CN106910179B - Multimode medical image fusion method based on wavelet transformation - Google Patents
Multimode medical image fusion method based on wavelet transformation Download PDFInfo
- Publication number
- CN106910179B CN106910179B CN201710046867.4A CN201710046867A CN106910179B CN 106910179 B CN106910179 B CN 106910179B CN 201710046867 A CN201710046867 A CN 201710046867A CN 106910179 B CN106910179 B CN 106910179B
- Authority
- CN
- China
- Prior art keywords
- image
- frequency
- component
- wavelet
- low
- 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
- 230000009466 transformation Effects 0.000 title claims abstract description 25
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000002156 mixing Methods 0.000 claims abstract description 18
- 230000003044 adaptive effect Effects 0.000 claims abstract description 11
- 210000000056 organ Anatomy 0.000 claims description 30
- 238000000354 decomposition reaction Methods 0.000 claims description 17
- 230000015556 catabolic process Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 230000003902 lesion Effects 0.000 description 3
- 210000001519 tissue Anatomy 0.000 description 3
- 210000003484 anatomy Anatomy 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 238000012797 qualification Methods 0.000 description 2
- 210000004872 soft tissue Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 230000002308 calcification Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000002224 dissection Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 230000001613 neoplastic effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 238000005549 size reduction Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000001835 viscera Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- 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
- G06T2207/10081—Computed x-ray tomography [CT]
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
Abstract
A kind of multimode medical image fusion method based on adaptive wavelet packet transform, the following steps are included: S1, using adaptive wavelet packet transform filter carrying out wavelet transformation to the medical images of different modalities, aforementioned image is separately disassembled into the component that high frequency, low frequency and low-and high-frequency combine；S2, the component combined to high frequency, low frequency and the low-and high-frequency that any two width different modalities medical image decomposes are overlapped, and obtain the component that the high frequency, low frequency and low-and high-frequency of blending image combine；S3, the component combined to the high frequency, low frequency and low-and high-frequency of blending image carry out discrete wavelet inverse transform, obtain the blending image of original size.Wavelet transformation technique is applied in field of image processing by the present invention, adaptive wavelet packet transform can effectively Lifting Wavelet coefficient to the details susceptibility of low frequency component, so that it is more accurate further to decompose obtained high frequency, low frequency component, so that syncretizing effect gets a promotion.
Description
Technical field
The present invention relates to medical field, the side that multi-modality medical image is merged in particular by image processing techniques
Method, specifically a kind of multimode medical image fusion method based on wavelet transformation.
Background technique
Currently, occurring many elder generations in the world as computer science and technology and medical treatment influence the fast development of engineering science
Into medical imaging device, for clinical medicine diagnosis provide the medical image of multiple modalities, these images are anti-from different aspect
The different information of organization of human body, internal organs and pathological tissues are reflected.
For example CT (Computed Tomography) image has stronger spatial resolution and geometrical property, to bone
Imaging it is very clear, it can provide preferable reference to lesion localization, but then relatively low to the contrast of soft tissue.MR
(Magnetic Resonance) image can clearly reflect the anatomical structure of soft tissue, organ, blood vessel etc., be conducive to determine
Lesion range, but MR image is insensitive to calcification point, and geometric distortion can be occurred by magnetic disturbance.SPEC, PET image can obtain
Radioactive concentration to human body any angle fault plane is distributed, and can reflect the metaboilic level and blood flow state of histoorgan, right
" hot spot " is presented in neoplastic lesion, provides the functional information of human body, but their resolution ratio is poor, hardly results in accurate dissection knot
Structure is also not easy to differentiate the boundary of tissue, organ.It can be seen that different imaging techniques have the advantage of itself also while possessing one
A little limitations, these images to the obtained form of the same anatomical structure of human body and functional information be each other difference, complement one another
's.
In clinical diagnosis, the image of single mode tends not to enough information required for providing doctor, therefore, if
The medical image of different modalities can be subjected to fusion appropriate, combine anatomic information and functional information organically, one
The information from a variety of imaging sources is synthetically expressed simultaneously on width image, so that doctor understands the synthesis feelings of pathological tissues or organ
Condition, and make more accurate diagnosis or make the therapeutic scheme of more scientific optimization, this will push modern medicine clinical
The huge advance of technology.
The characteristics of for different modalities medical image, in order to preferably merge the important information of different images, we
Propose the multimode medical image fusion method based on adaptive wavelet packet transform.Under the premise of image energy feature calculation, from
It adapts to selection optimal wavelet coefficient and carries out wavelet transformation, so that wavelet transformation can be effectively by the background of image and details
It distinguishes, under adjustable weight, the high and low frequency information of two secondary different modalities images is folded according to different proportion
Add, fast and efficiently completes fusion process.
Summary of the invention
The purpose of the present invention is aiming at the problem that image co-registration, propose a kind of multi-modality medical image based on wavelet transformation
Fusion method.
The technical scheme is that
A kind of multimode medical image fusion method based on adaptive wavelet packet transform, it the following steps are included:
S1, wavelet transformation is carried out using medical image of the adaptive wavelet packet transform filter to different modalities, by aforementioned image
It is separately disassembled into the component that high frequency, low frequency and low-and high-frequency combine；
The component that S2, the high frequency decomposed to any two width different modalities medical image, low frequency and low-and high-frequency combine into
Row superposition obtains the component that the high frequency, low frequency and low-and high-frequency of blending image combine；
S3, the component combined to the high frequency, low frequency and low-and high-frequency of blending image carry out discrete wavelet inverse transform, obtain original
The blending image of size.
In step S1 of the invention, low frequency component is decomposed again according to scale demand.
Step S1 of the invention specifically:
S1.1, wavelet structure base filter bank, i.e., based on meeting orthogonality condition fixed length wavelet filter, different
Multiple filter coefficient building wavelet basis filter banks are obtained under initial condition, and one is randomly choosed in wavelet basis filter bank
Filter coefficient is as initialization filter；
S1.2, first layer decomposition point is obtained using medical image progress wavelet transformation of the initialization filter to multiple mode
Amount passes through the low frequency in wavelet transform acquisition image low frequency component LL1 in the horizontal and vertical directions, horizontal direction
With the high fdrequency component LH1 in vertical direction, the low frequency component HL1 on the high frequency and vertical direction in horizontal direction and level and
High fdrequency component HH1 in vertical direction；
S1.3, filter coefficient is selected in wavelet basis filter bank according to the fluctuation of the Energy distribution and texture of image again
To step S1.2 obtain first layer decomposed component in low frequency component LL1 carry out second of wavelet transformation, obtain LL2, HH2,
HL2, LH2 repeat step S1.3 several times, complete picture breakdown.
In step S1.3 of the invention, repeat step S1.3 and carry out the number of picture breakdown to be 3-5 times.
In step S1.3 of the invention, selected in wavelet basis filter bank according to the Energy distribution of image and texture fluctuation
Filter coefficient method particularly includes:
S1.3-1, to image carry out organ extraction the step of:
Four components in current decomposition component are handled, extract human organ from the background of black,
Human organ is specifically extracted using image partition method, or human organ image is extracted using the method for setting boundary threshold
HLo and LHo；
S1.3-2, the step of image texture characteristic parameter is calculated:
Lateral image least energy Eh, longitudinal image least energy Ev, lateral image are calculated using following formula
The minimum very poor Eq of minimum very poor Ep, longitudinal image, transverse direction lines maximum fluctuation value Em and
Longitudinal lines maximum fluctuation value En；
Eh=min (max (| HLo |)) (1)
Ev=min (max (| LHo |)) (2)
Ep=min (max (| HLo |)-min (| HLo |)) (3)
Eq=min (max (| LHo |)-min (| LHo |)) (4)
Wherein, HLo indicates the corresponding human body device extracted of the high fdrequency component LH1 on the low frequency and vertical direction in horizontal direction
Official's image, LHo indicate the corresponding human organ figure extracted of low frequency component HL1 on high frequency and vertical direction in horizontal direction
Picture；I, j represents the serial number of row, and i ', j ' represent the serial number of column；S1.3-3, it is obtained according to aforementioned six image texture characteristic parameters
Wavelet basis filter coefficient.
In step S1.3-3 of the invention, wavelet basis filter coefficient acquisition methods are as follows: obtained according to step S1.3-2
Six image texture characteristic parameters obtain wavelet basis filter coefficient, preferably genetic programming algorithm using optimization algorithm.
In step S1.3-3 of the invention, wavelet basis filter coefficient acquisition methods are as follows: a certain amount of sample image is extracted,
The table of comparisons for establishing six characteristic indexs and wavelet basis filter coefficient is obtained in real-time calculate according to step S1.3-2
Six image texture characteristic parameter controls search and obtain corresponding wavelet basis filter coefficient.
In step S1.3-1 of the invention, human organ is extracted using the method for setting boundary threshold and specifically includes following step
It is rapid:
To as the high fdrequency component LHn on the low frequency and vertical direction in the previous horizontal direction decomposed and obtained, horizontal direction
On high frequency and vertical direction on low frequency component HLn two subgraphs carry out operations described below, respectively obtain organic image HLo
And LHo:
As sum (| Row |) > Threshold1, retains current line pixel data and otherwise make current line pixel data
For background, the row data are deleted；
As sum (| Column |) > Threshold2, retain when otherwise forefront pixel data will work as forefront pixel data
As background, the row data are deleted；
Wherein, Row is the pixel of row, and Column is the pixel of column, and Threshold1, Threshold2 are organ mould respectively
The corresponding parameter threshold of type.
In step S2 of the invention, two width different modalities medical images are decomposed to obtain high frequency, low frequency and low-and high-frequency combination
Component be overlapped under certain weight, obtain blending image high frequency, low frequency and low-and high-frequency combine component, specifically:
S2.1, it is merged with subgraph of certain weight to any two mode medical image after decomposition, according to
The corresponding principle being added of low-and high-frequency carries out, wherein the arbitrary small number between the fusion weight W selection 0.1~0.9 of a sub-picture, separately
Outer one secondary fusion weight is 1-W；
S2.2, the decomposition result AHHn, ALLn, AHLn, ALHn and BHHn to different modalities image A and B, BLLn, BHLn,
BLHn is overlapped operation, and n represents n-th layer decomposition, obtains four component Fs HHn, FLLn, FHLn and FLHn of blending image F:
FHHn=wHH*AHHn+ (1-wHH) * BHHn；WHH is that high frequency merges weight
FLLn=wLL*ALLn+ (1-wLL) * BLLn；WLL is that low frequency merges weight
FHLn=wHL*AHLn+ (1-wHL) * BHLn；WHL is that low-and high-frequency merges weight
FLHn=wLH*ALHn+ (1-wLH) * BLHn；WLH is that low high frequency merges weight.
Beneficial effects of the present invention:
Wavelet transformation technique is applied in field of image processing by the present invention, and adaptive wavelet packet transform can effective Lifting Wavelet
Coefficient is to the details susceptibility of low frequency component, so that it is more accurate further to decompose obtained high frequency, low frequency component, so that
Syncretizing effect gets a promotion；For the process for the adaptive wavelet packet transform coefficient analysis that medical image feature carries out, organ has been distinguished
Image and invalid background effectively improve the reliability of wavelet coefficient, and the method can form effective combination with medical big data,
Form the stronger medical image segmentation of robustness based on organ model, analysis model.
Detailed description of the invention
Fig. 1 is structural schematic diagram of the invention.
Fig. 2 is that image energy feature of the invention compares schematic diagram with wavelet coefficient.
Fig. 3 is quickly to distinguish the organ of medical image and the schematic diagram of background using threshold decision in the present invention.
Fig. 4 is the image schematic diagram that texture analysis obtains in the present invention.
Specific embodiment
The present invention is further illustrated with reference to the accompanying drawings and examples.
As shown in Figs 1-4, a kind of multimode medical image fusion method based on adaptive wavelet packet transform, it includes following step
It is rapid:
S1, wavelet transformation is carried out using medical image of the adaptive wavelet packet transform filter to different modalities, by aforementioned image
It is separately disassembled into the component that high frequency, low frequency and low-and high-frequency combine；
The component that S2, the high frequency decomposed to any two width different modalities medical image, low frequency and low-and high-frequency combine into
Row superposition obtains the component that the high frequency, low frequency and low-and high-frequency of blending image combine；
S3, the component combined to the high frequency, low frequency and low-and high-frequency of blending image carry out discrete wavelet inverse transform, obtain original
The blending image of size；
In step S1 of the invention, low frequency component is decomposed again according to scale demand.
Step S1 of the invention specifically:
S1.1, wavelet structure base filter bank, i.e., based on meeting orthogonality condition fixed length wavelet filter, different
Multiple filter coefficient building wavelet basis filter banks are obtained under initial condition, and one is randomly choosed in wavelet basis filter bank
Filter coefficient is as initialization filter；
S1.2, first layer decomposition point is obtained using medical image progress wavelet transformation of the initialization filter to multiple mode
Amount obtains image both horizontally and vertically by wavelet transform (Discrete Wavelet Transform, DWT)
On low frequency component LL1, the high fdrequency component LH1 on low frequency and vertical direction in horizontal direction, the high frequency in horizontal direction and
Low frequency component HL1 in vertical direction and both horizontally and vertically on high fdrequency component HH1；
S1.3, filter coefficient is selected in wavelet basis filter bank according to the fluctuation of the Energy distribution and texture of image again
To step S1.2 obtain first layer decomposed component in low frequency component LL1 carry out second of wavelet transformation, obtain LL2, HH2,
HL2, LH2 repeat step S1.3 several times, complete picture breakdown.
In step S1.3 of the invention, repeat step S1.3 carry out picture breakdown number be 3-5 time, syncretizing effect with
It can achieve equalization point in computational efficiency, be the 1/4 of current layer due to decomposing image size reduction every time, so stock size is very
Big image just will use 5 layers or more of decomposition and real-time is not high, and 3 layers of syncretizing effect below can be relatively weaker；For
Larger size image can choose 5 layers of decomposition, and 3 layers of smaller size image selection decomposition also can choose 4 layers and decompose as one
Equalization point.
According to medical image energy statistics: since medical image is usually gray level image, background is with noisy black
Background, prospect are the human organ observed, in step S1.3, according to the Energy distribution of image and texture fluctuation small
Filter coefficient is selected in wave base filter bank method particularly includes:,
S1.3-1, to image carry out organ extraction the step of:
Four components in current decomposition component are handled, extract human organ from the background of black,
Human organ is specifically extracted using image partition method, or human organ image is extracted using the method for setting boundary threshold
HLo and LHo；
S1.3-2, the step of image texture characteristic parameter is calculated:
Lateral image least energy Eh, longitudinal image least energy Ev, lateral image are calculated using following formula
The minimum very poor Eq of minimum very poor Ep, longitudinal image, transverse direction lines maximum fluctuation value Em and longitudinal lines maximum fluctuation value En；
(image energy parameter Eh, Ev are calculated, qualifications are set as with the sub- energy minimum of the high pass of image, enable to small echo base system
Number comes out unity and coherence in writing feature instantiation, improves the sensibility to detailed information；The wavelet coefficient that image static state obtains after decomposing is maximum
Value Ep, Eq, the wavelet coefficient distribution to downscaled images；Horizontal, longitudinal lines maximum fluctuation Em, En, that is, image row, column ash
The difference of the sum of angle value reflects the relationship of wavelet basis and grain details)
Eh=min (max (| HL0 |)) (1)
Ev=min (max (| LH0 |)) (2)
Ep=min (max (| HL0 |)-min (| HL0 |)) (3)
Eq=min (max (| LH0 |)-min (| LH0 |)) (4)
Wherein, HLo indicates the corresponding human body device extracted of the high fdrequency component LH1 on the low frequency and vertical direction in horizontal direction
Official's image, LHo indicate the corresponding human organ figure extracted of low frequency component HL1 on high frequency and vertical direction in horizontal direction
Picture；I, j represents the serial number of row, and i ', j ' represent the serial number of column；S1.3-3, it is obtained according to aforementioned six image texture characteristic parameters
Wavelet basis filter coefficient.
Image texture reflects that the visual signature of homogeneity phenomenon in image, Fig. 4 clearly show that texture region expresses figure
The important features such as edge, change of gradient of main target as in；We are using 6 energy of S1.3-2 and texture formula as preferably
Qualifications, thus the filter of selected suitable target texture image.Mainly preferred method are as follows: according to aforementioned six image textures
Characteristic parameter obtains wavelet basis filter coefficient using genetic programming algorithm.
In step S1.3-3 of the invention, wavelet basis filter coefficient acquisition methods are as follows: a certain amount of sample image is extracted,
The table of comparisons for establishing 6 characteristic indexs and wavelet basis filter coefficient carries out directly control when real-time calculate and searches.
As shown in figure 3, horizontal line is the calculating to row pixel, ordinate is the calculating to column pixel, although the method is rough
Organ general image is extracted, but it is highly effective in terms of guaranteeing to calculate real-time, in step S1.3-1, using setting
Set boundary threshold method extract human organ specifically includes the following steps:
To as the high fdrequency component LHn on the low frequency and vertical direction in the previous horizontal direction decomposed and obtained, horizontal direction
On high frequency and vertical direction on low frequency component HLn two subgraphs carry out operations described below, respectively obtain organic image HLo
And LHo:
As sum (| Row |) > Threshold1, retains current line pixel data and otherwise make current line pixel data
For background, the row data are deleted；
As sum (| Column |) > Threshold2, retain when otherwise forefront pixel data will work as forefront pixel data
As background, the row data are deleted；
Wherein, Row is the pixel of row, and Column is the pixel of column, and Threshold1, Threshold2 are organ mould respectively
The corresponding parameter threshold of type.
In step S2 of the invention, two width different modalities medical images are decomposed to obtain high frequency, low frequency and low-and high-frequency combination
Component be overlapped under certain weight, obtain blending image high frequency, low frequency and low-and high-frequency combine component, specifically:
S2.1, it is merged with subgraph of certain weight to any two mode medical image after decomposition, according to
The corresponding principle being added of low-and high-frequency carries out, and by taking any two width different modalities medical image as an example, the fusion weight W of a sub-picture can
To select the arbitrary small number between 0.1~0.9, in addition a secondary fusion weight is 1-W；
S2.2, the decomposition result AHHn, ALLn, AHLn, ALHn and BHHn to different modalities image A and B, BLLn, BHLn,
BLHn is overlapped operation, and n represents n-th layer decomposition, if blending image is F:
FHHn=wHH*AHHn+ (1-wHH) * BHHn；WHH is that high frequency merges weight
FLLn=wLL*ALLn+ (1-wLL) * BLLn；WLL is that low frequency merges weight
FHLn=wHL*AHLn+ (1-wHL) * BHLn；WHL is that low-and high-frequency merges weight
FLHn=wLH*ALHn+ (1-wLH) * BLHn；WLH is that low high frequency merges weight.
Part that the present invention does not relate to is the same as those in the prior art or can be realized by using the prior art.
Claims (7)
1. a kind of multimode medical image fusion method based on wavelet transformation, it is characterized in that it the following steps are included:
S1, wavelet transformation is carried out using medical image of the adaptive wavelet packet transform filter to different modalities, aforementioned image is distinguished
It is decomposed into the component that high frequency, low frequency and low-and high-frequency combine；
S2, the component combined to high frequency, low frequency and the low-and high-frequency that any two width different modalities medical image decomposes are folded
Add, obtains the component that the high frequency, low frequency and low-and high-frequency of blending image combine；
S3, the component combined to the high frequency, low frequency and low-and high-frequency of blending image carry out discrete wavelet inverse transform, obtain original size
Blending image；
The step S1 specifically:
S1.1, wavelet structure base filter bank, i.e., based on meeting orthogonality condition fixed length wavelet filter, in different initial values
Under the conditions of obtain multiple filter coefficients building wavelet basis filter banks, a filtering is randomly choosed in wavelet basis filter bank
Device coefficient is as initialization filter；
S1.2, first layer decomposed component is obtained using medical image progress wavelet transformation of the initialization filter to multiple mode,
I.e. by wavelet transform obtain image low frequency component LL1 in the horizontal and vertical directions, the low frequency in horizontal direction and
It low frequency component HL1 on the high frequency and vertical direction on high fdrequency component LH1, horizontal direction and level in vertical direction and hangs down
The upward high fdrequency component HH1 of histogram；
S1.3, select filter coefficient to step again in wavelet basis filter bank according to the fluctuation of the Energy distribution and texture of image
The low frequency component LL1 in first layer decomposed component that rapid S1.2 is obtained carries out second of wavelet transformation, obtain LL2, HH2, HL2,
LH2 repeats step S1.3 several times, completes picture breakdown；
In the step S1.3, filter is selected in wavelet basis filter bank according to the Energy distribution of image and texture fluctuation
Coefficient method particularly includes:
S1.3-1, to image carry out organ extraction the step of:
Four components in current decomposition component are handled, are extracted human organ from the background of black, specifically
Using image partition method extract human organ, or using setting boundary threshold method extract human organ image HLo and
LHo；
S1.3-2, the step of image texture characteristic parameter is calculated:
It is minimum that lateral image least energy Eh, longitudinal image least energy Ev, lateral image are calculated using following formula
The minimum very poor Eq of very poor Ep, longitudinal image, transverse direction lines maximum fluctuation value Em and longitudinal lines maximum fluctuation value En；
Eh=min (max (| HLo |)) (1)
Ev=min (max (| LHo |)) (2)
Ep=min (max (| HLo |)-min (| HLo |)) (3)
Eq=min (max (| LHo |)-min (| LHo |)) (4)
Wherein, HLo indicates the corresponding human organ figure extracted of the high fdrequency component LH1 on the low frequency and vertical direction in horizontal direction
Picture, LHo indicate the corresponding human organ image extracted of low frequency component HL1 on high frequency and vertical direction in horizontal direction；i,j
The serial number of row is represented, i ', j ' represent the serial number of column；S1.3-3, wavelet basis is obtained according to aforementioned six image texture characteristic parameters
Filter coefficient.
2. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S1, low frequency component is decomposed again according to scale demand.
3. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S1.3, repeat step S1.3 and carry out the number of picture breakdown to be 3-5 times.
4. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S1.3-3, wavelet basis filter coefficient acquisition methods are as follows: six image texture characteristics obtained according to step S1.3-2
Parameter obtains wavelet basis filter coefficient using genetic programming algorithm.
5. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S1.3-3, wavelet basis filter coefficient acquisition methods are as follows: extract suitable sample image, establish six image texture spies
The table of comparisons for levying parameter and wavelet basis filter coefficient, in real-time calculate, according to six image lines of step S1.3-2 acquisition
It manages characteristic parameter control and searches the corresponding wavelet basis filter coefficient of acquisition.
6. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S1.3-1, using setting boundary threshold method extract human organ specifically includes the following steps:
To when on the low frequency and vertical direction in the previous horizontal direction decomposed and obtained high fdrequency component LHn, in horizontal direction
Two subgraphs of low frequency component HLn on high frequency and vertical direction carry out operations described below, respectively obtain organic image HLo and
LHo:
As sum (| Row |) > Threshold1, retain current line pixel data, otherwise, using current line pixel data as carrying on the back
Scape deletes the row data；
As sum (| Column |) > Threshold2, retain when otherwise forefront pixel data will work as the conduct of forefront pixel data
Background deletes the column data；
Wherein, Row is the pixel of row, and Column is the pixel of column, and Threshold1, Threshold2 are organ model pair respectively
The parameter threshold answered.
7. the multimode medical image fusion method according to claim 1 based on wavelet transformation, it is characterized in that described
In step S2, two width different modalities medical images are decomposed to obtain component that high frequency, low frequency and low-and high-frequency combine in certain weight
Under be overlapped, obtain blending image high frequency, low frequency and low-and high-frequency combine component, specifically:
S2.1, it is merged with subgraph of certain weight to any two mode medical image after decomposition, according to height
The corresponding principle being added of frequency carries out, and wherein the fusion weight W of piece image selects the arbitrary small number between 0.1~0.9, and in addition one
It is 1-W that width, which merges weight,；
S2.2, the decomposition result AHHn, ALLn, AHLn, ALHn and BHHn to different modalities image A and B, BLLn, BHLn, BLHn
It is overlapped operation, n represents n-th layer decomposition, obtains four component Fs HHn, FLLn, FHLn and FLHn of blending image F:
FHHn=wHH*AHHn+ (1-wHH) * BHHn；WHH is that high frequency merges weight
FLLn=wLL*ALLn+ (1-wLL) * BLLn；WLL is that low frequency merges weight
FHLn=wHL*AHLn+ (1-wHL) * BHLn；WHL is that low-and high-frequency merges weight
FLHn=wLH*ALHn+ (1-wLH) * BLHn；WLH is that low high frequency merges weight.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710046867.4A CN106910179B (en) | 2017-01-22 | 2017-01-22 | Multimode medical image fusion method based on wavelet transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710046867.4A CN106910179B (en) | 2017-01-22 | 2017-01-22 | Multimode medical image fusion method based on wavelet transformation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106910179A CN106910179A (en) | 2017-06-30 |
| CN106910179B true CN106910179B (en) | 2019-03-15 |
Family
ID=59207184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710046867.4A Active CN106910179B (en) | 2017-01-22 | 2017-01-22 | Multimode medical image fusion method based on wavelet transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106910179B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107742279B (en) * | 2017-10-31 | 2020-07-10 | 珠海大横琴科技发展有限公司 | Image processing method, device and storage medium |
| CN107993236A (en) * | 2017-11-27 | 2018-05-04 | 上海交通大学 | A kind of method and platform of multi-modality images processing |
| CN109544550B (en) * | 2018-12-05 | 2021-10-22 | 易必祥 | CT image-based intelligent detection and identification method and system |
| CN109657709A (en) * | 2018-12-06 | 2019-04-19 | 湖北博华自动化系统工程有限公司 | A kind of equipment fault prediction technique based on particle group optimizing support vector regression |
| CN109919929B (en) * | 2019-03-06 | 2023-03-24 | 电子科技大学 | Tongue crack feature extraction method based on wavelet transformation |
| CN111445492A (en) * | 2020-03-26 | 2020-07-24 | 北京易康医疗科技有限公司 | Three-dimensional fusion calibration method for magnetic resonance image and radiotherapy positioning image |
| CN111667486B (en) * | 2020-04-29 | 2023-11-17 | 杭州深睿博联科技有限公司 | Multi-modal fusion pancreas segmentation method and system based on deep learning |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105844606A (en) * | 2016-03-22 | 2016-08-10 | 博康智能网络科技股份有限公司 | Wavelet transform-based image fusion method and system thereof |
-
2017
- 2017-01-22 CN CN201710046867.4A patent/CN106910179B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106910179A (en) | 2017-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106910179B (en) | Multimode medical image fusion method based on wavelet transformation | |
| Men et al. | Automatic segmentation of the clinical target volume and organs at risk in the planning CT for rectal cancer using deep dilated convolutional neural networks | |
| CN104809734B (en) | A method of the infrared image based on guiding filtering and visual image fusion | |
| Onofrey et al. | Generalizable multi-site training and testing of deep neural networks using image normalization | |
| Viji et al. | Automatic detection of brain tumor based on magnetic resonance image using CAD System with watershed segmentation | |
| CN103501699A (en) | Method and apparatus for isolating a potential anomaly in imaging data and its application to medical imagery | |
| Xia et al. | Research of multimodal medical image fusion based on parameter-adaptive pulse-coupled neural network and convolutional sparse representation | |
| CN110660063A (en) | Multi-image fused tumor three-dimensional position accurate positioning system | |
| JP7278224B2 (en) | Quantified aspects of lesions in medical images | |
| CN115018728A (en) | Image fusion method and system based on multi-scale transformation and convolution sparse representation | |
| Sun et al. | Liver lesion segmentation in CT images with MK-FCN | |
| Lepcha et al. | Multimodal medical image fusion based on pixel significance using anisotropic diffusion and cross bilateral filter | |
| Zhang et al. | Research on multi-mode medical image fusion algorithm based on wavelet transform and the edge characteristics of images | |
| CN116342444A (en) | Dual-channel multi-mode image fusion method and fusion imaging terminal | |
| CN115619693A (en) | Space-time fusion model based on nested multi-scale transformation | |
| Yang et al. | Medical image fusion method based on lifting wavelet transform and dual-channel PCNN | |
| Zhang et al. | An adaptive enhancement method for breast X-ray images based on the nonsubsampled contourlet transform domain and whale optimization algorithm | |
| Huang et al. | The segmentation of liver and vessels in CT images using 3D hierarchical seeded region growing | |
| Wang et al. | An improved image segmentation method using three-dimensional region growing algorithm | |
| CN113822796A (en) | Multi-modal brain image registration method based on improved image pyramid | |
| CN110084772B (en) | MRI/CT fusion method based on bending wave | |
| Chang et al. | An image decomposition fusion method for medical images | |
| Shaohai et al. | Block-matching based multimodal medical image fusion via PCNN with SML | |
| Abirami et al. | Kidney segmentation for finding its abnormalities in abdominal CT images | |
| Yao et al. | Uterine fibroid segmentation and volume measurement on MRI |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Zhang Shiping Inventor after: Wang Xiaofang Inventor before: Wang Xiaofang |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20181026 Address after: 518000 B1 701-72, Kexing Science Park, 15 Keyuan Road, Nanshan District, Shenzhen, Guangdong. Applicant after: Cabin (Shenzhen) Medical Technology Co.,Ltd. Address before: 210000 Room 403, 3 tower 141, Ma Tai Street, Nanjing, Jiangsu. Applicant before: NANJING MIZONG ELECTRONIC TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200525 Address after: 518101 B05, floor 3, workshop 1, Daqian industrial plant, zone 67, Xingdong community, Xin'an street, Bao'an District, Shenzhen City, Guangdong Province Patentee after: Kaben (Shenzhen) medical equipment Co.,Ltd. Address before: 518000 B1 701-72, Kexing Science Park, 15 Keyuan Road, Nanshan District, Shenzhen, Guangdong. Patentee before: Cabin (Shenzhen) Medical Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Multimodal medical image fusion method based on Wavelet Transform Effective date of registration: 20211229 Granted publication date: 20190315 Pledgee: Shenzhen hi tech investment small loan Co.,Ltd. Pledgor: Kaben (Shenzhen) medical equipment Co.,Ltd. Registration number: Y2021980017017 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230410 Granted publication date: 20190315 Pledgee: Shenzhen hi tech investment small loan Co.,Ltd. Pledgor: Kaben (Shenzhen) medical equipment Co.,Ltd. Registration number: Y2021980017017 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right |