CN111179350B - Hip joint image processing system - Google Patents
Hip joint image processing systemDownload PDFInfo
- Publication number
- CN111179350B CN111179350BCN202010090208.2ACN202010090208ACN111179350BCN 111179350 BCN111179350 BCN 111179350BCN 202010090208 ACN202010090208 ACN 202010090208ACN 111179350 BCN111179350 BCN 111179350B
- Authority
- CN
- China
- Prior art keywords
- image
- prosthesis
- hip
- image processing
- placement
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Graphics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Prostheses (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本发明涉及图像处理技术领域，尤其是涉及一种髋关节图像处理系统。The invention relates to the technical field of image processing, in particular to a hip joint image processing system.
背景技术Background technique
随着数字医学的快速发展，数字化技术在外科手术中的应用越来越重要，数字化的手术规划克服了外科医生的视觉局限，使数据测量更加精准，诊断更为精确，手术更加精准、更加高效。With the rapid development of digital medicine, the application of digital technology in surgery is becoming more and more important. Digital surgery planning overcomes the surgeon's visual limitations, making data measurement more accurate, diagnosis more accurate, and surgery more accurate and efficient. .
对于骨科手术(例如，髋关节置换手术)，传统方法利用X线片及假体模板相结合的方式进行术前规划并制定手术方案。传统规划方法使用假体模板在X线片上进行比对，因为X线与模板比例尺不统一，规划结果无法精确预测术中实际使用假体的大小，并且传统方法不能显示三维参数，无法评估假体摆放的空间位置，术者利用传统方式进行术前规划，耗时长，且经常会出现术前规划信息与实际使用假体大小型号及空间位置信息不符的情况。因此，传统规划方法规划时间长，结果不准确，无法显示三维参数及空间位置角度等信息，无法有效的降低手术难度，有时甚至提供错误的信息给临床医师，增加了手术风险。For orthopaedic surgery (eg, hip replacement surgery), traditional methods use a combination of radiographs and prosthetic templates for preoperative planning and surgical planning. The traditional planning method uses the prosthesis template to compare on the X-ray film. Because the scale of the X-ray and the template is not uniform, the planning result cannot accurately predict the size of the actual prosthesis used during the operation, and the traditional method cannot display the three-dimensional parameters and cannot evaluate the prosthesis. The spatial position of the placement, the surgeon uses the traditional method to carry out preoperative planning, which takes a long time, and often the preoperative planning information does not match the actual size, model and spatial position of the prosthesis used. Therefore, the traditional planning method takes a long time to plan, the results are inaccurate, and the information such as three-dimensional parameters and spatial position angles cannot be displayed, which cannot effectively reduce the difficulty of surgery, and sometimes even provide wrong information to clinicians, increasing the risk of surgery.
鉴于此，需要一种精准高效的三维术前规划系统，能够准确提供髋关节图像数据的解剖参数信息，自动高效计算关键解剖参数，与数据库人工关节假体进行匹配，给出最适合的推荐手术方案，以更好地辅助专业医生制定手术方案。In view of this, an accurate and efficient 3D preoperative planning system is needed, which can accurately provide anatomical parameter information of hip joint image data, automatically and efficiently calculate key anatomical parameters, match with the database artificial joint prosthesis, and give the most suitable recommended surgery. plan to better assist professional doctors in formulating surgical plans.
发明内容SUMMARY OF THE INVENTION
为此，本发明提供了针对髋关节的基于深度学习的髋关节图像处理方法及计算设备，以力图解决或者至少缓解上面存在的至少一个问题。To this end, the present invention provides a hip joint image processing method and computing device based on deep learning for the hip joint, so as to try to solve or at least alleviate at least one of the above problems.
根据本发明的一个方面，提供了一种基于深度学习的髋关节图像处理方法，该方法适于在计算设备中执行，包括步骤：获取与将进行手术的髋关节对应的髋关节信息，其中，所述髋关节信息包括所述髋关节的髋关节DICOM图像以及与手术相关的手术信息；将所述髋关节DICOM图像输入到从所述手术信息中确定的髋关节分割模型组件，获取包括骨骼的三维骨骼模型图像；通过对所述三维骨骼模型图像中的关键点的位置进行标注，生成具有标注数据的标注骨骼图像。According to one aspect of the present invention, there is provided a hip joint image processing method based on deep learning, the method is suitable for execution in a computing device, comprising the steps of: acquiring hip joint information corresponding to a hip joint to be operated on, wherein, The hip joint information includes a hip joint DICOM image of the hip joint and operation information related to the operation; the hip joint DICOM image is input into the hip joint segmentation model component determined from the operation information, and the image including the bones is obtained. A three-dimensional bone model image; by marking the positions of key points in the three-dimensional bone model image, a marked bone image with marked data is generated.
可选地，在根据本发明的方法中，所述髋关节图像是以DICOM格式存储的医学图像。Optionally, in the method according to the present invention, the hip joint image is a medical image stored in DICOM format.
可选地，在根据本发明的方法中，所述手术信息包括所述髋关节在人体中的方位、所患疾病以及将被放置的假体所属的品类。Optionally, in the method according to the present invention, the surgical information includes the orientation of the hip joint in the human body, the disease and the category of the prosthesis to be placed.
可选地，在根据本发明的方法中，将所述髋关节图像输入到从所述手术信息中确定的髋关节分割模型组件获取包括骨骼的三维骨骼模型图像的步骤包括：利用所述手术信息中的将被放置的假体所属的品类，确定与所述品类对应的髋关节分割模型组件；将所述髋关节图像分别输入到所述髋关节分割模型组件，获取仅包括骨骼的各个二维图像，其中各个二维图像包括相互分割的骨盆、左侧股骨、右侧股骨的图像；将所述各个二维图像在空间上进行叠加，生成仅包括骨骼的三维骨骼模型图像。Optionally, in the method according to the present invention, the step of inputting the image of the hip joint to obtain a three-dimensional bone model image including bones from the hip joint segmentation model component determined in the surgical information comprises: using the surgical information The category to which the prosthesis to be placed belongs in is determined, and the hip joint segmentation model component corresponding to the category is determined; the hip joint images are respectively input into the hip joint segmentation model component, and each two-dimensional model including only bones is obtained. images, wherein each two-dimensional image includes images of the pelvis, left femur, and right femur separated from each other; the respective two-dimensional images are spatially superimposed to generate a three-dimensional bone model image including only bones.
可选地，在根据本发明的方法中，所述髋关节分割模型组件根据多个训练髋关节图像以及与从所述多个训练髋关节图像分别提取出的多个训练骨骼之间的对应关系进行机器学习得到的。Optionally, in the method according to the present invention, the hip joint segmentation model component is based on a plurality of training hip joint images and the corresponding relationship between a plurality of training bones extracted from the plurality of training hip joint images respectively. obtained by machine learning.
可选地，在根据本发明的方法中，将所述各个二维图像在空间上进行叠加生成仅包括骨骼的三维骨骼模型图像的步骤包括：将所述各个二维图像中的骨盆的左右方向设置为x轴方向，CT扫描方向为z轴方向，与x轴和z轴所成平面垂直的方向设置为y轴方向；其中，骨盆的左右方向是指从骨盆的左侧按照水平方向到达骨盆的右侧的方向；将所述各个二维图像延z轴方向在空间上进行叠加，生成仅包括骨骼的三维骨骼模型图像。Optionally, in the method according to the present invention, the step of spatially superimposing the respective two-dimensional images to generate a three-dimensional bone model image including only bones includes: combining the left and right directions of the pelvis in the respective two-dimensional images. It is set as the x-axis direction, the CT scan direction is the z-axis direction, and the direction perpendicular to the plane formed by the x-axis and the z-axis is set as the y-axis direction; the left-right direction of the pelvis refers to the horizontal direction from the left side of the pelvis to the pelvis The direction of the right side of the 2D image is spatially superimposed along the z-axis direction to generate a 3D bone model image including only bones.
可选地，在根据本发明的方法中，根据所述标注骨骼图像生成具有标注数据的标注骨骼图像的步骤包括：识别出所述三维骨骼模型图像中的预先设定的关键点的位置；在所述三维骨骼模型图像中将这些关键点的位置标注出来，生成具有标注数据的所述标注骨骼图像。Optionally, in the method according to the present invention, the step of generating an annotated skeleton image with annotated data according to the annotated skeleton image includes: recognizing the position of a preset key point in the three-dimensional skeleton model image; The positions of these key points are marked in the three-dimensional bone model image, and the marked bone image with marked data is generated.
可选地，在根据本发明的方法中，所述关键点包括髂前上棘、耻骨联合、小转子、股骨头重心、髓腔轴线及髋臼轴线中的一个或多个。Optionally, in the method according to the present invention, the key points include one or more of the anterior superior iliac spine, the pubic symphysis, the lesser trochanter, the center of gravity of the femoral head, the medullary canal axis, and the acetabular axis.
可选地，在根据本发明的方法中，生成具有标注数据的标注骨骼图像的步骤后包括：对所述标注骨骼图像中的各个部位进行矫正处理，生成矫正后的标注骨骼图像。Optionally, in the method according to the present invention, the step of generating an annotated skeleton image with annotation data includes: performing correction processing on each part in the annotated skeleton image to generate a corrected annotated skeleton image.
可选地，在根据本发明的方法中，所述矫正处理包括对于骨盆的矫正处理以及对于两侧股骨的矫正处理。Optionally, in the method according to the present invention, the correction treatment includes a correction treatment for the pelvis and a correction treatment for both sides of the femur.
可选地，在根据本发明的方法中，针对骨盆的矫正处理，对所述标注骨骼图像中的各个部位进行矫正处理生成矫正后的标注骨骼图像的步骤包括：确定包括双侧髂前上棘及耻骨联合的三个关键点；利用这三个关键点所形成的APP平面，使APP平面与y轴垂直，以生成矫正后的标注骨骼图像作为标注骨骼图像。Optionally, in the method according to the present invention, for the correction processing of the pelvis, the step of performing correction processing on each part in the marked bone image to generate a corrected marked bone image includes: determining that the two sides include the anterior superior iliac spines. and the three key points of the pubic symphysis; the APP plane formed by these three key points is used to make the APP plane perpendicular to the y-axis to generate the corrected annotated bone image as the annotated bone image.
可选地，在根据本发明的方法中，针对两侧股骨的矫正处理，对所述标注骨骼图像中的各个部位进行矫正处理生成矫正后的标注骨骼图像的步骤包括：确定所述标注骨骼图像中的股骨头重心与髓腔轴线；利用所述股骨头重心与髓腔轴线形成矫正平面；将所述矫正平面按照与x轴方向和z轴方向形成的平面平行的方向来进行矫正，生成矫正后的标注骨骼图像作为标注骨骼图像。Optionally, in the method according to the present invention, for the correction processing of the femurs on both sides, the step of performing correction processing on each part in the marked bone image to generate a corrected marked bone image includes: determining the marked bone image. The center of gravity of the femoral head and the axis of the medullary cavity in the femoral head; use the center of gravity of the femoral head and the axis of the medullary cavity to form a correction plane; correct the correction plane according to the direction parallel to the plane formed by the x-axis direction and the z-axis direction to generate a correction The resulting annotated skeleton image is used as an annotated skeleton image.
可选地，在根据本发明的方法中，生成具有标注数据的标注骨骼图像的步骤后包括：根据所述标注骨骼图像，确定将被放置的假体以及所述假体的放置信息。Optionally, in the method according to the present invention, the step of generating an annotated bone image with annotation data includes: determining a prosthesis to be placed and placement information of the prosthesis according to the annotated bone image.
可选地，在根据本发明的方法中，根据所述标注骨骼图像确定将被放置的假体以及所述假体的放置信息的步骤包括：根据所述标注骨骼图像，确定髋臼杯假体的大小型号以及放置信息，其中，所述放置信息包括髋臼杯放置的角度以及三维空间放置的位置；根据所述标注骨骼图像中的标注，确定股骨旋转中心，股骨髓腔轴线和股骨髓腔尺寸，根据股骨旋转中心、股骨髓腔轴线和股骨髓腔尺寸，确定股骨柄假体的大小型号及三维空间放置位置，其中，所述放置位置包括放置的假体内翻外翻角度以及放置的位置。Optionally, in the method according to the present invention, the step of determining the prosthesis to be placed and the placement information of the prosthesis according to the annotated bone image includes: determining an acetabular cup prosthesis according to the annotated bone image The size, model and placement information of the acetabular cup, wherein the placement information includes the angle of placement of the acetabular cup and the placement position in three-dimensional space; according to the annotations in the annotated bone image, determine the center of rotation of the femur, the axis of the femoral medullary canal and the femoral medullary canal Size, according to the femoral center of rotation, the axis of the femoral medullary canal and the size of the femoral medullary canal, determine the size and model of the femoral stem prosthesis and the three-dimensional space placement position, wherein the placement position includes the placed prosthesis varus and valgus angle and placement. Location.
可选地，在根据本发明的方法中，根据所述标注骨骼图像确定髋臼杯假体的型号以及放置信息的步骤包括：识别出所述标注骨骼图像中的髋臼的月状面；利用所述月状面拟合出的球形，确定髋臼杯假体的旋转中心，大小型号以及三维放置信息。Optionally, in the method according to the present invention, the step of determining the model and placement information of the acetabular cup prosthesis according to the labeled bone image includes: identifying the lunate surface of the acetabulum in the labeled bone image; using The spherical shape fitted by the lunate surface determines the rotation center, size and model and three-dimensional placement information of the acetabular cup prosthesis.
可选地，在根据本发明的方法中，根据所述尺寸确定股骨柄假体的型号以及放置位置的步骤包括：通过髋臼旋转中心和双侧股骨小转子的位置确定所述股骨柄假体的初步位置；通过与股骨髓腔轴线及股骨髓腔在多个不同层面上的大小拟合，确定所述股骨柄假体的大小型号以及放置位置。Optionally, in the method according to the present invention, the step of determining the type and placement position of the femoral stem prosthesis according to the size includes: determining the femoral stem prosthesis according to the acetabular rotation center and the positions of the bilateral femoral lesser trochanter. The initial position of the femoral stem prosthesis is determined by fitting with the axis of the femoral medullary cavity and the size of the femoral medullary cavity at multiple different levels to determine the size and placement position of the femoral stem prosthesis.
可选地，在根据本发明的方法中，根据所述标注骨骼图像，确定将被放置的假体以及所述假体的放置信息的步骤还包括：对所述股骨柄假体及髋臼杯假体按照评估因子进行计算，生成评估信息。Optionally, in the method according to the present invention, the step of determining the prosthesis to be placed and the placement information of the prosthesis according to the annotated bone image further comprises: analysing the femoral stem prosthesis and the acetabular cup The prosthesis is calculated according to the evaluation factor to generate evaluation information.
可选地，在根据本发明的方法中，所述评估因子包括以下中的一个或多个：髋臼杯覆盖率、双下肢是否等长以及两侧偏距状况。Optionally, in the method according to the present invention, the evaluation factors include one or more of the following: acetabular cup coverage, whether the two lower limbs are of equal length, and bilateral offset status.
根据本发明的又一方面，提供了一种计算设备，包括：一个或多个处理器；和存储器；一个或多个程序，其中一个或多个程序存储在存储器中并被配置为由一个或多个处理器执行，一个或多个程序包括用于执行如上所述方法中的任一方法的指令。According to yet another aspect of the present invention, there is provided a computing device comprising: one or more processors; and a memory; one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more Multiple processors execute, one or more programs including instructions for performing any of the methods described above.
根据本发明的再一方面，提供了一种存储一个或多个程序的计算机可读存储介质，一个或多个程序包括指令，指令当计算设备执行时，使得计算设备执行如上所述的方法中的任一方法。According to yet another aspect of the present invention, there is provided a computer-readable storage medium storing one or more programs, the one or more programs comprising instructions that, when executed by a computing device, cause the computing device to perform any of the methods described above. any method.
根据本发明的方案，可在进行假体安置之前，为假体安置提供准确率高的髋关节数据。可通过生成仅包括骨骼信息的三维立体图像，确定假体型号大小以及假体所安放的位置。更进一步地，可利用已训练好的计算机模型更准确地识别出各个图像中的骨骼，并利用这些骨骼生成准确的三维图像，特别是在骨科，利用本发明的方案，可以帮助医师最大精度的定位髋臼杯假体及股骨柄假体的实际位置，帮助术者在三维信息上，全视角评估假体的放置位置，术前精确规划假体的型号及方位，安放好之后不仅可以360度旋转观察骨盆或股骨，评估假体的安放角度，同时还可以评估假体安放后的髋臼杯覆盖率、腿长、偏距等手术参数。缩短年轻临床医师的学习曲线，降低假体脱位，假体松动，疼痛等并发症的发生率。According to the solution of the present invention, the hip joint data with high accuracy can be provided for the prosthesis placement before the prosthesis placement is performed. The size of the prosthesis and the placement of the prosthesis can be determined by generating a three-dimensional stereoscopic image that includes only bone information. Further, the trained computer model can be used to more accurately identify the bones in each image, and use these bones to generate accurate three-dimensional images, especially in orthopedics, the solution of the present invention can help physicians in the maximum accuracy. Locating the actual position of the acetabular cup prosthesis and the femoral stem prosthesis helps the operator to evaluate the placement position of the prosthesis from a full perspective on three-dimensional information, and accurately plan the type and orientation of the prosthesis before surgery. Rotate to observe the pelvis or femur, evaluate the placement angle of the prosthesis, and also evaluate surgical parameters such as acetabular cup coverage, leg length, and offset after prosthesis placement. Shorten the learning curve for young clinicians and reduce the incidence of complications such as prosthesis dislocation, prosthesis loosening, and pain.
附图说明Description of drawings
为了实现上述以及相关目的，本文结合下面的描述和附图来描述某些说明性方面，这些方面指示了可以实践本文所公开的原理的各种方式，并且所有方面及其等效方面旨在落入所要求保护的主题的范围内。通过结合附图阅读下面的详细描述，本公开的上述以及其它目的、特征和优势将变得更加明显。遍及本公开，相同的附图标记通常指代相同的部件或元素。To achieve the above and related objects, certain illustrative aspects are described herein in conjunction with the following description and drawings, which are indicative of the various ways in which the principles disclosed herein may be practiced, and all aspects and their equivalents are intended to be within the scope of the claimed subject matter. The above and other objects, features and advantages of the present disclosure will become more apparent by reading the following detailed description in conjunction with the accompanying drawings. Throughout this disclosure, the same reference numbers generally refer to the same parts or elements.
图1示出了根据本发明一个实施例的计算设备100的构造示意图；FIG. 1 shows a schematic structural diagram of a computing device 100 according to an embodiment of the present invention;
图2示出了根据本发明一个实施例的针对髋关节的图像处理方法200的流程示意图；FIG. 2 shows a schematic flowchart of an
图3示出了根据本发明一个实施例的髋关节置换的示图；Figure 3 shows a diagram of a hip replacement according to one embodiment of the present invention;
图4示出了根据本发明一个实施例的针对髋关节的图像处理系统400的示意图。FIG. 4 shows a schematic diagram of an
具体实施方式Detailed ways
下面将参照附图更详细地描述本公开的示例性实施例。虽然附图中显示了本公开的示例性实施例，然而应当理解，可以以各种形式实现本公开而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本公开，并且能够将本公开的范围完整的传达给本领域的技术人员。Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.
图1是示例计算设备100的框图。在基本的配置102中，计算设备100典型地包括系统存储器106和一个或者多个处理器104。存储器总线108可以用于在处理器104和系统存储器106之间的通信。FIG. 1 is a block diagram of an example computing device 100 . In a basic configuration 102 , computing device 100 typically includes system memory 106 and one or more processors 104 . The memory bus 108 may be used for communication between the processor 104 and the system memory 106 .
取决于期望的配置，处理器104可以是任何类型的处理器，包括但不限于：微处理器(μP)、微控制器(μC)、数字信息处理器(DSP)或者它们的任何组合。处理器104可以包括诸如一级高速缓存110和二级高速缓存112之类的一个或者多个级别的高速缓存、处理器核心114和寄存器116。示例的处理器核心114可以包括运算逻辑单元(ALU)、浮点数单元(FPU)、数字信号处理核心(DSP核心)或者它们的任何组合。示例的存储器控制器118可以与处理器104一起使用，或者在一些实现中，存储器控制器118可以是处理器104的一个内部部分。Depending on the desired configuration, the processor 104 may be any type of processor including, but not limited to, a microprocessor (μP), a microcontroller (μC), a digital information processor (DSP), or any combination thereof. Processor 104 may include one or more levels of cache, such as
取决于期望的配置，系统存储器106可以是任意类型的存储器，包括但不限于：易失性存储器(诸如RAM)、非易失性存储器(诸如ROM、闪存等)或者它们的任何组合。系统存储器106可以包括操作系统120、一个或者多个应用122以及程序数据124。在一些实施方式中，应用122可以布置为在操作系统上利用程序数据124进行操作。在一些实施例中，计算设备100被配置为执行针对髋关节的图像处理方法200，程序数据124中就包含了用于执行上述各方法的指令。Depending on the desired configuration, system memory 106 may be any type of memory including, but not limited to, volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. System memory 106 may include operating system 120 , one or more applications 122 , and program data 124 . In some embodiments, application 122 may be arranged to operate with program data 124 on an operating system. In some embodiments, the computing device 100 is configured to perform the
计算设备100还可以包括有助于从各种接口设备(例如，输出设备142、外设接口144和通信设备146)到基本配置102经由总线/接口控制器130的通信的接口总线140。示例的输出设备142包括图形处理单元148和音频处理单元150。它们可以被配置为有助于经由一个或者多个A/V端口152与诸如显示器或者扬声器之类的各种外部设备进行通信。示例外设接口144可以包括串行接口控制器154和并行接口控制器156，它们可以被配置为有助于经由一个或者多个I/O端口158和诸如输入设备(例如，键盘、鼠标、笔、语音输入设备、图像输入设备)或者其他外设(例如打印机、扫描仪等)之类的外部设备进行通信。示例的通信设备146可以包括网络控制器160，其可以被布置为便于经由一个或者多个通信端口164与一个或者多个其他计算设备162通过网络通信链路的通信。Computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (eg, output device 142 , peripheral interface 144 , and communication device 146 ) to base configuration 102 via bus/
网络通信链路可以是通信介质的一个示例。通信介质通常可以体现为在诸如载波或者其他传输机制之类的调制数据信号中的计算机可读指令、数据结构、程序模块，并且可以包括任何信息递送介质。“调制数据信号”可以是这样的信号，它的数据集中的一个或者多个或者它的改变可以在信号中以编码信息的方式进行。作为非限制性的示例，通信介质可以包括诸如有线网络或者专线网络之类的有线介质，以及诸如声音、射频(RF)、微波、红外(IR)或者其它无线介质在内的各种无线介质。这里使用的术语计算机可读介质可以包括存储介质和通信介质二者。在一些实施例中，计算机可读介质中存储一个或多个程序，这一个或多个程序中包括执行某些方法(如方法200)的指令。A network communication link may be one example of a communication medium. Communication media may typically embody computer readable instructions, data structures, program modules in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media. A "modulated data signal" may be a signal in which one or more of its data sets or whose changes may be made in the signal in a manner that encodes information. By way of non-limiting example, communication media may include wired media, such as wired or leased line networks, and various wireless media, such as acoustic, radio frequency (RF), microwave, infrared (IR), or other wireless media. The term computer readable medium as used herein may include both storage media and communication media. In some embodiments, one or more programs are stored on a computer-readable medium, the one or more programs including instructions for performing certain methods (eg, method 200).
计算设备100可以实现为小尺寸便携(或者移动)电子设备的一部分，这些电子设备可以是诸如蜂窝电话、数码照相机、个人数字助理(PDA)、个人媒体播放器设备、无线网络浏览设备、个人头戴设备、应用专用设备、或者可以包括上面任何功能的混合设备。当然，计算设备100也可以实现为包括桌面计算机和笔记本计算机配置的个人计算机，或者是具有上述配置的服务器。本发明的实施方式对此均不作限制。Computing device 100 may be implemented as part of a small form factor portable (or mobile) electronic device such as a cellular telephone, digital camera, personal digital assistant (PDA), personal media player device, wireless web browsing device, personal headphone Wearables, application-specific devices, or hybrid devices that can include any of the above. Of course, the computing device 100 may also be implemented as a personal computer including a desktop computer and a notebook computer configuration, or as a server having the above-described configuration. The embodiments of the present invention are not limited thereto.
图2示出了根据本发明一个实施例的基于深度学习的髋关节的图像处理方法200的流程示意图。在对身体上的髋关节进行术前规划时，可采用本申请的图像处理方法确定适合的假体以及假体的安放位置。为了方便理解本发明，图3示出了髋关节置换的示图。FIG. 2 shows a schematic flowchart of an
髋关节主要有凸起的股骨头和凹陷的髋臼构成，凸起的股骨头呈球形、凹陷的髋臼像一只碗，所以股骨头和髋臼构成的髋关节在周边韧带、肌肉的包围下可以很稳定、同时又能像球在碗里面滑动一样使髋关节可以向各个方向自由运动。作为下肢与骨盆联结的关节，是承受人们活动(站立、行走和跑跳)时产生冲击力的重要关节。The hip joint is mainly composed of a convex femoral head and a concave acetabulum. The convex femoral head is spherical, and the concave acetabulum is like a bowl, so the hip joint composed of the femoral head and the acetabulum is surrounded by peripheral ligaments and muscles. It's very stable, and at the same time, like a ball sliding in a bowl, the hip joint can move freely in all directions. As the joint connecting the lower limbs with the pelvis, it is an important joint that bears the impact force generated by people's activities (standing, walking, running and jumping).
如图3所示，髋关节置换就是用人造的碗状假体301和球状假体302分别替代损坏了的髋臼和股骨头。在本发明中，可利用本发明的图像处理方法分别确定假体301以及假体302的型号与放置位置，从而为后续手术提供便利。As shown in FIG. 3, hip replacement is to replace the damaged acetabulum and femoral head with artificial bowl-shaped
以下将结合图2，详细阐述根据本发明实施例的图像处理方法针对髋关节的图像处理方法200的流程。The flow of the
在步骤S210，获取与将进行手术的髋关节对应的髋关节信息，其中，所述髋关节信息包括所述髋关节的髋关节图像以及与手术相关的手术信息。In step S210, hip joint information corresponding to the hip joint to be operated on is acquired, wherein the hip joint information includes a hip image of the hip joint and operation information related to the operation.
具体来说，在医学领域，可借助于某种介质(如X射线、电磁场、超声波等)与人体相互作用，把人体内部组织器官结构、密度以影像方式表现出来，供诊断医师根据影像提供的信息进行判断。Specifically, in the medical field, it is possible to interact with the human body by means of a certain medium (such as X-ray, electromagnetic field, ultrasound, etc.) information to judge.
DICOM被广泛应用于放射医疗，心血管成像以及放射诊疗诊断设备(X射线，CT，核磁共振，超声等)，并且在眼科和牙科等其它医学领域得到越来越深入广泛的应用。所有患者的医学图像都以DICOM文件格式进行存储。这样方便技术人员可利用同一格式的医学图像进行分析。DICOM is widely used in radiology, cardiovascular imaging and radiology diagnostic equipment (X-ray, CT, MRI, ultrasound, etc.), and has been more and more widely used in other medical fields such as ophthalmology and dentistry. All patient medical images are stored in DICOM file format. This makes it convenient for technicians to use the same format of medical images for analysis.
应用于本发明，医师可利用CT对髋关节进行扫描，生成DICOM格式的文件，并保存这些文件。为了更快地执行本方法，可将不同患者的DICOM文件按照不同文件夹进行存储，例如，如果有三个患者，则三个患者对应的髋关节图像分别存储在三个文件夹中。When applied to the present invention, the physician can scan the hip joint with CT, generate files in DICOM format, and save these files. In order to execute the method faster, the DICOM files of different patients can be stored in different folders. For example, if there are three patients, the images of the hip joints corresponding to the three patients are stored in three folders respectively.
此外，还可获取与手术相关的手术信息。所述手术信息包括所述髋关节在人体中的方位、所患疾病以及将被放置的假体所属的品类。In addition, surgical information related to the surgery can be obtained. The surgical information includes the position of the hip joint in the human body, the disease it suffers from, and the category of the prosthesis to be placed.
众所周知，每个人包含左右两侧的髋关节，即，在身体的左右两侧分别具有连接大腿与骨盆的髋关节，因此，在执行术前规划时，可确定将被执行手术的髋关节所在的方位，例如，左侧或者右侧。As we all know, each person contains left and right hip joints, that is, there are hip joints on the left and right sides of the body that connect the thigh and the pelvis. Therefore, when performing preoperative planning, it can be determined where the hip joint to be operated is located. Orientation, eg, left or right.
更进一步地，可确定患者所患的髋关节疾病，病种包括股骨头坏死、股骨颈骨折、先天性髋关节发育不良、骨关节炎以及强直性脊柱炎等。在确定了患者所患的病种后，可提供与所述病种相关的假体产品，例如，髋臼杯、内衬、球头、股骨柄。Further, the hip joint diseases that the patient suffers from can be determined, including femoral head necrosis, femoral neck fracture, congenital hip dysplasia, osteoarthritis and ankylosing spondylitis. After the patient's disease is determined, prosthetic products related to the disease can be provided, such as acetabular cups, liners, ball heads, and femoral stems.
随后，执行步骤S220，将所述髋关节图像输入到从所述手术信息中确定的髋关节分割模型组件，获取仅包括骨骼的三维骨骼模型图像。Then, step S220 is performed, the hip joint image is input into the hip joint segmentation model component determined from the operation information, and a three-dimensional bone model image including only bones is acquired.
具体来说，将所述髋关节图像分别输入到所述髋关节分割模型组件，获取仅包括骨骼的各个二维图像，其中，所述髋关节分割模型组件根据多个训练髋关节图像以及与从所述多个训练髋关节图像分别提取出的多个训练骨骼之间的对应关系进行机器学习得到的。在一种实施例中，训练骨骼为骨盆、左侧股骨、右侧股骨。这样，通过髋关节分割模型组件，获取的仅包括骨骼的各个二维图像包括相互分割的骨盆的图像、左侧股骨的图像、右侧股骨的图像。Specifically, the hip joint images are respectively input to the hip joint segmentation model component, and each two-dimensional image including only bones is obtained, wherein the hip joint segmentation model component is based on a plurality of training hip joint images and The correspondence between the plurality of training bones extracted from the plurality of training hip joint images is obtained through machine learning. In one embodiment, the training bones are pelvis, left femur, right femur. In this way, through the hip joint segmentation model component, the acquired two-dimensional images that only include bones include the image of the pelvis, the image of the left femur, and the image of the right femur, which are segmented from each other.
在实施中，可获取到多个训练髋关节图像，并利用人工标记的方式，从这些训练髋关节图像中分别提取出训练骨骼，随后，构建所述髋关节分割模型组件，设置有训练参数；利用多个训练髋关节图像以及与从所述多个训练髋关节图像分别提取出的多个训练骨骼之间的对应关系对所述髋关节分割模型组件进行训练，调整所述训练参数，直到所述髋关节分割模型组件达到预设要求。其中，所述髋关节分割模型组件可包括利用现有的机器学习算法形成的模型组件。这样，可将在手术中不需要的CT床以及软组织等信息进行去除。In the implementation, a plurality of training hip joint images can be obtained, and the training bones are respectively extracted from these training hip joint images by means of manual marking, and then the hip joint segmentation model component is constructed, and training parameters are set; The hip joint segmentation model component is trained using the plurality of training hip joint images and the corresponding relationships between the plurality of training bones extracted from the plurality of training hip joint images, and the training parameters are adjusted until all The hip joint segmentation model components meet the preset requirements. Wherein, the hip joint segmentation model component may include a model component formed by using an existing machine learning algorithm. In this way, information such as the CT bed and soft tissue that are not needed during the operation can be removed.
随后，将所述各个二维图像在空间上进行叠加，生成仅包括骨骼的三维骨骼模型图像，包括：将所述各个二维图像中的骨盆的左右方向设置为x轴方向，CT扫描方向为z轴方向，与x轴和z轴所成平面垂直的方向设置为y轴方向；将各个二维图像延z轴方向在空间上进行叠加，生成三维骨骼模型图像。Subsequently, the respective two-dimensional images are spatially superimposed to generate a three-dimensional bone model image including only bones, including: setting the left-right direction of the pelvis in the respective two-dimensional images as the x-axis direction, and the CT scanning direction as The z-axis direction, the direction perpendicular to the plane formed by the x-axis and the z-axis is set as the y-axis direction; each two-dimensional image is spatially superimposed along the z-axis direction to generate a three-dimensional bone model image.
在实施中，可获取到多个仅包含骨骼的二维图像，这些二维图像是从不同角度对同一个髋关节拍摄后获取的，因此，可能某些二维图像包含的是x轴和z轴平面的图像，有些是包含x轴和y轴平面的图像，通过这些的叠加，可生成仅包括骨骼的三维骨骼模型图像。In implementation, multiple 2D images containing only bones can be acquired, these 2D images are acquired after photographing the same hip joint from different angles, so it is possible that some 2D images contain x-axis and z-axis The images of the axis planes, some of which are images containing the x-axis and y-axis planes, through the superposition of these, a three-dimensional bone model image including only the bones can be generated.
随后，在步骤S230，通过对所述三维骨骼模型图像中的关键点的位置进行标注，生成具有标注数据的标注骨骼图像。具体包括：识别出所述三维骨骼模型图像中的预先设定的关键点的位置，其中，所述关键点可包括髂前上棘、耻骨联合、小转子、股骨头重心、髓腔轴线及髋臼轴线中的一个或多个。Then, in step S230, by annotating the positions of key points in the three-dimensional skeleton model image, an annotated skeleton image with annotated data is generated. Specifically, it includes: identifying the position of the preset key points in the three-dimensional bone model image, wherein the key points may include the anterior superior iliac spine, the pubic symphysis, the lesser trochanter, the center of gravity of the femoral head, the axis of the medullary canal, and the hip one or more of the mortar axes.
并且，在所述三维骨骼模型图像中将这些关键点的位置测量并标注出来，生成具有标注数据的所述标注骨骼图像，其中，所述测量数据包括髋臼尺寸、偏距等。In addition, the positions of these key points are measured and marked in the three-dimensional bone model image, and the marked bone image with marked data is generated, wherein the measured data includes the size of the acetabulum, the offset distance, and the like.
可选地，生成具有标注数据的标注骨骼图像的步骤后还包括：对所述标注骨骼图像中的各个部位进行矫正处理，生成矫正后的标注骨骼图像。在实施中，所述矫正处理可包括对于骨盆的矫正处理以及对于两侧股骨的矫正处理。Optionally, after the step of generating the labeled skeleton image with labeled data, the step further includes: performing correction processing on each part in the labeled skeleton image to generate a corrected labeled skeleton image. In implementation, the correction treatment may include correction treatment for the pelvis and correction treatment for both sides of the femur.
针对骨盆的矫正处理包括：1)可获取到双侧髂前上棘及耻骨联合这三个点，随后利用这三个点所形成的APP平面(anterior pelvic plane)，利用APP平面与y轴角度，来确定骨盆倾斜角度；2)令双侧髂前上棘连线与X轴平行，，以实现对骨盆的矫正处理。The correction treatment for the pelvis includes: 1) The three points of the bilateral anterior superior iliac spine and the pubic symphysis can be obtained, and then the APP plane (anterior pelvic plane) formed by these three points can be used, and the angle between the APP plane and the y-axis can be used. , to determine the pelvic tilt angle; 2) Make the line connecting the bilateral anterior superior iliac spines parallel to the X-axis to achieve corrective treatment of the pelvis.
针对股骨的矫正处理包括：可确定所述标注骨骼图像中的股骨头重心与髓腔轴线；利用所述股骨头重心与髓腔轴线形成矫正平面；将所述矫正平面按照与x轴方向和z轴方向形成的平面平行的方向来进行矫正；同时，令股骨左右侧后髁最低点连线与x轴方向和z轴方向形成的平面平行，以实现对股骨的矫正处理。The correction processing for the femur includes: determining the center of gravity of the femoral head and the axis of the medullary canal in the labeled bone image; using the center of gravity of the femoral head and the axis of the medullary canal to form a correction plane; At the same time, make the line connecting the lowest points of the left and right posterior condyles of the femur parallel to the plane formed by the x-axis and z-axis directions to realize the correction of the femur.
经过以上矫正处理，可生成矫正后的标注骨骼图像(包括对骨盆的矫正和对股骨的矫正)作为标注骨骼图像，即得到了矫正后的关键点位置。后续，根据这些关键点位置，可以从人工髋关节假体数据库模型中匹配到合适的假体，实现全髋关节置换的三维术前规划。After the above correction processing, the corrected annotated bone image (including the correction of the pelvis and the correction of the femur) can be generated as the marked bone image, that is, the corrected position of the key point is obtained. Subsequently, according to the positions of these key points, a suitable prosthesis can be matched from the artificial hip joint prosthesis database model to realize the three-dimensional preoperative planning of total hip joint replacement.
可选地，所述方法还包括：根据所述标注骨骼图像，确定将被放置的假体以及所述假体的放置信息。首先，根据所述标注骨骼图像，确定髋臼杯假体的大小型号以及放置信息，其中，所述放置信息包括髋臼杯放置的角度(例如，髋臼杯前倾角、髋臼杯外展角、髋臼杯放置深度、髋臼杯旋转中心位置等)以及髋臼杯在三维空间的放置位置，这可通过以下步骤获取：识别出所述标注骨骼图像中的髋臼的月状面；利用经由所述月状面拟合出的球形，确定髋臼杯假体的旋转中心、大小型号以及三维放置信息。Optionally, the method further includes: determining a prosthesis to be placed and placement information of the prosthesis according to the annotated bone image. First, determine the size and model of the acetabular cup prosthesis and placement information according to the labeled bone image, wherein the placement information includes the placement angle of the acetabular cup (eg, acetabular cup anteversion angle, acetabular cup abduction angle, etc.). , the placement depth of the acetabular cup, the position of the center of rotation of the acetabular cup, etc.) and the placement position of the acetabular cup in three-dimensional space, which can be obtained by the following steps: identifying the lunate surface of the acetabulum in the annotated bone image; using The center of rotation, size, and three-dimensional placement information of the acetabular cup prosthesis are determined through the spherical fitting of the lunate surface.
在实施中，通过机器学习算法自动将最合适大小的髋臼杯假体放置在最合理的位置，此外，临床医师可以根据自己的经验及习惯对髋臼杯假体的大小及位置角度进行调整、观察及评估。通过实践，髋臼杯放置的角度一般是外展40度及前倾20度。In the implementation, the most suitable size acetabular cup prosthesis is automatically placed in the most reasonable position through the machine learning algorithm. In addition, clinicians can adjust the size and position angle of the acetabular cup prosthesis according to their own experience and habits , observation and evaluation. Through practice, the angle of acetabular cup placement is generally 40 degrees of abduction and 20 degrees of anteversion.
在髋臼杯假体已经确定后，下一步可针对股骨柄假体进行操作。具体来说，根据所述标注骨骼图像中的标注(主要标注数据为所识别的关键点)，确定股骨旋转中心、股骨髓腔轴线和股骨髓腔尺寸；根据股骨旋转中心、股骨髓腔轴线和股骨髓腔尺寸，确定股骨柄假体的大小型号及三维空间放置位置，其中，所述放置位置包括放置的角度以及放置的位置，并且所述股骨柄假体的放置的角度可包括内外翻角度。After the acetabular cup prosthesis has been determined, the next step is to work on the femoral stem prosthesis. Specifically, according to the annotations in the annotated bone image (the main annotation data are the identified key points), determine the femoral rotation center, the femoral medullary canal axis and the femoral medullary canal size; according to the femoral rotation center, the femoral medullary canal axis and The size of the femoral medullary cavity, to determine the size and model of the femoral stem prosthesis and the placement position in three-dimensional space, wherein the placement position includes the placement angle and the placement position, and the placement angle of the femoral stem prosthesis may include the varus angle .
在根据所述尺寸确定股骨柄假体的型号以及放置位置时，可通过股骨旋转中心、股骨轴线、双侧股骨小转子的位置确定所述股骨柄假体的初步位置(较为准确的位置)。随后，利用所述髋臼杯假体的放置位置对初步位置进行调整，确定所述股骨柄假体的具体型号以及放置位置，具体来说，在利用髋臼的位置进行反推得到所述股骨柄假体的位置的情况下，在股骨柄假体的多个不同层面(如3个)骨髓腔上分别确定四个点，共12个点，这12个点与股骨皮质向重合最多的假体型号和放置位置即为最佳型号，简言之，通过与股骨髓腔在三个不同层面上的大小拟合来确定股骨柄的型号以及放置位置。When determining the model and placement position of the femoral stem prosthesis according to the size, the preliminary position (more accurate position) of the femoral stem prosthesis can be determined by the femoral rotation center, the femoral axis, and the positions of the bilateral lesser trochanter. Then, the preliminary position is adjusted using the placement position of the acetabular cup prosthesis, and the specific model and placement position of the femoral stem prosthesis are determined. In the case of the position of the stem prosthesis, four points are respectively determined on the medullary cavity of the femoral stem prosthesis at multiple different levels (such as 3), a total of 12 points, and these 12 points have the most overlap with the femoral cortex. The body size and placement position are the best size. In short, the size and placement of the femoral stem are determined by fitting with the femoral medullary cavity at three different levels.
此外，根据所述标注骨骼图像，确定将被放置的假体以及所述假体的放置信息的步骤后还包括：对所述股骨柄假体及髋臼杯假体按照评估因子进行计算，生成评估信息，其中，所述评估因子包括以下中的一个或多个：髋臼覆盖率、双下肢是否等长以及两侧偏距状况。In addition, after the step of determining the prosthesis to be placed and the placement information of the prosthesis according to the labeled bone image, the step further includes: calculating the femoral stem prosthesis and the acetabular cup prosthesis according to the evaluation factor, and generating Evaluation information, wherein the evaluation factors include one or more of the following: acetabular coverage, whether the two lower limbs are of equal length, and bilateral deviation.
髋臼覆盖率是指通过髋臼与髋臼杯假体的表面的相交的面积确定的。双肢是否等长则可通过两侧的小转子的位置来确定，两侧偏距状况可通过分别对比两侧偏距来判断。Acetabular coverage is determined by the area of intersection of the acetabulum and the surfaces of the acetabular cup prosthesis. Whether the two limbs are of equal length can be determined by the position of the lesser trochanter on both sides, and the deviation of the two sides can be judged by comparing the deviation of the two sides.
综上可述，根据本发明的方案，可获取到准确率高的髋关节数据，在此过程中，不仅利用机器学习精准识别出骨骼信息，去掉了与髋关节手术无关的干扰数据，并可利用这些图像形成三维立体图像，使得医者更直观地判断病情，更进一步地，可对形成的图像执行不同方面的矫正，从而避免了由于各种原因造成的偏差。在此基础上，可确定适合的假体安放方案，并在此过程中可不断进行调整，使得术前规划更可靠。更进一步地，可输出患者或医者期望输出的数据。To sum up, according to the solution of the present invention, hip joint data with high accuracy can be obtained. In this process, not only the bone information is accurately identified by machine learning, but the interference data irrelevant to hip joint surgery is removed, and the Using these images to form a three-dimensional image enables the doctor to judge the condition more intuitively, and further, different aspects of correction can be performed on the formed image, thereby avoiding deviations caused by various reasons. On this basis, a suitable prosthesis placement scheme can be determined, and continuous adjustment can be made during the process, making preoperative planning more reliable. Further, data that the patient or physician desires to be output may be output.
根据本发明的方案，可通过生成仅包括骨骼信息的三维立体图像，确定假体以及假体所安放的位置。更进一步地，可利用已训练好的计算机模型更准确地识别出各个图像中的骨骼，并利用这些骨骼生成准确地三维图像，特别是在骨科，利用本发明的方案，可以帮助医师最大精度的定位髋臼杯假体及股骨柄假体的实际位置，帮助术者在三维信息上，全视角评估假体的放置位置，术前精确规划假体的型号及方位，安放好之后不仅可以360度旋转观察骨盆或股骨，评估假体的安放角度，同时还可以评估假体安放后的腿长、偏距等手术参数。缩短年轻临床医师的学习曲线，降低假体脱位，假体松动，疼痛等并发症的发生率。According to the solution of the present invention, the prosthesis and the position where the prosthesis is placed can be determined by generating a three-dimensional stereo image including only bone information. Furthermore, the trained computer model can be used to more accurately identify the bones in each image, and use these bones to generate accurate three-dimensional images, especially in orthopedics, the solution of the present invention can help physicians in the maximum accuracy. Locating the actual position of the acetabular cup prosthesis and the femoral stem prosthesis helps the operator to evaluate the placement position of the prosthesis from a full perspective on three-dimensional information, and accurately plan the type and orientation of the prosthesis before surgery. Rotate to observe the pelvis or femur, evaluate the placement angle of the prosthesis, and also evaluate the surgical parameters such as leg length and offset after the prosthesis is placed. Shorten the learning curve for young clinicians and reduce the incidence of complications such as prosthesis dislocation, prosthesis loosening, and pain.
在实施中，还可提供如图4所示的针对髋关节的图像处理系统400。如图4所示，所述系统400可包括图像处理模块410、假体放置模块420以及功能模块430。In an implementation, an
图像处理模块410是执行根据本发明的一个实施例的针对髋关节的图像处理方法200。也就是说，图像处理模块410可对髋关节图像执行步骤S210至步骤S230，生成具有标注数据的标注骨骼图像。The
随后，可将该图像输入到假体放置模块420，利用该模块，确定将被放置的假体以及所述假体的位置。如何确定将被安放的假体以及所述假体的位置在以上已经具体描述，在此将不再赘述。This image can then be input to a
随后，可将已确定的假体安置方案输入到功能模块430。所述功能模块430可包括截骨模块、模拟运动模块、X线生线模块、生成数据模块、球头内衬型号调整模块、骨透明度调整模块以及参数测量模块。Subsequently, the determined prosthetic placement scheme may be input into
其中，截骨模块可在假体安装完成之后可以进行截骨；模拟运动模块则可在截完骨之后可以进行，可用于模拟安装假体后的运动情况。X线生成模块、骨透明度调整模块及参数测量模块可以在假体安置模块的全程进行，而生成数据模块则是在假体安置后进行，利用这些模块可在假体安放过程中进行实时调控，以对假体安置进行实时并动态地调整。球头内衬型号调整模块可在在股骨柄放置之后就可以进行调整。应注意，功能模块所包含的模块不限于以上子模块，所有可用于对假体安放进行功能性调整的模块均可应用于此。Among them, the osteotomy module can be used for osteotomy after the prosthesis is installed; the simulation motion module can be performed after the osteotomy is completed, and can be used to simulate the motion situation after the prosthesis is installed. The X-ray generation module, the bone transparency adjustment module and the parameter measurement module can be carried out during the whole process of the prosthesis placement module, while the data generation module is carried out after the prosthesis placement. These modules can be used for real-time adjustment during the prosthesis placement process. to make real-time and dynamic adjustments to prosthesis placement. The Ball Head Liner Model Adjustment Module can be adjusted after the femoral stem is placed. It should be noted that the modules included in the functional module are not limited to the above sub-modules, and all modules that can be used for functional adjustment of prosthesis placement can be applied here.
综上可述，根据本发明的方案，可利用图像处理模块，获取到准确率高的髋关节数据，在此过程中，不仅利用机器学习精准识别出骨骼信息，去掉了与髋关节手术无关的干扰数据，并可利用这些图像形成三维立体图像，使得医者更直观地判断病情，更进一步地，可对形成的图像执行不同方面的矫正，从而避免了由于各种原因造成的偏差。在此基础上，可利用假体安放模块确定适合的假体安放方案，并在此过程中可不断进行调整，使得术前规划更可靠。更进一步地，可利用功能模块输出患者或医者期望输出的数据。To sum up, according to the solution of the present invention, the image processing module can be used to obtain hip joint data with high accuracy. These images can be used to form a three-dimensional image, so that the doctor can judge the condition more intuitively. Furthermore, different aspects of correction can be performed on the formed image, thereby avoiding deviations caused by various reasons. On this basis, the appropriate prosthesis placement scheme can be determined by using the prosthesis placement module, and can be adjusted continuously during the process, making the preoperative planning more reliable. Furthermore, functional modules can be used to output data desired by the patient or the doctor.
根据本发明的方案，可通过生成仅包括骨骼信息的三维立体图像，确定假体以及假体所安放的位置。更进一步地，可利用已训练好的计算机模型更准确地识别出各个图像中的骨骼，并利用这些骨骼生成准确地三维图像，特别是在骨科，利用本发明的方案，可以帮助医师最大精度的定位髋臼杯假体及股骨柄假体的实际位置，帮助术者在三维信息上，全视角评估假体的放置位置，术前精确规划假体的型号及方位，安放好之后不仅可以360度旋转观察骨盆或股骨，评估假体的安放角度，同时还可以评估假体安放后的腿长、偏距等手术参数。缩短年轻临床医师的学习曲线，降低假体脱位，假体松动，疼痛等并发症的发生率。According to the solution of the present invention, the prosthesis and the position where the prosthesis is placed can be determined by generating a three-dimensional stereo image including only bone information. Furthermore, the trained computer model can be used to more accurately identify the bones in each image, and use these bones to generate accurate three-dimensional images, especially in orthopedics, the solution of the present invention can help physicians in the maximum accuracy. Locating the actual position of the acetabular cup prosthesis and the femoral stem prosthesis helps the operator to evaluate the placement position of the prosthesis from a full perspective on three-dimensional information, and accurately plan the type and orientation of the prosthesis before surgery. Rotate to observe the pelvis or femur, evaluate the placement angle of the prosthesis, and also evaluate the surgical parameters such as leg length and offset after the prosthesis is placed. Shorten the learning curve for young clinicians and reduce the incidence of complications such as prosthesis dislocation, prosthesis loosening, and pain.
应当理解，为了精简本公开并帮助理解各个发明方面中的一个或多个，在上面对本发明的示例性实施例的描述中，本发明的各个特征有时被一起分组到单个实施例、图、或者对其的描述中。然而，并不应将该公开的方法解释成反映如下意图：即所要求保护的本发明要求比在每个权利要求中所明确记载的特征更多特征。更确切地说，如下面的权利要求书所反映的那样，发明方面在于少于前面公开的单个实施例的所有特征。因此，遵循具体实施方式的权利要求书由此明确地并入该具体实施方式，其中每个权利要求本身都作为本发明的单独实施例。It will be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or in its description. This disclosure, however, should not be interpreted as reflecting an intention that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.
本领域那些技术人员应当理解在本文所公开的示例中的设备的模块或单元或组件可以布置在如该实施例中所描述的设备中，或者可替换地可以定位在与该示例中的设备不同的一个或多个设备中。前述示例中的模块可以组合为一个模块或者此外可以分成多个子模块。Those skilled in the art will appreciate that the modules or units or components of the apparatus in the examples disclosed herein may be arranged in the apparatus as described in this embodiment, or alternatively may be positioned differently from the apparatus in this example in one or more devices. The modules in the preceding examples may be combined into one module or further divided into sub-modules.
本领域那些技术人员可以理解，可以对实施例中的设备中的模块进行自适应性地改变并且把它们设置在与该实施例不同的一个或多个设备中。可以把实施例中的模块或单元或组件组合成一个模块或单元或组件，以及此外可以把它们分成多个子模块或子单元或子组件。除了这样的特征和/或过程或者单元中的至少一些是相互排斥之外，可以采用任何组合对本说明书(包括伴随的权利要求、摘要和附图)中公开的所有特征以及如此公开的任何方法或者设备的所有过程或单元进行组合。除非另外明确陈述，本说明书(包括伴随的权利要求、摘要和附图)中公开的每个特征可以由提供相同、等同或相似目的的替代特征来代替。Those skilled in the art will understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and further they may be divided into multiple sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method so disclosed may be employed in any combination, unless at least some of such features and/or procedures or elements are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
此外，本领域的技术人员能够理解，尽管在此所述的一些实施例包括其它实施例中所包括的某些特征而不是其它特征，但是不同实施例的特征的组合意味着处于本发明的范围之内并且形成不同的实施例。例如，在下面的权利要求书中，所要求保护的实施例的任意之一都可以以任意的组合方式来使用。Furthermore, those skilled in the art will appreciate that although some of the embodiments described herein include certain features, but not others, included in other embodiments, that combinations of features of different embodiments are intended to be within the scope of the invention within and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
本发明一并公开了：The present invention also discloses:
A9、如A1所述的图像处理方法，其特征在于，生成具有标注数据的标注骨骼图像的步骤后还包括：对所述标注骨骼图像中的各个部位进行矫正处理，生成矫正后的标注骨骼图像。A9. The image processing method according to A1, characterized in that, after the step of generating an annotated skeleton image with annotated data, the step further includes: performing correction processing on each part in the annotated skeleton image to generate a corrected annotated skeleton image .
A10、如A9所述的图像处理方法，其特征在于，所述矫正处理包括对于骨盆的矫正处理以及对于两侧股骨的矫正处理。A10. The image processing method according to A9, wherein the correction processing includes correction processing for the pelvis and correction processing for both sides of the femur.
A11、如A10所述的图像处理方法，其特征在于，针对骨盆的矫正处理，对所述标注骨骼图像中的各个部位进行矫正处理生成矫正后的标注骨骼图像的步骤包括：确定包括双侧髂前上棘及耻骨联合的三个关键点；利用这三个关键点所形成的APP平面，利用APP平面与y轴角度，来确定骨盆倾斜角度；令双侧髂前上棘连线与X轴平行，以生成矫正后的骨盆图像作为矫正后的标注骨骼图像。A11. The image processing method according to A10, wherein, for the correction processing of the pelvis, the step of performing correction processing on each part in the marked bone image to generate the corrected marked bone image includes: Three key points of the anterior superior spine and pubic symphysis; use the APP plane formed by these three key points, and use the angle between the APP plane and the y-axis to determine the pelvic tilt angle; make the line connecting the bilateral anterior superior iliac spines and the X-axis Parallel to generate the corrected pelvis image as the corrected annotated bone image.
A12、如A11所述的图像处理方法，其特征在于，针对两侧股骨的矫正处理，对所述标注骨骼图像中的各个部位进行矫正处理生成矫正后的标注骨骼图像的步骤包括：确定所述标注骨骼图像中的股骨头重心与髓腔轴线；利用所述股骨头重心与髓腔轴线形成矫正平面；将所述矫正平面按照与x轴方向和z轴方向形成的平面平行的方向来进行矫正；令股骨左右侧后髁最低点连线与x轴方向和z轴方向形成的平面平行，生成矫正后的标注骨骼图像作为标注骨骼图像。A12. The image processing method according to A11, wherein, for the correction processing of the femurs on both sides, the step of performing correction processing on each part in the marked bone image to generate a corrected marked bone image comprises: determining the Marking the center of gravity of the femoral head and the axis of the medullary cavity in the bone image; using the center of gravity of the femoral head and the axis of the medullary cavity to form a correction plane; correcting the correction plane in a direction parallel to the plane formed by the x-axis direction and the z-axis direction ; Make the line connecting the lowest points of the left and right posterior condyles of the femur parallel to the plane formed by the x-axis direction and the z-axis direction, and generate the corrected annotated bone image as the annotated bone image.
A13、如A12所述的图像处理方法，其特征在于，生成具有标注数据的标注骨骼图像的步骤后包括：根据所述标注骨骼图像，确定将被放置的假体型号大小以及所述假体的放置信息。A13. The image processing method according to A12, wherein the step of generating an annotated skeleton image with annotated data includes: determining, according to the annotated skeleton image, the size of the prosthesis to be placed and the size of the prosthesis. Place information.
A14、如A13所述的图像处理方法，其特征在于，根据所述标注骨骼图像确定将被放置的假体以及所述假体的放置信息的步骤包括：根据所述标注骨骼图像，确定髋臼杯假体的型号以及放置信息，其中，所述放置信息包括放置的角度以及放置的位置；根据所述标注骨骼图像中的标注，确定股骨髓腔的尺寸；根据所述尺寸，确定股骨柄假体的型号及放置位置，其中，所述放置位置包括放置的角度以及放置的位置。A14. The image processing method according to A13, wherein the step of determining the prosthesis to be placed and the placement information of the prosthesis according to the labeled bone image comprises: determining the acetabulum according to the labeled bone image The model and placement information of the cup prosthesis, wherein the placement information includes the placement angle and the placement position; the size of the femoral medullary cavity is determined according to the annotation in the annotated bone image; according to the size, the femoral stem prosthesis is determined The model and placement position of the body, wherein the placement position includes the placement angle and placement position.
A15、如A14所述的图像处理方法，其特征在于，根据所述标注骨骼图像确定髋臼杯假体的型号以及放置信息的步骤包括：识别出所述标注骨骼图像中的髋臼的月状面；利用经由所述月状面拟合出的球形，确定髋臼杯假体的旋转中心，假体型号以及位置放置信息。A15. The image processing method according to A14, wherein the step of determining the model and placement information of the acetabular cup prosthesis according to the annotated bone image comprises: identifying the lunar shape of the acetabulum in the annotated bone image surface; determine the rotation center of the acetabular cup prosthesis, the model of the prosthesis and the position information by using the sphere fitted by the lunate surface.
A16、如A15所述的图像处理方法，其特征在于，根据所述尺寸确定股骨柄假体的型号以及放置位置的步骤包括：通过髋臼旋转中心和双侧股骨小转子的位置确定所述股骨柄假体的初步位置；通过与股骨髓腔在多个不同层面上的大小拟合，确定所述股骨柄假体的型号以及放置位置。A16. The image processing method according to A15, wherein the step of determining the type and placement position of the femoral stem prosthesis according to the size includes: determining the femoral stem prosthesis according to the rotation center of the acetabulum and the positions of the bilateral femoral lesser trochanter Preliminary position of the stem prosthesis; determine the size and placement position of the femoral stem prosthesis by fitting with the femoral medullary cavity at multiple levels.
A17、如A16所述的图像处理方法，其特征在于，根据所述标注骨骼图像，确定将被放置的假体型号大小以及所述假体的位置信息的步骤后还包括：对所述股骨柄假体及髋臼杯假体按照评估因子进行计算，生成评估信息。A17. The image processing method according to A16, characterized in that, after the step of determining the size of the prosthesis to be placed and the position information of the prosthesis according to the labeled bone image, the step further comprises: processing the femoral stem The prosthesis and acetabular cup prosthesis are calculated according to the evaluation factors to generate evaluation information.
A18、如A17所述的图像处理方法，其特征在于，所述评估因子包括以下中的一个或多个：髋臼杯覆盖率、双下肢是否等长以及两侧偏距状况。A18. The image processing method according to A17, wherein the evaluation factors include one or more of the following: acetabular cup coverage, whether the two lower limbs are of equal length, and bilateral deviation.
这里描述的各种技术可结合硬件或软件，或者它们的组合一起实现。从而，本发明的方法和设备，或者本发明的方法和设备的某些方面或部分可采取嵌入有形媒介，例如软盘、CD-ROM、硬盘驱动器或者其它任意机器可读的存储介质中的程序代码(即指令)的形式，其中当程序被载入诸如计算机之类的机器，并被所述机器执行时，所述机器变成实践本发明的设备。The various techniques described herein can be implemented in conjunction with hardware or software, or a combination thereof. Thus, the method and apparatus of the present invention, or certain aspects or portions of the method and apparatus of the present invention, may take the form of program code embedded in a tangible medium, such as a floppy disk, CD-ROM, hard drive, or any other machine-readable storage medium (ie, instructions), wherein when a program is loaded into a machine, such as a computer, and executed by the machine, the machine becomes an apparatus for practicing the invention.
在程序代码在可编程计算机上执行的情况下，计算设备一般包括处理器、处理器可读的存储介质(包括易失性和非易失性存储器和/或存储元件)，至少一个输入装置，和至少一个输出装置。其中，存储器被配置用于存储程序代码；处理器被配置用于根据该存储器中存储的所述程序代码中的指令，执行本发明所述的方法。Where the program code is executed on a programmable computer, the computing device typically includes a processor, a storage medium readable by the processor (including volatile and nonvolatile memory and/or storage elements), at least one input device, and at least one output device. Wherein, the memory is configured to store program codes; the processor is configured to execute the method of the present invention according to the instructions in the program codes stored in the memory.
以示例而非限制的方式，计算机可读介质包括计算机存储介质和通信介质。计算机可读介质包括计算机存储介质和通信介质。计算机存储介质存储诸如计算机可读指令、数据结构、程序模块或其它数据等信息。通信介质一般以诸如载波或其它传输机制等已调制数据信号来体现计算机可读指令、数据结构、程序模块或其它数据，并且包括任何信息传递介质。以上的任一种的组合也包括在计算机可读介质的范围之内。By way of example and not limitation, computer-readable media includes computer storage media and communication media. Computer-readable media includes computer storage media and communication media. Computer storage media store information such as computer readable instructions, data structures, program modules or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of computer-readable media.
此外，所述实施例中的一些在此被描述成可以由计算机系统的处理器或者由执行所述功能的其它装置实施的方法或方法元素的组合。因此，具有用于实施所述方法或方法元素的必要指令的处理器形成用于实施该方法或方法元素的装置。此外，装置实施例的在此所述的元素是如下装置的例子：该装置用于实施由为了实施该发明的目的的元素所执行的功能。Furthermore, some of the described embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other means for performing the described functions. Thus, a processor having the necessary instructions for implementing the method or method element forms means for implementing the method or method element. Furthermore, an element of an apparatus embodiment described herein is an example of a means for carrying out the function performed by the element for the purpose of carrying out the invention.
如在此所使用的那样，除非另行规定，使用序数词“第一”、“第二”、“第三”等等来描述普通对象仅仅表示涉及类似对象的不同实例，并且并不意图暗示这样被描述的对象必须具有时间上、空间上、排序方面或者以任意其它方式的给定顺序。As used herein, unless otherwise specified, the use of the ordinal numbers "first," "second," "third," etc. to describe common objects merely refers to different instances of similar objects, and is not intended to imply such The objects being described must have a given order in time, space, ordinal, or in any other way.
尽管根据有限数量的实施例描述了本发明，但是受益于上面的描述，本技术领域内的技术人员明白，在由此描述的本发明的范围内，可以设想其它实施例。此外，应当注意，本说明书中使用的语言主要是为了可读性和教导的目的而选择的，而不是为了解释或者限定本发明的主题而选择的。因此，在不偏离所附权利要求书的范围和精神的情况下，对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。对于本发明的范围，对本发明所做的公开是说明性的，而非限制性的，本发明的范围由所附权利要求书限定。While the invention has been described in terms of a limited number of embodiments, those skilled in the art will appreciate, having the benefit of the above description, that other embodiments are conceivable within the scope of the invention thus described. Furthermore, it should be noted that the language used in this specification has been principally selected for readability and teaching purposes, rather than to explain or define the subject matter of the invention. Accordingly, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. This disclosure is intended to be illustrative, not restrictive, as to the scope of the present invention, which is defined by the appended claims.
Claims (12)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010090208.2ACN111179350B (en) | 2020-02-13 | 2020-02-13 | Hip joint image processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010090208.2ACN111179350B (en) | 2020-02-13 | 2020-02-13 | Hip joint image processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111179350A CN111179350A (en) | 2020-05-19 |
| CN111179350Btrue CN111179350B (en) | 2022-04-08 |
Family
ID=70649674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010090208.2AActiveCN111179350B (en) | 2020-02-13 | 2020-02-13 | Hip joint image processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111179350B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111568609B (en)* | 2020-05-25 | 2021-09-28 | 北京长木谷医疗科技有限公司 | Method and device for obtaining coverage rate of acetabular cup prosthesis |
| CN111652301B (en)* | 2020-05-27 | 2021-03-02 | 北京长木谷医疗科技有限公司 | Femoral lesser trochanter identification method and device based on deep learning and electronic equipment |
| CN111888059B (en)* | 2020-07-06 | 2021-07-27 | 北京长木谷医疗科技有限公司 | Total hip image processing method and device based on deep learning and X-ray |
| CN112641510B (en)* | 2020-12-18 | 2021-08-17 | 北京长木谷医疗科技有限公司 | Joint replacement surgery robot navigation and positioning system and method |
| CN112641511B (en)* | 2020-12-18 | 2021-09-10 | 北京长木谷医疗科技有限公司 | Joint replacement surgery navigation system and method |
| CN112957126B (en)* | 2021-02-10 | 2022-02-08 | 北京长木谷医疗科技有限公司 | Deep learning-based unicondylar replacement preoperative planning method and related equipment |
| CN112971981B (en)* | 2021-03-02 | 2022-02-08 | 北京长木谷医疗科技有限公司 | Deep learning-based total hip joint image processing method and equipment |
| CN113674841A (en)* | 2021-08-23 | 2021-11-19 | 东成西就教育科技有限公司 | A template measurement system for preoperative imaging |
| CN113689402B (en)* | 2021-08-24 | 2022-04-12 | 北京长木谷医疗科技有限公司 | Method, device and storage medium for shape recognition of femoral medullary cavity based on deep learning |
| CN113744214B (en)* | 2021-08-24 | 2022-05-13 | 北京长木谷医疗科技有限公司 | Femoral stem placing device based on deep reinforcement learning and electronic equipment |
| CN113962927B (en)* | 2021-09-01 | 2022-07-12 | 北京长木谷医疗科技有限公司 | Acetabular cup position adjustment method, device and storage medium based on reinforcement learning |
| CN113842211B (en)* | 2021-09-03 | 2022-10-21 | 北京长木谷医疗科技有限公司 | Three-dimensional preoperative planning system and prosthesis model matching method for knee replacement |
| CN113926208B (en)* | 2021-10-11 | 2023-08-22 | 网易（杭州）网络有限公司 | Method and device for generating movable doll model, electronic equipment and readable medium |
| CN114119934B (en)* | 2021-11-26 | 2024-10-01 | 杭州柳叶刀机器人有限公司 | Pelvic bone correcting method, operation system, storage medium and electronic equipment |
| CN114092466B (en)* | 2021-12-01 | 2024-08-23 | 杭州柳叶刀机器人有限公司 | Method and system for assisting in calculating leg length using deep learning, and readable storage medium |
| CN114299177B (en)* | 2021-12-24 | 2022-09-09 | 武汉迈瑞科技有限公司 | Image processing method, image processing device, electronic equipment and storage medium |
| CN114494183B (en)* | 2022-01-25 | 2024-04-02 | 哈尔滨医科大学附属第一医院 | Automatic acetabular radius measurement method and system based on artificial intelligence |
| CN114419618B (en)* | 2022-01-27 | 2024-02-02 | 北京长木谷医疗科技股份有限公司 | Preoperative planning system for total hip replacement based on deep learning |
| CN114663363B (en)* | 2022-03-03 | 2023-11-17 | 四川大学 | Deep learning-based hip joint medical image processing method and device |
| CN116172763A (en)* | 2022-12-27 | 2023-05-30 | 杭州键嘉医疗科技股份有限公司 | An end-to-end device and method for intelligently generating planning schemes for hip replacement surgery |
| CN116597002B (en)* | 2023-05-12 | 2024-01-30 | 北京长木谷医疗科技股份有限公司 | Automatic femoral stem placement method, device and equipment based on deep reinforcement learning |
| CN117058087A (en)* | 2023-08-09 | 2023-11-14 | 联影智能医疗科技(北京)有限公司 | Medical image-based hip joint prosthesis matching method and program product |
| CN118037929B (en)* | 2024-03-22 | 2024-10-01 | 北京长木谷医疗科技股份有限公司 | Texture mapping 3D reconstruction method, device and electronic device based on deep learning |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859213A (en)* | 2019-01-28 | 2019-06-07 | 艾瑞迈迪科技石家庄有限公司 | Bone critical point detection method and device in joint replacement surgery |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7634306B2 (en)* | 2002-02-13 | 2009-12-15 | Kinamed, Inc. | Non-image, computer assisted navigation system for joint replacement surgery with modular implant system |
| CN102125472B (en)* | 2011-04-08 | 2013-04-17 | 上海交通大学医学院附属第九人民医院 | Acetabular prosthesis of artificial hip joint with rotational ellipsoid joint interface |
| US9167989B2 (en)* | 2011-09-16 | 2015-10-27 | Mako Surgical Corp. | Systems and methods for measuring parameters in joint replacement surgery |
| US10779751B2 (en)* | 2013-01-25 | 2020-09-22 | Medtronic Navigation, Inc. | System and process of utilizing image data to place a member |
| CN110891488B (en)* | 2017-03-09 | 2023-05-23 | 史密夫和内修有限公司 | sagittal rotation determined |
| CN107296651A (en)* | 2017-06-21 | 2017-10-27 | 四川大学 | It is a kind of to digitize the method that auxiliary determines distal femur Osteotomy |
| CN108765417B (en)* | 2018-06-15 | 2021-11-05 | 西安邮电大学 | A system and method for femoral X-ray film generation based on deep learning and digital reconstruction of radiological images |
| CN109567942B (en)* | 2018-10-31 | 2020-04-14 | 上海盼研机器人科技有限公司 | Craniomaxillofacial surgical robot auxiliary system adopting artificial intelligence technology |
| CN110648337A (en)* | 2019-09-23 | 2020-01-03 | 武汉联影医疗科技有限公司 | Hip joint segmentation method, hip joint segmentation device, electronic apparatus, and storage medium |
- 2020
- 2020-02-13CNCN202010090208.2Apatent/CN111179350B/enactiveActive
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859213A (en)* | 2019-01-28 | 2019-06-07 | 艾瑞迈迪科技石家庄有限公司 | Bone critical point detection method and device in joint replacement surgery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111179350A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111179350B (en) | Hip joint image processing system | |
| Cabarcas et al. | Accuracy of patient-specific instrumentation in shoulder arthroplasty: a systematic review and meta-analysis | |
| CN110730639B (en) | System and method for determining leg length changes during hip surgery | |
| Walch et al. | Three-dimensional planning and use of patient-specific guides improve glenoid component position: an in vitro study | |
| US9508149B2 (en) | Virtual 3D overlay as reduction aid for complex fractures | |
| CN111223146B (en) | Method and computing device for processing hip joint images | |
| US20160117817A1 (en) | Method of planning, preparing, supporting, monitoring and/or subsequently checking a surgical intervention in the human or animal body, apparatus for carrying out such an intervention and use of the apparatus | |
| WO2023029923A1 (en) | Three-dimensional preoperative planning method and system for knee joint replacement | |
| US11957418B2 (en) | Systems and methods for pre-operative visualization of a joint | |
| US11803969B2 (en) | Intraoperative imaging and virtual modeling methods, systems, and instrumentalities for fracture reduction | |
| CN111292363B (en) | Joint image processing method and device and computing equipment | |
| US8644909B2 (en) | Radiographic imaging method and apparatus | |
| JP2019506959A (en) | Automated arthroplasty planning | |
| JP2003144454A (en) | Joint operation support information computing method, joint operation support information computing program, and joint operation support information computing system | |
| CN106170705A (en) | Bone reconstruction and orthopedic implants | |
| JP2016532475A (en) | Method for optimal visualization of bone morphological regions of interest in X-ray images | |
| CN112826641B (en) | Guide plate design method for total hip replacement and related equipment | |
| CN106963487A (en) | Knee joint disc-shaped meniscus simulation operation method | |
| CN115005987A (en) | Method and system for pelvis registration in hip revision surgery | |
| US20230263498A1 (en) | System and methods for calibration of x-ray images | |
| Bartels et al. | Computed tomography-based joint locations affect calculation of joint moments during gait when compared to scaling approaches | |
| Gomes et al. | Patient-specific modelling in orthopedics: from image to surgery | |
| RU2551304C2 (en) | Method of modelling individual implants for osteosynthesis of fractures of long tubular bones | |
| CN118453111A (en) | Intraoperative knee joint space adjustment device and knee joint surgery equipment | |
| JP2021137500A (en) | Bone surgery support devices, support methods, programs, and recording media |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | Inventor after:Zhang Yiling Inventor after:Liu Xingyu Inventor before:Zhang Yiling Inventor before:Chai Wei Inventor before:Liu Xingyu Inventor before:An Yicheng | |
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | Address after:1109, SOHO building, Zhongguancun, No. 8, Haidian North 2nd Street, Haidian District, Beijing 100190 Patentee after:Zhang Yiling Patentee after:Beijing Changmugu Medical Technology Co.,Ltd. Patentee after:Changmugu medical technology (Qingdao) Co.,Ltd. Address before:1109, Zhongguancun SOHO Building, No. 8 Haidian North 2nd Street, Haidian District, Beijing, China, 100190 Patentee before:Zhang Yiling Patentee before:BEIJING CHANGMUGU MEDICAL TECHNOLOGY Co.,Ltd. Patentee before:Changmugu medical technology (Qingdao) Co.,Ltd. | |
| CP03 | Change of name, title or address |