Medical image processing method, apparatus, and device, medium, and endoscope

1. A medical image processing method, performed by one or more computing devices, the method comprising:

determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object, wherein the reference object is a non-tissue object with a known reference size;

determining a feature size of the target object in the medical image based on the target mask;

determining a feature size of the reference object in the medical image based on the reference mask; and

determining a target size of the target object based on the feature size of the reference object, a mapping relationship between the feature size of the reference object and the known reference size of the reference object, and the feature size of the target object.

2. The method according to claim 1 , further comprising:

determining, according to the medical image, a type of the target object and the target mask of the target object, and a type of the reference object and the reference mask of the reference object in the medical image.

3. The method according to claim 1 , wherein the determining a feature size of the target object based on the target mask comprises:

determining two target feature points in the target mask, a distance between the two target feature points indicating a maximum size of the target object;

determining the distance between the two target feature points as a first feature size of the target mask;

determining a distance between one target feature point in the two target feature points and a center of the medical image as a second feature size of the target object; and

determining a distance between the other target feature point in the two target feature points and the center of the medical image as a third feature size of the target object.

4. The method according to claim 1 , wherein the determining a target size of the target object comprises:

determining at least one mapping parameter used in the mapping relationship based on the known reference size and the feature size of the reference object; and

determining the target size of the target object according to the feature size of the target object, and the at least one mapping parameter used in the mapping relationship.

5. The method according to claim 4 , wherein determining the at least one mapping parameter comprises:

fitting the feature size of the reference mask determined by using at least one related medical image, to determine the at least one mapping parameter.

6. The method according to claim 1 , wherein the determining a feature size of the reference object based on the reference mask comprises:

determining two reference feature points in the reference mask, a distance between the two reference feature points indicating a maximum size of the reference mask;

determining the distance between the two reference feature points as a first feature size of the reference object;

determining a distance between one reference feature point in the two reference feature points and a center of the medical image as a second feature size of the reference object; and

determining a distance between the other reference feature point in the two reference feature points and the center of the medical image as a third feature size of the reference object.

7. The method according to claim 4 , wherein the mapping relationship is represented in a form of a polynomial, the polynomial comprises at least one variable, the at least one variable represents the feature size of the reference object, and the mapping parameter is a coefficient of each term in the polynomial.

8. The method according to claim 1 , further comprising:

obtaining a frame of image from a real-time medical video stream as the medical image;

determining whether the medical image meets a preset condition according to the target mask and the reference mask;

determining the target size of the target object based on the feature size of the reference object, the feature size of the target object, and the reference size when the medical image meets the preset condition; and

obtaining another frame of image from the real-time medical video stream as the medical image when the medical image does not meet the preset condition.

9. The method according to claim 1 , wherein the medical image is an endoscopic image, and the reference object is a medical instrument or a part of a medical instrument.

10. The method according to claim 1 , wherein the determining a target size of the target object comprises:

determining the target size of the target object by using a weighted average of a plurality of target sizes of the target object determined by using a plurality of medical images.

11. A medical image processing apparatus, comprising: one or more processors; and one or more memories, the memory storing computer-readable code, wherein the one or more processors are configured to execute the computer-readable code to:

determine a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object, wherein the reference object is a non-tissue object with a known reference size;

determine a feature size of the target object in the medical image based on the target mask;

determine a feature size of the reference object in the medical image based on the reference mask; and

determine a target size of the target object based on the feature size of the reference object, a mapping relationship between the feature size of the reference object and the known reference size of the reference object, and the feature size of the target object.

12. The apparatus according to claim 11 , wherein the one or more processors are further configured to: determine, according to the medical image, a type of the target object and the target mask of the target object, and a type of the reference object and the reference mask of the reference object in the medical image.

13. The apparatus according to claim 11 , wherein the one or more processors are further configured to:

determine two target feature points in the target mask, a distance between the two target feature points indicating a maximum size of the target mask;

determine the distance between the two target feature points as a first feature size of the target object;

determine a distance between one target feature point in the two target feature points and a center of the medical image as a second feature size of the target object; and

determine a distance between the other target feature point in the two target feature points and the center of the medical image as a third feature size of the target object.

14. The apparatus according to claim 11 , wherein the one or more processors are further configured to:

determine at least one mapping parameter used in the mapping relationship based on the known reference size and the feature size of the reference object; and

determine the target size of the target object according to the feature size of the target object, and the at least one mapping parameter used in the mapping relationship.

15. The apparatus according to claim 14 , wherein the one or more processors are further configured to fit the feature size of the reference mask determined by using at least one related medical image, to determine the at least one mapping parameter.

16. The apparatus according to claim 14 , wherein the one or more processors are further configured to:

determine two reference feature points in the reference mask, a distance between the two reference feature points indicating a maximum size of the reference mask;

determine the distance between the two reference feature points as a first feature size of the reference object;

determine a distance between one reference feature point in the two reference feature points and a center of the medical image as a second feature size of the reference object; and

determine a distance between the other reference feature point in the two reference feature points and the center of the medical image as a third feature size of the reference object.

17. The apparatus according to claim 11 , wherein the one or more processors are further configured to:

obtain a frame of image from a real-time medical video stream as the medical image;

determine whether the medical image meets a preset condition according to the target mask and the reference mask;

determine the target size of the target object based on the feature size of the reference object, the feature size of the target object, and the reference size when the medical image meets the preset condition; and

obtain another frame of image from the real-time medical video stream as the medical image when the medical image does not meet the preset condition.

18. The apparatus according to claim 11 , wherein the medical image is an endoscopic image, and the reference object is a medical instrument or a part of a medical instrument.

19. The apparatus according to claim 11 , wherein the one or more processors are further configured to:

determine the target size of the target object by using a weighted average of a plurality of target sizes of the target object determined by using a plurality of medical images.

20. A non-transitory computer-readable storage medium, storing instructions, the instructions, when executed by a processor, causing the processor to perform:

determining a target mask of a target object in a medical image and a reference mask of a reference object in the medical image, the target mask indicating a position and a boundary of the target object, and the reference mask indicating a position and a boundary of the reference object, wherein the reference object is a non-tissue object with a known reference size;

determining a feature size of the target object in the medical image based on the target mask;

determining a feature size of the reference object in the medical image based on the reference mask;

determining at least one mapping parameter used in a mapping relationship between the feature size of the reference object and the known reference size of the reference object based on the known reference size and the feature size of the reference object; and

determining a target size of the target object based on the feature size of the reference object, the at least one mapping parameter used in the mapping relationship between the feature size of the reference object and the known reference size of the reference object, and the feature size of the target object.