CN109190677A - The control system and control method of inserting needle equipment in single ubarachnoid block art - Google Patents
The control system and control method of inserting needle equipment in single ubarachnoid block art Download PDFInfo
- Publication number
- CN109190677A CN109190677A CN201810890224.2A CN201810890224A CN109190677A CN 109190677 A CN109190677 A CN 109190677A CN 201810890224 A CN201810890224 A CN 201810890224A CN 109190677 A CN109190677 A CN 109190677A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- inserting needle
- value
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000012545 processing Methods 0.000 claims abstract description 29
- 206010002091 Anaesthesia Diseases 0.000 claims abstract description 20
- 230000037005 anaesthesia Effects 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 7
- 210000005036 nerve Anatomy 0.000 claims abstract description 6
- 230000003044 adaptive effect Effects 0.000 claims description 31
- 238000001914 filtration Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 22
- 210000004556 brain Anatomy 0.000 claims description 21
- 210000000576 arachnoid Anatomy 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 11
- 238000001931 thermography Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 241000239290 Araneae Species 0.000 claims description 2
- 238000012804 iterative process Methods 0.000 claims description 2
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 239000000835 fiber Substances 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 229920006395 saturated elastomer Polymers 0.000 claims 1
- 208000032851 Subarachnoid Hemorrhage Diseases 0.000 abstract description 6
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000001949 anaesthesia Methods 0.000 abstract description 2
- 238000000691 measurement method Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 208000032843 Hemorrhage Diseases 0.000 description 7
- 230000000740 bleeding effect Effects 0.000 description 7
- 210000001519 tissue Anatomy 0.000 description 5
- 206010052428 Wound Diseases 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 208000034158 bleeding Diseases 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000008058 pain sensation Effects 0.000 description 2
- 239000006187 pill Substances 0.000 description 2
- 239000002244 precipitate Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000001954 sterilising effect Effects 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 230000036413 temperature sense Effects 0.000 description 2
- 241001484259 Lacuna Species 0.000 description 1
- 230000018199 S phase Effects 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 1
- 210000003703 cisterna magna Anatomy 0.000 description 1
- 210000002808 connective tissue Anatomy 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 210000004055 fourth ventricle Anatomy 0.000 description 1
- 230000002008 hemorrhagic effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003977 optic chiasm Anatomy 0.000 description 1
- 230000004413 optic chiasma Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 210000003446 pia mater Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/03—Recognition of patterns in medical or anatomical images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to field of medical technology, the control system and control method of inserting needle equipment in a kind of single ubarachnoid block art are disclosed, control system includes: image capture module, parameter configuration module, central control module, image data processing module, anesthesia module, locating module, display module.The present invention can be shown the cavum subarachnoidale position for being identified as abnormal signal by image data processing module, it is referred to for medical worker, accurate data is provided for the diagnosis of medical worker, subarachnoid hemorrhage is accurately determined with auxiliary, can reduce mistaken diagnosis/rate of missed diagnosis of subarachnoid hemorrhage;Subarachnoid nerve block anesthesia plane is measured using infrared thermal imagery by anesthesia module simultaneously, change and uses tactile and cold and hot outmoded measurement method in the past, keep measurement means more scientific, more objective, more acurrate, safer, so that patient is performed the operation after being anesthetized safer with anaesthesia process.
Description
Technical field
The invention belongs to a kind of controls of inserting needle equipment in field of medical technology more particularly to single ubarachnoid block art
System and control method processed.
Background technique
Currently, the prior art commonly used in the trade is such that
Arachnoid is to constitute tissue by very thin connective tissue, is one layer of translucent film, and it is deep to be located at endocranium
Portion, having potentiality lacuna therebetween is cavum subdurale.It is intracavitary to contain a small amount of liquid.Arachnoid crosses over brain, is coated on the surface of brain, with
There are biggish gap, referred to as nethike embrane cavity of resorption between pia mater, it is intracavitary to be full of cerebrospinal fluid.At certain position, cavum subarachnoidale extension
And deepen, become cisternae subarachnoideales.Maximum is cisterna magna, it passes through median aperture and front-side holes and fourth ventricle's phase
Logical: bridge pond is located at pons veutro: interpeduncular cistern is recessed between foot;Cistern of chiasma is located in front of optic chiasma.However, existing for amount of bleeding
Smaller and bleeding is difficult to carry out accurate hemorrhagic areas segmentation in the subarachnoid hemorrhage of Dispersed precipitate and bleeding determines;Together
When, the measurement of existing subarachnoid block anesthesia plane is clinically often used needle point method, tactile method and temperature sense and obtains method;
Make patient itself since tolerance difference with reactive different have differences is unable to accurate judgement pain sensation sterilization pill, though needle point method
Block scope and effect can be predicted, but syringe needle used may puncture skin and bring wound or infection to patient.
In conclusion problem of the existing technology is:
Existing smaller for amount of bleeding and bleeding is difficult to carry out accurate bleeding in the subarachnoid hemorrhage of Dispersed precipitate
Region segmentation and bleeding determine;Meanwhile the measurement of existing subarachnoid block anesthesia plane, be clinically often used needle point method,
Tactile method and temperature sense obtain method;Make patient itself since tolerance difference cannot accurately be sentenced with reactive different have differences
Disconnected pain sensation sterilization pill, though needle point method can predict block scope and effect, syringe needle used may puncture skin to patient with
Come wound or infection.
Prior art image information processing accuracy is poor.Classification accuracy is low in conventional images Modulation recognition method asks
Topic.
Summary of the invention
In view of the problems of the existing technology, the present invention provides inserting needle equipment in a kind of single ubarachnoid block art
Control system and control method.
The invention is realized in this way in a kind of single ubarachnoid block art inserting needle equipment control method, it is described
The control method of inserting needle equipment includes: in single ubarachnoid block art
Acquire CT image data information;Configure inserting needle equipment parameters;
CT image is detected with the Pulse-coupled Neural Network Model of suitable processing biological tissue's class image information;CT
Image is handled by the lesser impulsive noise pollution of density by adaptive weighted filter;CT image is by the biggish pulse of density
Noise pollution is using the introducing binode constitutive element mathematical morphology progress secondary filtering for keeping edge detail information;
It is suitble to the Pulse-coupled Neural Network Model of processing biological tissue's class 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 window W to be processed, Δ is adjustment factor, chooses 1~3;
The method of CT image adaptive weighting filter noise filtering;
When pulse exports Yij=1 and NY=1~8, NYIt is to work as in 3*3 template B for 1 number, chooses filter window M, it is right
Image polluted by noise fijAdaptive-filtering, filtering equations are as follows:
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 mean value, max is maximizing symbol;
Identifying processing is carried out to the CT image of acquisition;The original CT signal got is pre-processed, to reduce artefact
Interference;Filter is created, by pretreated CT signal filtering to required frequency range;
Using Phase synchronization analysis method, phase of the CT signal of each frequency range between various time points every two channel is calculated
Position relationship, obtains dynamic function connection matrix;The time domain entropy for calculating phase relation value between two channels one by one, obtains each edge
Comentropy, to measure the complexity of each side time-domain of CT functional network;
Using the dynamic function connection entropy of each frequency range respectively as the characteristic of division of CT functional network, training is adaptive to be improved
Classifier obtains multiple adaptive raising classifiers and corresponding classification accuracy rate;
Classification is combined to sample in the way of voting by trained multiple adaptive raising classifiers;
The creation method of filter are as follows: CT signal is five frequency ranges, i.e. δ (1-10Hz), θ (11- using WAVELET PACKET DECOMPOSITION
20Hz),α(21-35Hz),β(36-55Hz)γ(56-70Hz);
Phase of the CT signal of each frequency range in various time points between every two channel is calculated using PGC demodulation value PLV
Position relationship, specific calculation formula are as follows:
PLV=| < exp (j { Фi(t)-Фj(t)})>|;
Wherein, Фi(t) and Фj(t) be respectively electrode i and j instantaneous phase;
The phase value of signal can be calculated using Hilbert transform, specific formula is as follows:
xi(τ) is the continuous time signal of electrode i, and τ is a time variable, and t indicates time point, and PV is Cauchy's principal value;
Instantaneous phase is calculated as follows:
Similarly, instantaneous phase Ф is calculatedj(t);
If selected CT port number is M, it is T that the CT time, which counts, and different channels pair is constructed using channel two-by-two, calculates institute
There is the PLV value in channel pair, obtain M × M × T three-dimensional matrice K at this time, wherein M × M is the upper triangle at a time point
Matrix:
Each element K of KijtFor the PLV value on t time point between i-th of electrode and j-th of electrode, which is
State function connects matrix, it not only contains the phase relation of the different channels CT between any two, further comprises the space in the channel CT
Information and temporal information;
Anesthetized area is determined using infrared thermal imaging inspection apparatus acquisition arachnoid thermal map;
Inserting needle position is positioned according to the arachnoid thermal image of acquisition;
Show the inserting needle location drawing picture information of acquisition.
Further, it chooses filter window M and chooses the filter window M that size is m*m, the selection principle of window size is:
Further, obtaining the optimal adaptive detailed process for improving classifier includes: to given sample (x1,
y1) ..., (xm, ym), wherein xi∈ X, yi∈ Y=(- 1,1), X are training characteristics, and Y is subject's classification, and initialization first is every
The weight of a training sample set isP iteration, D are carried out later1It (i) is i.e. p=1 each training when initializing
The weight of sample set, iterative process are as follows: variable p is initially increased to P from 1, and each iteration calculates each Weak Classifier h firstp
The error in classification classified to training sample set
Wherein, hp(xi) it is the tag along sort value that p-th of Weak Classifier obtains sample classification, DpIt (i) is pth time iteration
When each training sample set weight, then calculate sorting sequence weightThe each trained sample of final updating
The weight of this collectionWherein, D+1It (i) is each updated each training
The weight of this collection, ZpFor normalization factor,It is the weight in order to adjust sample set, when classification divides right, update
WeightThe weight of sample will reduce;When classification misclassification, weight is updatedSample
This weight will improve;
P Weak Classifier h under the frequency range is obtained after P iterationp, finally most by P Weak Classifier combination building
Whole classifier is optimal adaptive raising classifier:
Then the optimal adaptive classification accuracy rate for improving classifier under each frequency range is calculated separately.
Further, after trained multiple adaptive raising classifiers are combined in the way of voting, sample is divided
Class:
Further, anesthetized area determines that method includes:
Firstly, acquiring infrared signal using infrared thermal imaging inspection apparatus;
Then, to the infrared signal of acquisition, thermal map is formed after being analyzed relatively;
Finally, changing by the light and shade that thermal map is shown, the range of subarachnoid nerve block anesthesia plane is determined.
Inserting needle equipment in the single ubarachnoid block art is realized another object of the present invention is to provide a kind of
The computer program of control method.
Inserting needle equipment in the single ubarachnoid block art is realized another object of the present invention is to provide a kind of
The computer of control method.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the control method of inserting needle equipment in the single ubarachnoid block art.
Another object of the present invention is to provide a kind of control systems of inserting needle equipment in single ubarachnoid block art
Include:
Image capture module is connect with central control module, for acquiring brain CT image data information;
Parameter configuration module is connect with central control module, for configuring inserting needle equipment work in ubarachnoid block art
Make parameter;
Central control module, with image capture module, parameter configuration module, image data processing module, anesthesia module, fixed
Position module, display module connection, work normally for controlling modules;
Image data processing module is connect with central control module, for carrying out identifying processing to the image of acquisition;
Module is anaesthetized, is connect with central control module, for acquiring arachnoid thermal map by infrared thermal imaging inspection apparatus
Determine anesthetized area;
Locating module is connect with central control module, for the image by acquisition to single ubarachnoid block art
Middle inserting needle position is positioned;
Display module is connect with central control module, for the image information by display screen display acquisition.
Further, image data processing module includes region estimation module, characteristic extracting module, abnormal signal identification mould
Block;
Region estimation module carries out cavum subarachnoidale for receiving the brain CT image, and to the brain CT image
The estimation of area-of-interest;
Characteristic extracting module, for receiving the brain CT image after interesting region estimating, and to the area-of-interest
Brain CT image after estimation carries out feature extraction, obtains characteristic value;
Abnormal signal identification module, for receiving the brain CT image after the interesting region estimating and characteristic value, and
Using the method for pattern-recognition, identify whether there is abnormal signal in the area-of-interest according to the characteristic value, and will identification
As a result the display module is sent to.
Advantages of the present invention and good effect are as follows:
The present invention can be shown the cavum subarachnoidale position for being identified as abnormal signal by image data processing module
Out, it is referred to for medical worker, provides accurate data for the diagnosis of medical worker, subarachnoid hemorrhage is carried out with auxiliary
It is accurate to determine, it can reduce mistaken diagnosis/rate of missed diagnosis of subarachnoid hemorrhage;It is measured simultaneously by anesthesia module using infrared thermal imagery
Subarachnoid nerve block anesthesia plane changes in the past with needle thorn, tactile and cold and hot outmoded measurement method, makes measurement means more
It is scientific, more objective, more acurrate, safer, so that patient is performed the operation after being anesthetized safer with anaesthesia process.
The present invention is by improvement Pulse Coupled Neural Network without detecting single automatically in the case where setting detection threshold value
The noise in area's micro-image is anaesthetized in ubarachnoid block art, and the removal of noise is completed using multistage combination filter,
The information such as image edge detailss are protected while effectively filtering out noise jamming well.The present invention has the effect that
It 1) is research of the Image Information Processing technology to Chinese Traditional Medicine progress modern measure identification pretreatment application technology,
It is combined for the information age " tradition " with " modern times " analysis detection and completely new technical thought and method is provided, to modern not damaged letter
Breath, which tests and analyzes, carries out beneficial exploration;
2) in the micro-image impulse noise detection stage, the present invention utilizes the lock-out pulse granting of Pulse Coupled Neural Network
Characteristic distinguishes position pulse noise spot and signal pixels point position, relatively traditional to be examined based on intermediate value detection or related intermediate value of improving
Survey method has higher noise detection performance, relative to other threshold value noise detection methods;The present invention is without setting detection threshold
Value, noise fallout ratio and omission factor are low, and noise measuring precision is higher;Meanwhile relative to other noise iteration detection methods;This hair
Bright method detection time is short, and automaticity is strong;
There is presently no any impulse noise correction methods to apply the micro-image arteries and veins in single ubarachnoid block art
It rushes in the detection of noise;
3) filter out the stage in micro-image impulsive noise, the present invention first according to the above-mentioned noise detected and signaling point,
Classification processing is carried out to image pixel;Place only is filtered to the noise spot of detection when using first order adaptive weighted filter
Reason, protects signaling point information relative to the methods of other median filterings, Wiener filtering while effectively filtering out noise;?
It is to carry out supplement auxiliary to the related noise missed in prime filtering to filter out when second level mathematical morphology filter, while denoising
Noise jamming can be not only effectively filtered out, and the information such as image edge detailss can be protected well;
With stronger subjective vision effect and index is objectively evaluated, noise removal capability is strong, signal-to-noise ratio is high and adaptability is good, special
It is not to anesthesia area's micro-image in the single ubarachnoid block art by serious noise pollution, it is shown that bigger filtering is excellent
More property.
CT image classification method of the invention by using Phase synchronization analysis method, comentropy method, adaptively mention
High (adaboost) sorting algorithm, multi-categorizer ballot combined method, realize and dynamic function connection are described, thus greatly
Width improves classification accuracy.The present invention efficiently solves that traditional images signal data classification method classification accuracy is low to ask
Topic is suitable for CT image signal data and classifies.
Detailed description of the invention
Fig. 1 is the control method flow chart that the present invention implements inserting needle equipment in the single ubarachnoid block art provided.
Fig. 2 is the Control system architecture frame that the present invention implements inserting needle equipment in the single ubarachnoid block art provided
Figure.
In figure: 1, image capture module;2, parameter configuration module;3, central control module;4, image data processing module;
5, module is anaesthetized;6, locating module;7, display module.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to
Limit the present invention.
With reference to the accompanying drawing and specific embodiment is further described application principle of the invention.
As shown in Figure 1, in a kind of single ubarachnoid block art provided by the invention the control system of inserting needle equipment and
Its control method the following steps are included:
S101 acquires brain CT image data information by image capture module;Spider web is configured by parameter configuration module
Hypostegal cavity blocks inserting needle equipment parameters in art;
S102, central control module carry out identifying processing by image of the image data processing module to acquisition;
S103 acquires arachnoid thermal map using infrared thermal imaging inspection apparatus by anesthesia module and determines anesthetized area;
S104 determines inserting needle position in single ubarachnoid block art according to the image of acquisition by locating module
Position;
S105 passes through the image information of display module display acquisition.
As shown in Fig. 2, the control system of inserting needle equipment includes: figure in single ubarachnoid block art provided by the invention
As acquisition module 1, parameter configuration module 2, central control module 3, image data processing module 4, anesthesia module 5, locating module
6, display module 7.
Image capture module 1 is connect with central control module 3, for acquiring brain CT image data information;
Parameter configuration module 2 is connect with central control module 3, for configuring inserting needle equipment in ubarachnoid block art
Running parameter;
Central control module 3, with image capture module 1, parameter configuration module 2, image data processing module 4, anesthesia mould
Block 5, locating module 6, display module 7 connect, and work normally for controlling modules;
Image data processing module 4 is connect with central control module 3, for carrying out identifying processing to the image of acquisition;
Module 5 is anaesthetized, is connect with central control module 3, for acquiring arachnoid heat by infrared thermal imaging inspection apparatus
Scheme to determine anesthetized area;
Locating module 6 is connect with central control module 3, for the image by acquisition to single ubarachnoid block
Inserting needle position is positioned in art;
Display module 7 is connect with central control module 3, for the image information by display screen display acquisition.
Image data processing module 4 provided by the invention includes region estimation module, characteristic extracting module, abnormal signal knowledge
Other module;
Region estimation module carries out cavum subarachnoidale for receiving the brain CT image, and to the brain CT image
The estimation of area-of-interest;
Characteristic extracting module, for receiving the brain CT image after interesting region estimating, and to the area-of-interest
Brain CT image after estimation carries out feature extraction, obtains characteristic value;
Abnormal signal identification module, for receiving the brain CT image after the interesting region estimating and characteristic value, and
Using the method for pattern-recognition, identify whether there is abnormal signal in the area-of-interest according to the characteristic value, and will identification
As a result the display module is sent to.
The anesthetized area of anesthesia module 5 provided by the invention determines that method is as follows:
Firstly, acquiring infrared signal using infrared thermal imaging inspection apparatus;
Then, to the infrared signal of acquisition, thermal map is formed after being analyzed relatively;
Finally, changing by the light and shade that thermal map is shown, the range of subarachnoid nerve block anesthesia plane is determined.
Below with reference to concrete analysis, the invention will be further described.
The control method of inserting needle equipment in single ubarachnoid block art provided in an embodiment of the present invention, comprising:
Acquire CT image data information;Configure inserting needle equipment parameters;
CT image is detected with the Pulse-coupled Neural Network Model of suitable processing biological tissue's class image information;CT
Image is handled by the lesser impulsive noise pollution of density by adaptive weighted filter;CT image is by the biggish pulse of density
Noise pollution is using the introducing binode constitutive element mathematical morphology progress secondary filtering for keeping edge detail information;
It is suitble to the Pulse-coupled Neural Network Model of processing biological tissue's class 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 window W to be processed, Δ is adjustment factor, chooses 1~3;
The method of CT image adaptive weighting filter noise filtering;
When pulse exports Yij=1 and NY=1~8, NYIt is to work as in 3*3 template B for 1 number, chooses filter window M, it is right
Image polluted by noise fijAdaptive-filtering, filtering equations are as follows:
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 mean value, max is maximizing symbol;
Identifying processing is carried out to the CT image of acquisition;The original CT signal got is pre-processed, to reduce artefact
Interference;Filter is created, by pretreated CT signal filtering to required frequency range;
Using Phase synchronization analysis method, phase of the CT signal of each frequency range between various time points every two channel is calculated
Position relationship, obtains dynamic function connection matrix;The time domain entropy for calculating phase relation value between two channels one by one, obtains each edge
Comentropy, to measure the complexity of each side time-domain of CT functional network;
Using the dynamic function connection entropy of each frequency range respectively as the characteristic of division of CT functional network, training is adaptive to be improved
Classifier obtains multiple adaptive raising classifiers and corresponding classification accuracy rate;
Classification is combined to sample in the way of voting by trained multiple adaptive raising classifiers;
The creation method of filter are as follows: CT signal is five frequency ranges, i.e. δ (1-10Hz), θ (11- using WAVELET PACKET DECOMPOSITION
20Hz),α(21-35Hz),β(36-55Hz)γ(56-70Hz);
Phase of the CT signal of each frequency range in various time points between every two channel is calculated using PGC demodulation value PLV
Position relationship, specific calculation formula are as follows:
PLV=| < exp (j { Фi(t)-Фj(t)})>|;
Wherein, Фi(t) and Фj(t) be respectively electrode i and j instantaneous phase;
The phase value of signal can be calculated using Hilbert transform, specific formula is as follows:
xi(τ) is the continuous time signal of electrode i, and τ is a time variable, and t indicates time point, and PV is Cauchy's principal value;
Instantaneous phase is calculated as follows:
Similarly, instantaneous phase Ф is calculatedj(t);
If selected CT port number is M, it is T that the CT time, which counts, and different channels pair is constructed using channel two-by-two, calculates institute
There is the PLV value in channel pair, obtain M × M × T three-dimensional matrice K at this time, wherein M × M is the upper triangle at a time point
Matrix:
Each element K of KijtFor the PLV value on t time point between i-th of electrode and j-th of electrode, which is
State function connects matrix, it not only contains the phase relation of the different channels CT between any two, further comprises the space in the channel CT
Information and temporal information;
Anesthetized area is determined using infrared thermal imaging inspection apparatus acquisition arachnoid thermal map;
Inserting needle position is positioned according to the arachnoid thermal image of acquisition;
Show the inserting needle location drawing picture information of acquisition.
It chooses filter window M and chooses the filter window M that size is m*m, the selection principle of window size is:
Obtaining the optimal adaptive detailed process for improving classifier includes: to given sample (x1, y1) ..., (xm,
ym), wherein xi∈ X, yi∈ Y=(- 1,1), X are training characteristics, and Y is subject's classification, initialize each training sample set first
Weight beP iteration, D are carried out later1(i) be initialization when each training sample set of i.e. p=1 weight, repeatedly
As follows for process: variable p is initially increased to P from 1, and each iteration calculates each Weak Classifier h firstpTraining sample set is carried out
The error in classification that classification obtains
Wherein, hp(xi) it is the tag along sort value that p-th of Weak Classifier obtains sample classification, DpIt (i) is pth time iteration
When each training sample set weight, then calculate sorting sequence weightThe each trained sample of final updating
The weight of this collectionWherein, D+1It (i) is each updated each training
The weight of this collection, ZpFor normalization factor,It is the weight in order to adjust sample set, when classification divides right, update
WeightThe weight of sample will reduce;When classification misclassification, weight is updated
Sample weights will improve;
P Weak Classifier h under the frequency range is obtained after P iterationp, finally most by P Weak Classifier combination building
Whole classifier is optimal adaptive raising classifier:
Then the optimal adaptive classification accuracy rate for improving classifier under each frequency range is calculated separately.
After trained multiple adaptive raising classifiers are combined in the way of voting, classify to sample:
Anesthetized area determines that method includes:
Firstly, acquiring infrared signal using infrared thermal imaging inspection apparatus;
Then, to the infrared signal of acquisition, thermal map is formed after being analyzed relatively;
Finally, changing by the light and shade that thermal map is shown, the range of subarachnoid nerve block anesthesia plane is determined.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (10)
1. the control method of inserting needle equipment in a kind of single ubarachnoid block art, which is characterized in that the single arachnoid
The control method of inserting needle equipment includes: in cavity of resorption retardance art
Acquire CT image data information;Configure inserting needle equipment parameters;
CT image is detected with the Pulse-coupled Neural Network Model of suitable processing biological tissue's class image information;CT image
It is handled by the lesser impulsive noise pollution of density by adaptive weighted filter;CT image is by the biggish impulsive noise of density
Pollution is using the introducing binode constitutive element mathematical morphology progress secondary filtering for keeping edge detail information;
It is suitble to the Pulse-coupled Neural Network Model of processing biological tissue's class image information:
Fij[n]=Sij;
Uij[n]=Fij[n](1+βij[n]Lij[n]);
θij[n]=θ0e-αθ(n-1);
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 window W to be processed, Δ is adjustment factor, chooses 1~3;
The method of CT image adaptive weighting filter noise filtering;
When pulse exports Yij=1 and NY=1~8, NYIt is to work as in 3*3 template B for 1 number, filter window M is chosen, to noise dirt
Contaminate image fijAdaptive-filtering, filtering equations are as follows:
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 wave:
D in formulaijFor pixel grey scale intermediate value in box filter window M, ΩijEach pixel of filter window and center gray scale difference are absolutely equal
Value, max are maximizing symbol;
Identifying processing is carried out to the CT image of acquisition;The original CT signal got is pre-processed, to reduce artifacts;
Filter is created, by pretreated CT signal filtering to required frequency range;
Using Phase synchronization analysis method, calculates phase of the CT signal of each frequency range between various time points every two channel and close
System obtains dynamic function connection matrix;The time domain entropy for calculating phase relation value between two channels one by one, obtains the letter of each edge
Entropy is ceased, to measure the complexity of each side time-domain of CT functional network;
Using the dynamic function connection entropy of each frequency range respectively as the characteristic of division of CT functional network, training is adaptive to improve classification
Device obtains multiple adaptive raising classifiers and corresponding classification accuracy rate;
Classification is combined to sample in the way of voting by trained multiple adaptive raising classifiers;
The creation method of filter are as follows: CT signal using WAVELET PACKET DECOMPOSITION be five frequency ranges, i.e. δ (1-10Hz), θ (11-20Hz),
α(21-35Hz),β(36-55Hz)γ(56-70Hz);
Phase of the CT signal of each frequency range in various time points between every two channel is calculated using PGC demodulation value PLV to close
System, specific calculation formula are as follows:
PLV=| < exp (j { Φi(t)-Φj(t)})>|;
Wherein, Φi(t) and Φj(t) be respectively electrode i and j instantaneous phase;
The phase value of signal can be calculated using Hilbert transform, specific formula is as follows:
xi(τ) is the continuous time signal of electrode i, and τ is a time variable, and t indicates time point, and PV is Cauchy's principal value;
Instantaneous phase is calculated as follows:
Similarly, instantaneous phase Φ is calculatedj(t);
If selected CT port number is M, it is T that the CT time, which counts, and different channels pair is constructed using channel two-by-two, is calculated all logical
The PLV value in road pair obtains M × M × T three-dimensional matrice K at this time, and wherein M × M is the upper triangular matrix at a time point:
Each element K of KijtFor the PLV value on t time point between i-th of electrode and j-th of electrode, which is dynamic function
Energy connection matrix, it not only contains the phase relation of the different channels CT between any two, further comprises the spatial information in the channel CT
And temporal information;
Anesthetized area is determined using infrared thermal imaging inspection apparatus acquisition arachnoid thermal map;
Inserting needle position is positioned according to the arachnoid thermal image of acquisition;
Show the inserting needle location drawing picture information of acquisition.
2. the control method of inserting needle equipment in single ubarachnoid block art as described in claim 1, which is characterized in that
It chooses filter window M and chooses the filter window M that size is m*m, the selection principle of window size is:
3. the control method of inserting needle equipment in single ubarachnoid block art as described in claim 1, which is characterized in that
Obtaining the optimal adaptive detailed process for improving classifier includes: to given sample (x1, y1) ..., (xm, ym), wherein
xi∈ X, yi∈ Y=(- 1,1), X are training characteristics, and Y is subject's classification, and the weight for initializing each training sample set first isP iteration, D are carried out later1(i) be initialization when each training sample set of i.e. p=1 weight, iterative process is such as
Under: variable p is initially increased to P from 1, and each iteration calculates each Weak Classifier h firstpTraining sample set is classified to obtain
Error in classification εp=∑ Dp(i), hp(xi)≠yi,
Wherein, hp(xi) it is the tag along sort value that p-th of Weak Classifier obtains sample classification, Dp(i) every when being pth time iteration
Then the weight of a training sample set calculates sorting sequence weightThe each training sample of final updating
The weight of collectionWherein, D+1It (i) is each updated each training book
The weight of collection, ZpFor normalization factor,It is the weight in order to adjust sample set, when classification point is right, update is weighed
WeightThe weight of sample will reduce;When classification misclassification, weight is updatedSample
This weight will improve;
P Weak Classifier h under the frequency range is obtained after P iterationp, finally by P Weak Classifier combination building final classification
Device is optimal adaptive raising classifier:
Then the optimal adaptive classification accuracy rate for improving classifier under each frequency range is calculated separately.
4. the control method of inserting needle equipment in single ubarachnoid block art as described in claim 1, which is characterized in that
After trained multiple adaptive raising classifiers are combined in the way of voting, classify to sample:
5. the control method of inserting needle equipment in single ubarachnoid block art as described in claim 1, which is characterized in that fiber crops
Liquor-saturated area determination method includes:
Firstly, acquiring infrared signal using infrared thermal imaging inspection apparatus;
Then, to the infrared signal of acquisition, thermal map is formed after being analyzed relatively;
Finally, changing by the light and shade that thermal map is shown, the range of subarachnoid nerve block anesthesia plane is determined.
6. a kind of controlling party for realizing inserting needle equipment in single ubarachnoid block art described in Claims 1 to 5 any one
The computer program of method.
7. a kind of controlling party for realizing inserting needle equipment in single ubarachnoid block art described in Claims 1 to 5 any one
The computer of method.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires the control method of inserting needle equipment in single ubarachnoid block art described in 1-5 any one.
9. a kind of single spider web for realizing the control method of inserting needle equipment in single ubarachnoid block art described in claim 1
Hypostegal cavity blocks the control system of inserting needle equipment in art, which is characterized in that inserting needle is set in the single ubarachnoid block art
Standby control system includes:
Image capture module is connect with central control module, for acquiring brain CT image data information;
Parameter configuration module is connect with central control module, for configuring inserting needle equipment work ginseng in ubarachnoid block art
Number;
Central control module, with image capture module, parameter configuration module, image data processing module, anesthesia module, positioning mould
Block, display module connection, work normally for controlling modules;
Image data processing module is connect with central control module, for carrying out identifying processing to the image of acquisition;
Module is anaesthetized, is connect with central control module, is determined for acquiring arachnoid thermal map by infrared thermal imaging inspection apparatus
Anesthetized area;
Locating module is connect with central control module, for by acquisition image in single ubarachnoid block art into
Pin position is positioned;
Display module is connect with central control module, for the image information by display screen display acquisition.
10. the control system of inserting needle equipment in single ubarachnoid block art as claimed in claim 9, which is characterized in that
Image data processing module includes region estimation module, characteristic extracting module, abnormal signal identification module;
Region estimation module, for receiving the brain CT image, and it is emerging to carry out cavum subarachnoidale sense to the brain CT image
The estimation in interesting region;
Characteristic extracting module, for receiving the brain CT image after interesting region estimating, and to the interesting region estimating
Brain CT image afterwards carries out feature extraction, obtains characteristic value;
Abnormal signal identification module for receiving the brain CT image after the interesting region estimating and characteristic value, and uses
The method of pattern-recognition identifies whether there is abnormal signal in the area-of-interest according to the characteristic value, and by recognition result
Send the display module to.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810890224.2A CN109190677A (en) | 2018-07-30 | 2018-07-30 | The control system and control method of inserting needle equipment in single ubarachnoid block art |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810890224.2A CN109190677A (en) | 2018-07-30 | 2018-07-30 | The control system and control method of inserting needle equipment in single ubarachnoid block art |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109190677A true CN109190677A (en) | 2019-01-11 |
Family
ID=64920854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810890224.2A Pending CN109190677A (en) | 2018-07-30 | 2018-07-30 | The control system and control method of inserting needle equipment in single ubarachnoid block art |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109190677A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006532A (en) * | 2019-04-15 | 2019-07-12 | 高兴莲 | Long-range monitoring temperature patch control system and control method, temperature patch based on Internet of Things |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006122197A (en) * | 2004-10-27 | 2006-05-18 | Toshiba Corp | Ultrasonic diagnostic device, remote control system of ultrasonic diagnostic device and remote control method for ultrasonic diagnostic device |
CN101916443A (en) * | 2010-08-19 | 2010-12-15 | 中国科学院深圳先进技术研究院 | Processing method and system of CT image |
CN102100550A (en) * | 2009-12-21 | 2011-06-22 | 谭建强 | Infrared thermal imaging method for measuring subarachnoid space nerve block anesthesia plane |
WO2012130251A1 (en) * | 2011-03-28 | 2012-10-04 | Al-Romimah Abdalslam Ahmed Abdalgaleel | Image understanding based on fuzzy pulse - coupled neural networks |
CN103750844A (en) * | 2014-01-15 | 2014-04-30 | 杭州电子科技大学 | Identification method based on EEG phase synchronization |
CN103971124A (en) * | 2014-05-04 | 2014-08-06 | 杭州电子科技大学 | Multi-class motor imagery brain electrical signal classification method based on phase synchronization |
CN105046273A (en) * | 2015-07-07 | 2015-11-11 | 南京邮电大学 | Epilepsia electrocorticogram signal classification method based on multiscale sample entropy |
CN107016676A (en) * | 2017-03-13 | 2017-08-04 | 三峡大学 | A kind of retinal vascular images dividing method and system based on PCNN |
US9754190B1 (en) * | 2016-11-29 | 2017-09-05 | Seematics Systems Ltd | System and method for image classification based on Tsallis entropy |
CN108764043A (en) * | 2018-04-26 | 2018-11-06 | 太原理工大学 | The brain electricity sorting technique of entropy based on dynamic function connection |
-
2018
- 2018-07-30 CN CN201810890224.2A patent/CN109190677A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006122197A (en) * | 2004-10-27 | 2006-05-18 | Toshiba Corp | Ultrasonic diagnostic device, remote control system of ultrasonic diagnostic device and remote control method for ultrasonic diagnostic device |
CN102100550A (en) * | 2009-12-21 | 2011-06-22 | 谭建强 | Infrared thermal imaging method for measuring subarachnoid space nerve block anesthesia plane |
CN101916443A (en) * | 2010-08-19 | 2010-12-15 | 中国科学院深圳先进技术研究院 | Processing method and system of CT image |
WO2012130251A1 (en) * | 2011-03-28 | 2012-10-04 | Al-Romimah Abdalslam Ahmed Abdalgaleel | Image understanding based on fuzzy pulse - coupled neural networks |
CN103750844A (en) * | 2014-01-15 | 2014-04-30 | 杭州电子科技大学 | Identification method based on EEG phase synchronization |
CN103971124A (en) * | 2014-05-04 | 2014-08-06 | 杭州电子科技大学 | Multi-class motor imagery brain electrical signal classification method based on phase synchronization |
CN105046273A (en) * | 2015-07-07 | 2015-11-11 | 南京邮电大学 | Epilepsia electrocorticogram signal classification method based on multiscale sample entropy |
US9754190B1 (en) * | 2016-11-29 | 2017-09-05 | Seematics Systems Ltd | System and method for image classification based on Tsallis entropy |
CN107016676A (en) * | 2017-03-13 | 2017-08-04 | 三峡大学 | A kind of retinal vascular images dividing method and system based on PCNN |
CN108764043A (en) * | 2018-04-26 | 2018-11-06 | 太原理工大学 | The brain electricity sorting technique of entropy based on dynamic function connection |
Non-Patent Citations (4)
Title |
---|
PADMA GANASALA等: "Feature-Motivated Simplified Adaptive PCNN-Based Medical Image Fusion Algorithm in NSST Domain", 《BING》 * |
RUO-NAN DUAN等: "Differential Entropy Feature for EEG-based Emotion Classification", 《IEEE》 * |
方永慧: "基于运动想象脑电信号非线性特性分析的脑-机接口研究", 《中国博士学位论文全文数据库(电子期刊)信息科技辑》, vol. 2014, no. 12 * |
赵丹等: "基于NSST和改进PCNN的医学图像融合", 《光电子激光》, vol. 29, no. 01 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110006532A (en) * | 2019-04-15 | 2019-07-12 | 高兴莲 | Long-range monitoring temperature patch control system and control method, temperature patch based on Internet of Things |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Shakeel et al. | Neural network based brain tumor detection using wireless infrared imaging sensor | |
US20220343623A1 (en) | Blood smear full-view intelligent analysis method, and blood cell segmentation model and recognition model construction method | |
CN108549854B (en) | A kind of human face in-vivo detection method | |
CN111488921B (en) | Intelligent analysis system and method for panoramic digital pathological image | |
WO2019104767A1 (en) | Fabric defect detection method based on deep convolutional neural network and visual saliency | |
CN107169998B (en) | A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image | |
WO2018082084A1 (en) | Brain tumor automatic segmentation method by means of fusion of full convolutional neural network and conditional random field | |
US8139831B2 (en) | System and method for unsupervised detection and gleason grading of prostate cancer whole mounts using NIR fluorscence | |
CN102855491B (en) | A kind of central brain functional magnetic resonance image classification Network Based | |
Salem et al. | Segmentation of retinal blood vessels using a novel clustering algorithm (RACAL) with a partial supervision strategy | |
Kolář et al. | Detection of glaucomatous eye via color fundus images using fractal dimensions | |
CN102509123B (en) | Brain function magnetic resonance image classification method based on complex network | |
CN109712111A (en) | A kind of cutaneum carcinoma category identification method, system, computer equipment and storage medium | |
CN104751186B (en) | A kind of iris image quality sorting technique based on BP networks and wavelet transformation | |
CN111507426B (en) | Non-reference image quality grading evaluation method and device based on visual fusion characteristics | |
CN108596087B (en) | Driving fatigue degree detection regression model based on double-network result | |
CN107516312A (en) | A kind of Chinese medicine complexion automatic classification method using shallow-layer neutral net | |
CN106875391A (en) | The recognition methods of skin image and electronic equipment | |
CN102982542A (en) | Fundus image vascular segmentation method based on phase congruency | |
CN113261012B (en) | Method, device and system for processing image | |
Zhou et al. | Automatic optic disc detection using low-rank representation based semi-supervised extreme learning machine | |
CN114241511A (en) | Weak supervision pedestrian detection method, system, medium, equipment and processing terminal | |
Vimal et al. | RETRACTED ARTICLE: A method of progression detection for glaucoma using K-means and the GLCM algorithm toward smart medical prediction | |
CN110348326A (en) | The family health care information processing method of the identification of identity-based card and the access of more equipment | |
CN113657449A (en) | Traditional Chinese medicine tongue picture greasy classification method containing noise labeling data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190111 |