CN114224322B - Scoliosis assessment method based on key points of human bones - Google Patents
Scoliosis assessment method based on key points of human bones Download PDFInfo
- Publication number
- CN114224322B CN114224322B CN202111240365.8A CN202111240365A CN114224322B CN 114224322 B CN114224322 B CN 114224322B CN 202111240365 A CN202111240365 A CN 202111240365A CN 114224322 B CN114224322 B CN 114224322B
- Authority
- CN
- China
- Prior art keywords
- hip
- neck
- key points
- scoliosis
- midpoint
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1071—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring angles, e.g. using goniometers
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
- A61B5/4538—Evaluating a particular part of the muscoloskeletal system or a particular medical condition
- A61B5/4561—Evaluating static posture, e.g. undesirable back curvature
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a scoliosis assessment method based on skeleton key points of a human body, which is characterized in that 25 skeleton key points which are symmetrically distributed are extracted from a front view and a side view of the human body, based on the skeleton key points, front neutral bit lines and side neutral bit lines of the human body, triangles where neck, shoulders and hips are located are calculated, and assessment of the scoliosis of the human body is completed according to the deviation condition of the skeleton key points relative to the front neutral bit lines and the side neutral bit lines and the inclination state of each triangle. The invention can rapidly complete the evaluation of the scoliosis of the human body, can be applied to the scoliosis screening work of the masses, is beneficial to the early discovery, early diagnosis and early treatment of the scoliosis, and has important significance for the whole society and the health of the whole people.
Description
Technical Field
The invention relates to the technical field of intelligent recognition, in particular to a scoliosis assessment method based on key points of human bones.
Background
Scoliosis is a complex three-dimensional (3D) deformity of the spine characterized by lateral curvature and axial vertebral body rotation (AVR), from which the spine may move or rotate to other anatomical planes. Along with the popularization of electronic equipment and the increase of sedentary time of people, scoliosis with different degrees appears in children, teenagers and adults frequently, slight scoliosis can be recovered to be normal through long-term exercise rehabilitation, and severe surgery is needed, but both slight and severe scoliosis screening and evaluation are needed before treatment, and accurate and rapid scoliosis evaluation has important significance for correcting scoliosis.
At present, a manual evaluation method is still adopted for screening scoliosis, and the defects of low efficiency, strong subjectivity and high cost exist; the professional scoliosis evaluation can be performed in a hospital or a professional institution by a method for calculating the Cobb angle by shooting an x-ray film, and has the defects of high equipment price, complex flow and the like.
Disclosure of Invention
The invention provides a scoliosis assessment method based on key points of human bones, which solves the problems of low efficiency, strong subjectivity, high cost and the like of the traditional manual scoliosis assessment method.
The invention can be realized by the following technical scheme:
a scoliosis assessment method based on skeleton key points of a human body extracts 25 skeleton key points which are symmetrically distributed from a front face diagram and a side face diagram of the human body, calculates front neutral bit lines and side face neutral bit lines of the human body and triangles where neck, shoulders and hips are located based on the skeleton key points, and completes assessment of scoliosis of the human body according to the deviation condition of the skeleton key points relative to the front neutral bit lines and the side face neutral bit lines and the inclination states of the triangles.
Further, the 25 skeletal key points are respectively set to 0 nose, 1 neck, 2 right shoulder, 3 right elbow, 4 right wrist, 5 left shoulder, 6 left elbow, 7 left wrist, 8 hip center, 9 right hip, 10 right knee, 11 right ankle, 12 left hip, 13 left knee, 14 left ankle, 15 right eye, 16 left eye, 17 right ear, 18 left ear, 19 left big toe, 20 left little toe, 21 left heel, 22 right big toe, 23 right little toe, 24 right heel,
fitting the center of 0 nose, 1 neck, 8 buttocks and the center of 15 right eye and 16 left eye, the center of 17 right ear and 18 left ear, the center of 2 right shoulder and 5 left shoulder, the center of 9 right hip and 12 left hip, the center of 10 right knee and 13 left knee, the center of 11 right ankle and 14 left ankle in the key points of the bones to establish a front neutral bit line;
fitting 1 neck, 8 hip center, 13 left knee and 14 left ankle in the key points of the skeleton to establish a side neutral bit line;
the triangle of neck is by 0 nose, 1 neck and 18 left ears are constituteed, and the triangle of shoulder is by 1 neck, 8 buttocks and 5 left shoulders are constituteed, and the triangle of hip is by 1 neck, 8 buttocks and 12 left hips are constituteed.
Further, the degree of offset in the neutral position of the spine is estimated using the root mean square error RMSE using the following equation,
wherein y is i Representing 0 nose, 1 neck, 8 hip center, 15 right eye and 16 left eye midpoint, 17 right ear and 18 left ear midpoint, 2 right shoulder and 5 left shoulder midpoint, 9 right hip and 12 left hip midpoint, 10 right knee and 13 left knee midpoint, 11 right ankle and 14 left ankle midpoint, or 1 neck, 8 hip center, 13 left knee, 14 left ankle;
using the equation |theta i -90 ° | assessing the degree of offset of spinal levelness, wherein θ 1 Angle value of 18 left ear 0 nose 1 neck in triangle where neck is located, theta 2 The angle value of the angle 5 in the triangle where the shoulders are located and the angle 1 in the left shoulder, the neck and the angle 8 in the hip are shown, theta 3 The angle value of the left hip of the hip 12 of the neck 8 is 1 in the triangle where the hip is located.
Further, the front neutral bit line and the side neutral bit line are obtained by fitting by a least squares method, and 25 skeleton key points are extracted from a front view and a side view of a human body by using an OpenPose algorithm.
Further, when the front view and the side view of the human body are collected, the feet of the tester are separated, the interval is the same as the shoulder, the arms naturally droop, and eyes look in front.
The beneficial technical effects of the invention are as follows:
(1) The scoliosis screening and evaluating method based on the key points of the human bones can be used for early screening and evaluating the health condition of the spine of the public group, so that early discovery and early rehabilitation treatment can be realized.
(2) The scoliosis screening and evaluating method based on the key points of the human bones has the advantages of low cost and simple operation, and can collect pictures in real time for evaluation, and only one front view and one side view of the human body are required to be obtained when the pictures are collected.
(3) According to the invention, the OpenPose human skeleton key point extraction technology is combined with the artificial visual scoliosis assessment method, a scoliosis screening assessment algorithm based on human skeleton key points is provided, the scoliosis screening assessment efficiency can be greatly improved, and only 30 seconds are required for an average person to assess.
(4) The invention can obtain the detection result by inputting the front view and the side view into the algorithm by self-shooting without professional operation, thereby being beneficial to popularization and popularization of the method.
Drawings
FIG. 1 is a schematic illustration of a prior art scoliosis type of the present invention;
FIG. 2 is a schematic general flow diagram of the present invention;
FIG. 3 is a schematic diagram showing the identification and extraction effects of key points of human bones according to the present invention;
FIG. 4 is a schematic diagram of the constructed front and side neutral models of the present invention, where a represents the front neutral model and b represents the side neutral model;
FIG. 5 is a schematic view of a triangle angle model according to the present invention.
Detailed Description
The following detailed description of the invention refers to the accompanying drawings and preferred embodiments.
In recent years, scoliosis phenomena of different degrees frequently occur in children, teenagers and adults, and psychological problems such as lack of confidence, depression tendency and the like are seriously caused to generate a suicide concept. Lateral curvature screening is a necessary precursor link for treating the disease, and early discovery, early diagnosis and early treatment of scoliosis have important significance for the realization of national health.
The currently common scoliosis types are C-scoliosis and S-scoliosis, as shown in FIG. 1, and either type of scoliosis ultimately causes abnormal movement of the various joints, e.g., C-scoliosis results in significant differences in height between the left and right shoulders and the left and right hips. The study finds that when a scoliosis crowd stands or walks, each joint point of the human body has different degrees of offset, and the angle of each joint of the human body is different from that of a normal person, so that the degree of the scoliosis can be evaluated by utilizing the coordinate information of the joint point of the human body.
Considering that the OpenPose algorithm is a multi-person 2D gesture detection open source real-time system, is an open source library developed by the university of Carniken Mercury (CMU) based on a convolutional neural network and supervised learning and taking caffe as a framework, can realize accurate identification of human skeleton joints by matching with a COCO data set, can detect information of a plurality of skeleton key points including a body, feet, hands, faces and the like, and therefore, the invention provides a scoliosis assessment method based on the human skeleton key points, which utilizes the OpenPose algorithm to extract coordinate information of the skeleton key points of the human body, and performs scoliosis screening through a specific position relation of the skeleton key points, so as to provide a solution for the scoliosis screening work of a wide population, as shown in fig. 2, 25 skeleton key points which are symmetrically distributed are extracted from a front face diagram and a side diagram of the human body, a front neutral bit line and a side neutral bit line of the human body, a triangle where neck is located are calculated based on the skeleton key points, and the state of the human body is assessed on the side of the triangle where the neck, the neck and the neck are inclined relative to the front neutral bit line and the side of the skeleton key points. Therefore, only the front view and the side view of the human body are required to be collected, 25 skeleton key points which are symmetrically distributed are identified and extracted from the front view and the side view, and the evaluation of the scoliosis of the human body can be rapidly completed through the subsequent calculation of the median line and the triangle, so that the method can be applied to scoliosis screening work of the masses, is beneficial to early discovery, early diagnosis and early treatment of the scoliosis, has important significance for the whole society and the whole people health, and has the advantages of low cost, no damage, strong portability and the like compared with an X-ray, ultrasonic wave and visual inspection method by adopting a common camera and a method for detecting the skeleton key points of the human body. The method comprises the following steps:
step S1, acquiring front images and side images of a human body, wherein when the images of the human body are acquired, a person only needs to stand naturally, two feet are diverged, the distance between the two feet is the same as that between shoulders, the two arms naturally droop, the two hands are clung to trousers seams, eyes look in front of the head-on, and the object distance and other camera parameters need to be kept unchanged when photographing;
s2, processing the acquired human body image to enable pixels to be 480 x 640 in size, inputting the acquired human body image into an OpenPose algorithm to identify and extract key points of human bones, wherein 25 human body skeleton key points are symmetrically distributed, the number of the human body image is 0-24, and the human body image and each part of the human body are in one-to-one correspondence, as shown in figure 3;
s3, analyzing the acquired coordinate information of the key points of the bones to obtain a neutral position model of the spine on the right side and a triangle model to be constructed, and obtaining lateral bending parameters of the spine of the human body through analysis;
1. front side neutral bit offset calculation:
the front neutral bit line is fitted by using 0, 1, 2, 5, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17 and 18 extracted by an OpenPose algorithm to obtain 15 joint points, wherein 15-16, 17-18, 2-5, 9-12, 10-13 and 11-14 are respectively in a pair, 6 pairs are totally extracted by using a formula 1, the midpoints of the 6 joint points are respectively marked as 25, 26, 27, 28, 29 and 30 from top to bottom, and then the total 9 points of 25-30 and 0, 1 and 8 are fitted by using a least square method and a formula 2 to obtain a straight line y=ax+b, as shown in fig. 4a, wherein a parameter a is obtained by using a formula 2, and a parameter b is obtained by using a formula 3 and is defined as the front neutral bit line. In consideration of the defect that the closer the straight line is to the vertical fitting effect is worse when the straight line is fitted by least squares, the coordinate values of x and y of the 9 points need to be interchanged before the straight line is fitted, so that the problem can be solved.
Then, the distance between the 9 bone key points and the median line in the front is calculated by using a point-to-straight distance formula 4, and finally, a root mean square error RMSE is calculated by a formula 5, wherein RMSE is defined as the median offset in the front of the spine, which is an average value, and the farthest distance Smax represents the position of the key point with the largest deviation among the 9 bone key points and the position with the largest influence on the human body due to scoliosis, wherein y i Representing 0 nose, 1 neck, 8 hip center, 15 right eye and 16 left eye midpoint, 17 right ear and 18 left ear midpoint, 2 right shoulder and 5 left shoulder midpoint, 9 right hip and 12 left hip midpoint, 10 right knee and 13 left knee midpoint, 11 right ankle and 14 left ankle midpoint, or 1 neck, 8 hip center, 13 left knee, 14 left ankle;
the corresponding ordinate is shown when the fitting results are on the front neutral bit line or the side neutral bit line with the abscissa of 0 nose, 1 neck, 8 hip center, and 15 right eye and 16 left eye midpoint, 17 right ear and 18 left ear midpoint, 2 right shoulder and 5 left shoulder midpoint, 9 right hip and 12 left hip midpoint, 10 right knee and 13 left knee midpoint, 11 right ankle and 14 left ankle midpoint, or 1 neck, 8 hip center, 13 left knee, 14 left ankle abscissa.
In addition, the height difference delta h of the bone key points 4 and 7 in the vertical direction can well reflect the degree of scoliosis. A larger Δh indicates a greater degree of lateral curvature and a less healthy spine, requiring further examination and treatment to the hospital.
Δh＝|y 4 -y 7 | (6)
2. Side neutral position offset calculation
The parameters a are obtained by using the formulas 2-3 according to the total of 4 joint points of 1, 8, 13 and 14 extracted by using the OpenPose algorithm to fit the side neutral bit line 1 、b 1 Resulting in a straight line y1=a 1 x+b 1 The furthest distance Smax1 of each bone keypoint 1, 8, 13, 14 from the lateral neutral bitline and the lateral spinal neutral offset RMSE1 are then obtained using equations 4, 5, wherein the lateral neutral model is shown in fig. 4 b.
3. Level assessment
a. Constructing a triangle: three bone key points 1, 5 and 8 extracted by the OpenPose algorithm are extracted to construct delta ABC, wherein A corresponds to the bone key point 1, B corresponds to the bone key point 5, C corresponds to the bone key point 8, and the degree of the angle BAC can be used for measuring the horizontality of the left shoulder.
b. Calculating the side length of the triangle: and obtaining the side lengths a, b and c of the triangle 3 side by using a distance formula 7 between the two points.
c. As shown in FIG. 5, the angles θ obtained in the previous step are directly obtained by taking the angles a, b, and c into the formula 8 1 Degrees.
As shown in fig. 5, the same method is used for obtaining skeleton key points 1 (B1), 8 (A1) and 12 (C1) to construct delta A1B1C1, and obtaining angle B1A1C1; taking skeleton key points 1 (B2), 0 (A2) and 18 (C2) to construct delta A2B2C2,calculating angle B2A2C2, and finally obtaining angle BAC (theta 1 )、∠B1A1C1(θ 2 ) And +.B2A2C2 (θ) 3 ) The degrees of the three angles are used for completing the horizontality evaluation of the left shoulder, the left hip and the neck.
For convenience of description of error in horizontality, θ 1 、θ 2 、θ 3 The absolute value of the difference from 90 ° is used as final data for evaluating the scoliosis degree, and the calculation formula is as follows:
Δθ i ＝|θ i -90 0 |,i＝1,2,3 (9)
and S3, analyzing the acquired scoliosis parameters so as to acquire a scoliosis analysis report.
The analysis report parameters of the scoliosis comprise RMSE, RMSE1 and delta theta i And Δh, and the greater the above parameter values, the more severe the scoliosis.
In order to prove the feasibility of the method provided by the invention, the comparison tests of the neutral position offset of the spine, the vertical height difference of the hands and the specific joint angle difference of different groups of people are designed. The hardware system required by the experiment is as follows: a Kinect V2 camera, a Y9000K 2019SE notebook computer and the like; the software is an openPose system and runs on Visual Studio 2019.
Selecting 20 normal people, people with mild scoliosis and people with moderate scoliosis as testees, acquiring key point coordinate information of bones on the front and the side of the human body according to the steps, processing the coordinate information by using the method provided by the invention, and respectively calculating the front RMSE, smax and delta theta of each testee 1 、△θ 2 、△θ 3 The values of Δh and the values of side RMSE, smax1 were obtained for different populations and the test results are shown in table 1:
TABLE 1 calculation results of eigenvalues for different populations
The experimental data can find that the front RMSE, smax, delta theta 1, delta theta 2, delta theta 3, delta h values, the side RMSE and Smax1 values of different crowds are obviously different, and normal people, people with mild scoliosis and people with moderate scoliosis can be distinguished according to the differences; if the root mean square error of the spine deviates from the neutral position by more than 2.4, the height difference of the hand in the vertical direction by more than 6.4 pixels or the inclination angle delta theta 1 of the shoulder exceeds 2.50, lateral curvature of the spine may occur. The method can be applied to practice as a method for screening scoliosis of masses. To further illustrate the superiority of the present method table 2 compares the screening evaluation of existing scoliosis with the methods presented herein.
TABLE 2 comparison of the advantages and disadvantages and sensitivity of different screening and evaluation methods for scoliosis
While particular embodiments of the present invention have been described above, it will be appreciated by those skilled in the art that these are merely illustrative, and that many changes and modifications may be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims.
Claims (3)
1. A scoliosis assessment method based on key points of human bones is characterized by comprising the following steps of: extracting 25 skeleton key points symmetrically distributed from a front view and a side view of a human body, calculating front neutral bit lines and side neutral bit lines of the human body and triangles where the neck, the shoulder and the hip are located based on the skeleton key points, and completing evaluation of scoliosis of the human body according to the deviation condition of the skeleton key points relative to the front neutral bit lines and the side neutral bit lines and the inclination states of the triangles;
the 25 skeletal key points are respectively set as 0 nose, 1 neck, 2 right shoulder, 3 right elbow, 4 right wrist, 5 left shoulder, 6 left elbow, 7 left wrist, 8 hip center, 9 right hip, 10 right knee, 11 right ankle, 12 left hip, 13 left knee, 14 left ankle, 15 right eye, 16 left eye, 17 right ear, 18 left ear, 19 left big toe, 20 left little toe, 21 left heel, 22 right big toe, 23 right little toe, 24 right heel,
fitting the center of 0 nose, 1 neck, 8 buttocks and the center of 15 right eye and 16 left eye, the center of 17 right ear and 18 left ear, the center of 2 right shoulder and 5 left shoulder, the center of 9 right hip and 12 left hip, the center of 10 right knee and 13 left knee, the center of 11 right ankle and 14 left ankle in the key points of the bones to establish a front neutral bit line;
fitting 1 neck, 8 hip center, 13 left knee and 14 left ankle in the key points of the skeleton to establish a side neutral bit line;
the triangle of neck comprises 0 nose, 1 neck and 18 left ears, the triangle of shoulder comprises 1 neck, 8 buttocks and 5 left shoulders, the triangle of hip comprises 1 neck, 8 buttocks and 12 left hips;
the degree of offset in the neutral position of the spine is estimated using the root mean square error RMSE using the following equation,
wherein y is i Representing 0 nose, 1 neck, 8 hip center, 15 right eye and 16 left eye midpoint, 17 right ear and 18 left ear midpoint, 2 right shoulder and 5 left shoulder midpoint, 9 right hip and 12 left hip midpoint, 10 right knee and 13 left knee midpoint, 11 right ankle and 14 left ankle midpoint, or 1 neck, 8 hip center, 13 left knee, 14 left ankle;
using the equation |theta i -90 deg., evaluate the degree of offset of spinal levelness, where θ 1 The angle value of the angle 5 in the triangle where the shoulders are located and the angle 1 in the left shoulder, the neck and the angle 8 in the hip are shown, theta 2 Represents the angle value of the left hip of the 1 neck 8 buttock 12 in the triangle of the hip, theta 3 The angle value of the left ear of the nose 18 is represented by 1 neck 0 in the triangle where the neck is located.
2. The scoliosis assessment method based on key points of human bones according to claim 1, wherein: the front neutral bit line and the side neutral bit line are obtained by adopting a least binomial fitting method, and 25 skeleton key points are extracted from a front view and a side view of a human body by adopting an OpenPose algorithm.
3. The scoliosis assessment method based on key points of human bones according to claim 1, wherein: when the front view and the side view of the human body are collected, the feet of the tester are separated, the interval is the same as the shoulder, the two arms naturally drop, and eyes look in front.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240365.8A CN114224322B (en) | 2021-10-25 | 2021-10-25 | Scoliosis assessment method based on key points of human bones |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240365.8A CN114224322B (en) | 2021-10-25 | 2021-10-25 | Scoliosis assessment method based on key points of human bones |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114224322A CN114224322A (en) | 2022-03-25 |
| CN114224322B true CN114224322B (en) | 2023-06-02 |
Family
ID=80743216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111240365.8A Active CN114224322B (en) | 2021-10-25 | 2021-10-25 | Scoliosis assessment method based on key points of human bones |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114224322B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013248089A (en) * | 2012-05-31 | 2013-12-12 | Kitasato Institute | Scoliosis screening system, scoliosis determination program used therefor, and terminal device |
| CN106022213A (en) * | 2016-05-04 | 2016-10-12 | 北方工业大学 | Human body motion recognition method based on three-dimensional bone information |
| CN107481228A (en) * | 2017-07-28 | 2017-12-15 | 电子科技大学 | Human body back scoliosis angle measurement method based on computer vision |
| CN112472111A (en) * | 2020-12-14 | 2021-03-12 | 上海交通大学医学院附属新华医院 | Early self-checking and rehabilitation cloud platform for scoliosis |
| CN113499180A (en) * | 2021-06-25 | 2021-10-15 | 西安交通大学 | Scoliosis orthosis and manufacturing method thereof |
Family Cites Families (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004509722A (en) * | 2000-09-29 | 2004-04-02 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Method and system for extracting vertebral frontal geometry data including vertebral pedicle location |
| ITTO20030309A1 (en) * | 2003-04-18 | 2004-10-19 | St Microelectronics Srl | RELATIVE ANGULAR POSITION MEASURING DEVICE |
| US8014625B2 (en) * | 2004-11-10 | 2011-09-06 | Agfa Healthcare | Method of performing measurements on digital images |
| US20090226055A1 (en) * | 2004-12-10 | 2009-09-10 | Harry Dankowicz | Systems and methods for multi-dimensional characterization and classification of spinal shape |
| JP5344401B2 (en) * | 2009-02-23 | 2013-11-20 | 公立大学法人高知工科大学 | Disc load measuring device and measuring method |
| JP5710497B2 (en) * | 2009-11-24 | 2015-04-30 | 株式会社 レキシー | Program for preoperative planning of hip replacement surgery |
| JP2011160824A (en) * | 2010-02-04 | 2011-08-25 | Future Univ-Hakodate | Spinal curvature determination support apparatus |
| JP2012120647A (en) * | 2010-12-07 | 2012-06-28 | Alpha Co | Posture detection system |
| WO2012112985A2 (en) * | 2011-02-18 | 2012-08-23 | The General Hospital Corporation | System and methods for evaluating vocal function using an impedance-based inverse filtering of neck surface acceleration |
| JP2015150220A (en) * | 2014-02-14 | 2015-08-24 | 株式会社日立メディコ | X-ray CT apparatus and imaging method |
| CN105877751A (en) * | 2015-01-06 | 2016-08-24 | 中国人民解放军空军总医院 | Dynamic spine function detecting system |
| US10695099B2 (en) * | 2015-02-13 | 2020-06-30 | Nuvasive, Inc. | Systems and methods for planning, performing, and assessing spinal correction during surgery |
| JP6230084B1 (en) * | 2016-07-08 | 2017-11-15 | 株式会社ＲｅＴｅｃｈ | Posture evaluation system |
| US10751243B2 (en) * | 2017-02-22 | 2020-08-25 | Edward B. MacMahon | Scoliosis of the mid segment of the thoraco lumbar spine in adolescents: a proposed non-operative solution to the transmitter problem |
| CN107103309A (en) * | 2017-05-31 | 2017-08-29 | 天津中科智能识别产业技术研究院有限公司 | A kind of sitting posture of student detection and correcting system based on image recognition |
| CN108764089B (en) * | 2018-05-18 | 2021-04-13 | 四川效率未来科技有限公司 | Human back spine midline recognition method based on depth camera |
| CN109330602B (en) * | 2018-11-01 | 2022-06-24 | 中山市人民医院 | Female body intelligent evaluation detection device and method and storage medium |
| CN209916224U (en) * | 2019-01-31 | 2020-01-10 | 上海长征医院 | Device for measuring curvature change of thoracolumbar vertebra in operation |
| CN110016504B (en) * | 2019-05-20 | 2022-05-24 | 广州市妇女儿童医疗中心 | Application of CDR1as in prenatal screening of neural tube deformity, product and method for prenatal screening of neural tube deformity |
| CN110495889B (en) * | 2019-07-04 | 2022-05-27 | 平安科技（深圳）有限公司 | Posture evaluation method, electronic device, computer device, and storage medium |
| CN111383221B (en) * | 2020-03-12 | 2023-04-28 | 南方科技大学 | Scoliosis detection model generation method and computer equipment |
| WO2021179230A1 (en) * | 2020-03-12 | 2021-09-16 | 南方科技大学 | Scoliosis detection model generating method and computer device |
| CN213155886U (en) * | 2020-03-31 | 2021-05-11 | 绍兴文理学院元培学院 | Intelligent vest for preventing hunchback of teenagers |
| CN111759314A (en) * | 2020-07-09 | 2020-10-13 | 上海工程技术大学 | Foot length measuring instrument and human body characteristic data acquisition device |
| CN111904740A (en) * | 2020-08-18 | 2020-11-10 | 上海工程技术大学 | Multifunctional intelligent wheelchair and intelligent wheelchair combined bed |
| CN113052842B (en) * | 2021-05-27 | 2021-08-27 | 腾讯科技（深圳）有限公司 | Scoliosis image detection model training method, scoliosis image detection model determining device and scoliosis image detection model determining equipment |
-
2021
- 2021-10-25 CN CN202111240365.8A patent/CN114224322B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013248089A (en) * | 2012-05-31 | 2013-12-12 | Kitasato Institute | Scoliosis screening system, scoliosis determination program used therefor, and terminal device |
| CN106022213A (en) * | 2016-05-04 | 2016-10-12 | 北方工业大学 | Human body motion recognition method based on three-dimensional bone information |
| CN107481228A (en) * | 2017-07-28 | 2017-12-15 | 电子科技大学 | Human body back scoliosis angle measurement method based on computer vision |
| CN112472111A (en) * | 2020-12-14 | 2021-03-12 | 上海交通大学医学院附属新华医院 | Early self-checking and rehabilitation cloud platform for scoliosis |
| CN113499180A (en) * | 2021-06-25 | 2021-10-15 | 西安交通大学 | Scoliosis orthosis and manufacturing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114224322A (en) | 2022-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zago et al. | 3D tracking of human motion using visual skeletonization and stereoscopic vision | |
| CN108209924B (en) | The analysis method of gait feature after a kind of Anterior Cruciate Ligament Ruptures | |
| CN106022213B (en) | A kind of human motion recognition method based on three-dimensional bone information | |
| CN110473192A (en) | Digestive endoscope image recognition model training and recognition methods, apparatus and system | |
| CN110969114A (en) | Human body action function detection system, detection method and detector | |
| KR100909350B1 (en) | 3D biomechanical data and parameter analysis method and apparatus using the method | |
| CN107115102A (en) | A kind of osteoarticular function appraisal procedure and device | |
| WO2017080137A1 (en) | Joint movement detection system and method, and dynamic assessment method and system for knee joint | |
| WO2015162158A1 (en) | Human motion tracking | |
| Churchill et al. | RIVCAM: a simple video-based kinematic analysis for clinical disorders of gait | |
| CN113139962B (en) | System and method for scoliosis probability assessment | |
| Yang et al. | Autonomous gait event detection with portable single-camera gait kinematics analysis system | |
| CN110751100A (en) | Auxiliary training method and system for stadium | |
| Hopkins et al. | Validity and reliability of standing posture measurements using a mobile application | |
| Vafadar et al. | Assessment of a novel deep learning-based marker-less motion capture system for gait study | |
| CN114224322B (en) | Scoliosis assessment method based on key points of human bones | |
| CN113642506A (en) | Method and system for image annotation based on data matching | |
| Pradhan et al. | Feature extraction from 2D images for body composition analysis | |
| CN115105062B (en) | Hip and knee joint coordination evaluation method, device and system and storage medium | |
| CN114052725B (en) | Gait analysis algorithm setting method and device based on human body key point detection | |
| US20230355135A1 (en) | Intelligent gait analyzing apparatus | |
| CN116543455A (en) | Method, equipment and medium for establishing parkinsonism gait damage assessment model and using same | |
| KR20090059095A (en) | Method for three-dimensional biomechanical data and parameter analysis and apparatus using the same method | |
| CN114983396A (en) | Automatic detection system for scoliosis | |
| CN114283404A (en) | Posture evaluation method based on three-dimensional skeleton key point detection |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |