WO2023056877A1 - 膝关节股骨力线确定方法和装置、电子设备、存储介质 - Google Patents

膝关节股骨力线确定方法和装置、电子设备、存储介质 Download PDF

Info

Publication number
WO2023056877A1
WO2023056877A1 PCT/CN2022/122398 CN2022122398W WO2023056877A1 WO 2023056877 A1 WO2023056877 A1 WO 2023056877A1 CN 2022122398 W CN2022122398 W CN 2022122398W WO 2023056877 A1 WO2023056877 A1 WO 2023056877A1
Authority
WO
WIPO (PCT)
Prior art keywords
medullary cavity
dimensional
femur
femoral
anatomical axis
Prior art date
Application number
PCT/CN2022/122398
Other languages
English (en)
French (fr)
Inventor
张逸凌
刘星宇
Original Assignee
北京长木谷医疗科技有限公司
张逸凌
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京长木谷医疗科技有限公司, 张逸凌 filed Critical 北京长木谷医疗科技有限公司
Publication of WO2023056877A1 publication Critical patent/WO2023056877A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02—Prostheses implantable into the body
    • A61F2/30—Joints
    • A61F2/46—Special tools or methods for implanting or extracting artificial joints, accessories, bone grafts or substitutes, or particular adaptations therefor
    • A61F2/4657—Measuring instruments used for implanting artificial joints
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
    • A61F2/02—Prostheses implantable into the body
    • A61F2/30—Joints
    • A61F2/46—Special tools or methods for implanting or extracting artificial joints, accessories, bone grafts or substitutes, or particular adaptations therefor
    • A61F2/4657—Measuring instruments used for implanting artificial joints
    • A61F2002/4663—Measuring instruments used for implanting artificial joints for measuring volumes or other three-dimensional shapes

Definitions

  • the present application relates to the field of medical technology, in particular, to a method and device for determining the force line of the femur of the knee joint, electronic equipment, and a storage medium.
  • Knee femoral alignment is an extremely important parameter in total knee replacement surgery, which can directly affect the surgical planning and postoperative effect of total knee replacement. Therefore, it is very meaningful to measure the femoral alignment in advance in CT images .
  • Determining the femoral line of alignment is less precise and slower.
  • the main purpose of the present application is to provide a method for determining the force line of the knee joint and femur to solve the above problems.
  • a method for determining the force line of the femur of the knee joint is provided.
  • the method for determining the line of force of the knee joint femur according to the present application includes:
  • image segmentation processing is performed on the two-dimensional medical image of the femur to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity;
  • the first position coordinates of the center point of the femoral head and the anatomical axis of the medullary cavity are obtained respectively;
  • Knee femoral force lines are obtained based on the first position coordinates and the second position coordinates.
  • the pre-trained image segmentation network model is used to perform image segmentation processing on the two-dimensional medical image of the femur to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity, including:
  • the image of the femoral head portion and the image of the femoral medullary cavity are segmented to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity.
  • said obtaining the first position coordinates of the center point of the femoral head according to the two-dimensional segmentation result of the femoral head includes:
  • the first position coordinates of the central point of the femoral head in the three-dimensional coordinate system are obtained.
  • the obtaining the anatomical axis of the medullary cavity according to the two-dimensional medical image of the femoral medullary cavity includes:
  • the two-dimensional segmentation results of the femoral medullary cavity are classified into layers, and multiple medullary cavity layers are obtained;
  • a straight line was fitted to the center point of the femoral medullary canal at all levels of the medullary canal by the least square method;
  • the anatomical axis of the medullary cavity is obtained.
  • the obtaining the three-dimensional straight line equation of the anatomical axis of the medullary cavity to obtain the second position coordinates of the intersection point of the anatomical axis of the medullary cavity and the distal end of the femur includes:
  • a three-dimensional coordinate system is established based on the corrected anatomical axis of the medullary cavity, and the anatomical axis of the medullary cavity is perpendicular to the XY plane and parallel to the Z axis, so that the coordinates of all pixel points passed by the anatomical axis of the medullary cavity are (x_xis, y_xis , z), where x_xis, y_xis are fixed values, and z is a variable value;
  • the space inverse transformation is performed on the anatomical axis of the medullary cavity and the femur through the rotation matrix to obtain the second position coordinates before the anatomical axis of the femur and the anatomical medullary cavity are corrected.
  • said obtaining the knee femoral line of force based on the first position coordinates and the second position coordinates includes:
  • the first position coordinates and the second position coordinates are converted from three-dimensional to two-dimensional coordinates, and then the two-dimensional point coordinates of the center point of the femoral head, the anatomical axis of the medullary cavity and the outer bone surface of the distal femur are respectively obtained
  • the present application also provides a device for determining the line of force of the knee joint femur, comprising:
  • An image acquisition module configured to acquire a two-dimensional medical image of the femur
  • the image segmentation module is configured to perform image segmentation processing on the two-dimensional medical image of the femur based on a pre-trained image segmentation network model to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity;
  • the calculation processing module is configured to obtain the first position coordinates of the center point of the femoral head and the anatomical axis of the medullary cavity respectively according to the two-dimensional segmentation results of the femoral head and the femoral medullary cavity;
  • the coordinate establishment module is configured to obtain the three-dimensional straight line equation of the anatomical axis of the medullary cavity, and obtain the second position coordinates of the intersection point of the anatomical axis of the medullary cavity and the distal end of the femur;
  • the line of force determination module is configured to obtain the line of force of the femur of the knee joint based on the first position coordinates and the second position coordinates.
  • the image segmentation module includes:
  • the image recognition unit is configured to recognize the femoral head part and the femoral medullary cavity part in the two-dimensional medical image of the femur according to the image segmentation network model;
  • the image segmentation unit is configured to segment the image of the femoral head part and the image of the femoral medullary cavity to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity.
  • calculation processing module includes:
  • the central point calculation unit is configured to perform three-dimensional modeling based on the two-dimensional segmentation results of the femoral head at each level to obtain a three-dimensional medical image of the femoral head; based on the three-dimensional medical image of the femoral head, to obtain The coordinates of the first position under ;
  • the medullary cavity anatomical axis calculation unit is configured to classify the two-dimensional medical images of the femoral medullary cavity based on computer vision technology to obtain multiple medullary cavity levels; according to the center point calculation formula, extract the femoral medullary cavity center of all medullary cavity levels point; through the least squares method, the center points of the femoral medullary canal of all medullary canal levels are fitted with a straight line; based on the fitting results, the anatomical axis of the medullary canal is obtained.
  • the coordinate establishment module includes:
  • a correction unit configured to obtain a three-dimensional medical image of the femur, and synchronously correct the anatomical axis of the femur and the medullary cavity to a vertical state based on the rotation matrix;
  • the three-dimensional coordinate system establishment unit is configured to establish a three-dimensional coordinate system based on the corrected anatomical axis of the medullary cavity, and make the anatomical axis of the medullary cavity perpendicular to the XY plane and parallel to the Z axis to obtain all the anatomical axes of the medullary cavity.
  • the coordinates of the pixel point are (x_xis, y_xis, z), where x_xis, y_xis are fixed values, and z values are variable;
  • the pixel point identification unit is configured to identify multiple pixel points containing bone among all the pixel points passing by the anatomical axis of the medullary cavity based on computer vision technology, and record the coordinates of the multiple pixel points in the three-dimensional coordinate system, Wherein the pixel point with the largest vertical coordinate among the plurality of pixel points is the intersection point of the anatomical axis of the medullary cavity and the distal end of the femur;
  • a position coordinate acquisition unit configured to obtain a second position coordinate corresponding to the pixel point with the largest ordinate
  • the processing unit is configured to perform spatial inverse transformation on the anatomical axis of the medullary cavity and the femur through the rotation matrix to obtain the second position coordinates of the anatomical axis of the femur and the medullary cavity before correction.
  • the line of force determination module includes:
  • the coordinate reconstruction unit is configured to convert the first position coordinates and the second position coordinates from three-dimensional to two-dimensional coordinates based on the transformation model, and then respectively obtain the two-dimensional point coordinates of the center point of the femoral head and the anatomical axis of the medullary cavity Two-dimensional point coordinates of the intersection point with the lateral bone surface of the distal femur;
  • the line of force calculation unit is configured as a two-dimensional point coordinate based on the two-dimensional point coordinates of the center point of the femoral head, the two-dimensional point coordinates of the intersection point of the anatomical axis of the medullary cavity and the outer bone surface of the distal end of the femur, and obtains
  • the straight line at the intersection of the distal ends of the femur is the line of force of the knee joint femur.
  • An electronic device includes a memory and a processor, the memory stores a computer program, and the processor calls the computer program in the memory to implement any one of the above methods when executed.
  • a storage medium the computer program is stored in the storage medium, and the computer program is used to realize any one of the above methods when executed in the storage medium.
  • the femoral head is quickly segmented by deep learning technology, and the center of the femoral head is calculated.
  • the centerline of the medullary cavity is extracted using image technology, and the intersection point between the centerline of the medullary cavity and the bone of the distal femur is calculated.
  • the calculation of the femoral force line achieves a more accurate and faster technical effect of calculating the femoral force line, and then solves the technical problems of time-consuming, labor-intensive and poor accuracy in the calculation of the femoral force line in the prior art.
  • Fig. 1 is the flow chart of the method for determining the force line of knee joint femur according to the embodiment of the present application;
  • Fig. 2 is the schematic diagram of the force line of knee joint femur according to the embodiment of the present application
  • FIG. 3 is a schematic diagram of a segmentation reference standard label of a femoral head according to an embodiment of the present application
  • FIG. 4 is a schematic diagram of the center point of the femoral medullary cavity according to an embodiment of the present application.
  • Fig. 5 is a schematic diagram of synchronous correction of the anatomical axes of the femur and the medullary cavity according to an embodiment of the present application.
  • serial numbers of the processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, rather than by the execution order of the embodiments of the present application.
  • the implementation process constitutes no limitation.
  • the terms “installed”, “disposed”, “provided”, “connected”, “connected”, “socketed” are to be interpreted broadly. For example, it may be a fixed connection, a detachable connection, or an integral structure; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediary; internal connectivity.
  • installed disposed, “provided”, “connected”, “connected”, “socketed”
  • it may be a fixed connection, a detachable connection, or an integral structure; it may be a mechanical connection or an electrical connection; it may be a direct connection or an indirect connection through an intermediary; internal connectivity.
  • a method for determining the force line of the knee joint femur includes the following steps:
  • the pre-trained image segmentation network model performs image segmentation processing on the two-dimensional medical image of the femur to obtain the two-dimensional segmentation results of the femoral head and the two-dimensional segmentation results of the femoral medullary cavity ,include:
  • the first position coordinates of the center point of the femoral head are obtained according to the two-dimensional segmentation result of the femoral head, including:
  • said obtaining the anatomical axis CB of the medullary cavity according to the two-dimensional segmentation result of the femoral medullary cavity includes:
  • the obtaining the three-dimensional straight line equation of the anatomical axis CB of the medullary cavity to obtain the second position coordinates of the intersection point of the anatomical axis CB of the medullary cavity and the distal end of the femur includes:
  • the obtaining the knee-femoral line of force AB based on the first position coordinates and the second position coordinates includes:
  • the present application provides a kind of device for determining the force line of knee joint femur, comprising:
  • An image acquisition module configured to acquire a two-dimensional medical image of the femur
  • the image segmentation module is configured to perform image segmentation processing on the two-dimensional medical image of the femur based on a pre-trained image segmentation network model to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity;
  • the calculation processing module is configured to obtain the first position coordinates of the center point of the femoral head and the anatomical axis of the medullary cavity according to the two-dimensional segmentation results of the femoral head and the femoral medullary cavity, respectively, and obtain the two-dimensional medical images of the femoral head and the femoral medullary cavity respectively.
  • the coordinate establishment module is configured to obtain the three-dimensional straight line equation of the anatomical axis CB of the medullary cavity, and obtain the second position coordinates of the intersection point of the anatomical axis CB of the medullary cavity and the distal end of the femur;
  • the force line determining module is configured to obtain the knee joint femoral force line AB based on the first position coordinates and the second position coordinates.
  • the image segmentation module includes:
  • the image recognition unit is configured to recognize the femoral head part and the femoral medullary cavity part in the two-dimensional medical image of the femur according to the image segmentation network model;
  • the image segmentation unit is configured to segment the image of the femoral head part and the image of the femoral medullary cavity to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity.
  • the calculation processing module includes:
  • the central point calculation unit is configured to perform three-dimensional modeling based on the two-dimensional segmentation results of the femoral head at each level to obtain a three-dimensional medical image of the femoral head; based on the three-dimensional medical image of the femoral head, to obtain The coordinates of the first position under ;
  • the medullary cavity anatomical axis calculation unit is configured to classify the two-dimensional medical images of the femoral medullary cavity based on computer vision technology to obtain multiple medullary cavity levels; according to the center point calculation formula, extract the femoral medullary cavity center of all medullary cavity levels point; through the least squares method, a straight line is fitted to the central points of the femoral medullary canal at all levels of the medullary canal; based on the fitting result, the anatomical axis CB of the medullary canal is obtained.
  • the coordinate establishment module includes:
  • a correction unit configured to obtain a three-dimensional medical image of the femur, and synchronously correct the anatomical axis CB of the femur and the medullary cavity to a vertical state based on the rotation matrix;
  • the three-dimensional coordinate system establishment unit is configured to establish a three-dimensional coordinate system based on the corrected anatomical axis CB of the medullary cavity, and make the anatomical axis of the medullary cavity perpendicular to the XY plane and parallel to the Z axis to obtain the
  • the coordinates of all pixel points are (x_xis, y_xis, z), where x_xis, y_xis are fixed values, and z values are variable;
  • the pixel point identification unit is configured to identify multiple pixel points containing bone among all the pixel points passing by the anatomical axis CB of the medullary cavity based on computer vision technology, and record the coordinates of the multiple pixel points in the three-dimensional coordinate system , wherein the pixel point with the largest vertical coordinate among the plurality of pixel points is the intersection point of the anatomical axis CB of the medullary cavity and the distal end of the femur;
  • a position coordinate acquisition unit configured to obtain a second position coordinate corresponding to the pixel point with the largest ordinate
  • the processing unit is configured to perform spatial inverse transformation on the anatomical axis CB of the medullary cavity and the femur through the rotation matrix to obtain the second position coordinates of the anatomical axis CB of the femur and the anatomical medullary cavity before correction.
  • the line of force determination module includes:
  • the coordinate reconstruction unit is configured to convert the first position coordinates and the second position coordinates from three-dimensional to two-dimensional coordinates based on the conversion model, and then respectively obtain the two-dimensional point coordinates A of the central point of the femoral head and the anatomy of the medullary cavity The two-dimensional point coordinate B of the intersection of the axis CB and the outer bone surface of the distal femur;
  • the line of force calculation unit is configured as a two-dimensional point coordinate B based on the two-dimensional point coordinate A of the center point of the femoral head, the two-dimensional point coordinate B of the intersection of the anatomical axis CB of the medullary cavity and the outer bone surface of the distal end of the femur, and obtains
  • the straight line at the intersection of the anatomical axis CB and the lateral bone surface of the distal end of the femur is the knee femoral force line AB.
  • the present application provides a storage medium, and a computer program is stored in the storage medium.
  • the computer program is executed in the storage medium, it is used to realize the above-mentioned method for determining the line of force of the knee joint and femur.
  • the method includes :
  • image segmentation processing is performed on the two-dimensional medical image of the femur to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity;
  • the first position coordinates of the center point of the femoral head and the anatomical axis CB of the medullary cavity are respectively obtained;
  • the femoral force line of the knee joint is obtained.
  • the readable storage medium may be a computer storage medium, or a communication medium.
  • Communication media includes any medium that facilitates transfer of a computer program from one place to another.
  • Computer storage media can be any available media that can be accessed by a general purpose or special purpose computer.
  • a readable storage medium is coupled to the processor such that the processor can read information from, and write information to, the readable storage medium.
  • the readable storage medium can also be a component of the processor.
  • the processor and the readable storage medium may be located in application specific integrated circuits (Application Specific Integrated Circuits, ASIC). Additionally, the SIC may be located in the user equipment.
  • ASIC Application Specific Integrated Circuits
  • the processor and the readable storage medium can also exist in the communication device as discrete components.
  • the readable storage medium may be read only memory (ROM), random access memory (RM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices, among others.
  • the present application also provides a program product, which includes execution instructions, and the execution instructions are stored in a readable storage medium. At least one processor of the device may read the execution instruction from the readable storage medium, and at least one processor executes the execution instruction so that the device implements the methods provided by the above-mentioned various implementations.
  • the present application provides an electronic device, including a memory and a processor, the memory stores a computer program, and the processor invokes the computer program in the memory to implement the above-mentioned knee joint.
  • a method for determining the line of force of the femur the method comprising:
  • image segmentation processing is performed on the two-dimensional medical image of the femur to obtain a two-dimensional segmentation result of the femoral head and a two-dimensional segmentation result of the femoral medullary cavity;
  • the first position coordinates of the center point of the femoral head and the anatomical axis CB of the medullary cavity are respectively obtained;
  • the femoral force line of the knee joint is obtained.
  • each module or each step of the above-mentioned application can be realized by a general-purpose computing device, and they can be concentrated on a single computing device, or distributed in a network composed of multiple computing devices
  • they can be implemented with program codes executable by a computing device, so that they can be stored in a storage device and executed by a computing device, or they can be made into individual integrated circuit modules, or they can be integrated into Multiple modules or steps are fabricated into a single integrated circuit module to realize.
  • the present application is not limited to any specific combination of hardware and software.

Landscapes

  • Health & Medical Sciences (AREA)
  • Orthopedic Medicine & Surgery (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Transplantation (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Cardiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Biophysics (AREA)
  • Surgery (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Vascular Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)

Abstract

一种膝关节股骨力线（AB）确定方法和装置、电子设备、存储介质。方法包括：获取股骨的二维医学图像（S100）；基于预先训练好的图像分割网络模型，对股骨的二维医学图像进行图像分割处理，得到股骨头的二维医学图像、股骨髓腔的二维医学图像（S200）；根据股骨头和股骨髓腔的二维医学图像分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线（CB）（S300）；获取髓腔解剖轴线（CB）的三维直线方程，得到髓腔解剖轴线（CB）与股骨远端的交点的第二位置坐标（S400）；基于第一位置坐标和第二位置坐标得到膝关节股骨力线（AB）（S500）。解决了传统方法确定股骨力线（AB）不够精准，且速度较慢的技术问题。

Description

膝关节股骨力线确定方法和装置、电子设备、存储介质
相关申请的交叉引用
本申请要求于2021年10月08日提交的申请号为202111173899.3，名称为“膝关节股骨力线确定方法和装置、电子设备、存储介质”的中国专利申请的优先权，其通过引用方式全部并入本文。
技术领域
本申请涉及医学技术领域，具体而言，涉及一种膝关节股骨力线确定方法和装置、电子设备、存储介质。
背景技术
膝关节股骨力线是在全膝关节置换手术中极其重要的一个参数，可以直接影响全膝置换的手术规划和术后效果，因此在CT影像中提前对股骨力线进行测量是十分有意义的。
目前，市场上现有技术的缺点：
确定股骨力线不够精准，且速度较慢。
针对相关技术中传统方法确定股骨力线不够精准，且速度较慢的问题，目前尚未提出有效的解决方案。
发明内容
本申请的主要目的在于提供一种膝关节股骨力线确定方法，以解决上述问题。
为了实现上述目的，根据本申请的一个方面，提供了一种膝关节股骨力线确定方法。
根据本申请的膝关节股骨力线确定方法包括：
获取股骨的二维医学图像；
基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置 坐标和髓腔解剖轴线；
获取所述髓腔解剖轴线的三维直线方程，得到所述髓腔解剖轴线与股骨远端的交点的第二位置坐标；
基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线。
进一步的，所述基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果，包括：
根据图像分割网络模型识别股骨的二维医学图像中的股骨头部分、股骨髓腔部分；
将股骨头部分的图像与股骨髓腔部分的图像分割，得到股骨头的二维分割结果、股骨髓腔的二维分割结果。
进一步的，所述根据股骨头的二维分割结果得到股骨头中心点的第一位置坐标，包括：
基于各个层面的股骨头的二维分割结果，进行三维重建，得到股骨头的三维医学图像；
基于股骨头的三维医学图像，得到股骨头中心点在三维坐标系下的第一位置坐标。
进一步的，所述根据股骨髓腔的二维医学图像得到髓腔解剖轴线，包括：
基于计算机视觉技术对股骨髓腔的二维分割结果进行层面分类，得到多个髓腔层面；
根据中心点计算公式，提取所有髓腔层面的股骨髓腔中心点；
通过最小二乘法对所有髓腔层面的股骨髓腔中心点进行直线拟合；
基于拟合结果，得到所述髓腔解剖轴线。
进一步的，所述获取所述髓腔解剖轴线的三维直线方程，得到所述髓腔解剖轴线与股骨远端的交点的第二位置坐标，包括：
获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线同步矫正至竖直状态；
基于矫正后的髓腔解剖轴线建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
基于计算机视觉技术在髓腔解剖轴线经过的所有像素点中识别包含有骨质 的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线与股骨远端的交点；
获得所述纵坐标最大的像素点对应的第二位置坐标；
通过所述旋转矩阵对所述髓腔解剖轴线和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线矫正前的第二位置坐标。
进一步的，所述基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线包括：
基于转换模型，将所述第一位置坐标和第二位置坐标进行从三维至二维的坐标转换，进而分别得到股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端外侧骨表面的交点的二维点坐标；
基于股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端的交点的二维点坐标，得到经过股骨头中心点、髓腔解剖轴线与股骨远端外侧骨表面的交点的直线，即为膝关节股骨力线。
本申请还提供了一种膝关节股骨力线确定装置，包括：
图像采集模块，被配置为获取股骨的二维医学图像；
图像分割模块，被配置为基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
计算处理模块，被配置为根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线；
坐标建立模块，被配置为获取所述髓腔解剖轴线的三维直线方程，得到所述髓腔解剖轴线与股骨远端的交点的第二位置坐标；
力线确定模块，被配置为基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线。
进一步的，所述图像分割模块包括：
图像识别单元，被配置为根据图像分割网络模型识别股骨的二维医学图像中的股骨头部分、股骨髓腔部分；
图像分割单元，被配置为将股骨头部分的图像与股骨髓腔部分的图像分割，得到股骨头的二维分割结果、股骨髓腔的二维分割结果。
进一步的，所述计算处理模块包括：
中心点计算单元，被配置为基于各个层面的股骨头的二维分割结果，进行 三维建模，得到股骨头的三维医学图像；基于股骨头的三维医学图像，得到股骨头中心点在三维坐标系下的第一位置坐标；
髓腔解剖轴线计算单元，被配置为基于计算机视觉技术对股骨髓腔的二维医学图像进行层面分类，得到多个髓腔层面；根据中心点计算公式，提取所有髓腔层面的股骨髓腔中心点；通过最小二乘法对所有髓腔层面的股骨髓腔中心点进行直线拟合；基于拟合结果，得到所述髓腔解剖轴线。
进一步的，所述坐标建立模块包括：
矫正单元，被配置为获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线同步矫正至竖直状态；
三维坐标系建立单元，被配置为基于矫正后的髓腔解剖轴线建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
像素点识别单元，被配置为基于计算机视觉技术在髓腔解剖轴线经过的所有像素点中识别包含有骨质的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线与股骨远端的交点；
位置坐标获取单元，被配置为获得所述纵坐标最大的像素点对应的第二位置坐标；
处理单元，被配置为通过所述旋转矩阵对所述髓腔解剖轴线和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线矫正前的第二位置坐标。
进一步的，所述力线确定模块包括：
坐标重建单元，被配置为基于转换模型，将所述第一位置坐标和第二位置坐标进行从三维至二维的坐标转换，进而分别得到股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端外侧骨表面的交点的二维点坐标；
力线计算单元，被配置为基于股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端外侧骨表面的交点的二维点坐标，得到经过股骨头中心点、髓腔解剖轴线与股骨远端的交点的直线，即为膝关节股骨力线。
一种电子设备，包括存储器和处理器，所述存储器存储计算机程序，所述处理器调用所述存储器中的所述计算机程序执行时用于实现上述任一种方法。
一种存储介质，所述存储介质中存储有计算机程序，所述计算机程序在存 储介质中执行时用于实现上述任一种方法。
在本申请实施例中，通过深度学习技术快速分割出股骨头，并计算出股骨头中心，同时利用图像技术提取髓腔中心线，并计算髓腔中心线和股骨远端骨质的交点，最终计算出股骨力线，实现了较为精准，且速度较快的计算股骨力线的技术效果，进而解决了现有技术在计算股骨力线时，耗时耗力，精准度差的技术问题。
附图说明
构成本申请的一部分的附图用来提供对本申请的进一步理解，使得本申请的其它特征、目的和优点变得更明显。本申请的示意性实施例附图及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：
图1是根据本申请实施例的膝关节股骨力线确定方法的流程图；
图2是根据本申请实施例的膝关节股骨力线的示意图；
图3是根据本申请实施例的股骨头的分割参考标准标签示意图；
图4是根据本申请实施例的股骨髓腔中心点的示意图；
图5是根据本申请实施例的股骨和髓腔解剖轴线同步矫正的示意图。
具体实施方式
为了使本技术领域的人员更好地理解本申请方案，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分的实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都应当属于本申请保护的范围。
需要说明的是，本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本申请的实施例。此外，术语“包括”和“具有”以及他们的任何变形，意图在于覆盖不排他的包含，例如，包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元，而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
应当理解，在本申请的各种实施例中，各过程的序号的大小并不意味着执 行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
在本申请中，术语“上”、“下”、“左”、“右”、“前”、“后”、“顶”、“底”、“内”、“外”、“中”、“竖直”、“水平”、“横向”、“纵向”等指示的方位或位置关系为基于附图所示的方位或位置关系。这些术语主要是为了更好地描述本实用新型及其实施例，并非用于限定所指示的装置、元件或组成部分必须具有特定方位，或以特定方位进行构造和操作。
并且，上述部分术语除了可以用于表示方位或位置关系以外，还可能用于表示其他含义，例如术语“上”在某些情况下也可能用于表示某种依附关系或连接关系。对于本领域普通技术人员而言，可以根据具体情况理解这些术语在本实用新型中的具体含义。
此外，术语“安装”、“设置”、“设有”、“连接”、“相连”、“套接”应做广义理解。例如，可以是固定连接，可拆卸连接，或整体式构造；可以是机械连接，或电连接；可以是直接相连，或者是通过中间媒介间接相连，又或者是两个装置、元件或组成部分之间内部的连通。对于本领域普通技术人员而言，可以根据具体情况理解上述术语在本实用新型中的具体含义。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
根据本申请实施例，如图1所示，提供了一种膝关节股骨力线确定方法，该方法包括如下的步骤：
S100、获取股骨的二维医学图像；
S200、基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
S300、根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线CB；
S400、获取所述髓腔解剖轴线CB的三维直线方程，得到所述髓腔解剖轴线CB与股骨远端的交点的第二位置坐标；
S500、基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线AB。
在进一步的实施例中，所述基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果，包括：
S202、根据图像分割网络模型识别股骨的二维医学图像中的股骨头部分、股骨髓腔部分；
S204、将股骨头部分的图像与股骨髓腔部分的图像分割，得到股骨头的二维分割结果、股骨髓腔的二维分割结果。
在进一步的实施例中，根据股骨头的二维分割结果得到股骨头中心点的第一位置坐标，包括：
S302、基于各个层面的股骨头的二维分割结果，进行三维建模，得到股骨头的三维医学图像；
S304、基于股骨头的三维医学图像，得到股骨头中心点在三维坐标系下的第一位置坐标。
在进一步的实施例中，所述根据股骨髓腔的二维分割结果得到髓腔解剖轴线CB，包括：
S306、基于计算机视觉技术对股骨髓腔的二维分割结果进行层面分类，得到多个髓腔层面；
S308、根据中心点计算公式，提取所有髓腔层面的股骨髓腔中心点，如图5所示；
S310、通过最小二乘法对所有髓腔层面的股骨髓腔中心点进行直线拟合；
S312、基于拟合结果，得到所述髓腔解剖轴线CB。
在进一步的实施例中，所述获取所述髓腔解剖轴线CB的三维直线方程，得到所述髓腔解剖轴线CB与股骨远端的交点的第二位置坐标，包括：
S402、获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线CB同步矫正至竖直状态，如图5所示；
S404、基于矫正后的髓腔解剖轴线CB建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
S406、基于计算机视觉技术在髓腔解剖轴线CB经过的所有像素点中识别包含有骨质的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线CB与股骨远端的交点；
S408、获得所述纵坐标最大的像素点对应的第二位置坐标；
S410、通过所述旋转矩阵对所述髓腔解剖轴线CB和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线CB矫正前的第二位置坐标。
在进一步的实施例中，所述基于所述第一位置坐标和所述第二位置坐标，得到膝关节股骨力线AB，包括：
S502、基于转换模型，将所述第一位置坐标和第二位置坐标进行从三维至二维的坐标转换，进而分别得到股骨头中心点的二维点坐标A、髓腔解剖轴线CB与股骨远端的交点的二维点坐标B；
S504、基于股骨头中心点的二维点坐标A、髓腔解剖轴线CB与股骨远端的交点的二维点坐标B，得到经过股骨头中心点、髓腔解剖轴线CB与股骨远端的交点的直线，即为膝关节股骨力线AB，如图2所示。
还包括一个实施例，本申请提供一种膝关节股骨力线确定装置，包括：
图像采集模块，被配置为获取股骨的二维医学图像；
图像分割模块，被配置为基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
计算处理模块，被配置为根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线，根据股骨头和股骨髓腔的二维医学图像分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线CB；
坐标建立模块，被配置为获取所述髓腔解剖轴线CB的三维直线方程，得到所述髓腔解剖轴线CB与股骨远端的交点的第二位置坐标；
力线确定模块，被配置为基于所述第一位置坐标和所述第二位置坐标，得到膝关节股骨力线AB。
在进一步的实施例中，所述图像分割模块包括：
图像识别单元，被配置为根据图像分割网络模型识别股骨的二维医学图像中的股骨头部分、股骨髓腔部分；
图像分割单元，被配置为将股骨头部分的图像与股骨髓腔部分的图像分割，得到股骨头的二维分割结果、股骨髓腔的二维分割结果。
在进一步的实施例中，所述计算处理模块包括：
中心点计算单元，被配置为基于各个层面的股骨头的二维分割结果，进行三维建模，得到股骨头的三维医学图像；基于股骨头的三维医学图像，得到股骨头中心点在三维坐标系下的第一位置坐标；
髓腔解剖轴线计算单元，被配置为基于计算机视觉技术对股骨髓腔的二维医学图像进行层面分类，得到多个髓腔层面；根据中心点计算公式，提取所有髓腔层面的股骨髓腔中心点；通过最小二乘法对所有髓腔层面的股骨髓腔中心点进行直线拟合；基于拟合结果，得到所述髓腔解剖轴线CB。
在进一步的实施例中，所述坐标建立模块包括：
矫正单元，被配置为获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线CB同步矫正至竖直状态；
三维坐标系建立单元，被配置为基于矫正后的髓腔解剖轴线CB建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
像素点识别单元，被配置为基于计算机视觉技术在髓腔解剖轴线CB经过的所有像素点中识别包含有骨质的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线CB与股骨远端的交点；
位置坐标获取单元，被配置为获得所述纵坐标最大的像素点对应的第二位置坐标；
处理单元，被配置为通过所述旋转矩阵对所述髓腔解剖轴线CB和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线CB矫正前的第二位置坐标。
在进一步的实施例中，所述力线确定模块包括：
坐标重建单元，被配置为基于转换模型，将所述第一位置坐标和第二位置坐标进行从三维至二维的坐标转换，进而分别得到股骨头中心点的二维点坐标A、髓腔解剖轴线CB与股骨远端外侧骨表面的交点的二维点坐标B；
力线计算单元，被配置为基于股骨头中心点的二维点坐标A、髓腔解剖轴线CB与股骨远端外侧骨表面的交点的二维点坐标B，得到经过股骨头中心点、髓腔解剖轴线CB与股骨远端外侧骨表面的交点的直线，即为膝关节股骨力线AB。
还包括一个实施例，本申请提供一种存储介质，所述存储介质中存储有计算机程序，所述计算机程序在存储介质中执行时用于实现上述的膝关节股骨力线确定方法，该方法包括：
获取股骨的二维医学图像；
基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线CB；
获取所述髓腔解剖轴线CB的三维直线方程，得到所述髓腔解剖轴线CB与股骨远端的交点的第二位置坐标；
基于所述第一位置坐标和所述第二位置坐标，得到膝关节股骨力线。
其中，可读存储介质可以是计算机存储介质，也可以是通信介质。通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。计算机存储介质可以是通用或专用计算机能够存取的任何可用介质。例如，可读存储介质耦合至处理器，从而使处理器能够从该可读存储介质读取信息，且可向该可读存储介质写入信息。当然，可读存储介质也可以是处理器的组成部分。处理器和可读存储介质可以位于专用集成电路(Application Specific Integrated Circuits，ASIC)中。另外，该SIC可以位于用户设备中。当然，处理器和可读存储介质也可以作为分立组件存在于通信设备中。可读存储介质可以是只读存储器(ROM)、随机存取存储器(RM)、CD-ROM、磁带、软盘和光数据存储设备等。
本申请还提供一种程序产品，该程序产品包括执行指令，该执行指令存储在可读存储介质中。设备的至少一个处理器可以从可读存储介质读取该执行指 令，至少一个处理器执行该执行指令使得设备实施上述的各种实施方式提供的方法。
还包括一个实施例，本申请提供一种电子设备，包括存储器和处理器，所述存储器存储计算机程序，所述处理器调用所述存储器中的所述计算机程序执行时用于实现上述的膝关节股骨力线确定方法，该方法包括：
获取股骨的二维医学图像；
基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线CB；
获取所述髓腔解剖轴线CB的三维直线方程，得到所述髓腔解剖轴线CB与股骨远端的交点的第二位置坐标；
基于所述第一位置坐标和所述第二位置坐标，得到膝关节股骨力线。
需要说明的是，在附图的流程图示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。
显然，本领域的技术人员应该明白，上述的本申请的各模块或各步骤可以用通用的计算装置来实现，它们可以集中在单个的计算装置上，或者分布在多个计算装置所组成的网络上，可选地，它们可以用计算装置可执行的程序代码来实现，从而，可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成各个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件结合。
以上所述仅为本申请的优选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种膝关节股骨力线确定方法，包括：
    获取股骨的二维医学图像；
    基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
    根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线；
    获取所述髓腔解剖轴线的三维直线方程，得到所述髓腔解剖轴线与股骨远端的交点的第二位置坐标；
    基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线。
  2. 根据权利要求1所述的方法，其中，所述基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果，包括：
    根据图像分割网络模型识别股骨的二维医学图像中的股骨头部分、股骨髓腔部分；
    将股骨头部分的图像与股骨髓腔部分的图像分割，得到股骨头的二维分割结果、股骨髓腔的二维分割结果。
  3. 根据权利要求1所述的方法，其中，所述根据股骨头的二维分割结果得到股骨头中心点的第一位置坐标，包括：
    基于各个层面的股骨头的二维分割结果，进行三维重建，得到股骨头的三维医学图像；
    基于股骨头的三维医学图像，得到股骨头中心点在三维坐标系下的第一位置坐标。
  4. 根据权利要求1所述的方法，其中，所述根据股骨髓腔的二维分割结果得到髓腔解剖轴线，包括：
    基于计算机视觉技术对股骨髓腔的二维分割结果进行层面分类，得到多个髓腔层面；
    根据中心点计算公式，提取所有髓腔层面的股骨髓腔中心点；
    通过最小二乘法对所有髓腔层面的股骨髓腔中心点进行直线拟合；
    基于拟合结果，得到所述髓腔解剖轴线。
  5. 根据权利要求1所述的方法，其中，所述获取所述髓腔解剖轴线的三维直线方程，得到所述髓腔解剖轴线与股骨远端的交点的第二位置坐标，包括：
    获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线同步矫正至竖直状态；
    基于矫正后的髓腔解剖轴线建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
    基于计算机视觉技术在髓腔解剖轴线经过的所有像素点中识别包含有骨质的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线与股骨远端的交点；
    获得所述纵坐标最大的像素点对应的第二位置坐标；
    通过所述旋转矩阵对所述髓腔解剖轴线和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线矫正前的第二位置坐标。
  6. 根据权利要求5所述的方法，其中，所述基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线，包括：
    基于转换模型，将所述第一位置坐标和第二位置坐标进行从三维至二维的坐标转换，进而分别得到股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端的交点的二维点坐标；
    基于股骨头中心点的二维点坐标、髓腔解剖轴线与股骨远端的交点的二维点坐标，得到经过股骨头中心点、髓腔解剖轴线与股骨远端的交点的直线，即为膝关节股骨力线。
  7. 一种膝关节股骨力线确定装置，包括：
    图像采集模块，被配置为获取股骨的二维医学图像；
    图像分割模块，被配置为基于预先训练好的图像分割网络模型，对所述股骨的二维医学图像进行图像分割处理，得到股骨头的二维分割结果、股骨髓腔的二维分割结果；
    计算处理模块，被配置为根据股骨头和股骨髓腔的二维分割结果分别得到股骨头中心点的第一位置坐标和髓腔解剖轴线；
    坐标建立模块，被配置为获取所述髓腔解剖轴线的三维直线方程，得到所 述髓腔解剖轴线与股骨远端的交点的第二位置坐标；
    力线确定模块，被配置为基于所述第一位置坐标和所述第二位置坐标得到膝关节股骨力线。
  8. 根据权利要求7所述的装置，其中，所述坐标建立模块包括：
    矫正单元，被配置为获得所述股骨的三维医学图像，并基于旋转矩阵将股骨和髓腔解剖轴线同步矫正至竖直状态；
    三维坐标系建立单元，被配置为基于矫正后的髓腔解剖轴线建立三维坐标系，并使所述髓腔解剖轴线与XY平面垂直，与Z轴平行，得到所述髓腔解剖轴线经过的所有像素点的坐标为(x_xis，y_xis，z)，其中x_xis，y_xis为固定值，z值为变量；
    像素点识别单元，被配置为基于计算机视觉技术在髓腔解剖轴线经过的所有像素点中识别包含有骨质的多个像素点，并记录所述多个像素点在三维坐标系下的坐标，其中所述多个像素点中纵坐标最大的像素点即为髓腔解剖轴线与股骨远端外侧骨表面的交点；
    位置坐标获取单元，被配置为获得所述纵坐标最大的像素点对应的第二位置坐标；
    处理单元，被配置为通过所述旋转矩阵对所述髓腔解剖轴线和股骨进行空间逆变换，得到在所述股骨和髓腔解剖轴线矫正前的第二位置坐标。
  9. 一种电子设备，包括存储器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述计算机程序在所述处理器中执行所述程序时实现权利要求1至6中任一项所述的方法。
  10. 一种存储介质，存储计算机程序，所述计算机程序在所述存储介质中执行所述程序时实现权利要求1至6中任一项所述的方法。
PCT/CN2022/122398 2021-10-08 2022-09-29 膝关节股骨力线确定方法和装置、电子设备、存储介质 WO2023056877A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111173899.3 2021-10-08
CN202111173899.3A CN113974920B (zh) 2021-10-08 2021-10-08 膝关节股骨力线确定方法和装置、电子设备、存储介质

Publications (1)

Publication Number Publication Date
WO2023056877A1 true WO2023056877A1 (zh) 2023-04-13

Family

ID=79737831

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/122398 WO2023056877A1 (zh) 2021-10-08 2022-09-29 膝关节股骨力线确定方法和装置、电子设备、存储介质

Country Status (2)

Country Link
CN (1) CN113974920B (zh)
WO (1) WO2023056877A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113974920B (zh) * 2021-10-08 2022-10-11 北京长木谷医疗科技有限公司 膝关节股骨力线确定方法和装置、电子设备、存储介质
CN114693602B (zh) * 2022-03-02 2023-04-18 北京长木谷医疗科技有限公司 膝关节动张力平衡态评估方法及装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101449967A (zh) * 2008-12-29 2009-06-10 清华大学深圳研究生院 用于辅助人体下肢生物力线测量的方法及装置
US20190239926A1 (en) * 2007-12-18 2019-08-08 Howmedica Osteonics Corporation System and method for image segmentation, bone model generation and modification, and surgical planning
CN110613469A (zh) * 2019-09-18 2019-12-27 北京理工大学 一种腿骨下肢力线自动检测方法及装置
CN111652888A (zh) * 2020-05-25 2020-09-11 北京长木谷医疗科技有限公司 基于深度学习的确定髓腔解剖轴线的方法及装置
CN113017829A (zh) * 2020-08-22 2021-06-25 张逸凌 一种基于深度学习的全膝关节置换术的术前规划方法、系统、介质和设备
CN113974920A (zh) * 2021-10-08 2022-01-28 北京长木谷医疗科技有限公司 膝关节股骨力线确定方法和装置、电子设备、存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1187026C (zh) * 2003-05-29 2005-02-02 上海交通大学 全自动股骨基轴线确定方法
CN111297436A (zh) * 2020-03-31 2020-06-19 北京市春立正达医疗器械股份有限公司 一种膝关节髓内定位装置
CN111888059B (zh) * 2020-07-06 2021-07-27 北京长木谷医疗科技有限公司 基于深度学习与x线的全髋关节图像处理方法及装置
CN112842529B (zh) * 2020-12-31 2022-02-08 北京长木谷医疗科技有限公司 全膝关节图像处理方法及装置
CN113069134A (zh) * 2021-02-05 2021-07-06 仰峰(上海)科技发展有限公司 一种基于ct三维重建图像的股骨髓腔内形态学参数三维测量方法
CN113450294A (zh) * 2021-06-07 2021-09-28 刘星宇 多模态医学图像配准融合方法、装置及电子设备

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190239926A1 (en) * 2007-12-18 2019-08-08 Howmedica Osteonics Corporation System and method for image segmentation, bone model generation and modification, and surgical planning
CN101449967A (zh) * 2008-12-29 2009-06-10 清华大学深圳研究生院 用于辅助人体下肢生物力线测量的方法及装置
CN110613469A (zh) * 2019-09-18 2019-12-27 北京理工大学 一种腿骨下肢力线自动检测方法及装置
CN111652888A (zh) * 2020-05-25 2020-09-11 北京长木谷医疗科技有限公司 基于深度学习的确定髓腔解剖轴线的方法及装置
CN113017829A (zh) * 2020-08-22 2021-06-25 张逸凌 一种基于深度学习的全膝关节置换术的术前规划方法、系统、介质和设备
CN113974920A (zh) * 2021-10-08 2022-01-28 北京长木谷医疗科技有限公司 膝关节股骨力线确定方法和装置、电子设备、存储介质

Also Published As

Publication number Publication date
CN113974920A (zh) 2022-01-28
CN113974920B (zh) 2022-10-11

Similar Documents

Publication Publication Date Title
WO2023056877A1 (zh) 膝关节股骨力线确定方法和装置、电子设备、存储介质
WO2020173052A1 (zh) 图像三维测量方法、电子设备、存储介质及程序产品
CN110033465B (zh) 一种应用于双目内窥镜医学图像的实时三维重建方法
US8861891B2 (en) Hierarchical atlas-based segmentation
CN101071473A (zh) 检测特征点的设备及检测特征点的方法
CN108836479B (zh) 一种医学图像配准方法和手术导航系统
CN109887071A (zh) 一种3d电子内镜系统及三维重建方法
WO2024011943A1 (zh) 基于深度学习的膝关节髌骨置换三维术前规划方法及系统
US11798161B2 (en) Method and apparatus for determining mid-sagittal plane in magnetic resonance images
CN108090954A (zh) 基于图像特征的腹腔环境地图重建与腹腔镜定位的方法
CN115619790B (zh) 一种基于双目定位的混合透视方法、系统及设备
EP3543955A1 (en) Image processing device and projection system
Kyme et al. Markerless motion estimation for motion-compensated clinical brain imaging
Patias Medical imaging challenges photogrammetry
WO2019180746A1 (en) A method for obtaining 3-d deformity correction for bones
CN113786228B (zh) 一种基于ar增强现实的辅助穿刺导航系统
CN114049344A (zh) 图像分割方法及其模型的训练方法及相关装置、电子设备
CN112261399B (zh) 胶囊内窥镜图像三维重建方法、电子设备及可读存储介质
US20240016550A1 (en) Scanner for intraoperative application
CN108804861A (zh) 一种具有真实力反馈的脊柱微创手术培训系统及方法
CN113786229A (zh) 一种基于ar增强现实的辅助穿刺导航方法
CN113662663A (zh) 一种ar全息手术导航系统坐标系转换方法、装置及系统
Perperidis et al. Spatio-temporal free-form registration of cardiac MR image sequences
CN206863747U (zh) 一种具有真实力反馈的脊柱微创手术培训系统
Wang et al. 3D surgical overlay with markerless image registration using a single camera

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22877896

Country of ref document: EP

Kind code of ref document: A1