CN105701846B - Medical image processing devices and method and medical imaging devices - Google Patents
Medical image processing devices and method and medical imaging devices Download PDFInfo
- Publication number
- CN105701846B CN105701846B CN201410705942.XA CN201410705942A CN105701846B CN 105701846 B CN105701846 B CN 105701846B CN 201410705942 A CN201410705942 A CN 201410705942A CN 105701846 B CN105701846 B CN 105701846B
- Authority
- CN
- China
- Prior art keywords
- image
- image processing
- processing devices
- medical image
- profile
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
This disclosure relates to medical image processing devices, medical image processing method and medical imaging devices.The medical image processing devices include determination unit, recognition unit and selecting unit.Determination unit is configured as the frequency domain character according to magnetic resonance marker image, determines the candidate image in magnetic resonance marker image sequence.Recognition unit is configured as identifying the profile of predetermined object in candidate image.Selecting unit is configured as being selected one of candidate image as the initial pictures for carrying out predetermined object motion analysis according to the shape feature of profile.
Description
Technical field
The present disclosure relates generally to Medical Image Processings, more particularly, to medical image processing devices, Medical Image Processing
Method and medical imaging devices.
Background technique
Magnetic resonance marker image (tagging image) can be used for the Noninvasive visualization and phase at locomotive organ or position
Pass processing, such as contour detecting, motion analysis etc..Mark line in tag image can be with time decline, it is possible to shadow
Ring the accuracy of contour detecting etc..
Summary of the invention
It has been given below about brief overview of the invention, in order to provide about the basic of certain aspects of the invention
Understand.It should be appreciated that this summary is not an exhaustive overview of the invention.It is not intended to determine pass of the invention
Key or pith, nor is it intended to limit the scope of the present invention.Its purpose only provides certain concepts in simplified form,
Taking this as a prelude to a more detailed description discussed later.
According to an aspect of the present invention, a kind of medical image processing devices are provided comprising determination unit, recognition unit
And selecting unit.Determination unit is configured as the frequency domain character according to magnetic resonance marker image, determines magnetic resonance marker image
Candidate image in sequence.Recognition unit is configured as identifying the profile of predetermined object in candidate image.Selecting unit is matched
It is set to and selects one of candidate image as the initial pictures for carrying out motion analysis to predetermined object according to the shape feature of profile.
According to another aspect of the present invention, a kind of medical image processing method is provided.This method includes according to magnetic resonance
The frequency domain character of tag image determines the step of candidate image in magnetic resonance marker image sequence.This method further includes in candidate
The step of profile of predetermined object is identified in image.This method further includes selecting one of candidate image according to the shape feature of profile
The step of as the initial pictures for carrying out motion analysis to predetermined object.
According to a further aspect of the invention, a kind of medical imaging devices are provided comprising according to an embodiment of the present invention
Medical image processing method.
According to another aspect of the present invention, a kind of program product of instruction code including machine-readable is provided.
When being read by computer and executing the instruction code, enable a computer to execute the above-mentioned medicine according to the embodiment of the present application
Image processing method.
According to a further aspect of the invention, provide it is a kind of carry it is above-mentioned include machine-readable instruction code
The storage medium of program product.
Embodiment through the invention can automatically select the higher tag image of picture quality, to be conducive to
Improve the accuracy of the processing such as Contour extraction.
Detailed description of the invention
The present invention can be by reference to being better understood, wherein in institute below in association with description given by attached drawing
Have and has used the same or similar appended drawing reference in attached drawing to indicate same or similar component.The attached drawing is together with following
It is described in detail together comprising in the present specification and forming a part of this specification, and is used to that this is further illustrated
The preferred embodiment and explanation the principle of the present invention and advantage of invention.In the accompanying drawings:
Fig. 1 is the block diagram for showing the configuration example of medical image processing devices according to an embodiment of the invention；
Fig. 2 is the exemplary curve graph for showing the frequency domain character of magnetic resonance marker image；
Fig. 3 shows the example of magnetic resonance marker image；
Fig. 4 shows the example of the candidate image of magnetic resonance marker image；
Fig. 5 is the block diagram for showing the configuration example of medical image processing devices in accordance with another embodiment of the present invention；
Fig. 6 is the block diagram for showing the configuration example of the medical image processing devices of another embodiment according to the present invention；
Fig. 7 is the flow chart for showing the process example of medical image processing method according to an embodiment of the invention；
Fig. 8 is the block diagram for showing the configuration example of medical imaging devices according to an embodiment of the invention；And
Fig. 9 is the block diagram for showing the exemplary structure for the computer that can be used to implement the process and apparatus of the present invention.
Specific embodiment
Illustrate the embodiment of the present invention below with reference to accompanying drawings.In an attached drawing of the invention or a kind of embodiment
The elements and features of description can be combined with elements and features shown in one or more other attached drawings or embodiment.
It should be noted that for purposes of clarity, unrelated to the invention, those of ordinary skill in the art have been omitted in attached drawing and explanation
The expression and description of the component and processing known.
As shown in Figure 1, including determination unit 110, recognition unit according to the medical image processing devices 100 of one embodiment
120 and selecting unit 130.
Determination unit 110 is configured as determining magnetic resonance marker image sequence according to the frequency domain character of magnetic resonance marker image
In candidate image.
It may include a series of magnetic resonance marker images being for example sequentially arranged in magnetic resonance marker image sequence.
As described in below in conjunction with specific embodiment, magnetic resonance marker image may include vertical tag image (such as the example institute of Fig. 3
Show) or level marks image (similar with the example of Fig. 3, mark line is horizontal direction), or may include vertical tag image
With the merging image of level marks image (as shown in the example of Fig. 4).
Frequency domain character refers to the feature in frequency domain extraction of tag image, is able to reflect marking signal in tag image
The clarity of intensity mark line in other words.
According to one embodiment, candidate image can be determined according to the amplitude of first harmonic in frequency domain.Mark line is in space
Two-dimentional sine wave (and off-gauge sine wave) subject to performance in domain, therefore in the frequency domain of tag image, as the example of Fig. 2 is shown
Out, other than the low frequency peak 202 at origin, symmetrically there are several harmonic peaks in 202 two sides of low frequency peak, i.e., it is primary humorous
The harmonic peaks of wave crest 201 and higher order, wherein first harmonic is able to reflect almost all marking signal.Marking signal is stronger, more
Conducive to obtaining better outline identification result.
More specifically, determination unit 110 can be configured as the magnetic that first harmonic amplitude in frequency domain is higher than to predeterminated level
Resonance tag image is determined as candidate image.Alternatively, can be high by the ratio between first harmonic amplitude and the amplitude at low frequency peak in frequency domain
It is determined as candidate image in the tag image of predetermined threshold (such as 75%).
It, can not be total to magnetic in the case where the amplitude based on first harmonic determines candidate image compared with predeterminated level
Whole tag images in vibration image sequence carry out this determination process, but can determine predetermined quantity candidate image
The determination process no longer is carried out to other tag images afterwards.
On the other hand, above-mentioned determining processing can also be carried out for all or part of image in magnetic resonance image sequence,
And the tag image of the higher predetermined number of first harmonic amplitude is determined as candidate image.
The frequency domain character of tag image can be obtained in several ways.For example, according to one embodiment, determination unit
Magnetic resonance marker image can be converted into frequency domain data by Fourier transformation by 110, and determine candidate based on frequency domain data
Image.Alternatively, determination unit 110 can be determined based on the K space data of magnetic resonance marker image according to another embodiment
Candidate image.
Recognition unit 120 is configured as identifying the profile of predetermined object in candidate image.
Recognition unit can carry out the outline identification based on tag image using several known methods, such as can use
Segmentation of Myocardial Boundaries in Tagged Cardiac MRI Using Active
Contours:A Gradient-Based Approach Integrating Texture Analysis,Aymeric
Description in Histace, et al. (International Journal of Biomedical Imaging Volume2009)
Method.
According to a specific embodiment, predetermined object includes cardiac muscle, more specifically, including myocardium of left ventricle.However this hair
Bright without being limited thereto, the object of outline identification also may include organ of any movement, such as muscle, joint etc..
According to one embodiment, merging image of the recognition unit 120 based on vertical tag image and level marks image come
Identify the profile of predetermined object.However the invention is not limited thereto, for example, in the feelings of the main horizontally extending profile of identification
Under condition, outline identification can be carried out based on vertical tag image, in the case where the profile that identification extends mainly in the vertical direction,
Outline identification can be carried out based on level marks image.
Referring to Fig. 4, example markup image (A, B, the C in figure for being confirmed as the myocardium of left ventricle of candidate image are shown
And D), it is the merging image of vertical tag image and level marks image.Also, it is shown in identified cardiac muscle
Profile.
Selecting unit 130 is configured as the shape feature selection candidate image of the profile identified according to recognition unit 120
One of as to predetermined object carry out motion analysis initial pictures.
According to the difference of imaging object, feature selecting standard can be taken different shapes.For example, according to specific object
Style characteristic, selecting unit 120 can circularities according to the profile that recognition unit 120 identifies, rectangular degree
(rectangularity) one or more and in main shaft ratio (axis ratio) select initial pictures.Such as this field
It is known, such as circularity can be characterized with the ratio between square of the perimeter for the area and profile that profile surrounds, it can be with profile
The ratio of the area minimum circumscribed rectangle that accounts for profile characterize rectangular degree (or referred to as compactedness), main shaft ratio can be with finger wheel exterior feature
Ratio of semi-minor axis length.For example, can the circularity of profile is higher, rectangular degree is higher or main shaft relatively 1 tag image
It is selected as above-mentioned initial pictures.
In the example shown in figure 4, it is based on above-mentioned standard, tag image D is selected as initial pictures.
According to the style characteristic of imaging object, the profile for meeting corresponding predetermined condition is more likely to be aligned really to identify
Profile, by the accuracy for using the profile as above selected as initial pictures, being conducive to improve subsequent Contour extraction process.
The initial pictures selected by the selecting unit 130 according to the medical image processing devices 100 of the present embodiment can be by
It provides or notifies to other Medical Image Processing equipment to carry out subsequent processing, such as Contour extraction or motion analysis.Alternatively, such as
It will illustrate below, medical image equipment according to an embodiment of the present invention may include that other unit is such as used for Contour extraction
Or the unit of motion analysis, and subsequent processing is carried out according to the initial pictures that selecting unit 130 selects.
In addition, as shown in figure 5, including determination unit 510 according to the medical image processing devices 500 of one embodiment, knowing
Other unit 520, selecting unit 530 and optimization unit 540.Wherein it is determined that unit 510, recognition unit 520 and selecting unit
530 configuration is similar with the configuration described above by reference to Fig. 1, omits the detailed description herein.
Optimization unit 540 is configured as optimizing identified profile using algorithm of convex hull.Optimization unit 540 can use
Algorithm of convex hull known in the art, such as Graham scanning algorithm etc..By optimizing the processing of unit 540, the profile identified
In concave portion can be processed, occur during subsequent Contour extraction contour line to reduce and the error conditions such as intersect
Occur.
In addition, as shown in fig. 6, including determination unit 610 according to the medical image processing devices 600 of one embodiment, knowing
Other unit 620, selecting unit 630 and tracking cell 640.Wherein it is determined that unit 610, recognition unit 620 and selecting unit
630 configuration is similar with the configuration described above by reference to Fig. 1, omits the detailed description herein.
The image that tracking cell 640 is configured as selecting using selecting unit 630 is as initial pictures in medical image
Predetermined object carry out Contour extraction.
Tracking cell 640 can be used to be retouched in a variety of contour tracing methods, such as US6757423B1 or US6892089B1
The method stated.
Although it may be noted that being illustrated herein mainly for the example of two-dimensional medical images, above-mentioned medicine figure
As may include two dimensional image or 3-D image.It correspondingly, can be using the respective algorithms for two dimensional image and 3-D image
Carry out above-mentioned various processing.
During description to the medical image processing devices in embodiment above, it is clear that also disclose some processing
Or method.Hereinafter, the general introduction of these methods is provided in the case where not repeating the certain details being already discussed above.
As shown in fig. 7, including the frequency according to magnetic resonance marker image according to the medical image processing method of one embodiment
Characteristic of field determines the step of candidate image in magnetic resonance marker image sequence (S710)；Predetermined object is identified in candidate image
Profile the step of (S720)；And one of candidate image is selected to transport as to predetermined object according to the shape feature of profile
The step of initial pictures of dynamic analysis (S730).
In step S710, the magnetic resonance marker image that first harmonic amplitude in frequency domain can be higher than to predeterminated level is determined
For candidate image.First harmonic amplitude is higher than the amplitude that predeterminated level for example may include: first harmonic and is higher than predetermined threshold, or
The ratio between amplitude and the amplitude at low frequency peak of person's first harmonic are higher than predetermined threshold.
In step S710, magnetic resonance marker image can be converted by frequency domain data by Fourier transformation, and be based on
Frequency domain data determines candidate image；Alternatively, can determine candidate image based on the K space data of magnetic resonance marker image.
In step S710, candidate image can be determined based on vertical tag image or level marks image.
In step S720, can the merging image based on vertical tag image and level marks image come contour identification.
In step S730, it can be selected according to one or more than in of the circularity of profile, rectangular degree and main shaft
Select initial pictures.
In medical image processing method according to an embodiment of the present invention, predetermined object may include myocardium of left ventricle.
Medical image processing method according to an embodiment of the present invention can also be identified including the use of algorithm of convex hull to optimize
Profile the step of.
In addition, medical image processing method according to an embodiment of the present invention can also include carrying out Contour extraction to object
Step.
The embodiment of the present invention further includes medical imaging devices, such as MR imaging apparatus.As shown in figure 8, according to this
The medical imaging devices 800 of inventive embodiments include medical image processing devices 810.Medical image processing devices 810 can have
There is the configuration of the front medical image processing devices according to an embodiment of the present invention that-Fig. 6 illustrates referring to Fig.1.
In addition, the embodiment of the present invention further include include machine-readable instruction code program product, by counting
It calculates machine-readable when taking and executing described instruction code, enables a computer to execute Medical Image Processing according to an embodiment of the present invention
Method, or it is used as medical image processing devices according to an embodiment of the present invention.
In addition, the embodiment of the present invention further includes the storage medium for carrying above procedure product.
As an example, each composition of each step of above-mentioned image processing method and above-mentioned image processing apparatus
Module and/or unit may be embodied as software, firmware, hardware or combinations thereof.It, can in the case where being realized by software or firmware
To be installed from storage medium or network to the computer (such as general purpose computer 900 shown in Fig. 9) with specialized hardware structure
The program for implementing the software of the above method is constituted, which is able to carry out various functions when being equipped with various programs
Deng.
In Fig. 9, operation processing unit (i.e. CPU) 901 according to the program stored in read-only memory (ROM) 902 or from
The program that storage section 908 is loaded into random access memory (RAM) 903 executes various processing.In RAM 903, also basis
Need to store the data required when CPU 901 executes various processing etc..CPU 901, ROM 902 and RAM 903 are via total
The link each other of line 904.Input/output interface 905 also link to bus 904.
Components described below link is to input/output interface 905: importation 906 (including keyboard, mouse etc.), output section
Divide 907 (including display, such as cathode-ray tube (CRT), liquid crystal display (LCD) etc. and loudspeakers etc.), storage section
908 (including hard disks etc.), communications portion 909 (including network interface card such as LAN card, modem etc.).Communications portion 909
Communication process is executed via network such as internet.As needed, driver 910 can also link to input/output interface 905.
Detachable media 911 such as disk, CD, magneto-optic disk, semiconductor memory etc. is installed in driver 910 as needed
On, so that the computer program read out is mounted to as needed in storage section 908.
It is such as removable from network such as internet or storage medium in the case where series of processes above-mentioned by software realization
Unload the program that the installation of medium 911 constitutes software.
It will be understood by those of skill in the art that this storage medium be not limited to it is shown in Fig. 9 be wherein stored with program,
Separately distribute with equipment to provide a user the detachable media 911 of program.The example of detachable media 911 includes disk
(including floppy disk (registered trademark)), CD (including compact disc read-only memory (CD-ROM) and digital versatile disc (DVD)), magneto-optic disk
(including mini-disk (MD) (registered trademark)) and semiconductor memory.Alternatively, storage medium can be ROM 902, storage section
Hard disk for including in 908 etc., wherein computer program stored, and user is distributed to together with the equipment comprising them.
The present invention also proposes a kind of program product of instruction code for including machine-readable.Described instruction code is by machine
When device reads and executes, above-mentioned image processing method according to an embodiment of the present invention can be performed.
Correspondingly, it is also wrapped for carrying the storage medium of the program product of the above-mentioned instruction code for including machine-readable
It includes in disclosure of the invention.The storage medium includes but is not limited to floppy disk, CD, magneto-optic disk, storage card, memory stick etc.
Deng.
In the description above to the specific embodiment of the invention, for the feature a kind of embodiment description and/or shown
It can be used in one or more other embodiments with same or similar mode, with the feature in other embodiment
It is combined, or the feature in substitution other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, element, step or component when using herein, but simultaneously
It is not excluded for the presence or additional of one or more other features, element, step or component.
In above-described embodiment and example, each step and/or unit are indicated using the appended drawing reference of number composition.
It should be appreciated by those skilled in the art that these appended drawing references are only to facilitate describing and drawing, and not indicate that its is suitable
Sequence or any other restriction.
In addition, method of the invention be not limited to specifications described in time sequencing execute, can also according to it
His time sequencing, concurrently or independently execute.Therefore, the execution sequence of method described in this specification is not to this hair
Bright technical scope is construed as limiting.
Although being had been disclosed above by the description to specific embodiments of the present invention to the present invention, it answers
The understanding, above-mentioned all embodiments and example are exemplary, and not restrictive.Those skilled in the art can be in institute
Design is to various modifications of the invention, improvement or equivalent in attached spirit and scope of the claims.These modification, improve or
Person's equivalent should also be as being to be considered as included in protection scope of the present invention.
According to above description, it is known that the application at least discloses following technical scheme:
It is attached a kind of 1. medical image processing devices, comprising:
Determination unit is configured as the frequency domain character according to magnetic resonance marker image, determines magnetic resonance marker image sequence
In candidate image；
Recognition unit is configured as identifying the profile of predetermined object in the candidate image；And
Selecting unit is configured as the shape feature according to the profile, selects one of described candidate image as to institute
State the initial pictures that predetermined object carries out motion analysis.
The medical image processing devices according to note 1 of note 2., wherein
The determination unit is configured as: first harmonic amplitude in frequency domain is higher than to the magnetic resonance marker of predeterminated level
Image is determined as the candidate image.
The medical image processing devices according to note 2 of note 3., wherein
The magnetic resonance marker image is converted into frequency domain data by Fourier transformation by the determination unit, and is based on institute
It states frequency domain data and determines the candidate image.
The medical image processing devices according to note 2 of note 4., wherein
The determination unit determines the candidate image based on the K space data of the magnetic resonance marker image.
The medical image processing devices according to note 1 of note 5., wherein the determination unit is based on vertical label figure
As or level marks image determine the candidate image.
The medical image processing devices according to note 1 of note 6., wherein the recognition unit is based on vertical label figure
The merging image of picture and level marks image identifies the profile.
The medical image processing devices according to note 1 of note 7., wherein the selecting unit is according to the profile
One or more than in of circularity, rectangular degree and main shaft select the initial pictures.
The medical image processing devices according to any one of note 1 to 7 of note 8., wherein the predetermined object packet
Include myocardium of left ventricle.
The medical image processing devices according to any one of note 1 to 7 of note 9., further includes:
Optimize unit, is configured as optimizing identified profile using algorithm of convex hull.
The medical image processing devices according to any one of note 1 to 7 of note 10., further includes:
Tracking cell is configured as carrying out Contour extraction to the object.
It is attached a kind of 11. medical image processing methods, comprising:
According to the frequency domain character of magnetic resonance marker image, the candidate image in magnetic resonance marker image sequence is determined；
The profile of predetermined object is identified in the candidate image；And
According to the shape feature of the profile, one of described candidate image is selected to move as to the predetermined object
The initial pictures of analysis.
The medical image processing method according to note 11 of note 12., wherein be higher than first harmonic amplitude in frequency domain
The magnetic resonance marker image of predeterminated level is determined as the candidate image.
The medical image processing method according to note 12 of note 13., wherein be total to the magnetic by Fourier transformation
Vibration tag image is converted into frequency domain data, and determines the candidate image based on the frequency domain data.
The medical image processing method according to note 12 of note 14., wherein based on the magnetic resonance marker image
K space data determines the candidate image.
The medical image processing method according to note 11 of note 15., wherein based on vertical tag image or horizontal mark
Image is remembered to determine the candidate image.
The medical image processing method according to note 11 of note 16., wherein based on vertical tag image and horizontal mark
The merging image of image is remembered to identify the profile.
The medical image processing method according to note 11 of note 17., wherein according to the circularity of the profile, square
One or more than in of shape degree and main shaft select the initial pictures.
The medical image processing method according to any one of note 11 to 17 of note 18., wherein the predetermined object
Including myocardium of left ventricle.
The medical image processing method according to any one of note 11 to 17 of note 19., further comprising the steps of:
Optimize identified profile using algorithm of convex hull.
The medical image processing method according to any one of note 11 to 17 of note 20., further comprising the steps of:
Contour extraction is carried out to the object.
It is attached a kind of 21. medical imaging devices comprising the Medical Image Processing according to any one of note 1-10
Device.
Be attached 22. it is a kind of include machine-readable instruction code program product, read by computer and executed
When described instruction code, so that the computer is able to carry out the medical image processing method as described in note 11 to 20, or
As the medical image processing devices as described in note 1 to 10.
Be attached 23. it is a kind of carrying just like note 22 described in program product storage medium.
Claims (12)
1. a kind of medical image processing devices, comprising:
Determination unit is configured as the frequency domain character according to magnetic resonance marker image, determines in magnetic resonance marker image sequence
Candidate image；
Recognition unit is configured as identifying the profile of predetermined object in the candidate image；And
Selecting unit is configured as the shape feature according to the profile, selects one of described candidate image as to described pre-
Determine the initial pictures that object carries out motion analysis.
2. medical image processing devices according to claim 1, wherein
The determination unit is configured as: first harmonic amplitude in frequency domain is higher than to the magnetic resonance marker image of predeterminated level
It is determined as the candidate image.
3. medical image processing devices according to claim 2, wherein
The magnetic resonance marker image is converted into frequency domain data by Fourier transformation by the determination unit, and is based on the frequency
Numeric field data determines the candidate image.
4. medical image processing devices according to claim 2, wherein
The determination unit determines the candidate image based on the K space data of the magnetic resonance marker image.
5. medical image processing devices according to claim 1, wherein the determination unit be based on vertical tag image or
Level marks image determines the candidate image.
6. medical image processing devices according to claim 1, wherein the recognition unit be based on vertical tag image and
The merging image of level marks image identifies the profile.
7. medical image processing devices according to claim 1, wherein the selecting unit is according to the circle of the profile
One or more than in of degree, rectangular degree and main shaft select the initial pictures.
8. medical image processing devices according to any one of claim 1 to 7, wherein the predetermined object includes a left side
Myocardium of ventricle.
9. medical image processing devices according to any one of claim 1 to 7, further includes:
Optimize unit, is configured as optimizing identified profile using algorithm of convex hull.
10. medical image processing devices according to any one of claim 1 to 7, further includes:
Tracking cell is configured as carrying out Contour extraction to the predetermined object.
11. a kind of medical image processing method, comprising:
According to the frequency domain character of magnetic resonance marker image, the candidate image in magnetic resonance marker image sequence is determined；
The profile of predetermined object is identified in the candidate image；And
According to the shape feature of the profile, one of described candidate image is selected to carry out motion analysis as to the predetermined object
Initial pictures.
12. a kind of medical imaging devices comprising medical image processing devices according to claim 1 to 10.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705942.XA CN105701846B (en) | 2014-11-27 | 2014-11-27 | Medical image processing devices and method and medical imaging devices |
| JP2015083699A JP6466233B2 (en) | 2014-11-27 | 2015-04-15 | Medical image processing apparatus, medical image processing method, and medical imaging apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410705942.XA CN105701846B (en) | 2014-11-27 | 2014-11-27 | Medical image processing devices and method and medical imaging devices |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105701846A CN105701846A (en) | 2016-06-22 |
| CN105701846B true CN105701846B (en) | 2019-01-15 |
Family
ID=56088281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410705942.XA Active CN105701846B (en) | 2014-11-27 | 2014-11-27 | Medical image processing devices and method and medical imaging devices |
Country Status (2)
| Country | Link |
|---|---|
| JP (1) | JP6466233B2 (en) |
| CN (1) | CN105701846B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476761B (en) * | 2020-03-18 | 2023-07-21 | 河北科技大学 | Visibility measurement method and system based on system identification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1515912A (en) * | 2003-08-27 | 2004-07-28 | 中国人民解放军第一军医大学 | Automatic reverse correcting method of nuclear magnetic resonance image rigid translational aliasing artifact |
| EP2736015A1 (en) * | 2012-11-26 | 2014-05-28 | Samsung Electronics Co., Ltd | Method and apparatus for medical image registration |
| CN104156975A (en) * | 2013-05-13 | 2014-11-19 | 株式会社东芝 | Medical image analyzing device and method and medical imaging device |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5275163A (en) * | 1991-04-02 | 1994-01-04 | U.S. Philips Corporation | Magnetic resonance imaging method and device for monitoring motion of a part of an object |
| JP3392690B2 (en) * | 1997-03-17 | 2003-03-31 | 株式会社東芝 | Image processing method and image processing apparatus |
| CA2368237A1 (en) * | 1999-04-22 | 2000-11-02 | The Johns Hopkins University | Cardiac motion tracking using cine harmonic phase (harp) magnetic resonance imaging |
| US6597935B2 (en) * | 2000-02-10 | 2003-07-22 | The Johns Hopkins University | Method for harmonic phase magnetic resonance imaging |
| JP3751591B2 (en) * | 2000-10-31 | 2006-03-01 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | Method and system for tag detection and tracking in MRI tagged images |
| JP4163526B2 (en) * | 2003-02-12 | 2008-10-08 | 独立行政法人科学技術振興機構 | Displacement measurement system and method using MR tagging images |
| WO2009051123A1 (en) * | 2007-10-18 | 2009-04-23 | Hitachi Medical Corporation | Magnetic resonance imaging device |
| CN105105775B (en) * | 2011-07-19 | 2018-11-09 | 东芝医疗系统株式会社 | Cardiac motion resolver |
-
2014
- 2014-11-27 CN CN201410705942.XA patent/CN105701846B/en active Active
-
2015
- 2015-04-15 JP JP2015083699A patent/JP6466233B2/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1515912A (en) * | 2003-08-27 | 2004-07-28 | 中国人民解放军第一军医大学 | Automatic reverse correcting method of nuclear magnetic resonance image rigid translational aliasing artifact |
| EP2736015A1 (en) * | 2012-11-26 | 2014-05-28 | Samsung Electronics Co., Ltd | Method and apparatus for medical image registration |
| CN104156975A (en) * | 2013-05-13 | 2014-11-19 | 株式会社东芝 | Medical image analyzing device and method and medical imaging device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105701846A (en) | 2016-06-22 |
| JP6466233B2 (en) | 2019-02-06 |
| JP2016101470A (en) | 2016-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jimenez-del-Toro et al. | Cloud-based evaluation of anatomical structure segmentation and landmark detection algorithms: VISCERAL anatomy benchmarks | |
| JP6993334B2 (en) | Automated cardiac volume segmentation | |
| US8837789B2 (en) | Systems, methods, apparatuses, and computer program products for computer aided lung nodule detection in chest tomosynthesis images | |
| CN107886508B (en) | Differential subtraction method and medical image processing method and system | |
| Chang et al. | Segmentation of breast tumor in three-dimensional ultrasound images using three-dimensional discrete active contour model | |
| Jafari et al. | Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training | |
| Yang et al. | Fully automatic segmentation and objective assessment of atrial scars for long‐standing persistent atrial fibrillation patients using late gadolinium‐enhanced MRI | |
| JP4964171B2 (en) | Target region extraction method, apparatus, and program | |
| Mahmoudi et al. | GPU-based segmentation of cervical vertebra in X-ray images | |
| CN101681514A (en) | Inspection of tubular-shaped structures | |
| Morais et al. | Cardiac motion and deformation estimation from tagged MRI sequences using a temporal coherent image registration framework | |
| Yao et al. | Advances on pancreas segmentation: a review | |
| Gao et al. | Segmentation of ultrasonic breast tumors based on homogeneous patch | |
| Khallaghi et al. | Experimental validation of an intrasubject elastic registration algorithm for dynamic‐3D ultrasound images | |
| CN104156975B (en) | Medical image analysis apparatus and method and medical imaging devices | |
| CN105701846B (en) | Medical image processing devices and method and medical imaging devices | |
| CN104146766B (en) | Scanning means, scan method and medical image equipment | |
| Cruz-Aceves et al. | Multiple active contours guided by differential evolution for medical image segmentation | |
| Li et al. | Automated motion-artifact correction in an OCTA image using tensor voting approach | |
| Zhou et al. | Automatic segmentation of liver from CT scans with CCP–TSPM algorithm | |
| WO2014106747A1 (en) | Methods and apparatus for image processing | |
| Arega et al. | Using Polynomial Loss and Uncertainty Information for Robust Left Atrial and Scar Quantification and Segmentation | |
| US11295451B2 (en) | Robust pulmonary lobe segmentation | |
| JP2017111129A (en) | Contour extraction device, contour extraction method and program | |
| Wang et al. | Three-dimensional structure tensor based PET/CT fusion in gradient domain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160708 Address after: Japan Tochigi Tian Yuan City Applicant after: Toshiba Medical System Co., Ltd. Address before: Tokyo, Japan, Japan Applicant before: Toshiba Corp Applicant before: Toshiba Medical System Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |