CN106408509A - Registration method and apparatus - Google Patents
Registration method and apparatus Download PDFInfo
- Publication number
- CN106408509A CN106408509A CN201610284148.1A CN201610284148A CN106408509A CN 106408509 A CN106408509 A CN 106408509A CN 201610284148 A CN201610284148 A CN 201610284148A CN 106408509 A CN106408509 A CN 106408509A
- Authority
- CN
- China
- Prior art keywords
- image
- dimensional
- offset vector
- medical images
- registration
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 239000013598 vector Substances 0.000 claims abstract description 72
- 238000001959 radiotherapy Methods 0.000 claims description 23
- 238000013508 migration Methods 0.000 claims description 15
- 230000005012 migration Effects 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 abstract 1
- 230000005855 radiation Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000001225 therapeutic effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000004807 localization Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 208000019155 Radiation injury Diseases 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000002675 image-guided surgery Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002601 radiography Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a registration method and apparatus. The registration method comprises steps of carrying out registration of a digital reconstruction ray image and a two-dimension medical image acquired at the same angle, and calculating a two-dimension image offset vector; determining the selection range of a three-dimension image offset vector according to the two-dimension image offset vector; determining a final three-dimension image offset vector based on image mutual information between the digital reconstruction ray image and the two-dimension medical image in the range; and taking the three-dimension image offset vector as an offset vector for registration of the two-dimension medical image and a three-dimension medical image. The technical scheme can rapidly and conveniently carry out registration of the two-dimension medical image and the three-dimension medical image, and is particularly accurate in positioning registration of a verification patient.
Description
Technical field
The present invention relates to field of medical image processing, particularly to the registration of medical image.
Background technology
It will usually (for example computer breaks by medical imaging devices before carrying out radiotherapy or image-guided surgery
Layer imaging device) medical imaging is carried out to patient, controlled based on the patient's 3-D view (also referred to as volume data) collecting
Treat planning.When formulating radiotherapy treatment planning, the computed tomography image of patient can be imported to radiotherapy treatment planning system
(TPS, Therapy Planning System), determines radiocurable angle, dose of radiation, launched field based on the image of patient
Scope etc..Actual carry out radiotherapy when, patient lies in radiotherapy equipment and also can shoot medical image again, will now
The medical image shooting and the image doing before during radiation plan carry out registration, thus carrying out position correction, to guarantee that development puts
Penetrate the positional precision for the treatment of, it is to avoid the radiation injury that non-focal area is caused to patient.
In carrying out process of image registration, do the medical image gathering during radiotherapy treatment planning and be usually 3-D view number
According to, and the medical image gathering in radiotherapy is usually electronics launched field imaging system (EPID, Electronic Portal
Imaging Device) two-dimensional image data that collects.Therefore it will usually 3 d image data is projected into two-dimensional digital weight
Build ray image (DRR, Digital Reconstructed Radiography), then the two dimensional image collecting with EPID enters
Row registration.According to registration result, to patient, the position in therapeutic bed is corrected.
For example in the U.S. Patent application text of Publication No. US20040114718A1, describe a kind of linear accelerating
EPID used in device and DRR registered placement technology, are all to define an area-of-interest (ROI) on DRR and EPID image,
Calculate the correlation of two area-of-interests using coefficient correlation (correlation coefficient).Specifically root first
Calculate the translational movement between two width images according to normalized correlation (NCC, normalised cross correlation), then
By phorogenesis after EPID image, then with NCC method calculate one degree of freedom the anglec of rotation, the optimal translational movement obtained and
The anglec of rotation, after EPID image is converted, maximum with the NCC value of corresponding DRR image.
And in the United States Patent (USP) disclosure of Publication No. US8249317B2, describe over the course for the treatment of, obtain respectively
Take EPID image and ultrasonoscopy, extract tissue anatomical structure from ultrasonoscopy, by itself and EPID image co-registration Cheng Xin
EPID image.The ultrasonoscopy that this patent is mentioned is 3-D view, extracts profile to three-dimensional ultrasound pattern dividing method, and
Two dimensional surface to the image projection extracted to EPID, with projection the data obtained with EPID imaging importing thus strengthening EPID figure
Picture.Enhanced EPID image and DRR image are carried out registering, calculate offset vector.
But above the first method based on gray value, can be because DRR image be different from the gray difference of EPID image
Impact result calculates, second method, and ultrasonic and EPID image co-registration mode of sampling implements more complicated.
Content of the invention
The problem to be solved in the present invention is to provide a kind of side based on two-dimensional medical images and the registration of 3 d medical images
Method and its device, during solution medical figure registration, speed is slower, particularly the less accurate problem of radiotherapy localization and positioning.
For solving the above problems, the invention provides the method for registering of a kind of two-dimensional medical images and 3 d medical images,
Including:The two-dimensional medical images that digital reconstruction ray image and same angle acquisition are obtained carry out registration, are calculated
Two dimensional image offset vector;Described digital reconstruction ray image is by 3 d medical images data genaration, different including at least two
The image of angle;Determine the selection range of 3-D view offset vector according to described two dimensional image offset vector;In described scope
Interior, determine that final 3-D view offsets to based on the image mutual information between digital reconstruction ray image and two-dimensional medical images
Amount;Described 3-D view offset vector is as the offset vector of two-dimensional medical images and 3 d medical images registration.
Preferably, described digital reconstruction ray image, by 3 d medical images data genaration, generates two different angles
Image.Described two difference angles are two angles mutually at a right angle.Described two angles are 0 degree and 90 degree.Or described two
Individual angle is 45 degree and 135 degree.
Preferably, enter in the described two-dimensional medical images obtaining digital reconstruction ray image and same angle acquisition
Before row registration, also include the step to two-dimensional medical images image enhaucament.
Preferably, the described two-dimensional medical images obtaining digital reconstruction ray image and same angle acquisition are carried out
Registration, is the registration based on mutual information.
Preferably, described included according to the selection range that two dimensional image offset vector determines 3-D view offset vector:Root
According to the value in total coordinate direction for the two dimensional image offset vector interval as 3-D view offset vector selection range correspondence
Value is interval.
Preferably, described in the range of, based on the image mutual trust between digital reconstruction ray image and two-dimensional medical images
Breath determines that 3-D view offset vector includes:In described scope, calculate the numeral of each 3-D view offset vector corresponding angle
Image association relationship between reconstructed rays image and two-dimensional medical images;Maximum according to image association relationship sum, it is defined as
Final 3-D view offset vector.
Preferably, described two-dimensional medical images are to be collected by the electronics launched field imaging system of radiotherapy equipment.
Described 3 d medical images are the 3 d medical images of plan CT.
For solving the above problems, present invention also offers the registration dress of a kind of two-dimensional medical images and 3 d medical images
Put, including:Two-dimensional migration vector calculation unit, for digital reconstruction ray image and same angle acquisition are obtained two
Dimension medical image carries out registration, is calculated two dimensional image offset vector;Described digital reconstruction ray image is by 3 D medical figure
As data genaration, including the image of at least two different angles;3-D migration vector determination unit, for according to described X-Y scheme
As offset vector determines the selection range of 3-D view offset vector;In described scope, based on digital reconstruction ray image and
Image mutual information between two-dimensional medical images determines final 3-D view offset vector.
Compared with prior art, technical scheme can be easily and fast to two-dimensional medical images and 3 D medical figure
As carrying out registration, particularly positioning patient, in the position of radiation therapeutical bed with respect to the side-play amount of plan CT position, verifies patient
More accurate during the registration of pendulum position.
Brief description
Fig. 1 is the structural representation of radiotherapy equipment;
Fig. 2 is the flow chart of medical image registration method of the present invention;
Fig. 3 is the schematic diagram being obtained digital reconstruction ray image by 3 d medical images data;
Fig. 4 is the schematic diagram of the digital reconstruction ray image under two angles;
Fig. 5 is the schematic diagram of collection two-dimensional medical images during radiotherapy equipment rotation;
Fig. 6 is the schematic diagram of the two-dimensional medical images under two angles;
Fig. 7 is the schematic diagram that two angle hypographs are carried out with registration;
Fig. 8 is the structure chart of medical figure registration device of the present invention;
Fig. 9 is EPID difference angular image collection schematic diagram of the present invention.
Specific embodiment
Understandable for enabling the above objects, features and advantages of the present invention to become apparent from, below in conjunction with the accompanying drawings to the present invention
Specific embodiment be described in detail.Elaborate detail in order to fully understand the present invention in the following description.But
It is that the present invention can be implemented different from alternate manner described here with multiple, those skilled in the art can be without prejudice to this
Similar popularization is done in the case of invention intension.Therefore the present invention is not limited by following public specific embodiment.
Fig. 1 is the structural representation of radiotherapy equipment, as shown in figure 1, radiotherapy equipment 100 includes rotating part
102.Rotating part 102 is installed on standing part 101, and rotating part 102 can be entered along r direction axle centered on z direction
Row rotation.The side of rotating part 102 is fixed with treatment head 103.It should be noted that the radiotherapy equipment illustrating here
100 is the equipment of homology two-beam type, and treatment head 103 can send imaging ray (KeV rank) and treatment ray (MeV level respectively
Not).When treatment head 103 sends treatment ray, for carrying out radiotherapy to patient, meanwhile, the electronics launched field of opposite side becomes
As system (EPID) 104 can be configured to receive the ray through patient, form the patient image in treatment.In addition, controlling
Before treating or after treatment, the imaging ray that treatment head sends can be received by electronics launched field imaging system (EPID) 104 and be formed
Patient image.Radiotherapy equipment 100 also includes sick bed 105, is imaged below treatment head 103 for carrying patient and moving to
Or treatment.
The correlation of the control of radiotherapy equipment, data is carried out processing etc. and can be carried out by computer.To radiating
Registration between three-dimensional data that treatment plan obtains and the two dimensional image being collected by EPID is equally completed by computer.
In the exemplary embodiment of the present invention, with the three-dimensional data that obtained by radiotherapy treatment planning with by treatment during EPID adopt
Collect that the registration between the two dimensional image that obtains is described it being understood, however, that according to the present invention, to by radiotherapy meter
Draw the three-dimensional data that obtains and by the registration before treatment or between two dimensional image that after treatment, EPID collects
It is possible.
The invention discloses a kind of patient radiation is treated before 3 d medical images data and pass through during radiotherapy
The method that the two-dimensional medical images data that EPID collects carries out registration, referring to Fig. 2.
First according to step S201, by the digital reconstruction ray diagram of 3 d medical images data genaration at least two angle
Picture.Referring to Fig. 3,3 D medical data 300 is the data gathering before radiation treatment, can choose two angles (direction a, sides
To b) projecting, obtain the digital reconstruction ray image of corresponding two angles, respectively two-dimensional medical images 301, two to it
Dimension medical image 302.For example for the 3 d medical images data of patient's brain, angle a and angle b can respectively obtain as
Shown in Fig. 4 two two-dimensional medical images.
In radiotherapy, referring to Fig. 5, under the Therapeutic mode of radiotherapy equipment 100, treatment head 103 is revolved along direction r
Go to the position of corresponding angle a, angle b, collected the two dimension of this two angles corresponding while treatment by EPID respectively
Medical image, referring to Fig. 9, X, Y, Z represent three-dimensional coordinate system to EPID difference angular image collection schematic diagram, in angle a side
To collection two dimensional image coordinate system be xa, ya, angle b direction collection two dimensional image coordinate system be xb, yb, wherein xa and
Xb direction is parallel with three-dimensional Z axis, projects gained by three-dimensional Z axis.The two-dimensional medical images collecting are such as
Shown in Fig. 6.
In the preferred embodiment of the present invention, angle a and angle b are chosen for two angles mutually at a right angle, now obtain
The useful information taking is at most, more accurate being subsequently calculated 3-D migration vector by two-dimensional migration vector.Particularly angle
A, angle b can elect 0 degree and 90 degree as, now correspond to two dimensional image be respectively in crown bit image and sagittal image organ it
Between block minimum, be easy to subsequently carry out registration.
Step S202, the two-dimensional medical images that digital reconstruction ray image and its equal angular are collected carry out slightly fixed
Position, here, when coarse positioning refers to image and image registration, the position gap due to originally two images may be larger, can be with all
If the mode elder generation coarse localization of picture search is to substantially aligned position.This step is to know for those of ordinary skill in the art
's.
Step S203, the two-dimensional medical images that digital reconstruction ray image and its equal angular are collected are joined
Standard, is calculated the two dimensional image offset vector under corresponding angle.
As shown in fig. 7, two dimensional image offset vector (the Δ x being calculated respectively under angle aa, Δ ya), angle b X-Y scheme
As offset vector (Δ xb, Δ yb).The method for registering of concrete two dimensional image has many kinds, is known in the art technology, here no longer
Repeat.Preferably can be with using the registering mode based on mutual information.
Because the general definition of EPID image in treatment is poor, noise is more, figure more preferably can be carried out before registration
Image intensifying, strengthens the development of bone texture structure.The method of image enhaucament can carry out bandpass filtering, high-pass filtering to image
Deng.
Obtain after two two dimensional image offset vectors according to step S203, this two two-dimensional migration vectorial coordinates have three-dimensional
One common coordinate axle in space, considers that the difference of the side-play amount that two groups of two dimensional images calculate in common coordinate direction of principal axis is first
No within tolerance interval.If in tolerance interval, carry out step S204, first offset to based on two two dimensional images
Amount determines the scope of 3-D view offset vector.It should be noted that two dimensional image coordinate system here and becoming of introducing before
Image space coordinate system is two coordinate systems.With reference to Fig. 9, can get three-dimensional coordinate X, Y, Z and xa,yaAnd xb,ybRelation as follows:
In one embodiment, if | Δ xa+Δxb|<1mm, then can according to following formula (1) directly from two-dimensional migration to
Amount (Δ xa, Δ ya) and (Δ xb, Δ yb) calculate 3-D migration vector (Δ x, Δ y, Δ z).
As it was previously stated, because angle a, angle b are chosen for 0 degree and 90 degree, therefore 3-D migration vector is drawn according to formula (1)
(each value of Δ x, Δ y, Δ z):Δ x=Δ ya, Δ y=Δ yb, Δ z=(Δ xb-xa)/2.
If 1mm≤| Δ xa+Δxb|<During 6mm ,-Δ xa~Δ xb is defined as the selection of 3-D migration vector z-component
Scope, calculates the image between digital reconstruction ray image and two-dimensional medical images under two angles mutual in the range of this respectively
The value of information.Such as selection-Δ xa~Δ xbBetween value Δ zc, then now the two dimensional image offset vector of corresponding angle a and b is
(Δxa,-Δ zc) and (Δ xb, Δ zc), corresponding angle a, the image association relationship I of angle b respectively can be calculatedaAnd Ib.
The method calculating association relationship between two width images has a lot, for example, utilize below equation (2):
Wherein pdrr&epid(x, y) is that DRR image is distributed with the gray probability of combining of EPID image, pdrrX () is DRR image
Gray probability is distributed, pepidY () is EPID gradation of image probability distribution.
It is calculated association relationship IaAnd IbAfterwards, simplest method is directly by Ia、IbCorresponding Δ z when sum is maximum
Z-component deviant for the final 3-D view offset vector chosen.Or using more complicated algorithm, mutual information long-pending
Mode.(Δ x, Δ y, Δ z) are the 3-D migration vector calculating:
If | Δ xa+Δxb|>During 6mm, then system can remind user's side-play amount excessive, user can again put position or
Adjustment area-of-interest.
Here the 3-D view offset vector calculating determination is joined as two-dimensional medical images of the present invention and 3 d medical images
Accurate offset vector.
It will appreciated by the skilled person that will | Δ xa+Δxb| according to 1mm (can be described as first threshold) and 6mm
(Second Threshold) carry out segmented to process is exemplary, indeed, it is possible to be carried out according to the levels of precision of required registration
Accommodation, for example, first threshold is readily modified as 2mm, and Second Threshold is readily modified as 10mm.When | Δ xa+Δxb| in the first threshold
In the range of value, when calculating 3-D view side-play amount by two groups of two dimensional image side-play amounts, it would however also be possible to employ similar to corresponding second threshold
The side-play amount to calculate 3-D view for the mutual information computational methods of value scope, simply calculates meeting slightly complexity a bit.
Those of ordinary skill in the art should also be as it is appreciated that working as | Δ xa+Δxb| less than 1 or less than first threshold when,
Still as above existing can be adopted using the method based on association relationship, in other words | Δ xa+Δxb| it is more than or equal to
First threshold and be less than the method that Second Threshold is adopted.
Only describe corresponding when choosing two angles in described above, the joining of two-dimensional medical images and 3 d medical images
Standard, it is also possible to be penetrated by the digital reconstruction that 3 d medical images generate more than two angle in the other embodiment of the present invention
Line image, gathers the two-dimensional medical images of more than two angle afterwards, is calculated the two of more than two angle under corresponding angle
Dimension image shift vector, finally determines 3-D view offset vector by two dimensional image offset vector, simply concrete corresponding formula 1
Slightly change with formula 2, change belong to those skilled in the art being capable of the scope that obtains of reasoning.
On the basis of the above, present invention also offers a kind of registration apparatus, referring to Fig. 8, registration apparatus 800 include:
Two-dimensional migration vector calculation unit 801, for obtaining digital reconstruction ray image and same angle acquisition
Two-dimensional medical images carry out registration, be calculated two dimensional image offset vector;Described digital reconstruction ray image is cured by three-dimensional
Learn view data to generate, including the image of at least two different angles.
According to described two dimensional image offset vector, 3-D migration vector determination unit 802, for determining that 3-D view offsets
The selection range of vector;In described scope, based on the image mutual trust between digital reconstruction ray image and two-dimensional medical images
Breath determines final 3-D view offset vector.
The embodiment of two-dimensional medical images and 3 d medical images registration apparatus refers to medical figure registration of the present invention
The embodiment of method, repeats no more here.
On the basis of existing technology, technical scheme is from two angle shot EPID for technical scheme
Image, carries out registering with the DRR image of corresponding angle, calculates the result of two groups of two dimensional images registration respectively, at known two group two
Under conditions of dimension offsets to value, consider the mutual information of two groups of two dimensional images, by the mutual information of two groups of DRR and EPID image
With maximum solution as optimum offset vector solution, it is defined as optimal three dimensions offset vector.
Although the present invention is open as above with preferred embodiment, it is not for limiting the present invention, any this area
Without departing from the spirit and scope of the present invention, the methods and techniques content that may be by the disclosure above is to this for technical staff
Bright technical scheme makes possible variation and modification, and therefore, every content without departing from technical solution of the present invention, according to the present invention
Technical spirit any simple modification, equivalent variations and modification that above example is made, belong to technical solution of the present invention
Protection domain.
Claims (11)
1. a kind of method for registering, including:
The two-dimensional medical images that digital reconstruction ray image and same angle acquisition are obtained carry out registration, are calculated two
Dimension image shift vector;Described digital reconstruction ray image by 3 d medical images data genaration, including at least two different angles
The image of degree;
Determine the selection range of 3-D view offset vector according to described two dimensional image offset vector;In described scope, it is based on
Image mutual information between digital reconstruction ray image and two-dimensional medical images determines final 3-D view offset vector;
3-D migration vector is determined according to the two dimensional image offset vector of described difference angle;
Described 3-D view offset vector is as the offset vector of two-dimensional medical images and 3 d medical images registration.
2. method for registering according to claim 1 is it is characterised in that described two difference angle is mutually at a right angle two
Angle.
3. method for registering according to claim 2 is it is characterised in that described two angle is 0 degree and 90 degree.
4. method for registering according to claim 2 is it is characterised in that described two angle is 45 degree and 135 degree.
5. method for registering according to claim 1 it is characterised in that described by digital reconstruction ray image and with its phase
Carry out before registration with the two-dimensional medical images that angle acquisition obtains, also include the step to described two-dimensional medical images image enhaucament
Suddenly.
6. method for registering according to claim 1 is it is characterised in that described by digital reconstruction ray image and same
The two-dimensional medical images that angle acquisition obtains carry out registration, are the registrations based on mutual information.
7. method for registering according to claim 1 is it is characterised in that described determine three-dimensional according to two dimensional image offset vector
The selection range of image shift vector includes:Interval according to the value in total coordinate direction for the two dimensional image offset vector is as three
The respective value of dimension image shift vector selection range is interval.
8. method for registering according to claim 1 it is characterised in that described in the range of, based on digital reconstruction ray diagram
Image mutual information between picture and two-dimensional medical images determines that 3-D view offset vector includes:
In described scope, calculate digital reconstruction ray image and the two-dimensional medical figure of each 3-D view offset vector corresponding angle
Image association relationship between picture;
Maximum according to image association relationship sum, it is defined as final 3-D view offset vector.
9. method for registering according to claim 1 is it is characterised in that described two-dimensional medical images are by radiotherapy equipment
Electronics launched field imaging system collect.
10. method for registering according to claim 1 is it is characterised in that described 3 d medical images are the three-dimensional of plan CT
Medical image.
A kind of 11. registration apparatus are it is characterised in that include:
Two-dimensional migration vector calculation unit, for the two dimension doctor obtaining digital reconstruction ray image and same angle acquisition
Learn image and carry out registration, be calculated two dimensional image offset vector;Described digital reconstruction ray image is by 3 d medical images number
According to generation, including the image of at least two different angles;
3-D migration vector determination unit, for determining the choosing of 3-D view offset vector according to described two dimensional image offset vector
Take scope;In described scope, determined based on the image mutual information between digital reconstruction ray image and two-dimensional medical images
Whole 3-D view offset vector.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610284148.1A CN106408509A (en) | 2016-04-29 | 2016-04-29 | Registration method and apparatus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610284148.1A CN106408509A (en) | 2016-04-29 | 2016-04-29 | Registration method and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106408509A true CN106408509A (en) | 2017-02-15 |
Family
ID=58006238
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610284148.1A Pending CN106408509A (en) | 2016-04-29 | 2016-04-29 | Registration method and apparatus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106408509A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123137A (en) * | 2017-04-28 | 2017-09-01 | 上海联影医疗科技有限公司 | Medical image processing method and equipment |
CN108742678A (en) * | 2018-06-01 | 2018-11-06 | 妙智科技(深圳)有限公司 | Method for registering images, device and computer readable storage medium |
CN109559296A (en) * | 2018-10-08 | 2019-04-02 | 广州市本真网络科技有限公司 | Medical image registration method and system based on full convolutional neural networks and mutual information |
CN110310314A (en) * | 2019-03-26 | 2019-10-08 | 上海联影智能医疗科技有限公司 | Method for registering images, device, computer equipment and storage medium |
CN111149128A (en) * | 2018-07-03 | 2020-05-12 | 西安大医集团股份有限公司 | Method and device for acquiring marking data, training method and device and medical equipment |
CN111388880A (en) * | 2020-03-20 | 2020-07-10 | 上海联影医疗科技有限公司 | Arc radiotherapy calibration method, device, equipment and storage medium |
CN111615365A (en) * | 2018-12-26 | 2020-09-01 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
CN111615413A (en) * | 2018-12-26 | 2020-09-01 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
WO2020237537A1 (en) * | 2019-05-29 | 2020-12-03 | 西安大医集团股份有限公司 | Image guidance method and apparatus, and medical device and computer readable storage medium |
CN112750152A (en) * | 2021-01-18 | 2021-05-04 | 上海联影医疗科技股份有限公司 | Image registration method and device, computer equipment and storage medium |
CN112863641A (en) * | 2019-11-12 | 2021-05-28 | 西安大医集团股份有限公司 | Radiation therapy system and offset determination method and device of radiation source thereof |
CN113573776A (en) * | 2020-02-14 | 2021-10-29 | 西安大医集团股份有限公司 | Image guiding method, image guiding device, radiotherapy equipment and computer storage medium |
WO2022116114A1 (en) * | 2020-12-03 | 2022-06-09 | 西安大医集团股份有限公司 | Monitoring method and apparatus, and computer storage medium |
WO2022198553A1 (en) * | 2021-03-25 | 2022-09-29 | 中国科学院近代物理研究所 | Three-dimensional image-guided positioning method and system, and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1631321A (en) * | 2003-12-23 | 2005-06-29 | 中国科学院自动化研究所 | Multiple modality medical image registration method based on mutual information sensitive range |
CN102222330A (en) * | 2011-05-16 | 2011-10-19 | 付东山 | Two-dimensional and three-dimensional medical image registration method and system |
US8249317B2 (en) * | 2007-07-20 | 2012-08-21 | Eleckta Ltd. | Methods and systems for compensating for changes in anatomy of radiotherapy patients |
CN103065322A (en) * | 2013-01-10 | 2013-04-24 | 合肥超安医疗科技有限公司 | Two dimensional (2D) and three dimensional (3D) medical image registration method based on double-X-ray imaging |
CN103886586A (en) * | 2014-02-18 | 2014-06-25 | 南京邮电大学 | Medical image registration method based on combination of mutual information and gradient information |
CN104637061A (en) * | 2015-01-30 | 2015-05-20 | 中国科学院自动化研究所 | Two-dimensional and three-dimensional medical image registration method |
CN104751438A (en) * | 2013-12-31 | 2015-07-01 | 同方威视技术股份有限公司 | Method and equipment for interactively registering medical three-dimensional image |
-
2016
- 2016-04-29 CN CN201610284148.1A patent/CN106408509A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1631321A (en) * | 2003-12-23 | 2005-06-29 | 中国科学院自动化研究所 | Multiple modality medical image registration method based on mutual information sensitive range |
US8249317B2 (en) * | 2007-07-20 | 2012-08-21 | Eleckta Ltd. | Methods and systems for compensating for changes in anatomy of radiotherapy patients |
CN102222330A (en) * | 2011-05-16 | 2011-10-19 | 付东山 | Two-dimensional and three-dimensional medical image registration method and system |
CN103065322A (en) * | 2013-01-10 | 2013-04-24 | 合肥超安医疗科技有限公司 | Two dimensional (2D) and three dimensional (3D) medical image registration method based on double-X-ray imaging |
CN104751438A (en) * | 2013-12-31 | 2015-07-01 | 同方威视技术股份有限公司 | Method and equipment for interactively registering medical three-dimensional image |
CN103886586A (en) * | 2014-02-18 | 2014-06-25 | 南京邮电大学 | Medical image registration method based on combination of mutual information and gradient information |
CN104637061A (en) * | 2015-01-30 | 2015-05-20 | 中国科学院自动化研究所 | Two-dimensional and three-dimensional medical image registration method |
Non-Patent Citations (2)
Title |
---|
XIN CHEN 等: "Automatic 3D-2D image registration using partial digitally reconstructed radiographs along projected anatomic contours", 《MEDICAL INFORMATION VISUALISATION - BIOMEDICAL VISUALISATION(MEDIVIS 2007)》 * |
张密: "放射治疗中2D/3D医学图像配准算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107123137B (en) * | 2017-04-28 | 2020-05-22 | 上海联影医疗科技有限公司 | Medical image processing method and equipment |
CN107123137A (en) * | 2017-04-28 | 2017-09-01 | 上海联影医疗科技有限公司 | Medical image processing method and equipment |
CN108742678A (en) * | 2018-06-01 | 2018-11-06 | 妙智科技(深圳)有限公司 | Method for registering images, device and computer readable storage medium |
CN108742678B (en) * | 2018-06-01 | 2022-02-18 | 妙智科技(深圳)有限公司 | Image registration method and device and computer-readable storage medium |
CN111149128A (en) * | 2018-07-03 | 2020-05-12 | 西安大医集团股份有限公司 | Method and device for acquiring marking data, training method and device and medical equipment |
CN111149128B (en) * | 2018-07-03 | 2024-03-29 | 西安大医集团股份有限公司 | Method and device for acquiring marking data, training method and device and medical equipment |
US11972582B2 (en) | 2018-07-03 | 2024-04-30 | Our United Corporation | Method and apparatus for acquiring labeled data, training method and apparatus, and medical equipment |
CN109559296B (en) * | 2018-10-08 | 2020-08-25 | 广州市大智网络科技有限公司 | Medical image registration method and system based on full convolution neural network and mutual information |
CN109559296A (en) * | 2018-10-08 | 2019-04-02 | 广州市本真网络科技有限公司 | Medical image registration method and system based on full convolutional neural networks and mutual information |
CN111615365A (en) * | 2018-12-26 | 2020-09-01 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
CN111615413A (en) * | 2018-12-26 | 2020-09-01 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
CN111615365B (en) * | 2018-12-26 | 2021-11-30 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
CN111615413B (en) * | 2018-12-26 | 2022-05-13 | 西安大医集团股份有限公司 | Positioning method and device and radiotherapy system |
CN110310314A (en) * | 2019-03-26 | 2019-10-08 | 上海联影智能医疗科技有限公司 | Method for registering images, device, computer equipment and storage medium |
CN110310314B (en) * | 2019-03-26 | 2022-01-25 | 上海联影智能医疗科技有限公司 | Image registration method and device, computer equipment and storage medium |
WO2020237537A1 (en) * | 2019-05-29 | 2020-12-03 | 西安大医集团股份有限公司 | Image guidance method and apparatus, and medical device and computer readable storage medium |
CN113891740B (en) * | 2019-05-29 | 2024-01-16 | 西安大医集团股份有限公司 | Image guidance method and device, medical equipment and computer readable storage medium |
CN113891740A (en) * | 2019-05-29 | 2022-01-04 | 西安大医集团股份有限公司 | Image guidance method and device, medical equipment and computer readable storage medium |
CN112863641A (en) * | 2019-11-12 | 2021-05-28 | 西安大医集团股份有限公司 | Radiation therapy system and offset determination method and device of radiation source thereof |
CN113573776A (en) * | 2020-02-14 | 2021-10-29 | 西安大医集团股份有限公司 | Image guiding method, image guiding device, radiotherapy equipment and computer storage medium |
US11883684B2 (en) | 2020-02-14 | 2024-01-30 | Our United Corporation | Image-guided method, radio therapy device, and computer storage medium |
CN111388880B (en) * | 2020-03-20 | 2022-06-14 | 上海联影医疗科技股份有限公司 | Arc radiotherapy calibration method, device, equipment and storage medium |
CN111388880A (en) * | 2020-03-20 | 2020-07-10 | 上海联影医疗科技有限公司 | Arc radiotherapy calibration method, device, equipment and storage medium |
WO2022116114A1 (en) * | 2020-12-03 | 2022-06-09 | 西安大医集团股份有限公司 | Monitoring method and apparatus, and computer storage medium |
CN112750152A (en) * | 2021-01-18 | 2021-05-04 | 上海联影医疗科技股份有限公司 | Image registration method and device, computer equipment and storage medium |
WO2022198553A1 (en) * | 2021-03-25 | 2022-09-29 | 中国科学院近代物理研究所 | Three-dimensional image-guided positioning method and system, and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106408509A (en) | Registration method and apparatus | |
JP6894987B2 (en) | 3D localization and tracking for adaptive radiation therapy | |
CN107530552B (en) | Three-dimensional localization of moving targets for adaptive radiotherapy | |
Rottmann et al. | A multi-region algorithm for markerless beam's-eye view lung tumor tracking | |
Nie et al. | Site‐specific deformable imaging registration algorithm selection using patient‐based simulated deformations | |
JP6886565B2 (en) | Methods and devices for tracking surface movements | |
Ge et al. | Toward the development of intrafraction tumor deformation tracking using a dynamic multi‐leaf collimator | |
EP2175931B1 (en) | Systems for compensating for changes in anatomy of radiotherapy patients | |
Brahme et al. | 4D laser camera for accurate patient positioning, collision avoidance, image fusion and adaptive approaches during diagnostic and therapeutic procedures | |
Ébastien Clippe et al. | Patient setup error measurement using 3D intensity-based image registration techniques | |
Pawiro et al. | Validation for 2D/3D registration I: A new gold standard data set | |
van Sörnsen de Koste et al. | Markerless tracking of small lung tumors for stereotactic radiotherapy | |
Zhang et al. | Tracking tumor boundary in MV‐EPID images without implanted markers: A feasibility study | |
Li et al. | Augmented reality‐guided positioning system for radiotherapy patients | |
WO2020237537A1 (en) | Image guidance method and apparatus, and medical device and computer readable storage medium | |
Zhou et al. | Development of a deep learning‐based patient‐specific target contour prediction model for markerless tumor positioning | |
Hayashi et al. | Real‐time CT image generation based on voxel‐by‐voxel modeling of internal deformation by utilizing the displacement of fiducial markers | |
Yartsev et al. | Tomotherapy as a tool in image-guided radiation therapy (IGRT): current clinical experience and outcomes | |
Kim et al. | Interfractional diaphragmatic position variation according to stomach volume change during respiratory‐gated radiotherapy for hepatocellular carcinoma | |
Hoisak et al. | A history of surface guidance methods in radiation therapy | |
US20230404504A1 (en) | Kalman filter framework to estimate 3d intrafraction motion from 2d projection | |
Bekke | Evaluation of optical surface scanning of breast cancer patients for improved radiotherapy | |
Rozario et al. | An intra-fraction markerless daily lung tumor localization algorithm for EPID images | |
Abdullah et al. | Prediction of Motion of Chest Organs during Radiotherapy Using Image Registration Technique | |
Vergalasova | On-Board Imaging of Respiratory Motion: Investigation of Markerless and Self-Sorted Four-Dimensional Cone-Beam CT (4D-CBCT) |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |