Granted Patent B2

US 12,394,057 · App. 17/822,259 · Granted Aug 19, 2025

Inventors: Hao Yan (Xi'an, CN); Wen Wang (Xi'an, CN); Weiqun Yang (Xi'an, CN); Ningwei He (Xi'an, CN); Gaowa Siqin (Xi'an, CN); Jinsheng Li (Xi'an, CN)

Assignee: OUR UNITED CORPORATION

G06T7/0016G06T7/13G06T7/337G16H30/40G06T2207/30004

Abstract

Claims (91)

1. A method for processing a medical image, comprising:

acquiring a medical image of a target object;

determining an image type of the medical image of the target object; and

determining an image processing mode corresponding to the medical image of the target object based on the image type of the medical image of the target object and a predetermined corresponding relationship, wherein the predetermined corresponding relationship is a predefined corresponding relationship between the image type and the image processing mode;

acquiring a processing result by processing, without acquiring a user operation, the medical image using the image processing mode corresponding to the medical image of the target object; and

outputting the processing result in response to acquiring a user operation triggered by a user for viewing a processed medical image;

wherein the image type of the medical image of the target object comprises:

type I: an image acquired by imaging the target object using a same imaging mode in a same time period;

type II: an image acquired by imaging the target object using the same imaging mode in different time periods;

type III: an image acquired by imaging the target object using different imaging modes in the same time period; and

type IV: an image acquired by imaging the target object using different imaging modes in different time periods.

2. The method according to claim 1 , wherein

the medical image of the target object comprises a first medical image and a second medical image;

in the case that the image types of both the first medical image and the second medical image are type II, type III or type IV, acquiring the processing result by processing the medical image using the image processing mode corresponding to the medical image of the target object comprises:

automatically registering the first medical image and the second medical image;

acquiring a contour of at least one medical image by automatically contouring at least one of the first medical image and the second medical image;

and outputting the processing result in response to acquiring the user operation triggered by the user for viewing the processed medical image comprises:

outputting, in response to acquiring a first user operation triggered by the user for viewing a contoured image of the target object, the contoured image of the target object, wherein the contoured image of the target object is a superimposed image of an automatically registered first medical image and/or an automatically registered second medical image with the contour of the at least one medical image.

3. The method according to claim 2 , wherein acquiring the contour of the at least one medical image by automatically contouring at least one of the first medical image and the second medical image comprises:

acquiring the contour of the at least one medical image by automatically contouring at least one of the automatically registered first medical image and the automatically registered second medical image.

4. The method according to claim 2 , wherein prior to acquiring the first user operation triggered by the user for viewing the contoured image of the target object, the method further comprises:

acquiring the contoured image of the target object by superposing the automatically registered first medical image and/or the automatically registered second medical image with the contour of the at least one medical image; and

saving the contoured image of the target object.

5. The method according to claim 2 , wherein in the case that the image types of both the first medical image and the second medical image are type II or type IV, the method further comprises:

determining a deformation degree of the target object in different time periods; and

outputting a prompt information in response to the deformation degree being greater than a predetermined deformation degree, wherein the prompt information is configured to prompt the user whether to modify a treatment plan for the target object.

6. The method according to claim 5 , wherein determining the deformation degree of the target object in different time periods comprises:

determining the deformation degree of the target object in different time periods based on a deformation field acquired by automatic non-rigid registration of the first medical image and the second medical image;

determining the deformation degree of the target object in different time periods based on an overlap of a first contour of the first medical image and the second medical image in the superimposed image; or

determining the deformation degree of the target object in different time periods based on an overlap of a second contour of the second medical image and the first medical image in the superimposed image.

7. The method according to claim 5 , further comprising:

acquiring feedback information triggered by the user as to whether to modify the treatment plan for the target object; and

adjusting the predetermined deformation degree based on the feedback information.

8. The method according to claim 5 , wherein

the first medical image is a planned image in the treatment plan for the target object, and the second medical image is a real-time image acquired by an imaging apparatus of a radiation treatment device;

acquiring the contour of the at least one medical image by automatically contouring at least one of the first medical image and the second medical image comprises:

acquiring a first contour of the first medical image by automatically contouring the first medical image;

and in the case that the deformation degree is greater than the predetermined deformation degree, the method further comprises:

acquiring a second contour of the second medical image by automatically contouring the second medical image.

9. The method according to claim 5 , wherein

the first medical image is a planned image in the treatment plan for the target object, and the second medical image is a real-time image acquired by an imaging apparatus of a radiation treatment device;

acquiring the contour of the at least one medical image by automatically contouring at least one of the first medical image and the second medical image comprises:

acquiring a first contour of the first medical image by automatically contouring the first medical image;

and in the case that the deformation degree is greater than the predetermined deformation degree, and the feedback information triggered by the user for modifying the treatment plan for the target object is acquired, the method further comprises:

acquiring a second contour of the second medical image by automatically contouring the second medical image.

10. The method according to claim 5 , wherein

the first medical image is a planned image in the treatment plan for the target object, and the second medical image is a real-time image acquired by an imaging apparatus of a radiation treatment device;

acquiring the contour of the at least one medical image by automatically contouring at least one of the first medical image and the second medical image comprises:

acquiring a first contour of the first medical image by automatically contouring the first medical image;

and in the case that the deformation degree is greater than the predetermined deformation degree, the method further comprises:

acquiring a second contour of the second medical image by adjusting the first contour based on a deformation field acquired by automatic non-rigid registration of the first medical image and the second medical image.

11. The method according to claim 5 , wherein

the first medical image is a planned image in the treatment plan for the target object, and the second medical image is a real-time image acquired by an imaging apparatus of a radiation treatment device;

acquiring the contour of the at least one medical image by automatically contouring at least one of the first medical image and the second medical image comprises:

acquiring a first contour of the first medical image by automatically contouring the first medical image;

and in the case that the deformation degree is greater than the predetermined deformation degree, and the feedback information triggered by the user for modifying the treatment plan for the target object is acquired, the method further comprises:

acquiring a second contour of the second medical image by adjusting the first contour based on a deformation field acquired by automatic non-rigid registration of the first medical image and the second medical image.

12. The method according to claim 2 , wherein

acquiring the contour of the at least one medical image by automatically contouring at least one medical image of the first medical image and the second medical image comprises:

acquiring a first contour of the first medical image and a second contour of the second medical image by automatically contouring the first medical image and the second medical image;

the method further comprises:

generating a target contour based on the first contour and the second contour, wherein the contoured image of the target object is a superimposed image of the automatically registered first medical image and/or the automatically registered second medical image with the target contour.

13. The method according to claim 12 , wherein the first medical image and the second medical image are images acquired by imaging the target object using different imaging modes.

14. The method according to claim 2 , wherein outputting the processing result in response to acquiring the user operation triggered by the user for viewing the processed medical image further comprises:

acquiring an automatic registration result in response to acquiring a second user operation triggered by the user for viewing the automatic registration result, wherein the automatic registration result is a superimposed image of the automatically registered first medical image and the automatically registered second medical image; and

outputting the automatic registration result.

15. A device for processing a medical image, comprising: a processor and a memory configured to store an instruction executed by the processor, wherein the processor, when executing the instruction stored in the memory, is caused to perform the method for processing the medical image as defined in claim 1 .

16. A non-transitory computer-readable storage medium, storing an instruction therein, wherein the instruction, when executed on a computer, causes the computer to perform the method for processing the medical image as defined in claim 1 .

17. A method for processing a medical image, comprising:

acquiring a medical image of a target object;

determining an image type of the medical image of the target object; and

determining an image processing mode corresponding to the medical image of the target object based on the image type of the medical image of the target object and a predetermined corresponding relationship, wherein the predetermined corresponding relationship is a predefined corresponding relationship between the image type and the image processing mode;

acquiring a processing result by processing, without acquiring a user operation, the medical image using the image processing mode corresponding to the medical image of the target object, wherein the image processing mode comprises automatic registration and/or automatic contouring; and

saving the processing result;

wherein the image type of the medical image of the target object comprises:

type I: an image acquired by imaging the target object using a same imaging mode in a same time period;

type II: an image acquired by imaging the target object using the same imaging mode in different time periods;

type III: an image acquired by imaging the target object using different imaging modes in the same time period; and

type IV: an image acquired by imaging the target object using different imaging modes in different time periods.

18. A system for processing a medical image, comprising:

a server end and a user end;

wherein:

the server end is configured to acquire a medical image of a target object; determine an image type of the medical image of the target object; determine an image processing mode corresponding to the medical image of the target object based on the image type of the medical image of the target object and a predetermined corresponding relationship, wherein the predetermined corresponding relationship is a predefined corresponding relationship between the image type and the image processing mode; and acquire a processing result by processing, without acquiring a user operation, the medical image using the image processing mode corresponding to the medical image of the target object;

the user end is configured to acquire a user operation triggered by a user for viewing a processed medical image, and send the user operation to the server end;

the server end is further configured to output the processing result in response to acquiring the user operation; and

the user end is further configured to acquire the processing result and display a medical image corresponding to the processing result;

wherein the image type of the medical image of the target object comprises:

type I: an image acquired by imaging the target object using a same imaging mode in a same time period;

type II: an image acquired by imaging the target object using the same imaging mode in different time periods;

type III: an image acquired by imaging the target object using different imaging modes in the same time period; and

type IV: an image acquired by imaging the target object using different imaging modes in different time periods.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (37)