CN-114155376-B - Target feature point extraction method, device, computer equipment and storage medium

CN114155376BCN 114155376 BCN114155376 BCN 114155376BCN-114155376-B

Abstract

The application relates to a target feature point extraction method, a target feature point extraction device, computer equipment and a storage medium. The method comprises the steps of obtaining an image to be processed, obtaining a template corresponding to the image to be processed, and obtaining the position relation between the template and standard feature points, wherein the template is an image generated based on a sample image, the standard feature points are located in the template, registering the template to the image to be processed, and determining target feature points corresponding to the standard feature points in the image to be processed according to the position relation between the template and the standard feature points after the registration and the position relation between the template and the image to be processed. The method can realize automatic extraction of the target feature points.

Inventors

LIU HE
LIU PENGFEI

Assignees

苏州微创畅行机器人有限公司

Dates

Publication Date: 20260508
Application Date: 20211105

Claims (16)

1. The target feature point extraction method is characterized by comprising the following steps of: acquiring an image to be processed; the method comprises the steps of obtaining a template corresponding to an image to be processed, and obtaining the position relation between the template and standard characteristic points, wherein the template is an image generated based on a sample image, and the standard characteristic points are positioned in the template; registering the template to the image to be processed; According to the position relation between the template and the standard feature points, combining the registered position relation between the template and the image to be processed, and determining target feature points corresponding to the standard feature points in the image to be processed; The method for determining the target feature point corresponding to the standard feature point in the image to be processed according to the position relationship between the template and the standard feature point and by combining the registered position relationship between the template and the image to be processed, further comprises the following steps: when the standard characteristic points are not on the surface of the standard plate, selecting a preset number of points from the surface of the template according to the standard characteristic points as associated points; Determining a target point of the association point in the registration image according to the registration relation between the template and the image to be processed; And calculating target characteristic points of the image to be processed according to the target points.
2. The target feature point extraction method according to claim 1, characterized by further comprising, before the acquisition of the template corresponding to the image to be processed, generating the template as follows: acquiring a plurality of sample images; selecting an initial template from a plurality of sample images, and respectively registering the initial template to the rest sample images to obtain registered images; Calculating a statistical image corresponding to the registration image; and when the similarity between the statistical image and the initial template meets the requirement, taking the statistical image as a template, otherwise, taking the statistical image as a new initial template, and returning to the step of respectively registering the initial template to the rest sample images to obtain a registered image until the similarity between the statistical image and the initial template meets the requirement.
3. The method according to claim 2, wherein the calculating the statistical image corresponding to the registration image includes: acquiring initial positions of corresponding points in each registration image; And calculating an average value of the initial positions of the corresponding points as a target position of the corresponding points, and generating the statistical image according to the target position of the corresponding points.
4. The method of claim 2, further comprising, after the generating the template: Receiving a standard feature point configuration instruction aiming at the template; And configuring corresponding standard feature points in the template according to the standard feature point configuration instruction.
5. The method according to claim 2, further comprising, after the calculating the statistical image corresponding to the registration image: calculating the distance between the statistical image and the corresponding point in the initial template; and calculating the similarity between the statistical image and the initial template according to the distances between all the corresponding points.
6. The method according to claim 2, wherein the image to be processed and the sample image are three-dimensional grid point cloud images, further comprising preprocessing the image to be processed before the registering the initial template to the remaining sample images, and/or Before the registering the template to the image to be processed, the method further comprises: The sample image is preprocessed, wherein the preprocessing comprises at least one of extracting surface point cloud, down-sampling the point cloud and normalizing the point cloud; extracting surface point clouds, namely extracting vertexes of all grids in the image to be processed and the sample image to obtain the surface point clouds; the point cloud downsampling is to divide the image to be processed into at least one processing area, and sample the point closest to the center of the processing area in the processing area as a sampling point of the processing area; The normalization aligns points in the image to be processed to the same coordinate space.
7. The method according to claim 1, wherein registering the template to the image to be processed includes: Acquiring a registration function and initializing the registration function; inputting the image to be processed and the template into the registration function to optimize parameters in the registration function; and when the variation of the parameters of the registration function after and before optimization is smaller than a preset standard, judging that the template and the image to be processed are registered, otherwise, continuously inputting the image to be processed and the template into the registration function after parameter optimization to optimize the parameters in the registration function.
8. The method for extracting target feature points according to claim 1, wherein determining the target feature points corresponding to the standard feature points in the image to be processed according to the positional relationship between the template and the standard feature points and by combining the registered positional relationship between the template and the image to be processed includes: When the standard feature points are on the surface of the template, acquiring normal vectors of the standard feature points in the template after registration with the image to be processed; when an intersection point exists between the normal vector and the registered image to be processed, calculating the distance between the intersection point and the standard feature point; when the distance between the intersection point and the standard feature point is smaller than a preset distance, the intersection point is taken as a target feature point; And when the intersection point does not exist or the distance between the intersection point and the standard feature point is larger than the preset distance, selecting a point closest to the standard feature point in the registered template from the image to be processed as a target feature point.
9. The method according to any one of claims 1 to 8, wherein the image to be processed is a bone image to be processed, the standard feature points are bone feature points, and the bone feature points include at least one of femur feature points and tibia feature points.
10. A bone data processing method, characterized in that the bone data processing method comprises: acquiring a bone image to be processed; the target feature point extraction method according to any one of claims 1 to 9, wherein the bone image to be processed is processed to obtain bone feature points; and processing the bone characteristic points according to a preset rule.
11. The bone data processing method according to claim 10, wherein the processing the bone feature points according to a preset rule includes: And calculating at least one of a femoral mechanical axis, a femoral condyle through line and a tibial mechanical axis according to the bone characteristic points.
12. The bone data processing method according to claim 10, wherein the processing the bone feature points according to a preset rule further comprises: and optimizing the bone characteristic points according to a preset rule.
13. A target feature point extraction device, characterized in that the device comprises: the data acquisition module is used for acquiring an image to be processed; The template query module is used for acquiring a template corresponding to the image to be processed and acquiring the position relation between the template and the standard characteristic points, wherein the template is an image generated based on a sample image, and the standard characteristic points are positioned in the template; the registration module is used for registering the template to the image to be processed; the target extraction module is used for determining target feature points corresponding to the standard feature points in the image to be processed according to the position relation between the template and the standard feature points and the position relation between the template and the image to be processed after being registered; the target extraction module comprises: a correlation point acquisition unit, configured to select a preset number of points from the template surface according to the standard feature points as correlation points when the standard feature points are not on the standard plate surface; a target point acquisition unit, configured to determine a target point of the association point in the registered image according to a registration relationship between the template and the image to be processed; and the third bone characteristic determining unit is used for calculating target characteristic points of the image to be processed according to the target point.
14. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 9 or 10 to 12 when the computer program is executed.
15. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 9 or 10 to 12.
16. A computer program product comprising a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method of any one of claims 1 to 9 or 10 to 12.

Description

Target feature point extraction method, device, computer equipment and storage medium Technical Field The present application relates to the field of image processing technologies, and in particular, to a method and apparatus for extracting a target feature point, a computer device, and a storage medium. Background With the development of image processing technology, the automatic extraction of skeleton anatomical feature points in CT or MR images can be widely applied to application scenes of auxiliary diagnosis and auxiliary treatment based on medical images. Meanwhile, the quality requirements of people on medical services are increasingly improved, and bone surgery precision and digitization become the trend of global medical development, so that doctors can be assisted in surgery planning through automatic extraction of feature points, surgery efficiency is improved, and patients in areas with relatively deficient medical resources can enjoy better surgery effects. In the conventional technology, the skeletal anatomy feature points are usually manually performed by experienced doctors, and because the selection of the positions of the skeletal anatomy feature points is a key step of preoperative planning, the anatomical and imaging knowledge and clinical experience of the doctors in the process are required to be high, and the manual acquisition of the feature points requires much time and effort of the doctors and is complex to operate. Disclosure of Invention In view of the foregoing, it is desirable to provide a target feature point extraction method, apparatus, computer device, and storage medium capable of automatic positioning. In a first aspect, the present application provides a target feature point extraction method, where the target feature point extraction method includes: acquiring an image to be processed; the method comprises the steps of obtaining a template corresponding to an image to be processed, and obtaining the position relation between the template and standard characteristic points, wherein the template is an image generated based on a sample image, and the standard characteristic points are positioned in the template; registering the template to the image to be processed; and determining target feature points corresponding to the standard feature points in the image to be processed according to the position relation between the template and the standard feature points and the position relation between the template and the image to be processed after registration. In one embodiment, before the obtaining the template corresponding to the image to be processed, the method further includes the steps of: acquiring a plurality of sample images; selecting an initial template from a plurality of sample images, and respectively registering the initial template to the rest sample images to obtain registered images; Calculating a statistical image corresponding to the registration image; and when the similarity between the statistical image and the initial template meets the requirement, taking the statistical image as a template, otherwise, taking the statistical image as a new initial template, and returning to the step of respectively registering the initial template to the rest sample images to obtain a registered image until the similarity between the statistical image and the initial template meets the requirement. In one embodiment, the calculating the statistical image corresponding to the registration image includes: acquiring initial positions of corresponding points in each registration image; And calculating an average value of the initial positions of the corresponding points as a target position of the corresponding points, and generating the statistical image according to the target position of the corresponding points. In one embodiment, after the generating the template, the method further includes: Receiving a standard feature point configuration instruction aiming at the template; And configuring corresponding standard feature points in the template according to the standard feature point configuration instruction. In one embodiment, after the calculating the statistical image corresponding to the registration image, the method further includes: calculating the distance between the statistical image and the corresponding point in the initial template; and calculating the similarity between the statistical image and the initial template according to the distances between all the corresponding points. In one embodiment, the image to be processed and the sample pattern are three-dimensional grid point cloud images, and the method further comprises preprocessing the preprocessed image before registering the initial template with the rest of the sample images, and/or Before the registering the template to the image to be processed, the method further comprises: The sample image is preprocessed, wherein the preprocessing comprises at least one of extracting surface point clou