A method and program product for matching hip prostheses based on medical images

Abstract

In a hip joint prosthesis matching method and program product based on a medical image provided in the specification, a target prosthesis is obtained from each candidate prosthesis according to the position and structure parameters of key points in the medical image, a template of the target prosthesis is labeled to a corresponding position in the medical image according to the structure parameters and the position of the key points, the medical image is separated according to the position of the osteotomy line to obtain a femur sub-image and a hip joint sub-image, the position of the femur sub-image and / or the hip joint sub-image is adjusted according to the positional relationship between the target prostheses in the template labeled to the medical image to obtain a medical image after the target prosthesis is implanted. On the one hand, the target prosthesis of the patient does not need to be matched manually, and on the other hand, the user can also intuitively see the effect after the target prosthesis is implanted, which improves the accuracy of preoperative prosthesis matching and realizes efficient and high-accuracy matching of hip joint implanted prostheses.

Description

Technical Field

[0001] This specification relates to the field of image processing technology, and in particular to a method and program product for matching hip joint prostheses based on medical images. Background Technology

[0002] With advancements in medical technology, total hip replacement surgery has become the preferred treatment for hip-related diseases. Furthermore, the effectiveness of hip replacement surgery is closely related to the accuracy of prosthesis selection before surgery, as well as the direction and amount of osteotomy, and the alignment of the limb with the prosthesis. Therefore, the selection of the prosthesis and a detailed preoperative assessment are crucial for surgical success.

[0003] In existing technologies, the X-ray template measurement method is generally used to select the implant for the affected side. The user manually matches the implant template to the printed X-ray film to determine the implant to be used. The affected side refers to the side of the body that has a disease, injury, or abnormality, while the corresponding healthy side is the unaffected side.

[0004] However, in existing technologies, users can only manually match prostheses, and the accuracy depends on the user's experience, which can easily lead to a mismatch between the prosthesis selected before surgery and the actual surgical needs. Furthermore, the accuracy of template matching is limited by the quality and angle of X-ray images, the subjective influence of manual matching, and the accuracy of manually measured images, making the process complex and inefficient. At the same time, considering individual patient differences, bone condition, and diseases further increases the difficulty of manual matching.

[0005] Therefore, this specification provides a method and procedure for matching hip prostheses based on medical images. Summary of the Invention

[0006] This specification provides a method and program product for matching hip joint prostheses based on medical images, in order to partially solve the above-mentioned problems existing in the prior art.

[0007] The following technical solution is adopted in this specification:

[0008] This specification provides a method for matching hip prostheses based on medical images, including:

[0009] Determine a medical image of the entire hip in the anteroposterior position, wherein the medical image is a two-dimensional X-ray image;

[0010] Based on the medical image, determine the location and structural parameters of key points in the medical image;

[0011] Based on the structural parameters and the size parameters of each candidate prosthesis, a matching target prosthesis is determined, and a template image of the target prosthesis is obtained.

[0012] Based on the structural parameters and the positions of the key points, the template icon is annotated to the corresponding position in the medical image;

[0013] The osteotomy line position is determined in the medical image, and the image is separated according to the osteotomy line position to obtain a femoral sub-image and a hip joint sub-image;

[0014] Based on the positional relationship between the target prostheses in the template diagram labeled to the medical image, the positions of the femoral sub-diagram and / or hip joint sub-diagram are adjusted to obtain a medical image after the target prosthesis is placed.

[0015] Optionally, based on the medical image, the location and structural parameters of key points in the medical image are determined, specifically including:

[0016] Based on the medical image, identify the locations of key points and corresponding structural parameters in the medical image;

[0017] The measured value of the structural parameter is determined based on the position corresponding to the structural parameter;

[0018] Determine the magnification based on the medical images;

[0019] The measured values ​​of the structural parameters are corrected for magnification based on the magnification to obtain the structural parameters.

[0020] Optionally, the key points include at least the femoral head center and the lesser trochanter key point; the structural parameters include at least one of the following: femoral head diameter, diameter at the narrowest point of the transition portion, inner diameter of the isthmus medullary canal, eccentricity, neck-shaft angle, and difference in leg length.

[0021] Optionally, a matching target prosthesis is determined based on the structural parameters and the size parameters of each candidate prosthesis, specifically including:

[0022] For each candidate prosthesis, determine the structural parameters of the healthy side corresponding to each dimensional parameter of the candidate prosthesis;

[0023] Compare the corresponding dimensional parameters with the structural parameters to determine the difference;

[0024] Based on the determined differences, the overall comparison result of the candidate prosthesis is determined;

[0025] Based on the comprehensive comparison results of each candidate prosthesis, the matching candidate prosthesis is determined as the target prosthesis.

[0026] Optionally, the target prosthesis includes an acetabular cup and a femoral stem;

[0027] Based on the structural parameters and the positions of the key points, the template icon is annotated to the corresponding position in the medical image, specifically including:

[0028] Based on the location of the key points, the template icon of the acetabular cup is marked on the acetabular fossa of the healthy hip joint, and the template icon of the femoral stem is marked on the medullary cavity of the healthy femur.

[0029] Optionally, the location of the osteotomy line in the medical image is determined based on the location of the key points, specifically including:

[0030] Based on the location of the lesser trochanter of the healthy femur in the medical image and the anatomical axis of the femoral neck of the healthy side, the osteotomy direction of the healthy side in the medical image is determined.

[0031] The osteotomy line position is determined based on the location of the key point of the lesser trochanter of the healthy femur and the osteotomy direction.

[0032] Optionally, based on the location of the osteotomy line, the medical image is segmented to obtain a femoral sub-image and a hip joint sub-image, specifically including:

[0033] Based on the location of the osteotomy line, the medical image is segmented along the direction of the osteotomy line to obtain a hip joint sub-image labeled with the template image of the acetabular cup and a healthy femur sub-image labeled with the template image of the femoral stem.

[0034] Optionally, the positions of the femoral sub-map and / or hip joint sub-map are adjusted based on the positional relationship between the target prostheses in the template map mapped to the medical image; specifically including:

[0035] The template image of the acetabular cup in the medical image is mapped onto the affected side of the acetabular fossa of the medical image, with the midpubic line of the hip joint as the center line.

[0036] The healthy femur sub-image of the template image marked with the femoral stem in the medical image is mapped onto the affected side of the medical image with the midpubic line of the hip joint as the center line.

[0037] Based on the positional relationship between the femoral stem and the acetabular cup in the target prosthesis, the position of the healthy femoral sub-image and / or hip joint sub-image of the template image marked with the femoral stem is adjusted in the longitudinal axis direction of the femoral neck in the medical image, so that the upper center of the proximal femoral segment in the template image marked in the medical image coincides with the center of the acetabular cup.

[0038] And rotate the healthy femur sub-graph and / or hip joint sub-graph of the template diagram labeled with the femoral stem so that the angle between the femoral anatomical axis of the template diagram of the femoral stem and the midpubic line of the hip joint is within a specified angle range.

[0039] This specification provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for matching hip prostheses based on medical images.

[0040] This specification provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the above-described hip prosthesis matching method based on medical images.

[0041] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects:

[0042] In the hip prosthesis matching method based on medical images provided in this specification, a matching target prosthesis is obtained from each candidate prosthesis according to the position and structural parameters of key points in the medical image. According to the structural parameters and the position of key points, the template icon of the target prosthesis is marked on the corresponding position in the medical image. According to the position of osteotomy line in the medical image, the medical image is separated to obtain a femoral sub-image and a hip joint sub-image. According to the positional relationship between the target prostheses in the template image marked on the medical image, the position of the femoral sub-image and / or the hip joint sub-image is adjusted to obtain a medical image after the target prosthesis is placed.

[0043] As can be seen from the above method, after identifying the target prosthesis, by annotating the template icon of the target prosthesis into the medical image and separating the medical image, the positional relationship of the separated femoral sub-image and hip joint sub-image can be adjusted according to the positional relationship when the target prosthesis is correctly assembled, so as to obtain the medical image after the target prosthesis is placed. On the one hand, there is no need for manual matching of prostheses, and on the other hand, the postoperative effect can be predicted, which improves the accuracy of preoperative prosthesis selection and avoids the need to prepare a large number of candidate prostheses before surgery, thus achieving high-efficiency and high-accuracy matching of hip joint implantation prostheses. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of this specification and form part of this specification, illustrate exemplary embodiments and their descriptions and are used to explain this specification, but do not constitute an undue limitation of this specification.

[0045] In the attached diagram:

[0046] Figure 1 This is a flowchart illustrating a hip prosthesis matching method based on medical images provided in this specification.

[0047] Figure 2 A schematic diagram of a total hip anteroposterior view medical image provided for an embodiment of this specification;

[0048] Figure 3 Medical images of the entire hip in anteroposterior view, with the locations of key points and corresponding structural parameters marked for the embodiments of this specification;

[0049] Figure 4 Template diagrams of the acetabular cup and femoral stem provided for embodiments of this specification;

[0050] Figure 5 Medical images of the labeled template diagrams for the affected and healthy sides provided in the embodiments of this specification;

[0051] Figure 6 Medical images of the healthy side annotation template provided in the embodiments of this specification;

[0052] Figure 7 The results of the affected side medical image segmentation provided in the embodiments of this specification;

[0053] Figure 8 The results of the healthy side medical image segmentation provided in the embodiments of this specification;

[0054] Figure 9 Medical images of the implanted target prosthesis provided in the embodiments of this specification;

[0055] Figure 10 Medical images of the implanted target prosthesis provided in the embodiments of this specification;

[0056] Figure 11 This is a schematic diagram of a medical image-based hip prosthesis matching device provided in this specification.

[0057] Figure 12 This is a schematic structural diagram of a medical image-based hip joint prosthesis matching electronic device provided in this specification. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0059] In the field of medical image processing, medical images are diverse. Therefore, in clinical practice, hip prosthesis matching based on medical images can be achieved using either two-dimensional or three-dimensional medical images. However, while matching hip prostheses based on three-dimensional medical images (such as CT images) is highly reliable, the image scanning cost is too high. Therefore, clinical practice often uses the lower-cost two-dimensional medical images for hip prosthesis matching. However, matching hip prostheses based solely on two-dimensional medical images is limited by the quality and angle of the X-ray images, the subjective influence of manual matching, and the accuracy of manual image measurements, making the process complex and inefficient. Therefore, this specification provides a method for hip prosthesis matching based on medical images.

[0060] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0061] Figure 1 This is a flowchart illustrating a method for matching a hip prosthesis to a medical image, as provided in this specification, including the following steps:

[0062] S100: Determine a medical image of the entire hip in the anteroposterior position, wherein the medical image is a two-dimensional X-ray image.

[0063] In the embodiments described herein, the device used to perform the acetabular cup matching process is not limited. For example, a personal computer, mobile terminal, or server may be used. However, since subsequent steps involve model calculations and image sampling, which are computationally resource-intensive operations, they are generally performed by a server. Therefore, this specification will also describe the acetabular cup matching process performed by a server as an example. The server can be a single device or a combination of multiple devices, such as a distributed server; this specification does not limit the specific device used.

[0064] Specifically, in one or more embodiments of this specification, the server can determine a full hip anteroposterior medical image of a patient requiring hip replacement surgery. This medical image is a two-dimensional X-ray image. The full hip anteroposterior view, also known as the hip joint anteroposterior projection, generally refers to a medical image showing the left and right hip halves, left and right femoral necks, and left and right femurs in a frontal orientation. In the embodiments of this specification, since the purpose is to match the hip joint prosthesis, the medical image must at least completely include the patient's hip joint region. Figure 2 As shown.

[0065] Figure 2 This is a schematic diagram of a total hip anteroposterior view medical image provided in the embodiments of this specification. As can be seen, Figure 2The images include the structures of both femurs and both hip bones, and are anteroposterior medical images taken with the patient supine on the camera platform.

[0066] It should be noted that, in the embodiments of this specification, the femur and hip joint refer to the skeletal structure of the patient in the medical image, and the artificial prosthesis includes a femoral stem prosthesis and an acetabular cup prosthesis. The femoral stem is the prosthetic structure of the artificial prosthesis that is inserted into the patient's femur, and the acetabular cup is the prosthetic structure of the artificial prosthesis that is inserted into the patient's acetabular fossa.

[0067] S102: Determine the location and structural parameters of key points in the medical image based on the medical image.

[0068] In one or more embodiments of this specification, since the target prosthesis for the patient needs to be matched in subsequent steps and the template icon of the target prosthesis needs to be annotated on the medical image, it is necessary to determine the location of structural parameters and key points in this step. Furthermore, the subsequent steps of inserting the target prosthesis involve placing the femoral stem into the femoral medullary canal and the acetabular cup into the acetabular fossa. Therefore, it is necessary to determine whether the femoral stem matches the femoral medullary canal and whether the acetabular cup matches the acetabular fossa. Thus, the structural parameters determined in this step should meet the requirements for the insertion of the femoral stem and acetabular cup.

[0069] Specifically, the server can identify the locations of key points and corresponding structural parameters based on the patient's medical images, and automatically measure the structural parameters based on the determined locations. It should be noted that there are currently various and relatively mature methods for identifying the locations of key points or corresponding structural parameters in images. Therefore, this application does not impose restrictions on how the locations of key points and corresponding structural parameters are determined; these can be set as needed. For example, they can be determined using a pre-trained model.

[0070] In one or more embodiments of this specification, key points and structural parameters can be set according to requirements. For example, in this specification, the key points used include at least the femoral head center and the lesser trochanter key point, and the structural parameters include at least one of the following: femoral head diameter, diameter of the narrowest part of the transition portion, inner diameter of the isthmus medullary canal, eccentricity, neck-shaft angle, and the difference in leg length. Figure 3 As shown, Figure 3 This is a full-hip anteroposterior medical image, where key points include a (femoral head center point) and b (lesser trochanter key point). Structural parameters include c (femoral head diameter), d (diameter at the narrowest point of the transition region), f (isthmus medullary canal diameter), g (eccentricity), ∠h (neck-shaft angle), and i (leg length difference). Of course, this manual specifies that the server can also determine other structural parameters for prosthesis matching. The manual does not limit which structural parameters can be determined and can be set as needed.

[0071] Furthermore, the structural parameters obtained in the above process are measured values, and when the magnification is 1, the measured values ​​are the same as the actual values. However, the magnification of X-ray medical images may not be 1, meaning that the actual values ​​of the structural parameters are not consistent with the measured values. Since the target prosthesis in subsequent steps needs to be matched with the actual values ​​of the structural parameters, it is also necessary to correct the measured values ​​of the structural parameters according to the preset magnification in the medical image to obtain the actual structural parameters.

[0072] The preset magnification is pre-measured and fixed. For example, a reference object, such as a marker sphere, can be added to the medical image. Knowing the actual size of the marker sphere, the image is segmented and measured within the medical image to obtain the measurement results. The magnification of the medical image is then determined based on the difference between the measured results and the actual size, and this magnification is used to correct the measured values ​​of structural parameters in the medical image. Therefore, during X-ray medical image acquisition, the equipment can be adjusted as needed, thereby adjusting the magnification. The magnification is not fixed; its selection depends on the required medical image detail and visualization requirements. Therefore, this specification does not limit the origin of the magnification.

[0073] S104: Based on the structural parameters and the size parameters of each candidate prosthesis, determine the matching target prosthesis and obtain the template image of the target prosthesis.

[0074] In one or more embodiments of this specification, based on the structural parameters determined in step S102 and considering the patient's needs, a suitable prosthesis is selected as the target prosthesis from the candidate prosthesis models provided by existing manufacturers. To facilitate observation of the placement effect of the target prosthesis, a template image of the target prosthesis needs to be obtained in this step and annotated onto a medical image. The template image is as follows: Figure 4 As shown, this includes a template diagram of the acetabular cup and a template diagram of the femoral stem.

[0075] Specifically, the server can compare the various dimensional parameters of each candidate prosthesis with the corresponding structural parameters of the affected side to determine the differences. Then, it determines the overall comparison result for each candidate prosthesis. Based on the overall comparison results of all candidate prostheses, the target prosthesis for the patient is determined. That is, the candidate prosthesis with the smallest overall comparison result indicates the smallest difference between its structural parameters and the affected side, representing the highest match, and is thus selected as the target prosthesis for the patient. Furthermore, to obtain medical images after the target prosthesis is placed, the server can also access a template image of the target prosthesis.

[0076] Furthermore, this instruction manual does not limit the method for determining the comprehensive comparison results of each candidate prosthesis. For example, the comprehensive comparison results of each candidate prosthesis can be determined by the sum and difference between each dimensional parameter and its corresponding structural parameter. That is, the sum of the absolute values ​​of the differences between each dimensional parameter of each candidate prosthesis and the corresponding structural parameter of the affected side is considered the optimal comprehensive comparison result. Of course, the comprehensive comparison results of each candidate prosthesis can also be determined by statistical test methods (analysis of variance) or by setting the ratio (weight) of each difference. The method for determining the comprehensive comparison results between differences can be set according to needs, and there are no restrictions here.

[0077] Furthermore, in one or more embodiments provided in this specification, the server can perform prosthesis matching based on either the patient's affected side or the patient's unaffected side. In particular, when a patient experiences femoral neck fracture with impaction on the affected side, resulting in shortening of the femoral neck and rotational and abduction deformities of the affected limb, the hip joint deformity may affect the accuracy of structural parameter measurements and key point location positioning, increasing the risk of errors. Therefore, in such cases, the prosthesis matching can be switched to the patient's unaffected side.

[0078] Optionally, similar to prosthesis matching based on the affected side, the server can, for each candidate prosthesis, determine the structural parameters of the healthy side corresponding to each dimensional parameter of the candidate prosthesis, compare the dimensional parameters of the candidate prosthesis with these structural parameters, determine the differences, and then determine the overall comparison result of the candidate prosthesis. Based on the overall comparison results of all candidate prostheses, the target prosthesis for the patient is determined. That is, the candidate prosthesis with the smallest overall comparison result indicates that the difference between the candidate prosthesis and the structural parameters of the affected side is the smallest, the matching degree is the highest, and this candidate prosthesis is selected as the target prosthesis for the patient. Furthermore, in order to obtain medical images after the target prosthesis is placed, the server can also call the template image of the target prosthesis.

[0079] S106: Based on the structural parameters and the positions of the key points, the template icon of the target prosthesis is annotated to the corresponding position in the medical image.

[0080] In one or more embodiments of this specification, the template image of the target prosthesis obtained in step S104 can be annotated onto the medical image based on the location and structural parameters of key points in the medical image determined in step S102.

[0081] Specifically, based on the location of key points, the server annotates the template icon of the target prosthesis onto the corresponding side of the affected side on the medical image. That is, the template icon of the acetabular cup is annotated on the acetabular fossa of the affected hip joint, and the template icon of the femoral stem is annotated on the medullary canal of the affected femur. Furthermore, the server ensures that the key point of the femoral head center location determined in step S102 coincides with the center point of the acetabular cup prosthesis template image, and that the structural parameter locations determined in step S102 coincide with the corresponding dimensional parameter locations of the femoral stem prosthesis in the template image.

[0082] For example, in the case of impacted femoral neck fracture on the affected side, the impaction results in shortening of the femoral neck on the affected side and a 12mm shorter limb compared to the healthy side, along with rotational and abduction deformities of the affected limb. Figure 5 As shown in the image, the left side is the affected side and the right side is the healthy side. The template icon of the target prosthesis is marked on the corresponding position on the affected side.

[0083] Optionally, the target prosthesis determined in step S104, whether based on the affected side or the healthy side, can be used to annotate the template icon of the target prosthesis onto the healthy side of the medical image. Similar to the above annotation of the template image based on the affected side, the server annotates the template icon of the target prosthesis onto the corresponding side of the healthy side on the medical image based on the location of key points; that is, the template icon of the acetabular cup is annotated on the acetabular fossa of the healthy hip joint, and the template icon of the femoral stem is annotated on the medullary canal of the healthy femur. The server also ensures that the key point of the femoral head center position determined in step S102 coincides with the center point of the acetabular cup prosthesis, and that the positions of the structural parameters determined in step S102 coincide with the corresponding dimensional parameters of the femoral stem prosthesis. Figure 6 As shown, following the previous example, the template icon of the target prosthesis was marked in the corresponding position on the healthy side.

[0084] S108: Based on the position of the osteotomy line in the medical image, the medical image is divided into a femoral sub-image and a hip joint sub-image.

[0085] In one or more embodiments of this specification, after determining the target prosthesis and the template image of the target prosthesis, the server can further divide the medical image into a femoral sub-image and a hip joint sub-image, so that the position of the sub-images can be adjusted in subsequent steps to obtain a medical image after the target prosthesis is inserted, so that the user can observe the effect after the target prosthesis is inserted and adjust the surgical plan in a timely manner.

[0086] Furthermore, since hip replacement surgery involves osteotomy at the femoral osteotomy line before inserting the femoral stem, in order to determine the medical image after the target prosthesis is inserted, the server can first determine the position of the osteotomy line in the medical image, and then divide the medical image according to the position of the osteotomy line in the medical image to obtain the femoral sub-image and the hip joint sub-image.

[0087] Specifically, firstly, since hip replacement surgery involves osteotomy at the femoral osteotomy line before inserting the femoral stem, the server can determine the osteotomy line position in order to obtain medical images of the implanted prosthesis in subsequent steps. That is, the server can use the location of the lesser trochanter of the affected femur in the medical image, and the anatomical axis of the femoral neck on the affected side (i.e., a perpendicular line drawn from the lesser trochanter to the anatomical axis of the femoral neck on the affected side) as the osteotomy direction on the affected side. Based on the location of the lesser trochanter of the affected femur and this osteotomy direction, the osteotomy line position is determined. The osteotomy line position is shown on the medical image as the junction of the femur and femoral neck.

[0088] Then, based on the determined osteotomy line position, the medical image is divided along the osteotomy direction to obtain a hip joint sub-image with the template image labeled with the acetabular cup on the affected side, and a femoral sub-image with the template image labeled with the femoral stem on the affected side. Using the example from step S106, such as... Figure 7 As shown, the determined osteotomy line is located on the affected side in the medical image.

[0089] Optionally, in step S106, a template icon of the target prosthesis is annotated onto the medical image. The location annotated on the medical image can be either the affected side or the healthy side. When the template icon of the target prosthesis is annotated onto the healthy side of the medical image, firstly, since hip replacement surgery involves osteotomy at the femoral osteotomy line before inserting the femoral stem, the server can first determine the osteotomy line position to obtain the medical image after the target prosthesis is inserted in subsequent steps. That is, the server can determine the osteotomy direction on the healthy side based on the position of the lesser trochanter key point of the healthy femur in the medical image and the anatomical axis of the femoral neck on the healthy side. In other words, a perpendicular line is drawn from the lesser trochanter to the anatomical axis of the femoral neck on the healthy side as the osteotomy direction on the healthy side in the medical image. Based on the position of the lesser trochanter key point of the healthy femur and the osteotomy direction, the osteotomy line position is determined. The osteotomy line position is presented on the medical image as the junction of the femur and the femoral neck.

[0090] Based on the determined osteotomy line position, the medical image is divided along the osteotomy direction to obtain a hip joint sub-image with the template image labeled with the acetabular cup on the healthy side, and a femoral sub-image with the template image labeled with the femoral stem on the healthy side. Using the example from step S106, such as... Figure 8 As shown, the determined osteotomy line is located on the healthy side in the medical image.

[0091] S110: Based on the positional relationship between the target prostheses when they are correctly assembled, adjust the position of the femoral sub-image and / or the hip joint sub-image to obtain a medical image after the target prosthesis is inserted.

[0092] In step S108, a hip joint sub-diagram with a template diagram labeled with the acetabular cup and a femoral sub-diagram with a template diagram labeled with the femoral stem were obtained. The acetabular cup and femoral stem have a conventional and correct assembly method, such as... Figure 4 The image on the right shows the correct assembly of the acetabular cup and femoral stem in a hip joint prosthesis as seen in a medical image.

[0093] Furthermore, in this step, to obtain medical images after the target prosthesis is placed, the positions of the femoral sub-image and / or the hip joint sub-image need to be adjusted. Simultaneously, the medical images after the target prosthesis is placed allow the user to visually observe the position of the hip prosthesis, ensuring that the placed hip prosthesis matches the patient's hip joint structure, and assisting the user in a detailed assessment of whether the placed target prosthesis is a good match, so as to adjust or improve the surgical plan in a timely manner.

[0094] Specifically, in step S108, the server will obtain the hip joint sub-image of the template image marked with the acetabular cup on the affected side, and the femoral sub-image of the template image marked with the femoral stem on the affected side. Based on the positional relationship between the femoral stem and the acetabular cup when correctly assembled in the target prosthesis, the position of the femoral sub-image and / or the hip joint sub-image will be adjusted in the longitudinal axis of the femoral neck in the medical image. That is, either the position of the femoral sub-image or the position of the hip joint sub-image can be adjusted, or they can be adjusted simultaneously.

[0095] The process involves aligning the upper center of the proximal femur segment in the template diagram annotated on the medical image with the center of the acetabular cup, and rotating the affected femoral sub-image and / or hip joint sub-image so that the angle between the femoral anatomical axis of the template diagram of the femoral stem and the midpubic line of the hip joint is within a specified range. Finally, a medical image of the target prosthesis after placement is obtained. Following the example of step S106 above, such as... Figure 9 As shown, this figure is a medical image of the implanted target prosthesis obtained after adjusting the sub-image position on the affected side.

[0096] Optionally, in the above steps, after annotating the template icon of the target prosthesis onto the healthy side of the medical image and dividing the medical image according to the osteotomy line position on the healthy side, the server can adjust the position of the healthy side femoral sub-image with the femoral stem template icon and / or the hip joint sub-image labeled with the acetabular cup template icon according to the positional relationship when the acetabular cup and femoral stem are correctly assembled, to obtain the medical image after the target prosthesis is placed. Specifically, the server symmetrically maps the template icon of the acetabular cup labeled on the healthy side hip joint sub-image (i.e., the template icon of the acetabular cup is centered on the midpubic line of the hip joint structure) onto the acetabular fossa on the affected side of the medical image, and symmetrically maps the healthy side femoral sub-image labeled with the femoral stem template icon (i.e., the healthy side femoral sub-image is centered on the midpubic line of the hip joint) onto the affected side of the medical image, covering the original affected side femoral region in the hip joint sub-image.

[0097] Based on the correct positional relationship between the femoral stem and the acetabular cup in the target prosthesis, the positions of the contralateral femoral sub-image and / or hip joint sub-image are adjusted along the longitudinal axis of the femoral neck in the medical image. This adjustment can be made on either side, or simultaneously. The goal is to ensure that the upper center of the proximal femoral segment in the template image coincides with the center of the acetabular cup. Furthermore, the contralateral femoral sub-image and / or hip joint sub-image are rotated so that the angle between the femoral anatomical axis of the template image and the midpubic line of the hip joint is within a specified range. Finally, a medical image after the target prosthesis is inserted is obtained. Following the above steps, an example is provided. Figure 10 As shown, this figure is a medical image of the implanted target prosthesis obtained after adjusting the sub-image position on the healthy side.

[0098] based on Figure 1 The provided method for matching hip prostheses based on medical images allows the server to obtain a matching target prosthesis from candidate prostheses based on the location and structural parameters of key points in the medical image. Based on the structural parameters and the location of key points, a template icon of the target prosthesis is annotated to the corresponding position in the medical image. The medical image is then segmented according to the osteotomy line position to obtain a femoral sub-image and a hip joint sub-image. Based on the positional relationship between the target prostheses in the template image annotated in the medical image, the positions of the femoral sub-image and / or the hip joint sub-image are adjusted to obtain a medical image after the target prosthesis is inserted.

[0099] As can be seen from the above method, after identifying the target prosthesis, by annotating the template icon of the target prosthesis into the medical image and separating the medical image, the positional relationship of the separated femoral sub-image and hip joint sub-image can be adjusted according to the positional relationship when the target prosthesis is correctly assembled, so as to obtain the medical image after the target prosthesis is placed. On the one hand, there is no need for manual matching of prostheses, and on the other hand, the postoperative effect can be predicted, which improves the accuracy of preoperative prosthesis selection and avoids the need to prepare a large number of candidate prostheses before surgery, thus achieving high-efficiency and high-accuracy matching of hip joint implantation prostheses.

[0100] In the above method, the server can perform prosthesis matching based on the affected side of the patient's medical images, and similarly, it can perform prosthesis matching based on the unaffected side. Especially when the patient's hip joint lesions cause limb deformities, matching based on the unaffected side yields higher accuracy. For example, when a patient has an impacted femoral neck fracture on the affected side, resulting in shortening of the femoral neck and rotational and abduction deformities of the affected limb, the deformities of the hip joint structure and limb may affect the measurement results of structural parameters and the accuracy of locating key points. This, in turn, affects subsequent steps such as determining the osteotomy line position, image segmentation, and sub-image position adjustment, increasing the risk of errors in the entire process. Therefore, by matching the prosthesis based on the unaffected acetabulum and femoral medullary canal, the influence of the patient's affected side lesions can be avoided, resulting in more accurate location of key points and measurement of structural parameters.

[0101] In one or more embodiments of this specification, the server can exchange information with the user. That is, in this specification, when the server determines the location of key points and structural parameters in a medical image, it can also send the medical image with the location of key points and the corresponding location of structural parameters marked to the terminal.

[0102] Furthermore, the terminal displays the medical image, responds to the user's adjustment operation, adjusts the positions of key points and structural parameters in the medical image, and returns the adjusted medical image to the server.

[0103] Based on the returned medical images, the server determines the locations and structural parameters of key points needed for subsequent steps.

[0104] Similar to the steps described above, after obtaining the target prosthesis model and annotating the template icon of the target prosthesis onto the medical image, the medical image with the template icon of the target prosthesis can be sent to the terminal and displayed on the terminal. If the user believes that the size parameters of the model do not quite match the patient's structural parameters, the user can select other candidate prostheses. The terminal returns the candidate prosthesis selected by the user to the server. That is, the server responds to the user's selection operation and, based on the selected candidate prosthesis as the matching target prosthesis, continues to execute the steps after determining the target prosthesis, and finally obtains the medical image of the target prosthesis being inserted.

[0105] The user-friendly human-computer interaction makes the entire process smoother. It also allows for monitoring of the entire process, from obtaining medical images of the implanted prosthesis to preventing errors in any step that could lead to incorrect images and thus improving work efficiency.

[0106] The above describes one or more embodiments of the hip joint prosthesis matching method provided in this specification. Based on the same idea, this specification also provides corresponding hip joint prosthesis matching devices, such as... Figure 11 As shown.

[0107] The acquisition module 1100 determines a medical image of the entire hip in an anteroposterior view, wherein the medical image is a two-dimensional X-ray image;

[0108] The image recognition module 1101 determines the position and structural parameters of key points in the medical image based on the medical image.

[0109] The matching module 1102 determines the target prosthesis to be matched based on the structural parameters and the size parameters of each candidate prosthesis, and obtains a template image of the target prosthesis.

[0110] The template annotation module 1103 annotates the template icon of the target prosthesis to the corresponding position in the medical image according to the structural parameters and the position of the key points;

[0111] The image segmentation module 1104 segments the medical image according to the position of the osteotomy line in the medical image to obtain a femoral sub-image and a hip joint sub-image.

[0112] The image adjustment module 1105 adjusts the position of the femoral sub-image and / or the hip joint sub-image according to the positional relationship between the target prostheses when they are correctly assembled, so as to obtain a medical image after the target prosthesis is placed.

[0113] Optionally, the image recognition module 1101 is specifically used to identify the positions of key points and structural parameters in the medical image; determine the measured values ​​of the structural parameters based on the positions of the structural parameters; determine the magnification based on the medical image; and correct the magnification of the measured values ​​of the structural parameters based on the magnification to obtain the structural parameters; the key points include at least the femoral head center and the lesser trochanter key point; the structural parameters include at least one of the following: femoral head diameter, diameter at the narrowest point of the transition portion, inner diameter of the isthmus medullary canal, eccentricity, neck-shaft angle, and difference in leg length.

[0114] Optionally, the matching module 1102 is specifically used to determine the structural parameters of the healthy side corresponding to each size parameter of the candidate prosthesis for each candidate prosthesis; compare the corresponding size parameters with the structural parameters to determine the difference; determine the comprehensive comparison result of the candidate prosthesis based on the determined difference; and determine the matching candidate prosthesis as the target prosthesis based on the comprehensive comparison result of each candidate prosthesis.

[0115] Optionally, the template annotation module 1103 is specifically used to annotate the template icon of the acetabular cup on the acetabular fossa of the healthy hip joint and the template icon of the femoral stem on the medullary canal of the healthy femur according to the location of the key points; the target prosthesis includes the acetabular cup and the femoral stem.

[0116] Optionally, the image segmentation module 1104 is specifically used to determine the osteotomy direction of the healthy side in the medical image based on the position of the lesser trochanter key point of the healthy femur and the anatomical axis of the femoral neck bone of the healthy side; determine the position of the osteotomy line based on the position of the lesser trochanter key point of the healthy femur and the osteotomy direction; and segment the medical image along the osteotomy line direction based on the position of the osteotomy line to obtain a hip joint sub-image with a template image labeled with the acetabular cup and a healthy femur sub-image with a template image labeled with the femoral stem.

[0117] Optionally, the image adjustment module 1105 is specifically used to map the template image of the acetabular cup in the medical image onto the affected side of the acetabular fossa in the medical image, with the midpubic line of the hip joint as the center line; to map the healthy side femoral sub-image of the template image marked with the femoral stem in the medical image onto the affected side of the medical image, with the midpubic line of the hip joint as the center line; to adjust the position of the healthy side femoral sub-image and / or hip joint sub-image of the template image marked with the femoral stem in the longitudinal axis direction of the femoral neck in the medical image according to the positional relationship between the femoral stem and the acetabular cup in the target prosthesis, so that the upper center of the proximal femoral segment in the template image marked in the medical image coincides with the center of the acetabular cup; and to rotate the healthy side femoral sub-image and / or hip joint sub-image of the template image marked with the femoral stem so that the angle between the femoral anatomical axis of the template image of the femoral stem and the midpubic line of the hip joint is within a specified angle range.

[0118] This specification also provides a computer-readable storage medium storing a computer program that can be used to execute the above-described... Figure 1 The provided method for matching hip prostheses.

[0119] This instruction manual also provides Figure 12 The diagram shows a schematic structural representation of the electronic device. Figure 12 At the hardware level, the autonomous driving device includes a processor, internal bus, network interface, memory, and non-volatile memory, and may also include other hardware required for various operations. The processor reads the corresponding computer program from the non-volatile memory into memory and then runs it to achieve the above-mentioned functions. Figure 1 The hip joint prosthesis matching method described above. Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of hardware and software, etc. That is to say, the execution subject of the following processing flow is not limited to individual logic units, but can also be hardware or logic devices.

[0120] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0121] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0122] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0123] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0124] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0126] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0128] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0129] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0130] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0131] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0132] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0133] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0134] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0135] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this application.

Claims

1. A method for matching hip joint prostheses based on medical images, characterized in that, include: Determine a medical image of the entire hip in the anteroposterior position, wherein the medical image is a two-dimensional X-ray image; Based on the medical image, determine the location and structural parameters of key points in the medical image; Based on the structural parameters and the dimensional parameters of each candidate prosthesis, a matching target prosthesis is determined, and a template image of the target prosthesis is obtained; wherein, the target prosthesis includes an acetabular cup and a femoral stem; Based on the location of the key points, the template icon of the acetabular cup is marked on the acetabular fossa of the healthy hip joint, and the template icon of the femoral stem is marked on the medullary canal of the healthy femur. Based on the location of the lesser trochanter of the healthy femur in the medical image and the anatomical axis of the femoral neck of the healthy side, the osteotomy direction of the healthy side in the medical image is determined. The osteotomy line position is determined based on the location of the key point of the lesser trochanter of the healthy femur and the osteotomy direction. The medical image is divided along the osteotomy line to obtain a hip joint sub-image with the template image labeled with the acetabular cup on the healthy side, and a femoral sub-image with the template image labeled with the femoral stem on the healthy side. The template image of the acetabular cup marked in the hip joint sub-image is mapped onto the acetabular fossa on the affected side of the medical image, with the midpubic line of the hip joint as the center line. The healthy femur sub-image of the template image marked with the femur stem is mapped onto the affected side of the medical image with the mid-pubic line of the hip joint as the center line, covering the affected femur region in the hip joint sub-image. Based on the positional relationship between the femoral stem and the acetabular cup when they are correctly assembled in the target prosthesis, the position of the contralateral femoral sub-image and / or the position of the hip joint sub-image are adjusted in the longitudinal axis of the femoral neck in the medical image so that the upper center of the proximal femoral segment in the template image marked in the medical image coincides with the center of the acetabular cup. And rotate the healthy femur sub-map and / or the hip joint sub-map so that the angle between the femoral anatomical axis of the template map of the femoral stem and the midpubic line of the hip joint is within a specified angle range.

2. The method as described in claim 1, characterized in that, Based on the medical image, the location and structural parameters of key points in the medical image are determined, specifically including: Based on the medical image, identify the locations of key points and corresponding structural parameters in the medical image; The measured value of the structural parameter is determined based on the position corresponding to the structural parameter; Determine the magnification of the medical image; The measured values ​​of the structural parameters are corrected for magnification based on the magnification to obtain the structural parameters.

3. The method as described in claim 1, characterized in that, The key points include at least the femoral head center and the lesser trochanter key points; the structural parameters include at least one of the following: femoral head diameter, diameter of the narrowest part of the transition portion, inner diameter of the isthmus medullary canal, eccentricity, neck-shaft angle, and difference in leg length.

4. The method as described in claim 1, characterized in that, Based on the structural parameters and the size parameters of each candidate prosthesis, a matching target prosthesis is determined, specifically including: For each candidate prosthesis, determine the structural parameters of the healthy side corresponding to each dimensional parameter of the candidate prosthesis; Compare the corresponding dimensional parameters with the structural parameters to determine the difference; Based on the determined differences, the overall comparison result of the candidate prosthesis is determined; Based on the comprehensive comparison results of each candidate prosthesis, the matching candidate prosthesis is determined as the target prosthesis.

5. A computer program product, characterized in that, When the computer program product is executed by a processor, it implements the method described in any one of claims 1 to 4.

6. An electronic device, characterized in that, The invention includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the program to implement the method described in any one of claims 1 to 4.

Images