CN113724208B - Blood flow spectrum signal classification method and system - Google Patents
Blood flow spectrum signal classification method and system Download PDFInfo
- Publication number
- CN113724208B CN113724208B CN202110928460.0A CN202110928460A CN113724208B CN 113724208 B CN113724208 B CN 113724208B CN 202110928460 A CN202110928460 A CN 202110928460A CN 113724208 B CN113724208 B CN 113724208B
- Authority
- CN
- China
- Prior art keywords
- blood flow
- spectrum
- transfer function
- image
- change curve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 111
- 230000017531 blood circulation Effects 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000012546 transfer Methods 0.000 claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 49
- 230000008859 change Effects 0.000 claims abstract description 36
- 230000008321 arterial blood flow Effects 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000005540 biological transmission Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000010276 construction Methods 0.000 claims abstract description 4
- 210000002302 brachial artery Anatomy 0.000 claims description 35
- 238000011049 filling Methods 0.000 claims description 16
- 238000003708 edge detection Methods 0.000 claims description 12
- 210000004204 blood vessel Anatomy 0.000 claims description 11
- 210000001715 carotid artery Anatomy 0.000 claims description 9
- 238000002604 ultrasonography Methods 0.000 claims description 6
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 238000001595 flow curve Methods 0.000 description 4
- 210000001168 carotid artery common Anatomy 0.000 description 3
- 208000029078 coronary artery disease Diseases 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 230000004087 circulation Effects 0.000 description 1
- 230000001427 coherent effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
Images
Classifications
-
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/06—Measuring blood flow
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/10132—Ultrasound image
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Hematology (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses a blood flow spectrum signal classification method and a system, wherein the method comprises the following steps: s1, collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve; s2, establishing an ARX transfer function of a blood flow velocity spectrum according to an arterial blood flow spectrum change curve; s3, performing fitting analysis on an ARX transfer function of a blood flow velocity spectrum to obtain transfer function characteristics; s4, processing the transmission function features by adopting an SVM classifier to finish blood flow spectrum signal classification. The system comprises: the device comprises a frequency spectrum curve extraction module, a transfer function construction module, a characteristic calculation module and a classification module. By using the invention, accurate classification of signals is realized. The blood flow spectrum signal classification method and system can be widely applied to the field of signal classification.
Description
Technical Field
The invention relates to the field of signal classification, in particular to a blood flow spectrum signal classification method and system.
Background
Ultrasound technology is widely used for medical imaging and measurement. The external counterpulsation is one of the noninvasive biofeedback technologies for effectively regulating and controlling the heart brain circulation hemodynamic environment, namely the blood flow perfusion of important organs, and has great development potential in the field of cardiovascular and cerebrovascular disease rehabilitation, and the diagnosis of doctors can be assisted by classifying the change signals of the peripheral ultrasonic blood flow frequency spectrum in the external counterpulsation process, but the data under the current dynamic continuous monitoring has the problems of strong noise, low robustness and the like.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a blood flow spectrum signal classification method and a system, which are used for processing dynamically monitored signals so as to accurately classify the signals.
The first technical scheme adopted by the invention is as follows: a method of classifying a blood flow spectrum signal, comprising the steps of:
s1, collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve;
s2, establishing an ARX transfer function of a blood flow velocity spectrum according to an arterial blood flow spectrum change curve;
s3, performing fitting analysis on an ARX transfer function of a blood flow velocity spectrum to obtain transfer function characteristics;
s4, processing the transmission function features by adopting an SVM classifier to finish blood flow spectrum signal classification.
Further, the step of collecting the arterial vessel ultrasonic image and extracting the arterial blood flow spectrum change curve specifically comprises the following steps:
s11, collecting carotid artery blood vessel ultrasonic images and brachial artery blood vessel ultrasonic images;
s12, performing interference factor elimination processing, binarization processing, cavity filling processing and Sobel operator edge detection processing on the carotid blood vessel ultrasonic image to obtain a first Sobel gradient image;
s13, extracting the first Sobel gradient image to obtain a carotid blood flow spectrum change curve;
s14, performing interested region selection, binarization processing, cavity filling processing and Sobel operator edge detection processing on the brachial artery vessel ultrasonic image to obtain a second Sobel gradient image;
s15, identifying the 0-axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain a brachial artery blood flow spectrum change curve.
Further, the step of performing interference factor rejection processing, binarization processing, cavity filling processing and Sobel operator edge detection processing on the carotid blood vessel ultrasound image to obtain a first Sobel gradient image specifically includes:
s121, setting a pixel value of an interference factor in the carotid blood vessel ultrasonic image as background black to obtain a carotid blood flow spectrum image after interference factors are removed;
s122, converting the carotid blood flow spectrum image with interference factors removed into a binary image;
s123, performing hole filling processing on the binary image by adopting closed operation to obtain a filled image;
s124, respectively calculating gradients of the filled images in the horizontal direction and the vertical direction by adopting a Sobel operator, and synthesizing to obtain a first Sobel gradient image.
Further, the step of identifying the 0 axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain the brachial artery blood flow spectrum change curve specifically includes:
s151, globally searching pixel points with pixel values of 1 in the region of interest in the second Sobel gradient image to obtain a position set of white pixel values;
s152, determining the position of the 0 axis in the region of interest according to the four highest ordinate values in the position set;
s153, setting K as 1, and extracting an upper envelope from top to bottom until a pixel point in a 0-axis range is identified;
s154, setting K as-1, and extracting a lower envelope from bottom to top until a pixel point in a 0-axis range is identified;
s155, returning to the step S153 until all pixel points in the region of interest are identified, and obtaining a brachial artery blood flow spectrum change curve.
Further, the ARX transfer function of the blood flow velocity spectrum is specifically a 12-order ARX model, and the step of fitting and analyzing the ARX transfer function of the blood flow velocity spectrum to obtain transfer function features specifically includes:
and carrying out fitting analysis on an ARX transfer function of the blood flow velocity spectrum based on a least square method, and extracting and obtaining coefficient characteristics, zero abscissa characteristics and pole abscissa characteristics of the transfer function.
Further, the step of processing the transmission function features by using an SVM classifier to complete classification of the blood flow spectrum signals specifically includes:
selecting transfer function features based on LASSO regression algorithm to obtain selected pole abscissa features;
classifying according to the selected zero-pole abscissa and ordinate features based on the SVM classifier to obtain a classification result;
and reflecting the corresponding blood flow spectrum signal classification according to the classification result.
The second technical scheme adopted by the invention is as follows: a blood flow spectral signal classification system, comprising:
the frequency spectrum curve extraction module is used for collecting an arterial blood vessel ultrasonic image and extracting an arterial blood flow frequency spectrum change curve;
the transfer function construction module is used for establishing an ARX transfer function of the blood flow velocity spectrum according to the arterial blood flow spectrum change curve;
the feature calculation module is used for carrying out fitting analysis based on an ARX transfer function of the blood flow velocity spectrum to obtain transfer function features;
and the classification module is used for processing the transmission function characteristics by adopting an SVM classifier to finish blood flow spectrum signal classification.
The method and the system have the beneficial effects that: according to the invention, the blood vessel ultrasonic image is preprocessed to extract an accurate blood flow spectrum curve, an ARX model is constructed to calculate parameter characteristics, and finally, the blood flow spectrum signals are classified by classifying the parameter characteristics, so that the classified signals can be used for assisting a doctor in diagnosis.
Drawings
FIG. 1 is a flow chart of steps of a blood flow spectrum signal classification method according to the present invention;
fig. 2 is a block diagram of a blood flow spectrum signal classification system according to the present invention.
Detailed Description
The invention will now be described in further detail with reference to the drawings and to specific examples. The step numbers in the following embodiments are set for convenience of illustration only, and the order between the steps is not limited in any way, and the execution order of the steps in the embodiments may be adaptively adjusted according to the understanding of those skilled in the art.
Referring to fig. 1, the present invention provides a blood flow spectrum signal classification method, which includes the steps of:
s1, collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve;
s2, establishing an ARX transfer function of a blood flow velocity spectrum according to an arterial blood flow spectrum change curve;
s3, performing fitting analysis on an ARX transfer function of a blood flow velocity spectrum to obtain transfer function characteristics;
s4, processing the transmission function features by adopting an SVM classifier to finish blood flow spectrum signal classification.
Further as a preferred embodiment of the method, the step of acquiring an arterial vessel ultrasound image and extracting an arterial blood flow spectrum change curve specifically includes:
s11, collecting carotid artery blood vessel ultrasonic images and brachial artery blood vessel ultrasonic images;
specifically, an external counterpulsation (EECP) anterior-middle-posterior cervical total brachial artery vessel ultrasound image is acquired, and blood flow spectrum raw data in DICOM format is derived.
S12, performing interference factor elimination processing, binarization processing, cavity filling processing and Sobel operator edge detection processing on the carotid blood vessel ultrasonic image to obtain a first Sobel gradient image;
s13, extracting the first Sobel gradient image to obtain a carotid blood flow spectrum change curve;
s14, performing interested region selection, binarization processing, cavity filling processing and Sobel operator edge detection processing on the brachial artery vessel ultrasonic image to obtain a second Sobel gradient image;
s15, identifying the 0-axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain a brachial artery blood flow spectrum change curve.
Specifically, the blood flow velocity change modes of the brachial artery and the common carotid artery are different, and the peripheral brachial artery blood vessel mainly takes three-way blood flow.
Further as a preferred embodiment of the method, the step of performing interference factor rejection processing, binarization processing, hole filling processing and Sobel operator edge detection processing on the carotid blood vessel ultrasound image to obtain a first Sobel gradient image specifically includes:
the carotid blood flow signal is relatively stable and there is no reverse blood flow in the normal state. The blood flow velocity spectrum curve is distributed above the 0 axis, and the repeatability is good without the treatment of filtering and the like.
