CN107680072A - It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI - Google Patents
It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI Download PDFInfo
- Publication number
- CN107680072A CN107680072A CN201711053557.1A CN201711053557A CN107680072A CN 107680072 A CN107680072 A CN 107680072A CN 201711053557 A CN201711053557 A CN 201711053557A CN 107680072 A CN107680072 A CN 107680072A
- Authority
- CN
- China
- Prior art keywords
- image
- positron emission
- rarefaction representation
- component
- depth
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 21
- 238000002595 magnetic resonance imaging Methods 0.000 claims abstract description 46
- 238000003325 tomography Methods 0.000 claims abstract description 21
- 238000007689 inspection Methods 0.000 claims abstract description 17
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000002600 positron emission tomography Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims abstract description 5
- 238000003384 imaging method Methods 0.000 claims abstract description 4
- 230000004927 fusion Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 5
- 229910000831 Steel Inorganic materials 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 239000010985 leather Substances 0.000 claims description 4
- 239000010959 steel Substances 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000007910 cell fusion Effects 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 12
- 230000000694 effects Effects 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000037396 body weight Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 230000000717 retained 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 using two or more images, e.g. averaging or 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
- G06T2207/10088—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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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]
-
- 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
- G06T2207/20081—Training; Learning
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
- Nuclear Medicine (AREA)
Abstract
The present invention provides a kind of positron emission fault image and MRI based on depth rarefaction representation, it is characterised in that：Including the magnetic resonance imaging component for generating magnetic resonance imaging image, for generating the positron emission computerized tomography component of image in positron emission tomography, for the inspection platform automatically moved of load-bearing, for controlling the imaging of positron emission computerized tomography component and magnetic resonance imaging component.Pass through wavelet basis function initialization and training dictionary, training dictionary on the multiple yardsticks of wavelet field, the ability that it will can be made both to have kept rarefaction representation data, but also with the performance of multiscale analysis, and then the syncretizing effect more excellent compared with the image interfusion method under single scale based on dictionary learning and multi-scale wavelet fusion method can be reached in the multiple dimensioned lower significant feature of marginally coefficient extraction image in image co-registration problem.
Description
Technical field
The present invention relates to medical apparatus and instruments technical field, specially a kind of positron emission based on depth rarefaction representation
The fusion method of faultage image and MRI.
Background technology
The image co-registration of Same Scene is piece image by image fusion technology, solves information between image well
Complementary and redundancy, so as to preferably describe target or scene.Image co-registration mainly includes feature extraction, the spy to extraction
Sign is merged and reconstructed the image after being merged.Because rarefaction representation can represent signal with a small amount of atom as far as possible,
Preferably extract the principal character of signal, therefore exploration to the Image Fusion based on rarefaction representation and research are increasingly
It is popular.
In view of the fusion method for being currently based on learning-oriented dictionary is all that image is merged under the single yardstick of image area
, although this kind of method compared with analytic transformation type-word allusion quotation can more accurately fitting data, can not multiple dimensioned ground analyze data.
Different features is generally comprised under different scale, different directions in view of image, and these features are often image co-registration
The protrusion information for needing to distinguish and retaining, existing technology are difficult to solve problem above.
The content of the invention
(1) technical problem solved
In view of the shortcomings of the prior art, the invention provides a kind of positron emission fault figure based on depth rarefaction representation
The fusion method of picture and MRI, solve mentioned above in view of being currently based on the fusion method of learning-oriented dictionary is all
Image is merged under the single yardstick of image area, although this kind of method can more accurately be intended compared with analytic transformation type-word allusion quotation
Data are closed, but can not multiple dimensioned ground analyze data.Generally comprised in view of image under different scale, different directions different
Feature, and these features be often image co-registration need distinguish and retain protrusion information, existing technology be difficult solve with
Upper problem.
(2) technical scheme
To realize object above, the present invention is achieved by the following technical programs：It is a kind of based on depth rarefaction representation
Positron emission fault image and MRI, including for generating the magnetic resonance imaging component of magnetic resonance imaging image, use
In the positron emission computerized tomography component of generation image in positron emission tomography, the inspection automatically moved for load-bearing
Platform, for controlling the imaging of positron emission computerized tomography component and magnetic resonance imaging component, storage, show and utilize first
Memory cell merges magnetic resonance imaging image and image in positron emission tomography, first memory cell are internally provided with
Multiple yardstick training dictionaries, described to check that platform checks the electric machine assembly of platform movement equipped with control, the inspection platform is set
The centre of positron emission computerized tomography device and magnetic resonance imaging component is placed in, first memory cell is sent out with the positive electron
Penetrate section scanner, the MR scanner is connected by data line respectively with the patient couch.
Preferably, first memory cell is internally provided with multiple yardstick training dictionaries, and training step is as follows：
Step 1：Wavelet basis function is selected, sub- dictionary number is with S (relevant with decomposed class and wavelet type), every sub- word
The size n and training image of the atomicity dictionary atom of allusion quotation, wherein, training image can be source images in itself or
With the image of its same type；
Step 2：Initialize all sub- dictionaries；
Step 3：Wavelet transformation decomposition is carried out to each width training image, then each width training image decomposites S subband；
To all training image subbands using step as sliding step, the sliding window that size is √ n × √ n divides step 4.
Block, stretch and be arranged in order into vector again；
Step 5：Learn sub- dictionary to each subband respectively with K-SVD algorithms to calculate；
Step 6：It is just multi-scale dictionary to obtain all sub- dictionaries.
Preferably, the inspection platform is made up of steel plate, backing plate and leather, the inspection platform and the mobile motor
Component is electrically connected with.
Preferably, between the inspection platform and the positron emission computerized tomography device and magnetic resonance imaging component at least
Between be separated with 380cm.
Preferably, the shell of the positron emission computerized tomography component is pasted with radio frequency shielded enclosure.
Preferably, the mobile motor component is made up of motor, gear, belt and power transmission shaft, the motor of the movement
Component can realize the upset within the transverse shifting for checking platform and 60 °.
Preferably, the positron emission computerized tomography component is made up of nonmagnetic substance.
Preferably, it is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion side of MRI
Method,
Step 1：According to source images or with the excessively complete dictionary of source images acquisition mode identical image study；
Step 2：Sparse coding extraction source characteristics of image is carried out to source images by the dictionary；
Step 3：Further according to certain rule fusion rarefaction representation coefficient；
Step 4：Fused images are reconstructed finally by dictionary and the rarefaction representation coefficient of fusion.
(3) beneficial effect
The invention provides a kind of based on the positron emission fault image of depth rarefaction representation and melting for MRI
Conjunction method.Possesses following beneficial effect：
1st, should be based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI, by small
Ripple basic function initializes and training dictionary, training dictionary on the multiple yardsticks of wavelet field, it can be made both to keep rarefaction representation
The ability of data, can be multiple dimensioned lower with marginally but also with the performance of multiscale analysis, and then in image co-registration problem
The significant feature of coefficient extraction image, reaches compared with image interfusion method and multi-scale wavelet based on dictionary learning under single scale
The more excellent syncretizing effect of fusion method.
2nd, should based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI, by
First memory cell is internally provided with multiple yardstick training dictionaries, makes image to carry out Its Sparse Decomposition on the dictionary, i.e., few
Measuring the linear combination of atom just can represent source images, recycle rarefaction representation coefficient to be closed correspondingly with atom in redundant dictionary
System so that atom corresponding to non-zero rarefaction representation coefficient can be with the notable feature in effecting reaction source images, by merging these
Feature, obtain final fused images.
3rd, should based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI, by with
First memory cell is internally provided with the Sparse coding extraction source characteristics of image inside multiple yardstick training dictionaries, can more chis
Degree ground analyze data, and the protrusion information characteristics that these image co-registrations need to distinguish and retain can be preserved.
4th, should be based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI, by setting
Inspection platform is put, checks that platform is made up of steel plate, backing plate and leather, checks that platform is electrically connected with mobile electric machine assembly,
380cm is separated between checking between platform and positron emission computerized tomography device and magnetic resonance imaging component at least, is not only increased
The hardness and bearing capacity of platform are checked, is used in the examinee of all body weight, and positional distance is set most preferably, is easy to
Normal, the efficient work of positron emission computerized tomography device and magnetic resonance imaging component.
5th, should be based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI, by setting
Mobile motor component is put, mobile motor component is made up of motor, gear, belt and power transmission shaft, and mobile motor component can be realized
Check platform transverse shifting and 60 ° within upset, not only increase check platform stationarity and automation journey
Degree, and doctor can check platform to move the body of examinee by controlling so that the body energy of examinee
Enough in optimum detection region, reduce traditional checking step, improve inspection efficiency.
Embodiment
Below in conjunction with the embodiment of the present invention, the technical scheme in the embodiment of the present invention is clearly and completely described,
Obviously, described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Based in the present invention
Embodiment, the every other embodiment that those of ordinary skill in the art are obtained under the premise of creative work is not made, all
Belong to the scope of protection of the invention.
The embodiment of the present invention provides a kind of positron emission fault image and MRI based on depth rarefaction representation,
Including the magnetic resonance imaging component for generating magnetic resonance imaging image, for generating image in positron emission tomography just
Positron emission tomography component, for the inspection platform automatically moved of load-bearing, for controlling positron emission computerized tomography
The imaging of component and magnetic resonance imaging component, storage, show and using the first memory cell fusion magnetic resonance imaging image and just
Positron emission tomography image, the first memory cell are internally provided with multiple yardstick training dictionaries, check platform equipped with control
System checks the electric machine assembly of platform movement, checks that platform is arranged at positron emission computerized tomography device and magnetic resonance imaging component
Centre, the first memory cell pass through data respectively with positron emission computerized tomography device, MR scanner and patient couch
Transmission line connects.
In summary, should be based on the positron emission fault image of depth rarefaction representation and the fusion side of MRI
Method, by wavelet basis function initialization and training dictionary, training dictionary on the multiple yardsticks of wavelet field, it can be made both to keep
The ability of rarefaction representation data, can be under multiple dimensioned but also with the performance of multiscale analysis, and then in image co-registration problem
With the significant feature of marginally coefficient extraction image, reach compared with the image interfusion method under single scale based on dictionary learning and small
The more excellent syncretizing effect of ripple Multiscale Fusion method.
Secondly, by being internally provided with multiple yardstick training dictionaries in the first memory cell, image energy on the dictionary is made
Its Sparse Decomposition is enough carried out, i.e., the linear combination of a small amount of atom just can represent source images, recycle rarefaction representation coefficient and redundancy word
The one-to-one relation of atom in allusion quotation so that atom corresponding to non-zero rarefaction representation coefficient can be with aobvious in effecting reaction source images
Feature is write, by merging these features, obtains final fused images.
Also, carried by being internally provided with the Sparse coding inside multiple yardstick training dictionaries with the first memory cell
Take source images feature, energy multiple dimensioned ground analyze data, and the prominent letter that these image co-registrations can be needed to distinguish and retained
Breath feature preserves.
Also, platform is checked by setting, checks that platform is made up of steel plate, backing plate and leather, checks platform and movement
Electric machine assembly be electrically connected with, check and be at least spaced between platform and positron emission computerized tomography device and magnetic resonance imaging component
There is 380cm, not only increase the hardness and bearing capacity for checking platform, be used in the examinee of all body weight, and position
Put distance to set most preferably, be easy to normal, the efficient work of positron emission computerized tomography device and magnetic resonance imaging component.
Also, by setting mobile motor component, mobile motor component is made up of motor, gear, belt and power transmission shaft,
Mobile motor component can realize the upset within the transverse shifting for checking platform and 60 °, not only increase and check the flat of platform
Stability and automaticity, and doctor can check platform to move the body of examinee by controlling so that quilt
The body of inspection personnel can reduce traditional checking step in optimum detection region, improve inspection efficiency.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.
Although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of changes, modification can be carried out to these embodiments, replace without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (8)
1. a kind of positron emission fault image and MRI based on depth rarefaction representation, it is characterised in that：Including with
In the magnetic resonance imaging component of generation magnetic resonance imaging image, the positive electron for generating image in positron emission tomography is sent out
Penetrate tomoscan component, for the inspection platform automatically moved of load-bearing, for control positron emission computerized tomography component and
The imaging of magnetic resonance imaging component, storage, show and utilize the first memory cell fusion magnetic resonance imaging image and positive electron hair
Penetrate tomoscan image, first memory cell is internally provided with multiple yardstick training dictionaries, the inspection platform equipped with
Control checks the electric machine assembly of platform movement, and the inspection platform is arranged at positron emission computerized tomography device and magnetic resonance imaging
The centre of component, first memory cell and the positron emission computerized tomography device, the MR scanner and described
Patient couch is connected by data line respectively.
2. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：First memory cell is internally provided with multiple yardstick training dictionaries, and training step is such as
Under：
Step 1：Wavelet basis function is selected, sub- dictionary number is with S（It is relevant with decomposed class and wavelet type）, every individual sub- dictionary
The size n and training image of atomicity dictionary atom, wherein, training image can be source images in itself or and its
The image of same type；
Step 2：Initialize all sub- dictionaries；
Step 3：Wavelet transformation decomposition is carried out to each width training image, then each width training image decomposites S subband；
For step 4. to all training image subbands using step as sliding step, size is √ n × √ n sliding window piecemeal, is drawn
Directly vector is arranged in order into again；
Step 5：Learn sub- dictionary to each subband respectively with K-SVD algorithms to calculate；
Step 6：It is just multi-scale dictionary to obtain all sub- dictionaries.
3. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：It is described inspection platform be made up of steel plate, backing plate and leather, it is described inspection platform with it is described
Mobile electric machine assembly is electrically connected with.
4. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：The inspection platform and the positron emission computerized tomography device and magnetic resonance imaging component
Between at least between be separated with 380cm.
5. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：The shell of the positron emission computerized tomography component is pasted with radio frequency shielded enclosure.
6. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：The mobile motor component is made up of motor, gear, belt and power transmission shaft, the movement
Electric machine assembly can realize check platform transverse shifting and 60 ° within upset.
7. a kind of positron emission fault image and MRI based on depth rarefaction representation according to claim 1
Fusion method, it is characterised in that：The positron emission computerized tomography component is made up of nonmagnetic substance.
8. a kind of existed based on the positron emission fault image of depth rarefaction representation with the fusion method of MRI, its feature
In：
Step 1：According to source images or with the excessively complete dictionary of source images acquisition mode identical image study；
Step 2：Sparse coding extraction source characteristics of image is carried out to source images by the dictionary；
Step 3：Further according to certain rule fusion rarefaction representation coefficient；
Step 4：Fused images are reconstructed finally by dictionary and the rarefaction representation coefficient of fusion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053557.1A CN107680072A (en) | 2017-11-01 | 2017-11-01 | It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053557.1A CN107680072A (en) | 2017-11-01 | 2017-11-01 | It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107680072A true CN107680072A (en) | 2018-02-09 |
Family
ID=61143417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711053557.1A Pending CN107680072A (en) | 2017-11-01 | 2017-11-01 | It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107680072A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020118617A1 (en) * | 2018-12-13 | 2020-06-18 | 深圳先进技术研究院 | Large-view magnetic resonance scanning image reconstruction method and device based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101496721A (en) * | 2008-01-31 | 2009-08-05 | 上海西门子医疗器械有限公司 | Examining bed |
| US20110196228A1 (en) * | 2004-09-06 | 2011-08-11 | Zang Hee Cho | Pet-mri hybrid apparatus and method of implementing the same |
| CN102688053A (en) * | 2011-03-22 | 2012-09-26 | 北京大基康明医疗设备有限公司 | System and method for fusing image of positron emission tomography and image of magnetic resonance imaging |
| CN102855616A (en) * | 2012-08-14 | 2013-01-02 | 西北工业大学 | Image fusion method based on multi-scale dictionary learning |
| CN106228528A (en) * | 2016-07-29 | 2016-12-14 | 华北电力大学 | A kind of multi-focus image fusing method based on decision diagram Yu rarefaction representation |
| CN107194912A (en) * | 2017-04-20 | 2017-09-22 | 中北大学 | The brain CT/MR image interfusion methods of improvement coupling dictionary learning based on rarefaction representation |
-
2017
- 2017-11-01 CN CN201711053557.1A patent/CN107680072A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110196228A1 (en) * | 2004-09-06 | 2011-08-11 | Zang Hee Cho | Pet-mri hybrid apparatus and method of implementing the same |
| CN101496721A (en) * | 2008-01-31 | 2009-08-05 | 上海西门子医疗器械有限公司 | Examining bed |
| CN102688053A (en) * | 2011-03-22 | 2012-09-26 | 北京大基康明医疗设备有限公司 | System and method for fusing image of positron emission tomography and image of magnetic resonance imaging |
| CN102855616A (en) * | 2012-08-14 | 2013-01-02 | 西北工业大学 | Image fusion method based on multi-scale dictionary learning |
| CN106228528A (en) * | 2016-07-29 | 2016-12-14 | 华北电力大学 | A kind of multi-focus image fusing method based on decision diagram Yu rarefaction representation |
| CN107194912A (en) * | 2017-04-20 | 2017-09-22 | 中北大学 | The brain CT/MR image interfusion methods of improvement coupling dictionary learning based on rarefaction representation |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020118617A1 (en) * | 2018-12-13 | 2020-06-18 | 深圳先进技术研究院 | Large-view magnetic resonance scanning image reconstruction method and device based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | Image segmentation algorithm of lung cancer based on neural network model | |
| El-Baz et al. | Biomedical image segmentation: advances and trends | |
| Gerig et al. | Shape analysis of brain ventricles using spharm | |
| CN102737250B (en) | To the method and system of spinal injury automatic detection in 3D medical images | |
| CN106203488B (en) | A kind of galactophore image Feature fusion based on limited Boltzmann machine | |
| CN109978838A (en) | Image-region localization method, device and Medical Image Processing equipment | |
| Li et al. | Wavelet-based segmentation of renal compartments in DCE-MRI of human kidney: initial results in patients and healthy volunteers | |
| CN106096636A (en) | A kind of Advancement Type mild cognition impairment recognition methods based on neuroimaging | |
| Yousif et al. | An improved approach for medical image fusion using sparse representation and Siamese convolutional neural network | |
| CN104834943A (en) | Brain tumor classification method based on deep learning | |
| CN103985099A (en) | Dispersion tensor magnetic resonance image tensor domain non-local mean denoising method | |
| CN109522971A (en) | A kind of CS-MRI image reconstructing method based on classification image block rarefaction representation | |
| Qian et al. | [Retracted] 3D Automatic Segmentation of Brain Tumor Based on Deep Neural Network and Multimodal MRI Images | |
| CN100444176C (en) | Method and system for displaying confidence intervals for source reconstruction | |
| CN104281856A (en) | Image preprocessing method and system for brain medical image classification | |
| Vanstone et al. | A survey of the application of soft computing to investment and financial trading | |
| CN107680072A (en) | It is a kind of based on the positron emission fault image of depth rarefaction representation and the fusion method of MRI | |
| CN112150564A (en) | Medical image fusion algorithm based on deep convolutional neural network | |
| CN106251299A (en) | A kind of high-efficient noise-reducing visual pattern reconstructing method | |
| CN104331864B (en) | Based on the processing of the breast image of non-down sampling contourlet and the significant model of vision | |
| CN110363833A (en) | A kind of complete human body sport parameter representation method based on local rarefaction representation | |
| CN113935957A (en) | Medical image comparison method and device, electronic equipment and storage medium | |
| Wang et al. | An efficient fusion algorithm combining feature extraction and variational optimization for CT and MR images | |
| Zhang et al. | Iterative convolutional encoder-decoder network with multi-scale context learning for liver segmentation | |
| CN109146005A (en) | A kind of brain cognitive ability analysis method based on rarefaction representation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180209 |