CN110473143A - A kind of three-dimensional MRA medical image joining method and device, electronic equipment - Google Patents
A kind of three-dimensional MRA medical image joining method and device, electronic equipment Download PDFInfo
- Publication number
- CN110473143A CN110473143A CN201910666640.9A CN201910666640A CN110473143A CN 110473143 A CN110473143 A CN 110473143A CN 201910666640 A CN201910666640 A CN 201910666640A CN 110473143 A CN110473143 A CN 110473143A
- Authority
- CN
- China
- Prior art keywords
- image
- overlapping region
- region
- overlapping
- fused
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 83
- 238000005304 joining Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 43
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 230000002708 enhancing effect Effects 0.000 claims abstract description 8
- 230000001788 irregular Effects 0.000 claims abstract description 8
- 238000009499 grossing Methods 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 25
- 230000009466 transformation Effects 0.000 claims description 25
- 238000002224 dissection Methods 0.000 claims description 16
- 239000000523 sample Substances 0.000 claims description 10
- 238000003384 imaging method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 10
- 239000003814 drug Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000002583 angiography Methods 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 230000002308 calcification Effects 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005401 electroluminescence Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
- 230000002792 vascular Effects 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
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/32—Indexing scheme for image data processing or generation, in general involving image mosaicing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The present invention is more particularly directed to a kind of three-dimensional MRA medical image joining method and devices, electronic equipment.The described method includes: carrying out Laplce's denoising, enhancing and irregular smoothing processing to the two neighboring three-dimensional MRA medical image to be spliced that real-time reception arrives, the first image and the second image are obtained；Overlapping Layer Detection is carried out to the first image and the second image, determines the second overlapping region in the first overlapping region and the second image in the first image；Anastomosing and splicing processing is carried out to the first overlapping region and the second overlapping region using weighted mean method, the third image after obtaining anastomosing and splicing.It can be seen that, the embodiment of the present invention is by carrying out overlapping Layer Detection to pretreated two neighboring three-dimensional MRA medical image to be spliced respectively, determine the overlapping region in two three-dimensional MRA medical images to be spliced, then anastomosing and splicing is carried out to two overlapping regions, it can be improved the determination efficiency of overlapping region in image, and then improve image mosaic efficiency.
Description
Technical field
The present invention relates to technical field of medical image processing, in particular to a kind of three-dimensional MRA medical image joining method and
Device, electronic equipment.
Background technique
Magnetic resonance angiography (Magnetic Resonance Angiography, MRA) is a kind of utilization electromagnetic wave production
The inspection method for describing the 3 d medical images of human body information is given birth to, by the inspection method, panorama three-dimensional doctor can be obtained
Image is learned, preferably help doctor carries out comprehensive, intuitive evaluation to the state of an illness.
But in MRA inspection, due to the limitation of MRA equipment, can not one-off scanning obtain panorama 3 d medical images,
It is generally necessary to carry out segmentation imaging, then two often adjacent segmentations are spliced, panorama 3 d medical images could be obtained.
Therefore, 3 d medical images splicing has a wide range of applications in medical image research, or even in the life insurance air control of financial industry
In also become a kind of new application method, for example, the panorama 3 d medical images passed through to spliced insurer carry out intelligence
Analysis, can help the application of insuring for auditing insurer.
In the prior art, when carrying out 3 d medical images splicing, usually by doctor manually by three-dimensional to be spliced
Medical image reaches visual overlapping region by operations such as translations and merges, to determine that picture registration region carries out image spelling
It connects.Can be too low using the artificial efficiency for determining picture registration region in this mode, and accuracy is not high, time-consuming, to lead
Cause image mosaic efficiency excessively low.
Summary of the invention
In order to solve the problems, such as that image mosaic efficiency present in the relevant technologies is excessively low, the present invention provides one kind three
Tie up MRA medical image joining method and device, electronic equipment.
First aspect of the embodiment of the present invention discloses a kind of three-dimensional MRA medical image joining method, which comprises
The two neighboring three-dimensional MRA medical image to be spliced that real-time reception scanning device is sent；
Laplce's denoising, enhancing and irregular smooth are carried out to the two neighboring three-dimensional MRA medical image to be spliced
Processing obtains the first image and the second image；
Overlapping Layer Detection is carried out to the first image and second image respectively, to determine in the first image
The second overlapping region in first overlapping region and second image；
Anastomosing and splicing processing is carried out to first overlapping region and second overlapping region using weighted mean method, is obtained
Third image after obtaining anastomosing and splicing.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described to utilize weighted mean method pair
First overlapping region and second overlapping region carry out anastomosing and splicing processing, the third image after obtaining anastomosing and splicing it
Afterwards, the method also includes:
The disposal of gentle filter is carried out to the third image using low-pass filter, obtains smooth target image.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described respectively to first figure
Picture and second image carry out overlapping Layer Detection, to determine the first overlapping region and second figure in the first image
Before the second overlapping region as in, the method also includes:
The first image and the respective maximum intensity projection imaging of second image are compared, to determine
State first in the first image the second coincidence segment being overlapped in segment and second image；
And it is described overlapping Layer Detection is carried out to the first image and second image respectively, with determination described
The second overlapping region in the first overlapping region and second image in one image, comprising:
Overlapping Layer Detection is carried out to the first coincidence segment and the second coincidence segment, to determine the first image
In the first overlapping region and second image in the second overlapping region.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described to first overlapping slice
Section and the second coincidence segment carry out overlapping Layer Detection, to determine the first overlapping region in the first image and described the
The second overlapping region in two images, comprising:
The first coincidence segment is divided into the multiple first regions to be measured, and the second coincidence segment is divided into multiple
Second region to be measured, first region to be measured are corresponded with the described second region to be measured；
Successively judge the quantity in each described first region to be measured with the overlapping layer in corresponding second region to be measured
Whether difference is less than default value；
If the difference is less than the default value, using the described first region to be measured as first in the first image
The component part of overlapping region, using corresponding second region to be measured as the second overlapping region in second image
Component part, with determination first overlapping region and second overlapping region.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described by the described first area to be measured
Component part of the domain as the first overlapping region in the first image, using corresponding second region to be measured as described in
The component part of the second overlapping region in second image, with determination first overlapping region and second overlapping region it
Afterwards and it is described anastomosing and splicing processing is carried out to the first overlapping region and the second overlapping region using weighted mean method, melted
Before closing spliced third image, the method also includes:
According to the image location information of the first image and second image, sampled point is determined；Wherein, described image
Location information is used to describe the first image and second image corresponds to the position of human dissection coordinate system；
According to the first image coordinate of the human dissection coordinate of the sampled point, the sampled point in the first image
And the second image coordinate in second image, obtain registration transformation matrix；
According to the registration transformation matrix, it is registrated first overlapping region and second overlapping region.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described according to the registration transformation
Matrix is registrated first overlapping region and second overlapping region, comprising:
Using first overlapping region as benchmark region, will there are same human body anatomic coordinates in second overlapping region
Point the same position of first overlapping region is registrated to by the registration transformation matrix；Alternatively,
Using second overlapping region as benchmark region, will there are same human body anatomic coordinates in first overlapping region
Point the same position of second overlapping region is registrated to by the registration transformation matrix.
As an alternative embodiment, in first aspect of the embodiment of the present invention, it is described to utilize weighted mean method pair
First overlapping region and second overlapping region carry out anastomosing and splicing processing, the third image after obtaining anastomosing and splicing,
Include:
First overlapping region is divided into the multiple first column regions to be fused, and second overlapping region is divided into
Multiple second column regions to be fused, first column region to be fused are corresponded with the described second column region to be fused；
According to sequence of each first column region to be fused at a distance from second overlapping region from small to large, according to
It is secondary obtain each first column region to be fused the first default weight coefficient, wherein the first default weight coefficient with
Its corresponding described first column region to be fused become larger at a distance from second overlapping region and become smaller；
According to the described first default weight coefficient, it is corresponding described second to be fused to obtain the described first column region to be fused
The default weight coefficient of the second of column region, wherein the first default weight coefficient and the described second default weight coefficient and value
Equal to one；
According to the described first default weight coefficient and the second default weight coefficient, by each first column to be fused
Region carries out pixel value with corresponding second column region to be fused and is added calculating, fusion pixel values is obtained, to be merged
Spliced third image.
Second aspect of the embodiment of the present invention discloses a kind of three-dimensional MRA medical image splicing apparatus, and described device includes:
Receiving unit, the two neighboring three-dimensional MRA medical image to be spliced sent for real-time reception scanning device；
Unit is denoised, for carrying out Laplce's denoising, enhancing to the two neighboring three-dimensional MRA medical image to be spliced
With irregular smoothing processing, the first image and the second image are obtained；
Probe unit, for carrying out overlapping Layer Detection to the first image and second image respectively, to determine
State the second overlapping region in the first overlapping region and second image in the first image；
Concatenation unit, for being melted using weighted mean method to first overlapping region and second overlapping region
Splicing is closed, the third image after obtaining anastomosing and splicing.
The third aspect of the embodiment of the present invention discloses a kind of electronic equipment, and the electronic equipment includes:
Processor；
Memory is stored with computer-readable instruction on the memory, and the computer-readable instruction is by the processing
When device executes, three-dimensional MRA medical image joining method disclosed in first aspect of the embodiment of the present invention is realized.
Fourth aspect of the embodiment of the present invention discloses a kind of computer readable storage medium, stores computer program, institute
Stating computer program makes computer execute three-dimensional MRA medical image joining method disclosed in first aspect of the embodiment of the present invention.
The technical solution that the embodiment of the present invention provides can include the following benefits:
The technical program includes the following steps: the two neighboring three-dimensional MRA doctor to be spliced that real-time reception scanning device is sent
Learn image；Laplce's denoising, enhancing and irregular smoothing processing are carried out to two neighboring three-dimensional MRA medical image to be spliced,
Obtain the first image and the second image；Overlapping Layer Detection is carried out to the first image and the second image respectively, to determine the first image
In the first overlapping region and the second image in the second overlapping region；Using weighted mean method to the first overlapping region and second
Overlapping region carries out anastomosing and splicing processing, the third image after obtaining anastomosing and splicing.
Under the method, by respectively to real-time reception to two neighboring three-dimensional MRA medical image to be spliced located in advance
Overlapping layer detection is carried out after reason, to determine the overlapping region in two three-dimensional MRA medical images to be spliced, and utilizes weighted average
Method carries out anastomosing and splicing to two overlapping regions, can be improved the determination efficiency of overlapping region in image, and then improves image and spell
Connect efficiency.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
Invention.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows and meets implementation of the invention
Example, and in specification together principle for explaining the present invention.
Fig. 1 is a kind of structural schematic diagram of three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention；
Fig. 2 is a kind of flow diagram of three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention；
Fig. 3 is the flow diagram of another three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention；
Fig. 4 is the flow diagram of another three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention；
Fig. 5 is the structural schematic diagram of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention；
Fig. 6 is the structural schematic diagram of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention；
Fig. 7 is the structural schematic diagram of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention.
Specific embodiment
Here will the description is performed on the exemplary embodiment in detail, the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistented with the present invention.On the contrary, they be only with it is such as appended
The example of device and method being described in detail in claims, some aspects of the invention are consistent.
Embodiment one
Implementation environment of the invention can be electronic equipment, such as smart phone, tablet computer, desktop computer.
Under a kind of application scenarios, method disclosed in the embodiment of the present invention suitable for the life insurance air control of financial industry,
Specifically, intellectual analysis is carried out by the panorama 3 d medical images to insurer after splicing, can helps to audit insurer's
It insures application.Under another application scenarios, method disclosed in the embodiment of the present invention be suitable for medical field magnetic resonance at
As equipment, the three-dimensional MRA medical image for the segmented that scanning device scans is spliced, to obtain panorama three-dimensional doctor
Image is learned, doctor can be helped comprehensively, intuitively evaluate to the state of an illness.
Fig. 1 is a kind of structural schematic diagram of three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention.Device
100 can be above-mentioned electronic equipment.As shown in Figure 1, device 100 may include following one or more components: processing component
102, memory 104, power supply module 106, multimedia component 108, audio component 110, sensor module 114 and communication component
116。
The integrated operation of the usual control device 100 of processing component 102, such as with display, telephone call, data communication, phase
Machine operation and the associated operation of record operation etc..Processing component 102 may include one or more processors 118 to execute
Instruction, to complete all or part of the steps of following methods.In addition, processing component 102 may include one or more modules,
For convenient for the interaction between processing component 102 and other assemblies.For example, processing component 102 may include multi-media module, use
In to facilitate the interaction between multimedia component 108 and processing component 102.
Memory 104 is configured as storing various types of data to support the operation in device 100.These data are shown
Example includes the instruction of any application or method for operating on the device 100.Memory 104 can be by any kind of
Volatibility or non-volatile memory device or their combination are realized, such as static random access memory (Static
RandomAccess Memory, abbreviation SRAM), electrically erasable programmable read-only memory (Electrically Erasable
Programmable Read-Only Memory, abbreviation EEPROM), Erasable Programmable Read Only Memory EPROM (Erasable
Programmable Read Only Memory, abbreviation EPROM), programmable read only memory (Programmable Red-
Only Memory, abbreviation PROM), read-only memory (Read-Only Memory, abbreviation ROM), magnetic memory, flash
Device, disk or CD.It is also stored with one or more modules in memory 104, is configured to for the one or more module
It is executed by the one or more processors 118, to complete all or part of step in method as follows.
Power supply module 106 provides electric power for the various assemblies of device 100.Power supply module 106 may include power management system
System, one or more power supplys and other with for device 100 generate, manage, and distribute the associated component of electric power.
Multimedia component 108 includes the screen of one output interface of offer between device 100 and user.In some realities
It applies in example, screen may include liquid crystal display (Liquid Crystal Display, abbreviation LCD) and touch panel.If
Screen includes touch panel, and screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes
One or more touch sensors are to sense the gesture on touch, slide, and touch panel.Touch sensor can be sensed not only
The boundary of a touch or slide action, but also detect duration and pressure relevant to touch or slide.Screen may be used also
To include display of organic electroluminescence (Organic Light Emitting Display, abbreviation OLED).
Audio component 110 is configured as output and/or input audio signal.For example, audio component 110 includes a Mike
Wind (Microphone, abbreviation MIC), when device 100 is in operation mode, such as call model, logging mode and speech recognition mould
When formula, microphone is configured as receiving external audio signal.The received audio signal can be further stored in memory
104 or via communication component 116 send.In some embodiments, audio component 110 further includes a loudspeaker, for exporting
Audio signal.
Sensor module 114 includes one or more sensors, and the state for providing various aspects for device 100 is commented
Estimate.For example, sensor module 114 can detecte the state that opens/closes of device 100, the relative positioning of component, sensor group
Part 114 can be with the position change of 100 1 components of detection device 100 or device and the temperature change of device 100.Some
In embodiment, which can also include Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 116 is configured to facilitate the communication of wired or wireless way between device 100 and other equipment.Device
100 can access the wireless network based on communication standard, such as WiFi (Wireless-Fidelity, Wireless Fidelity).In the present invention
In embodiment, communication component 116 receives broadcast singal or broadcast correlation from external broadcasting management system via broadcast channel
Information.In embodiments of the present invention, communication component 116 further includes near-field communication (Near Field Communication, abbreviation
NFC) module, for promote short range communication.For example, radio frequency identification (Radio Frequency can be based in NFC module
Identification, abbreviation RFID) technology, Infrared Data Association (Infrared DataAssociation, abbreviation IrDA)
Technology, ultra wide band (UltraWideband, abbreviation UWB) technology, Bluetooth technology and other technologies are realized.
In the exemplary embodiment, device 100 can be by one or more application specific integrated circuit (Application
Specific Integrated Circuit, abbreviation ASIC), it is digital signal processor, digital signal processing appts, programmable
Logical device, field programmable gate array, controller, microcontroller, microprocessor or other electronic components are realized, for executing
Following methods.
Embodiment two
Referring to Fig. 2, the process that Fig. 2 is a kind of three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention is shown
It is intended to.Three-dimensional MRA medical image joining method as shown in Figure 2 may comprise steps of:
201, the two neighboring three-dimensional MRA medical image to be spliced that real-time reception scanning device is sent.
It should be noted that wherein the format of three-dimensional MRA medical image to be spliced should be digital imaging and communications in medicine
(Digital Imaging and Communications in Medicine, DICOM) format, can be used to data exchange
Medical Image Format.
202, Laplce's denoising, enhancing and irregular smooth are carried out to two neighboring three-dimensional MRA medical image to be spliced
Processing obtains the first image and the second image.
In the embodiment of the present invention, due to the limitation of MRA equipment, the three-dimensional MRA medical image to be spliced of acquisition is inevitable
There are noises.Therefore, it is necessary to pre-process to three-dimensional MRA medical image to be spliced.First to two neighboring to be spliced three
It ties up MRA medical image and carries out Laplce's denoising, remove extra useless interference signal, then the image after denoising is increased
Strength reason, finally carries out irregular picture smooth treatment for enhanced image, as far as possible to provide good the in next step
One image and the second image.
It as another optional embodiment, can also be using the Weighted Neighborhood method of average to three-dimensional MRA medicine to be spliced
Image carries out smoothing denoising.Wherein, the Weighted Neighborhood method of average is to show in neighborhood that each pixel is multiplied by different coefficients, to more important
Pixel multiplied by biggish weight.As an example it is assumed that medical image is f (x, y), if taking neighborhood S, Weighted Neighborhood is average
Calculation formula are as follows:
Wherein, ∑ is summation symbol, is used to indicate sum operation；A is the upper bound of the first sum operation, and-a is the first summation
The lower bound of operation, a can be specified constant, to indicate that the value range of s is [- a, a], to limit the first sum operation
Independent variable value range.Similarly, b is the upper bound of the second sum operation, and-b is the lower bound of the second sum operation, and b can be specified
Constant, to indicate that the value range of t is [- b, b], to limit the independent variable value range of the second sum operation.Wherein, w
(s, t) be weight function, belong to a kind of common weight function, be using each point in neighborhood at a distance from central point as the letter of variable
Number, in the function, central point has maximum weight, shows this to the decision percentage contribution of Weighted Neighborhood average value and its
Distance to central point is inversely proportional.Wherein, (s, t) is the coordinate of each point in neighborhood, and w is the corresponding weight of point.
Implement the embodiment, denoising speed can be increased.
203, overlapping Layer Detection is carried out to the first image and the second image respectively, to determine that first in the first image is overlapped
The second overlapping region in region and the second image.
In the embodiment of the present invention, due to the limitation of MRA equipment, can not one-off scanning obtain panorama 3 d medical images,
It is generally necessary to carry out segmentation imaging, then two often adjacent segmentations are spliced, panorama 3 d medical images could be obtained.
It should be noted that described first image and the second image are substantially three-dimensional MRA medicine in embodiments of the present invention
Image, but for panorama 3 d medical images, the first image and the second image refer to resulting point of segmentation imaging
Section.
It is appreciated that since three-dimensional MRA medical image is used to show the lesion situation of patient, in order to avoid the information of scanning
Missing is omitted, there are overlapping regions between the first image and the second image, and the two overlapping regions are respectively present in two figures
The both ends of the joining place of picture.Wherein, the joining place of two images can be the boundary on any one side of any one image.
Wherein, the first image and the second image can be the image obtained at different conditions with scanning device, different
Condition may include different weathers, illumination, camera position and angle etc..
It should be noted that since overlapping region generally has the identical or close overlapping number of plies, to the first image
Overlapping Layer Detection is carried out with the second image, it may be determined that overlapping region.
204, anastomosing and splicing processing is carried out to the first overlapping region and the second overlapping region using weighted mean method, is melted
Close spliced third image.
In the embodiment of the present invention, using weighted mean method respectively to the pixel in the first overlapping region and the second overlapping region
Superposed average, each pixel are endowed different weights according to from the significance level in whole image again after being weighted,
So as to realize image smoothing transition, the suture in image is effectively eliminated.
As it can be seen that implementing method described in Fig. 2, pass through the two neighboring three-dimensional MRA to be spliced arrived respectively to real-time reception
Medical image carries out overlapping layer detection after being pre-processed, to determine the coincidence area in two three-dimensional MRA medical images to be spliced
Domain, and anastomosing and splicing is carried out to two overlapping regions using weighted mean method, it can be improved determining for overlapping region in image and imitate
Rate, and then improve image mosaic efficiency.
Embodiment three
Referring to Fig. 3, Fig. 3 is the process of another three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention
Schematic diagram.As shown in figure 3, three-dimensional MRA medical image joining method may comprise steps of:
301~303.Wherein, the description for step 301~303 please refers to the detailed of step 201~203 in embodiment two
Thin description, details are not described herein by the present invention.
304, the first overlapping region is divided into the multiple first column regions to be fused, and the second overlapping region is divided into multiple
Second column region to be fused, the first column region to be fused and the second column region to be fused correspond.
Wherein, the one-to-one first column region to be fused and the second column region to be fused have coincidence relation.
305, the sequence according to each first column region to be fused at a distance from the second overlapping region from small to large, is successively obtained
Take the first default weight coefficient of each the first column region to be fused, wherein the first default weight coefficient with its corresponding
One column region to be fused becomes larger at a distance from the second overlapping region and is become smaller.
It is appreciated that in the first overlapping region, closer to the decision of the first column region to be fused of the second overlapping region
Percentage contribution is bigger, therefore default weight coefficient should be bigger.Similarly in the second overlapping region, closer to the first overlapping region
The second column region to be fused decision percentage contribution it is bigger, therefore default weight coefficient should be bigger.It optionally, can be according to
One column region to be fused presets the first default weight coefficient at a distance from the second overlapping region, for the first column region to be fused.
For example, if having 2 the first column regions to be fused, respectively A and B in the first overlapping region, first is to be fused
Column region B column region A more to be fused than first closer to the first overlapping region edge, also closer to the second overlapping region, then
The first default weight coefficient of the first column region A to be fused can be set as 0.8, the first default weight of the first column region B to be fused
Coefficient is 0.6.It is of course also possible to set other numerical value, such as 0.4 or 0.5 etc., it is not limited thereto.
306, according to the first default weight coefficient, corresponding second column region to be fused of the first column region to be fused is obtained
Second default weight coefficient, wherein the first default weight coefficient and the second default weight coefficient and value be equal to one.
Also there are 2 the second column regions to be fused, respectively C and D based on above-mentioned example, in the second overlapping region, second
Column region C column region D more to be fused than second to be fused is also overlapped area closer to first closer to the edge of the second overlapping region
Domain, then presetting power with second of the second column region C to be fused corresponding to the first column region A to be fused in the second overlapping region
Weight coefficient is 1-0.8=0.2, in the second overlapping region with the second column region D to be fused corresponding to the first column region B to be fused
The second default weight coefficient be 1-0.6=0.4.
307, according to the first default weight coefficient and the second default weight coefficient, by each first column region to be fused with it is right
Second answered column region to be fused carries out pixel value and is added calculating, fusion pixel values is obtained, to obtain the third after anastomosing and splicing
Image.
Implementation steps 304~307, by the way that overlapping region is divided into multiple column regions to be fused, and according to column area to be fused
The significance level in domain configures different weight coefficients to it, and the default weight coefficient of two column regions to be fused of arbitrary neighborhood is not
Together, smooth and seamless splicing can be carried out to the first image and the second image, makes image excessively more naturally, improve splicing effect,
Promote visual effect.
308, the disposal of gentle filter is carried out to third image using low-pass filter, obtains smooth target image.
As it can be seen that method described in implementing Fig. 3, can be improved the determination efficiency of overlapping region in image, and then improve figure
As splicing efficiency, additionally it is possible to the two neighboring three-dimensional MRA medical image to be spliced that real-time reception scanning device is sent, and treat
Splicing three-dimensional MRA medical image is pre-processed, and provides good first image and the second image for next step.In addition, passing through
Overlapping region is divided into multiple column regions to be fused, and according to the significance level of column region to be fused, different power is configured to it
Weight coefficient, the default weight coefficient of two column regions to be fused of arbitrary neighborhood is different, can to the first image and the second image into
The splicing of row smooth and seamless makes image excessively more naturally, improvement splicing effect, promotes visual effect.
Example IV
Referring to Fig. 4, Fig. 4 is the process of another three-dimensional MRA medical image joining method disclosed by the embodiments of the present invention
Schematic diagram.Three-dimensional MRA medical image joining method as shown in Figure 4 may comprise steps of:
401~402.Wherein, the description for step 401~402 please refers to the detailed of step 201~202 in embodiment two
Thin description, details are not described herein by the present invention.
403, the first image and the respective maximum intensity projection imaging of the second image are compared, to determine the first figure
First as in is overlapped the second coincidence segment in segment and the second image.
Wherein, maximum intensity projection (Maximal Intensity Projection, MIP) is one kind widely used three
Tie up MRA Medical Image Processing.MIP obtains two dimensional image with perspective, i.e., is penetrated by calculating along scanned every
The maximal density pixel that is encountered on line and generate.When original image of the fiber optic bundle by one section of tissue, density in image
Maximum pixel is retained, and is projected on a two-dimensional surface, to form MIP reconstruction image.MIP can react corresponding picture
The x-ray pad value of element, lesser variable density can also show in MIP image, can show well the narrow of blood vessel, expansion,
Filling defect and the contrast medium of calcification and Endovascular on differentiation vascular wall.Therefore, it is imaged by maximum intensity projection, it can be first
It walks and determines that the first coincidence segment in the first image and second in the second image is overlapped segment.
404, the first coincidence segment is divided into the multiple first regions to be measured, and the second coincidence segment is divided into multiple second
Region to be measured, the first region to be measured are corresponded with the second region to be measured.
405, successively judge the number differences in each first region to be measured with the overlapping layer in corresponding second region to be measured
Whether default value is less than.If so, executing step 406；Conversely, terminating this process.
Wherein, default value can be developer and be previously set according to the actual situation.
406, using the first region to be measured as the component part of the first overlapping region in the first image, by corresponding second
Component part of the region to be measured as the second overlapping region in the second image, to determine that the first overlapping region and second is overlapped area
Domain.
407, according to the image location information of the first image and the second image, sampled point is determined.Wherein, image location information
Correspond to the position of human dissection coordinate system for describing the first image and the second image.
It should be noted that image location information can be set provided in the header file of the first image and the second image
Obtained in standby scanning information, equipment scanning information include picture position, image direction, pixel resolution, thickness, patient body position and
Scan the information such as bed.
It is appreciated that corresponding to the position of human dissection coordinate system by the origin of image, any point in image can be asked
Positioned at the position of human dissection coordinate system, therefore sampled point can be above-mentioned origin, be also possible in addition to above-mentioned origin
Any one coincidence point.Wherein, the origin of image is located at the upper left corner of image, figure of this origin in image coordinate system
As coordinate is zero, and the human dissection coordinate that this origin corresponds in human dissection coordinate system can be obtained from image location information
, therefore, according to the human dissection coordinate of the first image and the respective origin of the second image, the first image and the can also be described
The positional relationship of two images.
Wherein, human dissection coordinate system refers to the anatomic space coordinate-system in technical field of medical image processing,
Also referred to as patient coordinate system.Human body anatomical coordinate system is made of three planes, for description standard human body anatomically
Position.Wherein, three individual faces include cross section, coronal-plane and sagittal plane；Wherein, cross section is parallel to the ground, separates human body
Head and foot；Coronal-plane is perpendicular to the ground, separates the front and rear of human body；Sagittal plane is perpendicular to the ground, separates human body
Left part and right part.
408, the first image coordinate according to the human dissection coordinate of sampled point, sampled point in the first image and
The second image coordinate in two images obtains registration transformation matrix.
Wherein, human dissection coordinate refers to that sampled point corresponds to the coordinate information of human dissection coordinate system；First image
Coordinate or the second image coordinate refer to sample in the coordinate information of image coordinate system.
Wherein, registration transformation matrix for being translated to the first image or the second image, the behaviour such as change of scale and rotation
One of work is a variety of.Generally, when the point for knowing two image same human body anatomic coordinates, it can determine registration transformation
Matrix.For example, [the second image coordinate of sampled point in the second image] * [registration transformation matrix]=[sampled point in the first image
The first image coordinate].
409, according to registration transformation matrix, the first overlapping region and the second overlapping region are registrated.
As an alternative embodiment, step 409 may include:
Using the first overlapping region as benchmark region, the point in the second overlapping region with same human body anatomic coordinates is passed through
Registration transformation matrix is registrated to the same position of the first overlapping region；Alternatively, using the second overlapping region as benchmark region, by first
Point in overlapping region with same human body anatomic coordinates is registrated to the same position of the second overlapping region by registration transformation matrix
It sets.
Implement the embodiment, compared with the existing technology in manually identifying picture registration region mode, save the time,
While improving efficiency, additionally it is possible to increase the accuracy of image mosaic.
It as another optional embodiment, can also be according at the image chosen in advance before executing step 409
The size for adjusting son is extended processing to the first overlapping region and the second overlapping region respectively, obtain the first region subject to registration with
Second region subject to registration.Still optionally further, step 409 may include: to obtain registration coefficient based on mutual information maximization method,
The point of same characteristic features in the first region subject to registration and the second region subject to registration is registrated to by being registrated coefficient according to registration coefficient
Same position.Wherein, image processing operators include but is not limited to find the Luo Baici operator at edge (again using local difference operator
Claim Roberts operator), the Sobel operator for edge detection, the edge detection for first order differential operator Prewitt calculate
Son, for the Laplacian operator of second-order differential or Gauss-Laplace operator etc..
Implement the embodiment, by being extended processing, base to the first determining overlapping region and the second overlapping region
The first region subject to registration and the second region subject to registration after extension are registrated, and the accuracy of image registration can be improved, together
The effect of Shi Tigao image procossing.
410, anastomosing and splicing processing is carried out to the first overlapping region and the second overlapping region using weighted mean method, is melted
Close spliced third image.
As it can be seen that implementing method described in Fig. 4, the determination efficiency of overlapping region in image can be improved, and then improve figure
As splicing efficiency.In addition to this, by using an overlapping region as benchmark region, will there is same person in another overlapping region
The point of body anatomic coordinates is registrated to same position by registration transformation matrix, compared with the existing technology middle manually identifying picture registration
The mode in region is saving time, the while of improving efficiency, additionally it is possible to increase the accuracy of image mosaic.
Embodiment five
Referring to Fig. 5, Fig. 5 is the structure of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention
Schematic diagram.As shown in figure 5, three-dimensional MRA medical image splicing apparatus may include receiving unit 501, denoising unit 502, visit
Survey unit 503 and concatenation unit 504, wherein
Receiving unit 501, the two neighboring three-dimensional MRA medical image to be spliced sent for real-time reception scanning device.
Unit 502 is denoised, for carrying out Laplce's denoising, enhancing to two neighboring three-dimensional MRA medical image to be spliced
With irregular smoothing processing, the first image and the second image are obtained.
Probe unit 503, for carrying out overlapping Layer Detection to the first image and the second image respectively, to determine the first image
In the first overlapping region and the second image in the second overlapping region.
Concatenation unit 504, for carrying out fusion spelling to the first overlapping region and the second overlapping region using weighted mean method
Processing is connect, the third image after obtaining anastomosing and splicing.
As it can be seen that implementing device shown in fig. 5, by curing respectively to the two neighboring three-dimensional MRA to be spliced that real-time reception arrives
It learns after image is pre-processed and carries out overlapping layer detection, to determine the overlapping region in two three-dimensional MRA medical images to be spliced,
And anastomosing and splicing is carried out to two overlapping regions using weighted mean method, it can be improved the determination efficiency of overlapping region in image,
And then improve image mosaic efficiency.
Embodiment six
Referring to Fig. 6, Fig. 6 is the structure of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention
Schematic diagram.Three-dimensional MRA medical image splicing apparatus shown in fig. 6 be three-dimensional MRA medical image splicing apparatus as shown in Figure 5 into
Row optimization obtains.Compared with three-dimensional MRA medical image splicing apparatus shown in fig. 5, three-dimensional MRA medicine figure shown in fig. 6
As in splicing apparatus:
Above-mentioned denoising unit 502 is also used in concatenation unit 504 using weighted mean method to the first overlapping region and the
Two overlapping regions carry out anastomosing and splicing processing, after the third image after obtaining anastomosing and splicing, using low-pass filter to third
Image carries out the disposal of gentle filter, obtains smooth target image.
As an alternative embodiment, in device shown in fig. 6, concatenation unit 504 may include:
Subelement 5041 is divided, for the first overlapping region to be divided into the multiple first column regions to be fused, and by second
Overlapping region is divided into the multiple second column regions to be fused, and the first column region to be fused and the second column region to be fused correspond.
First obtain subelement 5042, for according to each first column region to be fused at a distance from the second overlapping region from
It is small to arrive big sequence, the first default weight coefficient of each the first column region to be fused is successively obtained, wherein the first default power
Weight coefficient becomes smaller as its corresponding first column region to be fused becomes larger at a distance from the second overlapping region.
Second obtains subelement 5043, for it is corresponding to obtain the first column region to be fused according to the first default weight coefficient
The second column region to be fused the second default weight coefficient, wherein the first default weight coefficient and the second default weight coefficient
It is equal to one with value.
Splice subelement 5044, is used for according to the first default weight coefficient and the second default weight coefficient, by each first
Column region to be fused carries out pixel value with corresponding second column region to be fused and is added calculating, obtains fusion pixel values, to obtain
Third image after anastomosing and splicing.
Implement the embodiment, by the way that overlapping region is divided into multiple column regions to be fused, and according to column region to be fused
Significance level, configure different weight coefficients to it, the default weight coefficient of two column regions to be fused of arbitrary neighborhood is different,
Smooth and seamless splicing can be carried out to the first image and the second image, make image excessively more naturally, improvement splicing effect, is promoted
Visual effect.
As another optional embodiment, above-mentioned denoising unit 502 is also used to using the Weighted Neighborhood method of average pair
Three-dimensional MRA medical image to be spliced carries out smoothing denoising.Wherein, the Weighted Neighborhood method of average is to show in neighborhood each pixel multiplied by not
Same coefficient, to more important pixel multiplied by biggish weight.As an example it is assumed that medical image is f (x, y), if taking neighbour
Domain S, the then average calculation formula of Weighted Neighborhood are as follows:
Wherein, ∑ is summation symbol, is used to indicate sum operation；A is the upper bound of the first sum operation, and-a is the first summation
The lower bound of operation, a can be specified constant, to indicate that the value range of s is [- a, a], to limit the first sum operation
Independent variable value range.Similarly, b is the upper bound of the second sum operation, and-b is the lower bound of the second sum operation, and b can be specified
Constant, to indicate that the value range of t is [- b, b], to limit the independent variable value range of the second sum operation.Wherein, w
(s, t) be weight function, belong to a kind of common weight function, be using each point in neighborhood at a distance from central point as the letter of variable
Number, in the function, central point has maximum weight, shows this to the decision percentage contribution of Weighted Neighborhood average value and its
Distance to central point is inversely proportional.Wherein, (s, t) is the coordinate of each point in neighborhood, and w is the corresponding weight of point.
Implement the embodiment, denoising speed can be increased.
As it can be seen that implementing device shown in fig. 6, the determination efficiency of overlapping region in image can be improved, and then improve image
Splice efficiency, additionally it is possible to by the way that overlapping region is divided into multiple column regions to be fused, and according to the important journey of column region to be fused
Degree, configures different weight coefficients to it, and the default weight coefficient of two column regions to be fused of arbitrary neighborhood is different, can be to the
One image and the second image carry out smooth and seamless splicing, make image excessively more naturally, improving splicing effect, promotion vision is imitated
Fruit.
Embodiment seven
Referring to Fig. 7, Fig. 7 is the structure of another three-dimensional MRA medical image splicing apparatus disclosed by the embodiments of the present invention
Schematic diagram.Three-dimensional MRA medical image splicing apparatus shown in Fig. 7 be three-dimensional MRA medical image splicing apparatus as shown in Figure 6 into
Row optimization obtains.Compared with three-dimensional MRA medical image splicing apparatus shown in fig. 6, three-dimensional MRA medicine figure shown in Fig. 7
As splicing apparatus can also include: comparison unit 505, determination unit 506, acquiring unit 507 and registration unit 508, wherein
Comparison unit 505, for carrying out overlapping Layer Detection to the first image and the second image respectively in probe unit 503,
Before determining the second overlapping region in the first overlapping region and the second image in the first image, by the first image and second
The respective maximum intensity projection imaging of image compares, to determine that first in the first image is overlapped segment and the second image
In second be overlapped segment.
Correspondingly, above-mentioned probe unit 503 is used to carry out overlapping Layer Detection to the first image and the second image respectively, with
Determine that the mode of the second overlapping region in the first overlapping region and the second image in the first image specifically may is that
Above-mentioned probe unit 503, for carrying out overlapping Layer Detection to the first coincidence segment and the second coincidence segment, with true
The second overlapping region in the first overlapping region and the second image in fixed first image.
Still optionally further, above-mentioned probe unit 503 is used to carry out weight to the first coincidence segment and the second coincidence segment
Lamination detection, specifically may be used in a manner of determining the second overlapping region in the first overlapping region and the second image in the first image
To be:
Above-mentioned probe unit 503, for the first coincidence segment to be divided into the multiple first regions to be measured, and by the second weight
It closes segment and is divided into the multiple second regions to be measured, the first region to be measured is corresponded with the second region to be measured；And successively judgement is every
Whether one the first region to be measured is less than default value with the number differences of the overlapping layer in corresponding second region to be measured；If difference
Less than default value, using the first region to be measured as the component part of the first overlapping region in the first image, by corresponding
Component part of two regions to be measured as the second overlapping region in the second image, to determine that the first overlapping region and second is overlapped
Region.
Determination unit 506, in above-mentioned probe unit 503 using the first region to be measured as first in the first image
The component part of overlapping region, using corresponding second region to be measured as the component part of the second overlapping region in the second image
With determine after the first overlapping region and the second overlapping region and above-mentioned concatenation unit 504 using weighted mean method to the
One overlapping region and the second overlapping region carry out anastomosing and splicing processing, before the third image after obtaining anastomosing and splicing, according to the
The image location information of one image and the second image, determines sampled point.Wherein, image location information for describe the first image and
Second image corresponds to the position of human dissection coordinate system.
Acquiring unit 507, for first image of the human dissection coordinate, sampled point according to sampled point in the first image
Coordinate and the second image coordinate in the second image obtain registration transformation matrix.
Registration unit 508, for being registrated the first overlapping region and the second overlapping region according to registration transformation matrix.
As an alternative embodiment, registration unit 508 is used for according to registration transformation matrix, registration first is overlapped area
The mode of domain and the second overlapping region specifically may is that
Registration unit 508, for using the first overlapping region as benchmark region, will there is same human body in the second overlapping region
The point of anatomic coordinates is registrated to the same position of the first overlapping region by registration transformation matrix；Alternatively, with the second overlapping region
For benchmark region, the point in the first overlapping region with same human body anatomic coordinates is registrated to second by registration transformation matrix
The same position of overlapping region.
Implement the embodiment, compared with the existing technology in manually identifying picture registration region mode, save the time,
While improving efficiency, additionally it is possible to increase the accuracy of image mosaic.
As another optional embodiment, registration unit 508 is used for according to registration transformation matrix, and registration first is overlapped
The mode of region and the second overlapping region specifically may is that
Registration unit 508, for according to the size of image processing operators chosen in advance respectively to the first overlapping region and
Second overlapping region is extended processing, obtains the first region subject to registration and the second region subject to registration；And most based on mutual information
Bigization method obtains registration coefficient, according to registration coefficient by same characteristic features in the first region subject to registration and the second region subject to registration
Point is registrated to same position by being registrated coefficient.Wherein, image processing operators include but is not limited to be sought using local difference operator
Look for the Luo Baici operator (also known as Roberts operator) at edge, for the Sobel operator of edge detection, for first order differential operator
Edge detection Prewitt operator, for the Laplacian operator of second-order differential or Gauss-Laplace operator etc..
Implement the embodiment, by being extended processing, base to the first determining overlapping region and the second overlapping region
The first region subject to registration and the second region subject to registration after extension are registrated, and the accuracy of image registration can be improved, together
The effect of Shi Tigao image procossing.
As it can be seen that implementing device shown in Fig. 7, the determination efficiency of overlapping region in image can be improved, and then improve image
Splice efficiency.In addition to this, by using an overlapping region as benchmark region, will there is same human body in another overlapping region
The point of anatomic coordinates is registrated to same position by registration transformation matrix, compared with the existing technology middle manually identifying picture registration area
The mode in domain is saving time, the while of improving efficiency, additionally it is possible to increase the accuracy of image mosaic.
The present invention also provides a kind of electronic equipment, which includes:
Processor；
Memory is stored with computer-readable instruction on the memory, when which is executed by processor,
Realize three-dimensional MRA medical image joining method as previously shown.
The electronic equipment can be Fig. 1 shown device 100.
In one exemplary embodiment, the present invention also provides a kind of computer readable storage mediums, are stored thereon with calculating
Machine program when the computer program is executed by processor, realizes three-dimensional MRA medical image joining method as previously shown.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and change can executed without departing from the scope.The scope of the present invention is limited only by the attached claims.
Claims (10)
1. a kind of three-dimensional MRA medical image joining method, which is characterized in that the described method includes:
The two neighboring three-dimensional MRA medical image to be spliced that real-time reception scanning device is sent；
Laplce's denoising, enhancing and irregular smoothing processing are carried out to the two neighboring three-dimensional MRA medical image to be spliced,
Obtain the first image and the second image；
Overlapping Layer Detection is carried out to the first image and second image respectively, to determine first in the first image
The second overlapping region in overlapping region and second image；
Anastomosing and splicing processing is carried out to first overlapping region and second overlapping region using weighted mean method, is melted
Close spliced third image.
2. the method according to claim 1, wherein described utilize weighted mean method to first overlapping region
Anastomosing and splicing processing is carried out with second overlapping region, after the third image after obtaining anastomosing and splicing, the method is also wrapped
It includes:
The disposal of gentle filter is carried out to the third image using low-pass filter, obtains smooth target image.
3. according to the method described in claim 2, it is characterized in that, described respectively to the first image and second image
Overlapping Layer Detection is carried out, to determine that second in the first overlapping region and second image in the first image is overlapped area
Before domain, the method also includes:
The first image and second image respective maximum intensity projection imaging are compared, to determine described the
First in one image is overlapped the second coincidence segment in segment and second image；
And it is described overlapping Layer Detection is carried out to the first image and second image respectively, with determination first figure
The second overlapping region in the first overlapping region and second image as in, comprising:
Overlapping Layer Detection is carried out to the first coincidence segment and the second coincidence segment, to determine in the first image
The second overlapping region in first overlapping region and second image.
4. according to the method described in claim 3, it is characterized in that, described be overlapped segment and second coincidence to described first
Segment carries out overlapping Layer Detection, to determine the second weight in the first overlapping region and second image in the first image
Close region, comprising:
The first coincidence segment is divided into the multiple first regions to be measured, and the second coincidence segment is divided into multiple second
Region to be measured, first region to be measured are corresponded with the described second region to be measured；
Successively judge the number differences in each described first region to be measured with the overlapping layer in corresponding second region to be measured
Whether default value is less than；
If the difference is less than the default value, it is overlapped the described first region to be measured as first in the first image
The component part in region, using corresponding second region to be measured as the composition of the second overlapping region in second image
Part, with determination first overlapping region and second overlapping region.
5. according to the method described in claim 4, it is characterized in that, described using the described first region to be measured as first figure
The component part of the first overlapping region as in, using corresponding second region to be measured as second in second image
The component part of overlapping region, with after determination first overlapping region and second overlapping region and the utilization
Weighted mean method carries out anastomosing and splicing processing to the first overlapping region and the second overlapping region, the third figure after obtaining anastomosing and splicing
Before picture, the method also includes:
According to the image location information of the first image and second image, sampled point is determined；Wherein, described image position
Information is used to describe the first image and second image corresponds to the position of human dissection coordinate system；
According to the first image coordinate in the first image of the human dissection coordinate of the sampled point, the sampled point and
The second image coordinate in second image obtains registration transformation matrix；
According to the registration transformation matrix, it is registrated first overlapping region and second overlapping region.
6. according to the method described in claim 5, it is characterized in that, described according to the registration transformation matrix, it is registrated described the
One overlapping region and second overlapping region, comprising:
Using first overlapping region as benchmark region, will there is the point of same human body anatomic coordinates in second overlapping region
The same position of first overlapping region is registrated to by the registration transformation matrix；Alternatively,
Using second overlapping region as benchmark region, will there is the point of same human body anatomic coordinates in first overlapping region
The same position of second overlapping region is registrated to by the registration transformation matrix.
7. described in any item methods according to claim 1~6, which is characterized in that it is described using weighted mean method to described the
One overlapping region and second overlapping region carry out anastomosing and splicing processing, the third image after obtaining anastomosing and splicing, comprising:
First overlapping region is divided into the multiple first column regions to be fused, and second overlapping region is divided into multiple
Second column region to be fused, first column region to be fused are corresponded with the described second column region to be fused；
According to sequence of each first column region to be fused at a distance from second overlapping region from small to large, successively obtain
The first default weight coefficient of each first column region to be fused is taken, wherein the first default weight coefficient is with it
Corresponding first column region to be fused becomes larger at a distance from second overlapping region and is become smaller；
According to the described first default weight coefficient, the corresponding second column area to be fused of the column region to be fused of acquisition described first
The default weight coefficient of the second of domain, wherein the first default weight coefficient and the described second default weight coefficient and value be equal to
One；
According to the described first default weight coefficient and the second default weight coefficient, by each first column region to be fused
Pixel value is carried out with corresponding second column region to be fused and is added calculating, fusion pixel values is obtained, to obtain anastomosing and splicing
Third image afterwards.
8. a kind of three-dimensional MRA medical image splicing apparatus, which is characterized in that described device includes:
Receiving unit, the two neighboring three-dimensional MRA medical image to be spliced sent for real-time reception scanning device；
Unit is denoised, for carrying out Laplce's denoising to the two neighboring three-dimensional MRA medical image to be spliced, enhancing and not
Regular smooth processing, obtains the first image and the second image；
Probe unit, for carrying out overlapping Layer Detection to the first image and second image respectively, with determination described
The second overlapping region in the first overlapping region and second image in one image；
Concatenation unit, for carrying out fusion spelling to first overlapping region and second overlapping region using weighted mean method
Processing is connect, the third image after obtaining anastomosing and splicing.
