CN1299642C - Multiple modality medical image registration method based on mutual information sensitive range - Google Patents
Multiple modality medical image registration method based on mutual information sensitive range Download PDFInfo
- Publication number
- CN1299642C CN1299642C CN 200310122434 CN200310122434A CN1299642C CN 1299642 C CN1299642 C CN 1299642C CN 200310122434 CN200310122434 CN 200310122434 CN 200310122434 A CN200310122434 A CN 200310122434A CN 1299642 C CN1299642 C CN 1299642C
- Authority
- CN
- China
- Prior art keywords
- mutual information
- registration
- image
- sensitizing range
- medical 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000000605 extraction Methods 0.000 claims abstract description 6
- 230000009466 transformation Effects 0.000 claims abstract description 6
- 230000001235 sensitizing effect Effects 0.000 claims description 55
- 239000000284 extract Substances 0.000 claims description 9
- 239000004744 fabric Substances 0.000 claims description 9
- 210000003484 anatomy Anatomy 0.000 claims description 6
- 238000007667 floating Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 claims description 2
- 238000003709 image segmentation Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000012800 visualization Methods 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 claims 1
- 238000010191 image analysis Methods 0.000 abstract description 3
- 238000003384 imaging method Methods 0.000 description 22
- 230000006870 function Effects 0.000 description 15
- 238000002600 positron emission tomography Methods 0.000 description 7
- 238000005481 NMR spectroscopy Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000003759 clinical diagnosis Methods 0.000 description 4
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 239000002356 single layer Substances 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000003925 brain function Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000003920 cognitive function Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 230000002503 metabolic effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000035479 physiological effects, processes and functions Effects 0.000 description 2
- 238000002603 single-photon emission computed tomography Methods 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000003325 tomography Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000004761 scalp Anatomy 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 210000004872 soft tissue Anatomy 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
Images
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a multi-mode medical image registration method based on mutual information sensitive regions, which relates to the technical field of medical image analysis. The present invention comprises the main steps of the determination and the extraction of the mutual information sensitive regions, and the registration of the mutual information sensitive regions. The mutual information sensitive regions of images to be registered are extracted firstly, then the registration for the mutual information sensitive regions is realized by a mutual information maximization method, and thereby, the registration for the images to be registered is realized. The present invention can realize rapid and robust multi-mode medical image registration and is particularly suitable for registration of multi-mode head images. (The robustness in here refers to the insensitive initial value for space transformation of the registration method of the present invention.).
Description
Technical field
The present invention relates to the medical image analysis technical field, particularly a kind of multimodal medical image registration method based on the mutual information sensitizing range.
Background technology
Increasing imaging mode has appearred in the continuous development along with the medical image technology, and is widely used in the research and medical clinical diagnosis and treatment of big brain cognitive function.Because the principle of imaging is different with equipment, there is multiple imaging pattern, they mainly comprise anatomical structure imaging pattern (as: the area of computer aided x-ray tomography imaging (CT) of describing physiology and appearance, NMR (Nuclear Magnetic Resonance)-imaging (MRI) etc.) and describe bodily fuctions or metabolic functional imaging pattern (as: single photon emission tomography (SPECT), PET (positron emission tomography) (PET) and function NMR (Nuclear Magnetic Resonance)-imaging (fMRI) etc.) two big classes.This two classes imaging mode respectively has pluses and minuses, and the spatial resolution height of anatomical structure imaging can provide the anatomic structure information of human body; The functional imaging spatial resolution is lower, but the function information of human internal organs, brain etc. can be provided; Even same class imaging mode, the information that provides is also incomplete same, for example, CT can show the structure image of skeleton clearly in structure imaging, MRI is fit to the imaging of soft tissue form, therefore, and the information that the imaging mode of different modalities can provide form and function aspects to complement each other.
In brain function research and medical clinical diagnosis treatment,, need carry out various modes or, promptly, carry out analysis-by-synthesis same individual or a plurality of people usually simultaneously from a few width of cloth Image Acquisition information with a kind of repeatedly imaging of pattern based on multiple reason.To achieve these goals, Medical image registration is the problem that must solve.Medical figure registration is meant for two width of cloth or several medical images seeks a kind of (or a series of) spatial alternation, make they the pixel representative anatomic points spatially reach the concordance correspondence.Thereby reach the purpose that a few width of cloth image informations merge.
Present existing medical image registration method is broadly divided into two classes: based on the method for characteristics of image coupling with based on the maximized method of gradation of image information similarity.One of them famous method is that people such as Maes and Wells propose the maximized method for registering of mutual information, and the author is by finding the solution the purpose that the maximized spatial alternation of the mutual information that makes between the image subject to registration reaches image registration.The maximized method for registering of mutual information is present the most successful and representative a kind of multimodal medical image registration method, and its effectiveness and registration accuracy obtain many-sided checking.
Can there be following eight pieces by correlated technical literature:
[1]J.B.Antoine Maintz and M.A.Viergever″A Survey of Medical ImageRegistration″，Medical Image Analysis，Vol.2，No.1，pp.1-36，1998.
[2]F.Maes，A.Collignon，D.Vandermeulen，G.Marchal，and P.Suetens，″Multimodality Image Registration by Maximization of Mutual Information″，IEEE Tran.Medical Imaging，Vol.16，pp.187-198，1997.
[3]F.Maes，D.Vandermeulen，P.Suetens，″Comparative evaluation ofmultiresolution optimization strategies for multimodality image registration bymaximization of mutual information″，Medical Image Analysis，Vol.3，No.4，pp.373-386，1999
[4]J.P.W.Pluim，J.B.Antoine Maintz，M.A..Viergever，″ImageRegistration by Maximization of Combined Mutual Information and GradientInformation″，IEEE Trans.Medical Imaging，Vol.19，pp.809-814，2000
[5]C.Studholme，D.L.G.Hill and D.J.Hawkes，″An overlap invariantentropy measure of 3D medical image alignment″，Pattern Recognition，Vol.32，No.1，pp.71-86，1999
[6]W.M.Wells，III，P.Viola，H.Atsumi，S.Nakajima，and R.Kikinis，″Multi-modal Volume Registration by Maximization of Mutual Information″，Medical Image Analysis，Vol.1，pp.35-51，1996.
[7]J.West，J.M.Fitzpatrick，M.Y.Wang，B.M.Dawant，C.R.Maurer，Jr.，R.M.Kessler，and R.J.Maciunas，″Retrospective Intermodality RegistrationTechniques for Images of the Head：Surface-Based Versus Volume-Based″，IEEE Tran.Medical Imaging，Vol.18，No.2，pp.144-150，1999
[8]Yong Fan and Tianzi Jiang，″Fast and Robust Mutual Information basedRegistration for Images of the Head″，In Jian-Zhong Qian，Stefan Schaller，andShiyong Zhang，editors，Proceedings of the International Conference onDiagnostic Imaging and Analysis(ICDIA2002)，pp.162-167，ShanghaiScientific and Technological Literature Publishing House，Shanghai，China，2002.
Summary of the invention
The objective of the invention is to propose a kind of new multimodal medical image registration method, a kind of method of fast robust is provided for the registration of multi-modality medical image based on the mutual information sensitizing range.
Technical scheme of the present invention as shown in Figure 1, mainly comprises following two steps composition:
1, determining and extraction of information sensing zone:
(1) mutual information sensitizing range
In multimodal medical image registration was used, the mutual information sensitizing range of two width of cloth images subject to registration was defined as the image-region that meets the following conditions:
A) anatomical structure of image-region correspondence exists in two width of cloth images subject to registration jointly;
B) half-tone information of this image-region of image subject to registration roughly has one-to-one relationship.
For example in the head image registration application of MRI and CT, the mutual information sensitizing range is a scalp, the image-region of skull and background correspondence.
(2) extraction of mutual information sensitizing range
After determining the mutual information sensitizing range, can use sophisticated image segmentation algorithm to extract mutual information sensitive image zone.Owing to only need a floating image in the realization of method for registering, thereby can be from image subject to registration extract in the higher image of space resolution the mutual information sensitizing range.Here, robustness is meant that our method for registering is insensitive to the initial value of spatial alternation.
2, the registration of mutual information sensitizing range
Ultimate principle based on the multi-modality images method for registering of mutual information sensitizing range is to extract the mutual information sensitizing range from image subject to registration, thereby by realize the registration of image based on this mutual information sensitizing range of mutual information maximization approach registration.With the present invention of mathematical linguistics conceptual description, can be defined as definition: establish I
f(floating image) I
rWith (reference picture) is the image that two width of cloth are wanted registration or alignd, Ω
fWith Ω
rBe from mutual information sensitizing range to extract the epigraph.Registration is sought certain spatial alternation Φ: Ω exactly
f→ Ω
rMake Ω
fAnatomic points ω spatially with Ω
rAnatomic points Φ (ω) concordance correspondence.It is exactly the floating image Φ (I that makes after the conversion that this spatial alternation is generalized in the image
f(x
f, y
f, z
f)) and reference picture I
r(x
r, y
r, z
r) the anatomical structure concordance correspondence spatially of representative.On mathematics, can obtain this spatial alternation by finding the solution following optimization problem
F wherein
SimilarityBe given similarity measurement, and θ ∈ Θ is the parameter of spatial alternation.
In multimodal medical image registration method based on the mutual information sensitizing range, adopt normalized mutual information or mutual information as similarity measurement,
The present invention and existing multimodal medical image registration technology relatively have following advantage:
The present invention has at first proposed the mutual information maximization medical image registration method based on the mutual information sensitizing range.Compare with medical image method in the past, this technology all increases significantly on the robustness of registration and registration speed.
This method is compared based on the maximized method for registering of mutual information with classics, embody very big advantage in robustness aspect finding the solution, be that the mutual information registration function has the bigger domain of attraction of separating, mainly show: (1) is at the comparison of the registration function curve of image translation; (2) the registration function curve at the image rotation compares.This external the present invention, the calculating strength in the method for registering images is reduced greatly owing to adopt the mutual information sensitizing range.A large amount of experiments shows that this method is a fast robust.
Description of drawings
Fig. 1 is based on the flow chart of the multimodal medical image registration method of mutual information sensitizing range.
S1 extracts the mutual information sensitizing range from original floating image.
S2 is for to carry out spatial alternation to the mutual information sensitizing range that extracts.
S3 is the mutual information in the zone of mutual information sensitizing range after the computer memory conversion and its space corresponding reference image.
S4 is for to judge whether the spatial alternation among the S2 makes the mutual information that calculates among the S3 reach extreme value, as reaches extreme value, then carries out S5: stop to calculate the output region transformation parameter; As not reaching extreme value, then carry out S2.
S5 is according to registration results (spatial alternation parameter), carries out visual.
Fig. 2 demonstration result who multi-modality images is carried out registration based on the maximized medical image registration method of the mutual information of mutual information sensitizing range.
Fig. 2 (a) is the monolayer image of original MRI image,
Fig. 2 (b) is the corresponding monolayer image of original CT image,
Fig. 2 (c) is the result who directly merges without registration,
Fig. 2 (d) is the result through merging behind the registration,
Fig. 2 (e) is the three-dimensional surface demonstration without the direct fusion results of registration,
Fig. 2 (f) is that the three-dimensional surface of fusion results behind the registration shows.
Fig. 3 shows based on the maximized medical image registration method of the mutual information of mutual information sensitizing range and is used for the two-dimensional result that the multi-modality images registration is the mutual information sensitizing range that extracts.
Fig. 3 (a) is the monolayer image of original MRI image,
Fig. 3 (b) is the mutual information sensitizing range that extracts,
Fig. 3 (c) is the space structure of mutual information sensitizing range.
The maximized medical image registration method of mutual information that Fig. 4 is based on the mutual information sensitizing range is used for Registration of MR I image and resulting mutual information registration function curve of CT image and normalized mutual information function curve, has provided the corresponding function curve of existing method simultaneously in Fig. 4 simultaneously.
Fig. 4 (a) is the mutual information function curve of image subject to registration during with respect to registration position genetic horizon internal rotation,
Fig. 4 (b) is the mutual information function curve of image subject to registration during with respect to registration position generation translation,
Fig. 4 (c) is the normalized mutual information function curve of image subject to registration during with respect to registration position genetic horizon internal rotation,
Fig. 4 (d) is the normalized mutual information function curve of image subject to registration during with respect to registration position generation translation.
The specific embodiment: be that example illustrates using method of the present invention only with Registration of MR I and CT picture headers image.
Increasing imaging mode has appearred in the continuous development along with the medical image technology, and is widely used in the research and medical clinical diagnosis and treatment of big brain cognitive function.Because the principle of imaging is different with equipment, have multiple imaging pattern, they mainly comprise the anatomical structure imaging pattern (as: CT, MRI etc.) of describing physiology and appearance and describe bodily fuctions or metabolic functional imaging pattern (as: fMRI, PET, SPECT etc.) two big classes.In brain function research and medical clinical diagnosis treatment,, need carry out various modes or, promptly, carry out analysis-by-synthesis same individual or a plurality of people usually simultaneously from a few width of cloth Image Acquisition information with a kind of repeatedly imaging of pattern based on multiple reason.To achieve these goals, Medical image registration is the problem that must solve.
Introduce below based on the maximized medical image registration method of the mutual information of mutual information sensitizing range:
Can be converted into a kind of optimization problem based on the maximized medical image registration method of the mutual information of mutual information sensitizing range, the work process of its registration can be in order to flowcharting down
The statement use of finishing the multi-modality images registration based on the maximized medical image registration method of the mutual information of mutual information sensitizing range now.Here provide same patient's nuclear magnetic resonance image (MRI) and example and the registration evaluation result thereof that the CT image carries out registration, had three aspects: the precision of registration, the amount of calculation of registration and registration function curve.
Among Fig. 1, provided flow chart based on the multimodal medical image registration method of mutual information sensitizing range.
S1 extracts the mutual information sensitizing range from original floating image.
S2 is for to carry out spatial alternation to the mutual information sensitizing range that extracts.
S3 is the mutual information in the zone of mutual information sensitizing range after the computer memory conversion and its space corresponding reference image.
S4 is for to judge whether the spatial alternation among the S2 makes the mutual information that calculates among the S3 reach extreme value, as reaches extreme value, then carries out S5: stop to calculate the output region transformation parameter; As not reaching extreme value, then carry out S2.
S5 is according to registration results (spatial alternation parameter), carries out visual.The output region transformation parameter provides visualization result.
Among Fig. 2, provided the image before the registration, and the example as a result of carrying out image co-registration before and after the registration, comprised 2 dimension examples and 3 dimension examples, from these figure we as can be seen our method have a very high precision.
Among Fig. 3, provided original image, mutual information sensitizing range, and the space structure of mutual information sensitizing range.
Because in our method, the calculating of mutual information is just based on the mutual information sensitizing range, and mainly concentrates on the calculating of mutual information based on the amount of calculation of the method for registering of mutual information, thereby reduces calculating strength greatly.The calculating strength of our method is 5%～6% of other method for registering, and the registration time on present ordinary individual's computer is generally less than 5 minutes.
Among Fig. 4, from these registration function curves we as can be seen, our method has the bigger domain of attraction of separating for existing method, thereby the easier realization of registration, has stronger robustness.The quantitative assessment of the registration accuracy of method shows that our method can obtain the precision of time pixel level.
The present invention can realize the multimodal medical image registration of fast robust, is particularly suitable for the registration of multi-modal head image.
In order to estimate the registration accuracy of our method quantitatively, we are to (the project " Evaluation of Retrospective ImageRegistration " of Vanderbilt Univ USA's " complete retrospective registration assessment item ", Vanderbilt University, Nashville, TN.) 41 couples of MR that provided and CT image, the 30 couples of MR and PET image have carried out the rigid body registration.This project has provided registration error evaluation (table 1,2) to our method registration results.This quantitative assessment shows that our method can obtain the precision (size of the pixel of CT image is 4mm, and the size of the pixel of PET image is 8mm) of time pixel level.PD is the PD parametric image of MRI in the table, and T1 is the T1 parametric image of MRI, and T2 is the T2 parametric image of MRI, PDrect, T1rect, with T2rect be respectively the result of the above-mentioned geometric correction of imagery.
The registration error of table one: MR and CT image (unit: millimeter)
| Error mean | The error intermediate value | Max value of error | Image is to number | |
| PD | 2.20 | 2.10 | 4.56 | 7 |
| T1 | 1.65 | 1.65 | 2.86 | 7 |
| T2 | 2.89 | 2.93 | 6.33 | 7 |
| PDrect | 1.17 | 1.01 | 2.90 | 7 |
| T1rect | 1.03 | 1.00 | 2.06 | 6 |
| T2rect | 1.28 | 1.09 | 3.80 | 7 |
The registration error of table two: MR and PET image (unit: millimeter)
| Error mean | The error intermediate value | Max value of error | Image is to number | |
| PD | 3.65 | 3.25 | 6.83 | 7 |
| T1 | 3.27 | 3.15 | 6.39 | 7 |
| T2 | 3.93 | 3.64 | 10.09 | 7 |
| PDrect | 2.90 | 2.31 | 7.01 | 5 |
| T1rect | 2.26 | 1.83 | 6.05 | 4 |
| T2rect | 2.57 | 2.03 | 6.20 | 5 |
Claims (5)
1. multimodal medical image registration method based on the mutual information sensitizing range, it is characterized in that, in the medical figure registration process, at first extract image-region to the mutual information sensitivity, realize the registration of image then by the above-mentioned mutual information sensitive image of registration zone, described mutual information sensitizing range is used for mutual information and calculates.
2. multimodal medical image registration method according to claim 1, it is characterized in that, the similarity measurement that uses when realizing the registration of mutual information sensitizing range adopts mutual information or normalized mutual information, and other is based on the combination entropy image similarity tolerance similar to mutual information.
According to the multimodal medical image registration method based on the mutual information sensitizing range of claim 1, it is characterized in that 3, determine and the extraction of mutual information sensitizing range comprise:
(1) mutual information sensitizing range
In multimodal medical image registration was used, the mutual information sensitizing range of two width of cloth images subject to registration was defined as the image-region that meets the following conditions:
A) anatomical structure of image-region correspondence exists in two width of cloth images subject to registration jointly;
B) half-tone information of this image-region of image subject to registration has one-to-one relationship;
(2) extraction of mutual information sensitizing range
After determining the mutual information sensitizing range, use sophisticated image segmentation algorithm to extract mutual information sensitive image zone.
4, according to the multimodal medical image registration method based on the mutual information sensitizing range of claim 1, it is characterized in that the registration of mutual information sensitizing range comprises:
Ultimate principle based on the multi-modality images method for registering of mutual information sensitizing range is to extract the mutual information sensitizing range from image subject to registration, thereby by realize the registration of image based on this mutual information sensitizing range of mutual information maximization approach registration.
5 one kinds of multimodal medical image registration methods based on the mutual information sensitizing range, its concrete steps are as follows;
S1 is extraction mutual information sensitizing range from original floating image,
S2 is for to carrying out spatial alternation in the mutual information sensitizing range that extracts,
S3 is the mutual information in the zone of mutual information sensitizing range after the computer memory conversion and its space corresponding reference image,
S4 is for to judge whether the spatial alternation among the S2 makes the mutual information that calculates among the S3 reach extreme value, as reaches extreme value, then carries out S5: stop to calculate the output region transformation parameter; As not reaching extreme value, then carry out S2,
S5 is according to registration results, and the spatial alternation parameter is carried out visually, and the output region transformation parameter provides visualization result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200310122434 CN1299642C (en) | 2003-12-23 | 2003-12-23 | Multiple modality medical image registration method based on mutual information sensitive range |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200310122434 CN1299642C (en) | 2003-12-23 | 2003-12-23 | Multiple modality medical image registration method based on mutual information sensitive range |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1631321A CN1631321A (en) | 2005-06-29 |
| CN1299642C true CN1299642C (en) | 2007-02-14 |
Family
ID=34844502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200310122434 Expired - Fee Related CN1299642C (en) | 2003-12-23 | 2003-12-23 | Multiple modality medical image registration method based on mutual information sensitive range |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1299642C (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204415A (en) * | 2015-05-04 | 2016-12-07 | 南京邮电大学 | A kind of novel method for registering images |
| US9934586B2 (en) | 2016-02-05 | 2018-04-03 | Sony Corporation | System and method for processing multimodal images |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070049817A1 (en) * | 2005-08-30 | 2007-03-01 | Assaf Preiss | Segmentation and registration of multimodal images using physiological data |
| CN100454337C (en) * | 2005-11-01 | 2009-01-21 | 中国科学院自动化研究所 | Method for registering images by combining space information |
| CN101334843B (en) * | 2007-06-29 | 2010-08-25 | 中国科学院自动化研究所 | Pattern recognition characteristic extraction method and apparatus |
| CN101303767B (en) * | 2007-11-15 | 2012-05-09 | 复旦大学 | Method for registration of digital cucoloris image based on self-adaption sort of block image contents |
| CN102971735B (en) * | 2010-06-30 | 2017-07-14 | 皇家飞利浦电子股份有限公司 | Interactive image analysis |
| CN102178505B (en) * | 2011-04-02 | 2012-10-10 | 南方医科大学 | Capsule endoscope-assisted film reading method and system thereof |
| CN103020976B (en) * | 2012-12-31 | 2015-08-19 | 中国科学院合肥物质科学研究院 | A kind of 3 d medical images method for registering based on cum rights Fuzzy Mutual Information and system |
| CN103593842B (en) * | 2013-10-25 | 2016-10-12 | 西安电子科技大学 | Based on intersect climb the mountain memetic quantum evolution calculate medical image registration method |
| CN106353354A (en) * | 2015-07-14 | 2017-01-25 | 艾斯拜克特成像有限公司 | Magnetic resonance imaging device and method for samples and processes under high temperature and high pressure |
| CN106408509A (en) * | 2016-04-29 | 2017-02-15 | 上海联影医疗科技有限公司 | Registration method and apparatus |
| CN106097347A (en) * | 2016-06-14 | 2016-11-09 | 福州大学 | A kind of multimodal medical image registration and method for visualizing |
| EP3264365A1 (en) * | 2016-06-28 | 2018-01-03 | Siemens Healthcare GmbH | Method and device for registration of a first image data set and a second image data set of a target region of a patient |
| CN107657989B (en) * | 2017-09-11 | 2021-05-28 | 山东第一医科大学(山东省医学科学院) | Multimodal medical image platform based on sparse learning and mutual information |
| CN108171738B (en) * | 2018-01-25 | 2022-02-01 | 北京雅森科技发展有限公司 | Multi-modal medical image registration method based on brain function template |
| CN108765399B (en) * | 2018-05-23 | 2022-01-28 | 平安科技（深圳）有限公司 | Lesion site recognition device, computer device, and readable storage medium |
-
2003
- 2003-12-23 CN CN 200310122434 patent/CN1299642C/en not_active Expired - Fee Related
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106204415A (en) * | 2015-05-04 | 2016-12-07 | 南京邮电大学 | A kind of novel method for registering images |
| CN106204415B (en) * | 2015-05-04 | 2020-09-01 | 南京邮电大学 | Image registration method |
| US9934586B2 (en) | 2016-02-05 | 2018-04-03 | Sony Corporation | System and method for processing multimodal images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN1631321A (en) | 2005-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1299642C (en) | Multiple modality medical image registration method based on mutual information sensitive range | |
| Makela et al. | A review of cardiac image registration methods | |
| US8774481B2 (en) | Atlas-assisted synthetic computed tomography using deformable image registration | |
| AU2014212517B2 (en) | Method and apparatus for generating a derived image using images of different types | |
| Zaidi et al. | Quantitative molecular positron emission tomography imaging using advanced deep learning techniques | |
| CN1920882A (en) | System and method for salient region feature based 3d multi modality registration of medical images | |
| Chowdhury et al. | Concurrent segmentation of the prostate on MRI and CT via linked statistical shape models for radiotherapy planning | |
| Gupta et al. | Study on anatomical and functional medical image registration methods | |
| Lei et al. | MRI-based pseudo CT generation using classification and regression random forest | |
| Shekhar et al. | High-speed registration of three-and four-dimensional medical images by using voxel similarity | |
| Gupta et al. | A hybrid framework for registration of carotid ultrasound images combining iconic and geometric features | |
| Dong et al. | Air, bone and soft-tissue segmentation on 3D brain MRI using semantic classification random forest with auto-context model | |
| Goldsmith et al. | Nonlinear tube-fitting for the analysis of anatomical and functional structures | |
| Zhang et al. | A novel medical image registration method based on mutual information and genetic algorithm | |
| Sabokrohiyeh et al. | Sketch-based registration of 3d cine mri to 4d flow mri | |
| Wang et al. | Automatic hybrid registration for 2-dimensional CT abdominal images | |
| Li et al. | SOMA: Subject‐, object‐, and modality‐adapted precision atlas approach for automatic anatomy recognition and delineation in medical images | |
| Bin et al. | Rapid multimodal medical image registration and fusion in 3D conformal radiotherapy treatment planning | |
| Liao et al. | A hybrid strategy to integrate surface-based and mutual-information-based methods for co-registering brain SPECT and MR images | |
| Hahn et al. | A practical salient region feature based 3d multi-modality registration method for medical images | |
| Pradeepa et al. | A multimodal image registration using mutual information | |
| Kamble et al. | 3D MRI Image Segmentation using 3D UNet Architectures: Technical | |
| Sreelekshmi et al. | A Review on Multimodal Medical Image Fusion | |
| Penhaker et al. | Image registration in neurology applications | |
| Trojacanec et al. | Content based retrieval of MRI based on brain structure changes in Alzheimer’s disease |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070214 Termination date: 20171223 |