CN112686854B - Method and system for automatically measuring scoliosis Cobb angle - Google Patents
Method and system for automatically measuring scoliosis Cobb angle Download PDFInfo
- Publication number
- CN112686854B CN112686854B CN202011568345.9A CN202011568345A CN112686854B CN 112686854 B CN112686854 B CN 112686854B CN 202011568345 A CN202011568345 A CN 202011568345A CN 112686854 B CN112686854 B CN 112686854B
- Authority
- CN
- China
- Prior art keywords
- vertebral body
- boundary
- centrum
- boundary points
- extracting
- 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
Landscapes
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a system for automatically measuring a scoliosis Cobb angle, wherein the method comprises the following steps: s1: collecting an X-ray image; s2: extracting a plurality of cone boundary points of the X-ray image through a neural network unit; s3: generating vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points; s4: extracting a vertebral body end plate corresponding to the vertebral body based on all the vertebral body boundary information; s5: a scoliosis Cobb angle is generated based on all of the vertebral endplates. According to the invention, a plurality of vertebral body boundary points of the X-ray image are automatically detected by using the neural network unit, the vertebral body end plates corresponding to the vertebral bodies are extracted through the vertebral body boundary points, and the scoliosis Cobb angle is generated through all the vertebral body end plates, so that the detection of the scoliosis Cobb angle is automatically completed, the steps of manual calibration and calculation in the traditional Cobb angle are avoided, the influence of human factors on the detection result is reduced, and the detection precision of the scoliosis Cobb angle is effectively improved.
Description
Technical Field
The invention relates to the technical field of human posture recognition, in particular to a method and a system for automatically measuring a scoliosis Cobb angle
Background
Scoliosis is a three-dimensional deformity of the spine that includes sequential abnormalities in the coronal, sagittal and axial positions. The Cobb angle is the intersection angle of the perpendicular line of the upper edge of the cephalic end vertebra and the perpendicular line of the lower edge of the caudal end vertebra, and is the most critical index for evaluating the severity of scoliosis. The diagnostic standard of the scoliosis is that the Cobb angle is larger than 10 degrees, and the surgical indication of the scoliosis is that the Cobb angle is larger than 45 degrees, so that the accurate measurement of the Cobb is particularly important for diagnosis and treatment of the scoliosis.
The traditional Cobb angle measurement method mainly comprises two methods, namely, marking on an X-ray film by a marking pen and measuring an intersection angle by a protractor, and calling the X-ray film by a medical image storage and transmission system and measuring the Cobb angle by a computer with angle measurement work. However, in both methods, a doctor needs to manually select the upper vertebra and the lower vertebra and perform the marking work of the parallel lines of the vertebral end plates of the upper vertebra and the lower vertebra, the marking work is greatly influenced by the experience limitation/subjective judgment of the doctor, and the calculation result of the obtained Cobb angle has errors.
Therefore, the existing method for measuring the Cobb angle has the problems of low automation degree and low detection precision.
Disclosure of Invention
In view of this, the invention provides a method and a system for automatically measuring a scoliosis Cobb angle, which solve the problems of low automation degree and low detection accuracy of the existing method for measuring the Cobb angle by improving an image detection method.
In order to solve the problems, the technical scheme of the invention is to adopt a method for automatically measuring the scoliosis Cobb angle, which comprises the following steps: s1: collecting an X-ray image; s2: extracting a plurality of vertebral body boundary points of the X-ray image through a neural network unit; s3: generating vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points; s4: extracting a vertebral body end plate corresponding to the vertebral body based on all the vertebral body boundary information; s5: a scoliosis Cobb angle is generated based on all of the vertebral endplates.
Optionally, the S2 includes: acquiring a data set consisting of a plurality of X-ray pictures, labeling a cone boundary point of each X-ray picture, and generating a training sample set and a test set consisting of a plurality of X-ray pictures containing cone boundary point marks; based on the training sample set and the test set, training and verifying by using an HRNet model under an Encoder-Decoder framework to generate a centrum boundary point detection model for extracting the centrum boundary points; inputting the X-ray image into the neural network unit, and extracting a plurality of centrum boundary points in the X-ray image based on the centrum boundary point detection model.
Optionally, the S3 includes: s31: extracting coordinates of all the cone boundary points, and constructing first cone boundary information by using the four cone boundary points with the maximum vertical coordinates; s32: extracting four vertebral body boundary points with the largest vertical coordinate in the remaining vertebral body boundary points to construct second vertebral body boundary information; s33: and repeating the step S32 until all the vertebral body boundary points are traversed, and generating vertebral body boundary information and position relation information corresponding to each vertebral body.
Optionally, the vertebral body endplates comprise a superior vertebral body endplate and an inferior vertebral body endplate.
Optionally, the S4 includes: s41: extracting two centrum boundary points with the maximum vertical coordinate in the centrum boundary information and connecting lines thereof to construct the centrum upper end plate, and constructing the centrum lower end plate by using the remaining two centrum boundary points in the centrum boundary information and connecting lines thereof; s42: and repeating the step S41 until all the upper vertebral body end plates and the lower vertebral body end plates corresponding to the vertebral bodies are extracted.
Accordingly, the present invention provides a system for automatically measuring the scoliosis Cobb angle, comprising: the acquisition unit is used for acquiring an X-ray image; a neural network unit for extracting a plurality of cone boundary points of the X-ray image; the data processing unit generates vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points, and extracts a vertebral body endplate corresponding to each vertebral body based on all the vertebral body boundary information; a scoliosis Cobb angle is generated based on all of the vertebral endplates.
Optionally, the neural network unit generates a training sample set and a test set composed of a plurality of X-ray pictures containing cone boundary point marks by acquiring a data set composed of a plurality of X-ray pictures and labeling the cone boundary points of each X-ray picture, based on the training sample set and the test set, a HRNet model is used for training and verifying under an Encoder-Decoder framework, a cone boundary point detection model for extracting the cone boundary points is generated, and after the X-ray images are input into the neural network unit, a plurality of cone boundary points in the X-ray images are extracted based on the cone boundary point detection model.
Optionally, the neural network unit is further provided with a residual network Resnet101 for preventing degradation of the network model.
Optionally, the data processing unit extracts coordinates of all the vertebral body boundary points, and constructs first vertebral body boundary information with the four vertebral body boundary points with the largest vertical coordinates; extracting four vertebral body boundary points with the largest vertical coordinate in the remaining vertebral body boundary points to construct second vertebral body boundary information; and repeatedly extracting the centrum boundary information until all the centrum boundary points are traversed, and generating centrum boundary information and position relation information corresponding to each centrum.
Optionally, the system for measuring the scoliosis Cobb angle further comprises a data storage unit, which stores the X-ray image to be processed, a data set composed of a plurality of X-ray pictures for training of the neural network unit, and scoliosis Cobb angle information generated by the data processing unit.
The invention has the primary improvement that the method for automatically measuring the scoliosis Cobb angle is provided, a plurality of centrum boundary points of an X-ray image are automatically detected by using a neural network unit, centrum end plates corresponding to the centrum are extracted through the centrum boundary points, and the scoliosis Cobb angle is generated through all the centrum end plates, so that the detection of the scoliosis Cobb angle is automatically completed, the steps of manual calibration and calculation in the traditional Cobb angle are avoided, the influence of human factors on the detection result is reduced, the detection precision of the scoliosis Cobb angle is effectively improved, and the problems of low automation degree and low detection precision of the traditional method for measuring the Cobb angle are solved.
Drawings
FIG. 1 is a simplified flow diagram of a method of the present invention for automatically measuring the lateral bending Cobb angle of the spine;
fig. 2 is a simplified modular connection diagram of the system for automatically measuring the scoliosis Cobb angle of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood by those skilled in the art, the present invention will be further described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1, a method for automatically measuring a scoliosis Cobb angle, comprises: s1: collecting an X-ray image; s2: extracting a plurality of cone boundary points of the X-ray image through a neural network unit; s3: generating vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points; s4: extracting a vertebral body end plate corresponding to the vertebral body based on all the vertebral body boundary information; s5: generating a scoliosis Cobb angle based on all of the vertebral endplates. Wherein the vertebral body end plate comprises a vertebral body upper end plate and a vertebral body lower end plate.
According to the invention, a plurality of vertebral body boundary points of the X-ray image are automatically detected by using the neural network unit, the vertebral body end plates corresponding to the vertebral bodies are extracted through the vertebral body boundary points, and the scoliosis Cobb angle is generated through all the vertebral body end plates, so that the detection of the scoliosis Cobb angle is automatically completed, the steps of manual calibration and calculation in the traditional Cobb angle are avoided, the influence of human factors on the detection result is reduced, the detection precision of the scoliosis Cobb angle is effectively improved, and the problems of low automation degree and low detection precision of the existing method for measuring the Cobb angle are solved.
Further, the S2 includes: acquiring a data set consisting of a plurality of X-ray pictures, labeling a cone boundary point of each X-ray picture, and generating a training sample set and a test set consisting of a plurality of X-ray pictures containing cone boundary point labels; training and verifying under an Encoder-Decoder framework by using an HRNet model based on the training sample set and the test set to generate a vertebral body boundary point detection model for extracting the vertebral body boundary points; inputting the X-ray image into the neural network unit, and extracting a plurality of vertebral body boundary points in the X-ray image based on the vertebral body boundary point detection model. The invention utilizes the characteristics of the HRNet model: the high-resolution and low-resolution networks are connected in parallel, so that the image can keep high resolution, the resolution is not restored through a low-to-high process, and the accuracy of the neural network output for predicting the vertebral body boundary point is further improved.
Further, the S3 includes: s31: extracting coordinates of all the cone boundary points, and constructing first cone boundary information by using the four cone boundary points with the maximum vertical coordinates; s32: extracting four vertebral body boundary points with the largest vertical coordinate in the remaining vertebral body boundary points to construct second vertebral body boundary information; s33: and repeating the step S32 until all the vertebral body boundary points are traversed, and generating vertebral body boundary information and position relation information corresponding to each vertebral body. If the detected object is all human vertebras, the number of all vertebral body boundary points is 68, the number of all vertebral bodies is 17, and the detected object comprises 12 thoracic vertebras and 5 lumbar vertebras. If the detected object is part of human vertebra, the number of the vertebra bodies can be calculated according to the number of the vertebra body boundary points.
Further, the S4 includes: s41: extracting two centrum boundary points with the largest vertical coordinate in the centrum boundary information and connecting lines thereof to construct the centrum upper end plate, and constructing the centrum lower end plate by using the remaining two centrum boundary points in the centrum boundary information and connecting lines thereof; s42: and repeating the step S41 until all the upper vertebral body end plates and the lower vertebral body end plates corresponding to the vertebral bodies are extracted.
Further, a method for generating a scoliosis Cobb angle based on all of the vertebral endplates may be: the data processing unit takes any vertebral body end plate as a first end plate; respectively calculating and storing the included angles between the first end plate and the other vertebral body end plates, taking any other vertebral body end plate except the first end plate as a second end plate, and respectively calculating and storing the included angles between the second end plate and the other vertebral body end plates; repeating the steps until the angle relation existing on the end plate of the complete vertebral body is traversed; and extracting the maximum included angle as a scoliosis Cobb angle.
Still further, the method of generating the scoliosis Cobb angle based on all of the vertebral endplates may further be: respectively calculating included angles of all the directions of the upper vertebral body end plate and the lower vertebral body end plate relative to the horizontal direction, and constructing an end plate included angle waveform diagram used for representing included angle information corresponding to the upper vertebral body end plate and the lower vertebral body end plate; and extracting the maximum value and the minimum value of the included angle in the end plate included angle oscillogram, and calculating the difference value between the maximum value and the minimum value of the included angle to generate a scoliosis Cobb angle. After a scoliosis Cobb angle is generated, the vertebral body corresponding to the maximum included angle value and the vertebral body corresponding to the minimum included angle value are extracted, and upper end vertebral information and lower end vertebral information used for representing scoliosis are generated based on the position relation information corresponding to each vertebral body. When the end plate included angle oscillogram used for representing the included angle information corresponding to the upper end plate and the lower end plate of the vertebral body is constructed, the construction can be carried out by taking the sequence of the vertebral body as a horizontal coordinate and taking the degree of an included angle between a final plate line of the vertebral body and the horizontal plane as a vertical coordinate.
Accordingly, as shown in fig. 2, the present invention provides a system for automatically measuring the scoliosis Cobb angle, comprising: the acquisition unit is used for acquiring an X-ray image; a neural network unit for extracting a plurality of cone boundary points of the X-ray image; the data processing unit generates vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points, and extracts a vertebral body endplate corresponding to each vertebral body based on all the vertebral body boundary information; a scoliosis Cobb angle is generated based on all of the vertebral endplates. The acquisition unit, the data storage unit, the neural network unit and the data processing unit are sequentially cascaded.
Furthermore, the neural network unit generates a training sample set and a test set which are composed of a plurality of X-ray pictures containing cone boundary point marks by acquiring a data set composed of a plurality of X-ray pictures and labeling the cone boundary points of each X-ray picture, based on the training sample set and the test set, an HRNet model is used for training and verifying under an Encoder-Decoder framework, a cone boundary point detection model for extracting the cone boundary points is generated, and after the X-ray images are input into the neural network unit, a plurality of cone boundary points in the X-ray images are extracted based on the cone boundary point detection model. Wherein the neural network unit is further provided with a residual error network Resnet101 for preventing degradation of the network model.
Further, the data processing unit extracts coordinates of all the vertebral body boundary points, and constructs first vertebral body boundary information by using the four vertebral body boundary points with the largest vertical coordinates; extracting four vertebral body boundary points with the maximum vertical coordinate in the rest vertebral body boundary points to construct second vertebral body boundary information; and repeatedly extracting the centrum boundary information until all the centrum boundary points are traversed, and generating the centrum boundary information and the position relation information corresponding to each centrum.
Further, the system for measuring the scoliosis Cobb angle further comprises a data storage unit, wherein the data storage unit stores the X-ray image to be processed, a data set composed of a plurality of X-ray pictures for training of the neural network unit and the scoliosis Cobb angle information generated by the data processing unit.
The method and the system for automatically measuring the scoliosis Cobb angle provided by the embodiment of the invention are described in detail above. The embodiments are described in a progressive mode in the specification, the emphasis of each embodiment is on the difference from the other embodiments, and the same and similar parts among the embodiments can be referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description. It should be noted that, for those skilled in the art, it is possible to make various improvements and modifications to the present invention without departing from the principle of the present invention, and those improvements and modifications also fall within the scope of the claims of the present invention.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the components and steps of the various examples have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Claims (4)
1. A method of automatically measuring the scoliosis Cobb angle, comprising:
s1: collecting an X-ray image;
s2: extracting, by a neural network unit, a plurality of cone boundary points of the X-ray image, including: acquiring a data set consisting of a plurality of X-ray pictures, labeling a cone boundary point of each X-ray picture, and generating a training sample set and a test set consisting of a plurality of X-ray pictures containing cone boundary point marks; based on the training sample set and the test set, training and verifying by using an HRNet model under an Encoder-Decoder framework to generate a centrum boundary point detection model for extracting the centrum boundary points; inputting the X-ray image into the neural network unit, and extracting a plurality of vertebral body boundary points in the X-ray image based on the vertebral body boundary point detection model;
s3: generating vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points, including: s31: extracting coordinates of all the cone boundary points, and constructing first cone boundary information by using the four cone boundary points with the maximum vertical coordinates; s32: extracting four vertebral body boundary points with the maximum vertical coordinate in the rest vertebral body boundary points to construct second vertebral body boundary information; s33: repeating the step S32 until all the vertebral body boundary points are traversed, and generating vertebral body boundary information and position relation information corresponding to each vertebral body;
s4: based on all the vertebral body boundary information, extracting a vertebral body endplate corresponding to the vertebral body, wherein the extraction comprises the following steps: s41: extracting two centrum boundary points with the maximum vertical coordinate in the centrum boundary information and connecting lines thereof to construct the centrum upper end plate, and constructing the centrum lower end plate by using the remaining two centrum boundary points in the centrum boundary information and connecting lines thereof; s42: repeating the step S41 until the upper vertebral body endplate and the lower vertebral body endplate corresponding to all the vertebral bodies are extracted; wherein the vertebral body end plate comprises a vertebral body upper end plate and a vertebral body lower end plate;
s5: generating a scoliosis Cobb angle based on all of the vertebral endplates.
2. A system for automatically measuring the scoliosis Cobb angle, comprising:
the acquisition unit is used for acquiring an X-ray image;
a neural network unit for extracting a plurality of vertebral body boundary points of the X-ray image, comprising: acquiring a data set consisting of a plurality of X-ray pictures, labeling a cone boundary point of each X-ray picture, and generating a training sample set and a test set consisting of a plurality of X-ray pictures containing cone boundary point marks; training and verifying under an Encoder-Decoder framework by using an HRNet model based on the training sample set and the test set to generate a vertebral body boundary point detection model for extracting the vertebral body boundary points; inputting the X-ray image into the neural network unit, and extracting a plurality of vertebral body boundary points in the X-ray image based on the vertebral body boundary point detection model;
the data processing unit generates vertebral body boundary information corresponding to each vertebral body based on the plurality of vertebral body boundary points, and comprises: s31: extracting coordinates of all the vertebral body boundary points, constructing first vertebral body boundary information by using the four vertebral body boundary points with the maximum vertical coordinates, and S32: extracting four vertebral body boundary points with the maximum vertical coordinate in the residual vertebral body boundary points to construct second vertebral body boundary information, and S33: repeating the step S32 until all the centrum boundary points are traversed, and generating centrum boundary information and position relation information corresponding to each centrum; based on all the vertebral body boundary information, extracting the vertebral body end plate corresponding to the vertebral body comprises the following steps: s41: extracting two centrum boundary points with the maximum vertical coordinate in the centrum boundary information and connecting lines thereof to construct the centrum upper end plate, and constructing the centrum lower end plate by using the remaining two centrum boundary points in the centrum boundary information and connecting lines thereof, S42: repeating the step S41 until the upper vertebral body end plate and the lower vertebral body end plate corresponding to all the vertebral bodies are extracted, wherein the vertebral body end plates comprise the upper vertebral body end plate and the lower vertebral body end plate; generating a scoliosis Cobb angle based on all of the vertebral endplates.
3. The system for automatically measuring scoliosis Cobb angle according to claim 2, wherein the neural network unit is further provided with a residual error network Resnet101 for preventing network model degradation.
4. The system for automatically measuring the scoliosis Cobb angle of claim 3, wherein the system for measuring the scoliosis Cobb angle further comprises a data storage unit for storing the X-ray image to be processed, a data set consisting of a plurality of X-ray pictures for the neural network unit training and the scoliosis Cobb angle information generated by the data processing unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011568345.9A CN112686854B (en) | 2020-12-25 | 2020-12-25 | Method and system for automatically measuring scoliosis Cobb angle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011568345.9A CN112686854B (en) | 2020-12-25 | 2020-12-25 | Method and system for automatically measuring scoliosis Cobb angle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112686854A CN112686854A (en) | 2021-04-20 |
| CN112686854B true CN112686854B (en) | 2023-01-24 |
Family
ID=75452016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011568345.9A Active CN112686854B (en) | 2020-12-25 | 2020-12-25 | Method and system for automatically measuring scoliosis Cobb angle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112686854B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114078120B (en) * | 2021-11-22 | 2022-05-20 | 北京欧应信息技术有限公司 | Method, apparatus and medium for detecting scoliosis |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573502A (en) * | 2018-03-06 | 2018-09-25 | 安徽大学 | A kind of method at the angles automatic measurement Cobb |
| CN111627560A (en) * | 2020-05-27 | 2020-09-04 | 四川大学华西医院 | Spinal near-end junction angle operation optimization method based on finite element and machine learning |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8900146B2 (en) * | 2009-07-27 | 2014-12-02 | The Hong Kong Polytechnic University | Three-dimensional (3D) ultrasound imaging system for assessing scoliosis |
| KR101695079B1 (en) * | 2015-01-28 | 2017-01-10 | 울산대학교 산학협력단 | Apparatus and Method for Measuring Cobb angle |
| CN108053394A (en) * | 2017-12-08 | 2018-05-18 | 李书纲 | A kind of Medical Imaging System |
| CN108320288B (en) * | 2017-12-08 | 2023-05-30 | 李书纲 | Data processing method for idiopathic scoliosis image |
| CN110175502A (en) * | 2019-04-03 | 2019-08-27 | 中国科学院深圳先进技术研究院 | A kind of backbone Cobb angle measuring method, device, readable storage medium storing program for executing and terminal device |
| CN110415291A (en) * | 2019-08-07 | 2019-11-05 | 清华大学 | Image processing method and relevant device |
| CN112102947B (en) * | 2020-04-13 | 2024-02-13 | 国家体育总局体育科学研究所 | Apparatus and method for body posture assessment |
| CN111671454B (en) * | 2020-06-08 | 2023-10-31 | 平安科技（深圳）有限公司 | Spine bending angle measuring method, device, computer equipment and storage medium |
-
2020
- 2020-12-25 CN CN202011568345.9A patent/CN112686854B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108573502A (en) * | 2018-03-06 | 2018-09-25 | 安徽大学 | A kind of method at the angles automatic measurement Cobb |
| CN111627560A (en) * | 2020-05-27 | 2020-09-04 | 四川大学华西医院 | Spinal near-end junction angle operation optimization method based on finite element and machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112686854A (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100488451C (en) | Medical image process apparatus with medical image measurement function | |
| WO2020199694A1 (en) | Spine cobb angle measurement method and apparatus, readable storage medium, and terminal device | |
| CN112734757B (en) | Spine X-ray image cobb angle measuring method | |
| CN112535489B (en) | Method and system for measuring scoliosis Cobb angle by using oscillogram | |
| CN113674257A (en) | Method, device and equipment for measuring scoliosis angle and storage medium | |
| CN102652004B (en) | Method and apparatus for measuring spinal characteristics of patient | |
| CN115880281B (en) | Spine centrum key point detection and scoliosis recognition device and method | |
| CN112686854B (en) | Method and system for automatically measuring scoliosis Cobb angle | |
| CN112802019B (en) | Leke typing method based on spine AIS image | |
| CN109464148A (en) | Measure the apparatus and system of spinal curvature | |
| CN111317580A (en) | Vertebral stabilization system and method | |
| US11195262B2 (en) | Body region identification device and method | |
| CN111652300A (en) | Spine curvature classification method, computer device and storage medium | |
| CN113515875B (en) | Bone biomechanics modeling method, system and device based on multi-modal image | |
| CN111179242A (en) | Image processing method and device | |
| JP2022050004A (en) | Medical image processing device and medical image processing method and learning method of learning model | |
| KR101464862B1 (en) | Method and apparatus for determining scoliosis using camera | |
| CN115393622A (en) | Deep learning-based sacrum three-dimensional model matching method and device | |
| Moura et al. | Real-scale 3D models of the scoliotic spine from biplanar radiography without calibration objects | |
| CN111986138A (en) | Method and device for obtaining rib positioning | |
| CN108814611B (en) | Method and device for measuring rotation angle of vertebral body | |
| Marchi et al. | Reproducibility and equivalence of cobbmeter application in the sagittal evaluation of the spine | |
| Adibatti et al. | Design and performance analysis of Cobb angle measurement from X-ray images | |
| CN118037668A (en) | Deep learning-based pedicle identification method for CT spine image | |
| CN115797320A (en) | Method and system for identifying vertebral column lateral curvature end vertebra |
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 |