An interactive measurement system and method for Cobb angle of three-dimensional spine model

Abstract

The present disclosure provides an interactive measurement system and method for the Cobb angle of a three-dimensional spine model, which belongs to the field of image processing technology. The scheme includes: acquiring spinal CT data to be measured, and performing data segmentation on the spinal CT data to generate a plurality of vertebrae data; distinguishing the vertebrae region from the background based on a binarization operation, and visually displaying the vertebrae data based on a visualization tool; selecting an upper vertebra and a lower vertebra to be measured based on the visualized vertebrae, selecting a partial point set on the upper surface of the lower vertebra according to a first preset rule, and obtaining a first plane based on least squares fitting; at the same time, selecting a partial point set on the lower surface of the upper vertebra according to a second preset rule, and obtaining a second plane based on least squares fitting; respectively calculating the normal vectors of the first plane and the second plane, and calculating the angle between the first plane and the second plane based on the two plane normal vectors to realize the calculation of the Cobb angle.

Description

Technical Field

[0001] The present invention belongs to the field of image processing technology, and in particular relates to an interactive measurement system and method for the Cobb angle of a three-dimensional spine model. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] The angle of scoliosis is directly related to the prediction of the risk of worsening spinal deformity and the determination of treatment methods. On X-rays, congenital scoliosis is very difficult to determine the end vertebra of scoliosis due to the combination of multiple continuous vertebral deformities and rib obstruction. The Cobb angle is a common standard for judging the severity of spinal deformity, determining the treatment method of spinal deformity, and observing the development and changes of spinal deformity. It is usually measured on a full-length spinal X-ray. The measurement steps are first to determine the upper and lower end vertebrae of the scoliosis, and then draw parallel lines along the upper end plate of the upper end vertebra and the lower end plate of the lower end vertebra. The angle formed by the two parallel lines is the Cobb angle.

[0004] However, the inventors found that the spine actually exists in three-dimensional space, and ordinary X-rays can only display two-dimensional information, so they often cannot provide comprehensive information. Moreover, due to the developmental deformity of the vertebral body, rib protrusions and kyphotic deformity of the scoliosis, the upper and lower vertebrae of the scoliosis are unclear or even unrecognizable on the X-rays, making the Cobb angle error of severe congenital scoliosis measured on the X-rays large and poor consistency. Therefore, the Cobb angle cannot be accurately used to judge spinal deformity on the X-rays. At the same time, the traditional Cobb angle measurement method often relies on the personal experience of the doctor. The cost of training an experienced doctor is high, and the intuition of each person is inevitably in error, resulting in the situation of misjudgment, which may delay the opportunity of early treatment and form a serious and rigid spinal deformity. Summary of the invention

[0005] In order to solve the above-mentioned problems, the present disclosure provides an interactive measurement system and method for the Cobb angle of a three-dimensional spine model. The scheme is based on visualization technology, which models the two-dimensional image data obtained from medical imaging equipment and converts them into three-dimensional data, thereby displaying the three-dimensional morphology of the human spine; at the same time, through the interactive selection of vertebrae to be measured, the subjective initiative of people is brought into play to avoid errors in the traditional measurement of Cobb angles due to the lack of experience of doctors or human intuitive factors, resulting in misjudgment.

[0006] According to a first aspect of an embodiment of the present disclosure, there is provided an interactive measurement system for the Cobb angle of a three-dimensional spine model, comprising:

[0007] A data acquisition unit, which is used to acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data;

[0008] A model building and visualization unit, which is used to distinguish the vertebral area from the background based on a binarization operation, and to visualize the vertebral data based on a visualization tool;

[0009] An interaction and fitting unit, which is used to select an upper vertebra and a lower vertebra to be tested based on a plurality of vertebrae displayed visually, select a partial point set on the upper surface of the lower vertebra according to a first preset rule, and obtain a first plane based on a least squares fitting method; at the same time, select a partial point set on the lower surface of the upper vertebra according to a second preset rule, and obtain a second plane based on a least squares fitting method;

[0010] The Cobb angle calculation unit is used to calculate the normal vectors of the first plane and the second plane respectively, and calculate the angle between the first plane and the second plane based on the two plane normal vectors to realize the calculation of the Cobb angle.

[0011] Furthermore, the vertebral area is distinguished from the background based on a binarization operation, specifically: based on a preset threshold range, the segmented vertebral data is binarized, and the binarized vertebral data is converted into an STL model.

[0012] Furthermore, the spinal CT data is segmented by inputting the spinal CT data into a pre-trained deep learning segmentation model to obtain segmented data of a plurality of vertebrae;

[0013] Furthermore, the vertebra data is visualized based on a visualization tool, specifically: the vertebra stl model is read based on the visualization function interface in the VTK visualization toolkit, and the vertebrae are rendered through the pipeline mechanism of VTK to obtain the visualization result of the vertebrae.

[0014] Furthermore, the first preset rule is specifically: obtaining the midpoint coordinate x of the lower cone bone data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min , a preset number of data points are selected to meet the following constraints:

[0015] X-axis direction:

[0016] Y-axis direction:

[0017] z-axis direction: point[x] <z mod .

[0018] Furthermore, the second preset rule is specifically: obtaining the midpoint coordinate x of the upper cone bone data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min , a preset number of data points are selected to meet the following constraints:

[0019] X-axis direction:

[0020] Y-axis direction:

[0021] z-axis direction: point[x]>z mod .

[0022] Furthermore, the lower vertebra and the upper vertebra are adjacent vertebrae.

[0023] According to a second aspect of an embodiment of the present disclosure, there is provided an interactive measurement method of the Cobb angle of a three-dimensional spine model, comprising:

[0024] Acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data;

[0025] Distinguishing the vertebral region from the background based on a binarization operation, and visually displaying the vertebral data based on a visualization tool;

[0026] Based on the visualized display of several vertebrae, the upper vertebrae and the lower vertebrae to be tested are selected, a partial point set is selected on the upper surface of the lower vertebra according to a first preset rule, and a first plane is obtained by fitting based on the least square method; at the same time, a partial point set is selected on the lower surface of the upper vertebra according to a second preset rule, and a second plane is obtained by fitting based on the least square method;

[0027] The normal vectors of the first plane and the second plane are calculated respectively, and based on the two plane normal vectors, the angle between the first plane and the second plane is calculated to realize the calculation of the Cobb angle.

[0028] According to a third aspect of an embodiment of the present disclosure, there is provided an electronic device comprising a memory, a processor and a computer program stored and running on the memory, wherein when the processor executes the program, the method for interactively measuring the Cobb angle of a three-dimensional spine model is implemented.

[0029] According to a fourth aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the interactive measurement method of the Cobb angle of a three-dimensional spine model is implemented.

[0030] Compared with the prior art, the beneficial effects of the present invention are:

[0031] The scheme disclosed in the present invention provides an interactive measurement system and method for the Cobb angle of a three-dimensional spine model. The scheme is based on the vertebral modeling results and uses an interactive method to measure the Cobb angle of the spine. After modeling, the structural information of the spine can be intuitively displayed, which improves the disadvantage that ordinary X-rays can only display two-dimensional information, so that the spine that actually exists in three-dimensional space can be more intuitively represented in a three-dimensional way, and is closer to people's intuitive feelings. Interactive selection of appropriate vertebrae not only gives play to people's subjective initiative, but also avoids the errors caused by the traditional measurement of Cobb angles due to the doctor's lack of experience or people's intuitive factors, resulting in misjudgment.

[0032] Advantages of additional aspects of the present disclosure will be given in part in the following description, and in part will become apparent from the following description, or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0034] Figure 1 It is a schematic diagram of the processing flow of an interactive measurement system for the Cobb angle of a three-dimensional spine model described in an embodiment of the present disclosure.

[0035] FIG. 2( a ) and FIG. 2( b ) are respectively the display results of the segmented vertebrae described in the embodiment of the present disclosure;

[0036] FIG3( a ) and FIG3( b ) are schematic diagrams of plane fitting based on the least square method described in an embodiment of the present disclosure;

[0037] Figure 4 It is a schematic diagram of calculating the Cobb angle based on the fitting plane described in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0038] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0039] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0040] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0041] In the absence of conflict, the embodiments in the present disclosure and the features in the embodiments may be combined with each other.

[0042] Embodiment 1:

[0043] The purpose of this embodiment is to provide an interactive measurement system for the Cobb angle of a three-dimensional spine model.

[0044] like Figure 1 As shown, an interactive measurement system for Cobb angle of a three-dimensional spine model includes:

[0045] A data acquisition unit, which is used to acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data;

[0046] A model building and visualization unit, which is used to distinguish the vertebral area from the background based on a binarization operation, and to visualize the vertebral data based on a visualization tool;

[0047] An interaction and fitting unit, which is used to select an upper vertebra and a lower vertebra to be tested based on a plurality of vertebrae displayed visually, select a partial point set on the upper surface of the lower vertebra according to a first preset rule, and obtain a first plane based on a least squares fitting method; at the same time, select a partial point set on the lower surface of the upper vertebra according to a second preset rule, and obtain a second plane based on a least squares fitting method;

[0048] The Cobb angle calculation unit is used to calculate the normal vectors of the first plane and the second plane respectively, and calculate the angle between the first plane and the second plane based on the two plane normal vectors to realize the calculation of the Cobb angle.

[0049] Furthermore, the vertebral area is distinguished from the background based on a binarization operation, specifically: based on a preset threshold range, the segmented vertebral data is binarized, and the binarized vertebral data is converted into an STL model.

[0050] Furthermore, the spinal CT data is segmented by inputting the spinal CT data into a pre-trained deep learning segmentation model to obtain segmented data of a plurality of vertebrae;

[0051] Furthermore, the vertebra data is visualized based on a visualization tool, specifically: the vertebra stl model is read based on the visualization function interface in the VTK visualization toolkit, and the vertebrae are rendered through the pipeline mechanism of VTK to obtain the visualization result of the vertebrae.

[0052] Furthermore, the first preset rule is specifically: obtaining the midpoint coordinate x of the lower cone bone data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min , a preset number of data points are selected to meet the following constraints:

[0053] X-axis direction:

[0054] Y-axis direction:

[0055] z-axis direction: point[x] <z mod .

[0056] Furthermore, the second preset rule is specifically: obtaining the midpoint coordinate x of the upper cone bone data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min , a preset number of data points are selected to meet the following constraints:

[0057] X-axis direction:

[0058] Y-axis direction:

[0059] z-axis direction: point[x]>z mod .

[0060] Furthermore, the lower vertebra and the upper vertebra are adjacent vertebrae.

[0061] Specifically, for ease of understanding, the solution disclosed in the present disclosure is described in detail below with reference to the accompanying drawings:

[0062] In order to deal with the problem of measuring the Cobb angle of the spine, the commonly used method is usually to measure it on the spinal X-ray film, but the two-dimensional X-ray film cannot provide three-dimensional spinal information, resulting in errors in the measurement of the Cobb angle. Therefore, we propose to use visualization technology to model the two-dimensional image data obtained from medical imaging equipment and convert it into three-dimensional data, so as to show the three-dimensional morphology of the human spine. At the same time, an interactive measurement system for the Cobb angle of the three-dimensional spine model is proposed, such as Figure 1 As shown, the system specifically performs the following steps:

[0063] Step 1: Segmentation of CT data;

[0064] For the input spinal CT data, the entire spine is segmented into different vertebrae according to the pre-trained deep learning segmentation model to generate segmented vertebrae data. Specifically, the segmentation steps of CT data include:

[0065] Input the CT data of the spine into the trained model, which is trained by deep learning. The segmented spine data can be output by inputting the CT data. Among them, this step uses the nnune network in deep learning to train the model. Nnunet is an existing network for segmentation. This network is trained with a pre-standard vertebral CT data set to obtain a trained deep learning segmentation model. Figure 2 (a) and Figure 2 (b) show the segmented vertebrae results respectively;

[0066] Step 2: Model construction;

[0067] The vertebral data obtained in step 1 is threshold processed to generate a three-dimensional model. Specifically, it includes:

[0068] (1) Since the output of the previous model is a multimodal segmentation result, each vertebra has its own special threshold range, so when modeling, these segmented vertebrae must first be binarized so that the vertebrae can be distinguished from the background and can be converted into an STL model.

[0069] (2) The binary segmentation data is read into the memory in the form of DICOM using VTK, and the pipeline mechanism of VTK is used to generate it into an STL model.

[0070] Step 3: Model visualization. The vertebral model data is read into the system. The system page is composed of Pyqt. Based on the visualization method in the VTK visualization toolkit and the Pyqt development environment, the vertebral model is displayed in the visualization interface. Among them, the read-in stl model is rendered using the VTK pipeline mechanism.

[0071] Step 4: Fitting the lower surface of the lower vertebra. Select the lower vertebra to be tested, and the system selects a part of the point set on the lower vertebra according to the set rules, highlights these point sets and fits the point sets to the surface by the least squares method. FIG3 (a) shows a schematic diagram of the plane fitting of the lower surface of the lower vertebra based on the least squares method described in the embodiment of the present disclosure;

[0072] Figure 4 It is a schematic diagram of calculating the Cobb angle based on the fitting plane described in an embodiment of the present disclosure.

[0073] Specifically, the user selects a suitable lower vertebra. After the user selects a suitable lower vertebra, a suitable part of the point set in the lower vertebra is selected, and is highlighted in color on the page and participates in the surface fitting.

[0074] 1) According to the shape characteristics of the lower vertebra and the required information, the selection rule of the lower vertebra midpoint is as follows: Select the midpoint of the lower vertebra and obtain the midpoint coordinate x of the lower vertebra data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min , a preset number of data points are selected to meet the following constraints:

[0075] X-axis direction:

[0076] Y-axis direction:

[0077] z-axis direction: point[x] <z mod .

[0078] After three-dimensional constraint, a suitable point on the upper surface of the lower vertebra can be selected.

[0079] 2) In order to make the selected point highlighted in the model, a filter needs to be set. The filter rules are as follows: Add the selected point to the filter, the filter will loop the model, and for each point coordinate in the loop, find the edge in the grid that connects the nearest points (and is arranged along the line that forms a loop). At the current point, the grid edge that faces the direction and whose end point is closest to the straight line will be selected. Follow the edge to the new endpoint and repeat the process. This process will continue until the entire loop is created. In this way, the selected point is highlighted.

[0080] 3) Next, use the least squares method to fit the surface

[0081] Given a data point (x i ,y i , zi ), i = 1, 2 ..., N, find a plane equation z = ax + by + z, so that the total error Minimum.

[0082] Q(x,y,z) is a ternary function about unknown numbers a,b,c. From the knowledge of calculus, we know that we can determine the values ​​of a,b,c by only finding the extreme values ​​of the ternary function Q(x,y,z) about a,b,c. That is, a,b,c should satisfy: and

[0083] have to

[0084] The same goes for

[0085]

[0086] Combining (1), (2) and (3) we get a system of equations. If the coefficient matrix has the determinant D≠0, we can connect the values ​​of a, b and c.

[0087] Since "three points not on the same straight line determine a plane", to fit the plane equation, we need to give the data points (x i ,y i , z i ) must have at least three points, otherwise the fitting operation cannot be performed. However, under the screening rules, the number of points involved in the fitting is much greater than three, so the fitting operation can be performed.

[0088] Step 5: Fitting the upper surface of the upper vertebra. Select the upper vertebra to be tested, and the system selects a portion of the point set on the upper vertebra according to the set rules, highlights these point sets, and fits the point sets to the surface using the least squares method. FIG3( b ) shows a schematic diagram of plane fitting of the upper surface of the upper vertebra based on the least squares method described in the embodiment of the present disclosure.

[0089] Specifically include:

[0090] Further, after the appropriate upper vertebra is selected, the appropriate part of the upper vertebra is selected, changed color and highlighted in the page and participates in the surface fitting.

[0091] 1) According to the shape characteristics of the upper vertebra and the required information, the selection rule of the upper vertebra midpoint is as follows: Get the midpoint coordinate x of the upper vertebra data mod ,y mod , z mod ; and determine the maximum value x in the x-axis and y-axis directions max ,y max and the minimum value x min ,y min, a preset number of data points are selected to meet the following constraints:

[0092] X-axis direction:

[0093] Y-axis direction:

[0094] z-axis direction: point[x]>z mod .

[0095] After three-dimensional constraint, a suitable point on the upper surface of the upper vertebra can be selected.

[0096] 2) In order to make the selected point highlighted in the model, a filter needs to be set. The filter rules are as follows: Add the selected point to the filter, the filter will loop the model, and for each point coordinate in the loop, find the edge in the grid that connects the nearest points (and is arranged along the line that forms a loop). At the current point, the grid edge that faces the direction and whose end point is closest to the straight line will be selected. Follow the edge to the new endpoint and repeat the process. This process will continue until the entire loop is created, so that the selected point can be highlighted.

[0097] 3) Next, use the least squares method to fit the surface

[0098] Given a data point (x i ,y i , z i ), i = 1, 2 ..., N, find a plane equation z = ax + by + z so that the total error Minimum.

[0099] Q(x,y,z) is a ternary function about unknown numbers a,b,c. From the knowledge of calculus, we know that we can determine the values ​​of a,b,c by only finding the extreme values ​​of the ternary function Q(x,y,z) about a,b,c. That is, a,b,c should satisfy: and

[0100] have to

[0101] The same goes for

[0102]

[0103] Combining (1), (2) and (3) we get a system of equations. If the coefficient matrix has the determinant D≠0, we can connect the values ​​of a, b and c.

[0104] Since "three points not on the same straight line determine a plane", to fit the plane equation, we need to give the data points (x i ,y i, z i ) must have at least three points, otherwise the fitting operation cannot be performed. However, under the screening rules, the number of points involved in the fitting is much greater than three, so the fitting operation can be performed.

[0105] Step 6: Calculate and display the Cobb angle. Calculate the normal vector of the surface fitted in steps 4 and 5. Calculate the Cobb angle from the two plane normal vectors and display the calculated angle. Figure 4 A schematic diagram showing the calculation of the Cobb angle based on the fitted plane.

[0106] Among them, the calculation and display of the Cobb angle, the normal vectors of the two planes obtained in step 4 and step 5, according to the dihedral angle formula of the spatial plane, can get the angle formed by the two normal vectors, that is, the angle formed by the two spatial planes. Since the angle between the spatial planes is an acute angle, we also need to determine whether the angle calculated by the two plane normal vectors is an obtuse angle. If it is an obtuse angle, the next step must be carried out.

[0107]

[0108] θ=arccos(cosθ)

[0109]

[0110] The scheme described in this embodiment proposes to use an interactive method to measure the Cobb angle of the spine after modeling. After modeling, the structural information of the spine can be intuitively displayed, which improves the disadvantage that ordinary X-rays can only display two-dimensional information, so that the spine actually existing in three-dimensional space can be more intuitively displayed in a three-dimensional manner, which is closer to people's intuitive feelings, and the spinal deformity can be observed from multiple angles through rotation technology. In this way, when measuring the Cobb angle, it is helpful to identify the end vertebra of scoliosis and overcome the error caused by measuring the Cobb angle on a two-dimensional image. In addition, there is a unified method for traditionally measuring the Cobb angle. This measurement method often relies on the personal experience of the doctor, and each person's intuition is inevitably prone to errors, resulting in misjudgment, which may delay the opportunity for early treatment and form severe and rigid spinal deformities.

[0111] The interactive Cobb angle measurement method only requires the doctor to click on two appropriate vertebrae to generate the Cobb angle. Since the fitting surface uses not only a single CT slice, but the information of most CT slices, it avoids the measurement errors caused by different doctors' subjective intuition, which delays the treatment of the disease.

[0112] Embodiment 2:

[0113] The purpose of this embodiment is to provide an interactive measurement method for the Cobb angle of a three-dimensional spine model.

[0114] An interactive measurement method for Cobb angle of a three-dimensional spine model, comprising:

[0115] Acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data;

[0116] Distinguishing the vertebral region from the background based on a binarization operation, and visually displaying the vertebral data based on a visualization tool;

[0117] Based on the visualized display of several vertebrae, the upper vertebrae and the lower vertebrae to be tested are selected, a partial point set is selected on the upper surface of the lower vertebra according to a first preset rule, and a first plane is obtained by fitting based on the least square method; at the same time, a partial point set is selected on the lower surface of the upper vertebra according to a second preset rule, and a second plane is obtained by fitting based on the least square method;

[0118] The normal vectors of the first plane and the second plane are calculated respectively, and based on the two plane normal vectors, the angle between the first plane and the second plane is calculated to realize the calculation of the Cobb angle.

[0119] Furthermore, the method described in this embodiment corresponds to the solution of the system described in Embodiment 1, and its technical details have been described in detail in Embodiment 1, so they will not be repeated here.

[0120] In further embodiments, there is also provided:

[0121] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 2 is performed. For the sake of brevity, no further description is given here.

[0122] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0123] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0124] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method described in the second embodiment is completed.

[0125] The method in the second embodiment can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0126] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0127] The interactive measurement system and method of the Cobb angle of a three-dimensional spine model provided in the above embodiment can be realized and has broad application prospects.

[0128] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. An interactive measurement system for Cobb angle of a three-dimensional spine model, characterized in that: include: A data acquisition unit, which is used to acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data; the data segmentation on the spinal CT data is specifically performed by using a deep learning-based method to input the spinal CT data into a pre-trained deep learning segmentation model to obtain the segmented plurality of vertebrae data; A model building and visualization unit, which is used to distinguish the vertebral area from the background based on a binarization operation, and to visualize the vertebral data based on a visualization tool; An interaction and fitting unit, which is used to select an upper vertebra and a lower vertebra to be tested based on a plurality of vertebrae displayed visually, select a partial point set on the upper surface of the lower vertebra according to a first preset rule, and obtain a first plane based on a least squares fitting method; at the same time, select a partial point set on the lower surface of the upper vertebra according to a second preset rule, and obtain a second plane based on a least squares fitting method; The user selects a suitable lower vertebra. After the user selects a suitable lower vertebra, a suitable part of the point set in the lower vertebra is selected, changes color and is highlighted on the page and participates in the surface fitting; after the user selects a suitable upper vertebra, a suitable part of the upper vertebra is selected, changes color and is highlighted on the page and participates in the surface fitting; By setting filters, the selected points are highlighted in the model; The first preset rule is specifically: obtaining the midpoint coordinates of the lower cone bone data ; And determine the maximum value in the x-axis and y-axis directions and minimum value , a preset number of data points are selected to meet the following constraints: x-axis direction: point[x]≥ ,point[x]≤ ; Y-axis direction: point[y]≥ ,point[y]≤ ; z-axis direction: point[z]< ; The second preset rule is specifically: obtaining the midpoint coordinates of the upper cone bone data ; And determine the maximum value in the x-axis and y-axis directions and minimum value , a preset number of data points are selected to meet the following constraints: x-axis direction: point[x]≥ ,point[x]≤ ; Y-axis direction: point[y]≥ ,point[y]≤ ; z-axis direction: point[z]> ; The Cobb angle calculation unit is used to calculate the normal vectors of the first plane and the second plane respectively, and calculate the angle between the first plane and the second plane based on the two plane normal vectors to realize the calculation of the Cobb angle.

2. The interactive measurement system of Cobb angle of a three-dimensional spine model according to claim 1, characterized in that: The vertebral area is distinguished from the background based on the binarization operation. Specifically, based on a preset threshold range, the segmented vertebral data is binarized and the binarized vertebral data is converted into an STL model.

3. The interactive measurement system of Cobb angle of a three-dimensional spine model according to claim 1, characterized in that: The vertebra data is visualized based on a visualization tool, specifically: the vertebra stl model is read based on the visualization function interface in the VTK visualization toolkit, and the vertebrae are rendered through the pipeline mechanism of VTK to obtain the visualization result of the vertebrae.

4. The interactive measurement system of Cobb angle of a three-dimensional spine model according to claim 1, characterized in that: The lower vertebra and the upper vertebra are adjacent vertebrae.

5. An interactive measurement method for the Cobb angle of a three-dimensional spine model, characterized in that: include: Acquire the spinal CT data to be tested, and perform data segmentation on the spinal CT data to generate a plurality of vertebrae data; the data segmentation on the spinal CT data is specifically performed by using a deep learning-based method, inputting the spinal CT data into a pre-trained deep learning segmentation model to obtain a plurality of segmented vertebrae data; Distinguishing the vertebral region from the background based on a binarization operation, and visually displaying the vertebral data based on a visualization tool; Based on the visualized display of several vertebrae, the upper vertebrae and the lower vertebrae to be tested are selected, a partial point set is selected on the upper surface of the lower vertebra according to a first preset rule, and a first plane is obtained by fitting based on the least square method; at the same time, a partial point set is selected on the lower surface of the upper vertebra according to a second preset rule, and a second plane is obtained by fitting based on the least square method; The user selects a suitable lower vertebra. After the user selects a suitable lower vertebra, a suitable part of the point set in the lower vertebra is selected, changes color and is highlighted on the page and participates in the surface fitting; after the user selects a suitable upper vertebra, a suitable part of the upper vertebra is selected, changes color and is highlighted on the page and participates in the surface fitting; By setting filters, the selected points are highlighted in the model; The first preset rule is specifically: obtaining the midpoint coordinates of the lower cone bone data ; and determine the maximum value in the x-axis and y-axis directions and minimum value , a preset number of data points are selected to meet the following constraints: x-axis direction: point[x]≥ ,point[x]≤ ; Y-axis direction: point[y]≥ ,point[y]≤ ; z-axis direction: point[z]< ; The second preset rule is specifically: obtaining the midpoint coordinates of the upper cone bone data ; And determine the maximum value in the x-axis and y-axis directions and minimum value , a preset number of data points are selected to meet the following constraints: x-axis direction: point[x]≥ ,point[x]≤ ; Y-axis direction: point[y]≥ ,point[y]≤ ; z-axis direction: point[z]> ; The normal vectors of the first plane and the second plane are calculated respectively, and based on the two plane normal vectors, the angle between the first plane and the second plane is calculated to realize the calculation of the Cobb angle.

6. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the interactive measurement method of the Cobb angle of a three-dimensional spine model as described in claim 5 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, an interactive measurement method of the Cobb angle of a three-dimensional spine model as described in claim 5 is implemented.

Images