TKA post-operation lower limb three-dimensional force line assessment method based on multi-modal data fusion

Abstract

The invention provides a TKA postoperative lower limb three-dimensional force line assessment method and system based on multi-modal data fusion and a computer readable storage medium. The TKA post-operation lower limb three-dimensional force line evaluation method based on multi-modal data fusion comprises the following steps: acquiring double lower limb CT images of a patient before total knee arthroplasty; wherein the coverage range of the two lower limbs is from the upper part of the hip joint to the lower part of the ankle joint; performing three-dimensional reconstruction on the double-lower-limb CT image to clearly display each skeleton and surrounding soft tissue structure of the lower limbs; a biplane lower limb full-length X-ray acquisition system is utilized to acquire normal position and lateral position X-ray images of two lower limbs of a patient at a load-bearing position, and the space relation between skeletons and prostheses of the lower limbs in the load-bearing state is determined; and performing fusion analysis on CT reconstruction data and data acquired by a biplane lower limb full-length X-ray acquisition system to form a fusion image in a three-dimensional space, and accurately calculating angles of a thighbone prosthesis, a tibia prosthesis and a lower limb force line in the three-dimensional space after the TKA operation.

Description

Technical Field

[0001] This application belongs to the field of three-dimensional lower limb alignment assessment after total knee arthroplasty (TKA), and particularly relates to a method, system, and computer-readable storage medium for three-dimensional lower limb alignment assessment after TKA based on multimodal data fusion. Background Art

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

[0003] (1) Conventional X-ray examination: Taking anteroposterior and lateral X-ray films of the knee joint, and estimating the lower limb alignment angle by measuring the connection lines 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: The X-ray film is a two-dimensional image, which cannot accurately reflect the true alignment of the lower limb in the three-dimensional space, and the measurement error is large. There are obvious limitations especially when evaluating the alignment in the sagittal and axial planes.

[0005] (2) CT scan: Reconstructing the image after CT scanning of the knee joint, and analyzing the relative positions of the knee joint and some lower limb bones to infer the alignment.

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

[0007] When the existing technologies measure the three-dimensional lower limb alignment after TKA, the following main deficiencies exist:

[0008] (1) Unable to perform three-dimensional alignment assessment: Unable to accurately obtain the true overall alignment angles of the lower limb in multiple planes such as the sagittal, coronal, and axial planes, which affects the accurate judgment of the knee joint mechanical state, and may further lead to complications such as uneven wear and loosening of the prosthesis.

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

[0010] (3) Incomplete data: The single-plane imaging method cannot comprehensively display the complex spatial relationships among the lower limb bones, prosthesis, and soft tissues, which is not conducive to the comprehensive assessment of the overall state of the knee joint and lower limb, and may miss some potential influencing factors. Summary of the Invention

[0011] The embodiments of the present application provide a method, system and computer-readable storage medium for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion, which can accurately obtain the true overall alignment angles of the lower limb in multiple planes such as the sagittal plane, coronal plane and axial plane for three-dimensional alignment evaluation; can reflect the actual alignment changes of the lower limb under the weight-bearing state; and can comprehensively display the complex spatial relationships among the various bones, prostheses and soft tissues of the lower limb, which is beneficial to comprehensively evaluating the overall state of the knee joint and the lower limb.

[0012] In a first aspect, the embodiments of the present application provide a method for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion, including:

[0013] Obtain the CT images of both lower limbs of the patient before total knee arthroplasty; wherein, the coverage range of both lower limbs: from above the hip joint to below the ankle joint;

[0014] Perform three-dimensional reconstruction on the CT images of both lower limbs to clearly display the structures of each bone and surrounding soft tissues of the lower limb;

[0015] Use a bi-planar full-length lower limb X-ray acquisition system to collect the anteroposterior and lateral X-ray images of both lower limbs of the patient in the weight-bearing position, and determine the spatial relationships of the bones and prostheses of the lower limb in the weight-bearing state;

[0016] Fuse and analyze the CT reconstruction data and the data collected by the bi-planar full-length lower limb X-ray acquisition system to form a fused image in three-dimensional space, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis and lower limb alignment in three-dimensional space after TKA.

[0017] Optionally, accurately calculating the angles of the femoral prosthesis, tibial prosthesis and lower limb alignment in three-dimensional space after TKA includes at least:

[0018] Before surgery:

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

[0020] Sagittal plane: the posterior tibial plateau angle, the sagittal alignment;

[0021] Axial plane: the femoral torsion angle, the tibial torsion angle, the femur-tibia rotation angle;

[0022] After surgery:

[0023] The postoperative HKA angle; the postoperative femoral component angle in the coronal plane; the postoperative tibial component angle in the coronal plane;

[0024] The postoperative femoral component angle in the sagittal plane; the postoperative tibial component angle in the sagittal plane; the postoperative sagittal alignment;

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

[0026] Optionally, obtain the CT images of both lower limbs of the patient before total knee arthroplasty, and perform three-dimensional reconstruction on the CT images of both lower limbs, including:

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

[0028] Use professional software to perform three-dimensional reconstruction on the scanned data to clearly display the bones and surrounding soft tissue structures of each lower limb.

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

[0030] The patient stands on the biplane full-length lower limb X-ray acquisition system, adjusts the posture to the required standard weight-bearing position to ensure uniform force on both lower limbs;

[0031] Acquire the anteroposterior and lateral X-ray images of both lower limbs of the patient to ensure that the images clearly show the overall shape of the lower limbs, especially the knee joint and adjacent parts.

[0032] Optionally, perform fusion analysis on the CT reconstruction data and the data acquired by the biplane full-length lower limb X-ray acquisition system to form a fused 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, including:

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

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

[0035] The first network branch is used to correct, convert the data format and extract the feature map of the CT reconstruction data to obtain the first feature map;

[0036] The second network branch is used to correct, convert the data format and extract the feature map of the data acquired by the biplane full-length lower limb X-ray acquisition system to obtain the second feature map;

[0037] A three-dimensional lower limb alignment evaluation network is used to register and fuse a first feature map and a second feature map, and evaluate the angle of the lower limb alignment in three-dimensional space according to the registration and fusion result.

[0038] Optionally, after accurately calculating the angle of the lower limb alignment in three-dimensional space, it further includes:

[0039] Display the calculation result of the angle of the lower limb alignment in three-dimensional space graphically on the screen, including the angle information of the lower limb alignment in three-dimensional space, and intuitively display the situation of the lower limb alignment;

[0040] Generate a detailed analysis report, which at least includes patient basic information, image data, measured angles and analysis conclusions, for clinical doctors to refer to, facilitating archiving and subsequent comparative analysis.

[0041] In a second aspect, an embodiment of the present application provides a three-dimensional lower limb alignment evaluation system based on multi-modal data fusion, including:

[0042] A CT image acquisition module for acquiring bilateral lower limb CT images of a patient before total knee arthroplasty; wherein, the coverage range of the bilateral lower limbs: from above the hip joint to below the ankle joint;

[0043] A three-dimensional reconstruction module for performing three-dimensional reconstruction on the bilateral lower limb CT images to clearly display the bones and surrounding soft tissue structures of the lower limbs;

[0044] An X-ray image acquisition module for using a bilateral full-length lower limb X-ray acquisition system to acquire the anteroposterior and lateral X-ray images of the patient's bilateral lower limbs in the weight-bearing position, and determining the spatial relationship between the bones and prostheses of the lower limbs in the weight-bearing state;

[0045] A lower limb alignment angle evaluation module for performing fusion analysis on the CT reconstruction data and the data acquired by the bilateral full-length lower limb X-ray acquisition system to form a fused image in three-dimensional space, and accurately calculating the angles of the femoral prosthesis, tibial prosthesis and lower limb alignment in three-dimensional space after TKA.

[0046] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, a method for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion is implemented.

[0047] The method, system and computer-readable storage medium for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion in the embodiments of the present application can accurately obtain the true overall alignment angles of the lower limb in multiple planes such as the sagittal plane, coronal plane and axial plane for three-dimensional alignment evaluation; can reflect the actual alignment changes of the lower limb under the weight-bearing state; can comprehensively display the complex spatial relationships among the bones, prostheses and soft tissues of the lower limb, which is conducive to comprehensively evaluating the overall state of the knee joint and the lower limb.

[0048] The method for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion includes:

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

[0050] Perform three-dimensional reconstruction on the CT images of the bilateral lower limbs to clearly display the bones and surrounding soft tissue structures of the lower limb;

[0051] Use a bi-planar full-length lower limb X-ray acquisition system to collect the anteroposterior and lateral X-ray images of the bilateral lower limbs of the patient in the weight-bearing position, and determine the spatial relationships of the bones and prostheses of the lower limb in the weight-bearing state;

[0052] Fuse and analyze the CT reconstruction data and the data collected by the bi-planar full-length lower limb X-ray acquisition system to form a fused image in three-dimensional space, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis and lower limb alignment in three-dimensional space after TKA. Description of the Drawings

[0053] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0054] Figure 1 It is a schematic flow chart of the method for evaluating the three-dimensional lower limb alignment after TKA based on multi-modal data fusion provided by an embodiment of the present application;

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

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

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

[0058] Figure 5 It is a schematic diagram of the angle of the femoral component in the coronal plane after surgery provided by an embodiment of the present application;

[0059] Figure 6 It is a schematic diagram of the angle of the tibial component in the coronal plane after surgery provided by an embodiment of the present application;

[0060] Figure 7 It is a schematic diagram of the angle of the femoral component in the sagittal plane after surgery provided by an embodiment of the present application;

[0061] Figure 8 It is a schematic diagram of the angle of the tibial component in the sagittal plane after surgery provided by an embodiment of the present application;

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

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

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

[0065] Figure 12 It is a schematic diagram of the structure of a three-dimensional lower limb force line evaluation system after TKA based on multi-modal data fusion provided by an embodiment of the present application. Detailed implementation manners

[0066] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than 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 intended to provide a better understanding of the present application by showing examples of the present application.

[0067] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

[0068] To solve the problems of the prior art, the embodiments of the present application provide a method, a system and a computer-readable storage medium for evaluating the three-dimensional lower limb force line after TKA based on multi-modal data fusion. First, the method for evaluating the three-dimensional lower limb force line after TKA based on multi-modal data fusion provided by the embodiments of the present application will be introduced below.

[0069] Figure 1 The flowchart of the method for evaluating the three-dimensional lower limb force line after TKA based on multi-modal data fusion provided by an embodiment of the present application is shown. As Figure 1 shown, the method for evaluating the three-dimensional lower limb force line after TKA based on multi-modal data fusion includes:

[0070] S101. Obtain the CT images of both lower limbs of the patient before total knee arthroplasty; wherein, the coverage range of both lower limbs: from above the hip joint to below the ankle joint;

[0071] S102. Perform three-dimensional reconstruction on the CT images of both lower limbs to clearly display the bones and surrounding soft tissue structures of the lower limbs;

[0072] The three-dimensional reconstruction of the CT images of both lower limbs provides information on the knee joint and the entire lower limb bones, including the shapes, positions, etc. of each bone.

[0073] In one embodiment, obtaining the CT images of both lower limbs of the patient before total knee arthroplasty and performing three-dimensional reconstruction on the CT images of both lower limbs includes:

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

[0075] Use professional software to perform three-dimensional reconstruction on the scanned data to clearly display the bones and surrounding soft tissue structures of the lower limbs.

[0076] S103. Use a dual - plane full - length lower limb X - ray acquisition system to acquire the anteroposterior and lateral X - ray images of the patient's weight - bearing lower limbs, and determine the spatial relationship between the bones and prostheses of the lower limbs in the weight - bearing state;

[0077] The dual - plane full - length lower limb X - ray acquisition system obtains the anteroposterior and lateral X - ray images of the weight - bearing lower limbs, determines the spatial relationship between the bones and prostheses of the lower limbs in the weight - bearing state, and provides a weight - bearing reference for three - dimensional mechanical axis calculation.

[0078] In one embodiment, using a dual - plane full - length lower limb X - ray acquisition system to acquire the anteroposterior and lateral X - ray images of the patient's weight - bearing lower limbs includes:

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

[0080] Acquire the anteroposterior and lateral X - ray images of the patient's lower limbs, and ensure that the images clearly show the overall morphology of the lower limbs, especially the knee joint and adjacent parts.

[0081] S104. Perform fusion analysis on the CT reconstruction data and the data acquired by the dual - plane full - length lower limb X - ray acquisition system to form a fused image in three - dimensional space, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis, and lower limb mechanical axis in three - dimensional space after TKA.

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

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

[0084] In one embodiment, accurately calculating the angles of the femoral prosthesis, tibial prosthesis, and lower limb mechanical axis in three - dimensional space after TKA includes at least:

[0085] Pre - operation:

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

[0087] Sagittal plane: Posterior tibial plateau angle, sagittal mechanical axis;

[0088] Axial plane: Femoral torsion angle, tibial torsion angle, femur - tibia rotation angle;

[0089] Post - operation:

[0090] Post - operative HKA angle; Post - operative coronal femoral component angle; Post - operative coronal tibial component angle;

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

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

[0093] Among them, the schematic diagram of the postoperative HKA angle is as shown in Figure 4 ; the schematic diagram of the postoperative coronal femoral component angle is as shown in Figure 5 ; the schematic diagram of the postoperative coronal tibial component angle is as shown in Figure 6 ; the schematic diagram of the postoperative sagittal femoral component angle is as shown in Figure 7 ; the schematic diagram of the postoperative sagittal tibial component angle is as shown in Figure 8 ;

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

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

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

[0097] Determine the ellipse closest to the size of the tibial plateau at the tibial osteotomy plane and mark the center (C), project this center onto the tibial tubercle plane, and connect the projection point of the center of the tibial plateau on this plane with the mid-inner 1 / 3 point of the tibial tubercle, which is the tibial tubercle axis (Line CB).

[0098] Project the longitudinal axis of the tibial prosthesis (Line TA) onto the tibial tubercle layer, and the included angle between the longitudinal axis of the tibial prosthesis (Line TA) and the tibial tubercle axis (Line CB) is the rotation angle of the tibial prosthesis relative to the inner 1 / 3 of the tibial tubercle).

[0099] Fuse and analyze the CT reconstruction data and the data collected by the biplane full-length lower limb X-ray acquisition system through a specific algorithm, accurately calculate the angles of the overall lower limb alignment in key planes such as the sagittal, coronal, and axial planes, and at the same time consider the influence of knee joint flexion / extension, varus / valgus and other movement states on the alignment.

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

[0101] Three-dimensional alignment calculation: The algorithm automatically identifies the femoral anatomical axis, tibial anatomical axis, lower limb alignment, and prosthesis-related axes; calculates the angles of the overall lower limb alignment in the sagittal, coronal, axial, and other directions according to preset formulas, including but not limited to:

[0102] Before surgery:

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

[0104] Sagittal plane: Posterior tibial plateau angle, sagittal alignment;

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

[0106] After surgery:

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

[0108] Postoperative femoral component angle in the sagittal plane; postoperative tibial component angle in the sagittal plane; postoperative sagittal alignment;

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

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

[0111] Input the CT reconstruction data and the data collected by the biplane full-length lower limb X-ray acquisition system into the trained deep learning multi-modal data registration and fusion model for image registration, correction, and data format conversion, so that the two sets of data can accurately correspond, eliminate the errors caused by different imaging methods, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis, and lower limb alignment in three-dimensional space after TKA.

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

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

[0114] The first network branch is used to correct the CT reconstruction data, convert the data format, and extract the feature map to obtain the first feature map;

[0115] The second network branch is used to correct the data collected by the biplane full-length lower limb X-ray acquisition system, convert the data format, and extract the feature map to obtain the second feature map;

[0116] The lower limb three-dimensional mechanical axis evaluation network is used to register and fuse the first feature map and the second feature map, and evaluate the angle of the lower limb mechanical axis in the three-dimensional space according to the registration and fusion result.

[0117] In one embodiment, after accurately calculating the angle of the lower limb mechanical axis in the three-dimensional space, it further includes:

[0118] Displaying the calculation result of the angle of the lower limb mechanical axis in the three-dimensional space in a graphical manner on the screen, including the angle information of the lower limb mechanical axis in the three-dimensional space, and intuitively showing the situation of the lower limb mechanical axis;

[0119] Generating a detailed analysis report, which at least includes the patient's basic information, image data, measured angle, and analysis conclusion, for clinical doctors' reference, facilitating archiving and subsequent comparative analysis.

[0120] Result display and output: The measurement result is displayed in a graphical manner on the screen, including the angle information of the lower limb mechanical axis in the three-dimensional space, intuitively showing the situation of the lower limb mechanical axis; generating a detailed PDF report, including the patient's basic information, image data, measured angle, analysis conclusion, etc., for clinical doctors' reference, facilitating archiving and subsequent comparative analysis.

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

[0122] (1) Innovation in inspection method: For the first time, artificial intelligence is used to combine the biplane full-length lower limb X-ray acquisition system with the real-world data reconstruction of bones and prostheses, giving full play to the advantages of both, and pioneering a method for monitoring the three-dimensional mechanical axis of the prosthesis after total knee arthroplasty.

[0123] (2) Accurate measurement in the weight-bearing position: Emphasize the overall mechanical axis measurement in the weight-bearing position, which is more in line with the human physiological state, provides a reliable basis for evaluating the performance of the knee joint and lower limbs in actual use, and helps to improve the service life of the prosthesis and the knee joint function.

[0124] (3) Intelligent algorithm processing: Adopt advanced image processing and analysis algorithms to automatically identify each bone, prosthesis, and related anatomical landmark points of the lower limb, accurately calculate the three-dimensional mechanical axis angle, reduce human errors, and improve the measurement efficiency and accuracy.

[0125] During the testing and verification process, multiple TKA postoperative patients were tested, and the measurement results of this method were compared with those of traditional measurement methods and the theoretically calculated mechanical axis angles through simulation. The results showed that:

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

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

[0128] Therefore, compared with the existing technologies, the present invention has the following significant differences:

[0129] (1) Greatly improved measurement accuracy: It can be accurate to within ±1°, significantly improving the accuracy compared with the existing technologies, enabling a more accurate assessment of the lower limb mechanical axis state and providing strong support for clinical decision-making.

[0130] (2) Comprehensive mechanical axis assessment: It can simultaneously analyze the angles of the overall lower limb mechanical axis in multiple planes and its relationships with various components (bones, prostheses, etc.), providing a more comprehensive assessment of the knee joint and lower limb states, which helps to detect potential problems and intervene in a timely manner.

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

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

[0133] The three-dimensional lower limb mechanical axis assessment system for TKA postoperative patients based on multi-modal data fusion includes:

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

[0135] A three-dimensional reconstruction module 1202, configured to perform three-dimensional reconstruction on the bilateral lower limb CT images to clearly display the bones and surrounding soft tissue structures of the lower limbs;

[0136] An X-ray image acquisition module 1203, configured to use a bilateral full-length lower limb X-ray acquisition system to acquire anteroposterior and lateral X-ray images of the bilateral lower limbs of the patient in the weight-bearing position, and determine the spatial relationships of the bones and prostheses in the lower limbs in the weight-bearing state;

[0137] The lower limb mechanical axis angle evaluation module 1204 is used to fuse and analyze the CT reconstruction data and the data collected by the biplane full-length lower limb X-ray acquisition system to form a fused image in three-dimensional space, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis and lower limb mechanical axis in three-dimensional space after TKA.

[0138] The above is only the specific implementation manner of the present application. Those skilled in the art can clearly understand that the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present application.

Claims

1. A method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion, characterized in that: include: Obtain CT images of both lower limbs of the patient before total knee replacement surgery; the coverage range of both lower limbs: from above the hip joint to below the ankle joint; Perform three-dimensional reconstruction of the CT images of both lower limbs to clearly display the bones and surrounding soft tissue structures of the lower limbs; Using a dual-plane lower limb full-length X-ray acquisition system, collect anteroposterior and lateral X-ray images of the patient's lower limbs in a weight-bearing position to determine the spatial relationship between the bones and prostheses of the lower limbs in a weight-bearing state; The CT reconstruction data and the data collected by the dual-plane lower limb full-length X-ray acquisition system are fused and analyzed to form a fusion image in three-dimensional space, and the angles of the femoral prosthesis, tibial prosthesis and lower limb force lines in three-dimensional space after TKA surgery are accurately calculated.

2. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 1, characterized in that: Accurately calculate the angles of the femoral prosthesis, tibial prosthesis and lower limb force lines in three-dimensional space after TKA, including at least: Preoperative: Coronal plane: HKA of lower limbs (the angle between the mechanical axis of the femur and the mechanical axis of the tibia); LDFA, MPTA, JLO; Sagittal plane: posterior tilt angle of tibial plateau, sagittal force line; Axis: femoral torsion angle, tibial torsion angle, femoral-tibial rotation angle; After surgery: Postoperative HKA angle; Postoperative coronal femoral component angle; Postoperative coronal tibial component angle; Postoperative sagittal femoral component angle; postoperative sagittal tibial component angle; postoperative sagittal alignment; Postoperative rotation angle of distal femoral prosthesis; postoperative rotation angle of proximal tibial prosthesis; relative rotation angle of femoral prosthesis and tibial prosthesis.

3. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 1, characterized in that: Obtain CT images of both lower limbs of the patient before total knee replacement surgery, and perform three-dimensional reconstruction of the CT images of both lower limbs, including: The patient lay supine on the CT scanning bed, and a CT scan of both lower limbs of the patient was performed according to the standard scanning protocol, ranging from above the hip joint to below the ankle joint; Professional software is used to reconstruct the scan data in three dimensions to clearly display the bones of the lower limbs and the surrounding soft tissue structures.

4. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 1, characterized in that: Using the dual-plane lower limb full-length X-ray acquisition system, the patient's weight-bearing lower limbs are collected in the anteroposterior and lateral X-ray images, including: The patient stands on the dual-plane lower limb full-length X-ray acquisition system and adjusts his posture to the required standard weight-bearing position to ensure that both lower limbs are evenly stressed; Collect anteroposterior and lateral X-ray images of the patient's lower limbs to ensure that the images clearly show the overall shape of the lower limbs, especially the knee joints and adjacent parts.

5. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 1, characterized in that: The CT reconstruction data and the data collected by the dual-plane lower limb full-length X-ray acquisition system are fused and analyzed to form a fusion image in three-dimensional space, and the angles of the femoral prosthesis, tibial prosthesis and lower limb force line in three-dimensional space after TKA are accurately calculated, including: The CT reconstruction data and the data collected by the dual-plane lower limb full-length X-ray acquisition system are input into the trained deep learning multimodal data registration and fusion model for image registration, correction and data format conversion, so that the data of the two can accurately correspond, eliminate the errors caused by different imaging methods, and accurately calculate the angles of the femoral prosthesis, tibial prosthesis and lower limb force lines in three-dimensional space after TKA surgery.

6. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 5, characterized in that: Deep learning multimodal data registration and fusion model, including: The first network branch is used to correct the CT reconstruction data, convert the data format and extract the feature map to obtain a first feature map; The second network branch is used to correct, convert the data format and extract the feature map of the data collected by the dual-plane lower limb full-length X-ray collection system to obtain a second feature map; The lower limb three-dimensional force line evaluation network is used to align 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 alignment and fusion results.

7. The method for evaluating three-dimensional force lines of lower limbs after TKA based on multimodal data fusion according to claim 2, characterized in that: After accurately calculating the angle of the lower limb force line in three-dimensional space, it also includes: The angle calculation results of the force line of the lower limbs in three-dimensional space are displayed on the screen in a graphical manner, including the angle information of the force line of the lower limbs in three-dimensional space, which can intuitively display the force line situation of the lower limbs; Generate a detailed analysis report, which at least includes basic patient information, image data, measurement angles and analysis conclusions, for reference by clinicians and to facilitate archiving and subsequent comparative analysis.

8. A three-dimensional force line assessment system for lower limbs after TKA based on multimodal data fusion, characterized in that: The system comprises: The CT image acquisition module is used to obtain CT images of both lower limbs of the patient before total knee replacement surgery; the coverage range of both lower limbs is from above the hip joint to below the ankle joint; The 3D reconstruction module is used to perform 3D reconstruction of the CT images of both lower limbs to clearly display the bones and surrounding soft tissue structures of the lower limbs; An X-ray image acquisition module is used to acquire the anteroposterior and lateral X-ray images of the patient's lower limbs in a weight-bearing position 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; The lower limb force line angle assessment module is used to fuse and analyze the CT reconstruction data and the data collected by the dual-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, tibial prosthesis and lower limb force lines in three-dimensional space after TKA surgery.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the method for evaluating three-dimensional force lines of lower limbs after TKA surgery based on multimodal data fusion is implemented as described in any one of claims 1 to 7.

Images