a first state and the second color image depicts the patient in a second state; identifying, using a first machine learning (ML) model, a first area in the first color image that corresponds to the body part of the patient; identifying, using the first ML model, a second area in the second color image that corresponds to the body part of the patient; extracting a first plurality of features from the first area of the first color image and a second plurality of features from the second area of the second color image; determining a preliminary motion of the body part of the patient based on the first plurality of features and the second plurality of features; calculating a movement of the medical scanner between a time when the patient is in the first state and a time when the patient is in the second state; and determining the motion of the body part of the patient by subtracting the calculated movement of the medical scanner from the preliminary motion of the body part.

10 . The method of claim 9 , wherein the medical scanner includes a computed tomography (CT) scanner or a magnetic resonance imaging (MRI) scanner.

11 . The method of claim 9 , further comprising obtaining one or more images of the medical scanner, wherein the movement of the medical scanner is calculated based on the one or more obtained images.

12 . The method of claim 9 , further comprising receiving information regarding the movement of the medical scanner from the medical scanner, wherein the movement of the medical scanner is calculated based on the received information.

13 . The method of claim 9 , wherein the preliminary motion is determined in multiple dimensions and wherein the movement of the medical scanner is subtracted from at least one of the multiple dimensions.

14 . The method of claim 9 , wherein determining the preliminary motion associated with the body part of the patient based at least on the first plurality of features and the second plurality of features comprises determining corresponding features from the first plurality of features and the second plurality of features, and determining the preliminary motion associated with the body part of the patient based on differences between the corresponding features.

15 . The method of claim 14 , wherein determining the corresponding features from the first plurality of features and the second plurality of features comprises identifying corresponding pixels in the first area of the first color image and the second area of the second color image that are associated with the body part of the patient, and determining the corresponding features from the first plurality of features and the second plurality of features by selecting respective features from the first plurality of features and the second plurality of features that are associated with the identified pixels.

16 . The method of claim 9 , wherein the first plurality of features is extracted from the first area of the first color image and the second plurality of features is extracted from the second area of the second color image using the first ML model or a second ML model.

Assignees

• Shanghai United Imaging Intelligence Co Ltd

Inventors

• Gao Zhongpai
• Sharma Abhishek
• Zheng Meng
• Planche Benjamin
• Wu Ziyan
• Chen Terrence

Classifications

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06T2207/10081

  Computed x-ray tomography [CT] · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T2207/10088

  Magnetic resonance imaging [MRI] · CPC title

• G06V10/25 Primary

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title