CN106875376A - The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model - Google Patents
The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model Download PDFInfo
- Publication number
- CN106875376A CN106875376A CN201611241396.4A CN201611241396A CN106875376A CN 106875376 A CN106875376 A CN 106875376A CN 201611241396 A CN201611241396 A CN 201611241396A CN 106875376 A CN106875376 A CN 106875376A
- Authority
- CN
- China
- Prior art keywords
- model
- shape
- parameters
- projection
- image
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000010276 construction Methods 0.000 title claims abstract description 10
- 238000005070 sampling Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 239000004576 sand Substances 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000001356 surgical procedure Methods 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 abstract description 2
- 238000007796 conventional method Methods 0.000 abstract 1
- 238000002591 computed tomography Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002675 image-guided surgery Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The present invention relates to the construction method and lumbar vertebrae method for registering of a kind of lumbar vertebrae registration prior model.The present invention carries out DRR projections by substantial amounts of lumbar vertebrae CT samples, obtains projected image sample, and to projected image sample extraction characteristic point, and then build the prior model of lumbar vertebrae registration.Lumbar vertebrae is being carried out with punctual, the lumbar vertebrae CT images of patient is first being obtained before surgery, and using the correlation of height between shape and projective parameter, set up attitude mode；After the form parameter for obtaining lumbar vertebrae by X ray images in the operation, its projective parameter directly can be obtained by attitude mode, so as to complete registration.Avoid and search for a projected image for best match degree in conventional method in substantial amounts of projected image so that the present invention can efficiently carry out the 3D/2D registrations of lumbar vertebrae, while precision is ensured, meet the requirement of high real-time in operation.
Description
Technical Field
The invention relates to the field of image processing, in particular to a construction method of a lumbar vertebra registration prior model and a lumbar vertebra registration method.
Background
Image guidance is required by the surgeon during spinal surgery to enable the position and posture of the spine and the specific location of the surgical implant (e.g., screws) to be known. However, since intraoperative Computed Tomography (CT) equipment is expensive and has only a few hospital configurations, preoperative CT and intraoperative X-ray (X-ray) images are often used to assist the surgeon in surgery. The intraoperative X-ray can provide two-dimensional images, and the intraoperative X-ray and preoperative CT are required to be registered to obtain three-dimensional information, so that 3D/2D image registration is a key problem in image-guided surgery.
The current 3D/2D registration generally projects 3D data onto a 2D plane, then performs 2D/2D registration, and finally finds an optimal projection parameter in a projection parameter space so that the projection image and the target image can be optimally registered. However, due to the high spatial complexity of the projection parameters, the 3D/2D registration method based on the search strategy is computationally expensive. Some of these treatments require significant manual intervention, which also results in inefficiencies.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a construction method of a lumbar vertebra registration prior model and a lumbar vertebra registration method, which greatly improve the registration efficiency while ensuring the precision and meet the requirement of real-time registration in the operation.
The invention provides a construction method of a lumbar vertebra registration prior model and a lumbar vertebra registration method, which comprise the following steps:
step A1, performing Digital Reconstruction Radiographic (DRR) projection on a preset number of lumbar vertebra CT image samples to obtain projection image samples, and extracting feature points from the projection image samples;
step A2, establishing a statistical shape model according to the characteristic points extracted in the step A1;
step A3, establishing a statistical gray model;
and step A4, establishing a combined model by connecting the shape model parameters and the gray model parameters in series.
Preferably, step a2 is specifically:
mapping the extracted characteristic points to a common two-dimensional coordinate system by using a Poisson analysis method, so that the gravity center of each projection image sample characteristic point is coincided with the origin of coordinates, and the influence of translation, scaling and rotation on different projection image sample characteristic points is eliminated; obtaining orthonormal basis P of shape model by Principal Component Analysis (PCA) for feature points mapped to common two-dimensional coordinate systemsThen, the feature point shape model of each projection image sample is:
wherein,is the average shape, which is the average position of each feature point, bsAre shape model parameters.
Preferably, step a3 is specifically:
carrying out shape standardization on each projection image sample so that the characteristic points of the projection image samples are deformed to an average shape; sampling the image subjected to shape standardization in an area covered by the shape model, and normalizing sampling points to enable the gray average value to be 0 and the variance to be 1; obtaining an appearance model P by principal component analysisgAnd then, the gray model g of the characteristic point of each projection image sample is as follows:
wherein,is average gray scale, PgBeing the orthonormal basis of the gray model, bgAre the gray scale model parameters.
Preferably, step a4 is specifically:
step A41, shape model parameter bsAnd a gray scale model parameter bgAre connected in series with each other and are connected in series,
wherein, WsThe diagonal matrix is used for balancing the dimension of the shape model and the gray model parameter;
step A42, obtaining a combined model by using a principal component analysis method for the parameters of the shape model and the gray model which are connected in series:
since the mean value of the shape model parameter and the gradation model parameter is 0, the mean value0, then there are:
b＝Qc，
wherein c is a combined modelQ is the orthogonal basis of the joint model, QsBeing orthogonal bases of shape models, QgIs an orthogonal basis for the gray scale model;
step A43, using the joint model parameter c to express the shape x and the gray scale g:
wherein,is an average shape, PsIs an orthonormal basis for the shape model,is average gray scale, PgIs the orthonormal basis of the gray scale model.
Preferably, a triangle deformation algorithm is used when the shape normalization is performed on each projection image sample.
The invention also provides a lumbar vertebra registration method, which comprises the following steps:
step B1, acquiring a target lumbar vertebra CT image before operation, and performing DRR projection on the CT image to generate a preset number of DRR images;
and step B2, segmenting the target lumbar vertebra and extracting shape parameters for each DRR image according to a preset initial position and the lumbar vertebra registration prior model.
Step B3, establishing a posture model according to the projection parameters of the DRR image and the corresponding shape parameters;
step B4, acquiring an X-ray image in the operation process, segmenting the target lumbar vertebra on the X-ray image according to the lumbar vertebra registration prior model, and extracting shape parameters;
and B5, obtaining corresponding projection parameters according to the shape parameters of the target lumbar vertebra obtained on the X-ray image and the posture model obtained in the step B3, and thus completing registration.
Preferably, the establishing the attitude model in step B3 specifically includes:
using the linear model R ═ MB, the pose model was obtained:
M＝RBT(BBT)-1。
wherein R is a projection parameter, B is a shape parameter, and M is a pose model.
Preferably, step B5 is specifically:
calculating projection parameters corresponding to the X-ray image according to the attitude model and the shape parameters obtained in the step B4:
RX-ray＝MBX-ray，
wherein B isX-rayM is a pose model for the shape parameters of the X-ray image extracted in step B4.
Preferably, in steps B2 and B4, the target lumbar vertebrae are segmented and the shape parameters are extracted using the AAM algorithm.
The invention establishes a two-dimensional statistical model of lumbar vertebrae, and learns an attitude model by utilizing the high correlation between the shape model and the projection parameters. After the shape parameters of the lumbar vertebra are obtained in the operation, the projection parameters can be directly obtained through the posture model, so that the condition that a projection image with the optimal matching degree is searched in a large number of projection images in the traditional method is avoided, the 3D/2D registration of the lumbar vertebra can be efficiently carried out, the precision is ensured, and the requirement of high real-time performance in the operation is met.
Drawings
FIG. 1 is a schematic flow chart of a lumbar vertebra registration prior model construction method in this embodiment;
fig. 2 is a schematic diagram of feature point extraction performed on a DRR projection image in the present embodiment;
fig. 3 is a flowchart illustrating the lumbar vertebrae registration method in the present embodiment.
Detailed Description
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and are not intended to limit the scope of the present invention.
In this embodiment, an algorithm platform Matlab R2014b is run on a PC configured as an intel (R) core (tm) i5-2400CPU @3.10GHz, 4G memory.
The invention provides a construction method of a lumbar vertebra registration prior model and a lumbar vertebra registration method, as shown in figure 1, the construction method comprises the following steps:
step A1, carrying out DRR projection on a preset number of lumbar vertebra CT image samples to obtain projection image samples, and extracting characteristic points from the projection image samples;
step A2, establishing a statistical shape model according to the characteristic points extracted in the step A1;
step A3, establishing a statistical gray model;
and step A4, establishing a combined model by connecting the shape model parameters and the gray model parameters in series.
In this embodiment, when the statistical shape model is established, the model on the two-dimensional image is selected to be established because the feature points of the two-dimensional image are easier to mark and acquire. As shown in fig. 2, 93 feature points are extracted from each DRR image, and the overall shape is as shown in a sub-image a, and the overall shape is mainly divided into 6 parts: vertebral body contour (shown in sub-figure b), central grayscale depression (shown in sub-figure c), pedicles close to physiologic structures (shown in sub-figures d and e), and left and right inferior chamfer angles of vertebral bodies (shown in sub-figures f and g).
In this embodiment, step a2 specifically includes:
mapping the extracted characteristic points to a common two-dimensional coordinate system by using a Poisson analysis method, so that the gravity center of each projection image sample characteristic point is coincided with the origin of coordinates, and the influence of translation, scaling and rotation on different projection image sample characteristic points is eliminated; obtaining the orthonormal basis P of the shape model by using principal component analysis method for the feature points mapped to the common two-dimensional coordinate systemsThen, the feature point shape model of each projection image sample is as shown in formula (1):
wherein,is the average shape, which is the average position of each feature point, bsAre shape model parameters.
In this embodiment, step a3 specifically includes:
carrying out shape standardization on each projection image sample so that the characteristic points of the projection image samples are deformed to an average shape; sampling the image subjected to shape standardization in an area covered by the shape model, and normalizing sampling points to enable the gray average value to be 0 and the variance to be 1; obtaining an appearance model P by principal component analysisgThen, the gray model g of the feature point of each projection image sample is as shown in formula (2):
wherein,is average gray scale, PgBeing the orthonormal basis of the gray model, bgAre the gray scale model parameters.
In this embodiment, step a4 specifically includes:
step A41, shape model parameter bsAnd a gray scale model parameter bgIn series, as shown in equation (3):
wherein, WsThe diagonal matrix is used for balancing the dimension of the shape model and the gray model parameter;
step A42, obtaining a combined model by using principal component analysis method for the shape model and the gray model parameters connected in series, as shown in formula (4):
since the mean value of the shape model parameter and the gradation model parameter is 0, the mean valueIs 0, then as shown in equation (5):
b＝Qc (5)
wherein, Q is the orthogonal base of the combined model, and the Q value is shown in formula (6):
Qsis an orthogonal basis for the shape model,Qgis an orthogonal base of the gray model, and c is a parameter of the combined model;
step A43, using the joint model parameter c to express the shape x and the gray scale g, as shown in equations (7) and (8), respectively:
wherein,is an average shape, PsIs an orthonormal basis for the shape model,is average gray scale, PgIs the orthonormal basis of the gray scale model.
In this embodiment, a triangle deformation algorithm is used when the shape of each projection image sample is normalized.
The invention also provides a lumbar vertebra registration method, which is used for acquiring the lumbar vertebra CT image of the patient to be operated before the operation, processing the CT image and providing information for the segmentation and registration in the operation. This allows more computational work to be done preoperatively, allowing intraoperative segmentation and registration to be done in a more efficient manner, thereby meeting real-time requirements.
As shown in fig. 3, the method comprises the following steps:
step B1, acquiring a target lumbar vertebra CT image before operation, and performing DRR projection on the CT image to generate a preset number of DRR images;
and step B2, segmenting the target lumbar vertebra and extracting shape parameters for each DRR image according to a preset initial position and the lumbar vertebra registration prior model.
Step B3, establishing a posture model according to the projection parameters of the DRR image and the corresponding shape parameters;
step B4, acquiring an X-ray image in the operation process, segmenting the target lumbar vertebra on the X-ray image according to the lumbar vertebra registration prior model, and extracting shape parameters;
and B5, obtaining corresponding projection parameters according to the shape parameters of the target lumbar vertebra obtained on the X-ray image and the posture model obtained in the step B3, and thus completing registration.
In this embodiment, the establishing the attitude model in step B3 specifically includes:
using the linear model R ═ MB, the attitude model is obtained, as shown in equation (9):
M＝RBT(BBT)-1(9)
wherein R is a projection parameter, B is a shape parameter, and M is a pose model.
In this embodiment, step B5 specifically includes:
calculating a projection parameter corresponding to the X-ray image according to the attitude model and the shape parameter obtained in the step B4, wherein the projection parameter is a required registration result; the calculation method is shown in formula (10):
RX-ray＝MBX-ray(10)
wherein B isX-rayM is a pose model for the shape parameters of the X-ray image extracted in step B4.
In this embodiment, in the steps B2 and B4, the aam (active application model) algorithm is used to segment the target lumbar vertebrae and extract the shape parameters.
Those of skill in the art will appreciate that the method steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described above generally in terms of their functionality in order to clearly illustrate the interchangeability of electronic hardware and software. Whether such functionality is implemented as electronic hardware or software depends upon the particular application and design constraints imposed on the 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.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can fall into the protection scope of the invention.
Claims (9)
1. A construction method of a lumbar vertebra registration prior model and a lumbar vertebra registration method are characterized by comprising the following steps:
step A1, carrying out DRR projection on a preset number of lumbar vertebra CT image samples to obtain projection image samples, and extracting characteristic points from the projection image samples;
step A2, establishing a statistical shape model according to the characteristic points extracted in the step A1;
step A3, establishing a statistical gray model;
and step A4, establishing a combined model by connecting the shape model parameters and the gray model parameters in series.
2. The method according to claim 1, wherein step a2 is specifically:
mapping the extracted characteristic points to a common two-dimensional coordinate system by using a Poisson analysis method, so that the gravity center of each projection image sample characteristic point is coincided with the origin of coordinates, and the influence of translation, scaling and rotation on different projection image sample characteristic points is eliminated; obtaining the orthonormal basis P of the shape model by using principal component analysis method for the feature points mapped to the common two-dimensional coordinate systemsThen, the feature point shape model of each projection image sample is:
wherein,is the average shape, which is the average position of each feature point, bsAre shape model parameters.
3. The method according to claim 2, wherein step a3 is specifically:
carrying out shape standardization on each projection image sample so that the characteristic points of the projection image samples are deformed to an average shape; sampling the image subjected to shape standardization in an area covered by the shape model, and normalizing sampling points to enable the gray average value to be 0 and the variance to be 1; obtaining an appearance model P by principal component analysisgAnd then, the gray model g of the characteristic point of each projection image sample is as follows:
wherein,is average gray scale, PgBeing the orthonormal basis of the gray model, bgAre the gray scale model parameters.
4. The method according to claim 3, wherein step A4 is specifically:
step A41, shape model parameter bsAnd a gray scale model parameter bgAre connected in series with each other and are connected in series,
wherein, WsThe diagonal matrix is used for balancing the dimension of the shape model and the gray model parameter;
step A42, obtaining a combined model by using a principal component analysis method for the parameters of the shape model and the gray model which are connected in series:
since the mean value of the shape model parameter and the gradation model parameter is 0, the mean value0, then there are:
b＝Qc，
wherein c is a parameter of the joint model, Q is an orthogonal base of the joint model, and Q issBeing orthogonal bases of shape models, QgIs an orthogonal basis for the gray scale model;
step A43, using the joint model parameter c to express the shape x and the gray scale g:
wherein,is an average shape, PsIs an orthonormal basis for the shape model,is average gray scale, PgIs the orthonormal basis of the gray scale model.
5. The method of claim 3 wherein a triangle warping algorithm is used to shape normalize each sample of the projection images.
6. A lumbar registration method, comprising the steps of:
step B1, acquiring a target lumbar vertebra CT image before operation, and performing DRR projection on the CT image to generate a preset number of DRR images;
step B2, for each DRR image, segmenting a target lumbar vertebra and extracting shape parameters according to a preset initial position and the lumbar vertebra registration prior model constructed by the method of any one of claims 1-5;
step B3, establishing a posture model according to the projection parameters of the DRR image and the corresponding shape parameters;
step B4, acquiring an X-ray image in the operation process, segmenting the target lumbar vertebra on the X-ray image based on the lumbar vertebra registration prior model in the step B2, and extracting shape parameters;
and B5, obtaining corresponding projection parameters according to the shape parameters of the target lumbar vertebra obtained on the X-ray image and the posture model obtained in the step B3, and thus completing registration.
7. The method according to claim 6, wherein the establishing of the pose model in step B3 includes:
using the linear model R ═ MB, the pose model was obtained:
M＝RBT(BBT)-1，
wherein R is a projection parameter, B is a shape parameter, and M is a pose model.
8. The method according to claim 7, wherein step B5 is specifically:
calculating projection parameters corresponding to the X-ray image according to the attitude model and the shape parameters obtained in the step B4:
RX-ray＝MBX-ray；
wherein, BX-rayM is a pose model for the shape parameters of the X-ray image extracted in step B4.
9. The method of claim 6, wherein in the steps B2 and B4, the AAM algorithm is used to segment the target lumbar vertebra and extract the shape parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611241396.4A CN106875376B (en) | 2016-12-29 | 2016-12-29 | The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611241396.4A CN106875376B (en) | 2016-12-29 | 2016-12-29 | The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106875376A true CN106875376A (en) | 2017-06-20 |
| CN106875376B CN106875376B (en) | 2019-10-22 |
Family
ID=59164930
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611241396.4A Active CN106875376B (en) | 2016-12-29 | 2016-12-29 | The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106875376B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846830A (en) * | 2018-05-25 | 2018-11-20 | 妙智科技（深圳）有限公司 | The method, apparatus and storage medium be automatically positioned to lumbar vertebrae in CT |
| CN112989081A (en) * | 2021-05-20 | 2021-06-18 | 首都医科大学附属北京安贞医院 | Method and device for constructing digital reconstruction image library |
| CN117237426A (en) * | 2023-09-18 | 2023-12-15 | 北京大学第三医院（北京大学第三临床医学院） | Vertebra registration method based on lumbar vertebra double-oblique X-ray film |
| WO2024016248A1 (en) * | 2022-07-21 | 2024-01-25 | 中国人民解放军总医院第一医学中心 | Image registration system and method for femoral surgery |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1931097A (en) * | 2006-09-30 | 2007-03-21 | 南方医科大学 | Human body orthopedic navigation system |
| US7653226B2 (en) * | 2004-04-21 | 2010-01-26 | Siemens Medical Solutions Usa, Inc. | Flexible generation of digitally reconstructed radiographs |
| CN102208117A (en) * | 2011-05-04 | 2011-10-05 | 西安电子科技大学 | Method for constructing vertebral three-dimensional geometry and finite element mixture model |
| CN102968633A (en) * | 2012-10-29 | 2013-03-13 | 东软飞利浦医疗设备系统有限责任公司 | Lumbar vertebra identification method and device based on computed tomography (CT) side position positioning sheet |
| CN103310219A (en) * | 2012-03-08 | 2013-09-18 | 佳能株式会社 | Method and equipment for precision evaluation of object shape registration, and method and equipment for registration |
| CN103514441A (en) * | 2013-09-21 | 2014-01-15 | 南京信息工程大学 | Facial feature point locating tracking method based on mobile platform |
| US20160260220A1 (en) * | 2015-03-05 | 2016-09-08 | Broncus Medical Inc. | Gpu-based system for performing 2d-3d deformable registration of a body organ using multiple 2d fluoroscopic views |
-
2016
- 2016-12-29 CN CN201611241396.4A patent/CN106875376B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7653226B2 (en) * | 2004-04-21 | 2010-01-26 | Siemens Medical Solutions Usa, Inc. | Flexible generation of digitally reconstructed radiographs |
| CN1931097A (en) * | 2006-09-30 | 2007-03-21 | 南方医科大学 | Human body orthopedic navigation system |
| CN102208117A (en) * | 2011-05-04 | 2011-10-05 | 西安电子科技大学 | Method for constructing vertebral three-dimensional geometry and finite element mixture model |
| CN103310219A (en) * | 2012-03-08 | 2013-09-18 | 佳能株式会社 | Method and equipment for precision evaluation of object shape registration, and method and equipment for registration |
| CN102968633A (en) * | 2012-10-29 | 2013-03-13 | 东软飞利浦医疗设备系统有限责任公司 | Lumbar vertebra identification method and device based on computed tomography (CT) side position positioning sheet |
| CN103514441A (en) * | 2013-09-21 | 2014-01-15 | 南京信息工程大学 | Facial feature point locating tracking method based on mobile platform |
| US20160260220A1 (en) * | 2015-03-05 | 2016-09-08 | Broncus Medical Inc. | Gpu-based system for performing 2d-3d deformable registration of a body organ using multiple 2d fluoroscopic views |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108846830A (en) * | 2018-05-25 | 2018-11-20 | 妙智科技（深圳）有限公司 | The method, apparatus and storage medium be automatically positioned to lumbar vertebrae in CT |
| CN112989081A (en) * | 2021-05-20 | 2021-06-18 | 首都医科大学附属北京安贞医院 | Method and device for constructing digital reconstruction image library |
| WO2024016248A1 (en) * | 2022-07-21 | 2024-01-25 | 中国人民解放军总医院第一医学中心 | Image registration system and method for femoral surgery |
| CN117237426A (en) * | 2023-09-18 | 2023-12-15 | 北京大学第三医院（北京大学第三临床医学院） | Vertebra registration method based on lumbar vertebra double-oblique X-ray film |
| CN117237426B (en) * | 2023-09-18 | 2024-03-22 | 北京大学第三医院（北京大学第三临床医学院） | Vertebra registration method based on lumbar vertebra double-oblique X-ray film |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106875376B (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11657518B2 (en) | Method for deformable 3D-2D registration using multiple locally rigid registrations | |
| Markelj et al. | Robust gradient-based 3-D/2-D registration of CT and MR to X-ray images | |
| Zheng et al. | A 2D/3D correspondence building method for reconstruction of a patient-specific 3D bone surface model using point distribution models and calibrated X-ray images | |
| JP5486197B2 (en) | Vertebral center detecting device, method and program | |
| CN106875376B (en) | The construction method and lumbar vertebrae method for registering of lumbar vertebrae registration prior model | |
| Zheng | Statistical shape model‐based reconstruction of a scaled, patient‐specific surface model of the pelvis from a single standard AP x‐ray radiograph | |
| Ketcha et al. | Multi-stage 3D–2D registration for correction of anatomical deformation in image-guided spine surgery | |
| WO2008141996A2 (en) | Semi-automatic contour detection | |
| CN112509022A (en) | Non-calibration object registration method for preoperative three-dimensional image and intraoperative perspective image | |
| Zheng et al. | Scaled, patient-specific 3D vertebral model reconstruction based on 2D lateral fluoroscopy | |
| CN109166177A (en) | Air navigation aid in a kind of art of craniomaxillofacial surgery | |
| Kurazume et al. | 3D reconstruction of a femoral shape using a parametric model and two 2D fluoroscopic images | |
| Noser et al. | A method for assessing 3D shape variations of fuzzy regions and its application on human bony orbits | |
| US10078906B2 (en) | Device and method for image registration, and non-transitory recording medium | |
| JP2012529319A (en) | Improved registration of body part shapes from images | |
| Chaoui et al. | Recognition-based segmentation and registration method for image guided shoulder surgery | |
| Novosad et al. | Three-dimensional (3-D) reconstruction of the spine from a single X-ray image and prior vertebra models | |
| Zheng | Statistically deformable 2D/3D registration for estimating post-operative cup orientation from a single standard AP X-ray radiograph | |
| Rasoulian et al. | A statistical multi-vertebrae shape+ pose model for segmentation of CT images | |
| Zheng | Statistically deformable 2D/3D registration for accurate determination of post-operative cup orientation from single standard X-ray radiograph | |
| Dong et al. | Automatic extraction of proximal femur contours from calibrated X‐ray images using 3D statistical models: an in vitro study | |
| Chen et al. | An Optimization-based Baseline for Rigid 2D/3D Registration Applied to Spine Surgical Navigation Using CMA-ES | |
| Zheng et al. | 3-D reconstruction of a surface model of the proximal femur from digital biplanar radiographs | |
| Wodzinski et al. | Application of demons image registration algorithms in resected breast cancer lodge localization | |
| Zheng et al. | 2D/3D reconstruction of a scaled lumbar vertebral model from a single fluoroscopic image |
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 |