CN109686425A - A method of accelerating global reconstruction human brain neuro images technology - Google Patents
A method of accelerating global reconstruction human brain neuro images technology Download PDFInfo
- Publication number
- CN109686425A CN109686425A CN201910045069.9A CN201910045069A CN109686425A CN 109686425 A CN109686425 A CN 109686425A CN 201910045069 A CN201910045069 A CN 201910045069A CN 109686425 A CN109686425 A CN 109686425A
- Authority
- CN
- China
- Prior art keywords
- module
- output end
- input terminal
- global
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R33/00—Arrangements or instruments for measuring magnetic variables
- G01R33/20—Arrangements or instruments for measuring magnetic variables involving magnetic resonance
- G01R33/44—Arrangements or instruments for measuring magnetic variables involving magnetic resonance using nuclear magnetic resonance [NMR]
- G01R33/48—NMR imaging systems
- G01R33/54—Signal processing systems, e.g. using pulse sequences ; Generation or control of pulse sequences; Operator console
- G01R33/56—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution
- G01R33/5602—Image enhancement or correction, e.g. subtraction or averaging techniques, e.g. improvement of signal-to-noise ratio and resolution by filtering or weighting based on different relaxation times within the sample, e.g. T1 weighting using an inversion pulse
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- General Health & Medical Sciences (AREA)
- Radiology & Medical Imaging (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- High Energy & Nuclear Physics (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
Accelerate the global method for rebuilding human brain neuro images technology the invention discloses a kind of, Step 1: the construction of neural map；Step 2: image to be reconstructed and neural atlas image are registrated；Neural connection is rebuild using global method for reconstructing, forms general neural map after the screening of data comparison module, Step 3: global reconstruction of individual neuro images on the basis of neural map；Step 4: the update deposit of neural map；The present invention relates to rebuild human brain neuro images technical field from human brain diffusion weighted magnetic resonance images, and the overall situation.The method of acceleration overall situation reconstruction human brain neuro images technology, utilize neural map and the anatomical knowledge of priori, effectively reduce the time of global cerebral nerve image reconstruction, it is doctor within the time short to the greatest extent, a kind of means of effective assisting in diagnosis and treatment are provided, deposit is updated to information simultaneously, reinforces the practical application effect of the technology, specifies better and better, more perfect developing direction.
Description
Technical field
The present invention relates to from human brain diffusion weighted magnetic resonance images, and it is global rebuild human brain neuro images technical field,
It is specially a kind of to accelerate the global method for rebuilding human brain neuro images technology.
Background technique
Nerve is to be made of the nerve fibre gathered into bundles, and nerve fibre construction itself is outside the aixs cylinder by neuron
Myelin cladding is formed by by Deiter's cells；Many nerve fibres gather into bundles, and outside encloses to be made of connective
Film just becomes a nerve, and nervous system is mainly made of three digest journals, i.e. central nervous system, cranial nerve, spinal nerve.Respectively
Between system centered on central nervous system, mental functioning, diffusion-weighted MR imaging are realized in division of labor collaboration jointly
It is then to provide a kind of means portraying human brain nerve and connecting with clinician for scientific research personnel, is the development for judging brain, degenerates
And the important channel of lesion.
(Global) and local (Local) two that the reconstruction (Tractography) of neuro images is divided into the algorithm overall situation is big
The speed of class, partial reconstruction method is fast, but application condition is big；Global reconstruction technique gives fixed number in view of reconstructed results and entirely
Whether according to matching, therefore no matter algorithm for reconstructing from accuracy and noise resisting ability all than part is much better than.But due to complete
Office's method for reconstructing be from entire unordered state, it is gradually excellent by Monte Carlo-Markov chain combination simulated annealing algorithm
Change reconstruction model, is finally reached optimal solution, needs long time, the perfect reconstruction of the neuro images of usual one common human brain
Process, few then three to five hours, more then a couple of days.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, accelerate the global side for rebuilding human brain neuro images technology the present invention provides a kind of
Method, solving existing global method for reconstructing is to need long time since entire unordered state, can complete mind
The problem of through image perfect reconstruction process.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs: a kind of acceleration is global to rebuild human brain mind
Method through image technique, specifically includes the following steps:
Step 1: the construction of neural map: user enters server from client, the register pipe after authentication
In reason system, is directly networked using central processing module by the key message extraction module in pretreatment unit and weighted from open
Magnetic resonance data set obtains DW-MRI data and T1 image；
Step 2: image to be reconstructed and neural atlas image are registrated: the DW-MRI data and T1 that will be obtained in step 1
Image rebuilds respectively nerve connection using the global method rebuild respectively, FNIRT of the segment of fiber in FSL software package is passed through non-
The direction in Linear Mapping module transfer MNI standard brain space, segment of fiber adjusts module according to local deformation by segment of fiber
The adjustment of Jacobian value forms general neural map after the screening of data comparison module, then passes general neural map
It is defeated into Comparison of standards module；
Step 3: global on the basis of neural map of individual neuro images is rebuild: by input module by one side of information
Face is input in step 2 in Comparison of standards module obtained, is formed registration image by preliminary image-forming module, is on the other hand existed
Complete the reconstruction work of cerebral nerve image on the basis of this with conventional general global method for reconstructing by traditional reconstruction module
Make；
Step 4: the update deposit of neural map: by intact nervous map obtained in traditional reconstruction module in step 3
It is transferred in the memory module updated in deposit unit, then extraction module extracts the information of addition and passed by analysis
Defeated into information comparison module, the information after comparison is transferred in temporary storage module, and information is then passed through encryption transmitting mould
Block encryption is transferred in information storage module, completes storage.
Preferably, a kind of acceleration is global rebuilds human brain neuro images technology, including client, server and operational administrative system
System, the client are bi-directionally connected by Ethernet and server realization, the server via Ethernet and operational administrative system
System realizes and is bi-directionally connected that the operational administrative system is bi-directionally connected with central processing module realization, the central processing module point
Not with open weighted magnetic resonance data set, pretreatment unit, rebuild trimming unit, Comparison of standards module, input module and information
Memory module realization is bi-directionally connected, and the output end of the open weighted magnetic resonance data set and the input terminal of pretreatment unit connect
It connects, the output end of the pretreatment unit is connect with the input terminal for rebuilding trimming unit, the reconstruction trimming unit and input mould
The output end of block is connect with the input terminal of Comparison of standards module, the output end and preliminary image-forming module of the Comparison of standards module
Input terminal connection, the output end of the input module and preliminary image-forming module connect with the input terminal of traditional reconstruction module,
The output end of the traditional reconstruction module with update deposit unit input terminal connect, it is described update deposit unit output end and
The input terminal of information storage module connects.
Preferably, the pretreatment unit includes key message extraction module, DW-MRI data and T1 image, the key
The output end of information extraction modules is connect with the input terminal of DW-MRI data and T1 image respectively.
Preferably, the reconstruction trimming unit includes non-linear mapping module, segment of fiber adjustment module, Data Integration mould
Block, data comparison module and general neural map, output end and the segment of fiber of the non-linear mapping module adjust the defeated of module
Enter end connection, the output end of the segment of fiber adjustment module is connect with the input terminal of Data Integration module, the Data Integration mould
The output end of block and the input terminal of data comparison module connect, the output end of the data comparison module and general neural map
Input terminal connection.
Preferably, the update deposit unit includes memory module, analysis extraction module, information comparison module, temporarily deposits
Module and encryption transmitting module are stored up, the output end of the memory module is connect with the input terminal of analysis extraction module, the analysis
The output end of extraction module is connect with the input terminal of information comparison module, the output end of the information comparison module and interim storage
The input terminal of module connects, and the output end of the temporary storage module is connect with the input terminal of encryption transmitting module.
Preferably, the output end of the encryption transmitting module and the input terminal of information storage module connect.
Preferably, the quantity that the key message extraction module extracts is 20 components.
Preferably, segment of fiber is exactly that nerve has spatial position (three in connection performance in the segment of fiber adjustment module
Dimension) and direction (bidimensional) two attributes segment of fiber one by one.
(3) beneficial effect
Accelerate the global method for rebuilding human brain neuro images technology the present invention provides a kind of.Have it is following the utility model has the advantages that
The method that the acceleration overall situation rebuilds human brain neuro images technology, by Step 1: neural map construction: Yong Hucong
Client enters server, after authentication in register management system, passes through pretreatment using central processing module
Key message extraction module in unit, which is directly networked, obtains DW-MRI data and T1 image from open weighted magnetic resonance data set；
Step 2: image to be reconstructed and neural atlas image are registrated: the DW-MRI data obtained in step 1 and T1 image are utilized
The method that the overall situation is rebuild rebuilds respectively nerve connection respectively, and FNIRT of the segment of fiber in FSL software package is passed through Nonlinear Mapping
The direction in module transfer MNI standard brain space, segment of fiber adjusts Jacobian of the module according to local deformation by segment of fiber
Value adjustment forms general neural map after the screening of data comparison module, and general neural map is then transferred to standard
In contrast module；Step 3: global on the basis of neural map of individual neuro images is rebuild: by input module by information one
Aspect is input in step 2 in Comparison of standards module obtained, is passed through preliminary image-forming module and is formed registration image, on the other hand
Complete the reconstruction of cerebral nerve image with conventional general global method for reconstructing by traditional reconstruction module on this basis
Work；Step 4: the update deposit of neural map: by intact nervous map transmission obtained in traditional reconstruction module in step 3
Into the memory module updated in deposit unit, then extraction module extracts the information of addition and is transmitted to by analysis
In information comparison module, the information after comparison is transferred in temporary storage module, then adds information by encrypting transmitting module
It is close to be transferred in information storage module, storage is completed, using neural map and the anatomical knowledge of priori, is effectively reduced global big
The time of cranial nerve image reconstruction provides a kind of means of effective assisting in diagnosis and treatment within the time short to the greatest extent for doctor, while right
Information is updated deposit, strengthens the practical application effect of the technology, specifies better and better, more perfect development side
To.
Detailed description of the invention
Fig. 1 is system principle diagram of the invention；
Fig. 2 is the system principle diagram of pretreatment unit of the present invention；
Fig. 3 is the system principle diagram that the present invention rebuilds trimming unit；
Fig. 4 is the system principle diagram that the present invention updates storage unit.
In figure, 1-client, 2-servers, 3-operational administrative systems, 4-central processing modules, 5-open weightings
Magnetic resonance data set, 6-pretreatment units, 7-rebuild trimming unit, 8-Comparison of standards modules, 9-input modules, 10-letters
Breath memory module, 11-preliminary image-forming modules, 12-traditional reconstruction modules, 13-update deposit units, 14-key messages mention
Modulus block, 15-DW-MRI data, 16-T1 images, 17-non-linear mapping modules, 18-segment of fiber adjustment module, 19-numbers
According to integrate module, 20-data comparison modules, 21-general neural maps, 22-memory modules, 23-analysis extraction modules,
24-information comparison modules, 25-temporary storage modules, 26-encryption transmitting modules.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Please refer to Fig. 1-4, the embodiment of the present invention provides a kind of technical solution: a kind of acceleration is global to rebuild human brain neuro images
The method of technology, specifically includes the following steps:
Step 1: the construction of neural map: user enters server 2, the register after authentication from client 1
In management system 3, using central processing module 4 by the key message extraction module 14 in pretreatment unit 6 directly network from
Open weighted magnetic resonance data set 5 obtains DW-MRI data 15 and T1 image 16；Step 2: image to be reconstructed and neural map figure
The registration of picture: the DW-MRI data 15 obtained in step 1 and T1 image 16 are rebuild respectively respectively using the global method rebuild
Segment of fiber is transmitted MNI standard brain space by non-linear mapping module 17 with the FNIRT in FSL software package by nerve connection,
The direction of segment of fiber adjusts module 18 by segment of fiber and adjusts according to the Jacobian value of local deformation, by data comparison module
General neural map 21 is formed after 20 screening, and then general neural map 21 is transferred in Comparison of standards module 8；Step
Three, global reconstruction of individual neuro images on the basis of neural map: on the one hand information is input to by step by input module 9
In two in Comparison of standards module 8 obtained, registration image is formed by preliminary image-forming module 11, on the other hand on this basis
The reconstruction of cerebral nerve image is completed with conventional general global method for reconstructing by traditional reconstruction module 12；Step
Four, the update deposit of neural map: by intact nervous map obtained is transferred to update in traditional reconstruction module 12 in step 3
It lays in the memory module 22 in unit 13, then extraction module 23 extracts the information of addition and is transmitted to by analysis
In information comparison module 24, the information after comparison is transferred in temporary storage module 25, and information is then passed through encryption transmitting mould
26 encrypted transmission of block is completed storage, using neural map and the anatomical knowledge of priori, is effectively subtracted into information storage module 10
The time of few overall situation cerebral nerve image reconstruction is doctor within the time short to the greatest extent, provides a kind of hand of effective assisting in diagnosis and treatment
Section, while deposit is updated to information, the practical application effect of the technology is strengthened, is specified better and better, more perfect
Developing direction.
A kind of acceleration is global to rebuild human brain neuro images technology, including client 1, server 2 and operational administrative system 3,
Client 1 is bi-directionally connected by Ethernet and the realization of server 2, and server 2 is realized double by Ethernet and operational administrative system 3
To connection, operational administrative system 3 is bi-directionally connected with the realization of central processing module 4, and central processing module 4 is ARM9 series of processes
Device, central processing module 4 respectively with open weighted magnetic resonance data set 5, pretreatment unit 6, rebuild trimming unit 7, standard pair
Be bi-directionally connected than the realization of module 8, input module 9 and information storage module 10, the output end of open weighted magnetic resonance data set 5 with
The input terminal of pretreatment unit 6 connects, and pretreatment unit 6 includes key message extraction module 14, DW-MRI data 15 and T1 figure
As 16, the quantity that key message extraction module 14 extracts is 20 components, the output end of key message extraction module 14 respectively with
DW-MRI data 15 are connected with the input terminal of T1 image 16, the output end of pretreatment unit 6 and the input terminal for rebuilding trimming unit 7
Connection, rebuilding trimming unit 7 includes non-linear mapping module 17, segment of fiber adjustment module 18, Data Integration module 19, data ratio
Compared with module 20 and general neural map 21, the input terminal of output end and segment of fiber the adjustment module 18 of non-linear mapping module 17 connects
It connects, segment of fiber is exactly that nerve has spatial position (three-dimensional) and direction (bidimensional) in connection performance in segment of fiber adjustment module 18
The output end of the segment of fiber one by one of two attributes, segment of fiber adjustment module 18 is connect with the input terminal of Data Integration module 19,
The output end of Data Integration module 19 is connect with the input terminal of data comparison module 20, the output end of data comparison module 20 and logical
Connected with the input terminal of neural map 21, rebuild the output end of trimming unit 7 and input module 9 with Comparison of standards module 8
Input terminal connection, the output end of Comparison of standards module 8 connect with the input terminal of preliminary image-forming module 11, input module 9 with tentatively
The output end of image-forming module 11 is connect with the input terminal of traditional reconstruction module 12, the output end of traditional reconstruction module 12 and update
The input terminal connection for laying in unit 13 updates deposit unit 13 including memory module 22, analysis extraction module 23, information and compares mould
Block 24, temporary storage module 25 and encryption transmitting module 26, the input of the output end and analysis extraction module 23 of memory module 22
End connection, analysis extraction module 23 output end connect with the input terminal of information comparison module 24, information comparison module 24 it is defeated
Outlet is connect with the input terminal of temporary storage module 25, the input of the output end and encryption transmitting module 26 of temporary storage module 25
The output end of end connection, encryption transmitting module 26 is connect with the input terminal of information storage module 10, updates the defeated of deposit unit 13
Outlet is connect with the input terminal of information storage module 10.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions.By sentence " element limited including one ..., it is not excluded that
There is also other identical elements in the process, method, article or apparatus that includes the element ".
It 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 variations, modification, replacement can be carried out to these embodiments 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 accelerate the global method for rebuilding human brain neuro images technology, it is characterised in that: specifically includes the following steps:
Step 1: the construction of neural map: user enters server (2) from client (1), the register after authentication
It is straight by the key message extraction module (14) in pretreatment unit (6) using central processing module (4) in management system (3)
It connects networking and obtains DW-MRI data (15) and T1 image (16) from open weighted magnetic resonance data set (5)；
Step 2: image to be reconstructed and neural atlas image are registrated: the DW-MRI data (15) and T1 that will be obtained in step 1
Image (16) rebuilds respectively nerve connection using the global method rebuild respectively, and FNIRT of the segment of fiber in FSL software package is led to
Cross non-linear mapping module (17) transmission MNI standard brain space, the direction of segment of fiber by segment of fiber adjust module (18) according to
It is adjusted according to the Jacobian value of local deformation, forms general neural map (21) after the screening of data comparison module (20),
Then general neural map (21) is transferred in Comparison of standards module (8)；
Step 3: global on the basis of neural map of individual neuro images is rebuild: by input module (9) by information on the one hand
It is input in step 2 in Comparison of standards module (8) obtained, passes through preliminary image-forming module (11) and form registration image, another party
Face passes through traditional reconstruction module (12) on this basis and completes cerebral nerve image with conventional general global method for reconstructing
Reconstruction；
Step 4: the update deposit of neural map: by intact nervous map obtained in traditional reconstruction module (12) in step 3
It is transferred in the memory module (22) updated in deposit unit (13), then extraction module (23) extracts addition by analysis
Information is simultaneously transmitted in information comparison module (24), and the information after comparison is transferred in temporary storage module (25), then
Information is completed into storage in information storage module (10) by encryption transmitting module (26) encrypted transmission.
2. a kind of acceleration is global to rebuild human brain neuro images technology, including client (1), server (2) and operational administrative system
(3), the client (1) is realized by Ethernet and server (2) and is bi-directionally connected, the server (2) by Ethernet and
Operational administrative system (3) realization is bi-directionally connected, it is characterised in that: the operational administrative system (3) and central processing module (4) are real
Now be bi-directionally connected, the central processing module (4) respectively with open weighted magnetic resonance data set (5), pretreatment unit (6), again
Trimming unit (7), Comparison of standards module (8), input module (9) and information storage module (10) realization is built to be bi-directionally connected, it is described
The output end of open weighted magnetic resonance data set (5) is connect with the input terminal of pretreatment unit (6), the pretreatment unit (6)
Output end with rebuild trimming unit (7) input terminal connect, it is described reconstruction trimming unit (7) and input module (9) output
End is connect with the input terminal of Comparison of standards module (8), the output end and preliminary image-forming module of the Comparison of standards module (8)
(11) input terminal connection, the output end of the input module (9) and preliminary image-forming module (11) with traditional reconstruction module
(12) input terminal connection, the output end of the traditional reconstruction module (12) are connect with the input terminal for updating deposit unit (13),
The output end for updating deposit unit (13) is connect with the input terminal of information storage module (10).
3. a kind of acceleration according to claim 2 is global to rebuild human brain neuro images technology, it is characterised in that: the pre- place
Reason unit (6) includes key message extraction module (14), DW-MRI data (15) and T1 image (16), and the key message extracts
The output end of module (14) is connect with the input terminal of DW-MRI data (15) and T1 image (16) respectively.
4. a kind of acceleration according to claim 2 is global to rebuild human brain neuro images technology, it is characterised in that: the reconstruction
Trimming unit (7) includes non-linear mapping module (17), segment of fiber adjustment module (18), Data Integration module (19), data ratio
Compared with module (20) and general neural map (21), the output end and segment of fiber of the non-linear mapping module (17) adjust module
(18) input terminal connection, the output end of segment of fiber adjustment module (18) and the input terminal of Data Integration module (19) connect
It connects, the output end of the Data Integration module (19) is connect with the input terminal of data comparison module (20), and the data compare mould
The output end of block (20) is connect with the input terminal of general neural map (21).
5. a kind of acceleration according to claim 2 is global to rebuild human brain neuro images technology, it is characterised in that: the update
Deposit unit (13) includes memory module (22), analysis extraction module (23), information comparison module (24), temporary storage module
(25) connect with encryption transmitting module (26), the output end of the memory module (22) and the input terminal of analysis extraction module (23)
It connects, the output end of analysis extraction module (23) is connect with the input terminal of information comparison module (24), and the information compares mould
The output end of block (24) is connect with the input terminal of temporary storage module (25), the output end of the temporary storage module (25) with plus
The input terminal of close transmitting module (26) connects.
6. a kind of acceleration according to claim 5 is global to rebuild human brain neuro images technology, it is characterised in that: the encryption
The output end of transmitting module (26) is connect with the input terminal of information storage module (10).
7. a kind of acceleration according to claim 3 is global to rebuild human brain neuro images technology, it is characterised in that: the key
The quantity that information extraction modules (14) are extracted is 20 components.
8. a kind of acceleration according to claim 4 is global to rebuild human brain neuro images technology, it is characterised in that: the fiber
In section adjustment module (18) segment of fiber be exactly nerve in connection performance with spatial position (three-dimensional) and direction (bidimensional) two
The segment of fiber one by one of attribute.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910045069.9A CN109686425B (en) | 2019-01-17 | 2019-01-17 | System and method for accelerating global reconstruction technology of human brain nerve image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910045069.9A CN109686425B (en) | 2019-01-17 | 2019-01-17 | System and method for accelerating global reconstruction technology of human brain nerve image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109686425A true CN109686425A (en) | 2019-04-26 |
| CN109686425B CN109686425B (en) | 2020-08-11 |
Family
ID=66193482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910045069.9A Expired - Fee Related CN109686425B (en) | 2019-01-17 | 2019-01-17 | System and method for accelerating global reconstruction technology of human brain nerve image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109686425B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093455A (en) * | 2012-12-21 | 2013-05-08 | 西北工业大学 | Diffusion tensor imaging white matter fiber clustering method |
| CN104240291A (en) * | 2014-09-03 | 2014-12-24 | 中国科学院计算技术研究所 | Image segmentation and reconstruction method and system based on nuclear magnetic resonance image sequences |
| CN104523275A (en) * | 2014-12-25 | 2015-04-22 | 西安电子科技大学 | Construction method for health people white matter fiber tract atlas |
| CN107182216A (en) * | 2015-12-30 | 2017-09-19 | 中国科学院深圳先进技术研究院 | A kind of rapid magnetic resonance imaging method and device based on depth convolutional neural networks |
| US20170285124A1 (en) * | 2014-09-09 | 2017-10-05 | The Trustees Of The University Of Pennsylvania | Edema invariant tractography |
| CN108921789A (en) * | 2018-06-20 | 2018-11-30 | 华北电力大学 | Super-resolution image reconstruction method based on recurrence residual error network |
-
2019
- 2019-01-17 CN CN201910045069.9A patent/CN109686425B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103093455A (en) * | 2012-12-21 | 2013-05-08 | 西北工业大学 | Diffusion tensor imaging white matter fiber clustering method |
| CN104240291A (en) * | 2014-09-03 | 2014-12-24 | 中国科学院计算技术研究所 | Image segmentation and reconstruction method and system based on nuclear magnetic resonance image sequences |
| US20170285124A1 (en) * | 2014-09-09 | 2017-10-05 | The Trustees Of The University Of Pennsylvania | Edema invariant tractography |
| CN104523275A (en) * | 2014-12-25 | 2015-04-22 | 西安电子科技大学 | Construction method for health people white matter fiber tract atlas |
| CN107182216A (en) * | 2015-12-30 | 2017-09-19 | 中国科学院深圳先进技术研究院 | A kind of rapid magnetic resonance imaging method and device based on depth convolutional neural networks |
| CN108921789A (en) * | 2018-06-20 | 2018-11-30 | 华北电力大学 | Super-resolution image reconstruction method based on recurrence residual error network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109686425B (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113643821B (en) | Multi-center knowledge graph joint decision support method and system | |
| CN112162959B (en) | Medical data sharing method and device | |
| EP2409255B1 (en) | Method for creating asymmetrical cryptographic key pairs | |
| CN106295938A (en) | The storage of medical document based on cloud service and utilize system and using method thereof | |
| Fan et al. | Axiomatic design theory: Further notes and its guideline to applications | |
| Turesky et al. | The relationship between biological and psychosocial risk factors and resting‐state functional connectivity in 2‐month‐old Bangladeshi infants: A feasibility and pilot study | |
| DE102019107971A1 (en) | Universal transceiver container | |
| CN109472379A (en) | A kind of reservation diagnosis and treatment management system and method based on internet and cloud platform | |
| CN112565289A (en) | System and method for credible issuing and verifying of medical certificate based on block chain | |
| CN111143859A (en) | Module for collecting credible data and data transmission method | |
| CN111460040A (en) | Data management system based on medical block chain | |
| CN116543210A (en) | Medical image classification method based on federal learning and attention mechanism | |
| CN109686425A (en) | A method of accelerating global reconstruction human brain neuro images technology | |
| CN110084809A (en) | Diabetic retinopathy data processing method, device and electronic equipment | |
| CN105844674A (en) | Color image fusion system and method based on ternary number wavelet transform | |
| CN116189911B (en) | Hospital information system intercommunication method and system based on blockchain side chain technology | |
| CN116580824A (en) | Cross-region medical cooperation prediction method based on federal graph machine learning | |
| CN111680798A (en) | Joint learning model system and method, apparatus, and computer-readable storage medium | |
| DE102018206616A1 (en) | Method for merging different partial data | |
| Qu et al. | Baenet: A brain age estimation network with 3d skipping and outlier constraint loss | |
| CN107731297A (en) | A kind of internet classification instructional management system (IMS) and control method | |
| CN108595291B (en) | Medical data backup system | |
| Yang Luo et al. | Collaborative Modeling of Medical Image Segmentation Based on Blockchain Network | |
| WO2017043680A1 (en) | Artificial neural-network distributed learning system and method for protecting personal information of medical data | |
| Udayakumar et al. | Diffusion MRI preprocessing for Deep Learning Analysis of Brain Structural Connectivity |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200811 Termination date: 20220117 |