CN107653185A - A kind of schizophrenia susceptibility gene detection system - Google Patents

A kind of schizophrenia susceptibility gene detection system Download PDF

Info

Publication number
CN107653185A
CN107653185A CN201711106066.9A CN201711106066A CN107653185A CN 107653185 A CN107653185 A CN 107653185A CN 201711106066 A CN201711106066 A CN 201711106066A CN 107653185 A CN107653185 A CN 107653185A
Authority
CN
China
Prior art keywords
module
image
dna
detection
protein
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
Application number
CN201711106066.9A
Other languages
Chinese (zh)
Inventor
赵庆莲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201711106066.9A priority Critical patent/CN107653185A/en
Publication of CN107653185A publication Critical patent/CN107653185A/en
Pending legal-status Critical Current

Links

Classifications

    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
    • C12Q1/6876—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes
    • C12Q1/6883—Nucleic acid products used in the analysis of nucleic acids, e.g. primers or probes for diseases caused by alterations of genetic material
    • C—CHEMISTRY; METALLURGY
    • C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
    • C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
    • C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
    • C12Q1/68—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving nucleic acids
    • C12Q1/6806—Preparing nucleic acids for analysis, e.g. for polymerase chain reaction [PCR] assay
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B30/00—ICT specially adapted for sequence analysis involving nucleotides or amino acids
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10088—Magnetic resonance imaging [MRI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • G06T2207/30072—Microarray; Biochip, DNA array; Well plate
    • 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
    • G06T2207/30096—Tumor; Lesion

Landscapes

  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Organic Chemistry (AREA)
  • Proteomics, Peptides & Aminoacids (AREA)
  • Physics & Mathematics (AREA)
  • Analytical Chemistry (AREA)
  • Zoology (AREA)
  • Wood Science & Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Genetics & Genomics (AREA)
  • Biotechnology (AREA)
  • Biophysics (AREA)
  • Biochemistry (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Immunology (AREA)
  • Microbiology (AREA)
  • Molecular Biology (AREA)
  • General Physics & Mathematics (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Quality & Reliability (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Investigating Or Analysing Biological Materials (AREA)

Abstract

The invention belongs to detection means manufacture field, discloses a kind of schizophrenia susceptibility gene detection system, extracts serum module connecting detection serum content module；The detection serum content module connection removes protein module；Extract the connection of DNA modules and remove protein module；The detection DNA modules connection extracts DNA modules and refers to DNA library module；DNA species content module connecting detection DNA kind of module；The on-line checking module connection DNA species contents module and sealing archive module.DNA of the invention by extracting patient, the DNA species that Detection and Extraction come out, comparing dna storehouse, it can accurately recognize whether patient suffers from schizophrenia susceptibility gene, treat schizophrenia and advocate early stage, the development of timely, enough antipsychotics symptom managements, prevent recurrence, therefore, diagnosis can be quickly and accurately made, it is significant for the therapy rehabilitation of patient.

Description

A kind of schizophrenia susceptibility gene detection system
Technical field
The invention belongs to detection means manufacture field, more particularly to a kind of schizophrenia susceptibility gene detection system.
Background technology
Schizophrenia is the unknown mental disease of one group of cause of disease, clinical more between twenty and fifty slow or subacute onset On often show as the different syndrome of symptom, be related to many obstacles such as sensory perception, thinking, emotion and behavior and spirit Movable is uncoordinated.The general Clear consciousness of patient, intelligence is normal, but cognition work(occurs in some patientss in lysis The infringement of energy.The course of disease is typically delayed, and in recurrent exerbation, exacerbation or deterioration, some patientss finally occur failing and mental disorder, but Some patients can keep state of fully recovering or be almost recovered after treatment.
At present, China is in the trend risen year by year, schizoid treatment with schizoid number Process is highly difficult, it is necessary to and prevent trouble before it happens, there is doubtful patient to arrive hospital and checked, existing detection schizophrenia Disease method can not accurately recognize the situation of patient very much, and the inspection for some genes is not very well, it is impossible to can be accurate Diagnosis quickly is made, critical effect is not had for the therapy rehabilitation of patient.
Available extraction nucleic acid and nucleic acid detection method are not suitable in sampling onsite application or the reality in sampling onsite application It is limited with property, it is necessary to exquisite, heavy and expensive instrument etc..Therefore, operation inconvenience, the time is expended, extraction can not be made, expanded Increase, detection is carried out as overall.
Diffusion tensor imaging (DTI) is a kind of imaging skill that can provide in vivo water diffusion motion of Noninvasive Art, it can detect traditional MRI not it is observed that tissue micro-variations, be MR imaging techniques important breakthrough.Based on brain The pattern classification of image information is the hot subject in current brain image research.Using image classification method, DTI images tool is calculated There is the possibility size of certain attribute, or automatically differentiate the category attribute of image, be a weight of computer-assisted analysis Apply.
Document " Alexander AL, Lee JE, et a l.Diffusion tensor imaging of the corpus callosum in Autism.Neuroimage.2007；34(1):61-73. " side based on area-of-interest is used Effect of the method research corpus callosum in autism, but this method needs the priori about certain pathology or lesion region to know Know, so without generalization well.
Document " Ridgway GR, Henley SM, et a l.Ten simple rules for reporting voxel-based morphometry studies.Neuroimage.2008；40(4):1429-1435. " use and be based on voxel Double sample t inspection statistics technique study patients and normal person between group difference.This method is assuming that variable meets The influence of single variable is only considered in the case of normal distribution not while considers the influence of multiple variables, and can not be judged Whether single people is patient either normal person.
Document " Madhura Ingalhalikar, et a l.Diffusion based Abnormality Markers of Pathology:Towards Learned Diagnostic Prediction of ASD.Neuroimage.2011；57 (3):918-927 " it is then that gained is special using the anisotropy (FA) in atlas and the value of Mean diffusivity (MD) as feature Sign is added in SVMs (SVM), constantly selects that SVMs can be made to obtain best accuracy by leaving-one method With the feature of generalization.However, this method based on atlas can not extract the correlated variables conduct of subregion under atlas Feature, it can not thus find the region of lesion in subregion.Meanwhile this method does not account for shadow of the age factor to white matter Ring.
In summary, the problem of prior art is present be：Schizoid therapeutic process is highly difficult, it is necessary to prevent in Possible trouble, there is doubtful patient to arrive hospital and checked, existing detection schizophrenia method can not be very accurate The situation of patient is solved, the inspection for some genes is not very well, it is impossible to diagnosis can be quickly and accurately made, for patient Therapy rehabilitation do not have critical effect.The operation inconvenience of existing gene assaying device, expends the time, can not make extraction, Amplification, detection are carried out as overall.
The content of the invention
The problem of existing for prior art, the invention provides a kind of schizophrenia susceptibility gene detection system.
The present invention is achieved in that a kind of schizophrenia susceptibility gene detection system, the schizophrenia susceptibility Gene detection system includes：Blood collector, anticoagulant tube, pipe support, cool room, gene extractor, centrifuge tube, adsorption column, collection Pipe, gene magnification device, gel electrophoresis device；The blood collector is connected with the anticoagulant tube, and the anticoagulant tube is fixed on described On pipe support, the anticoagulant tube is adjacent with the cool room, and the cool room side is the gene extractor, the gene extraction Device is connected with the centrifuge tube, and the adsorption column and the collecting pipe are both placed on the pipe support, the gene magnification device and The gel electrophoresis device is placed on the pipe support side；
The pipe support is connected in the bottom of this device by the way of bolt fixation；
The centrifugation bottom of the tube is connected with centrifugation motor；
The blood collector includes：
Extract serum module, detection serum content module, remove protein module, extraction DNA modules, detection DNA species Module, with reference to DNA library module, DNA species contents module, on-line checking module, sealing archive module；
The extraction serum module connecting detection serum content module；It is mainly to extract the serum of separation to extract serum module In albumen detect nerve growth factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), TNF (TNF-α), BDNF (BDNF), glial fibrillary acidic albumen (GFAP), alkalescence 8 kinds of albumen factor contents of myelin protein (MBP)；Detect serum content and mainly extract 8 kinds of protein factor contents；
The detection serum content module connection removes protein module；Protein module is removed mainly by nerve growth The factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), TNF (TNF- α), BDNF (BDNF), glial fibrillary acidic albumen (GFAP), the hatching egg of myelin basic protein (MBP) 8 Protein outside white factor content removes.
The extraction DNA modules connection removes protein module；Extraction DNA modules mainly remove abundant protein, Compound not soluble in water is formed using using SDS, protein and K ions, the precipitation containing protein is removed by centrifuging, will DNA is extracted；
The detection DNA kind of module connection extracts DNA modules and refers to DNA library module；The extraction DNA modules be by The type classification of DNA with schizophrenia tumor susceptibility gene is good, and then contrast refers to DNA library module, and the DNA of tumor susceptibility gene is sieved Elect；
The DNA species contents module connecting detection DNA kind of module；The DNA species contents module can detect sieve The content for the DNA species elected, then the protein factor content of contrasting detection compared with normal reference value, the classification of science Judge schizophrenia；
The on-line checking module connection DNA species contents module and sealing archive module；Sealing archive module will can be examined The result come is measured to be sealed,
Personal user's login system is installed inside the sealing archive module, after patient is checked, logs in and checks knot Fruit, for protecting the privacy of patient；
On-line checking module carries out the collection of view data using built-in image pickup module, wherein, described image number According to being divided into normal person's group and with two groups of schizophrenic patients group；Disperse view data, institute are obtained using diffusion-weighting sequence again Stating image pickup module includes magnetic resonance equipment；The detection method of line detection module specifically includes：
Step 1, the disperse view data is pre-processed；
Step 1.1, vortex is carried out to the disperse view data with the FSL softwares based on Linux to handle；
Step 1.2, to handling the image drawn using the pulse-couple god for being adapted to processing image information through the step 1.1 Disperse image is detected through network model；Disperse image is passed through adaptive weighted by the less impulsive noise pollution of density Filtering process；By the larger impulsive noise pollution of density using the introducing double structure for keeping edge detail information in disperse image Element mathematical morphology carries out secondary filtering；
It is adapted to the Pulse-coupled Neural Network Model of processing image information：
Fij[n]=Sij；
Uij[n]=Fij[n](1+βij[n]Lij[n])；
Wherein, βij[n] is adaptive link strength factor；
Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, inside Active entry and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
When Pulse-coupled Neural Network Model detects to disperse image, the gray scale is set to be using network characteristicPicture Vegetarian refreshments fire activation, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sij max/1+βijLij,Sij max] between Pixel capture activation, make Y corresponding to the pixel that activates twiceijExport as 1；Then place is highlighted to former image polluted by noise Reason, then to the image S after processingijProcessing is iterated by foregoing, and makes corresponding output Yij=1, utilize picture noise pixel It is small with surrounding pixel correlation, the big characteristic of gray scale difference, when neuron excite do not cause it is most near region When exciting of neuron of number, just illustrates that the neuron respective pixel is probably noise spot；
Tentatively screen out YijPixel corresponding to=0 is the signaling point of disperse image, is protected；To YijExport as 1 Pixel is counted to export Y in the range of 3*3 templates BijNeighborhood element value is 1 number N centered on=1YDifferentiate and sort out：1≤ NY≤8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
Step 1.3, dispersion tensor fitting is carried out to handling the image drawn through the step 1.2, draws anisotropy figure Picture, Mean diffusivity image, radial direction diffusivity image；
Step 1.4, the anisotropy image is registrated to normed space by non-linear registration method；
Step 1.5, all anisotropy images for being registrated to normed space are averagely obtained averagely each to different Property image；
Step 1.6, the average anisotropy image is subjected to skeletonizing；
Step 1.7, by the anisotropy image drawn in step 1.3, Mean diffusivity image, image by individual point Do not project on the white matter skeleton, obtain each individual anisotropy skeleton image, Mean diffusivity skeleton image and footpath To diffusivity skeleton image；
Step 2, multi-variables analysis is carried out to the region of the presence significant difference obtained by step 1：
Step 2.1, respectively to the anisotropy value in the region that significant difference be present, Mean diffusivity value, radial direction Diffusivity value is averaged, and obtains the average anisotropy value in the region that significant difference be present, be averaged Mean diffusivity Value, average radial diffusivity value；
Step 2.2, based on MATLAB softwares by the average anisotropy value described in step 2.1, average Mean diffusivity Value, average radial diffusivity value are input in linear SVM as feature, by leaving-one method to linear SVM It is trained, finally draws the region where feature, so as to obtains the region relevant with lesion.
Further, in the step 2.2, the specific implementation step that is trained by leaving-one method to linear SVM It is as follows：
Step 1, the individual sum in data sample is represented with n, and each individual has a m characteristic quantity, and each individual class Attribute is all known, i.e., with schizophrenic patients or normal person；Obtained data sample is divided into two groups, one group is test Collection, comprising an individual, one group is training set, including except contained external owner in test set, common n-1 individual；
Step 2, the linear SVM is trained with the training set, draws SVMs after training：According to It is a m dimensional vector that weight vector w, w, which is calculated, in lower formula, each corresponding characteristic quantity of element therein；
yi(wTxi+b)-1+ξi≥0
s.t.ξi≥0；
Wherein, γ is punishment parameter, for realizing algorithm complex and the wrong compromise for dividing sample number；ξiMeasurement mistake divides journey Degree；yiFor everyone generic attribute；xiFor each individual characteristic vector；B is constant；
Step 3, the performance of SVMs after the training is assessed with the test set of known generic attribute：With institute SVMs judges the generic attribute of the test set after stating training, and supporting vector chance provides attribute tags after the training 1 or -1, wherein 1 is with schizophrenic patients, -1 is normal person, the judgement knot drawn by SVMs after the training Fruit is compared with the actual generic attribute of the test set, if both are consistent, support vector cassification is correct after the training, no Then, then classification error；
Step 4, is divided into test set and training set by n individual again, and the test set includes an individual, and this Body differs with the individual in the preceding test set once tested, and remaining all individuals are used as training set, then according to step 2 Method train the linear SVM, SVMs after training is drawn, then according still further to the method for the step 3 The performance of SVMs after the training that assessment is drawn；The n-1 rear stopping of repeat step four；
Step 5, n weights of each feature are averaging weights, and according to average weight by the descending progress of feature Sequence, remove the minimum characteristic quantity that sorts；
Step 6, repeat step one to step 4, then performs step 7；
Step 7, according to the classification in n test of the wheel drawn after repeat step one to step 4 in step 6 just True rate and the classification accuracy rate result of the comparison of last round of n test judge whether to stop：If the classification of n test of the wheel is just True rate is more than or equal to the classification accuracy rate of last round of n times test, then returns and perform step 5 to step 6, otherwise stop.
Further,
The implementation method of disperse image adaptive weighting filter noise filtering；
When pulse exports Yij=1 and NY=1~8, NYIt is the selection filter window M when in 3*3 templates B be 1 number, it is right Image polluted by noise fijAdaptive-filtering, filtering equations are：
In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fij To correspond to the output valve of window center position after filtering：
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are exhausted To average, max is maximizing symbol；
Further, choose filter window M and choose the filter window M that size is m*m, the selection principle of window size is：
Further, the specific method of binode constitutive element mathematical morphology second level filtering：
The microimage of Chinese medical herb of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
In formulaAccorded with for dilation operation, F and G are f and E domain respectively, and x-z is displacement parameter；
Above formula extension relationship is all to be merged into all background dots contacted with object in object, border is expanded to outside Process, the hole filled up in object；
Above formula Θ accords with for erosion operation, and corrosion is to eliminate boundary point, and border is internally shunk, while in the base of corrosion expansion On plinth, in conjunction with morphologic opening and closing operation：
Advantages of the present invention and good effect are：A kind of schizophrenia susceptibility gene detection system is by extracting patient DNA, Detection and Extraction come out DNA species, comparing dna storehouse can accurately recognize whether patient suffers from schizophrenia Tumor susceptibility gene, treatment schizophrenia advocate early stage, the development of timely, enough antipsychotics symptom managements, prevent recurrence, Accordingly, it is capable to diagnosis is quickly and accurately made, it is significant for the therapy rehabilitation of patient.
The Image Information Processing technology of the present invention is combined with " modern times " analysis detection for information age medical science " tradition " and carried For brand-new technical thought and method, carry out beneficial exploration for harmless information detection and analysis and establish basis early stage；
Invention provides characteristic using the lock-out pulse of Pulse Coupled Neural Network and distinguishes position pulse noise spot and signal picture Vegetarian refreshments position, it is relatively conventional that higher noise detection performance is had based on value detection method in intermediate value detection or related improvement, Relative to other threshold value noise detection methods；The present invention need not set detection threshold value, and noise fallout ratio and loss are low, noise inspection It is higher to survey precision；Meanwhile relative to other noise iteration detection methods；The inventive method detection time is short, and automaticity is strong；
There is presently no any impulse noise correction method to apply in the detection of disperse image impulse noise；
In the Filtering image impulse noise stage, the present invention is first according to the above-mentioned noise detected and signaling point, to image Pixel carries out classification processing；Processing, phase only are filtered to the noise spot of detection when using first order adaptive weighted filter Signaling point information is protected while noise is effectively filtered out for the methods of other medium filterings, Wiener filtering；In the second level It is to carry out supplement auxiliary to the related noise missed in prime filtering to filter out during mathematical morphology filter, while denoising not only Noise jamming can be effectively filtered out, and the information such as image detail can be protected well.
The present invention carries out preliminary feature extraction as covariant using permutation test and using age factor, overcomes double sample T examines the hypothesis that Normal Distribution is wanted for variable, it is contemplated that influence of the age to white matter；
Permutation test is carried out in voxel level, overcoming the method based on area-of-interest (ROI) needs priori The shortcomings that, while overcome the shortcomings that atlas neutron region can not be observed based on map diversity method；
Postsearch screening is carried out to the feature of primary election using linear SVM, removal is not due to difference caused by lesion And it is due to difference caused by image preprocessing or noise, while consider the phase interaction of multiple different zones difference variables With overcoming t and examine the shortcomings that only considering single variable.
Brief description of the drawings
Fig. 1 is schizophrenia susceptibility gene detection system schematic diagram provided in an embodiment of the present invention.
Fig. 2 is blood collector schematic diagram provided in an embodiment of the present invention.
In figure：1st, blood collector；2nd, anticoagulant tube；3rd, pipe support；4th, cool room；5th, gene extractor；6th, centrifuge tube；7th, inhale Attached column；8th, collecting pipe；9th, gene magnification device；10th, gel electrophoresis device；11st, serum module is extracted；12nd, serum content module is detected； 13rd, protein module is removed；14th, DNA modules are extracted；15th, DNA kind of module is detected；16th, with reference to DNA library module；17th, DNA kinds Class content module；18th, on-line checking module；19th, archive module is sealed.
Embodiment
In order to further understand the content, features and effects of the present invention, hereby enumerating following examples, and coordinate accompanying drawing 1 detailed description is as follows.
The structure of the present invention is explained in detail below in conjunction with the accompanying drawings.
As shown in figure 1, a kind of schizophrenia susceptibility gene assaying device is provided with：Blood collector 1, anticoagulant tube 2, pipe Frame 3, cool room 4, gene extractor 5, centrifuge tube 6, adsorption column 7, collecting pipe 8, gene magnification device 9, gel electrophoresis device 10.It is described Blood collector 1 is connected with the anticoagulant tube 2, and the anticoagulant tube 2 is fixed on the pipe support 3, the anticoagulant tube 2 and the system Cold house 4 is adjacent, and the side of cool room 4 is the gene extractor 5, and the gene extractor 5 is connected with the centrifuge tube 6, The adsorption column 7 and the collecting pipe 8 are both placed on the pipe support 3, the gene magnification device 9 and the gel electrophoresis device 10 It is placed on the side of pipe support 3.
As the presently preferred embodiments, the pipe support 3 is connected in the bottom of this device by the way of bolt fixation.
As the presently preferred embodiments, the bottom of centrifuge tube 6 is connected with centrifugation motor.
It is placed in anticoagulant tube after gathering blood using blood collector, after anticoagulant tube is put into cool room certain time, uses Gene extractor carries out DNA extraction, and the DNA of extraction is put into centrifuge tube carries out centrifugal treating, with adsorption column by after processing DNA moves into collecting pipe, carries out gene magnification device amplification, the electrophoretic separation identification of gel electrophoresis device afterwards.
As shown in Figure 2, the blood collector 1 includes：Extraction serum module 11, detection serum content module 12, go Isolating protein module 13, extraction DNA modules 14, detect DNA kind of module 15, with reference to DNA library module 16, DNA species content moulds Block 17, on-line checking module 18, sealing archive module 19.
The connecting detection serum content module 12 of extraction serum module 1；Extract the mainly extraction separation of serum module 11 Haemocyanin in detect nerve growth factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), TNF (TNF-α), BDNF (BDNF), glial fibrillary acidic albumen (GFAP), 8 kinds of albumen factor contents of myelin basic protein (MBP)；Detect serum content module 12 and mainly extract 8 kinds of protein Factor content.
The detection serum content module 12, which connects, removes protein module 13；Protein module 13 is removed mainly by god Through growth factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), TNF (TNF-α), BDNF (BDNF), glial fibrillary acidic albumen (GFAP), myelin basic protein (MBP) Protein outside 8 kinds of albumen factor contents removes.
The connection of extraction DNA modules 14 removes protein module 13；Extraction DNA modules 14 mainly remove abundant egg White matter, compound not soluble in water is formed using using SDS, protein and K ions, sinking containing protein is removed by centrifuging Form sediment, DNA is extracted.
The connection of the detection DNA kind of module 15 extraction DNA modules 14 and reference DNA library module 16；The extraction DNA moulds Block 14 is that the type classification of the DNA with schizophrenia tumor susceptibility gene is good, and then contrast refers to DNA library module 16, will be susceptible The DNA of gene is screened.
The connecting detection DNA kind of module 15 of DNA species contents module 17；The DNA species contents module 7 can detect To the content of the DNA species screened, then the protein factor content of contrasting detection compares with normal reference value, science Classification judges schizophrenia.
The on-line checking module 18 connects DNA species contents module 17 and sealing archive module 19.Seal archive module 19 can be sealed the result detected, and patient oneself goes and finds out what's going on, and doctor has a responsibility for protecting the privacy of patient, it is impossible to right The situation of outer open patient.
Personal user's login system is installed inside the sealing archive module 19, after patient is checked, logs in and checks As a result, the privacy of patient is sufficiently protected.
The operation principle of the present invention：The serum of patient is extracted by extracting serum module 11, detects serum content module 12 carry out the serum extracted the detection of content, remove protein module 13 and carry out the protein enriched in the serum of extraction Remove, extraction DNA modules 14 are extracted the DNA removed in protein module 13 with the method centrifuged.By reference to The DNA extracted contrast the DNA content of normal value, on-line checking by DNA library module 16 and the module of detection DNA species 15 Module 18 can accurately analyze the DNA content of patient and the DNA content of normal value, and seal data is existed into sealing archive module In, facilitate patient query, not external disclosure, protect the privacy of patient.A kind of schizophrenia susceptibility gene detection system leads to The DNA of extraction patient is crossed, the DNA species that Detection and Extraction come out, comparing dna storehouse, can accurately recognize whether patient suffers from Schizophrenia susceptibility gene, treatment schizophrenia advocate early stage, timely, enough antipsychotics symptom managements hair Exhibition, prevention recurrence, accordingly, it is capable to diagnosis is quickly and accurately made, it is significant for the therapy rehabilitation of patient.
With reference to concrete analysis, the invention will be further described.
The on-line checking module of the present invention carries out the collection of view data using built-in image pickup module, wherein, institute State view data and be divided into normal person's group and with two groups of schizophrenic patients group；Disperse image is obtained using diffusion-weighting sequence again Data, described image acquisition module include magnetic resonance equipment；The detection method of line detection module specifically includes：
Step 1, the disperse view data is pre-processed；
Step 1.1, vortex is carried out to the disperse view data with the FSL softwares based on Linux to handle；
Step 1.2, to handling the image drawn using the pulse-couple god for being adapted to processing image information through the step 1.1 Disperse image is detected through network model；Disperse image is passed through adaptive weighted by the less impulsive noise pollution of density Filtering process；By the larger impulsive noise pollution of density using the introducing double structure for keeping edge detail information in disperse image Element mathematical morphology carries out secondary filtering；
It is adapted to the Pulse-coupled Neural Network Model of processing image information：
Fij[n]=Sij；
Uij[n]=Fij[n](1+βij[n]Lij[n])；
Wherein, βij[n] is adaptive link strength factor；
Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, inside Active entry and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
When Pulse-coupled Neural Network Model detects to disperse image, the gray scale is set to be using network characteristicPicture Vegetarian refreshments fire activation, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sij max/1+βijLij,Sij max] between Pixel capture activation, make Y corresponding to the pixel that activates twiceijExport as 1；Then place is highlighted to former image polluted by noise Reason, then to the image S after processingijProcessing is iterated by foregoing, and makes corresponding output Yij=1, utilize picture noise pixel It is small with surrounding pixel correlation, the big characteristic of gray scale difference, when neuron excite do not cause it is most near region When exciting of neuron of number, just illustrates that the neuron respective pixel is probably noise spot；
Tentatively screen out YijPixel corresponding to=0 is the signaling point of disperse image, is protected；To YijExport as 1 Pixel is counted to export Y in the range of 3*3 templates BijNeighborhood element value is 1 number N centered on=1YDifferentiate and sort out：1≤ NY≤8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
Step 1.3, dispersion tensor fitting is carried out to handling the image drawn through the step 1.2, draws anisotropy figure Picture, Mean diffusivity image, radial direction diffusivity image；
Step 1.4, the anisotropy image is registrated to normed space by non-linear registration method；
Step 1.5, all anisotropy images for being registrated to normed space are averagely obtained averagely each to different Property image；
Step 1.6, the average anisotropy image is subjected to skeletonizing；
Step 1.7, by the anisotropy image drawn in step 1.3, Mean diffusivity image, image by individual point Do not project on the white matter skeleton, obtain each individual anisotropy skeleton image, Mean diffusivity skeleton image and footpath To diffusivity skeleton image；
Step 2, multi-variables analysis is carried out to the region of the presence significant difference obtained by step 1：
Step 2.1, respectively to the anisotropy value in the region that significant difference be present, Mean diffusivity value, radial direction Diffusivity value is averaged, and obtains the average anisotropy value in the region that significant difference be present, be averaged Mean diffusivity Value, average radial diffusivity value；
Step 2.2, based on MATLAB softwares by the average anisotropy value described in step 2.1, average Mean diffusivity Value, average radial diffusivity value are input in linear SVM as feature, by leaving-one method to linear SVM It is trained, finally draws the region where feature, so as to obtains the region relevant with lesion.
In the step 2.2, the specific implementation step being trained by leaving-one method to linear SVM is as follows：
Step 1, the individual sum in data sample is represented with n, and each individual has a m characteristic quantity, and each individual class Attribute is all known, i.e., with schizophrenic patients or normal person；Obtained data sample is divided into two groups, one group is test Collection, comprising an individual, one group is training set, including except contained external owner in test set, common n-1 individual；
Step 2, the linear SVM is trained with the training set, draws SVMs after training：According to It is a m dimensional vector that weight vector w, w, which is calculated, in lower formula, each corresponding characteristic quantity of element therein；
yi(wTxi+b)-1+ξi≥0
s.t.ξi≥0；
Wherein, γ is punishment parameter, for realizing algorithm complex and the wrong compromise for dividing sample number；ξiMeasurement mistake divides journey Degree；yiFor everyone generic attribute；xiFor each individual characteristic vector；B is constant；
Step 3, the performance of SVMs after the training is assessed with the test set of known generic attribute：With institute SVMs judges the generic attribute of the test set after stating training, and supporting vector chance provides attribute tags after the training 1 or -1, wherein 1 is with schizophrenic patients, -1 is normal person, the judgement knot drawn by SVMs after the training Fruit is compared with the actual generic attribute of the test set, if both are consistent, support vector cassification is correct after the training, no Then, then classification error；
Step 4, is divided into test set and training set by n individual again, and the test set includes an individual, and this Body differs with the individual in the preceding test set once tested, and remaining all individuals are used as training set, then according to step 2 Method train the linear SVM, SVMs after training is drawn, then according still further to the method for the step 3 The performance of SVMs after the training that assessment is drawn；The n-1 rear stopping of repeat step four；
Step 5, n weights of each feature are averaging weights, and according to average weight by the descending progress of feature Sequence, remove the minimum characteristic quantity that sorts；
Step 6, repeat step one to step 4, then performs step 7；
Step 7, according to the classification in n test of the wheel drawn after repeat step one to step 4 in step 6 just True rate and the classification accuracy rate result of the comparison of last round of n test judge whether to stop：If the classification of n test of the wheel is just True rate is more than or equal to the classification accuracy rate of last round of n times test, then returns and perform step 5 to step 6, otherwise stop.
The implementation method of disperse image adaptive weighting filter noise filtering；
When pulse exports Yij=1 and NY=1~8, NYIt is the selection filter window M when in 3*3 templates B be 1 number, it is right Image polluted by noise fijAdaptive-filtering, filtering equations are：
In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fij To correspond to the output valve of window center position after filtering：
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are exhausted To average, max is maximizing symbol；
Choose filter window M and choose the filter window M that size is m*m, the selection principle of window size is：
The specific method of binode constitutive element mathematical morphology second level filtering：
The microimage of Chinese medical herb of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
In formulaAccorded with for dilation operation, F and G are f and E domain respectively, and x-z is displacement parameter；
Above formula extension relationship is all to be merged into all background dots contacted with object in object, border is expanded to outside Process, the hole filled up in object；
Above formula Θ accords with for erosion operation, and corrosion is to eliminate boundary point, and border is internally shunk, while in the base of corrosion expansion On plinth, in conjunction with morphologic opening and closing operation：
It is described above to be only the preferred embodiments of the present invention, any formal limitation not is made to the present invention, Every technical spirit according to the present invention belongs to any simple modification made for any of the above embodiments, equivalent variations and modification In the range of technical solution of the present invention.

Claims (5)

  1. A kind of 1. schizophrenia susceptibility gene detection system, it is characterised in that the schizophrenia susceptibility genetic test system System includes：Blood collector, anticoagulant tube, pipe support, cool room, gene extractor, centrifuge tube, adsorption column, collecting pipe, gene magnification Device, gel electrophoresis device；The blood collector is connected with the anticoagulant tube, and the anticoagulant tube is fixed on the pipe support, described Anticoagulant tube is adjacent with the cool room, and the cool room side is the gene extractor, the gene extractor with it is described from Heart pipe is connected, and the adsorption column and the collecting pipe are both placed on the pipe support, the gene magnification device and gel electricity Nestocalyx is placed on the pipe support side；
    The pipe support is connected in the bottom of this device by the way of bolt fixation；
    The centrifugation bottom of the tube is connected with centrifugation motor；
    The blood collector includes：
    Extract serum module, detection serum content module, remove protein module, extraction DNA modules, detection DNA kind of module, With reference to DNA library module, DNA species contents module, on-line checking module, sealing archive module；
    The extraction serum module connecting detection serum content module；It is mainly to extract the haemocyanin of separation to extract serum module Middle detection nerve growth factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), tumour Necrosin (TNF-α), BDNF (BDNF), glial fibrillary acidic albumen (GFAP), alkaline myelin 8 kinds of albumen factor contents of albumen (MBP)；Detect serum content and mainly extract 8 kinds of protein factor contents；
    The detection serum content module connection removes protein module；Protein module is removed mainly by nerve growth factor (NGF), interleukins (IL-6), Calcium-binding protein S100B, interferon (IFN-γ), TNF (TNF-α), brain Derived neurotrophic factor (BDNF), glial fibrillary acidic albumen (GFAP), 8 kinds of albumen of myelin basic protein (MBP) because Protein outside sub- content removes.
    The extraction DNA modules connection removes protein module；Extraction DNA modules mainly remove abundant protein, utilize Compound not soluble in water is formed using SDS, protein and K ions, the precipitation containing protein is removed by centrifuging, DNA is carried Take out；
    The detection DNA kind of module connection extracts DNA modules and refers to DNA library module；The extraction DNA modules are to suffer from The DNA of spiritedness division tumor susceptibility gene type classification is good, and then contrast refers to DNA library module, and the DNA of tumor susceptibility gene is screened Out；
    The DNA species contents module connecting detection DNA kind of module；The DNA species contents module, which can detect, to be filtered out The content for the DNA species come, then the protein factor content of contrasting detection compared with normal reference value, the classification of science judgement Schizophrenia；
    The on-line checking module connection DNA species contents module and sealing archive module；Sealing archive module will can detect The result come is sealed,
    Personal user's login system is installed inside the sealing archive module, after patient is checked, logs in and checks result, is used In the privacy of protection patient；
    On-line checking module carries out the collection of view data using built-in image pickup module, wherein, described image data point For normal person's group and with two groups of schizophrenic patients group；Disperse view data, the figure are obtained using diffusion-weighting sequence again As acquisition module includes magnetic resonance equipment；The detection method of line detection module specifically includes：
    Step 1, the disperse view data is pre-processed；
    Step 1.1, vortex is carried out to the disperse view data with the FSL softwares based on Linux to handle；
    Step 1.2, to handling the image drawn using the pulse coupled neural net for being adapted to processing image information through the step 1.1 Network model detects to disperse image；Disperse image is passed through adaptive weighted filter by the less impulsive noise pollution of density Processing；By the larger impulsive noise pollution of density using the introducing binode constitutive element for keeping edge detail information in disperse image Mathematical morphology carries out secondary filtering；
    It is adapted to the Pulse-coupled Neural Network Model of processing image information：
    Fij[n]=Sij；
    Uij[n]=Fij[n](1+βij[n]Lij[n])；
    Wherein, βij[n] is adaptive link strength factor；
    Sij、Fij[n]、Lij[n]、Uij[n]、θij[n] is respectively received image signal, feed back input, link input, internal activity Item and dynamic threshold, NwFor the sum of all pixels in selected pending window W, Δ is adjustment factor, chooses 1~3；
    When Pulse-coupled Neural Network Model detects to disperse image, gray scale is set to be S using network characteristicijmaxPixel Fire activation, then second of Pulse Coupled Neural Network iterative processing is carried out, between [Sijmax/1+βijLij,Sijmax] between pixel Capture activation, makes Y corresponding to the pixel that activates twiceijExport as 1；Then processing is highlighted to former image polluted by noise, then it is right Image S after processingijProcessing is iterated by foregoing, and makes corresponding output Yij=1, utilize picture noise pixel and surrounding Pixel interdependence is small, the big characteristic of gray scale difference, when exciting for neuron does not cause most of nerves near region When exciting of member, just illustrates that the neuron respective pixel is probably noise spot；
    Tentatively screen out YijPixel corresponding to=0 is the signaling point of disperse image, is protected；To YijExport the pixel for 1 Point is counted to export Y in the range of 3*3 templates BijNeighborhood element value is 1 number N centered on=1YDifferentiate and sort out：1≤NY≤ 8, it is noise spot, works as NY=9, it is determined as image slices vegetarian refreshments；
    Step 1.3, dispersion tensor fitting is carried out to handling the image drawn through the step 1.2, draws anisotropy image, puts down Equal diffusivity image, radial direction diffusivity image；
    Step 1.4, the anisotropy image is registrated to normed space by non-linear registration method；
    Step 1.5, all anisotropy images for being registrated to normed space are averagely obtained into average anisotropy figure Picture；
    Step 1.6, the average anisotropy image is subjected to skeletonizing；
    Step 1.7, the anisotropy image drawn in step 1.3, Mean diffusivity image, image are thrown respectively by individual It is mapped on the white matter skeleton, obtains each individual anisotropy skeleton image, Mean diffusivity skeleton image and radial direction more The rate of dissipating skeleton image；
    Step 2, multi-variables analysis is carried out to the region of the presence significant difference obtained by step 1：
    Step 2.1, respectively to the anisotropy value in the region that significant difference be present, Mean diffusivity value, radial direction disperse Rate value is averaged, and is obtained the average anisotropy value in the region that significant difference be present, average Mean diffusivity value, is put down Radial direction diffusivity value；
    Step 2.2, based on MATLAB softwares by the average anisotropy value described in step 2.1, average Mean diffusivity value, flat Radial direction diffusivity value is input in linear SVM as feature, and linear SVM is instructed by leaving-one method Practice, the region where feature is finally drawn, so as to obtain the region relevant with lesion.
  2. 2. schizophrenia susceptibility gene assaying device as claimed in claim 1, it is characterised in that in the step 2.2, pass through The specific implementation step that leaving-one method is trained to linear SVM is as follows：
    Step 1, the individual sum in data sample is represented with n, and each individual has a m characteristic quantity, and each individual generic attribute All it is known, i.e., with schizophrenic patients or normal person；Obtained data sample is divided into two groups, one group is test set, Comprising an individual, one group is training set, including except contained external owner in test set, common n-1 individual；
    Step 2, the linear SVM is trained with the training set, draws SVMs after training：According to following public affairs It is a m dimensional vector that weight vector w, w, which is calculated, in formula, each corresponding characteristic quantity of element therein；
    yi(wTxi+b)-1+ξi≥0
    s.t.ξi≥0；
    Wherein, γ is punishment parameter, for realizing algorithm complex and the wrong compromise for dividing sample number；ξiMeasurement mistake divides degree；yiFor Everyone generic attribute；xiFor each individual characteristic vector；B is constant；
    Step 3, the performance of SVMs after the training is assessed with the test set of known generic attribute：With the instruction SVMs judges the generic attribute of the test set after white silk, after the training supporting vector chance provide attribute tags 1 or- 1, wherein 1 is that -1 be normal person with schizophrenic patients, the judged result that is drawn by SVMs after the training and The actual generic attribute of the test set compares, if both are consistent, support vector cassification is correct after the training, otherwise, Then classification error；
    Step 4, n individual is divided into test set and training set again, the test set includes an individual, and the individual with Individual in the preceding test set once tested differs, and remaining all individuals are used as training set, then according to the side of step 2 Method trains the linear SVM, draws SVMs after training, is then assessed according still further to the method for the step 3 The performance of SVMs after the training drawn；The n-1 rear stopping of repeat step four；
    Step 5, n weights of each feature are averaging weights, and arranged according to average weight by feature is descending Sequence, remove the minimum characteristic quantity that sorts；
    Step 6, repeat step one to step 4, then performs step 7；
    Step 7, according to the classification accuracy rate in n test of the wheel drawn after repeat step one to step 4 in step 6 Judge whether to stop with the classification accuracy rate result of the comparison of last round of n times test：If the classification accuracy rate of n test of the wheel More than or equal to the classification accuracy rate of last round of n times test, then return and perform step 5 to step 6, otherwise stop.
  3. 3. schizophrenia susceptibility gene assaying device as claimed in claim 1, it is characterised in that
    The implementation method of disperse image adaptive weighting filter noise filtering；
    When pulse exports Yij=1 and NY=1~8, NYIt is 1 number in 3*3 templates B to be, choose filter window M, dirty to noise Contaminate image fijAdaptive-filtering, filtering equations are：
    In formula, xrsIt is the coefficient of respective pixel in filter window, SrsFor the gray value of respective pixel in filter window, fijFor filter The output valve of window center position is corresponded to after ripple：
    D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are definitely equal Value, max is maximizing symbol.
  4. 4. schizophrenia susceptibility gene assaying device as claimed in claim 1, it is characterised in that choose filter window M and choose Size is m*m filter window M, and the selection principle of window size is：
  5. 5. schizophrenia susceptibility gene assaying device as claimed in claim 1, it is characterised in that binode constitutive element Mathematical Morphology Learn the specific method of second level filtering：
    The microimage of Chinese medical herb of residual impulse noise is f, and E is structural element SE, then expansion has following relational expression：
    In formulaAccorded with for dilation operation, F and G are f and E domain respectively, and x-z is displacement parameter；
    Above formula extension relationship is all to be merged into all background dots contacted with object in object, makes border to the mistake of outside expansion Journey, the hole filled up in object；
    Above formulaBeing accorded with for erosion operation, corrosion is to eliminate boundary point, and border is internally shunk, while on the basis of corrosion expands, In conjunction with morphologic opening and closing operation：
CN201711106066.9A 2017-11-10 2017-11-10 A kind of schizophrenia susceptibility gene detection system Pending CN107653185A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711106066.9A CN107653185A (en) 2017-11-10 2017-11-10 A kind of schizophrenia susceptibility gene detection system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711106066.9A CN107653185A (en) 2017-11-10 2017-11-10 A kind of schizophrenia susceptibility gene detection system

Publications (1)

Publication Number Publication Date
CN107653185A true CN107653185A (en) 2018-02-02

Family

ID=61121078

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711106066.9A Pending CN107653185A (en) 2017-11-10 2017-11-10 A kind of schizophrenia susceptibility gene detection system

Country Status (1)

Country Link
CN (1) CN107653185A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110136775A (en) * 2019-05-08 2019-08-16 赵壮志 A kind of cell division and anti-interference detection system and method
CN114219752A (en) * 2021-09-23 2022-03-22 四川大学 Abnormal region detection method for serum protein electrophoresis
CN116800551A (en) * 2023-08-29 2023-09-22 北京金泰康辰生物科技有限公司 Online feedback system for molecular detection

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732500A (en) * 2015-04-10 2015-06-24 天水师范学院 Traditional Chinese medicinal material microscopic image noise filtering system and method adopting pulse coupling neural network

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104732500A (en) * 2015-04-10 2015-06-24 天水师范学院 Traditional Chinese medicinal material microscopic image noise filtering system and method adopting pulse coupling neural network

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110136775A (en) * 2019-05-08 2019-08-16 赵壮志 A kind of cell division and anti-interference detection system and method
CN114219752A (en) * 2021-09-23 2022-03-22 四川大学 Abnormal region detection method for serum protein electrophoresis
CN114219752B (en) * 2021-09-23 2023-07-25 四川大学 Abnormal region detection method for serum protein electrophoresis
CN116800551A (en) * 2023-08-29 2023-09-22 北京金泰康辰生物科技有限公司 Online feedback system for molecular detection
CN116800551B (en) * 2023-08-29 2023-12-22 北京金泰康辰生物科技有限公司 Online feedback system for molecular detection

Similar Documents

Publication Publication Date Title
Greene et al. Multivariate pattern classification of pediatric Tourette syndrome using functional connectivity MRI
Hilton et al. Wavelet denoising of functional MRI data
CN107653185A (en) A kind of schizophrenia susceptibility gene detection system
CN108511055B (en) Ventricular premature beat recognition system and method based on classifier fusion and diagnosis rules
CN108932452A (en) Arrhythmia cordis beat classification method based on multiple dimensioned convolutional neural networks
CN103646183A (en) Intelligent alzheimer disease discriminant analysis method based on artificial neural network and multi-modal MRI (Magnetic Resonance Imaging)
CN109461163A (en) A kind of edge detection extraction algorithm for magnetic resonance standard water mould
CN109509552A (en) A kind of mental disease automatic distinguishing method of the multi-level features fusion based on function connects network
CN104207778B (en) The tranquillization state functional MRI data processing method of Mental health evaluation grader
CN108710822A (en) Personnel falling detection system based on infrared array sensor
CN110321783A (en) A kind of MEG spike detection method and system based on 1D convolutional neural networks
CN103942567A (en) Automatic discrimination analysis method of mild cognitive impairment based on support vector machine
Deng et al. Age-related dedifferentiation and hyperdifferentiation of perceptual and mnemonic representations
Li et al. Altered topological characteristics of morphological brain network relate to language impairment in high genetic risk subjects and schizophrenia patients
Nakamura et al. Comprehensive study of coronavirus disease 2019 (covid-19) classification based on deep convolution neural networks
EP0329356A2 (en) Physiologic waveform analysis
Hsieh et al. Diagnosis of schizophrenia patients based on brain network complexity analysis of resting-state fMRI
CN110507299A (en) Heart rate signal detection device and method
CN111751770A (en) Method for quantitatively measuring exchange speed of water molecules inside and outside blood vessels by means of non-magnetic resonance contrast agent
CN110200624A (en) Based on convolutional neural networks-Recognition with Recurrent Neural Network-support vector machines mixed model disease identification algorithm
CN108596219A (en) A kind of hospital pharmacy drug shortage is automatically reminded to medicine storage cabinet and based reminding method
CN108280832A (en) Medical image analysis method, medical image analysis system and storage medium
Supriyanti et al. Simple Classification of the Alzheimer’s Severity in Supporting Strengthening the Diagnosis of Patients based on ROC Diagram
Sindhu et al. A review of magnetic resonance imaging and its clinical applications
Bampis et al. Segmentation and extraction of the spinal canal in sagittal MR images

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180202