CN113974828B

CN113974828B - Surgical reference scheme generation method and device

Info

Publication number: CN113974828B
Application number: CN202111169025.0A
Authority: CN
Inventors: 王坤正; 王伟; 沈丽萍; 陈汉清; 戴维焕
Original assignee: Second Affiliated Hospital Army Medical University; Hangzhou Santan Medical Technology Co Ltd
Current assignee: Second Affiliated Hospital Army Medical University; Hangzhou Santan Medical Technology Co Ltd
Priority date: 2021-09-30
Filing date: 2021-09-30
Publication date: 2024-02-09
Anticipated expiration: 2041-09-30
Also published as: CN113974828A

Abstract

The embodiment of the invention provides a method and a device for generating a surgical reference scheme, which relate to the technical field of data processing, and the method comprises the following steps: identifying key points of a preset joint part of an object body in a two-dimensional skeleton perspective image; determining a distorted part of the object body based on the position information of the key points, and determining a correction angle, an osteotomy line length and an osteotomy height for correcting bones of the distorted part; a surgical reference plan is generated with the distorted portion, the correction angle, the length of the osteotomy line, and the height of the osteotomy as reference information. The scheme provided by the embodiment of the invention is used for generating the operation reference scheme, so that reference information can be provided for doctors.

Description

Surgical reference scheme generation method and device

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for generating a surgical reference scheme.

Background

Now, before performing a tibial high-level osteotomy on a subject, a doctor obtains a two-dimensional bone perspective image, for example, an X-ray image, of the subject, and then the doctor knows the lower limb bone structure of the subject from the two-dimensional bone perspective image, thereby determining a surgical plan.

In this case, the surgical plan determined by the doctor is often affected by subjective factors such as the age of the subject, the operation experience of the doctor, and the like, resulting in low accuracy of the surgical plan. Accordingly, there is a need to provide a surgical reference protocol that provides reference information to a physician, thereby improving the accuracy of the ultimately determined surgical protocol.

Disclosure of Invention

The embodiment of the invention aims to provide a method and a device for generating a surgical reference scheme so as to provide reference information for doctors. The specific technical scheme is as follows:

in a first aspect, an embodiment of the present invention provides a method for generating a surgical reference plan, the method including:

identifying key points of a preset joint part of an object body in a two-dimensional skeleton perspective image;

determining a distorted part of the object body based on the position information of the key points, and determining a correction angle, an osteotomy line length and an osteotomy height for correcting bones of the distorted part;

and generating an operation reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information.

In a second aspect, an embodiment of the present invention provides a surgical reference plan generating apparatus, the apparatus including:

The identification module is used for identifying key points of a preset joint part of the object body in the two-dimensional skeleton perspective image;

the first determining module is used for determining a distorted part of the object body based on the position information of the key points and determining a correction angle, an osteotomy line length and an osteotomy height for correcting bones of the distorted part;

and the generation module is used for generating an operation reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information.

In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

and a processor, configured to implement the method steps described in the first aspect when executing the program stored in the memory.

In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having stored therein a computer program which, when executed by a processor, implements the method steps of the first aspect.

In a fifth aspect, embodiments of the present invention also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method steps of the first aspect described above.

The embodiment of the invention has the beneficial effects that:

from the above, when the scheme generation information provided by the embodiment of the present invention is applied, a surgical reference scheme including a distorted portion, a correction angle, an osteotomy line length, and an osteotomy height as reference information can be generated according to the two-dimensional bone perspective image of the subject, and a doctor can refer to the reference information included in the surgical reference scheme, thereby determining the surgical scheme. Therefore, the surgical reference scheme generation scheme provided by the embodiment of the invention can provide reference information for doctors.

Drawings

In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other embodiments may be obtained according to these drawings to those skilled in the art.

FIG. 1a is a schematic flow chart of a first method for generating a surgical reference plan according to an embodiment of the present invention;

FIG. 1b is a two-dimensional bone perspective image of a subject's hip joint according to an embodiment of the present invention;

FIG. 2 is a flow chart of a second method for generating a surgical reference plan according to an embodiment of the present invention;

FIG. 3a is a two-dimensional bone perspective image of a lower extremity bone structure of a subject in accordance with an embodiment of the present invention;

FIG. 3b is a schematic diagram illustrating the location of key points in a first two-dimensional bone perspective image according to an embodiment of the present invention;

FIG. 4a is a flow chart of a third method for generating a surgical reference plan according to an embodiment of the present invention;

FIG. 4b is a schematic diagram illustrating the location of key points in a second two-dimensional bone perspective image according to an embodiment of the present invention;

FIG. 5a is a flow chart of a fourth method for generating surgical reference plans according to an embodiment of the invention;

FIG. 5b is a schematic view illustrating the location of key points in a third two-dimensional bone perspective image according to an embodiment of the present invention;

FIG. 6 is a flow chart of a fifth method for generating surgical reference plans according to an embodiment of the invention;

FIG. 7a is a flowchart of a sixth surgical reference plan generation method according to an embodiment of the present invention;

FIG. 7b is a schematic diagram illustrating the location of key points in a fourth two-dimensional bone perspective image according to an embodiment of the present invention;

FIG. 8 is a schematic structural view of a first surgical reference plan generating device according to an embodiment of the present invention;

FIG. 9 is a schematic structural view of a second surgical reference plan generating device according to an embodiment of the present invention;

FIG. 10 is a schematic structural view of a third surgical reference plan generating device according to an embodiment of the present invention;

fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by the person skilled in the art based on the present invention are included in the scope of protection of the present invention.

Referring to fig. 1a, a flow diagram of a first surgical reference plan generation method is provided, the method comprising the following steps S101-S103.

Step S101: and identifying key points of a preset joint part of the object body in the two-dimensional skeleton perspective image.

The object may be a human body, an animal body, or the like.

The two-dimensional bone fluoroscopic image may be an X-ray image.

Before the tibial high-level osteotomy is performed on the subject, in order to enable a doctor to better observe the bone structure of the subject, the bone of the subject displayed by the two-dimensional bone perspective image may be a lower limb bone of the subject, so the two-dimensional bone perspective image may be a full-length X-ray image of the lower limb force line when the subject is in a loading position.

The preset joint part can be a hip joint, a knee joint, an ankle joint or the like.

The key points are pixel points positioned in a preset joint part of the object body in the two-dimensional skeleton perspective image.

Specifically, since the positions of the joint portions of the object body in the two-dimensional bone perspective image are generally unchanged, the region where the preset joint portions are located may be first determined in the two-dimensional bone perspective image, and then the key points of the preset joint portions of the object body may be identified in the region based on the shape features of different bones in the preset joint portions.

For example, fig. 1b is a two-dimensional bone perspective image of a hip joint of a subject, and since the hip joint includes a femoral head, and the femoral head is an approximately circular region in the image, in fig. 1b, a region where the femoral head is located may be determined by using a rounding method, such as a circular region shown by a dotted line in fig. 1b, and a center of the circular region is taken as a key point of the hip joint of the subject.

In addition, the feature extraction can be performed on the two-dimensional skeleton perspective image, and key points of the preset joint parts of the object body in the two-dimensional skeleton perspective image can be determined.

The feature extraction of the two-dimensional bone perspective image can be realized based on a trained deep neural network for identifying key points of preset joint parts of the object body in the two-dimensional bone perspective image.

When training the deep neural network, the sample data may be divided into training data, verification data, and test data. The training data is used for training the deep neural network, the verification data is used for adjusting super parameters of the deep neural network, such as learning rate, regularization parameters and the like, and the test data is used for testing the network performance of the deep neural network.

Before the key points in the two-dimensional skeleton perspective image are identified by using the depth neural network, the two-dimensional skeleton perspective image can be preprocessed, and the specific operation of preprocessing can be to adjust the gray value of a pixel point with the gray value larger than a first gray threshold value in the two-dimensional skeleton perspective image to be a first preset gray value, or adjust the gray value of a pixel point with the gray value smaller than a second gray threshold value to be a second preset gray value, or adjust the size of the two-dimensional skeleton perspective image to be the preset image size, or increase noise in the two-dimensional skeleton perspective image, so that the image content is richer, and the like. In addition, the two-dimensional skeleton perspective image can be subjected to image normalization processing so as to accelerate the convergence speed of the deep neural network.

In one embodiment of the present invention, the deep neural network may be a res net (residual network), and the network layer number of the deep neural network may be 102 layers.

Step S102: and determining a distorted part of the object body based on the position information of the key points, and determining a correction angle, an osteotomy line length and an osteotomy height for correcting bones of the distorted part.

The position information of the key points, that is, the position information of the key points in the two-dimensional bone perspective image. Based on the location information of the keypoints, the relative locations between the different keypoints can be obtained.

Specifically, the distorted portion of the subject body may be determined according to the shape of the bone of the subject body, and if the bone of the subject body has a larger difference in shape than the bone under normal conditions, it may be determined that the bone of the subject body is distorted, and the distorted bone portion is the distorted portion.

In the above two-dimensional bone perspective image, since the key points of the preset joint portion of the object body may be pixel points in the bone included in the preset joint portion, the bone of the object body may be represented by the key points in the bone, and the shape feature of the bone of the object body may be represented by the relative positional relationship among the plurality of key points in the bone. Therefore, the specific parameters can be obtained by determining the relative positions of the different key points and based on the relative positions of the different key points, for example, the specific parameters can be the distances between the different key points or the angles obtained by using the different key points, and whether the parameter values of the specific parameters are in the preset parameter value range is judged, so that whether the bones corresponding to the key points are distorted or not is determined, and further the distortion part of the object body is determined. If the parameter value of the specific parameter is not in the preset parameter value range, determining that the skeleton corresponding to the key point is distorted.

The distortion site of the subject may be the tibia or femur. Therefore, whether the distorted part of the object body is the tibia can be determined through the relative position relation between the key points of the tibia in the two-dimensional skeleton perspective image, and whether the distorted part of the object body is the femur can be determined through the relative position relation between the key points of the femur.

In this case, after the distorted portion of the subject body is determined, the correction angle, the length of the osteotomy line, and the osteotomy height for correcting the distorted portion of the bone may be determined based on the positional information of the key points in the distorted portion of the bone.

In this case, the correction angle, the length of the osteotomy line, and the height of the osteotomy may be determined by the steps S102A-S102C in the embodiment shown in fig. 2, which will not be described in detail herein.

In another case, since the distorted portion of the subject may be a tibia or a femur, the distorted portion of the subject may be assumed to be a tibia, and the first correction angle, the first osteotomy length, and the first osteotomy height for correcting the tibia may be determined based on the positional information of the key point in the tibia. Then, assuming that the distorted part of the object body is a femur, and determining a second correction angle, a second osteotomy height and a second osteotomy height for correcting the femur based on the position information of the key points in the femur.

In this case, since the distortion location of the subject is assumed to be known, the first correction angle, the first osteotomy length, the first osteotomy height, the second correction angle, the second osteotomy height, and the second osteotomy height may be determined by steps S102A to S102C in the embodiment shown in fig. 2, which will not be described in detail herein.

Further, the first correction angle, the first osteotomy length and the first osteotomy height may be used as a first set of parameters, the second correction angle, the second osteotomy length and the second osteotomy height may be used as a second set of parameters, and a set of parameters may be selected between the two sets of parameters to be used as the correction angle, the osteotomy length and the osteotomy height for correcting the bone at the distorted portion.

For example, one of the two sets of parameters having a large correction angle parameter value may be selected, one of the two sets of parameters having a large length parameter value may be selected, and one of the two sets of parameters having a large height parameter value may be selected.

Step S103: a surgical reference plan is generated with the distorted portion, the correction angle, the length of the osteotomy line, and the height of the osteotomy as reference information.

The distortion part, the correction angle, the length of the osteotomy line and the osteotomy height obtained in the embodiment of the invention can be used as reference information to provide reference for doctors. The doctor can obtain the reference information when viewing the surgical reference plan.

When a doctor determines a surgical plan, the doctor can directly use the reference information contained in the surgical reference plan as information in the determined surgical plan, and can also adjust the reference information according to own surgical experience on the basis of the reference information, so as to determine the surgical plan.

In an embodiment of the present invention, referring to fig. 2, a flow chart of a second method for generating a surgical reference plan is provided, and in this embodiment, the step S102 may be implemented by the following steps S102A-S102C, compared with the embodiment shown in fig. 1.

Step S102A: and determining the distortion part of the object body based on the position information of the key points.

Specifically, the step is similar to the step S102, and the distortion part of the object body may be determined based on the position information of the key point, which is not described herein.

Step S102B: and obtaining target key points for bone correction from the key points according to the distortion parts.

The key points identified in step S101 may be a plurality of key points of a plurality of preset joint positions, however, the distorted positions of the subject are different, and the bones to be corrected are different, so that the correction angle, the osteotomy height and the osteotomy length may be determined only by the position information of a part of the key points, and therefore, the target key points for performing the skeletal correction in the key points need to be determined according to the distorted positions of the subject.

Specifically, in the case where the distorted portion is a femur, the target key point may be determined by step S102B1 in the embodiment shown in fig. 4a, which is not described in detail herein.