9. a kind of electronic equipment, including memory and processor, the memory are stored with computer program, which is characterized in that
The processor realizes that three-dimensional MRA medical image according to any one of claims 1 to 7 is spelled when executing the computer program
The step of connecing method.
10. a kind of computer readable storage medium, which is characterized in that it stores computer program, and the computer program makes
Computer perform claim requires 1~7 described in any item three-dimensional MRA medical image joining methods.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666640.9A CN110473143B (en) | 2019-07-23 | 2019-07-23 | Three-dimensional MRA medical image stitching method and device and electronic equipment |
| PCT/CN2019/118065 WO2021012520A1 (en) | 2019-07-23 | 2019-11-13 | Three-dimensional mra medical image splicing method and apparatus, and electronic device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666640.9A CN110473143B (en) | 2019-07-23 | 2019-07-23 | Three-dimensional MRA medical image stitching method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110473143A true CN110473143A (en) | 2019-11-19 |
| CN110473143B CN110473143B (en) | 2023-11-10 |
Family
ID=68508969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910666640.9A Active CN110473143B (en) | 2019-07-23 | 2019-07-23 | Three-dimensional MRA medical image stitching method and device and electronic equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110473143B (en) |
| WO (1) | WO2021012520A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145092A (en) * | 2019-12-16 | 2020-05-12 | 华中科技大学鄂州工业技术研究院 | Method and device for processing infrared blood vessel image on leg surface |
| CN111612690A (en) * | 2019-12-30 | 2020-09-01 | 苏州纽迈分析仪器股份有限公司 | Image splicing method and system |
| CN114170075A (en) * | 2021-10-26 | 2022-03-11 | 北京东软医疗设备有限公司 | Image splicing method, device and equipment |
| WO2023024697A1 (en) * | 2021-08-26 | 2023-03-02 | 北京旷视科技有限公司 | Image stitching method and electronic device |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116958104B (en) * | 2023-07-28 | 2024-05-28 | 上海感图网络科技有限公司 | Material surface image processing method, device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102551717A (en) * | 2010-12-31 | 2012-07-11 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for removing blood vessel splicing image artifacts in magnetic resonance imaging |
| US20170140532A1 (en) * | 2015-11-18 | 2017-05-18 | Lightlab Imaging, Inc. | X-ray image feature detection and registration systems and methods |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102855613B (en) * | 2011-07-01 | 2016-03-02 | 株式会社东芝 | Image processing equipment and method |
| US20140267267A1 (en) * | 2013-03-15 | 2014-09-18 | Toshiba Medical Systems Corporation | Stitching of volume data sets |
| CN104318604A (en) * | 2014-10-21 | 2015-01-28 | 四川华雁信息产业股份有限公司 | 3D image stitching method and apparatus |
| CN107146201A (en) * | 2017-05-08 | 2017-09-08 | 重庆邮电大学 | A kind of image split-joint method based on improvement image co-registration |
-
2019
- 2019-07-23 CN CN201910666640.9A patent/CN110473143B/en active Active
- 2019-11-13 WO PCT/CN2019/118065 patent/WO2021012520A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102551717A (en) * | 2010-12-31 | 2012-07-11 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for removing blood vessel splicing image artifacts in magnetic resonance imaging |
| US20170140532A1 (en) * | 2015-11-18 | 2017-05-18 | Lightlab Imaging, Inc. | X-ray image feature detection and registration systems and methods |
| CN108633312A (en) * | 2015-11-18 | 2018-10-09 | 光学实验室成像公司 | X-ray image feature detects and registration arrangement and method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145092A (en) * | 2019-12-16 | 2020-05-12 | 华中科技大学鄂州工业技术研究院 | Method and device for processing infrared blood vessel image on leg surface |
| CN111612690A (en) * | 2019-12-30 | 2020-09-01 | 苏州纽迈分析仪器股份有限公司 | Image splicing method and system |
| WO2023024697A1 (en) * | 2021-08-26 | 2023-03-02 | 北京旷视科技有限公司 | Image stitching method and electronic device |
| CN114170075A (en) * | 2021-10-26 | 2022-03-11 | 北京东软医疗设备有限公司 | Image splicing method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021012520A1 (en) | 2021-01-28 |
| CN110473143B (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110473143A (en) | A kind of three-dimensional MRA medical image joining method and device, electronic equipment | |
| CN106056537B (en) | A kind of medical image joining method and device | |
| Mahmood et al. | Deep adversarial training for multi-organ nuclei segmentation in histopathology images | |
| CN107665486B (en) | Automatic splicing method and device applied to X-ray images and terminal equipment | |
| CN107886508B (en) | Differential subtraction method and medical image processing method and system | |
| Stoyanov et al. | A practical approach towards accurate dense 3D depth recovery for robotic laparoscopic surgery | |
| Weibel et al. | Graph based construction of textured large field of view mosaics for bladder cancer diagnosis | |
| CN110678903B (en) | System and method for analysis of ectopic ossification in 3D images | |
| CN109791692A (en) | Computer aided detection is carried out using the multiple images of the different perspectives from area-of-interest to improve accuracy in detection | |
| CN100592336C (en) | System and method for registration of medical images | |
| CN113034354B (en) | Image processing method and device, electronic equipment and readable storage medium | |
| KR102258756B1 (en) | Determination method for stage of cancer based on medical image and analyzing apparatus for medical image | |
| CN112419326B (en) | Image segmentation data processing method, device, equipment and storage medium | |
| US10832420B2 (en) | Dynamic local registration system and method | |
| CN109461140A (en) | Image processing method and device, equipment and storage medium | |
| CN118015190A (en) | Autonomous construction method and device of digital twin model | |
| CN107945203A (en) | PET image processing method and processing device, electronic equipment, storage medium | |
| CN112330787A (en) | Image annotation method and device, storage medium and electronic equipment | |
| TW200937342A (en) | Line drawing processor, program and line drawing processing method | |
| CN115861175A (en) | Medical image quality monitoring method and device, electronic equipment and storage medium | |
| Kazwiny et al. | Extracting neuronal activity signals from microscopy recordings of contractile tissue using B-spline explicit active surfaces (BEAS) cell tracking | |
| CN115761134A (en) | Twin model generation method, system, nuclear magnetic resonance device, and medium | |
| US6418237B1 (en) | Abnormal pattern detection processing method and system and image display terminal | |
| Eresen et al. | New similarity metric for registration of MRI to histology: Golden retriever muscular dystrophy imaging | |
| CN108765399A (en) | Diseased region recognition methods and device, computer installation and readable storage medium storing program for executing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |