WO2022142741A1 - Total knee arthroplasty preoperative planning method and device - Google Patents

Abstract

A total knee arthroplasty preoperative planning method and device. The method comprises: acquiring a knee joint X-ray film image, and determining true dimensions of the knee joint X-ray film image (S101); inputting the knee joint X-ray film image into a neural network recognition model for recognition to determine key points of a bone structure in the knee joint X-ray film image and a key axis of the bone structure in the knee joint X-ray film image (S102); determining, on the basis of the key points of the bone structure in the knee joint X-ray film image, the key axis of the bone structure in the knee joint X-ray film image, and the true dimensions of the knee joint X-ray film image, femoral dimension parameters of the bone structure in the knee joint X-ray film image and tibial dimension parameters of the bone structure in the knee joint X-ray film image (S103); determining, on the basis of the femoral dimension parameters of the bone structure in the knee joint X-ray film image and the tibial dimension parameters of the bone structure in the knee joint X-ray film image, the type and model of a femoral prosthesis and the type and model of a tibial prosthesis (S104); and determining, on the basis of the key axis, the type and model of the femoral prosthesis, and the type and model of the tibial prosthesis, placement positions and placement angles corresponding to the femoral prosthesis and the tibial prosthesis (S105). The present invention can reduce cost, avoids the randomness of manual measurement, and provides an important reference function for the calculation of various parameters and the placement of a prosthesis, thus reducing dependence on a surgeon.

Description

Preoperative planning method and device for total knee arthroplasty

CROSS-REFERENCE TO RELATED APPLICATIONS

This application claims the priority of the Chinese patent application with the application number CN202011629571.3 and the invention titled "Preoperative Planning Method and Device for Total Knee Replacement", which was filed with the China Patent Office on December 31, 2020, the entire contents of which are by reference Incorporated in this application.

technical field

The invention relates to the field of artificial intelligence medical technology, in particular to a preoperative planning method and device for total knee arthroplasty.

Background technique

Total Knee Arthroplasty (TKA) is an effective method for the treatment of severe knee osteoarthritis and other diseases, and it is an indispensable item in the treatment of knee osteoarthritis. Accurate prosthesis matching is considered to be one of the important factors to reduce postoperative complications such as knee pain, prosthesis loosening, prosthesis wear, and postoperative bleeding, ensure good joint function, and improve postoperative satisfaction. Excessive size of the prosthesis may lead to poor contact between the prosthesis and the osteotomy surface, resulting in prosthesis loosening and too small flexion gap, resulting in limited flexion and excessive pressure on the patellofemoral joint, which affects the function of the knee extensor device. The oversized prosthesis compresses the surrounding ligaments and other structures, causing the suspension to cause pain. Undersized prosthesis may lead to excessive flexion gap and unstable flexion position, resulting in excessive posterior condylar osteotomy during anterior reference distal femoral anterior and posterior condylar osteotomies, and anterior condylar appearance during posterior reference distal femoral anterior and posterior condyle osteotomy The notch easily leads to postoperative fracture around the prosthesis, and the cortical bone of the osteotomy surface is poorly covered and the prosthesis sinks.

For total knee arthroplasty, the amount of osteotomy, the choice of prosthesis size, and the placement of the prosthesis are still determined by the experience of the surgeon. Individual differences of patients and doctor's experience have a certain impact on the surgical effect. It can be seen that the choice of lower extremity alignment, osteotomy volume and prosthesis size in traditional knee arthroplasty still relies on the simple measurement of the imaging department and the experience of the surgeon to finally grasp, individual differences of patients and the surgeon's proficiency in the equipment. may affect the outcome of the surgery.

SUMMARY OF THE INVENTION

In view of the problems existing in the prior art, embodiments of the present invention provide a preoperative planning method and device for total knee arthroplasty.

In a first aspect, an embodiment of the present invention provides a preoperative planning method for total knee arthroplasty, including:

Obtain a knee joint X-ray image, and determine the real size of the knee joint X-ray image;

Inputting the knee joint X-ray image into a neural network recognition model for identification, and determining the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image;

The knee X-ray is determined based on the key points of the bone structure in the knee X-ray image, the key axis of the bone structure in the knee X-ray image, and the real size of the knee X-ray image The femoral size parameter of the bone structure in the radiograph image and the tibia size parameter of the bone structure in the knee joint X-ray image;

Determine the type and size of the femoral prosthesis and the type and size of the tibial prosthesis based on the femoral size parameter of the bone structure in the knee joint X-ray image and the tibial size parameter of the bone structure in the knee joint X-ray image;

A placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis.

The knee joint X-ray image includes an anterior knee X-ray image and a knee joint lateral X-ray image;

Wherein, the knee joint X-ray image is input into a neural network recognition model for identification, and the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image are determined. ,include:

Converting the knee joint anteroposterior X-ray image into a first grayscale image, and converting the knee joint lateral X-ray image into a second grayscale image;

The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the tibial plateau Connect the lowest point, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network recognition model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior borders of the tibia, and anatomy of the tibia axis.

The femoral size parameters of the bone structure in the knee X-ray image include left-right diameter of the femur and the anteroposterior diameter of the femur; the tibia size parameters of the bone structure in the knee X-ray image include the left-right diameter of the tibia and the anterior-posterior diameter of the tibia;

The left-right diameter of the femur is determined according to the connecting line of the medial and lateral edges of the femur; the left-right diameter of the tibia is determined according to the connecting line of the medial and lateral edges of the tibia; the anterior-posterior diameter of the femur is determined according to the tangent line of the anterior cortex and the posterior condyle ; Determine the anterior and posterior diameter of the tibia according to the connecting line of the anterior and posterior edges of the tibia.

The key axis includes a femoral mechanical axis, a femoral anatomical axis, a tibial mechanical axis and a tibial anatomical axis; wherein the tibial mechanical axis and the tibial anatomical axis are the same key axis or a coincident key axis;

Wherein, the femoral mechanical axis is determined according to the center point of the femoral head and the center point of the knee joint;

Wherein, the knee joint X-ray image is input into the neural network recognition model for identification, and the key axis of the bone structure in the knee joint X-ray image is determined, including:

The first grayscale image is input into the neural network recognition model for identification, and the femoral region, the cortical bone region of the femur, the tibia region and the cortical bone region of the tibia are determined;

The femoral medullary cavity area is determined according to the femur area and the femoral cortical area, and the tibial medullary cavity area is determined according to the tibia area and the tibia cortical area;

The femoral anatomical axis is determined by performing straight line fitting on the center point of the femoral medullary cavity region, and the tibial anatomical axis and the tibial mechanical axis are determined by performing straight line fitting on the center point of the tibial medullary cavity region.

The type and size of femoral prosthesis and the type and size of tibial prosthesis are determined based on the femoral size parameter of the bone structure in the knee radiograph image and the tibial size parameter of the bone structure in the knee radiograph image, including :

establishing a prosthesis library, where prosthesis data is recorded; the prosthesis data includes the left and right diameters of the femoral prosthesis, the anterior and posterior diameters of the femoral prosthesis, the left and right diameters of the tibial prosthesis, and the anterior and posterior diameters of the tibial prosthesis;

Determine the left-right diameter of the femoral prosthesis and the anterior-posterior diameter of the femoral prosthesis according to the left-right diameter of the femur and the anterior-posterior diameter of the femur;

Wherein, the prosthesis data further includes femoral prosthesis osteotomy parameters and tibial prosthesis osteotomy parameters, which are determined based on the key axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis. The corresponding placement positions and placement angles of the femoral prosthesis and the tibial prosthesis include:

According to the femoral prosthesis osteotomy parameter, the tibial prosthesis osteotomy parameter and the key axis, the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined.

The method also includes at least one of the following steps:

Calculate the femoral-tibial mechanical axis angle mTFA according to the femoral mechanical axis and the tibial mechanical axis;

Calculate the included angle aTFA of the femoral tibial anatomical axis according to the femoral anatomical axis and the tibial anatomical axis;

Calculate the included angle AMA of the femoral mechanical axis anatomical axis according to the femoral mechanical axis and the femoral anatomical axis;

Calculate the lateral distal femoral angle mLDFA according to the connecting line between the mechanical axis of the femur and the lowest point of the distal femur;

Calculate the proximal medial angle of the tibia mMPTA according to the connecting line between the tibial mechanical axis and the lowest point of the tibial plateau;

The internal convergence angle JLCA was calculated according to the line connecting the lowest point of the distal femur and the lowest point of the tibial plateau.

Wherein, the knee joint is determined based on the key points of the bone structure in the knee joint X-ray image, the key axis of the bone structure in the knee joint X-ray image, and the real size of the knee joint X-ray image The femoral size parameter of the bone structure in the X-ray image and the tibia size parameter of the bone structure in the knee X-ray image, including:

The key points include the center of the femoral head, the medial border of the femur, the lateral border of the femur, the tangent line of the anterior cortex of the femur, the tangent line of the posterior condyle of the femur, the medial border of the tibia, the lateral border of the tibia, the anterior border of the tibia, and the posterior border of the tibia;

Determine the left and right diameter of the femur according to the medial border of the femur and the lateral border of the femur; determine the anterior and posterior diameter of the femur according to the tangent of the anterior cortex of the femur and the tangent of the posterior condyle of the femur;

Determine the left and right diameter of the tibia according to the medial border of the tibia and the lateral border of the tibia; determine the anterior and posterior diameter of the tibia according to the anterior border of the tibia and the posterior border of the tibia;

The femoral size parameter is determined according to the left-right diameter of the femur and the anterior-posterior diameter of the femur; the tibial size parameter is determined according to the left-right diameter of the tibia and the anterior-posterior diameter of the tibia.

Wherein, the type and model of the femoral prosthesis and the type and model of the tibial prosthesis are determined based on the femoral size parameter of the bone structure in the knee joint X-ray image and the tibial size parameter of the bone structure in the knee joint X-ray image ,include:

The left and right diameters and anterior and posterior diameters of the femur and tibia are calculated based on the identified key points: the left and right diameters of the femur are determined according to the medial and lateral borders of the femur determined by the neural network identification model, the anterior and posterior diameters of the femur are determined by the tangent of the anterior cortex of the femur and the tangent of the posterior condyle of the femur, and the inner and outer diameters of the femur are determined by the , The lateral edge determines the left and right diameter of the tibia, and the anterior and posterior edges of the tibia determine the anterior and posterior diameter of the tibia;

Based on the prosthesis matching rule, the prosthesis is matched in the prosthesis database, and the femoral or tibial prosthesis model is determined.

Among them, the prosthesis is matched based on the prosthesis matching rule, and the femoral or tibial prosthesis model is determined, including:

If the prosthesis is a femoral prosthesis, first match according to the data of the left and right diameters of the femur, and then match according to the data of the anteroposterior diameter of the femur to determine the model of the femoral prosthesis;

If the prosthesis is a tibial prosthesis, first match the tibial anterior and posterior diameter data, and then match the tibial left and right diameter data to determine the tibial prosthesis model.

In a second aspect, an embodiment of the present invention provides a preoperative planning device for total knee arthroplasty, including:

an acquisition module, configured to acquire an X-ray image of the knee joint, and determine the real size of the X-ray image of the knee joint;

The identification module is configured to input the knee joint X-ray image into a neural network identification model for identification, and determine the key points of the bone structure in the knee joint X-ray image and the bones in the knee joint X-ray image the key axes of the structure;

a parameter determination module configured to be based on key points of the bone structure in the knee radiograph image, key axes of the bone structure in the knee radiograph image, and the true size of the knee radiograph image determining the femoral size parameter of the bone structure in the knee joint X-ray image and the tibia size parameter of the bone structure in the knee joint X-ray image;

a determining prosthesis module configured to determine the type and size of femoral prosthesis and the tibia based on the femoral size parameter of the bone structure in the knee radiograph image and the tibial size parameter of the bone structure in the knee radiograph image Type and size of prosthesis;

A determination placement module configured to determine placement locations corresponding to the femoral prosthesis and the tibial prosthesis based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis placement angle.

The knee joint X-ray image in the acquisition module includes a knee joint frontal X-ray image and a knee joint lateral X-ray image;

Wherein, the identification module is configured as:

Converting the knee joint anteroposterior X-ray image into a first grayscale image, and converting the knee joint lateral X-ray image into a second grayscale image;

The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the tibial plateau Connect the lowest point, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network recognition model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior borders of the tibia, and anatomy of the tibia axis.

The femoral size parameter of the bone structure in the knee joint X-ray image in the determining parameter module includes the left and right diameter of the femur and the anteroposterior diameter of the femur; the tibia size parameter of the bone structure in the knee joint X-ray image includes the left and right diameter of the tibia and the tibia. Anterior and posterior diameter of tibia;

The left-right diameter of the femur is determined according to the connecting line of the medial and lateral edges of the femur; the left-right diameter of the tibia is determined according to the connecting line of the medial and lateral edges of the tibia; the anterior-posterior diameter of the femur is determined according to the tangent line of the anterior cortex and the posterior condyle ; Determine the anterior and posterior diameter of the tibia according to the connecting line of the anterior and posterior edges of the tibia.

The key axis includes a femoral mechanical axis, a femoral anatomical axis, a tibial mechanical axis and a tibial anatomical axis; wherein the tibial mechanical axis and the tibial anatomical axis are the same key axis or a coincident key axis;

Wherein, the femoral mechanical axis is determined according to the center point of the femoral head and the center point of the knee joint;

Wherein, the knee joint X-ray image is input into the neural network recognition model for identification, and the key axis of the bone structure in the knee joint X-ray image is determined, including:

The first grayscale image is input into the neural network recognition model for identification, and the femoral region, the cortical bone region of the femur, the tibia region and the cortical bone region of the tibia are determined;

The femoral medullary cavity area is determined according to the femur area and the femoral cortical area, and the tibial medullary cavity area is determined according to the tibia area and the tibia cortical area;

The femoral anatomical axis is determined by performing straight line fitting on the center point of the femoral medullary cavity region, and the tibial anatomical axis and the tibial mechanical axis are determined by performing straight line fitting on the center point of the tibial medullary cavity region.

The determining prosthesis module is configured to:

establishing a prosthesis library, where prosthesis data is recorded; the prosthesis data includes the left and right diameters of the femoral prosthesis, the anterior and posterior diameters of the femoral prosthesis, the left and right diameters of the tibial prosthesis, and the anterior and posterior diameters of the tibial prosthesis;

Determine the left-right diameter of the femoral prosthesis and the anterior-posterior diameter of the femoral prosthesis according to the left-right diameter of the femur and the anterior-posterior diameter of the femur;

Wherein, the prosthesis data further includes femoral prosthesis osteotomy parameters and tibial prosthesis osteotomy parameters, which are determined based on the key axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis. The corresponding placement positions and placement angles of the femoral prosthesis and the tibial prosthesis are configured as:

According to the femoral prosthesis osteotomy parameter, the tibial prosthesis osteotomy parameter and the key axis, the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined.

The device also includes at least one of the following computing modules:

The calculation module is configured to calculate the femoral-tibial mechanical axis angle mTFA according to the femoral mechanical axis and the tibial mechanical axis;

Calculate the included angle aTFA of the femoral tibial anatomical axis according to the femoral anatomical axis and the tibial anatomical axis;

Calculate the included angle AMA of the femoral mechanical axis anatomical axis according to the femoral mechanical axis and the femoral anatomical axis;

Calculate the lateral distal femoral angle mLDFA according to the connecting line between the mechanical axis of the femur and the lowest point of the distal femur;

Calculate the proximal medial angle of the tibia mMPTA according to the connecting line between the tibial mechanical axis and the lowest point of the tibial plateau;

The internal convergence angle JLCA was calculated according to the line connecting the lowest point of the distal femur and the lowest point of the tibial plateau. .

In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor implements the first above-mentioned program when the processor executes the program The steps of the preoperative planning method for total knee arthroplasty described in the aspect.

In a fourth aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, implements the total knee arthroplasty described in the first aspect above The steps of the pre-planning method.

It can be seen from the above technical solutions that the preoperative planning method and device for total knee arthroplasty provided by the embodiments of the present invention can obtain a knee joint X-ray image and determine the real size of the knee joint X-ray image; The joint X-ray image is input to the neural network recognition model for identification, and the key points of the skeletal structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image are determined; based on the knee joint The key points of the bone structure in the radiograph image, the key axes of the bone structure in the knee radiograph image, and the true size of the knee radiograph image determine the bone structure in the knee radiograph image The femoral size parameter and the tibia size parameter of the bone structure in the knee X-ray image; based on the femoral size parameter of the bone structure in the knee X-ray image and the femoral size parameter of the bone structure in the knee X-ray image The tibial size parameter determines the type and size of femoral prosthesis and the type and size of tibial prosthesis; based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis The placement position and placement angle of the prosthesis and the tibial prosthesis. It can be seen that the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention only needs to use X-ray images to perform preoperative work, which effectively saves costs. At the same time, due to the individual differences of patients, the randomness of manual measurement can be effectively avoided when measuring the key points and key axes of patients. The neural network recognition model based on deep learning can accurately identify the key to the determined knee X-ray images. point locations and key axis axes, so as to be based on the key points of the bone structure in the knee radiograph image, the key axes of the bone structure in the knee radiograph image, and the true nature of the knee radiograph image Size determining the femoral size parameter of the bone structure in the knee radiograph image and the tibia size parameter of the bone structure in the knee radiograph image, and then based on the femoral size of the bone structure in the knee radiograph image parameters and tibial dimension parameters of the bone structure in the knee radiograph image to determine the type and size of femoral prosthesis and the type and size of tibial prosthesis; based on the critical axis, the type and size of the femoral prosthesis and The type and model of the tibial prosthesis determine the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis, and the multiple parameters and data determined above are intuitively displayed on the display to reduce the experience of the surgeon. At the same time, it plays an important reference role in the calculation of various parameters and prosthesis placement in surgery, which helps to improve the efficiency and accuracy of surgery.

Description of drawings

In order to illustrate the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are For some embodiments of the present invention, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

1 is a schematic flowchart of a preoperative planning method for total knee arthroplasty provided by an embodiment of the present invention;

2 is a schematic diagram of a lateral X-ray image of a knee joint according to an embodiment of the present invention;

3 is a schematic diagram of an anteroposterior X-ray image of the knee joint provided by an embodiment of the present invention;

4 is a schematic diagram of key points in an anteroposterior X-ray image of the knee joint according to an embodiment of the present invention;

5 is a schematic diagram of key points in a lateral X-ray image of a knee joint according to an embodiment of the present invention;

6 is a structural diagram of a neural network recognition model provided by an embodiment of the present invention;

7 is a schematic diagram of input and output of key points and key axes provided by an embodiment of the present invention;

8 is a structural diagram of a neural network recognition model provided by another embodiment of the present invention;

FIG. 9 is a schematic diagram of a medullary cavity region provided by an embodiment of the present invention;

FIG. 10 is a schematic diagram of determining a key axis provided by an embodiment of the present invention;

11 is a schematic diagram of a prosthesis provided in an embodiment of the present invention placed in a lateral X-ray image of a knee joint;

12 is a schematic diagram of a prosthesis provided in an embodiment of the present invention placed in an anteroposterior X-ray image of the knee joint;

13 is a schematic structural diagram of a preoperative planning device for total knee arthroplasty provided by an embodiment of the present invention;

FIG. 14 is a schematic diagram of a physical structure of an electronic device according to an embodiment of the present invention.

Detailed ways

In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are the Some, but not all, embodiments are disclosed. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. The preoperative planning method for total knee arthroplasty provided by the present invention will be explained and described in detail below through specific embodiments.

FIG. 1 is a schematic flowchart of a preoperative planning method for total knee arthroplasty provided by an embodiment of the present invention; as shown in FIG. 1 , the method includes:

Step S101: Acquire a knee joint X-ray image, and determine the real size of the knee joint X-ray image.

In this step, for example, an X-ray file is selected to obtain a knee joint X-ray image; at the same time, the real size of the knee joint X-ray image is determined. Wherein, to determine the real size of the knee joint X-ray image, a scale, a preset reference object, a calibration object, etc. may be used for calibration. For example, when importing an X-ray image into the system, manually select the two ends of the scale bar or the two ends of the calibration object on the image, calculate the distance between the two end points on the image, and perform scale conversion with the actual size determined by the two ends to restore the image scale. For the real size (that is, to determine the real size of the knee joint X-ray image), the real size can also be directly determined by measuring the size of the bone structure in the X-ray image by setting a size reduction device with a known size in the system. The embodiment is not limited here.

In this step, the knee joint X-ray image may include a knee joint frontal X-ray image and a knee joint lateral X-ray image. Referring to FIG. 2 and FIG. 3 X-ray films can be used for planning, and the matching effect of different types and types (or sizes) of prostheses can be observed from the frontal and lateral views.

Step S102: Input the knee joint X-ray image into a neural network recognition model for identification, and determine the key points of the bone structure in the knee joint X-ray image and the key points of the bone structure in the knee joint X-ray image axis.

In this step, optionally, the key points can be: points and lines in Figure 4 (anteroposterior X-ray image); wherein: points 1 and 2 are the center points of the femoral head, a1 is the mechanical axis of the femur, and b1 is the The femoral anatomical axis, c1 is the tibia anatomical (mechanical) axis, d1 is the line connecting the lowest point of the distal end of the femur, e1 is the line connecting the lowest point of the tibial plateau, f1 is the left and right diameter of the femur, and g1 is the left and right diameter of the tibia. The key points can also be: the midpoint and line in Figure 5 (lateral X-ray image); among them, a2 is the tangent of the anterior femoral cortex, b2 is the tangent of the posterior condyle of the femur, c2 is the femoral anatomical axis, and d2 is the tibia anatomical axis, e2 is the anterior and posterior diameter of the tibia, f2 is the line connecting the anterior and posterior borders of the tibial plateau, and g2 is the anterior and posterior diameter of the femur. For example, if the knee joint anteroposterior X-ray image is converted into a first grayscale image, the knee joint lateral X-ray image is converted into a second grayscale image; the first grayscale image is input into the trained The first neural network identification model determines the following key points and lines: the center of the femoral head, the line connecting the lowest point of the distal end of the femur, the center point of the knee joint, the line connecting the inner and outer edges of the femur, the line connecting the lowest point of the tibial plateau, and the inner and outer sides of the tibia. The second grayscale image is input into the trained second neural network recognition model, and the following key lines are determined: the tangent line of the anterior cortex of the femur, the tangent line of the posterior condyle of the femur, and the line connecting the anterior and posterior edges of the tibia.

In this step, optionally the key axes include the femoral anatomical axis, the femoral mechanical axis and the tibial anatomical axis (the tibial mechanical axis is the same as the tibial anatomical axis), that is, the femoral anatomical axis and the femoral mechanical axis are not the same axis, but the tibial mechanical axis and the tibial mechanical axis are not the same axis. The tibial anatomical axis is the same axis. The critical axis may also include a line connecting the nadir of the distal femur and the nadir of the tibial plateau.

Input the sized knee joint X-ray image into the neural network recognition model for recognition, and the steps of determining the key axis include:

The first grayscale image is input into the trained third neural network recognition model to determine the femur area, the cortical bone area of the femur, the tibia area and the cortical bone area of the tibia; according to the femur area and the cortical bone area of the femur Determine the femoral medullary canal area, determine the tibial medullary canal area according to the tibia area and the cortical bone area of the tibia; perform linear fitting on multiple center points of the femoral medullary canal area to determine the femoral anatomical axis, and determine the femoral anatomical axis for the tibial medullary canal area. Linear fitting was performed at multiple center points to determine the mechanical axis of the tibia.

Step S103: Determine the knee joint based on the key points of the bone structure in the knee joint X-ray image, the key axis of the bone structure in the knee joint X-ray image, and the real size of the knee joint X-ray image. Femoral size parameters of the bone structure in the joint radiograph image and tibia size parameter of the bone structure in the knee radiograph image.

In this step, for example, the key points include the center of the femoral head, the medial and lateral borders of the femur, the tangent to the anterior cortex of the femur, the tangent to the posterior condyle of the femur, the medial and lateral borders of the tibia, and the anterior and posterior borders of the tibia. Then, the left and right diameters of the femur were determined according to the medial and lateral edges of the femur; the anterior and posterior diameters of the femur were determined according to the tangent of the anterior femoral cortex and the tangent of the posterior condyle of the femur; the left and right diameters of the tibia were determined according to the medial and lateral edges of the tibia; The left-right diameter of the femur and the anterior-posterior diameter of the femur were used as the femoral size parameters, and the left-right diameter of the tibia and the anterior-posterior diameter of the tibia were used as the tibia size parameters.

Step S104: Determine the type and size of the femoral prosthesis and the type and size of the tibial prosthesis based on the femoral size parameter of the bone structure in the knee X-ray image and the tibial size parameter of the bone structure in the knee X-ray image. model.

In this step, optionally, the prosthesis has different types, and there are prostheses of different sizes (ie, models) under the same type, and the sizes of the prostheses of different sizes are different).

For a better understanding of the present invention, for example:

(1) Establish a prosthesis library: the left and right diameters of the femoral prosthesis A1, the anterior and posterior diameters of the femoral prosthesis B1, the left and right diameters of the tibial prosthesis A2, the anterior and posterior diameters of the tibial prosthesis B2 data, the femoral prosthesis osteotomy parameters and the tibial prosthesis osteotomy parameter entry system;

(2) Calculate the left and right diameters and anterior and posterior diameters of the femur and tibia based on the identified key points: determine the left and right diameter X1 of the femur according to the medial and lateral edges of the femur determined by the neural network identification model, and determine the anterior and posterior femoral Diameter Y1, the inner and outer edges of the tibia determine the left and right diameter of the tibia X2, and the anterior and posterior edges of the tibia determine the anterior and posterior diameter of the tibia Y2;

(3) Prosthesis matching: The prosthesis matching is based on the following principles:

For the femoral prosthesis, it is firstly matched according to the left and right diameter data, and then the left and right diameter models are matched with the anterior and posterior diameters, and the femoral prosthesis model Z1 is comprehensively determined. For the selection of tibial prosthesis, the priority is to match according to the anteroposterior diameter data, so the anteroposterior diameter model of the tibial prosthesis is automatically matched, and then the left and right diameter models are matched. Intelligently match the tibial prosthesis model Z2 according to the left and right diameter data and anterior and posterior diameter data of the tibial prosthesis. Based on the femoral and tibial prosthesis data, the gasket model Z is intelligently recommended.

Step S105: Determine the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis based on the key axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis.

In this step, for example, the femur is determined according to the connecting line of the lowest point of the distal femur, the mechanical axis of the femur, and the osteotomy parameters of the femoral prosthesis (after determining the type and size of the femoral prosthesis, it is equivalent to determining the osteotomy parameters of the femoral prosthesis). The placement position and placement angle of the prosthesis are determined according to the connection of the lowest point of the tibial plateau, the mechanical axis of the tibial bone, and the osteotomy parameters of the tibial prosthesis (after determining the type and model of the tibial prosthesis, it is equivalent to determining the osteotomy parameters of the tibial prosthesis) to determine the tibial prosthesis. The placement position and placement angle of the body. The ultimate purpose of prosthesis placement is to restore the patient's mechanical axis alignment, so the prosthesis placement angle can be determined by identifying the mechanical axis.

It can be seen from the above technical solutions that the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention can obtain the X-ray image of the knee joint, and determine the real size of the X-ray image of the knee joint; The line film image is input to the neural network recognition model for recognition, and the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image are determined; based on the knee joint X-ray The key points of the bone structure in the radiograph image, the key axes of the bone structure in the knee radiograph image, and the true size of the knee radiograph image determine the femur of the bone structure in the knee radiograph image size parameter and tibia size parameter of the bone structure in the knee radiograph image; femoral size parameter based on the bone structure in the knee radiograph image and tibia size of the bone structure in the knee radiograph image The parameters determine the type and size of the femoral prosthesis and the type and size of the tibial prosthesis; based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis According to the placement position and placement angle of the tibial prosthesis, it can be seen that the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention only needs to use X-ray images to perform preoperative work, which effectively saves costs. The individual differences of patients can effectively avoid the randomness of manual measurement when measuring key points and key axes of patients. The neural network recognition model based on deep learning can accurately identify the key points of the knee X-ray image after the size is determined. and key axis axes, so as to be determined based on the key points of the skeletal structure in the knee radiograph image, the key axes of the bone structure in the knee radiograph image, and the true size of the knee radiograph image The femoral size parameter of the bone structure in the knee X-ray image and the tibia size parameter of the bone structure in the knee X-ray image, and then based on the femoral size parameter of the bone structure in the knee X-ray image and The tibial dimension parameter of the bone structure in the knee radiograph image determines the type and size of femoral prosthesis and the type and size of tibial prosthesis; based on the critical axis, the type and size of the femoral prosthesis, and the The type and model of the tibial prosthesis determine the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis, and the multiple parameters and data determined above are intuitively displayed on the monitor to reduce the dependence on the experience of the surgeon At the same time, it plays an important reference role in the calculation of various parameters and prosthesis placement in surgery, which helps to improve the efficiency and accuracy of surgery.

On the basis of the above embodiment, in this embodiment, the knee joint X-ray image includes a knee joint anteroposterior X-ray image and a knee joint lateral X-ray image;

Wherein, the knee joint X-ray image is input into a neural network recognition model for identification, and the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image are determined. ,include:

Converting the knee joint anteroposterior X-ray image into a first grayscale image, and converting the knee joint lateral X-ray image into a second grayscale image;

The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the tibial plateau Connect the lowest point, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network recognition model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior borders of the tibia, and anatomy of the tibia axis.

In this embodiment, the knee joint X-ray image may include a knee joint frontal X-ray image and a knee joint lateral X-ray image. Referring to Figures 2 and 3, two different shooting positions are used in the frontal and lateral positions. The X-ray films are used for planning, and the matching effect of different types and types (or sizes) of prostheses can be observed from the frontal and lateral views.

In this embodiment, optionally, the neural network recognition model is trained based on point recognition neural network training to recognize: the center point of the femoral head, the lowest point of the distal femur, the center point of the knee joint, the medial and lateral edge points of the femur, and the tangent to the anterior bone cortex, The tangent line of the posterior condyle of the femur; the line connecting the lowest point of the tibial plateau, the medial and lateral borders of the tibia, and the anterior and posterior borders of the tibia.

The structure diagram of the point recognition neural network is shown in Figure 6. See Figure 6 and Figure 7. The point recognition network can identify key anatomical points on the basis of accurate segmentation, which is more stable and accurate than manual punctuation.

First, you need to use the punctuation plug-in to manually mark key points such as the medial and lateral edges of the femur. Each picture corresponds to two point coordinates (X1, Y1), (X2, Y2), and the label.txt file is generated. Enter the orthographic image and label.txt with a pixel value of 0-255, and you can find the corresponding point coordinates through the name of each image; if you directly use the coordinates of the target point for learning, the neural network needs to convert the spatial position to coordinates by itself , is a training method that is more difficult to learn, so generating these points into a Gaussian graph can add a directional guidance to the training of the network. The closer it is to the target point, the larger the activation value, so that the network can go fast in a direction. Reach the target point, that is, quickly identify key points.

The network uses hourglass. First, the Conv layer and the Max Pooling layer are used to scale the features to a small resolution. At each maxpooling (downsampling), the network is bifurcated and pre-pooled to the original human pose resolution. After convolving the features of the lowest resolution, the network starts sampling up sampling, and gradually combines the feature information of different scales. Here, the nearest neighbor upsampling method is used for the lower resolution, and the element-wise addition of two different feature sets is performed. The entire hourglass is symmetrical. For each network layer in the process of acquiring low-resolution features, there will be a corresponding network layer in the upsampling process. After the output of the hourglass network module is obtained, two consecutive 1*1Conv layer for processing to get the final network output. The output is a collection of heatmaps, each heatmap representing the probability of keypoints existing at each pixel.

Before each downsampling, the Hourglass network divides the upper halfway to retain the original scale information; after each upsampling, it is added to the data of the previous scale; between two downsamplings, three residual network residual modules are used to extract features ; Between two additions, a residual network residual module is used to extract features. Since features at various scales are considered, it runs faster and the network training time is faster.

The point recognition network can accurately identify the key points of the medial and lateral border of the femur, the key points of the medial and lateral border of the tibia, the lowest point of the distal femur, the center point of the knee joint, and the lowest point of the tibial plateau. The placement of the prosthesis has an important reference role.

Preferably, in order to better and accurately determine the key points, after the key points are obtained, the identification of the key points is checked, and the key points whose identified positions are inaccurate are adjusted.

It can be seen from the above technical solutions that the preoperative planning method for total knee replacement provided by the embodiment of the present invention obtains key points based on the neural network identification model, thereby quickly and accurately obtaining the key points required for total knee replacement surgery, and can accurately Identifying key points on the basis of segmentation is more stable and accurate than manual punctuation, thereby obtaining stable and accurate measurement results, such as left and right femoral diameters and anteroposterior diameters of femurs, left and right tibia diameters, and anteroposterior diameters of tibia, etc. The measurement results are matched to the prosthesis with a high degree of fit, which in turn helps to improve the prosthesis placement effect and obtain a better prosthesis placement scheme.

On the basis of the above embodiment, in this embodiment, the femoral size parameters of the bone structure in the knee joint X-ray image include the left-right diameter of the femur and the anteroposterior diameter of the femur; The tibia size parameters include the left and right diameters of the tibia and the anterior and posterior diameters of the tibia; the left and right diameters of the femur are determined according to the connecting line of the medial and lateral edges of the femur; the left and right diameters of the tibia are determined according to the connecting line of the medial and lateral edges of the tibia; The tangent line and the tangent line of the posterior condyle of the femur determine the anterior and posterior diameter of the femur;

On the basis of the above embodiments, in this embodiment, the key axes include a femoral mechanical axis, a femoral anatomical axis, a tibial mechanical axis, and a tibial anatomical axis; wherein the tibial mechanical axis and the tibial anatomical axis are the same key axis axis or coincident critical axis;

Wherein, the femoral mechanical axis is determined according to the center point of the femoral head and the center point of the knee joint; wherein, the X-ray image of the knee joint is input into a neural network recognition model for identification, and the X-ray of the knee joint is determined The key axis of the bone structure in the slice image, including: inputting the first grayscale image into a neural network recognition model for recognition, and determining the femur area, the cortical bone area of the femur, the tibia area, and the cortical bone area of the tibia; according to the The femur area and the cortical bone area of the femur determine the femoral medullary cavity area, and the tibial medullary cavity area is determined according to the tibial area and the cortical bone area of the tibia; the center point of the femoral medullary cavity area is determined by linear fitting For the femoral anatomical axis, the tibial anatomical axis and the tibial mechanical axis are determined by performing straight line fitting on the center point of the tibial medullary cavity region.

In this embodiment, optionally, the neural network recognition model is shown in FIG. 8 . Referring to FIG. 8 , X-ray images of the knee joint are collected, and the femur area and cortical bone area in these images are marked; a segmentation convolutional neural network is established. Module, input the X-ray picture with pixel value of 0-255, the label mask of 0-2, where 0 is the background, 1 is the femur, and 2 is the bone cortex; it is passed into the convolutional neural network for convolution pooling The sampling has been iteratively learned and trained; the output is the prediction of each pixel value of the X-ray film, and each pixel value of the X-ray film will be classified into a category, namely 0-background, 1-femur, and 2-cortical bone. Referring to Figure 9, the nadir of the distal femur is cut to the distal end of the femur, and the femoral mask–cortical mask is the medullary mask. Referring to Figure 10, starting from the lowest point of the distal end of the femur, a horizontal line is drawn for each pixel point in turn, and there are four coordinates A1, A2, B1, B2 at the intersection with the medullary cavity; the midpoint can be calculated based on the two points, the formula: A1 (X1, Y1), midpoint coordinates of A2 (X2, Y2): X (midpoint)=(X1+X2)/2, Y (midpoint)=(Y1+Y2)/2. In the same way for B1 and B2, the midpoints of the medullary canal are obtained in turn, and the least squares method is used to fit these points into a straight line.

It can be seen from the above technical solutions that the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention determines the key axis based on the neural network identification model, so as to quickly and accurately obtain the key axis required for the operation, such as the femoral anatomical axis and the femoral mechanical axis. And the anatomical (mechanical) axis of the tibia, so as to obtain stable and accurate measurement results, which helps to improve the prosthesis placement effect and obtain a better prosthesis placement scheme.

On the basis of the above embodiment, in this embodiment, the femoral prosthesis is determined based on the femoral size parameter of the bone structure in the knee joint X-ray image and the tibia size parameter of the bone structure in the knee joint X-ray image Types and sizes of and types and sizes of tibial prostheses, including:

A prosthesis library is established, and prosthesis data is recorded in the prosthesis library; the prosthesis data includes the left and right diameters of the femoral prosthesis, the anterior and posterior diameters of the femoral prosthesis, the left and right diameters of the tibial prosthesis, and the anterior and posterior diameters of the tibial prosthesis; according to the The left-right diameter of the femur and the anterior-posterior diameter of the femur determine the left-right diameter of the femoral prosthesis and the anterior-posterior diameter of the femoral prosthesis, and the left-right diameter of the tibial prosthesis and the anterior-posterior diameter of the tibial prosthesis are determined according to the left-right diameter of the tibia and the anterior-posterior diameter of the tibia; The prosthesis data also includes femoral prosthesis osteotomy parameters and tibial prosthesis osteotomy parameters, which are determined based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis. The placement position and placement angle of the prosthesis and the tibial prosthesis, including: determining the femoral prosthesis and the tibial prosthesis according to the femoral prosthesis osteotomy parameter, the tibial prosthesis osteotomy parameter and the key axis The corresponding placement position and placement angle of the body.

On the basis of the foregoing embodiment, in this embodiment, the method further includes at least one of the following steps:

Calculate the femoral and tibial mechanical axis angle mTFA according to the femoral mechanical axis and the tibial mechanical axis; Calculate the anatomical axis angle AMA of the femoral mechanical axis; calculate the distal femoral lateral angle mLDFA according to the connection between the femoral mechanical axis and the lowest point of the distal femur; calculate the proximal tibia according to the connection between the tibial mechanical axis and the lowest point of the tibial plateau End medial angle mMPTA; Calculate the medial convergence angle JLCA according to the line connecting the lowest point of the distal femur and the lowest point of the tibial plateau.

In this embodiment, it can be understood that the included angle mTFA of the femoral and tibial mechanical axes is determined according to the femoral mechanical axis and the tibial mechanical axis; The included angle of the axis of the tibia aTFA.

In some preferred embodiments, the method of the present invention further comprises: in the lateral X-ray image of the knee joint, determining the posterior inclination angle of the tibial plateau according to the tibial anatomical axis and the line connecting the anterior and posterior edges of the tibial plateau. It should be noted that the posterior inclination angle of the tibial plateau is the included angle between the vertical line of the tibial anatomical axis and the line connecting the anterior and posterior edges of the tibial plateau (line f2 in Figure 5 ).

It can be seen from the above technical solutions that, in the preoperative planning method for total knee replacement provided by the embodiments of the present invention, the included angle mTFA is calculated according to the femoral mechanical axis and the tibial mechanical axis; Calculate the included angle aTFA; calculate the included angle AMA according to the mechanical axis of the femur and the anatomical axis of the femur; calculate the lateral angle of the distal femur mLDFA according to the mechanical axis of the femur and the lowest point of the distal femur; Connect the lowest point of the platform to calculate the proximal tibia internal measurement angle mMPTA; calculate the internal convergence angle JLCA according to the connection of the lowest point of the distal femur and the lowest point of the tibial platform; thus providing an important reference for the placement angle of the prosthesis, Then, the prosthesis placement effect is improved through the precise prosthesis placement angle, and a better prosthesis placement scheme is obtained.

It can be seen from the above technical solutions that the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention is based on the precise lowest point of the distal end of the femur and the lowest point of the tibial plateau, as well as the matching prosthesis model and prosthesis mentioned in the knee X-ray film. The size of the body determines the placement position of the prosthesis, so that the placement effect of the prosthesis can be improved through the precise placement position, and a better prosthesis placement scheme can be obtained.

On the basis of the above embodiment, in this embodiment, the method further includes: placing the matching prosthesis in the knee X-ray according to the placement position of the prosthesis and the placement angle of the prosthesis, and placing the prosthesis Results display.

In this embodiment, referring to FIG. 11 and FIG. 12 , the matching prosthesis is placed in the knee X-ray according to the placement position of the prosthesis and the placement angle of the prosthesis, and the prosthesis placement result is displayed. Preferably, for better placement effect, it is checked whether the placement is proper, and manual adjustment is performed if adjustment is required, so as to obtain the optimal placement effect.

It can be seen from the above technical solutions that in the preoperative planning method for total knee arthroplasty provided by the embodiment of the present invention, the computer automatically places the matched prosthesis in the knee X-ray according to the determined placement position and placement angle, and the operator or patient, etc. Relevant personnel can display the effect of prosthesis placement, thereby improving the efficiency of surgery.

13 is a schematic structural diagram of a preoperative planning device for total knee replacement provided by an embodiment of the present invention. As shown in FIG. 13 , the device includes: an acquisition module 201 , an identification module 202 , a parameter determination module 203 , and a prosthesis determination module 204 and determine placement module 205, where:

Wherein, the acquisition module 201 is configured to acquire a knee joint X-ray image, and determine the real size of the knee joint X-ray image;

The identification module 202 is configured to input the knee joint X-ray image into a neural network identification model for identification, and determine the key points of the bone structure in the knee joint X-ray image and the knee joint X-ray image. key axes of skeletal structure;

A determining parameter module 203, configured to be based on the key points of the bone structure in the knee joint X-ray image, the key axes of the bone structure in the knee joint X-ray image, and the truth of the knee joint X-ray image Size determining the femoral size parameter of the bone structure in the knee joint X-ray image and the tibia size parameter of the bone structure in the knee joint X-ray image;

A determining prosthesis module 204 is configured to determine the type and size of femoral prosthesis based on the femoral size parameter of the bone structure in the knee radiograph image and the tibial size parameter of the bone structure in the knee radiograph image and Type and size of tibial prosthesis;

determine placement module 205 configured to determine placement locations corresponding to the femoral prosthesis and the tibial prosthesis based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis and placement angle.

On the basis of the above embodiment, in this embodiment, the knee joint X-ray image in the acquisition module includes a knee joint anteroposterior X-ray image and a knee joint lateral X-ray image;

Wherein, the identification module is configured to: convert the knee joint anteroposterior X-ray image into a first grayscale image, and convert the knee joint lateral X-ray image into a second grayscale image; The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal end of the femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the lowest tibial plateau Connect the dots, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network identification model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior edges of the tibia, and anatomical axis of the tibia .

On the basis of the above embodiment, in this embodiment, the femoral size parameters of the bone structure in the knee joint X-ray image in the determining parameter module include the left-right diameter of the femur and the anteroposterior diameter of the femur; the knee joint X-ray The tibial size parameters of the bone structure in the image include the left-right diameter of the tibia and the anterior-posterior diameter of the tibia;

The left-right diameter of the femur is determined according to the connecting line of the medial and lateral edges of the femur; the left-right diameter of the tibia is determined according to the connecting line of the medial and lateral edges of the tibia; the anterior-posterior diameter of the femur is determined according to the tangent line of the anterior cortex and the posterior condyle ; Determine the anterior and posterior diameter of the tibia according to the connecting line of the anterior and posterior edges of the tibia.

On the basis of the above embodiments, in this embodiment, the key axes include a femoral mechanical axis, a femoral anatomical axis, a tibial mechanical axis, and a tibial anatomical axis; wherein the tibial mechanical axis and the tibial anatomical axis are the same key axis axis or coincident critical axis;

Wherein, the femoral mechanical axis is determined according to the center point of the femoral head and the center point of the knee joint;

Wherein, the knee joint X-ray image is input into the neural network recognition model for identification, and the key axis of the bone structure in the knee joint X-ray image is determined, including:

The first grayscale image is input into the neural network recognition model for identification, and the femoral region, the cortical bone region of the femur, the tibia region and the cortical bone region of the tibia are determined;

The femoral medullary cavity area is determined according to the femur area and the femoral cortical area, and the tibial medullary cavity area is determined according to the tibia area and the tibia cortical area;

The femoral anatomical axis is determined by performing straight line fitting on the center point of the femoral medullary cavity region, and the tibial anatomical axis and the tibial mechanical axis are determined by performing straight line fitting on the center point of the tibial medullary cavity region.

On the basis of the above embodiment, in this embodiment, the determining prosthesis module is configured as:

establishing a prosthesis library, where prosthesis data is recorded; the prosthesis data includes the left and right diameters of the femoral prosthesis, the anterior and posterior diameters of the femoral prosthesis, the left and right diameters of the tibial prosthesis, and the anterior and posterior diameters of the tibial prosthesis;

Determine the left-right diameter of the femoral prosthesis and the anterior-posterior diameter of the femoral prosthesis according to the left-right diameter of the femur and the anterior-posterior diameter of the femur;

Wherein, the prosthesis data further includes femoral prosthesis osteotomy parameters and tibial prosthesis osteotomy parameters, which are determined based on the key axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis. The corresponding placement positions and placement angles of the femoral prosthesis and the tibial prosthesis are configured as:

According to the femoral prosthesis osteotomy parameter, the tibial prosthesis osteotomy parameter and the key axis, the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined.

On the basis of the foregoing embodiment, in this embodiment, the apparatus further includes at least one of the following computing modules:

The calculation module is configured to calculate the femoral-tibial mechanical axis angle mTFA according to the femoral mechanical axis and the tibial mechanical axis;

Calculate the included angle aTFA of the femoral tibial anatomical axis according to the femoral anatomical axis and the tibial anatomical axis;

Calculate the included angle AMA of the femoral mechanical axis anatomical axis according to the femoral mechanical axis and the femoral anatomical axis;

Calculate the lateral distal femoral angle mLDFA according to the connecting line between the mechanical axis of the femur and the lowest point of the distal femur;

Calculate the proximal medial angle of the tibia mMPTA according to the connecting line between the tibial mechanical axis and the lowest point of the tibial plateau;

The internal convergence angle JLCA was calculated according to the line connecting the lowest point of the distal femur and the lowest point of the tibial plateau.

The preoperative planning device for total knee arthroplasty provided in the embodiment of the present invention can be specifically used to implement the preoperative planning method for total knee arthroplasty in the above-mentioned embodiment, and its technical principles and beneficial effects are similar. Repeat.

Based on the same inventive concept, an embodiment of the present invention provides an electronic device. Referring to FIG. 14 , the electronic device specifically includes the following contents: a processor 301, a communication interface 303, a memory 302, and a communication bus 304;

Among them, the processor 301, the communication interface 303, and the memory 302 complete the mutual communication through the bus 304; the communication interface 303 is used to realize the information transmission between various modeling software and the intelligent manufacturing equipment module library and other related equipment; the processor 301 uses In calling the computer program in the memory 302, the processor implements the methods provided by the above method embodiments when executing the computer program. For example, when the processor executes the computer program, the following steps are implemented: acquiring a knee joint X-ray image, and determining the The actual size of the knee joint X-ray image; the knee joint X-ray image is input to the neural network recognition model for identification, and the key points of the skeletal structure in the knee joint X-ray image and the knee joint X-ray image are determined. The key axis of the bone structure in the radiograph image; based on the key points of the bone structure in the knee radiograph image, the key axis of the bone structure in the knee radiograph image, and the knee radiograph image Determine the femoral size parameter of the bone structure in the knee X-ray image and the tibia size parameter of the bone structure in the knee X-ray image; based on the femur of the bone structure in the knee X-ray image Size parameters and tibial size parameters of the bone structure in the knee radiograph image determine the type and size of femoral prosthesis and the type and size of tibial prosthesis; based on the critical axis, the type and size of the femoral prosthesis And the type and size of the tibial prosthesis determine the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis.

Based on the same inventive concept, another embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, and the computer program is implemented when executed by a processor to execute the methods provided by the foregoing method embodiments. method, for example, acquiring a knee joint X-ray image, and determining the real size of the knee joint X-ray image; inputting the knee joint X-ray image into a neural network recognition model for identification, and determining the knee joint X-ray image The key points of the bone structure in the radiograph image and the key axes of the bone structure in the knee radiograph image; based on the key points of the bone structure in the knee radiograph image, the knee radiograph image The critical axis of the bone structure, and the true size of the knee radiograph image determines the femoral size parameter of the bone structure in the knee radiograph image and the tibia size parameter of the bone structure in the knee radiograph image determining the type and size of the femoral prosthesis and the type and size of the tibial prosthesis based on the femoral size parameter of the bone structure in the knee joint radiograph image and the tibia size parameter of the bone structure in the knee joint radiograph image; A placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis.

The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place , or distributed to multiple network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

From the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on this understanding, the above-mentioned technical solutions can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in computer-readable storage media, such as ROM/RAM, magnetic Disks, optical discs, etc., include instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods of various embodiments or portions of embodiments.

Claims (13)

1. A preoperative planning method for total knee arthroplasty, comprising:

   Obtain a knee joint X-ray image, and determine the real size of the knee joint X-ray image;

   Inputting the knee joint X-ray image into a neural network recognition model for identification, and determining the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image;

   The knee X-ray is determined based on the key points of the bone structure in the knee X-ray image, the key axis of the bone structure in the knee X-ray image, and the real size of the knee X-ray image The femoral size parameter of the bone structure in the radiograph image and the tibia size parameter of the bone structure in the knee joint X-ray image;

   Determine the type and size of the femoral prosthesis and the type and size of the tibial prosthesis based on the femoral size parameter of the bone structure in the knee joint X-ray image and the tibial size parameter of the bone structure in the knee joint X-ray image;

   A placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis.
2. The method of claim 1, wherein the knee joint X-ray image includes a knee joint frontal X-ray image and a knee joint lateral X-ray image;

   Wherein, the knee joint X-ray image is input into a neural network recognition model for identification, and the key points of the bone structure in the knee joint X-ray image and the key axis of the bone structure in the knee joint X-ray image are determined. ,include:

   Converting the knee joint anteroposterior X-ray image into a first grayscale image, and converting the knee joint lateral X-ray image into a second grayscale image;

   The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the tibial plateau Connect the lowest point, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network recognition model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior borders of the tibia, and anatomy of the tibia axis.
3. The method according to claim 2, wherein the femoral size parameters of the bone structure in the knee X-ray image include left-right diameter of the femur and the anteroposterior diameter of the femur; the tibia size parameter of the bone structure in the knee X-ray image Including the left and right diameters of the tibia and the anterior and posterior diameters of the tibia;

   The left-right diameter of the femur is determined according to the connecting line of the medial and lateral edges of the femur; the left-right diameter of the tibia is determined according to the connecting line of the medial and lateral edges of the tibia; the anterior-posterior diameter of the femur is determined according to the tangent line of the anterior cortex and the posterior condyle ; Determine the anterior and posterior diameter of the tibia according to the connecting line of the anterior and posterior edges of the tibia.
4. The method according to claim 2 or 3, wherein the critical axis comprises a femoral mechanical axis, a femoral anatomical axis, a tibial mechanical axis and a tibial anatomical axis; wherein the tibial mechanical axis and the tibial anatomical axis are the same critical axis or coincident critical axes;

   Wherein, the femoral mechanical axis is determined according to the center point of the femoral head and the center point of the knee joint;

   Wherein, the knee joint X-ray image is input into the neural network recognition model for identification, and the key axis of the bone structure in the knee joint X-ray image is determined, including:

   The first grayscale image is input into the neural network recognition model for identification, and the femoral region, the cortical bone region of the femur, the tibia region and the cortical bone region of the tibia are determined;

   The femoral medullary cavity area is determined according to the femur area and the femoral cortical area, and the tibial medullary cavity area is determined according to the tibia area and the tibia cortical area;

   The femoral anatomical axis is determined by performing straight line fitting on the center point of the femoral medullary cavity region, and the tibial anatomical axis and the tibial mechanical axis are determined by performing straight line fitting on the center point of the tibial medullary cavity region.
5. 4. The method of claim 3, wherein the type of femoral prosthesis and the femoral prosthesis are determined based on a femoral size parameter of the bone structure in the knee radiograph image and a tibial size parameter of the bone structure in the knee radiograph image. Models and types and sizes of tibial prostheses, including:

   establishing a prosthesis library, where prosthesis data is recorded; the prosthesis data includes the left and right diameters of the femoral prosthesis, the anterior and posterior diameters of the femoral prosthesis, the left and right diameters of the tibial prosthesis, and the anterior and posterior diameters of the tibial prosthesis;

   Determine the left-right diameter of the femoral prosthesis and the anterior-posterior diameter of the femoral prosthesis according to the left-right diameter of the femur and the anterior-posterior diameter of the femur;

   Wherein, the prosthesis data further includes femoral prosthesis osteotomy parameters and tibial prosthesis osteotomy parameters, which are determined based on the key axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis. The corresponding placement positions and placement angles of the femoral prosthesis and the tibial prosthesis include:

   According to the femoral prosthesis osteotomy parameter, the tibial prosthesis osteotomy parameter and the key axis, the placement position and placement angle corresponding to the femoral prosthesis and the tibial prosthesis are determined.
6. The method of claim 1, further comprising at least one of the following steps:

   Calculate the femoral-tibial mechanical axis angle mTFA according to the femoral mechanical axis and the tibial mechanical axis;

   Calculate the included angle aTFA of the femoral tibial anatomical axis according to the femoral anatomical axis and the tibial anatomical axis;

   Calculate the included angle AMA of the femoral mechanical axis anatomical axis according to the femoral mechanical axis and the femoral anatomical axis;

   Calculate the lateral distal femoral angle mLDFA according to the connecting line between the mechanical axis of the femur and the lowest point of the distal femur;

   Calculate the proximal medial angle of the tibia mMPTA according to the connecting line between the tibial mechanical axis and the lowest point of the tibial plateau;

   The internal convergence angle JLCA was calculated according to the line connecting the lowest point of the distal femur and the lowest point of the tibial plateau.
7. The method of claim 1, wherein based on key points of bone structure in the knee radiograph image, key axes of bone structure in the knee radiograph image, and the knee radiograph The real size of the image determines the femoral size parameter of the bone structure in the knee joint X-ray image and the tibia size parameter of the bone structure in the knee joint X-ray image, including:

   The key points include the center of the femoral head, the medial border of the femur, the lateral border of the femur, the tangent line of the anterior cortex of the femur, the tangent line of the posterior condyle of the femur, the medial border of the tibia, the lateral border of the tibia, the anterior border of the tibia, and the posterior border of the tibia;

   Determine the left and right diameter of the femur according to the medial border of the femur and the lateral border of the femur; determine the anterior and posterior diameter of the femur according to the tangent of the anterior cortex of the femur and the tangent of the posterior condyle of the femur;

   Determine the left and right diameter of the tibia according to the medial border of the tibia and the lateral border of the tibia; determine the anterior and posterior diameter of the tibia according to the anterior border of the tibia and the posterior border of the tibia;

   The femoral size parameter is determined according to the left-right diameter of the femur and the anterior-posterior diameter of the femur; the tibial size parameter is determined according to the left-right diameter of the tibia and the anterior-posterior diameter of the tibia.
8. The method of claim 1, wherein the type of femoral prosthesis and the femoral prosthesis are determined based on a femoral size parameter of the bone structure in the knee radiograph image and a tibial size parameter of the bone structure in the knee radiograph image Models and types and sizes of tibial prostheses, including:

   The left and right diameters and anterior and posterior diameters of the femur and tibia are calculated based on the identified key points: the left and right diameters of the femur are determined according to the medial and lateral edges of the femur determined by the neural network identification model, the anterior and posterior diameters of the femur are determined by the tangent of the anterior cortex of the femur and the tangent of the posterior condyle of the femur, and the inner and outer diameters of the tibia are determined , The lateral edge determines the left and right diameter of the tibia, and the anterior and posterior edges of the tibia determine the anterior and posterior diameter of the tibia;

   Based on the prosthesis matching rule, the prosthesis is matched in the prosthesis database, and the femoral or tibial prosthesis model is determined.
9. The method according to claim 8, wherein the prosthesis matching is performed based on the prosthesis matching rule to determine the femoral or tibial prosthesis model, comprising:

   If the prosthesis is a femoral prosthesis, first match according to the data of the left and right diameters of the femur, and then match according to the data of the anteroposterior diameter of the femur to determine the model of the femoral prosthesis;

   If the prosthesis is a tibial prosthesis, first match the tibial anterior and posterior diameter data, and then match the tibial left and right diameter data to determine the tibial prosthesis model.
10. A preoperative planning device for total knee arthroplasty, comprising:

    an acquisition module, configured to acquire an X-ray image of the knee joint, and determine the real size of the X-ray image of the knee joint;

    The identification module is configured to input the knee joint X-ray image into a neural network identification model for identification, and determine the key points of the bone structure in the knee joint X-ray image and the bones in the knee joint X-ray image the key axes of the structure;

    a parameter determination module configured to be based on key points of the bone structure in the knee radiograph image, key axes of the bone structure in the knee radiograph image, and the true size of the knee radiograph image determining the femoral size parameter of the bone structure in the knee joint X-ray image and the tibia size parameter of the bone structure in the knee joint X-ray image;

    a determining prosthesis module configured to determine the type and size of femoral prosthesis and the tibia based on the femoral size parameter of the bone structure in the knee radiograph image and the tibial size parameter of the bone structure in the knee radiograph image Type and size of prosthesis;

    A determination placement module configured to determine placement locations corresponding to the femoral prosthesis and the tibial prosthesis based on the critical axis, the type and size of the femoral prosthesis, and the type and size of the tibial prosthesis placement angle.
11. The device according to claim 10, wherein the knee joint X-ray image in the acquiring module comprises an anterior knee X-ray image and a knee joint lateral X-ray image;

    Wherein, the identification module is configured as:

    Converting the knee joint anteroposterior X-ray image into a first grayscale image, and converting the knee joint lateral X-ray image into a second grayscale image;

    The first grayscale image is input into the neural network recognition model, and the following key points and key axes are determined: the center point of the femoral head, the line connecting the lowest point of the distal femur, the center point of the knee joint, the line connecting the medial and lateral edges of the femur, and the tibial plateau Connect the lowest point, connect the medial and lateral edges of the tibia; input the second grayscale image into the neural network recognition model to determine the following key axes: tangent to the anterior cortex of the femur, tangent to the posterior condyle of the femur, line connecting the anterior and posterior borders of the tibia, and anatomy of the tibia axis.
12. An electronic device, comprising a memory, a processor and a computer program stored on the memory and running on the processor, when the processor executes the program, the total knee joint according to any one of claims 1 to 9 is realized Steps in the preoperative planning method for replacement surgery.
13. A non-transitory computer-readable storage medium having a computer program stored thereon, the computer program implementing the steps of the preoperative planning method for total knee replacement according to any one of claims 1 to 9 when the computer program is executed by a processor.

Images