In the case where the distorted portion is the tibia, the target key point may be determined by step S102B2 in the embodiment shown in fig. 5a, which is not described in detail herein.

Step S102C: based on the position information of the target key points, the correction angle, the length of the osteotomy line and the osteotomy height for correcting the bones of the distorted part are determined.

When a doctor performs a tibial high-level osteotomy on a subject, the doctor generally needs to cut and saw bones of a distorted part of the subject, a notch formed after cutting and sawing can be called a bone notch, and then the bone notch is spread by a certain angle so as to correct the distorted part. Wherein, the angle that above-mentioned bone breach struts is correction angle, and the degree of depth of above-mentioned bone breach, that is the degree of depth of cutting the saw is osteotomy line length. Since the bone is sawn, two sections can be formed, the maximum distance between the two sections, i.e. the osteotomy height.

Under the condition, the position of a target key point of a preset joint part of the postoperative object body in the two-dimensional skeleton perspective image can be preset, and the correction angle, the length of an osteotomy line and the osteotomy height for correcting the skeleton of the distorted part are determined according to the position information of the target key point before the operation and the position information of the target key point after the operation.

Alternatively, in the case where the distorted portion is a femur, the correction angle, the length of the osteotomy line, and the height of the osteotomy may be determined by steps S102C1-S102C5 in the embodiment shown in fig. 4a, which will not be described in detail herein.

In the case where the distorted portion is a tibia, the correction angle, the length of the osteotomy line, and the height of the osteotomy may be determined by steps S102C6 to S102C10 in the embodiment shown in fig. 5a, which will not be described in detail herein.

From the above, in the solution provided by the embodiment of the present invention, firstly, the distorted portion of the object is determined based on the position information of the key points, then, the target key point among the key points is determined according to the distorted portion, and finally, the correction angle, the osteotomy length and the osteotomy height for correcting the bone of the distorted portion are determined based on the position information of the target key point. Because the key points in the two-dimensional skeleton perspective image correspond to the preset joint positions of the object body, the position information of the key points also reflects the position information of the preset joint positions relative to the lower limb bones of the object body, so that the distortion positions of the object body can be accurately determined based on the position information of the key points, and similarly, the correction angles, the osteotomy line lengths and the osteotomy heights for correcting the bones of the distortion positions can be accurately determined according to the position information of the target key points determined by the distortion positions, so that the reference information in the final operation reference scheme can be more accurate.

In one embodiment of the present invention, referring to fig. 3a, a two-dimensional bone perspective image of a lower limb bone structure of a subject is provided, and as can be seen from fig. 3a, points A1-a 12 and points B1-B12 are all key points of preset joint positions of the subject, and points A1-a 12 and points B1-B12 are symmetrical with each other, and the difference is that points A1-a 12 correspond to preset joint positions in a right leg of the subject, and points B1-B12 correspond to preset joint positions in a left leg of the subject.

Taking a point A1-a 12 as an example, a point A1 corresponds to the femoral head center of the object, a point A2 corresponds to the hinge position of the object, a point A3 and a point A5 respectively correspond to the upper two end points of the knee joint of the object, a point A4 corresponds to the knee joint center of the object, a point A6 and a point A8 respectively correspond to the lower two end points of the knee joint of the object, a point A7 corresponds to the lower limb center of the object, a point A9 corresponds to any position in the tibia of the object, which is 10mm to 15mm away from the tibia lateral platform, a point A10 corresponds to the ankle joint center of the object, a point A11 corresponds to the position in the tibia of the object, which is 30mm away from the tibia medial platform, and a point A12 corresponds to the position in the femur of the object, which is 30mm away from the medial platform.

The above 10mm, 15mm and 30mm are all lengths in a practical scene. In addition, the numerical values in mm or cm in the application document are all lengths in an actual scene, and the lengths in pixel points are all lengths in an image.

In one embodiment of the present invention, a first straight line where a first key point corresponding to a femoral head center of a subject and a second key point corresponding to a knee joint center of the subject are located in key points may be determined, a third key point corresponding to two end points on the knee joint upper side of the subject and a second straight line where a fourth key point corresponding to the subject are located in key points may be determined, and whether the angle of the first included angle is an angle in a first preset angle range may be determined, if not, the distorted portion of the subject is a femur, where the first included angle is: an included angle formed by the first straight line and the second straight line and close to the outer side of the thigh of the subject body.

The first predetermined angle range may be 84 ° -90 °.

In the above two-dimensional bone perspective image, since the preset joint portion of the subject may be a joint portion in a lower limb of the subject, the identified key point may be a key point of the joint portion of the lower limb of the subject, and the region where the two legs of the subject are located may be determined according to the positional information of the key point. For example, in fig. 3a, the region where the right leg of the subject is located can be determined based on the positional information of points A1 to a12, and the region where the left leg of the subject is located can be determined based on the positional information of points B1 to B12. Therefore, the thigh outside region, the thigh inside region, the shank outside region, and the shank inside region in the two-dimensional bone perspective image can be specified based on the regions where the two legs of the subject are located.

Referring to fig. 3b, a schematic representation of the location of key points in a first two-dimensional bone perspective image is shown. In fig. 3b, (1) in fig. 3b is a schematic diagram of the positions of some of the keypoints in the two-dimensional bone perspective image, (2) in fig. 3b is a schematic diagram of the relative positions of the keypoints in the femur of the subject, and (3) in fig. 3b is a schematic diagram of the relative positions of the keypoints in the tibia of the subject. The first key point is a point A1, the second key point is a point A4, the first straight line is L1, the first key point A1 and the second key point A4 are located on a first straight line L1, the third key point and the fourth key point are a point A3 and a point A5 respectively, the second straight line is L2, the third key point A3 and the fourth key point A5 are located on a second straight line L2, the first included angle is D1, and the first included angle D1 is an included angle formed by the first straight line L1 and the second straight line L2.

When the angle of D1 belongs to the angle in the first preset angle range, the first included angle is within the normal range, and at this time, the femur of the subject can be regarded as undistorted; when the angle D1 does not belong to the angle in the first preset angle range, the first included angle is out of the normal range, and at this time, the femur of the subject can be regarded as distorted, and the distorted part of the subject is determined to be the femur.

In another embodiment of the present invention, a third straight line where a fifth key point corresponding to a midpoint of a lower limb of the object and a sixth key point corresponding to an ankle center of the object are located in the key points may be determined, a seventh key point corresponding to two endpoints of a knee joint of the object and a fourth straight line where an eighth key point corresponding to the two endpoints of the knee joint of the object are located in the key points may be determined, and whether the angle of the second included angle is an angle in a second preset angle range may be determined, if not, the distorted portion of the object is a tibia, where the second included angle is: an included angle formed by the third straight line and the fourth straight line and close to the inner side of the lower leg of the object body.

The second preset angle range may be the same as the first preset angle range, or may be different from the first preset angle range.

In fig. 3b, the fifth key point is a point A7, the sixth key point is a point a10, the third straight line is L3, the fifth key point A7 and the sixth key point a10 are located on the third straight line L3, the seventh key point and the eighth key point are a point A6 and a point A8, respectively, the fourth straight line is L4, the seventh key point A6 and the eighth key point A8 are located on the fourth straight line L4, the second included angle is D2, and the second included angle D2 is an included angle formed by the third straight line L3 and the fourth straight line L4.

When the angle of D2 belongs to the angle in the second preset angle range, the second included angle is within the normal range, and at this time, the tibia of the subject can be regarded as undistorted; when the angle of D2 does not belong to the angle in the second preset angle range, it is indicated that the second included angle is out of the normal range, and at this time, the tibia of the subject can be regarded as distorted, and the distorted portion of the subject is determined to be the tibia.

In one embodiment of the present invention, the first straight line, the second straight line, the third straight line, and the fourth straight line may be determined, and whether the angle of the first included angle is an angle in a first preset angle range or not is determined, and whether the angle of the second included angle is an angle in a second preset angle range or not is determined, so as to determine the distortion portion of the object body.

If the angle of the first included angle belongs to the angle in the first preset angle range and the angle of the second included angle does not belong to the angle in the second preset angle range, determining that the distorted part of the object body is the tibia; if the angle of the first included angle does not belong to the angle in the first preset angle range and the angle of the second included angle belongs to the angle in the second preset angle range, determining that the distorted part of the object body is femur; if the angle of the first included angle does not belong to the angle in the first preset angle range and the angle of the second included angle does not belong to the angle in the second preset angle range, the distorted part of the object body can be determined to be tibia and femur.

From the above, in the solution provided by the embodiment of the present invention, the first angle or the second angle can be formed according to different straight lines where different key points are located, and by respectively determining whether the angle of the first angle is the angle in the first preset angle range or not, and whether the angle of the second angle is the angle in the second preset angle range, the distortion part of the object can be determined.

In an embodiment of the present invention, referring to fig. 4a, a flow chart of a third method for generating a surgical reference plan is provided, and in comparison with the embodiment shown in fig. 2, in this embodiment, in the case that the distorted portion is a femur, the above step S102B may be implemented by the following step S102B 1.

Step S102B1: and determining a first key point corresponding to the femoral head center of the object body, a fifth key point corresponding to the lower limb middle point of the object body, a sixth key point corresponding to the ankle joint center of the object body, a ninth key point corresponding to the hinge position of the object body and a tenth key point corresponding to the first preset position in the femur of the object body as target key points for bone correction.

The first predetermined position may be a position in the femur 30mm from the medial femoral plateau.

In fig. 3a, the first key point is a point A1, the fifth key point is a point A7, the sixth key point is a point a10, the ninth key point is a point A2, and the tenth key point is a point a12.

In the embodiment of the present invention, the above step S102C may also be implemented by the following steps S102C1 to S102C 5.

Referring to fig. 4b, a schematic diagram of the positions of the keypoints in the second two-dimensional bone fluoroscopic image is provided, wherein (1) in fig. 4b is a schematic diagram of the positions of the target keypoints in the first two-dimensional bone fluoroscopic image, and (2) in fig. 4b is a schematic diagram of the relative positions of the first target keypoints. Steps S102C1-S102C5 will be described below in connection with fig. 4 b.

Step S102C1: and determining a fifth straight line where the fifth key point and the sixth key point are located, and determining a first line segment taking the first key point and the ninth key point as endpoints.

In fig. 4b, the fifth straight line is L5, the fifth key point A7 and the sixth key point a10 are located on the fifth straight line L5, the first line segment is X1, and two end points of the first line segment X1 are the first key point A1 and the ninth key point A2, respectively.

Step S102C2: and determining a second line segment with the same length as the first line segment, wherein one end point of the second line segment is a ninth key point, the other end point of the second line segment is positioned on a fifth straight line, and the second line segment is close to the inner thigh of the object body compared with the first line segment.

In fig. 4b, the second line segment is X2, and two end points of the second line segment X2 are a ninth key point A2 and a point AC1 located on the fifth straight line L5, respectively.

In one embodiment of the present invention, the ninth key point A2 is taken as an origin, and the first line segment X1 is rotated in a direction close to the inner thigh of the subject until the other end point of the first line segment X1, that is, the first key point A1 is rotated to the fifth line L5, so as to determine that the rotated first line segment X1 is the second line segment X2.

Step S102C3: and determining the angle of the included angle formed by the first line segment and the second line segment as a correction angle.

In fig. 4b, the correction angle D3 is D3, and the correction angle D3 is an angle formed by the first line segment X1 and the second line segment X2.

Step S102C4: according to the distance between the ninth key point and the tenth key point and the preset proportion, determining the length of an osteotomy line for correcting the bone of the distorted part, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional bone fluoroscopic image and the unit length in the actual scene.

Since the length is generally expressed by the number of pixels in the image, the unit length in the two-dimensional bone fluoroscopic image may be expressed as the number of pixels in the two-dimensional bone fluoroscopic image, and the preset ratio may be expressed as a ratio between the number of pixels in the two-dimensional bone fluoroscopic image and the unit length in the actual scene.

For example, if the preset ratio is 300:1, the number of pixels occupied by the same object in the two-dimensional skeleton perspective image is 300, and the length of the same object in the actual scene is 1cm.

In fig. 4b, the distance between the ninth key point A2 and the tenth key point a12 may be determined, and the distance may be multiplied by the above predetermined ratio, where the result of the multiplication is the length of the osteotomy line for correcting the bone at the distorted portion.

Step S102C5: based on the correction angle and the osteotomy line length, determining the osteotomy height for correcting the bone of the distorted part according to the preset corresponding relation among the correction angle, the osteotomy line length and the osteotomy height.

The preset correspondence between the correction angle, the length of the osteotomy line, and the osteotomy height can be shown in table 1 below.

TABLE 1

4°

5°

6°

7°

8°

9°

10°

11°

12°

50mm

3mm

4mm

5mm

6mm

7mm

8mm

9mm

10mm

55mm

4mm

5mm

6mm

7mm

8mm

9mm

10mm

11mm

60mm

4mm

5mm

6mm

7mm

8mm

9mm

10mm

11mm

12mm

65mm

5mm

6mm

7mm

8mm

9mm

10mm

11mm

12mm

14mm

70mm

5mm

6mm

7mm

8mm

10mm

11mm

12mm

13mm

15mm

75mm

5mm

6mm

8mm

9mm

10mm

12mm

13mm

14mm

16mm

80mm

5mm

6mm

8mm

9mm

10mm

12mm

13mm

14mm

16mm

The parameters in the first row and the first column in table 1 are correction angles, and the parameters in the first column are osteotomy lengths, and the parameters in the other rows and the other columns are osteotomy heights.

By referring to table 1, the osteotomy height corresponding to the correction angle and the osteotomy line length can be determined.

For example, if the correction angle is 6 °, the osteotomy length is 65mm, the osteotomy height can be determined to be 7mm.

From the above, in the solution provided in the embodiment of the present invention, in the case where the distorted portion is a femur, the first key point, the fifth key point, the sixth key point, the ninth key point, and the tenth key point may be determined as target key points, and the fifth straight line, the first line segment, and the second line segment may be determined based on the target key points, so as to determine the correction angle, and according to the distance between the ninth key point and the tenth key point and the preset ratio, the length of the osteotomy line may be obtained, and finally, according to the preset correspondence between the correction angle, the length of the osteotomy line, and the osteotomy height, the osteotomy height may be obtained. Therefore, the correction angle, the length of the osteotomy line and the osteotomy height can be obtained only by utilizing the position information, the preset proportion and the preset corresponding relation of the target key points, and the distortion part of the object body is determined, so that the target key points are determined.

In an embodiment of the present invention, referring to fig. 5a, a flow chart of a fourth method for generating a surgical reference plan is provided, and in comparison with the embodiment shown in fig. 2, in this embodiment, in the case that the distorted portion is a tibia, the following step S102B2 may be implemented.

Step S102B2: and determining a first key point corresponding to the femoral head center of the object, a second key point corresponding to the knee joint center of the object, a sixth key point corresponding to the ankle joint center of the object, an eleventh key point corresponding to the second preset position in the tibia of the object and a twelfth key point corresponding to the third preset position in the tibia of the object as target key points for bone correction.

The second predetermined position may be any position within a range of positions from 10mm to 15mm from the lateral tibial plateau.

The third predetermined position may be a position 30mm from the medial tibial plateau.

In fig. 3a, the first key point is a point A1, the second key point is a point A4, the sixth key point is a point a10, the eleventh key point is a point A9, and the twelfth key point is a point a11.

In the embodiment of the present invention, the above step S102C may also be implemented by the following steps S102C6 to S102C 10.

Referring to fig. 5b, a schematic diagram of the positions of the key points in the third two-dimensional bone perspective image is provided, wherein (1) in fig. 5b is a schematic diagram of the positions of the target key points in the second two-dimensional bone perspective image, and (2) in fig. 5b is a schematic diagram of the relative positions of the second target key points. Steps S102C6-S102C10 will be described below in connection with fig. 5 b.

Step S102C6: and determining a sixth straight line where the first key point and the second key point are located, and determining a third line segment taking the sixth key point and the eleventh key point as end points.

In fig. 5b, the sixth straight line is L6, the first key point A1 and the second key point A4 are located on the sixth straight line L6, the first key point A1 is not shown in fig. 5b (1), the third line segment is X3, and both end points of the third line segment X3 are the sixth key point a10 and the eleventh key point A9, respectively.

Step S102C7: and determining a fourth line segment with the same length as the third line segment, wherein one end point of the fourth line segment is an eleventh key point, the other end point of the fourth line segment is positioned on a sixth straight line, and the fourth line segment is close to the outer side of the lower leg of the object body compared with the third line segment.

In fig. 5b, the fourth line segment X4 is the eleventh key point A9 and the point AC2 on the sixth straight line L6 are the two end points of the fourth line segment X4.

In one embodiment of the present invention, the eleventh key point A9 may be used as an origin, and the third segment X3 may be rotated in a direction close to the outer side of the lower leg of the subject until the other end point of the third segment X3, that is, the sixth key point a10 rotates onto the sixth straight line L6, so as to determine that the rotated third segment X3 is the fourth segment X4.

Step S102C8: and determining the angle of the included angle formed by the third line segment and the fourth line segment as a correction angle.

In fig. 5b, the correction angle D4 is D4, and the correction angle D4 is an included angle formed by the third line segment X3 and the fourth line segment X4.

Step S102C9: determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the eleventh key point and the twelfth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional bone fluoroscopic image and the unit length in the actual scene.

The difference between this step and the step S102C4 is that the distance between the eleventh and twelfth key points is used in this step, and the distance between the ninth and tenth key points is used in the step S102C4, which is not described here again.

Step S102C10: based on the correction angle and the osteotomy line length, determining the osteotomy height for correcting the bone of the distorted part according to the preset corresponding relation among the correction angle, the osteotomy line length and the osteotomy height.

This step is similar to step S102C5 described above, and will not be described again here.

From the above, in the solution provided in the embodiment of the present invention, in the case that the distorted portion is a tibia, the first key point, the second key point, the sixth key point, the eleventh key point and the twelfth key point may be determined as target key points, and the sixth straight line, the third line segment and the fourth line segment may be determined based on the target key points, so as to determine the correction angle, and according to the distance between the eleventh key point and the twelfth key point and the preset proportion, the length of the osteotomy line may be obtained, and finally according to the correction angle, the preset correspondence between the length of the osteotomy line and the osteotomy height, the osteotomy height may be obtained. Therefore, the correction angle, the length of the osteotomy line and the osteotomy height can be obtained only by utilizing the position information, the preset proportion and the preset corresponding relation of the target key points, and the distortion part of the object body is determined, so that the target key points are determined.

In an embodiment of the present invention, referring to fig. 6, a flowchart of a fifth method for generating a surgical reference plan is provided, and in this embodiment, after the key points of the preset joint portion of the object in the two-dimensional bone perspective image are identified in step S101, the following step S104 is further included, compared with the embodiment shown in fig. 1.

Step S104: based on the position information of the key points, the distortion type of the object body is determined.

Specifically, the type of distortion of the subject may be gonal inversion or gonal valgus. The type of distortion of the subject can be determined by determining the relative position and distance between the subject knee joint center and a mechanical axis that is a line of the subject femoral head center and ankle joint center.

In the two-dimensional bone perspective image, the key points of the preset joint part of the object body can be a first pixel point corresponding to the center of the knee joint of the object body, a second pixel point corresponding to the center of the femoral head of the object body and a third pixel point corresponding to the center of the ankle joint of the object body, so that the mechanical axis can be determined in the two-dimensional bone perspective image based on the position information of the key points, and the relative position and distance between the center of the knee joint of the object body and the mechanical axis can be determined, thereby determining the distortion type of the object body.

