CN109544673B - Three-dimensional imaging method and system for cartilage segmentation of medical image - Google Patents
Three-dimensional imaging method and system for cartilage segmentation of medical image Download PDFInfo
- Publication number
- CN109544673B CN109544673B CN201811222055.1A CN201811222055A CN109544673B CN 109544673 B CN109544673 B CN 109544673B CN 201811222055 A CN201811222055 A CN 201811222055A CN 109544673 B CN109544673 B CN 109544673B
- Authority
- CN
- China
- Prior art keywords
- cartilage
- differential
- dimensional
- dimensional curved
- segmentation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/10—Geometric effects
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves
- A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/08—Volume rendering
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Radiology & Medical Imaging (AREA)
- Computer Graphics (AREA)
- Veterinary Medicine (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- Geometry (AREA)
- High Energy & Nuclear Physics (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention relates to a medical image cartilage segmentation three-dimensional imaging method and system based on physiological anatomy feature and threshold screening, which can clearly distinguish which areas do not belong to cartilage areas through the physiological anatomy feature, and simultaneously realize the correct segmentation of the contact surface between cartilages according to the segmentation of the basic thickness of the cartilages by combining the threshold screening method, thereby avoiding the problems of low efficiency, easy error and the like caused by the traditional manual segmentation and greatly improving the cartilage diagnosis efficiency.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a medical image cartilage segmentation three-dimensional imaging method and system based on physiological anatomy feature and threshold screening.
Background
Cartilage is a layer of bone tissue with a certain elasticity, which covers the bone surface on the joint surface, and plays roles of reducing friction and buffering when the joint moves or slides relatively. The reduction of cartilage volume and the change of surface smoothness can affect the functions of joints, represent arthralgia, limit joint movement and easily cause disability in serious cases. The main method of examining cartilage is arthroscope, which can directly observe the condition of the outer surface of cartilage, but cannot observe the condition of the interface between cartilage and bone, and is an invasive examination, so nuclear magnetic resonance examination is often adopted. The nuclear magnetic resonance detection uses different gray values to identify human tissue structures with different densities, so that the positions and states of the human tissue structures can be intuitively distinguished. However, since cartilage is typically only about 2-3mm thick, the two cartilage surfaces inside the joint are in close contact, the density and water content of the cartilage are basically consistent with those of surrounding connective tissue and muscle tissue, so that the gray value change on the nuclear magnetic resonance image is not obvious enough, and the reason is that when the cartilage is separated by using the nuclear magnetic resonance detection method, the cartilage and other surrounding tissues are easily classified into the cartilage tissues by using the conventional method, and the contact surface between the two cartilage surfaces cannot be separated; the method of manually distinguishing cartilage contact surfaces is time consuming and has artificial differences, which may be the case for different people treating the same cartilage surface. There is therefore a great need for a system that can accurately segment cartilage based on nuclear magnetic resonance images.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a medical image cartilage segmentation three-dimensional imaging method and system based on physiological anatomical features combined with threshold screening, which areas do not belong to cartilage areas can be clearly distinguished through the physiological anatomical features, and meanwhile, the correct segmentation of the contact surface between the cartilages is realized according to the basic thickness and gray segmentation of the cartilages.
In order to achieve the above object, the present invention adopts the technical scheme that:
a three-dimensional imaging method for cartilage segmentation of medical images comprises the following working steps:
1) Obtaining a nuclear magnetic resonance medical image sequence of a person to be detected, and establishing a three-dimensional surface of the cartilage and joint skeleton contact surface, namely a three-dimensional surface of the cartilage inner surface, by using a threshold screening method;
2) Dividing the three-dimensional curved surface of the cartilage inner surface into a plurality of differential surfaces, namely the three-dimensional curved surface differential surfaces of the cartilage inner surface;
3) Taking the three-dimensional curved surface differential surface of the inner surface of the cartilage as a vector from the bottom surface to the cartilage growth direction, namely an external normal vector;
4) Taking a three-dimensional curved surface differential surface of the inner surface of the cartilage as a bottom surface and an external normal vector as a height direction as a differential body, and deducing a gray level distribution curve B=f (x) of the differential body along the height direction according to a nuclear magnetic resonance medical image sequence, wherein B represents gray level and x represents height;
5) When the gray level distribution curve of the differential body along the height direction has a point x' so that the curve change rate is larger than the gray level curve distinguishing point, namely, when the derivative of f (x) is smaller than the derivative distinguishing point, the differential surface position of the cartilage far bone surface corresponding to the differential body can be directly determined, namely, the differential surface position of the cartilage far bone surface corresponding to the differential body is directly determined by adopting a threshold value screening method, and the obtained differential surface position is the position of the cartilage outer surface three-dimensional curved surface differential surface, so that the cartilage thickness corresponding to the differential surface is obtained;
6) When the gray level distribution curve of the differential body along the height direction does not have one point x ' so that the curve change rate is larger than the gray level curve distinguishing point, correcting by adopting a physiological anatomical feature method, and when a point x ' between the value of x being 0 and the expected cartilage parameter thickness of a person to be detected exists, the x ' meets x ' so that the derivative of f (x) is 0 for the first time, the x ' is the position of the differential surface of the cartilage far bone surface corresponding to the differential body, namely the position of the differential surface of the three-dimensional curved surface of the cartilage outer surface, so that the cartilage thickness corresponding to the differential surface is obtained;
7) And connecting all the cartilage outer surface three-dimensional curved surface differential surfaces to form a cartilage outer surface three-dimensional curved surface, and combining the cartilage inner surface three-dimensional curved surfaces to form a cartilage three-dimensional image.
The expected cartilage parameter of the subject is obtained from a typical value of the cartilage parameter in medicine.
The expected cartilage parameters of the person to be detected are obtained by selecting proper cartilage parameters from a cartilage parameter database through personal factors of the person to be detected and selecting proper correction parameters from a correction parameter table through calculation.
The cartilage parameter database comprises a cartilage parameter database established by combining a physiological anatomical method with a past nuclear magnetic resonance medical image sequence and a corresponding correction parameter table.
The cartilage parameter database includes the thickness, density and volume of cartilage.
The correction parameter table determines corresponding correction parameters according to the ages, sexes, weights and cartilage positions of different subjects.
The expected cartilage parameters of the subject include the expected cartilage thickness of the subject, typically 2-3mm.
The threshold screening method comprises the step of carrying out binarization processing on the nuclear magnetic resonance medical image sequence.
The three-dimensional curved surface of the cartilage inner surface and the outer surface of the joint skeleton covered by the cartilage are the same curved surface.
And comparing the cartilage thickness of the differential surface determined by directly adopting the threshold screening method with the expected cartilage parameter of the person to be detected, receiving the calculation result if the error is within the allowable error, and correcting by adopting a physiological anatomical feature method if the error exceeds the allowable error, wherein the allowable error is within +15%.
The allowable error is preferably within +10%, more preferably within +5%.
The three-dimensional curved differential surface of the cartilage inner surface can be any regular polygon.
The three-dimensional curved differential surface of the cartilage inner surface is square.
The dividing number of the three-dimensional curved surface differential surfaces of the cartilage inner surface is 500 to 100000, preferably 5000 to 20000.
The derivative differentiation point is any negative number between-167 and-150.
The gray curve distinguishing point is any integer value between 45-55 gray values per pixel.
The cartilage thickness at each of the differential planes may be 0, but cannot be less than 0.
A medical image cartilage segmentation three-dimensional imaging system comprises an image sequence acquisition module, an image threshold screening processing module, an image differential processing module, an image physiological anatomical feature correction module and a cartilage three-dimensional image synthesis module;
the image sequence acquisition module acquires a nuclear magnetic resonance medical image sequence of a person to be detected, and the image threshold screening processing module establishes a three-dimensional surface of the cartilage and joint skeleton contact surface, namely a three-dimensional surface of the cartilage inner surface by using a threshold screening method;
the image differential processing module divides the three-dimensional curved surface of the cartilage inner surface into a plurality of differential surfaces, namely the three-dimensional curved surface differential surface of the cartilage inner surface, takes the three-dimensional curved surface differential surface of the cartilage inner surface as a bottom surface to conduct vector in the cartilage growth direction, namely an external normal vector, takes the three-dimensional curved surface differential surface of the cartilage inner surface as the bottom surface and takes the external normal vector as a height direction as a differential body, and deduces a gray level distribution curve B=f (x) of the differential body along the height direction according to the nuclear magnetic resonance medical image sequence, wherein B represents gray level, and x represents height;
the image threshold screening processing module processes the obtained differential body, when the gray level distribution curve of the differential body along the height direction has a point x 'so that the curve change rate is larger than the gray level curve distinguishing point, namely, when the gray level distribution curve has a point x' so that the derivative of f (x) is a negative number smaller than the derivative distinguishing point, the differential surface position of the cartilage far bone surface corresponding to the differential body can be directly determined, namely, the differential surface position of the cartilage far bone surface corresponding to the differential body is directly determined by adopting a threshold screening method, and the obtained differential surface position is the position of the cartilage outer surface three-dimensional curved surface differential surface, so that the cartilage thickness corresponding to the differential surface is obtained;
when the gray level distribution curve of the differentiator along the height direction does not have a point x ' so that the curve change rate is larger than the gray level curve differentiating point, the image physiological anatomical feature correction module is utilized to process that a point x ' is present between the value of x being 0 and the expected cartilage parameter thickness of a person to be detected so that the derivative of f (x) is 0 for the first time, and then x ' is the differentiating surface position of the cartilage far bone surface corresponding to the differentiator, namely the position of the cartilage outer surface three-dimensional curved surface differentiating surface, so that the cartilage thickness corresponding to the differentiating surface is obtained;
and finally, connecting all the cartilage outer surface three-dimensional curved surface differential surfaces by a cartilage three-dimensional image synthesis module to form a cartilage outer surface three-dimensional curved surface, and combining the cartilage inner surface three-dimensional curved surface to form a cartilage three-dimensional image.
The beneficial effects of the invention are as follows:
by adopting the technical scheme of the invention to divide the cartilage part in the nuclear magnetic resonance medical image, a three-dimensional image of the cartilage relative sliding surface can be obtained, so that the damaged condition of the cartilage surface can be accurately judged, and the method has great help for further targeted treatment. Meanwhile, the technical scheme of the invention avoids the problems of low efficiency, easy error and the like caused by manual segmentation in the past, and can greatly improve the cartilage diagnosis efficiency.
Drawings
FIG. 1 is a schematic diagram of the method of the present invention.
Fig. 2 is a schematic view of knee joint nuclear magnetic resonance image and micro-volume acquisition in an embodiment of the present invention.
Fig. 3 is a gray scale distribution curve of the S2 micro-scale object along the height direction in the embodiment of the present invention.
Fig. 4 is a gray scale distribution curve of the S1 micro-scale separator along the height direction in the embodiment of the present invention.
FIG. 5 is a schematic diagram of the system components of the present invention.
Detailed Description
For a clearer understanding of the present invention, reference will be made to the following detailed description taken in conjunction with the accompanying drawings and examples.
Taking knee cartilage imaging as an example in combination with the method shown in fig. 1:
1. obtaining a knee joint nuclear magnetic resonance medical image sequence of a person to be processed, wherein the knee joint nuclear magnetic resonance medical image sequence is shown as a picture in a picture 2, the femur nuclear magnetic image of the knee joint is shown as full black on the picture 2, a three-dimensional model of femur is built according to the picture, the three-dimensional model of femur is obtained after edge detection by using a threshold screening method comprising binarization treatment, and the outer surface of the three-dimensional model is the three-dimensional curved surface of the inner surface of femur cartilage, namely the three-dimensional curved surface of the inner surface of cartilage and the outer surface of joint skeleton covered by cartilage are the same curved surface.
2. Dividing the obtained three-dimensional curved surface of the inner surface of the femoral cartilage into a plurality of differential surfaces, wherein the differential surfaces can be square, the number of the differential surfaces can be 500 to 100000, preferably 5000 to 20000, according to practical situations, the obtained three-dimensional curved surface differential surface of the inner surface of the femoral cartilage can be any regular polygon, and the three-dimensional curved surface differential surface of the inner surface of the cartilage is square. The cartilage thickness at each of the differential planes may be 0, but cannot be less than 0.
3. Taking a cartilage growth direction practice vector according to the arbitrary differential plane O of the curved surface of the cartilage inner surface, namely an external normal vector, taking O as a bottom surface and taking the external normal vector as a height direction to obtain a differential body, deriving a gray level distribution curve B=f (x) of the differential body along the height direction according to a nuclear magnetic resonance medical image sequence, wherein B represents gray level, x represents height, and the cartilage thickness of the differential plane is obtained by carrying out different treatments according to the following two conditions:
a. when there is a point x ' to make the curve change rate greater than the gray value of the gray curve distinguishing point 50 per pixel (when there is a point x ' to make the derivative of f (x) smaller than the derivative distinguishing point-150), as at S2 in fig. 2, the position of the differential surface of the cartilage far bone surface corresponding to the differential body can be directly determined, that is, the position of the differential surface of the cartilage far bone surface corresponding to the differential body is directly determined by adopting a threshold screening method, and when the derivative of f (x) is the maximum negative value (changed from white to black suddenly), the point x ' (as shown in fig. 3) is the position of the three-dimensional curved differential surface of the cartilage outer surface, so as to obtain the cartilage thickness corresponding to the differential surface; and comparing the cartilage thickness of the differential surface determined by directly adopting the threshold screening method with the expected cartilage parameter of the person to be detected, receiving the calculation result if the error is within the allowable error, and correcting by adopting the physiological anatomical feature method b below if the error exceeds the allowable error, wherein the allowable error is within +15%. The allowable error is preferably within +10%, more preferably within +5%.
b. When the cartilage contact surface or other tissues are difficult to distinguish points, namely, a point x ' is not existed and the curve change rate is larger than the gray curve distinguishing point, as shown in the S1 of fig. 2, the physiological anatomical feature method is adopted for correction, when the value of x is 0 to the expected cartilage parameter (0, max (H)) of a person to be detected, a point x ' is existed, and x ' satisfies x, so that the derivative of f (x) is 0 for the first time, namely, the point x "(as shown in fig. 4) when f (x) is at the bottom of the convex function for the first time is the position of the three-dimensional curved surface differential surface of the cartilage outer surface. In this process, correction parameters are added according to age, sex, weight and the like to correct the expected cartilage parameters of the person to be tested, wherein the expected cartilage parameters can be obtained by the following ways: acquiring a certain number of normal knee joint cartilage nuclear magnetic resonance medical image sequences with different ages and sexes to obtain the average thickness H of cartilage, and manually establishing cartilage model parameters and correction parameters such as age, sex, position and the like; a cartilage parameter database can be established, and the cartilage parameter database comprises a cartilage parameter database and a corresponding correction parameter table which are established by combining a physiological anatomy method with a past nuclear magnetic resonance medical image sequence; the cartilage parameter database comprises the thickness, density and volume of cartilage; the correction parameter table determines corresponding correction parameters according to the ages, sexes, weights and cartilage positions of different subjects. The expected cartilage parameters of the subject include the expected cartilage thickness of the subject, typically 2-3mm. The expected cartilage parameters of the person to be detected are obtained by selecting proper cartilage parameters from the cartilage parameter database through personal factors of the person to be detected and selecting proper correction parameters from the correction parameter table through calculation.
4. And (3) through a third step of circulating operation, obtaining three-dimensional curved surface differential surfaces of all the cartilage outer surfaces, and connecting the three-dimensional curved surface differential surfaces of all the cartilage outer surfaces to form the three-dimensional curved surface of the cartilage outer surfaces.
5. And combining the three-dimensional curved surface of the outer surface and the three-dimensional curved surface of the inner surface of the cartilage to obtain a three-dimensional image of the cartilage, and further calculating the volume, the surface area, the thickness and the like of the cartilage at a certain position according to the three-dimensional image.
For the cartilaginous tissue nuclear magnetic resonance medical image sequences of other different parts of the body, the gray scale curve distinguishing point can be adjusted to 45 to 55 gray scale values per pixel according to actual needs, and the derivative distinguishing point is-167 to-150.
The foregoing is only a preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the scope of the present invention should be included in the scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.
Claims (20)
1. A three-dimensional imaging method for cartilage segmentation of medical images comprises the following steps:
(1) Obtaining a nuclear magnetic resonance medical image sequence of a person to be detected, and establishing a three-dimensional surface of the cartilage and joint skeleton contact surface, namely a three-dimensional surface of the cartilage inner surface, by using a threshold screening method;
(2) Dividing the three-dimensional curved surface of the cartilage inner surface into a plurality of differential surfaces, namely the three-dimensional curved surface differential surfaces of the cartilage inner surface;
(3) Taking the three-dimensional curved surface differential surface of the inner surface of the cartilage as a vector from the bottom surface to the cartilage growth direction, namely an external normal vector;
(4) Taking a three-dimensional curved surface differential surface of the inner surface of the cartilage as a bottom surface and an external normal vector as a height direction as a differential body, and deducing a gray level distribution curve B=f (x) of the differential body along the height direction according to a nuclear magnetic resonance medical image sequence, wherein B represents gray level and x represents height;
(5) When the gray level distribution curve of the differential body along the height direction has a point x' so that the curve change rate is larger than the gray level curve distinguishing point, namely, when the derivative of f (x) is smaller than the derivative distinguishing point, the differential surface position of the cartilage far bone surface corresponding to the differential body can be directly determined, namely, the differential surface position of the cartilage far bone surface corresponding to the differential body is directly determined by adopting a threshold value screening method, and the obtained differential surface position is the position of the cartilage outer surface three-dimensional curved surface differential surface, so that the cartilage thickness corresponding to the differential surface is obtained;
(6) When the gray level distribution curve of the differential body along the height direction does not have one point x ' so that the curve change rate is larger than the gray level curve distinguishing point, correcting by adopting a physiological anatomical feature method, and when a point x ' between the value of x being 0 and the expected cartilage parameter thickness of a person to be detected exists, the x ' meets x ' so that the derivative of f (x) is 0 for the first time, the x ' is the position of the differential surface of the cartilage far bone surface corresponding to the differential body, namely the position of the differential surface of the three-dimensional curved surface of the cartilage outer surface, so that the cartilage thickness corresponding to the differential surface is obtained;
(7) And connecting all the cartilage outer surface three-dimensional curved surface differential surfaces to form a cartilage outer surface three-dimensional curved surface, and combining the cartilage inner surface three-dimensional curved surfaces to form a cartilage three-dimensional image.
2. The method of three-dimensional imaging for cartilage segmentation in medical imaging according to claim 1, wherein the expected cartilage parameter of the subject is obtained from a representative value of the cartilage parameter in medicine.
3. The method according to claim 1, wherein the expected cartilage parameters of the subject are calculated by selecting appropriate cartilage parameters from a cartilage parameter database and selecting appropriate correction parameters from a correction parameter table based on personal factors of the subject.
4. A medical imaging cartilage segmentation three-dimensional imaging method according to claim 3, characterized in that said cartilage parameter database comprises the establishment of a cartilage parameter database and a corresponding correction parameter table by means of physiological anatomy in combination with a sequence of past nuclear magnetic resonance medical imaging images.
5. The method of three-dimensional imaging of cartilage segmentation in medical imaging according to claim 3 or 4, characterized in that said cartilage parameter database comprises the thickness, density and volume of cartilage.
6. The method according to claim 3 or 4, wherein the correction parameter table determines the corresponding correction parameters according to the age, sex, weight and cartilage position of different subjects.
7. A medical imaging cartilage segmentation three-dimensional imaging method according to claim 2 or 3, characterized in that the expected cartilage parameter of the subject comprises an expected cartilage thickness of the subject of 2-3mm.
8. The method of claim 1, wherein the threshold screening method comprises binarizing the sequence of medical image by nuclear magnetic resonance.
9. The method for three-dimensional imaging of cartilage segmentation in medical imaging according to claim 1, wherein the three-dimensional curved surface of the inner surface of cartilage is the same curved surface as the outer surface of the articular bone covered by cartilage.
10. The method of three-dimensional imaging for cartilage segmentation in medical imaging according to claim 1, wherein the thickness of cartilage of the differential plane determined directly by the threshold screening method is compared with the expected cartilage parameters of the person to be detected, the calculation result is accepted if the error is within the allowable error, and if the error exceeds the allowable error, the calculation result is corrected by the physiological anatomical feature method, and the allowable error is within +15%.
11. The method of three-dimensional imaging for cartilage segmentation in medical imaging according to claim 10, wherein the tolerance is within +10%.
12. The method of three-dimensional imaging for cartilage segmentation in medical imaging according to claim 11, wherein said tolerance is within +5%.
13. The method for three-dimensional imaging of cartilage segmentation in medical imaging according to claim 1, wherein the three-dimensional curved differential surface of the cartilage inner surface is an arbitrary regular polygon.
14. The method for three-dimensional imaging of cartilage segmentation in medical imaging according to claim 13, wherein the three-dimensional curved differential surface of the cartilage inner surface is square.
15. The method for three-dimensional imaging of cartilage segmentation in medical imaging according to claim 1, wherein the number of divisions of the three-dimensional curved differential plane of the cartilage inner surface is 500 to 100000.
16. The method for three-dimensional imaging of cartilage segmentation in medical imaging according to claim 15, wherein the number of divisions of the three-dimensional curved differential plane of the cartilage inner surface is 5000 to 20000.
17. The method of claim 1, wherein the derivative differentiation point is any negative number between-167 and-150.
18. The method of claim 1, wherein the gray curve differentiating point is any integer value between 45-55 gray values per pixel.
19. The method of three-dimensional imaging for cartilage segmentation in medical imaging according to claim 18, wherein the thickness of cartilage at each differential plane is 0 or more.
20. A medical image cartilage segmentation three-dimensional imaging system comprises an image sequence acquisition module, an image threshold screening processing module, an image differential processing module, an image physiological anatomical feature correction module and a cartilage three-dimensional image synthesis module;
the image sequence acquisition module acquires a nuclear magnetic resonance medical image sequence of a person to be detected, and the image threshold screening processing module establishes a three-dimensional surface of the cartilage and joint skeleton contact surface, namely a three-dimensional surface of the cartilage inner surface by using a threshold screening method;
the image differential processing module divides the three-dimensional curved surface of the cartilage inner surface into a plurality of differential surfaces, namely the three-dimensional curved surface differential surface of the cartilage inner surface, takes the three-dimensional curved surface differential surface of the cartilage inner surface as a bottom surface to conduct vector in the cartilage growth direction, namely an external normal vector, takes the three-dimensional curved surface differential surface of the cartilage inner surface as the bottom surface and takes the external normal vector as a height direction as a differential body, and deduces a gray level distribution curve B=f (x) of the differential body along the height direction according to the nuclear magnetic resonance medical image sequence, wherein B represents gray level, and x represents height;
the image threshold screening processing module processes the obtained differential body, when the gray level distribution curve of the differential body along the height direction has a point x 'so that the curve change rate is larger than the gray level curve distinguishing point, namely, when the gray level distribution curve has a point x' so that the derivative of f (x) is a negative number smaller than the derivative distinguishing point, the differential surface position of the cartilage far bone surface corresponding to the differential body can be directly determined, namely, the differential surface position of the cartilage far bone surface corresponding to the differential body is directly determined by adopting a threshold screening method, and the obtained differential surface position is the position of the cartilage outer surface three-dimensional curved surface differential surface, so that the cartilage thickness corresponding to the differential surface is obtained;
when the gray level distribution curve of the differentiator along the height direction does not have a point x ' so that the curve change rate is larger than the gray level curve differentiating point, the image physiological anatomical feature correction module is utilized to process that a point x ' is present between the value of x being 0 and the expected cartilage parameter thickness of a person to be detected so that the derivative of f (x) is 0 for the first time, and then x ' is the differentiating surface position of the cartilage far bone surface corresponding to the differentiator, namely the position of the cartilage outer surface three-dimensional curved surface differentiating surface, so that the cartilage thickness corresponding to the differentiating surface is obtained;
and finally, connecting all the cartilage outer surface three-dimensional curved surface differential surfaces by a cartilage three-dimensional image synthesis module to form a cartilage outer surface three-dimensional curved surface, and combining the cartilage inner surface three-dimensional curved surface to form a cartilage three-dimensional image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811222055.1A CN109544673B (en) | 2018-10-19 | 2018-10-19 | Three-dimensional imaging method and system for cartilage segmentation of medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811222055.1A CN109544673B (en) | 2018-10-19 | 2018-10-19 | Three-dimensional imaging method and system for cartilage segmentation of medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109544673A CN109544673A (en) | 2019-03-29 |
| CN109544673B true CN109544673B (en) | 2023-06-23 |
Family
ID=65844120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811222055.1A Active CN109544673B (en) | 2018-10-19 | 2018-10-19 | Three-dimensional imaging method and system for cartilage segmentation of medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544673B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097546B (en) * | 2019-04-30 | 2021-04-13 | 北京大学第三医院 | Method and device for evaluating defects of knee joint cartilage tissues |
| CN110038180A (en) * | 2019-05-05 | 2019-07-23 | 张新 | A kind of medical orthopedic injury cleaning device, control system and control method |
| CN110827285B (en) * | 2019-11-15 | 2022-07-26 | 上海联影智能医疗科技有限公司 | Cartilage thickness detection method and device, computer equipment and readable storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456004A (en) * | 2013-07-30 | 2013-12-18 | 深圳市旭东数字医学影像技术有限公司 | Articular cartilage partitioning method and articular cartilage partitioning system based on image sheet structure enhancement |
| CN106202738A (en) * | 2016-07-14 | 2016-12-07 | 哈尔滨理工大学 | Method for building up based on hyperelastic solids phase behaviour articular cartilage tow phase model |
-
2018
- 2018-10-19 CN CN201811222055.1A patent/CN109544673B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103456004A (en) * | 2013-07-30 | 2013-12-18 | 深圳市旭东数字医学影像技术有限公司 | Articular cartilage partitioning method and articular cartilage partitioning system based on image sheet structure enhancement |
| CN106202738A (en) * | 2016-07-14 | 2016-12-07 | 哈尔滨理工大学 | Method for building up based on hyperelastic solids phase behaviour articular cartilage tow phase model |
Non-Patent Citations (1)
| Title |
|---|
| MR图像中髋关节软骨厚度的测量及校正;曹宇等;《天津大学学报》;20100228;第161-167页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109544673A (en) | 2019-03-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544673B (en) | Three-dimensional imaging method and system for cartilage segmentation of medical image | |
| KR101883258B1 (en) | Detection of anatomical landmarks | |
| CN110363765B (en) | Osteoporosis parameter automatic measurement method based on CT image | |
| CN112804943B (en) | Learning completion model creation method, brightness adjustment method, and image processing apparatus | |
| Hareendranathan et al. | Toward automatic diagnosis of hip dysplasia from 2D ultrasound | |
| Baka et al. | Evaluation of automated statistical shape model based knee kinematics from biplane fluoroscopy | |
| CN107016683A (en) | The level set hippocampus image partition method initialized based on region growing | |
| Mahmood et al. | Image segmentation methods and edge detection: An application to knee joint articular cartilage edge detection | |
| Furuo et al. | Automatic benign and malignant estimation of bone tumors using deep learning | |
| CN112767265A (en) | Method, system and computer readable storage medium for correcting segmented image of removing metal artifact of CT image | |
| CN111292306A (en) | Knee joint CT and MR image fusion method and device | |
| Santhoshini et al. | Automatic segmentation of femur bone features and analysis of osteoporosis | |
| Tsunoda et al. | Pseudo-normal image synthesis from chest radiograph database for lung nodule detection | |
| CN103854288B (en) | Cruciate ligament segmentation method and system | |
| CN115526798A (en) | Medical X-ray video sequence image denoising method and system and readable storage medium | |
| CN107408301B (en) | Segmentation of objects in image data using channel detection | |
| Fischer et al. | Relationship between pelvic morphology and functional parameters in standing position for patient-specific cup planning in THA | |
| CN114119798A (en) | Radiographic image processing method and device based on respiratory motion | |
| CN110801204A (en) | Balance detection method based on human body frame | |
| O’Neill et al. | Segmentation of cam-type femurs from CT scans | |
| Wei et al. | Segmentation of lung lobes in clinical CT images | |
| Ouadahi et al. | Automatic êbroglandular tissue segmentation in breast MRI using a deep learning approach | |
| CN110246144A (en) | A kind of the blood vessel Enhancement Method and system of lung CT image | |
| Kamiya et al. | Automated recognition of the psoas major muscles on X-ray CT images | |
| Desai et al. | Arytenoid cartilage feature point detection using laryngeal 3D CT images in Parkinson's disease |
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 |