KR102357001B1 - Scoliosis Diagnosis Method and System using 3D Depth Camera - Google Patents

Abstract

According to the present invention, the processor acquires an image of a body to be examined for diagnosing a spinal deformity, extracting a plurality of feature points from the image of the body to be examined using an image processing algorithm, the key points calculating the surface height information by measuring the relative height between points of the evacuated body using distance information between the Disclosed are a scoliosis diagnosis method and a scoliosis diagnosis system using a 3D depth camera for inferring a structure of the spine of a body to be examined, including the steps of:

Description

Scoliosis Diagnosis Method and System using 3D Depth Camera}

The present invention relates to a scoliosis diagnosis method, and more particularly, to a scoliosis diagnosis method and a scoliosis diagnosis system using a 3D depth camera.

The spine is analyzed as a three-dimensional structure of the sagittal, coronal, and coronal surfaces. In particular, the sagittal and coronal plane alignment and the pelvic/vertebral relationship are important.

When performing whole-body sagittal and coronal X-rays, accurate analysis is possible, but it takes a lot of time to analyze, and there are limitations, so it is only used for patients with actual discomfort.

Accordingly, there is a need for a technology capable of inferring the spine structure of a patient without using X-rays using imaging technology and computer technology.

The present invention provides a method for diagnosing a scoliosis using a 3D depth camera and a system for diagnosing a scoliosis, in which a processor acquires an image of a cortex for diagnosing a spinal deformity; extracting a plurality of feature points from an image using an image processing algorithm; calculating surface height information by measuring a relative height between one point of the body to be examined using distance information between the feature points to calculate surface height information; and the surface height information The purpose of the present invention is to infer the structure of the vertebral body of the evacuated body using

In addition, another purpose is to find out the positions of the vertebrae, tailbone, and femur head, which are necessary for checking the balance of the spine but are difficult to understand with a 3D depth camera.

Other objects not specified in the present invention may be additionally considered within the scope that can be easily inferred from the following detailed description and effects thereof.

In order to solve the above problems, a method for diagnosing a scoliosis using a three-dimensional depth camera according to an embodiment of the present invention includes the steps of: acquiring, by a processor, an image obtained by photographing a body to be diagnosed with spinal deformity; extracting a plurality of feature points using an image processing algorithm from an image taken of and modeling the vertebral structure of the evacuated body by using surface height information and analyzing the degree of deformation of the vertebrae.

Here, the step of acquiring the image of the body to be evacuated includes acquiring images of the front, side, and back of the body to be evacuated.

Here, the characteristic points include a position of both shoulder joints, a nose position, an ear position, and a pelvic joint position on both sides of the evacuated body.

Here, the shoulder joint positions and the pelvic joint positions of the body to be examined are positions identified as center points of movement when the object to be tested moves its arms and legs in a standing state.

Here, the step of extracting a plurality of feature points using the image processing algorithm includes calculating 3D depth map data using the image taken of the body to be examined, and the distance to the object to be diagnosed from the depth map data. Comparing the distance to the reference background image to detect the outline of the object to be diagnosed, extracting first feature points from the detected outline of the object to be diagnosed, and the distance information to the object to be tested identified from the depth map data for each and extracting second feature points from the surface of the body to be examined.

Here, the step of calculating the surface height information by measuring the relative heights between points of the body to be tested includes generating an orthogonal line forming a virtual surface based on the outline of the body to be tested and setting the intersection points of the orthogonal lines as reference coordinates. setting the plurality of extracted feature points as relative coordinates, calculating a distance between one point of the body to be examined using the relative coordinates, and comparing the position with the reference coordinates adjacent to the relative coordinates to obtain the reference and calculating the distance and angle with respect to the coordinates as the surface height information.

Here, the step of modeling the spine structure of the body to be examined using the surface height information and analyzing the degree of deformation of the spine includes: estimating a rotation radius on a horizontal plane of the spine of the body covered by using the surface height information; Modeling the spinal structure by synthesizing the information including the rotation radius information, the shoulder joint position difference on both sides of the shoulder, the position difference of the pelvic joints on both sides, and the degree of movement of the central axis, and analyzing the degree of deformation of the spine based on the modeled vertebral structure including the steps of

Here, in the step of modeling the spine structure of the body to be examined and analyzing the degree of deformation of the spine by using the surface height information, the degree of deformation is analyzed by dividing the cervical thoracic and lumbar portions of the spine of the body to be examined.

Here, the step of analyzing the degree of deformation of the spine based on the modeled vertebral structure comprises: using information including the rotation radius information, the position difference of both shoulder joints, and the position difference of both pelvic joints in the modeled vertebral structure. Check the direction of occurrence of the scoliosis strain.

Here, the step of analyzing the degree of deformation of the spine based on the modeled vertebral structure comprises determining the boundary between the cervical thoracic and lumbar vertebrae of the spine, and determining the direction and curvature of the spine from the difference in the position of the pelvic joints on both sides, The curve between the center of the pelvic joint and the center of the thoracolumbar border is estimated through the angle.

Here, in the step of analyzing the degree of deformation of the spine based on the modeled spine structure, the curvature of the thoracic spine is checked using the thoracolumbar boundary and the center point of both shoulder joints, and the degree of inflection is determined in consideration of the rotation radius.

Here, to distinguish the cervical thoracic and lumbar parts of the spine of the body covered, the height at the total height of the body covered is measured by measuring the inflection point of the lumbar vertebrae and separating the cervical thoracic and lumbar parts.

A scoliosis diagnosis system using a three-dimensional depth camera according to an embodiment of the present invention includes an image capturing unit that captures an evacuated body for diagnosing a spinal deformity, and a spinal deformity of the evacuated body from an image captured by the evacuated body. A method comprising: a processor for performing a diagnosis method, wherein the processor includes: acquiring an image of an evacuated body for diagnosing a spinal deformity; extracting, calculating the surface height information by measuring the relative height between points of the body under investigation by using the distance information between the feature points, and modeling the spine structure of the body covered by using the surface height information, Perform the steps of analyzing the degree of deformation of the spine.

Here, the image capturing unit includes a 3D depth camera, and the processor acquires images obtained by photographing the front, side, and rear surfaces of the body to be examined.

Here, the characteristic points include a position of both shoulder joints, a nose position, an ear position, and a pelvic joint position on both sides of the evacuated body.

As described above, according to the embodiments of the present invention, the processor includes the steps of: acquiring, by the processor, an image obtained by photographing the body to be diagnosed; extracting feature points, calculating the surface height information by measuring the relative height between points of the body to be examined using distance information between the feature points, and calculating the spine structure of the body to be examined using the surface height information Including modeling and analyzing the degree of deformation of the spine, the structure of the spine of the subcutaneous tissue can be inferred.

In addition, it is possible to find out the positions of the vertebrae, the tailbone, and the head of the femur, which are necessary for checking the balance of the spine but are difficult to understand with an actual 3D depth camera.

Even if it is an effect not explicitly mentioned herein, the effects described in the following specification expected by the technical features of the present invention and their potential effects are treated as if they were described in the specification of the present invention.

1 is a block diagram of a scoliosis diagnosis system according to an embodiment of the present invention.
2 to 5 are flowcharts for explaining a scoliosis diagnosis method according to an embodiment of the present invention.
FIG. 6 is a diagram illustrating, as an example, imaging of a cortex of a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.
7 to 10 are diagrams illustrating a process of extracting feature points of a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.
11 is a diagram illustrating a process of calculating surface height information of a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention as an example.
12 to 15 are diagrams illustrating, as an example, a process of analyzing the degree of deformation of the spine of the scoliosis diagnosis method and the scoliosis diagnosis system according to an embodiment of the present invention.

Hereinafter, a scoliosis diagnosis method and a scoliosis diagnosis system using a three-dimensional depth camera according to the present invention will be described in more detail with reference to the drawings. However, the present invention may be embodied in various different forms, and is not limited to the described embodiments. In addition, in order to clearly explain the present invention, parts irrelevant to the description are omitted, and the same reference numerals in the drawings indicate the same members.

The suffixes "module" and "part" for components used in the following description are given or mixed in consideration of only the ease of writing the specification, and do not have distinct meanings or roles by themselves.

The present invention relates to a scoliosis diagnosis method and a scoliosis diagnosis system using a three-dimensional depth camera.

1 is a block diagram of a scoliosis diagnosis system according to an embodiment of the present invention.

Referring to FIG. 1 , a scoliosis diagnosis system 1 according to an embodiment of the present invention includes a processor 10 , an image capturing unit 20 , a memory 30 , and an I/O interface 40 .

The scoliosis diagnosis system 1 according to an embodiment of the present invention uses a 3D camera to measure the surface anatomical structure and height of an evacuated body, and models the spinal structure using images taken of the front, side, and back of the cortex. and it is a system that suggests the degree of deformation.

Important values in spinal alignment analysis (SVA to see sagittal alignment, C7-plumb line, T1 tilt, degree of knee flexion, tilting of the pelvis, anterior/kyphosis, shoulder height, pelvic misalignment, left-right alignment, scoliosis , Q-angle, etc.) is performed on a 3D-camera based postural analysis machine to accurately estimate the patient's body line.

The spine is analyzed as a three-dimensional structure of the sagittal, coronal, and coronal surfaces. In particular, the sagittal and coronal plane alignment and the pelvic/vertebral relationship are important. When performing whole-body sagittal and coronal X-rays, accurate analysis is possible, but it takes a lot of time to analyze, and there are limitations, so it is only used for patients with actual discomfort.

The scoliosis diagnosis system 1 according to an embodiment of the present invention has the advantage of inferring the structure of a patient's spine without using X-rays using imaging technology and computer technology.

The image capturing unit 20 captures an object to be diagnosed with a spinal deformity, and the processor 10 performs a method of diagnosing the deformation of the spine of the object to be diagnosed from the image captured by the image capturing unit.

The processor 10 may be divided into a plurality of modules according to functions, and functions may be performed by one processor.

The processor 10 may perform the steps of: obtaining an image of a body to be diagnosed for diagnosing a spinal deformity; The steps of calculating the surface height information by measuring the relative height between the points of the evacuated body using distance information, and modeling the spine structure of the evacuated body using the surface height information and analyzing the degree of deformation of the spine carry out

Here, the feature points include a position of both shoulder joints, a nose position, an ear position, and a position of both pelvic joints of the evacuated body.

In the scoliosis diagnosis system 1 according to an embodiment of the present invention, the image capturing unit includes a 3D depth camera, and the processor captures images of the front, side, and rear surfaces of the body to be examined. acquire

A 3D depth camera may calculate a depth value of each pixel of an image.

Unlike the 2D method, which was processed with only one camera module, 2 camera modules are used to calculate the pixel depth using various techniques to display a 3D image.

The memory 30 may store programs (one or more instructions) for processing and controlling the processor 10 .

The I/O interface 40 is a device capable of mounting a connection medium capable of connecting a system or equipment, and in the present invention, an image capturing unit and a processor are connected.

The scoliosis diagnosis system 1 according to an embodiment of the present invention uses a method for determining spinal deformity using a 3D depth camera, and uses a 3D camera at a predetermined distance to recognize a curvature of the spine. to acquire an image, and extract feature points from the acquired image based on an image processing algorithm.

Here, the characteristic point means the height of both shoulders, the nose position, the ear position, the center point of both sides of the pelvis, and the like. After going through the process of measuring the relative height using the distance information of these parts, the three-dimensional deformation degree of the spine is presented through data analysis using the data of the feature points.

After that, the data obtained through measurement is compared with standard data using existing data, and the degree of deformation is transmitted to the application system and informed to the subject.

The method of deforming the spine will be described in detail with reference to FIGS. 2 to 5 below.

2 to 5 are flowcharts illustrating a scoliosis diagnosis method according to an embodiment of the present invention.

Referring to FIG. 2 , the method for diagnosing scoliosis according to an embodiment of the present invention starts in step S100 in which the processor acquires an image of a body to be examined for diagnosing spinal deformity.

In the step of acquiring an image of the body to be covered, images obtained by photographing the front, side, and rear of the body to be covered are obtained.

As shown in FIG. 6, the patient is placed at a specific distance from the 3D camera, and the front, side, and back are measured.

In step S200, a plurality of feature points are extracted from the image captured by the diagnosed body by using an image processing algorithm.

Here, the characteristic points include a position of both shoulder joints, a nose position, an ear position, and a position of both pelvic joints of the body to be examined, and the positions of both shoulder joints and pelvic joints of the body to be examined are: and a position identified as a center point of movement when the leg is moved.

In step S300, the surface height information is calculated by measuring the relative height between the points of the body to be tested using the distance information between the feature points.

In step S400, the spine structure of the evacuated body is modeled using the surface height information and the degree of deformation of the spine is analyzed.

Referring to FIG. 3 , in the method for diagnosing scoliosis according to an embodiment of the present invention, the step of extracting a plurality of feature points using an image processing algorithm (S200) is performed using the image captured by the body to be examined in step S210. Compute the 3D depth map data.

According to the present invention, a group to be evacuated is photographed using a three-dimensional depth camera. A 3D depth camera may calculate a depth value of each pixel of an image.

Unlike the 2D method, which was processed with only one camera module, 2 camera modules are used to calculate the pixel depth using various techniques to display a 3D image.

In the step of calculating the 3D depth map data using the image captured by the present invention, the evacuated body is recognized based on 3D depth map data obtained using two cameras, and feature points are extracted. will do

Depth map data in 3D space means a distance to a subject in 3D space.

Using a 3D camera, two types of information can be obtained, and as shown in FIG. 7 below, the outside of the subject can be identified using the difference between the background and the patient, and between the camera and the subject's surface as shown in FIG. 8 below distance information can be obtained.

In step S220, the distance to the body to be tested and the distance to the reference background image checked from the depth map data are compared to detect the outline of the body to be tested.

The distance to the reference background image and other data are judged as the subject, and outline detection is performed. Edge detection is processed using various types of edges according to the shape of the boundary line of the object.

First feature points are extracted from the outline of the body to be diagnosed in step S230.

In step S240, second feature points are extracted from the surface of the body to be tested for each distance information from the depth map data to the body to be tested.

Using these two pieces of information, it is possible to obtain information on the height of a surface such as a patient through an image processing algorithm.

Referring to FIG. 4 , in the method for diagnosing scoliosis according to an embodiment of the present invention, the step of calculating surface height information by measuring the relative heights between points of the body covered (S300) is, in step S310, the outline of the body of the body covered. An orthogonal line forming a virtual surface is generated based on , and intersection points of the orthogonal line are set as reference coordinates.

The plurality of feature points extracted in step S320 are set as relative coordinates.

In step S330, the distance between one point of the body to be tested is calculated using the relative coordinates, and the distance and angle with the reference coordinates are calculated as the surface height information by comparing the position with the reference coordinates adjacent to the relative coordinates. do.

Referring to FIG. 5 , in the method for diagnosing scoliosis according to an embodiment of the present invention, the step (S400) of modeling the structure of the vertebral body of the evacuated body and analyzing the degree of deformation of the spine using surface height information (S410) Using the surface height information, the radius of rotation on the horizontal plane of the spine of the evacuated body is estimated.

In step S420, the spinal structure is modeled by synthesizing the information including the rotation radius information, the position difference between the shoulder and shoulder joints, the position difference between the pelvic joints, and the degree of movement of the central axis.

In step S430, the degree of deformation of the spine is analyzed based on the modeled spine structure.

In the step (S400) of modeling the structure of the spine of the body covered by the surface height information and analyzing the degree of deformation of the spine, the degree of deformation is analyzed by dividing the cervical thoracic and lumbar sections of the spine of the body covered.

Here, to distinguish the cervical thoracic and lumbar vertebrae of the vertebra of the body covered, the height at the total height of the body covered is measured as a reference for separating the cervical thoracic and lumbar vertebrae by measuring the inflection point of the lumbar vertebrae.

The step of analyzing the degree of deformation of the spine based on the modeled spinal structure (S430) is performed by using information including the rotation radius information, the position difference of both shoulder joints, and the position difference of both pelvic joints in the modeled spinal structure. Check the direction of occurrence of scoliosis of the spine, check the boundary between the cervical thoracic and lumbar vertebrae of the spine, determine the direction and curvature of the spine from the difference in the position of the pelvic joints on both sides, Estimate the curve between the angles.

In addition, the curvature of the thoracic spine is checked using the thoracolumbar border and the center point of both shoulder joints, and the degree of inflection is determined by considering the radius of rotation.

6 is a diagram illustrating, as an example, imaging of a cortex of a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.

In the scoliosis diagnosis system 1 according to an embodiment of the present invention, the sensor unit 21 includes a 3D depth camera, and the processor includes the front, side, and rear surfaces of the body 2 to be examined. Acquire an image of the

A 3D depth camera may calculate a depth value of each pixel of an image.

Unlike the 2D method, which was processed with only one camera module, 2 camera modules are used to calculate the pixel depth using various techniques to display a 3D image.

In the step of calculating the 3D depth map data using the image captured by the present invention, the evacuated body is recognized based on 3D depth map data obtained using two cameras, and feature points are extracted. will do

Depth map in 3D space means the distance to the subject in 3D space. Depth information uses a method using a stereo camera, a method using a laser scan, a method using a TOF (Time of Flight), etc. can be obtained by

Stereo matching using a stereo camera is a method of extracting information on depth (or distance) in space through an analysis process for a pair of images obtained by photographing the same subject with two cameras. To this end, the binocular difference on the same epipolar line of the images obtained from the two cameras is calculated. The binocular disparity includes distance information, and a geometrical characteristic calculated from the binocular disparity becomes a depth. By calculating the binocular difference value in real time from the input image, it is possible to measure the three-dimensional distance information in the observation space.

Position the patient at a certain distance from the 3D camera and measure the front/side/back. Using a 3D camera, you can obtain two types of information.

According to various embodiments, the sensor unit 21 may use a gyroscope, an acceleration sensor, and a position tracking sensor, and use the contact probe 22 to measure scoliosis more accurately.

The contact probe has a built-in gyroscope sensor and an acceleration sensor to estimate the probe's speed and direction within the 3D structure.

A position sensor that can grasp the position of the contact probe in three dimensions is used. For example, it is possible to check which position the probe is currently passing by, for example, by emitting infrared rays from the probe and detecting the position to determine the position. That is, the contact probe has 6 degrees of freedom.

Attach a sticker to the starting position (C7 spinous process) and ending position (l4 spinous process, PSIS center) of the probe and use it as a reference point. The probe is drawn along the spinous process of the spine between the starting point and the end point, as if drawn with a pen, measured with a sensor, and the degree of curvature of the spine is estimated. .

7 to 10 are diagrams illustrating a process of extracting feature points of a scoliosis diagnosis method and a scoliosis diagnosis system according to an exemplary embodiment of the present invention.

Using a 3D camera, two types of information can be obtained, and as shown in FIG. 7 below, the outside of the subject can be identified using the difference between the background and the patient, and between the camera and the subject's surface as shown in FIG. 8 below distance information can be obtained.

7 is a diagram illustrating, as an example, detecting an outline of a body to be examined in a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.

Referring to (a) of FIG. 7 , an outline of the body to be diagnosed is detected by comparing the distance to the body to be examined from the depth map data and the distance to the reference background image.

Specifically, the reference background image 222 is determined using certain data among the depth map data, and the subject area 221 is distinguished using the constant data and the data determined by the distance at which the object is located.

Thereafter, the outline 223 of the moving target body is detected by performing outline detection through an object extraction process.

Thereafter, first feature points are extracted from the detected outline of the body to be diagnosed.

Here, the first feature points are the center point of the crown 224, the center point of both ears 225, the center point of the shoulder joint 226, the center point of the pelvis joint 227, the center point of the ankle joint 228, the center point of both ears 225, the center point of the nose ( 229), and each body point of the evacuated body located on the outline may be extracted by distinguishing it for each depth map data.

Here, the shoulder joint center point, the pelvic joint center point, and the knee joint center point can be clearly identified by using the principle of the lever in FIG.

In addition, the center point of the crown 224, the center point of both ears 225, and the center point of the nose 229 can determine the axis of the body to easily grasp the degree of deformation of the spine.

As shown in (b) of FIG. 7 , the scoliosis diagnosis method according to an embodiment of the present invention measures the deformation by separating the cervical thoracic and lumbar vertebrae (D1).

FIG. 8 is a diagram illustrating the detection of the surface of the body to be examined in the scoliosis diagnosis method and the scoliosis diagnosis system according to an embodiment of the present invention as an example.

Second feature points are extracted from the surface of the body to be tested for each distance information from the depth map data to the body to be tested.

The first feature point is extracted based on the outline, and the second feature point is extracted for each distance information from the surface of the body to be evacuated.

Referring to FIG. 8A , by measuring depth data for each coordinate of each surface, coordinate information 211 and data information 212 may be checked on the surface of the body to be tested.

In each coordinate information, a part serving as a main axis, such as a center point of the crown, a shoulder joint, and a pelvic joint 213, may be denoted as +, and a plurality of characteristic points may be denoted by a dot.

Accordingly, it is possible to visually grasp the displacement of the posture on the surface of the body.

In (a) of FIG. 8 , it can be confirmed that the target object is positioned at an angle, and the feature points are asymmetrically positioned.

Fig. 8 (b) shows each characteristic point when the axis of the body is aligned in a standing state of the subject. The joint position 244 may be indicated.

In the present invention, since it is necessary to determine the spinal deformity in a state in which the axes of the body are aligned, the spinal deformity is analyzed in detail with an image in a state in which the feature points are aligned as shown in FIG. 8( b ).

Thereafter, surface height information is calculated by setting a plurality of feature points as relative coordinates and measuring the relative heights between points of the body to be tested, which will be described in detail with reference to FIG. 11 below.

9 is a view showing the confirmation of the position of the shoulder joint and the pelvic joint on both sides of the evacuated body.

A number of feature points are extracted from the image of the evacuated body by using an image processing algorithm.

Here, the feature points include the position of both shoulder joints 251, the nose position, the ear position, and the bilateral pelvic joint positions 252 of the group to be covered. When a group moves its arms and legs in a standing state, it is a position identified as the center of movement.

According to the present invention, the subject moves arms and legs while standing still, and through this, the center point of the shoulder joint/hip joint can be identified.

In the case of the shoulder and hip joint, it is configured like a lever, and for example, the shoulder joint becomes the fulcrum and the arm moves as a lever.

As shown in Fig. 9, when the arm is moved up and down, the center point (support point) of the shoulder joint can be grasped through the position of the arm (leverage), and in the same principle, the coronal plane and the sagittal plane If you take a picture, you can figure out the position of the center point in 3D, and through this, you can figure out the positions of a total of four places on both sides of the shoulder joint and the pelvis joint.

In addition, the knee center point 253 may be identified through the movement of bending the knee. Here, the point most protruding when bending the knee is identified as the knee center point. In addition, additional reference points are checked using a 3d depth camera. Additional reference points The feature points are as shown in FIGS. 7 and 8 .

Points that must be known in order to check the balance of the spine by identifying the positions of the shoulder joint and the pelvic joint in a total of 4 places, but difficult to know with a real 3d depth camera (xyz coordinates of the 7th vertebra position, the xyz axis coordinates of the 1st tailbone position) , the xyz coordinates of the femur head, the degree of tilting of the pelvis, etc.) can be found.

Through the present invention, x-ray imaging can be substituted for measurement of spine and musculoskeletal misalignment by using an algorithm that takes important markers in sagittal balance.

Fig. 10 shows an example of acquiring the position of the shoulder joint and the position of the pelvis joint on both sides of the evacuated body.

According to the present invention, as shown in FIG. 10 , a total of four locations on both sides of the shoulder joint and the pelvic joint can be identified, and additional reference points are checked using a 3d depth camera.

Here, P1, P2 are shoulder joint center points (right/left), P3, P4 are hip joint center points (right/left), P5, P6 are knee joint center points (right/left), P7, P8 are foot center points, and P9 is Auricular canal, P10 is the shoulder joint center point (sagittal plane), P11 is the hip joint center point (sagittal plane), P12 is the knee joint center point (sagittal plane), P13 is the ankle joint center point (sagittal plane), P14, P14', P15 are The location of the ASIS marker.

Thereafter, the relative height between points of the evacuated body is measured. Specifically, the difference in shoulder height is checked by comparing the heights of P1 and P2, and the height of the pelvis is confirmed by comparing the heights of P3 and P4.

In addition, the left and right deflection of the spine is checked by comparing the center points of P1 and P2 and the center points of P3 and P4, the degree of spine bending is confirmed using the position difference between P10 and P11, and turtle neck syndrome using the position difference between P9 and P10. check

Also, check the degree of knee flexion using the P11-P12/P12-P13 angle, and check the degree of distortion of the pelvis using the P14 and P14' markers.

In addition, the Q-angle is checked using P3-P5-P7 and P4-P6-P8, and the pelvis up and down is checked using the difference between the height of the P14-P14' marker and the height of P3/P4.

11 is a diagram illustrating a process of calculating surface height information of a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention as an example.

11 illustrates a method of obtaining height information of the back surface with respect to the left shoulder using surface information from a camera as an example.

In the scoliosis diagnosis method according to an embodiment of the present invention, the step (S300) of calculating the surface height information by measuring the relative height between points of the body to be examined is a virtual surface based on the outline of the body to be examined in step S310. Orthogonal lines 311 and 312 are generated, and intersections of the orthogonal lines are set as reference coordinates 313 .

Here, the reference coordinates are coordinates set based on the body type of the body to be tested and when the spine is correctly positioned.

The plurality of feature points extracted in step S320 are set as relative coordinates. The relative coordinates set based on the depth map data should ideally match the reference coordinate values. However, if the spine is deformed, it is not symmetrical with respect to the baseline, and the positions of the reference coordinates and the relative coordinates are misaligned. Using this, surface height information is calculated.

For example, in the case of FIG. 11 , it can be seen that the shoulder joint 321 is located on the orthogonal line, but the pelvic joint 323 is not located on the orthogonal line. Also, it may be determined that the position 322 of the ear is not symmetrical with respect to the central point.

In step S330, the distance between one point of the body to be tested is calculated by using the relative coordinates, and the distance and angle with the reference coordinates are calculated as the surface height information by comparing the position with the reference coordinates adjacent to the relative coordinates. do.

Here, the position with the reference coordinates adjacent to the relative coordinates is primarily measured as the distance between the two coordinates in the rectangular coordinate system, and in order to determine the distance from the spine, the distance measured with the spine as the origin on the spherical coordinate system and the positive The angle formed in the direction is calculated as surface height information.

12 to 15 are diagrams illustrating, as an example, a process of analyzing the degree of deformation of the spine of the scoliosis diagnosis method and the scoliosis diagnosis system according to an embodiment of the present invention.

Referring to (a) of FIG. 12 , the deformation of the spine is a three-dimensional process, and the rotation of the spine in the cross section has a great influence on scoliosis. At this time, the rotation of the spine also affects the positions (A1, A2, A3) of the ribs and shoulder blades, which are structures attached to the spine. can be estimated

As shown in (b) of FIG. 12 , when the relative heights of the grids are compared, the angle of rotation in the coronal plane is estimated using the height difference between the left and right and the gap from the center in the cross section of the arrow with severe scoliosis.

13 is a diagram illustrating a method for diagnosing a scoliosis and estimating a radius of gyration in a scoliosis diagnosis system according to an embodiment of the present invention.

In (a) of FIG. 13 , the rotation radius is estimated by obtaining the angle 332 from the alignment axis 331 of the spine of the relative coordinates.

As shown in Fig. 13 (a), the patient's spine estimates axial rotation (radius of rotation on the horizontal plane) through surface height information, and information such as shoulder height, pelvis height, and central axis movement degree is synthesized with this information. This allows you to check how severe the deformity of the spine is.

As shown in (b) of FIG. 13 , the degree of axial rotation of the spine can be analyzed through surface height information.

Since the radius of rotation means the distance between two points when one point rotates around another point, the rotation radius of each part of the spine is measured to determine that the spine is deformed when it is not constant.

14 is a diagram illustrating, as an example, measurement of spinal deformity (scoliosis) in a coronal plane in a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.

14 is for explaining the modeling of the spinal structure by synthesizing information including the rotation radius information, the position difference between the shoulder and shoulder joints, the position difference between the pelvic joints on both sides, and the degree of movement of the central axis.

In the state as shown in (a) of Figure 14, first, as shown in Figure 14 (b) using the difference between the pelvic height and the shoulder height and the patient's back surface height information, in which direction the scoliosis of the spine occurred Check it. Here, it can be seen that the shoulder height difference 431 occurs, the pelvic height 432 is constant, and the scoliosis deformity 433 of the spine occurs in the leftward curved direction.

As shown in FIG. 14(c), the cervical thoracic/lumbar border 436 is checked, the direction and curvature of the spine are determined from the pelvic height difference, and the center of the pelvic center - the center 438 of the thoracic-lumbar border. The curve of is estimated through the angle.

Check the thoracic curve 437 using the pelvis 435, the thoracolumbar boundary 436, and the shoulder center point 434, and determine the degree of inflection in consideration of axial rotation.

At this time, there are the following methods to separate the cervical thoracic and lumbar vertebrae.

The cervical thoracic/lumbar part separation method using sagittal plane information measures the inflection point of lumbar flexion in the sagittal plane, and measures the height in total height as a standard for separating the thoracic vertebrae and lumbar vertebrae.

Based on this height information, the thoracic/lumbar spine is also determined in the coronal plane.

In addition, the height at the center of the pelvis is estimated using the average data of the patients, and the average thoracolumbar inflection point is set in consideration of the height, age, and weight of the patients.

15 is a diagram illustrating, as an example, measurement of a sagittal spinal deformity in a scoliosis diagnosis method and a scoliosis diagnosis system according to an embodiment of the present invention.

Using the patient's surface information and central axis information in the sagittal plane, data such as posterior spine inclination and forward movement of the pelvis are obtained to secure kyphosis data.

Thereafter, by synthesizing the coronal and sagittal data, data on the three-dimensional deformation of the spine is obtained through an algorithm.

In summary, the center point of the left and right shoulder joints is measured through the movement of raising the arm from the front of the patient, and the center point of the left and right pelvis and the center of the knee are measured through the movement of lifting the leg from the front of the patient (step in place, etc.).

Thereafter, the center point of the ankle is measured by measuring the deepest point from the front using the 3D camera, and the ASIS position is measured using a 3D marker.

Measure the midpoint of the lateral shoulder, midpoint of the pelvis, midpoint of the knee, and midpoint of the ankle through the movement of raising the arm from the patient's side and lifting the leg (such as walking in place).

From the side, use the depth of the 3D camera to measure the center of the ear and check the ASIS position using a marker, and check the leg length difference, Q-angle, spine bending degree, turtle neck, knee flexion, and pelvic distortion by combining each position difference.

Using the probe for 6-DOF contact, estimate the spine curvature and build the spine model, build the patient posture model, and determine whether it is normal or not.

The above description is only one embodiment of the present invention, and those of ordinary skill in the art to which the present invention pertains will be able to implement in a modified form without departing from the essential characteristics of the present invention. Therefore, the scope of the present invention is not limited to the above-described embodiments, and should be construed to include various embodiments within the scope equivalent to the content described in the claims.

Claims (15)

obtaining, by the processor, an image obtained by photographing a cortical body for which a spinal deformity is to be measured;
extracting a plurality of feature points using an image processing algorithm from the image of the body to be evacuated;
calculating surface height information by measuring a relative height between points of the body to be tested using distance information between the feature points; and
Modeling the structure of the spine of the evacuated body by using the surface height information and analyzing the degree of deformation of the spine;
The step of extracting a plurality of feature points using the image processing algorithm may include: calculating 3D depth map data using the image captured by the body to be evacuated; detecting an outline of the body to be diagnosed by comparing the distance to the body to be examined from the depth map data and the distance to a reference background image; extracting first feature points from the detected outline of the body to be diagnosed; and extracting second feature points from the surface of the body to be tested for each distance information from the depth map data to the body to be diagnosed.
The step of calculating the surface height information by measuring the relative heights between points of the body to be tested includes generating an orthogonal line forming a virtual surface based on the outline of the body to be tested, and setting the intersection points of the orthogonal lines as reference coordinates. ; setting the plurality of extracted feature points as relative coordinates; and calculating the distance between the points of the body to be tested using the relative coordinates, comparing the position with the reference coordinates adjacent to the relative coordinates, and calculating the distance and angle with the reference coordinates as the surface height information. including;
The step of modeling the spine structure of the body to be evacuated by using the surface height information and analyzing the degree of deformation of the spine may include: estimating a rotation radius on a horizontal plane of the spine of the body covered by using the surface height information; modeling the spinal structure by synthesizing the information including the rotation radius information, the shoulder joint position difference, the bilateral pelvic joint position difference, and the degree of movement of the central axis; and analyzing the degree of deformation of the spine based on the modeled spinal structure. The method of claim 1,
The step of obtaining an image of the evacuated group includes:
Scoliosis measurement method, characterized in that the image obtained by photographing the front, side, and rear of the cortex. According to claim 1,
The characteristic points, scoliosis measurement method, characterized in that it includes the position of both shoulder joints, nose position, ear position and both sides of the pelvic joint position of the evacuated body. 4. The method of claim 3,
The shoulder joint position and the pelvic joint position of the evacuated body are,
The method for measuring a scoliosis, characterized in that the position is identified as a center point of movement when the subject moves an arm and a leg in a standing state. delete delete delete According to claim 1,
The step of modeling the structure of the spine of the evacuated body and analyzing the degree of deformation of the spine using the surface height information includes:
Scoliosis measurement method, characterized in that the degree of deformation is analyzed by dividing the cervical thoracic and lumbar vertebrae of the spine of the cortex. The method of claim 1,
The step of analyzing the degree of deformation of the spine based on the modeled spine structure comprises:
Scoliosis measurement method, characterized in that the generation direction of the scoliosis deformation of the spine is confirmed by using the information including the rotation radius information, the position difference of both shoulder joints, and the position difference of the pelvic joints in the modeled spinal structure. The method of claim 1,
The step of analyzing the degree of deformation of the spine based on the modeled spine structure comprises:
Checking the boundary between the cervical thoracic and lumbar vertebrae of the spine, determining the direction and curvature of the spine from the difference in the position of the pelvic joints on both sides, and estimating the curve between the center point of both pelvic joints and the center of the thoracolumbar boundary through the angle Characterized scoliosis measurement method. According to claim 1,
The step of analyzing the degree of deformation of the spine based on the modeled spine structure comprises:
A scoliosis measurement method, characterized in that the thoracic spine curve is checked using the thoracolumbar region and the center point of both shoulder joints, and the degree of inflection is determined by considering the radius of rotation. 9. The method of claim 8,
Distinguishing between the cervical thoracic and lumbar vertebrae of the spine of the cortex is,
A method for measuring a scoliosis, characterized in that by measuring an inflection point of lumbar flexion and measuring the height of the body under the diaphragm as a standard for separating the cervical thoracic vertebrae and the lumbar vertebrae. an image capturing unit for photographing a cortical body to measure spinal deformity; and
a processor for performing a method of measuring a spinal deformity of the body covered by the image captured by the body;
The processor may include: acquiring an image of a body to be diagnosed for diagnosing a spinal deformity; extracting a plurality of feature points from the image of the body to be diagnosed; Calculating surface height information by measuring the relative height between points of the body covered by using ,
The step of extracting a plurality of feature points using the image processing algorithm may include: calculating 3D depth map data using the image captured by the body to be evacuated; detecting an outline of the body to be diagnosed by comparing the distance to the body to be examined from the depth map data and the distance to a reference background image; extracting first feature points from the detected outline of the body to be diagnosed; and extracting second feature points from the surface of the body to be tested for each distance information from the depth map data to the body to be diagnosed.
The step of calculating the surface height information by measuring the relative heights between points of the body to be tested includes generating an orthogonal line forming a virtual surface based on the outline of the body to be tested, and setting the intersection points of the orthogonal lines as reference coordinates. ; setting the plurality of extracted feature points as relative coordinates; and calculating the distance between the points of the body to be tested using the relative coordinates, comparing the position with the reference coordinates adjacent to the relative coordinates, and calculating the distance and angle with the reference coordinates as the surface height information. including;
The step of modeling the spine structure of the body to be evacuated by using the surface height information and analyzing the degree of deformation of the spine may include: estimating a rotation radius on a horizontal plane of the spine of the body covered by using the surface height information; modeling the spinal structure by synthesizing the information including the rotation radius information, the shoulder joint position difference, the bilateral pelvic joint position difference, and the degree of movement of the central axis; and analyzing the degree of deformation of the spine based on the modeled spinal structure. 14. The method of claim 13,
The image capturing unit includes a 3D depth camera,
The processor, scoliosis measurement system, characterized in that to acquire the image of the front, side, and rear of the body to be examined. 14. The method of claim 13,
The feature points, scoliosis measurement system, characterized in that it includes the position of both shoulder joints, nose position, ear position and both sides of the pelvic joint position of the cortex.

Images