In the embodiment of the present invention, the above step S103 may also be implemented by the following step S103A.

Step S103A: a surgical reference plan is generated with the type of distortion, the distortion location, the correction angle, the length of the osteotomy line, and the height of the osteotomy as reference information.

The distortion type, the distortion part, the correction angle, the length of the osteotomy line and the osteotomy height obtained in the embodiment of the invention can be used as reference information to provide reference for doctors. The doctor can obtain the reference information when viewing the surgical reference plan.

From the above, in the solution provided by the embodiment of the present invention, the distortion type of the object body can be determined, and a surgical reference solution using the distortion type, the distortion part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information can be generated. Compared with the surgical reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the height of the osteotomy as the reference information, the surgical reference scheme in the scheme increases the distortion type as the reference information, so that the generated surgical reference scheme is more detailed, and more reference information can be provided for doctors.

In an embodiment of the present invention, referring to fig. 7a, a flowchart of a sixth surgical reference plan generating method is provided, and in comparison with the embodiment shown in fig. 6, in this embodiment, the step S104 may be implemented by the following steps S104A-S104E.

Referring to fig. 7b, a schematic diagram of the positions of the key points in the fourth two-dimensional bone perspective image is provided, in fig. 7b, (1) in fig. 7b is a two-dimensional bone perspective image of the knee valgus of the subject, (2) in fig. 7b is a two-dimensional bone perspective image of the knee valgus of the subject, and (3) in fig. 7b is a schematic diagram of the relative positions of the key points in the two-dimensional bone perspective image. Steps S104A-S104E will be described below in connection with fig. 7 b.

Step S104A: determining a seventh straight line where a first key point corresponding to the femoral head center of the object and a sixth key point corresponding to the ankle center of the object are located, if the second key point corresponding to the knee center of the object is closer to the inner side of the knee than the seventh straight line, executing step S104B, and if the second key point is closer to the outer side of the knee than the seventh straight line, executing step S104D.

Since the knee center, the femoral head center, and the ankle center of the subject are normally located on the same straight line, if the knee center of the subject is located closer to the inside of the knee than the mechanical axis, the distortion type of the subject may be genu varum, and if the knee center of the subject is located closer to the outside of the knee than the mechanical axis, the distortion type of the subject may be genu varum.

In fig. 7b, the seventh straight line is L7, that is, the mechanical axis of the object, and the first key point A1 and the sixth key point a10 are located on the seventh straight line L7. If the second key point A4 is located closer to the inner side of the knee joint than the seventh straight line L7, it is indicated that the distortion type of the object may be valgus, and step S104B is performed, and if the second key point A4 is located closer to the outer side of the knee joint than the seventh straight line L7, it is indicated that the distortion type of the object may be valgus, and step S104D is performed.

Step S104B: and judging whether the distance between the second key point and the seventh straight line is larger than the first preset distance, and if so, executing step S104C.

The first preset distance may be 10mm.

Since bones of different subject bodies are different, it is considered that if the knee joint center, the femoral head center and the ankle joint center of the subject body are approximately on the same straight line, the distortion degree of the lower limb bones of the subject body is light, the influence on the subject body is small, and the tibial high bone cutting operation can be omitted, that is, if the distance between the second key point and the seventh straight line is smaller than the first preset distance, the distortion degree of the lower limb bones of the subject body is light, and at this time, the distortion part of the subject body does not need to be determined. If the distance between the second key point and the seventh straight line is greater than the first preset distance, the distortion degree of the lower limb skeleton of the object body is relatively high, and at this time, the distortion part of the object body needs to be determined.

Step S104C: the type of distortion of the object is determined as knee valgus.

And if the distance between the second key point and the seventh straight line is larger than the first preset distance and the second key point is close to the inner side of the knee joint compared with the seventh straight line, determining that the distortion type of the object body is knee valgus.

Step S104D: and judging whether the distance between the second key point and the seventh straight line is larger than a second preset distance, and if so, executing step S104E.

The second preset distance may be 15mm.

The difference between this step and the step S104B is that the relative positions between the second key point and the seventh line are different, and the preset distances are different, which will not be described here.

Step S104E: the type of distortion of the subject is determined to be varus.

And if the distance between the second key point and the seventh straight line is larger than the second preset distance and the second key point is close to the outer side of the knee joint compared with the seventh straight line, determining that the distortion type of the object body is knee varus.

In one embodiment of the present invention, a fifth line segment having the second keypoint and the first keypoint as endpoints may also be determined, and a sixth line segment having the second keypoint and the sixth keypoint as endpoints may also be determined. And judging whether the angle of a fifth included angle formed by the fifth line segment and the sixth line segment and close to the outer side of the thigh is larger than 180 degrees.

In fig. 7b, the fifth line segment X5 has two end points of the fifth line segment X5 that are the first key point A1 and the second key point A4, the sixth line segment X6 has two end points of the sixth line segment X6 that are the second key point A4 and the sixth key point a10, and the fifth included angle is D5.

If the angle of the fifth included angle is larger than 180 degrees, judging whether the angle of the fifth included angle is in a first preset angle range, and if not, determining that the distortion type of the object body is gonyectyposis.

If the angle of the fifth included angle is smaller than or equal to 180 degrees, judging whether the angle of the fifth included angle is in a second preset angle range, and if not, determining that the distortion type of the object body is the knee valgus.

From the above, in the scheme provided by the embodiment of the invention, the distortion type of the object can be determined by judging the relative position and the distance between the second key point and the seventh straight line, and compared with the case that the doctor judges the distortion type according to experience, the method and the device for judging the distortion type of the object have higher speed, so that the efficiency of generating the operation reference scheme can be improved by applying the scheme provided by the embodiment of the invention.

Corresponding to the method for generating the surgical reference scheme, the embodiment of the invention also provides a device for generating the surgical reference scheme.

Referring to fig. 8, a schematic structural view of a first surgical reference plan generating device is provided, the device comprising:

the identification module 801 is used for identifying key points of a preset joint part of the object body in the two-dimensional skeleton perspective image;

A first determining module 802, configured to determine a distorted portion of the object based on the position information of the key point, and determine a correction angle, an osteotomy line length, and an osteotomy height for correcting a bone of the distorted portion;

a generating module 803 is configured to generate a surgical reference plan using the distorted portion, the correction angle, the length of the osteotomy line, and the height of the osteotomy line as reference information.

In an embodiment of the present invention, referring to fig. 9, a schematic structural diagram of a second surgical reference plan generating device is provided, and in this embodiment, compared to the embodiment shown in fig. 8, the first determining module 802 includes:

a first determining submodule 802A, configured to determine a distortion location of the object body based on the position information of the key point;

An obtaining submodule 802B, configured to obtain, according to the distortion location, a target key point for performing bone correction from the key points;

a second determining submodule 802C is configured to determine, based on the position information of the target key point, a correction angle, an osteotomy line length, and an osteotomy height for correcting the bone of the distorted portion.

In one embodiment of the present invention, the first determining submodule 802A is specifically configured to:

determining a first straight line of a first key point corresponding to the femoral head center of the object and a second key point corresponding to the knee joint center of the object in the key points, determining a third key point corresponding to the upper two endpoints of the knee joint of the object and a second straight line of a fourth key point corresponding to the upper two endpoints of the knee joint of the object in the key points, judging whether the angle of a first included angle is in a first preset angle range, if not, determining the distorted part of the object as femur, wherein the first included angle is: an included angle formed by the first straight line and the second straight line and close to the outer side of the thigh of the subject;

and/or

Determining a third straight line where a fifth key point corresponding to a middle point of a lower limb of the object and a sixth key point corresponding to an ankle joint center of the object are located in the key points, determining a seventh key point corresponding to two end points of the lower side of a knee joint of the object and a fourth straight line where an eighth key point corresponding to the key points are located, respectively, and judging whether the angle of a second included angle is an angle in a second preset angle range, if not, determining that the distorted part of the object is a tibia, wherein the second included angle is: and an included angle formed by the third straight line and the fourth straight line and close to the inner side of the lower leg of the object body.

In one embodiment of the present invention, in the case where the distortion location is a femur, the obtaining submodule 802B is specifically configured to:

determining a first key point corresponding to the femoral head center of the object, a fifth key point corresponding to the lower limb center of the object, a sixth key point corresponding to the ankle joint center of the object, a ninth key point corresponding to the hinge position of the object and a tenth key point corresponding to a first preset position in the femur of the object as target key points for bone correction;

The second determining submodule 802C is specifically configured to:

determining a fifth straight line where the fifth key point and the sixth key point are located, and determining a first line segment taking the first key point and the ninth key point as endpoints;

determining a second line segment with the same length as the first line segment, wherein one end point of the second line segment is the ninth key point, and the other end point of the second line segment is positioned on the fifth straight line, and the second line segment is close to the inner side of the thigh of the object body compared with the first line segment;

determining an angle of an included angle formed by the first line segment and the second line segment as a correction angle;

determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the ninth key point and the tenth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene;

based on the correction angle and the length of the osteotomy line, determining the osteotomy height for correcting the bone of the distorted part according to the preset corresponding relation among the correction angle, the length of the osteotomy line and the osteotomy height.

In one embodiment of the present invention, in the case where the distortion location is a tibia, the obtaining submodule 802B is specifically configured to:

Determining a first key point corresponding to the femoral head center of the object, a second key point corresponding to the knee joint center of the object, a sixth key point corresponding to the ankle joint center of the object, an eleventh key point corresponding to a second preset position in the tibia of the object and a twelfth key point corresponding to a third preset position in the tibia of the object as target key points for performing bone correction;

the second determining submodule 802C is specifically configured to:

determining a sixth straight line where the first key point and the second key point are located, and determining a third line segment taking the sixth key point and the eleventh key point as endpoints;

determining a fourth line segment with the same length as the third line segment, wherein one end point of the fourth line segment is the eleventh key point, and the other end point of the fourth line segment is positioned on the sixth straight line, and the fourth line segment is close to the outer side of the lower leg of the subject compared with the third line segment;

determining an angle of an included angle formed by the third line segment and the fourth line segment as a correction angle;

determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the eleventh key point and the twelfth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene;

In an embodiment of the present invention, referring to fig. 10, there is provided a schematic structural diagram of a third surgical reference plan generating device, and in this embodiment, the device further includes, compared to the embodiment shown in fig. 8, the following steps:

a second determining module 804, configured to determine a distortion type of the object based on position information of a key point of a preset joint portion of the object in the identified two-dimensional bone perspective image;

the generating module 803 is specifically configured to:

and generating a surgical reference scheme taking the distortion type, the distortion part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information.

In one embodiment of the present invention, the second determining module 804 is specifically configured to:

determining a seventh straight line where a first key point corresponding to the femoral head center of the object and a sixth key point corresponding to the ankle joint center of the object are located in the key points;

if the second key point corresponding to the center of the knee joint of the object body is close to the inner side of the knee joint compared with the seventh straight line, judging whether the distance between the second key point and the seventh straight line is larger than a first preset distance or not;

if the distance between the second key point and the seventh straight line is larger than the first preset distance, determining that the distortion type of the object body is knee valgus;

if the second key point is close to the outer side of the knee joint compared with the seventh straight line, judging whether the distance between the second key point and the seventh straight line is larger than a second preset distance or not;

and if the distance between the second key point and the seventh straight line is larger than the second preset distance, determining that the distortion type of the object body is gonyectyposis.

The embodiment of the present invention further provides an electronic device, as shown in fig. 11, including a processor 1101, a communication interface 1102, a memory 1103 and a communication bus 1104, where the processor 1101, the communication interface 1102 and the memory 1103 complete communication with each other through the communication bus 1104,

a memory 1103 for storing a computer program;

the processor 1101 is configured to execute a program stored in the memory 1103, and implement the following steps:

In addition, the electronic device may implement other surgical reference scheme generating methods as described in the previous method embodiment section, which will not be described in detail herein.

The communication bus mentioned above for the electronic devices may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present invention, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of any of the above-described surgical reference scheme generation methods.

In yet another embodiment of the present invention, there is also provided a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods of generating a surgical reference plan of the above embodiments.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

In this specification, each embodiment is described in a related manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for the apparatus, electronic device, computer readable storage medium, and computer program product embodiments, the description is relatively simple, as relevant to the method embodiments being referred to in the section of the description of the method embodiments.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method of surgical reference plan generation, the method comprising:

generating an operation reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information;

the determining the distorted part of the object body based on the position information of the key point, and determining the correction angle, the length of the osteotomy line and the osteotomy height for correcting the bone of the distorted part, comprises:

determining a distortion part of the object body based on the position information of the key points;

obtaining target key points for bone correction from the key points according to the distortion parts;

Based on the position information of the target key points, determining a correction angle, an osteotomy line length and an osteotomy height for correcting the bones of the distorted part;

the determining the distortion part of the object based on the position information of the key point includes:

and/or

Determining a third straight line where a fifth key point corresponding to a middle point of a lower limb of the object and a sixth key point corresponding to an ankle joint center of the object are located in the key points, determining a seventh key point corresponding to two end points of the lower side of a knee joint of the object and a fourth straight line where an eighth key point corresponding to the key points are located, respectively, and judging whether the angle of a second included angle is an angle in a second preset angle range, if not, determining that the distorted part of the object is a tibia, wherein the second included angle is: an included angle formed by the third straight line and the fourth straight line and close to the inner side of the lower leg of the subject;

And when the distorted part is a femur, obtaining a target key point for bone correction from the key points according to the distorted part, wherein the target key point comprises: determining a first key point corresponding to the femoral head center of the object, a fifth key point corresponding to the lower limb center of the object, a sixth key point corresponding to the ankle joint center of the object, a ninth key point corresponding to the hinge position of the object and a tenth key point corresponding to a first preset position in the femur of the object as target key points for bone correction; the determining, based on the position information of the target key point, a correction angle, an osteotomy line length, and an osteotomy height for correcting the bone of the distorted portion includes: determining a fifth straight line where the fifth key point and the sixth key point are located, and determining a first line segment taking the first key point and the ninth key point as endpoints; determining a second line segment with the same length as the first line segment, wherein one end point of the second line segment is the ninth key point, and the other end point of the second line segment is positioned on the fifth straight line, and the second line segment is close to the inner side of the thigh of the object body compared with the first line segment; determining an angle of an included angle formed by the first line segment and the second line segment as a correction angle; determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the ninth key point and the tenth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene; based on the correction angle and the length of the osteotomy line, determining the osteotomy height for correcting the bone of the distorted part according to a preset corresponding relation among the correction angle, the length of the osteotomy line and the osteotomy height;

In the case that the distorted portion is a tibia, the obtaining, according to the distorted portion, a target key point for performing bone correction from the key points includes: determining a first key point corresponding to the femoral head center of the object, a second key point corresponding to the knee joint center of the object, a sixth key point corresponding to the ankle joint center of the object, an eleventh key point corresponding to a second preset position in the tibia of the object and a twelfth key point corresponding to a third preset position in the tibia of the object as target key points for performing bone correction; the determining, based on the position information of the target key point, a correction angle, an osteotomy line length, and an osteotomy height for correcting the bone of the distorted portion includes: determining a sixth straight line where the first key point and the second key point are located, and determining a third line segment taking the sixth key point and the eleventh key point as endpoints; determining a fourth line segment with the same length as the third line segment, wherein one end point of the fourth line segment is the eleventh key point, and the other end point of the fourth line segment is positioned on the sixth straight line, and the fourth line segment is close to the outer side of the lower leg of the subject compared with the third line segment; determining an angle of an included angle formed by the third line segment and the fourth line segment as a correction angle; determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the eleventh key point and the twelfth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene; based on the correction angle and the length of the osteotomy line, determining the osteotomy height for correcting the bone of the distorted part according to the preset corresponding relation among the correction angle, the length of the osteotomy line and the osteotomy height.

2. The method of claim 1, further comprising, after identifying key points of a preset joint region of the subject in the two-dimensional bone perspective image:

determining the distortion type of the object body based on the position information of the key points;

the generating the surgical reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information comprises the following steps:

3. The method of claim 2, wherein the determining the distortion type of the object based on the location information of the keypoints comprises:

4. A surgical reference plan generation apparatus, the apparatus comprising:

the generation module is used for generating an operation reference scheme taking the distorted part, the correction angle, the length of the osteotomy line and the osteotomy height as reference information;

the first determining module includes:

The first determining submodule is used for determining the distortion part of the object body based on the position information of the key points;

the obtaining submodule is used for obtaining target key points for bone correction from the key points according to the distortion part;

the second determining submodule is used for determining a correction angle, an osteotomy line length and an osteotomy height for correcting the bones of the distorted part based on the position information of the target key points;

the first determining submodule is specifically configured to:

And/or

in the case where the distortion location is a femur, the obtaining sub-module is specifically configured to: determining a first key point corresponding to the femoral head center of the object, a fifth key point corresponding to the lower limb center of the object, a sixth key point corresponding to the ankle joint center of the object, a ninth key point corresponding to the hinge position of the object and a tenth key point corresponding to a first preset position in the femur of the object as target key points for bone correction; the second determining sub-module is specifically configured to: determining a fifth straight line where the fifth key point and the sixth key point are located, and determining a first line segment taking the first key point and the ninth key point as endpoints; determining a second line segment with the same length as the first line segment, wherein one end point of the second line segment is the ninth key point, and the other end point of the second line segment is positioned on the fifth straight line, and the second line segment is close to the inner side of the thigh of the object body compared with the first line segment; determining an angle of an included angle formed by the first line segment and the second line segment as a correction angle; determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the ninth key point and the tenth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene; based on the correction angle and the length of the osteotomy line, determining the osteotomy height for correcting the bone of the distorted part according to a preset corresponding relation among the correction angle, the length of the osteotomy line and the osteotomy height;

In the case where the distortion location is a tibia, the obtaining sub-module is specifically configured to: determining a first key point corresponding to the femoral head center of the object, a second key point corresponding to the knee joint center of the object, a sixth key point corresponding to the ankle joint center of the object, an eleventh key point corresponding to a second preset position in the tibia of the object and a twelfth key point corresponding to a third preset position in the tibia of the object as target key points for performing bone correction; the second determining sub-module is specifically configured to: determining a sixth straight line where the first key point and the second key point are located, and determining a third line segment taking the sixth key point and the eleventh key point as endpoints; determining a fourth line segment with the same length as the third line segment, wherein one end point of the fourth line segment is the eleventh key point, and the other end point of the fourth line segment is positioned on the sixth straight line, and the fourth line segment is close to the outer side of the lower leg of the subject compared with the third line segment; determining an angle of an included angle formed by the third line segment and the fourth line segment as a correction angle; determining the length of an osteotomy line for correcting the bone of the distorted part according to the distance between the eleventh key point and the twelfth key point and a preset proportion, wherein the preset proportion represents: the ratio between the unit length in the two-dimensional skeleton perspective image and the unit length in the actual scene; based on the correction angle and the length of the osteotomy line, determining the osteotomy height for correcting the bone of the distorted part according to the preset corresponding relation among the correction angle, the length of the osteotomy line and the osteotomy height.

5. The apparatus of claim 4, wherein the apparatus further comprises:

the second determining module is used for determining the distortion type of the object body based on the position information of the key points after the key points of the preset joint parts of the object body in the two-dimensional skeleton perspective image are identified;

the generating module is specifically configured to:

6. The apparatus of claim 5, wherein the second determining module is specifically configured to:

7. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for carrying out the method steps of any one of claims 1-3 when executing a program stored on a memory.

8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-3.