CN102903117A - 3D (three-dimensional) image registration method and device based on conformal geometric algebra - Google Patents
3D (three-dimensional) image registration method and device based on conformal geometric algebra Download PDFInfo
- Publication number
- CN102903117A CN102903117A CN2012104093237A CN201210409323A CN102903117A CN 102903117 A CN102903117 A CN 102903117A CN 2012104093237 A CN2012104093237 A CN 2012104093237A CN 201210409323 A CN201210409323 A CN 201210409323A CN 102903117 A CN102903117 A CN 102903117A
- Authority
- CN
- China
- Prior art keywords
- image
- registration
- floating image
- eigenvector
- unique point
- 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.)
- Pending
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a 3D (three-dimensional) image registration method and device based on conformal geometric algebra. The 3D image registration method comprises the following steps of: rebuilding a position relation restrain problem of a 3D medical image by using the conformal geometric algebra, analyzing conformal geometric transformation of the medical image, constructing a new 3D medical image registration similarity measure, and proposing a 3D medical image registration algorithm for 3D registration of CT (Computed Tomography) and MR_T1 (Magnetic Resonance) images. According to the three-dimensional image registration method and the three-dimensional image registration device, the direct alignment of 3D data is realized, the 3D positions of tissues and organs can be better positioned, the registration result is more direct, the image after registration is clearer, and the registration precision is higher.
Description
Technical field
The present invention relates to field of medical image processing, in particular a kind of 3-D view method for registering and device based on conformal geometric algebra.
Background technology
From data dimension, the registration of medical image can be divided into 2D/2D, three kinds of 2D/3D and 3D/3D.3D/3D registration, registration data are stereo data, and the geometric transformation type is more, more complicated, and the parameter difficulty is sought in its optimization to be increased, the easier local optimum that is absorbed in, and also the space complexity of whole registration process and time complexity will be far above the 2D/2D registrations.In the medical applications such as neurosurgery navigation, Medical Image Processing is very crucial, but also is faced with a lot of problems, especially aspect 3D/3D type registration.From pertinent literature, can find the method for much the dealing with problems reference that is worthy of our study.Such as Hsu and Loew a kind of Full-automatic multimould attitude medical image 3D method for registering that extracts based on layered characteristic has been proposed first; Non-homogeneousization of the human B batten deformable bodys such as Li Wenlong replace general cubic B-spline deformable body to be described as the nonlinear motion of picture tissue, have proposed the non-linear medical figure registration based on the 3D of free deformation; The people such as Harmouche have set up a kind of hinge model and have been used for the MR of backbone and the three-dimensional registration of X-ray by calculating the intervertebral distortion.
In the registration of medical image, mostly existing 3D registration approach is that the corresponding relation of hypothesis between the known registration point analyzed and how is out of shape, or known and how to be out of shape, only need to obtain the corresponding relation of registration point, be difficult to describe the solid position of registration, so that unintelligible through the medical image stereo display of registration, the precision of registration is not high.
Therefore, prior art has yet to be improved and developed.
Summary of the invention
The technical problem to be solved in the present invention is, for the defects of prior art, provides a kind of 3-D view method for registering and device based on conformal geometric algebra, in order to make the image of registration more clear, registration accuracy is higher.
The technical scheme that technical solution problem of the present invention adopts is as follows:
A kind of 3-D view method for registering based on conformal geometric algebra wherein, may further comprise the steps:
A, selected be used for registration with reference to image and floating image, carry out rim detection to described with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
B, according to described unique point with reference to image and floating image, under the conformal geometric algebra framework, generate the eigenvector of described unique point;
C, the eigenvector of the unique point of described floating image is carried out several rotation and translation, and the similar of eigenvector of calculating described unique point with reference to image and described floating image after each rotation and the translation estimated;
D, when the described similar number of times of estimating less than a reservation threshold or rotation and translation is greater than or equal to pre-determined number, export the eigenvector of described floating image unique point at this moment, floating image behind the generation registration, and with the floating image behind the registration and described with reference to image co-registration, obtain final registering images.
Described 3-D view method for registering based on conformal geometric algebra, wherein, described steps A also comprises: process described partition coefficient with reference to image and floating image and range of size scope consistent in advance.
Described 3-D view method for registering based on conformal geometric algebra wherein, adopts the canny operator to carry out rim detection to described with reference to image and floating image in the described steps A.
Described 3-D view method for registering based on conformal geometric algebra, wherein, described step C also comprises:
C1, obtain on the described floating image with described with reference to the corresponding closest approach of Characteristic of Image point, and according to the eigenvector of described closest approach, calculate rotation operator and translation operator;
C2, according to described rotation operator and translation operator, the eigenvector of the unique point of floating image is rotated and translation accordingly.
Described 3-D view method for registering based on conformal geometric algebra, wherein, similar among the described step C estimated by following formula and calculates:
Wherein, S
MNDescribedly similarly to estimate X
iAnd Y
jBe respectively the eigenvector of the unique point of described floating image and reference picture, Si is Xi and Yj inner product minimum value, and i and j are natural number.
Described 3-D view method for registering based on conformal geometric algebra, wherein, described step D also comprises:
When the described similar number of times during less than pre-determined number that is greater than or equal to described reservation threshold and rotation and translation of estimating, continuation is rotated and translation the eigenvector of the unique point of described floating image, until describedly similarly estimate number of times less than a reservation threshold or rotation and translation more than or equal to described pre-determined number.
Described 3-D view method for registering based on conformal geometric algebra, wherein, described reservation threshold is 1.0 * 10
-3, described pre-determined number is 1000.
A kind of 3-D view registration apparatus based on conformal geometric algebra, wherein, described device comprises:
The feature point extraction unit, be used for to selected be used for registration carry out rim detection with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
The eigenvector converting unit is used for the described unique point with reference to image and floating image according to the extraction of described feature point extraction unit, under the conformal geometric algebra framework, generates the eigenvector of described unique point;
The rotation translation unit is used for the eigenvector of described unique point is rotated peaceful movement calculation;
Similarly estimate computing unit, be used for calculating described rotation translation unit and rotate the similar of eigenvector of peaceful movement described unique point with reference to image and described floating image after calculating at every turn and estimate;
Registration unit, be used for when the described similar number of times of estimating less than a reservation threshold or rotation and translation is greater than or equal to pre-determined number, export the eigenvector of described floating image unique point at this moment, floating image behind the generation registration, and with the floating image behind the registration and described with reference to image co-registration, obtain final registering images.
Described 3-D view registration apparatus based on conformal geometric algebra, wherein, described device also comprises:
The image pretreatment unit to selected processing with reference to image and floating image, is processed consistent with range of size the selected resolution with reference to image and floating image in advance.
3-D view method for registering and device based on conformal geometric algebra provided by the present invention, realized the direct alignment of three-dimensional data, the three-dimensional position of position tissue organ makes the image of registration more clear preferably, registration accuracy is higher, and it is more accurate that image shows.
Description of drawings
Fig. 1 is the process flow diagram of the 3-D view method for registering based on conformal geometric algebra provided by the invention.
Fig. 2 is the front 8 layers of figure of CT among the embodiment of the 3-D view method for registering based on conformal geometric algebra provided by the invention.
Fig. 3 is the front 8 layers of figure of MR_T1 among the embodiment of the 3-D view method for registering based on conformal geometric algebra provided by the invention.
Fig. 4 is the three-dimensional brain model according to the different angles of CT figure reconstruction shown in Figure 2.
Fig. 5 is the three-dimensional brain model according to the different angles of MR_T1 figure reconstruction shown in Figure 3.
Fig. 6 is the 3 d effect graph through different angles after the CT of registration and the MR_T1 fusion.
Fig. 7 is the partially sliced figure of the described 3 d effect graph of Fig. 6.
Fig. 8 is the structured flowchart of the 3-D view registration apparatus based on conformal geometric algebra provided by the invention.
Fig. 9 is the structured flowchart of a preferred embodiment of the 3-D view registration apparatus based on conformal geometric algebra provided by the invention.
Embodiment
The present invention utilizes conformal geometric algebra to rebuild the position relationship restricted problem of 3D medical image, analyzed the conformal geometry conversion of medical image, constructed that a kind of new 3D medical figure registration is similar to be estimated, based on this 3D Medical Image Registration Algorithm has been proposed, the 3D registration that is used for CT and MR_T1 image, so as to realize the direct alignment of three-dimensional data, preferably the position tissue organ three-dimensional position and embody intuitively registration results.
For making purpose of the present invention, technical scheme and advantage clearer, clear and definite, developing simultaneously referring to accompanying drawing, the present invention is described in more detail for embodiment.Should be appreciated that specific embodiment described herein only in order to explain the present invention, is not intended to limit the present invention.
Referring to Fig. 1, Fig. 1 is the process flow diagram of the 3-D view method for registering based on conformal geometric algebra provided by the invention, may further comprise the steps:
Step S100, selected be used for registration with reference to image and floating image, carry out rim detection to described with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
Step S200, according to described unique point with reference to image and floating image, under the conformal geometric algebra framework, generate the eigenvector of described unique point;
Step S300, the eigenvector of the unique point of described floating image is carried out several rotation and translation, and the similar of eigenvector of calculating described unique point with reference to image and described floating image after each rotation and the translation estimated;
Step S400, when the described similar number of times of estimating less than a reservation threshold or rotation and translation is greater than or equal to pre-determined number, export the eigenvector of described floating image unique point at this moment, floating image behind the generation registration, and with the floating image behind the registration and described with reference to image co-registration, obtain final registering images.
Below in conjunction with specific embodiment above-mentioned steps is described in detail and describes.
At first, select the reference picture that needs registration
And floating image
, and reference picture and floating image carried out pre-service, make that the resolution of the two reaches consistent with range of size in the effective coverage, so that registration is more accurate.
In step S100, to the described image of examining
And floating image
Adopt the canny operator to carry out rim detection, obtain corresponding edge contour, the edge contour according to obtaining utilizes image segmentation algorithm, extracts reference picture
And floating image
In the set of unique point, be respectively
With
In order to realize better registration, the present invention is further processed above-mentioned unique point, is specially, and under conformal geometric algebra (CGA) framework, is preferably
The space will
With
Convert to
Form, therefore, after the conversion
,
Afterwards to the eigenvector of the characteristic point of floating image
Carry out the rotation peace movement of K iteration and calculate, at first calculate rotation operator
And translation operator
, wherein, K
Min=0, K
Max=1000,
With
The rotation operator and the translation operator that represent respectively the K time iteration.When calculating,
With
Pass through formula
The quadratic sum minimum is obtained for constraint condition, wherein, and S
iBe X
iWith Y
jThe inner product minimum value.That is to say and obtain on the floating image with described with reference to the corresponding closest approach of Characteristic of Image point, then according to the eigenvector of described closest approach, calculate rotation operator
And translation operator
, calculating rotation operator
And translation operator
After, the eigenvector of the unique point of floating image is rotated peaceful movement accordingly calculate X
iAfter the conversion be
,
Then calculate X after the rotation of each iteration and the translation
iWith Y
jsimilarly estimate, computing formula is:
Calculate and similarly estimate by stating formula
After, to similar estimate carry out
Judge, similarly estimate when described
Less than a reservation threshold
(
) or the number of times k of rotation and translation greater than or pre-determined number K
Max=1000 o'clock, export the eigenvector of described floating image unique point at this moment, and generate the floating image behind the registration, finish preliminary registration, and merge with the floating image behind the registration and with reference to image N, obtain final registering images.Otherwise iterations is added 1, proceed iteration and rotate peaceful movement and calculate, until describedly similarly estimate
Less than reservation threshold
Perhaps the number of times K of rotation and translation is greater than pre-determined number K
Max
For above-mentioned registration process more specifically and intuitively is described, the present invention by experiment view data advances to illustrate.
The present invention chooses the description of giving an example of the CT of head scanning in the U.S. Vanderbit university " The Retrospective Image Registration Evaluation Project " and MR_T1 sequence, and CT is with reference to image, and MR_T1 is floating image.
Particularly, CT figure has 28 layers, and pixel size is 0.65mm in the x and y direction, is 4.0mm on the Z direction.Fig. 2 is the front 8 layers of figure of CT, can find out the difference owing to Z direction position, and the human brain bone information of every layer of demonstration is all different.Contrast the phase diagram layer of each CT figure, can find out that they have similar outline, and inner because the imaging emphasis different, demonstration organize more or less difference.The imaging of different Z axis position has embodied the different details of tissue of patient as can be seen from Figure 2.
MR_T1 figure has 26 layers, and pixel size is 1.25mm in the x and y direction, is 4.0mm on the Z direction.Fig. 3 is the front 8 layers of figure of MR_T1, can find out the difference owing to Z direction position, and patient's brain soft tissue information of every layer of demonstration is all different.
Utilize these sequence chart of Fig. 2 and Fig. 3 can reconstruction of three-dimensional figure, Fig. 4 be the three-dimensional brain model of the different angles of rebuilding according to CT figure, can see the different piece of brain bone from different angles.Fig. 5 is the three-dimensional brain model according to the different angles of MR_T1 figure reconstruction, because the main brain soft tissue information of MR_T1 figure reflection, so the had an X-rayed part of the three-dimensional model diagram of rebuilding according to MR_T1 figure is less, only leaves a small amount of gap perspective between interior tissue and bone.
Before the registration, from the angle of five dimension conformal geometric algebras, CT figure and MR_T1 figure under the world coordinate system differ a translation operator
Calculate with a rotation
, that is to say that MR_T1 is at translation operator
With a rotation operator
Effect under will with the CT registration.In actual algorithm, because the optimizing strategy that adopts is based on the ICP algorithm, in fact MR_T1 is at translation operator
Calculate with a rotation
Continuous effect under obtain registration.Behind the registration, MR_T1 and CT figure bone portion merge, and the soft tissue portion among the MR_T1 will be inserted in the bone space of CT figure, and Fig. 6 is the 3 d effect graph through the different angles of the CT behind the registration and MR_T1 fusion.
Fig. 7 is the partially sliced figure after CT figure and MR_T1 figure merge behind the registration, and dark is the tissue that belongs to CT partly, and light-colored part is the tissue that belongs to MR_T1.Section behind the registration is to be different from CT before the registration and MR_T1 section as can see from Figure 7, and the homologue's alignment in CT and the MR_T1 section is merged, the different tissues demonstration that then complements each other in position.So that the three-dimensional position of position tissue organ preferably of the image behind the final registration makes registration results more directly perceived.
It is pointed out that above-mentioned Fig. 2 to Fig. 7 only is the design sketch that uses in order to explain registration process, and be not used in the restriction present embodiment.
Based on above-mentioned 3-D view method for registering, the present invention also provides a kind of 3-D view registration apparatus based on conformal geometric algebra, and as shown in Figure 8, wherein, shown device comprises:
Feature point extraction unit 10, be used for to selected be used for registration carry out rim detection with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
Similarly estimate computing unit 40, be used for calculating described rotation translation unit 30 and rotate the similar of eigenvector of peaceful movement described unique point with reference to image and described floating image after calculating at every turn and estimate;
Further, in order to carry out more accurately image registration, as shown in Figure 9, described device also comprises: image pretreatment unit 60, to selected processing with reference to image and floating image, process consistent with range of size the selected resolution with reference to image and floating image in advance.
In sum, by 3-D view method for registering and the device based on conformal geometric algebra provided by the invention, realized the direct alignment of three-dimensional data, the three-dimensional position of position tissue organ preferably, make registration results more directly perceived, the image behind the registration is more clear, and registration accuracy is higher.
Should be understood that application of the present invention is not limited to above-mentioned giving an example, for those of ordinary skills, can be improved according to the above description or conversion that all these improvement and conversion all should belong to the protection domain of claims of the present invention.
Claims (9)
1. the 3-D view method for registering based on conformal geometric algebra is characterized in that, may further comprise the steps:
A, selected be used for registration with reference to image and floating image, carry out rim detection to described with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
B, according to described unique point with reference to image and floating image, under the conformal geometric algebra framework, generate the eigenvector of described unique point;
C, the eigenvector of the unique point of described floating image is carried out several rotation and translation, and the similar of eigenvector of calculating described unique point with reference to image and described floating image after each rotation and the translation estimated;
D, when the described similar number of times of estimating less than a reservation threshold or rotation and translation is greater than or equal to pre-determined number, export the eigenvector of described floating image unique point at this moment, floating image behind the generation registration, and with the floating image behind the registration and described with reference to image co-registration, obtain final registering images.
2. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that described steps A also comprises: process described partition coefficient with reference to image and floating image and range of size scope consistent in advance.
3. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that, adopts the canny operator to carry out rim detection to described with reference to image and floating image in the described steps A.
4. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that described step C also comprises:
C1, obtain on the described floating image with described with reference to the corresponding closest approach of Characteristic of Image point, and according to the eigenvector of described closest approach, calculate rotation operator and translation operator;
C2, according to described rotation operator and translation operator, the eigenvector of the unique point of floating image is rotated and translation accordingly.
5. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that, similar among the described step C estimated by following formula and calculate:
Wherein, S
MNDescribedly similarly to estimate X
iAnd Y
jBe respectively the eigenvector of the unique point of described floating image and reference picture, Si is Xi and Yj inner product minimum value, and i and j are natural number.
6. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that described step D also comprises:
When the described similar number of times during less than pre-determined number that is greater than or equal to described reservation threshold and rotation and translation of estimating, continuation is rotated and translation the eigenvector of the unique point of described floating image, until describedly similarly estimate number of times less than a reservation threshold or rotation and translation more than or equal to described pre-determined number.
7. the 3-D view method for registering based on conformal geometric algebra according to claim 1 is characterized in that, described reservation threshold is 1.0 * 10
-3, described pre-determined number is 1000.
8. 3-D view registration apparatus based on conformal geometric algebra is characterized in that described device comprises:
The feature point extraction unit, be used for to selected be used for registration carry out rim detection with reference to image and floating image, draw corresponding edge contour, and utilize image segmentation algorithm, extract described unique point with reference to image and floating image;
The eigenvector converting unit is used for the described unique point with reference to image and floating image according to the extraction of described feature point extraction unit, under the conformal geometric algebra framework, generates the eigenvector of described unique point;
The rotation translation unit is used for the eigenvector of described unique point is rotated peaceful movement calculation;
Similarly estimate computing unit, be used for calculating described rotation translation unit and rotate the similar of eigenvector of peaceful movement described unique point with reference to image and described floating image after calculating at every turn and estimate;
Registration unit, be used for when the described similar number of times of estimating less than a reservation threshold or rotation and translation is greater than or equal to pre-determined number, export the eigenvector of described floating image unique point at this moment, floating image behind the generation registration, and with the floating image behind the registration and described with reference to image co-registration, obtain final registering images.
9. the 3-D view registration apparatus based on conformal geometric algebra according to claim 8 is characterized in that described device also comprises:
The image pretreatment unit to selected processing with reference to image and floating image, is processed consistent with range of size the selected resolution with reference to image and floating image in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104093237A CN102903117A (en) | 2012-10-24 | 2012-10-24 | 3D (three-dimensional) image registration method and device based on conformal geometric algebra |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104093237A CN102903117A (en) | 2012-10-24 | 2012-10-24 | 3D (three-dimensional) image registration method and device based on conformal geometric algebra |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102903117A true CN102903117A (en) | 2013-01-30 |
Family
ID=47575330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104093237A Pending CN102903117A (en) | 2012-10-24 | 2012-10-24 | 3D (three-dimensional) image registration method and device based on conformal geometric algebra |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102903117A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104146793A (en) * | 2014-07-28 | 2014-11-19 | 浙江大学 | Biological-activity organ manufacturing method |
| CN104182932A (en) * | 2013-05-27 | 2014-12-03 | 株式会社日立医疗器械 | CT (Computed Tomography) device, CT image system and CT image generation method |
| CN106251359A (en) * | 2016-08-09 | 2016-12-21 | 南通大学 | Based on Clifford algebraic geometry relative to the 3D rendering method for registering of invariant |
| CN106296685A (en) * | 2016-08-09 | 2017-01-04 | 南通大学 | Based on cranium outline feature geometries invariant multi information 3D medical image registration method |
| CN106846386A (en) * | 2017-02-08 | 2017-06-13 | 南通大学 | 3D cranium method for registering images based on ROI and conformal geometric algebra property invariant |
| CN108665538A (en) * | 2018-05-18 | 2018-10-16 | 天津流形科技有限责任公司 | A kind of threedimensional model approximating method, device, computer equipment and medium |
| CN109035314A (en) * | 2018-07-27 | 2018-12-18 | 深圳大学 | Medical image registration method and system based on Geometrical algebra |
| CN109949220A (en) * | 2019-01-29 | 2019-06-28 | 国网河南省电力公司郑州供电公司 | Panorama unmanned plane image split-joint method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1684105A (en) * | 2004-04-13 | 2005-10-19 | 清华大学 | Automatic registration method for large-scale three-dimensional scene multi-view laser scanning data |
| CN102169579A (en) * | 2011-03-31 | 2011-08-31 | 西北工业大学 | Rapid and accurate registration method of dense point cloud model |
| 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 |
-
2012
- 2012-10-24 CN CN2012104093237A patent/CN102903117A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1684105A (en) * | 2004-04-13 | 2005-10-19 | 清华大学 | Automatic registration method for large-scale three-dimensional scene multi-view laser scanning data |
| CN102169579A (en) * | 2011-03-31 | 2011-08-31 | 西北工业大学 | Rapid and accurate registration method of dense point cloud model |
| 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 |
Non-Patent Citations (2)
| Title |
|---|
| EDUARDO BAYRO-CORROCHANO等: "The Use of Geometric Algebra for 3D Modeling and Registration of Medical Data", 《J MATH IMAGING VIS》, 31 December 2009 (2009-12-31) * |
| 韩云生等: "基于Canny算子边缘特征匹配的双目深度测量", 《计算机系统应用》, no. 11, 31 December 2009 (2009-12-31) * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182932B (en) * | 2013-05-27 | 2017-04-12 | 株式会社日立制作所 | CT (Computed Tomography) device, CT image system and CT image generation method |
| CN104182932A (en) * | 2013-05-27 | 2014-12-03 | 株式会社日立医疗器械 | CT (Computed Tomography) device, CT image system and CT image generation method |
| CN104146793B (en) * | 2014-07-28 | 2015-12-30 | 浙江大学 | A kind of manufacture method with biological activity organ |
| CN104146793A (en) * | 2014-07-28 | 2014-11-19 | 浙江大学 | Biological-activity organ manufacturing method |
| CN106296685A (en) * | 2016-08-09 | 2017-01-04 | 南通大学 | Based on cranium outline feature geometries invariant multi information 3D medical image registration method |
| CN109308717B (en) * | 2016-08-09 | 2022-04-26 | 南通大学 | Three-dimensional medical image simplified registration method based on visual geometric features |
| CN106251359A (en) * | 2016-08-09 | 2016-12-21 | 南通大学 | Based on Clifford algebraic geometry relative to the 3D rendering method for registering of invariant |
| CN109308717A (en) * | 2016-08-09 | 2019-02-05 | 南通大学 | 3 d medical images based on intuitive geometry feature simplify method for registering |
| CN109410257A (en) * | 2016-08-09 | 2019-03-01 | 南通大学 | Multi information 3D medical image high registration accuracy method |
| CN109472782A (en) * | 2016-08-09 | 2019-03-15 | 南通大学 | The general method for registering of cranium outer profile image |
| CN109410257B (en) * | 2016-08-09 | 2022-07-08 | 南通大学 | Multi-information 3D medical image high-precision registration method |
| CN106296685B (en) * | 2016-08-09 | 2019-08-06 | 南通大学 | Based on cranium outer profile feature geometries invariant multi information 3D medical image registration method |
| CN109472782B (en) * | 2016-08-09 | 2022-04-26 | 南通大学 | General registration method for intracranial outline images |
| CN106846386A (en) * | 2017-02-08 | 2017-06-13 | 南通大学 | 3D cranium method for registering images based on ROI and conformal geometric algebra property invariant |
| CN106846386B (en) * | 2017-02-08 | 2019-06-28 | 南通大学 | 3D cranium method for registering images based on ROI and conformal geometric algebra property invariant |
| CN108665538A (en) * | 2018-05-18 | 2018-10-16 | 天津流形科技有限责任公司 | A kind of threedimensional model approximating method, device, computer equipment and medium |
| CN109035314A (en) * | 2018-07-27 | 2018-12-18 | 深圳大学 | Medical image registration method and system based on Geometrical algebra |
| CN109949220A (en) * | 2019-01-29 | 2019-06-28 | 国网河南省电力公司郑州供电公司 | Panorama unmanned plane image split-joint method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161326B (en) | System and method for unsupervised deep learning of deformable image registration | |
| CN102903117A (en) | 3D (three-dimensional) image registration method and device based on conformal geometric algebra | |
| CN107038728B (en) | Contour automated determination based on iterative reconstruction | |
| US9076201B1 (en) | Volumetric deformable registration method for thoracic 4-D computed tomography images and method of determining regional lung function | |
| Elhawary et al. | Multimodality non-rigid image registration for planning, targeting and monitoring during CT-guided percutaneous liver tumor cryoablation | |
| JP2005521502A (en) | Overlay of chest and abdominal image modalities | |
| EP3025303B1 (en) | Multi-modal segmentation of image data | |
| Vrtovec et al. | Automated curved planar reformation of 3D spine images | |
| CN103493098B (en) | Magic magiscan and method | |
| WO2012040721A2 (en) | Registration of scanned objects obtained from different orientations | |
| Zheng et al. | Scaled, patient-specific 3D vertebral model reconstruction based on 2D lateral fluoroscopy | |
| CN103942772A (en) | Multimodal multi-dimensional blood vessel fusion method and system | |
| Baka et al. | Statistical shape model-based femur kinematics from biplane fluoroscopy | |
| CN102651145A (en) | Three-dimensional femoral model visualization method | |
| CN115830016B (en) | Medical image registration model training method and equipment | |
| Miao et al. | A hybrid method for 2-D/3-D registration between 3-D volumes and 2-D angiography for trans-catheter aortic valve implantation (TAVI) | |
| US9665947B2 (en) | Method and apparatus for registration of multimodal imaging data by using a center line to optimize quality of alignment | |
| Krüger et al. | Simulation of mammographic breast compression in 3D MR images using ICP-based B-spline deformation for multimodality breast cancer diagnosis | |
| Carminati et al. | Reconstruction of the descending thoracic aorta by multiview compounding of 3-d transesophageal echocardiographic aortic data sets for improved examination and quantification of atheroma burden | |
| Batchelor et al. | 3D medical imaging | |
| Hopp et al. | Automatic multimodal 2D/3D image fusion of ultrasound computer tomography and x-ray mammography for breast cancer diagnosis | |
| Krüger et al. | Breast compression simulation using ICP-based B-spline deformation for correspondence analysis in mammography and MRI datasets | |
| Wildeman et al. | 2D/3D registration of micro-CT data to multi-view photographs based on a 3D distance map | |
| Steger et al. | Automated skeleton based multi-modal deformable registration of head&neck datasets | |
| Liu et al. | Optimization of reconstruction of 2D medical images based on computer 3D reconstruction technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130130 |
|
| RJ01 | Rejection of invention patent application after publication |