TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion

Abstract

The application provides a TKA postoperative lower limb three-dimensional force line evaluation method and system based on multi-modal data fusion and a computer readable storage medium. The TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion comprises the following steps: acquiring a double lower limb CT image of a patient before total knee arthroplasty; wherein the coverage range of the double lower limbs is from above the hip joint to below the ankle joint; performing three-dimensional reconstruction on the double lower limb CT image to clearly display each bone and surrounding soft tissue structure of the lower limb; collecting anteroposterior and lateral X-ray images of the patient's double lower limbs in a weight-bearing position by using a double-plane lower limb full-length X-ray acquisition system to determine the spatial relationship between the bones and the prosthesis of the lower limb in a weight-bearing state; fusing and analyzing the CT reconstruction data and the data collected by the double-plane lower limb full-length X-ray acquisition system to form a fusion image in a three-dimensional space, and accurately calculating the angles of the femoral prosthesis, tibial prosthesis and lower limb force line in the three-dimensional space after TKA.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of lower limb three-dimensional force line evaluation after TKA, and particularly relates to a lower limb three-dimensional force line evaluation method and system after TKA based on multi-modal data fusion and a computer readable storage medium. BACKGROUND

[0002] At present, lower limb force line evaluation after total knee arthroplasty (TKA) is crucial for judging the recovery of knee function, the stability of the prosthesis and predicting the service life of the prosthesis. The existing technologies mainly have the following methods:

[0003] (1) Conventional X-ray examination: Taking knee joint anteroposterior and lateral X-ray films, the lower limb force line angle is estimated by measuring the connecting line of some specific anatomical landmark points (such as the center of the femoral head, the center of the knee joint, the center of the ankle joint, etc.).

[0004] Disadvantages: X-ray film is a two-dimensional image, which cannot accurately reflect the real force line situation of the lower limb in three-dimensional space, and the measurement error is large, especially when evaluating the force line in the sagittal and axial positions, there is obvious limitation.

[0005] (2) CT scanning: After CT scanning of the knee joint, the image is reconstructed, and the relative position of the knee joint and part of the lower limb skeleton is analyzed to infer the force line.

[0006] Disadvantages: CT scanning lacks weight-bearing position information and cannot accurately simulate the force line situation under the actual standing state of the human body. At the same time, CT scanning has metal artifacts, which will interfere with the measurement results.

[0007] The existing technologies mainly have the following deficiencies when measuring the three-dimensional force line of the lower limb after TKA:

[0008] (1) Unable to evaluate three-dimensional force line: unable to accurately obtain the real overall force line angle of the lower limb in multiple planes such as sagittal, coronal and axial positions, which affects the accurate judgment of the mechanical state of the knee joint, and may lead to uneven prosthesis wear, loosening and other complications.

[0009] (2) Lack of weight-bearing position measurement: cannot reflect the actual force line changes of the lower limb under weight-bearing state, which is very important for evaluating the performance of the prosthesis in daily activities, because the lower limb force line will change under weight-bearing, and the existing technology cannot accurately capture this change.

[0010] (3) Incomplete data: single-plane imaging method cannot fully display the complex spatial relationship between the lower limb bones, prosthesis and soft tissues, which is not conducive to comprehensive evaluation of the overall state of the knee joint and lower limb, and some potential influencing factors may be missed. SUMMARY

[0011] The embodiment of the application provides a TKA postoperative lower limb three-dimensional force line evaluation method, system and computer readable storage medium based on multi-modal data fusion, which can accurately obtain the real overall force line angle of the lower limb in multiple planes such as the sagittal plane, the coronal plane and the axial plane, and perform three-dimensional force line evaluation; can reflect the actual force line change of the lower limb in the weight-bearing state; can comprehensively display the complex spatial relationship among the bones, the prosthesis and the soft tissue of the lower limb, and is beneficial to comprehensive evaluation of the knee joint and the overall state of the lower limb.

[0012] In a first aspect, the embodiment of the application provides a TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion, comprising:

[0013] Obtaining the CT images of the lower limbs of a patient before total knee arthroplasty; wherein the coverage range of the lower limbs is from above the hip joint to below the ankle joint;

[0014] Performing three-dimensional reconstruction on the CT images of the lower limbs to clearly display the bone and surrounding soft tissue structure of the lower limbs;

[0015] Using a two-plane lower limb full-length X-ray acquisition system, acquiring the anteroposterior and lateral X-ray images of the lower limbs of the patient in the weight-bearing position, and determining the spatial relationship of the bones and the prosthesis of the lower limbs in the weight-bearing state;

[0016] Fusing and analyzing the CT reconstruction data and the data acquired by the two-plane lower limb full-length X-ray acquisition system to form a fusion image in three-dimensional space, and accurately calculating the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA.

[0017] Optionally, the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA are accurately calculated, and at least include:

[0018] Before operation:

[0019] Coronal plane: HKA (the included angle between the femoral mechanical axis and the tibial mechanical axis) of the lower limb, LDFA, MPTA and JLO;

[0020] Sagittal plane: tibial plateau retroversion angle and sagittal force line;

[0021] Axial plane: femoral torsion angle, tibial torsion angle and femoral-tibial rotation angle;

[0022] After operation:

[0023] Postoperative HKA angle, postoperative coronal plane femoral component angle and postoperative coronal plane tibial component angle;

[0024] Postoperative sagittal plane femoral component angle, postoperative sagittal plane tibial component angle and postoperative sagittal force line;

[0025] Postoperative femoral distal prosthesis rotation angle; postoperative proximal tibial prosthesis rotation angle; relative rotation angle of femoral prosthesis and tibial prosthesis.

[0026] Optionally, a CT image of the lower limbs of the patient before total knee arthroplasty is obtained, and the CT image of the lower limbs is three-dimensionally reconstructed, comprising:

[0027] The patient is supine on the CT scanning bed, and CT scanning of the lower limbs of the patient is performed according to the standard scanning protocol, ranging from above the hip joint to below the ankle joint;

[0028] The scanning data is three-dimensionally reconstructed by using professional software, and the structures of the bones and surrounding soft tissues of the lower limbs are clearly displayed.

[0029] Optionally, a biplane lower limb full-length X-ray acquisition system is used to acquire the anteroposterior and lateral X-ray images of the lower limbs of the patient in the weight-bearing position, comprising:

[0030] The patient stands on the biplane lower limb full-length X-ray acquisition system, adjusts the posture to the required standard weight-bearing position, and ensures that the lower limbs are uniformly stressed;

[0031] The anteroposterior and lateral X-ray images of the lower limbs of the patient are acquired, and the overall morphology of the lower limbs, especially the knee joint and adjacent parts, is clearly displayed.

[0032] Optionally, the CT reconstruction data and the data acquired by the biplane lower limb full-length X-ray acquisition system are fused and analyzed to form a fused image in three-dimensional space, and the angles of the femoral prosthesis, the tibial prosthesis and the lower limb alignment in three-dimensional space after TKA are accurately calculated, comprising:

[0033] The CT reconstruction data and the data acquired by the biplane lower limb full-length X-ray acquisition system are input into the trained deep learning multi-modal data registration fusion model for image registration, correction and data format conversion, so that the two data can be accurately corresponded, the errors caused by different imaging methods are eliminated, and the angles of the femoral prosthesis, the tibial prosthesis and the lower limb alignment in three-dimensional space after TKA are accurately calculated.

[0034] Optionally, the deep learning multi-modal data registration fusion model comprises:

[0035] The first network branch is used for correcting, data format converting and feature map extracting the CT reconstruction data to obtain the first feature map;

[0036] The second network branch is used for correcting, data format converting and feature map extracting the data acquired by the biplane lower limb full-length X-ray acquisition system to obtain the second feature map;

[0037] The lower limb three-dimensional force line evaluation network is configured to register and fuse the first feature map and the second feature map, and perform angle evaluation of the lower limb force line in the three-dimensional space according to a registration and fusion result.

[0038] Optionally, after the angle of the lower limb force line in the three-dimensional space is accurately calculated, the method further includes:

[0039] The angle calculation result of the lower limb force line in the three-dimensional space is displayed on a screen in a graphical manner, including angle information of the lower limb force line in the three-dimensional space, and intuitively displaying the lower limb force line.

[0040] A detailed analysis report is generated, including at least patient basic information, image data, measured angles and analysis conclusions, for reference by a clinician, and for archiving and subsequent comparative analysis.

[0041] In a second aspect, the embodiments of the present application provide a TKA postoperative lower limb three-dimensional force line evaluation system based on multi-modal data fusion, including:

[0042] A CT image acquisition module is configured to acquire CT images of both lower limbs of a patient before total knee arthroplasty; wherein the coverage range of both lower limbs is from above the hip joint to below the ankle joint.

[0043] A three-dimensional reconstruction module is configured to perform three-dimensional reconstruction on the CT images of both lower limbs, to clearly display the bone and surrounding soft tissue structures of the lower limbs.

[0044] An X-ray image acquisition module is configured to use a double-plane lower limb full-length X-ray acquisition system to acquire anteroposterior and lateral X-ray images of both lower limbs of the patient in a weight-bearing position, to determine the spatial relationship between the bones and the prosthesis of the lower limbs in a weight-bearing state.

[0045] A lower limb force line angle evaluation module is configured to fuse and analyze the CT reconstruction data and the data acquired by the double-plane lower limb full-length X-ray acquisition system, to form a fusion image in a three-dimensional space, and to accurately calculate the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA.

[0046] In a third aspect, the embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores computer program instructions, which are executed by a processor to implement a TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion.

[0047] The TKA postoperative lower limb three-dimensional force line evaluation method, system and computer readable storage medium based on multi-modal data fusion of the embodiment of the application can accurately obtain the real overall force line angle of the lower limb in multiple planes such as the sagittal plane, the coronal plane and the axial plane, and perform three-dimensional force line evaluation; can reflect the actual force line change of the lower limb in the weight-bearing state; can comprehensively display the complex spatial relationship between each bone of the lower limb, the prosthesis and the soft tissue, and is beneficial to the comprehensive evaluation of the knee joint and the overall state of the lower limb.

[0048] The TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion comprises:

[0049] Obtain the CT images of the double lower limbs of the patient before total knee arthroplasty; wherein the coverage range of the double lower limbs is from above the hip joint to below the ankle joint;

[0050] Perform three-dimensional reconstruction on the CT images of the double lower limbs to clearly display each bone of the lower limb and the surrounding soft tissue structure;

[0051] Use a double-plane lower limb full-length X-ray acquisition system to acquire the anteroposterior and lateral X-ray images of the double lower limbs of the patient in the weight-bearing position, and determine the spatial relationship of the bones and the prosthesis of the lower limb in the weight-bearing state;

[0052] Fuse and analyze the CT reconstruction data and the data acquired by the double-plane lower limb full-length X-ray acquisition system to form a fusion image in three-dimensional space, and accurately calculate the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in three-dimensional space after TKA. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0054] Figure 1 is a flowchart of the TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion provided by an embodiment of the application;

[0055] Figure 2 is a schematic diagram of a fusion image in three-dimensional space provided by an embodiment of the application;

[0056] Figure 3 is a schematic diagram of the measurable angles provided by an embodiment of the application;

[0057] Figure 4 is a schematic diagram of the postoperative HKA angle provided by an embodiment of the application;

[0058] Figure 5 is a postoperative coronal femoral component angle diagram provided by an embodiment of the present application;

[0059] Figure 6 is a postoperative coronal tibial component angle diagram provided by an embodiment of the present application;

[0060] Figure 7 is a postoperative sagittal femoral component angle diagram provided by an embodiment of the present application;

[0061] Figure 8 is a postoperative sagittal tibial component angle diagram provided by an embodiment of the present application;

[0062] Figure 9 is a postoperative distal femoral prosthesis rotation angle diagram provided by an embodiment of the present application;

[0063] Figure 10 is a postoperative proximal tibial prosthesis rotation angle diagram provided by an embodiment of the present application;

[0064] Figure 11 is a structure diagram of a deep learning multi-modal data registration fusion model provided by an embodiment of the present application;

[0065] Figure 12 is a structure diagram of a TKA postoperative lower extremity three-dimensional force line evaluation system based on multi-modal data fusion provided by an embodiment of the present application. DETAILED DESCRIPTION

[0066] The features and exemplary embodiments of various aspects of the present application will be described in detail below, in order to make the purposes, technical solutions and advantages of the present application more clear and apparent, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, but not to limit the present application. For those skilled in the art, the present application can be implemented without some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by showing examples of the present application.

[0067] It is to be noted that, in the present document, relational terms such as first and second, and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0068] To solve the problems in the prior art, an embodiment of the present application provides a TKA postoperative lower limb three-dimensional force line evaluation method and system based on multi-modal data fusion and a computer readable storage medium. First, the TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion provided by the embodiment of the present application is introduced.

[0069] Figure 1 A flowchart of the TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion provided by an embodiment of the present application is shown. As shown in Figure 1 The TKA postoperative lower limb three-dimensional force line evaluation method based on multi-modal data fusion comprises the following steps.

[0070] S101, acquiring a CT image of both lower limbs of a patient before total knee arthroplasty; wherein the coverage range of both lower limbs is from above the hip joint to below the ankle joint;

[0071] S102, performing three-dimensional reconstruction on the CT image of both lower limbs to clearly display the bone and surrounding soft tissue structure of the lower limbs;

[0072] The CT three-dimensional reconstruction of both lower limbs provides information of the knee joint and the entire lower limb bone, including the shape and position of each bone.

[0073] In one embodiment, the CT image of both lower limbs of the patient before total knee arthroplasty is acquired, and the three-dimensional reconstruction on the CT image of both lower limbs comprises the following steps.

[0074] The patient lies on the CT scanning bed, and CT scanning is performed on the lower limbs of the patient according to a standard scanning protocol, with the range from above the hip joint to below the ankle joint;

[0075] The scanning data is three-dimensionally reconstructed by using professional software to clearly display the bone and surrounding soft tissue structure of the lower limbs.

[0076] S103, collecting the anteroposterior and lateral X-ray images of the double lower limbs of the patient in the weight-bearing position by using the biplane lower limb full-length X-ray acquisition system, and determining the spatial relationship between the bones and the prosthesis of the lower limbs in the weight-bearing state;

[0077] The biplane lower limb full-length X-ray acquisition system acquires the anteroposterior and lateral X-ray images of the double lower limbs in the weight-bearing position, determines the spatial relationship between the bones and the prosthesis of the lower limbs in the weight-bearing state, and provides a weight-bearing position reference for three-dimensional force line calculation.

[0078] In one embodiment, the anteroposterior and lateral X-ray images of the double lower limbs of the patient in the weight-bearing position are collected by using the biplane lower limb full-length X-ray acquisition system, including:

[0079] The patient stands on the biplane lower limb full-length X-ray acquisition system, adjusts the posture to the required standard weight-bearing position, and ensures that the double lower limbs are uniformly stressed;

[0080] The anteroposterior and lateral X-ray images of the double lower limbs of the patient are collected to ensure that the images clearly show the overall morphology of the lower limbs, especially the knee joint and adjacent parts.

[0081] S104, fusing and analyzing the CT reconstruction data and the biplane lower limb full-length X-ray acquisition system data to form a fusion image in a three-dimensional space, and accurately calculating the angles of the femoral prosthesis, tibial prosthesis and lower limb force line in the three-dimensional space after TKA.

[0082] Figure 2 is a schematic diagram of the fusion image in a three-dimensional space provided by one embodiment of the present application.

[0083] Figure 3 is a schematic diagram of the measurable angles provided by one embodiment of the present application.

[0084] In one embodiment, the angles of the femoral prosthesis, tibial prosthesis and lower limb force line in the three-dimensional space after TKA are accurately calculated, and at least include:

[0085] Preoperative:

[0086] Coronal plane: HKA (the included angle between the femoral mechanical axis and the tibial mechanical axis) of the lower limb, LDFA, MPTA, JLO;

[0087] Sagittal plane: tibial plateau retroversion angle, sagittal force line;

[0088] Axial plane: femoral torsion angle, tibial torsion angle, femoral-tibial rotation angle;

[0089] Postoperative:

[0090] Postoperative HKA angle; postoperative coronal plane femoral component angle; postoperative coronal plane tibial component angle;

[0091] Postoperative sagittal femoral component angle; postoperative sagittal tibial component angle; postoperative sagittal alignment;

[0092] Postoperative femoral distal prosthesis rotation angle; postoperative proximal tibial prosthesis rotation angle; relative rotation angle of femoral prosthesis and tibial prosthesis.

[0093] Wherein, the postoperative HKA angle diagram is shown in Figure 4 The postoperative coronal femoral component angle diagram is shown in Figure 5 The postoperative coronal tibial component angle diagram is shown in Figure 6 The postoperative sagittal femoral component angle diagram is shown in Figure 7 The postoperative sagittal tibial component angle diagram is shown in Figure 8

[0094] The postoperative femoral distal prosthesis rotation angle diagram is shown in Figure 9 sTEA: the line connecting the highest point of the medial epicondyle and the highest point of the lateral epicondyle; the line connecting the medial posterior condyle and the lateral posterior condyle of the femoral prosthesis; the angle between the above two lines is the femoral prosthesis distal rotation angle.

[0095] The postoperative proximal tibial prosthesis rotation angle diagram is shown in Figure 10 The rotation angle of the tibial prosthesis relative to the inner 1 / 3 of the tibial tuberosity.

[0096] The tibial prosthesis longitudinal axis (Line TA) is the perpendicular line of the tibial prosthesis posterior condyle axis (tPCA).

[0097] Determine the ellipse closest to the tibial plateau size in the tibial osteotomy plane, and mark the center (C). Project the center to the tibial tuberosity plane, and connect the projection point of the tibial plateau center in the plane with the inner 1 / 3 point of the tibial tuberosity, which is the tibial tuberosity axis (Line CB).

[0098] Project the tibial prosthesis longitudinal axis (Line TA) to the tibial tuberosity level. The angle between the tibial prosthesis longitudinal axis (Line TA) and the tibial tuberosity axis (Line CB) is the rotation angle of the tibial prosthesis relative to the inner 1 / 3 of the tibial tuberosity.

[0099] Fuse CT reconstruction data and biplane lower extremity full-length X-ray acquisition system data for analysis by a specific algorithm, accurately calculate the angle of the lower extremity overall alignment in the sagittal, coronal and axial planes, and consider the influence of knee flexion, internal and external rotation and other movement states on the alignment.

[0100] ​Data fusion and processing: import CT reconstruction data and biplane lower extremity full-length X-ray acquisition system data into the data fusion and processing unit; perform image registration, correction and data format conversion to accurately correspond the two data and eliminate errors caused by different imaging methods.

[0101] Three-dimensional force line calculation: the algorithm automatically identifies the femoral anatomical axis, tibial anatomical axis, lower extremity force line and prosthesis-related axis; calculates the angle of the overall lower extremity force line in the sagittal, coronal and axial directions according to the preset formula, including but not limited to:

[0102] Preoperative:

[0103] Coronal plane: lower extremity HKA (the included angle between the femoral mechanical axis and the tibial mechanical axis); LDFA, MPTA, JLO;

[0104] Sagittal plane: tibial plateau retroversion angle, sagittal force line;

[0105] Axial plane: femoral torsion angle, tibial torsion angle, femoral-tibial rotation angle;

[0106] Postoperative:

[0107] Postoperative HKA angle; postoperative coronal femoral component angle; postoperative coronal tibial component angle;

[0108] Postoperative sagittal femoral component angle; postoperative sagittal tibial component angle; postoperative sagittal force line;

[0109] Postoperative femoral distal prosthesis rotation angle; postoperative tibial proximal prosthesis rotation angle; relative rotation angle of femoral prosthesis and tibial prosthesis.

[0110] In one embodiment, CT reconstruction data and biplane lower extremity full-length X-ray acquisition system data are fused and analyzed to form a fusion image in three-dimensional space, and the angles of the femoral prosthesis, tibial prosthesis and lower extremity force line in three-dimensional space after TKA are accurately calculated, including:

[0111] CT reconstruction data and biplane lower extremity full-length X-ray acquisition system data are input into the trained deep learning multi-modal data registration fusion model for image registration, correction and data format conversion, so that the two data can be accurately corresponded, errors caused by different imaging methods are eliminated, and the angles of the femoral prosthesis, tibial prosthesis and lower extremity force line in three-dimensional space after TKA are accurately calculated.

[0112] Figure 11 FIG. 1 is a structural schematic diagram of a deep learning multi-modal data registration fusion model provided in an embodiment of the present application.

[0113] In one embodiment, the deep learning multi-modal data registration fusion model comprises:

[0114] a first network branch for correcting, data format converting and feature map extracting the CT reconstruction data to obtain a first feature map;

[0115] a second network branch for correcting, data format converting and feature map extracting the data collected by the biplane lower extremity full-length X-ray acquisition system to obtain a second feature map;

[0116] a lower extremity three-dimensional force line evaluation network for registering and fusing the first feature map and the second feature map, and evaluating the angle of the lower extremity force line in the three-dimensional space according to the registration and fusion result.

[0117] In one embodiment, after accurately calculating the angle of the lower extremity force line in the three-dimensional space, further comprising:

[0118] displaying the calculation result of the angle of the lower extremity force line in the three-dimensional space on the screen in a graphical manner, including the angle information of the lower extremity force line in the three-dimensional space, and intuitively displaying the lower extremity force line situation;

[0119] generating a detailed analysis report containing at least patient basic information, image data, measured angle and analysis conclusion for the reference of clinicians, facilitating archiving and subsequent comparative analysis.

[0120] The result is displayed and output: the measurement result is displayed on the screen in a graphical manner, including the angle information of the lower extremity force line in the three-dimensional space, and intuitively displaying the lower extremity force line situation; a detailed PDF report is generated, containing patient basic information, image data, measured angle and analysis conclusion, etc., for the reference of clinicians, facilitating archiving and subsequent comparative analysis.

[0121] The core innovation points of the present application include:

[0122] (1) Innovation of examination method: for the first time, the biplane lower extremity full-length X-ray acquisition system is combined with real-world data reconstruction of bones and prostheses through artificial intelligence, giving full play to the advantages of both, and a monitoring method for three-dimensional force line of prostheses after artificial knee arthroplasty is created.

[0123] (2) Accurate measurement in weight-bearing position: emphasizing the measurement of overall force line in weight-bearing position, which is more in line with the physiological state of the human body, providing reliable basis for evaluating the performance of the knee joint and lower extremity in actual use, and helping to improve the service life of the prosthesis and the function of the knee joint.

[0124] (3) Intelligent algorithm processing: advanced image processing and analysis algorithms are used to automatically identify each bone, prosthesis and related anatomical landmark points of the lower extremity, accurately calculate the three-dimensional force line angle, reduce human error, and improve measurement efficiency and accuracy.

[0125] In the test and verification process, multiple cases of TKA postoperative patients were tested, and the measurement results of the method were compared with the traditional measurement method and the theoretically calculated force line angle of simulation. The results showed that:

[0126] Compared with the traditional X-ray measurement method, the angle error is reduced by more than 80%, and the deviation from the actual implantation angle during the operation is within ±1°.

[0127] In the repeatability test of different measurement personnel and different time points, the consistency of the measurement results (ICC value) is greater than 0.98, with high stability and reliability.

[0128] Therefore, compared with the prior art, the present application has the following significant differences:

[0129] (1) The measurement accuracy is greatly improved: it can be accurate to within ±1°, which significantly improves the accuracy of the prior art, and can more accurately evaluate the lower limb force line state, providing strong support for clinical decision-making.

[0130] (2) Comprehensive force line evaluation: it can simultaneously analyze the angles of the lower limb force line in multiple planes and its relationship with each component (skeleton, prosthesis, etc.), providing more comprehensive evaluation of the knee joint and lower limb state, which helps to find potential problems and intervene in time.

[0131] (3) Strong clinical practicability: more accurate measurement results help doctors develop personalized treatment plans, such as adjusting prosthesis position, optimizing rehabilitation training plan, etc., to improve the rehabilitation quality and quality of life of TKA postoperative patients.

[0132] Figure 12 is a structural schematic diagram of a TKA postoperative lower limb three-dimensional force line evaluation system based on multi-modal data fusion provided by an embodiment of the present application;

[0133] The TKA postoperative lower limb three-dimensional force line evaluation system based on multi-modal data fusion comprises:

[0134] The CT image acquisition module 1201 is configured to acquire CT images of both lower limbs of a patient before total knee arthroplasty; wherein the coverage range of both lower limbs is from above the hip joint to below the ankle joint;

[0135] The three-dimensional reconstruction module 1202 is configured to perform three-dimensional reconstruction on the CT images of both lower limbs to clearly display the structures of each bone and surrounding soft tissue of the lower limbs;

[0136] The X-ray image acquisition module 1203 is configured to use a double-plane lower limb full-length X-ray acquisition system to acquire anteroposterior and lateral X-ray images of both lower limbs of a patient in a weight-bearing position, and determine the spatial relationship between the bones and the prosthesis of the lower limbs in the weight-bearing state.

[0137] The lower limb force line angle evaluation module 1204 is used for fusing and analyzing CT reconstruction data and biplane lower limb full-length X-ray acquisition system acquisition data, forming a fusion image in three-dimensional space, and accurately calculating the angles of the femoral prosthesis, tibial prosthesis and lower limb force line in three-dimensional space after TKA.

[0138] The above is only a specific implementation of the present application, and those skilled in the art can clearly understand that the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present application, and these modifications or replacements should be covered within the protection scope of the present application.

Claims

1. A method for evaluating the three-dimensional force line of the lower extremity after TKA based on multi-modal data fusion, characterized in that, The application relates to a method for accurately calculating the angles of a femoral prosthesis, a tibial prosthesis and a lower limb force line in a three-dimensional space after total knee arthroplasty (TKA), and a deep learning multi-modal data registration and fusion model. The method comprises the following steps: acquiring CT images of both lower limbs of a patient before TKA; wherein the coverage range of both lower limbs is from above the hip joint to below the ankle joint; performing three-dimensional reconstruction on the CT images of both lower limbs to clearly show the bone and surrounding soft tissue structures of the lower limbs; acquiring anteroposterior and lateral X-ray images of both lower limbs of the patient in a weight-bearing position by using a dual-plane lower limb full-length X-ray acquisition system to determine the spatial relationship between the bones and the prosthesis of the lower limbs in a weight-bearing state; fusing and analyzing the CT reconstruction data and the data acquired by the dual-plane lower limb full-length X-ray acquisition system to form a fusion image in a three-dimensional space and accurately calculate the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA; wherein the fusion and analysis of the CT reconstruction data and the data acquired by the dual-plane lower limb full-length X-ray acquisition system to form a fusion image in a three-dimensional space and accurately calculate the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA comprises the following steps: inputting the CT reconstruction data and the data acquired by the dual-plane lower limb full-length X-ray acquisition system into a trained deep learning multi-modal data registration and fusion model for image registration, correction and data format conversion, so that the two data can be accurately corresponded, the errors caused by different imaging methods can be eliminated, and the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA can be accurately calculated.

2. The TKA postoperative lower limb three-dimensional alignment evaluation method based on multi-modal data fusion according to claim 1, characterized in that, The deep learning multi-modal data registration and fusion model comprises: a first network branch for correcting, data format converting and feature map extracting the CT reconstruction data to obtain a first feature map; a second network branch for correcting, data format converting and feature map extracting the data acquired by the dual-plane lower limb full-length X-ray acquisition system to obtain a second feature map; and a lower limb three-dimensional force line evaluation network for registering and fusing the first feature map and the second feature map and evaluating the angles of the lower limb force line in the three-dimensional space according to the registration and fusion result. The accurate calculation of the angles of the femoral prosthesis, the tibial prosthesis and the lower limb force line in the three-dimensional space after TKA at least comprises the following steps: before operation: in the coronal plane: lower limb HKA (the included angle between the femoral mechanical axis and the tibial mechanical axis); LDFA, MPTA and JLO; in the sagittal plane: tibial plateau retroversion angle and sagittal force line; in the axial plane: femoral torsion angle, tibial torsion angle and femoral-tibial rotation angle; after operation: postoperative HKA angle; postoperative coronal plane femoral component angle; postoperative coronal plane tibial component angle; postoperative sagittal plane femoral component angle; postoperative sagittal plane tibial component angle; postoperative sagittal force line; 3. The TKA postoperative lower limb three-dimensional alignment evaluation method based on multi-modal data fusion according to claim 1, characterized in that, postoperative femoral distal prosthesis rotation angle; postoperative tibial proximal prosthesis rotation angle; relative rotation angle of the femoral prosthesis and the tibial prosthesis. The method comprises the following steps: the patient lies on the CT scanning bed, and CT scanning is performed on the lower limbs of the patient according to a standard scanning protocol, and the scanning range is from above the hip joint to below the ankle joint; three-dimensional reconstruction is performed on the scanning data by using professional software to clearly show the bone and surrounding soft tissue structures of the lower limbs.

4. The TKA postoperative lower limb three-dimensional alignment evaluation method based on multi-modal data fusion according to claim 1, characterized in that, The system comprises: The CT image acquisition module is configured to acquire CT images of the patient's lower limbs before total knee arthroplasty, wherein the coverage range of the lower limbs is from above the hip joint to below the ankle joint. The three-dimensional reconstruction module is configured to perform three-dimensional reconstruction on the CT images of the lower limbs to clearly display the bone structures and surrounding soft tissue structures of the lower limbs.

5. The TKA postoperative lower limb three-dimensional alignment evaluation method based on multi-modal data fusion according to claim 2, characterized in that, The X-ray image acquisition module is configured to acquire the frontal and lateral X-ray images of the patient's lower limbs in the weight-bearing position using a dual-plane full-length lower limb X-ray acquisition system to determine the spatial relationship between the bones and the prosthesis in the weight-bearing state. The lower limb force line angle evaluation module is configured to fuse and analyze the CT reconstruction data and the data acquired by the dual-plane full-length lower limb X-ray acquisition system to form a fusion image in three-dimensional space and accurately calculate the angles of the femoral prosthesis, tibial prosthesis, and lower limb force line in three-dimensional space after TKA. The deep learning multi-modal data registration and fusion model comprises:

6. A TKA postoperative lower limb three-dimensional force line evaluation system based on multi-modal data fusion, characterized in that, The first network branch is configured to correct, convert the data format, and extract the feature map of the CT reconstruction data to obtain a first feature map. The second network branch is configured to correct, convert the data format, and extract the feature map of the data acquired by the dual-plane full-length lower limb X-ray acquisition system to obtain a second feature map. The lower limb three-dimensional force line evaluation network is configured to register and fuse the first feature map and the second feature map and evaluate the angle of the lower limb force line in three-dimensional space based on the registration and fusion result. ​ ​ ​ ​ 7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer program instructions, and the computer program instructions are executed by a processor to implement the method for evaluating three-dimensional force lines of a lower limb after TKA based on multi-modal data fusion according to any one of claims 1-5.

Images