S121, setting a pixel value of an interference factor in the carotid blood vessel ultrasonic image as background black to obtain a carotid blood flow spectrum image after interference factors are removed;
specifically, because of the reasons of equipment, the collected ultrasonic image blood flow spectrum curves are provided with yellow star marks and period selection lines which are self-contained by the equipment, and a few images are provided with yellow lightning marks; these interference factors become abrupt points on the outer envelope line, and cause great interference to maximum speed spectrum curve extraction, thereby affecting data quality. According to the scheme, the yellow pixel point is set to be black in background according to the pixel value (254,254,0) of the yellow pixel point, so that the interference of the yellow star mark and the selected line is eliminated without influencing the threshold value of the subsequent binarization processing.
S122, converting the carotid blood flow spectrum image with interference factors removed into a binary image;
specifically, in order to solve the problems that the green outer envelope line on the yellow star mark is discontinuous and key characteristic points are lacking in the figure, the common carotid artery blood flow spectrum image after interference factors are removed is converted into a binary image, so that only black and white pixel points exist. Therefore, the missing key feature points can be replaced by the white pixel points below, so that the time for finding the points by using the manual difference value is saved, and the error is obviously reduced.
S123, performing hole filling processing on the binary image by adopting closed operation to obtain a filled image;
specifically, the edges of the blood flow spectrum image are coherent and full after the closed operation setting, so that preparation is made for extracting the outer edges in the next step. By the closed operation, a large number of images can be effectively extracted to the outer edge.
S124, respectively calculating gradients of the filled images in the horizontal direction and the vertical direction by adopting a Sobel operator, and synthesizing to obtain a first Sobel gradient image.
Specifically, the Sobel operator calculates the difference between the pixel points and surrounding pixel points according to the gradient of each pixel point of the image, finally separates the target and the background, extracts the outer edge area, comprises two groups of 3x3 matrixes which are respectively in the transverse direction and the longitudinal direction, and performs plane convolution on the matrixes and the image to respectively obtain the brightness difference approximate values in the two directions.
In the above formula, A represents an original image, G x G (G) y Representing the gray values of the image detected by the lateral and longitudinal edges, respectively
The lateral and longitudinal gray values of each pixel of the image are combined by equation (2) to calculate the magnitude of the dot gray:
if the gradient G is greater than a certain threshold, then the point (x, y) is considered to be an edge point; the gradient direction can then be calculated using equation (3):
the Sobel operator is a relatively common and effective edge detection method, and detects edges when the edges reach extreme values according to the gray weighting differences of the upper, lower, left and right adjacent points of the pixels, calculates the difference between the pixels and surrounding pixels according to the gradient of each pixel of the image, finally separates a target from a background, extracts an outer edge, and obtains an accurate brachial artery blood flow maximum speed curve.
Further as a preferred embodiment of the method, the step of identifying the 0 axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain the brachial artery blood flow spectrum change curve specifically includes:
the blood flow velocity spectrum of the brachial artery is mostly three-way blood flow in the acquisition process, namely, a blood flow spectrum curve passes through the 0 axis, and the blood flow of the brachial artery is unstable before, during and after EECP therapy, and the scale is changeable. Since the brachial artery blood flow curve passes through the 0 axis, this portion of the maximum blood flow velocity curve should consist of an upper envelope above the 0 axis together with a lower envelope below the 0 axis. The maximum blood flow velocity curve extracted from the brachial artery should also include a coincidence line between the period and the 0 axis, so that the identification of the 0 axis position in the brachial artery blood flow curve is particularly important. However, the scale of the blood flow curve is changeable, the distribution position of the blood flow spectrum curve in the image is not fixed, and the 0-axis determination becomes a key problem of extracting the blood flow curve from the brachial artery blood vessel.
S151, globally searching pixel points with pixel values of 1 in the region of interest in the second Sobel gradient image to obtain a position set of white pixel values;
specifically, for the brachial artery outer envelope extraction algorithm, a movable selection frame is mainly set in the study. The selection box may drag the position to select a region of interest (ROI). However, because of the difference in blood flow direction, the extraction algorithm for extracting the brachial artery maximum velocity curve needs to identify the 0-axis position first. Since the 0-axis is not a single straight line in the image, but a wide area having a certain width on the ordinate. Therefore, when searching for the 0-axis position, the ordinate range of the position needs to be acquired, and the position is obtained through a large amount of image observation, wherein the 0-axis comprises the height of four pixel points. In the algorithm for identifying the 0 axis, a pixel point with a pixel value of 1 is searched globally in the ROI, namely, all white pixel values are searched in a binary image of the Sobel edge, the position in which the white pixel values are concentrated is judged, and the four highest ordinate values in the set are obtained. The resulting four ordinate are the relative positions of the 0 axis within the ROI.
S152, determining the position of the 0 axis in the region of interest according to the four highest ordinate values in the position set;
s153, setting K as 1, and extracting an upper envelope from top to bottom until a pixel point in a 0-axis range is identified;
s154, setting K as-1, and extracting a lower envelope from bottom to top until a pixel point in a 0-axis range is identified;
s155, returning to the step S153 until all pixel points in the region of interest are identified, and obtaining a brachial artery blood flow spectrum change curve.
Specifically, after the 0-axis position is determined, the upper and lower envelopes need to be extracted and spliced in the Sobel gradient line respectively. In order to accurately extract the upper and lower outer envelopes, the specific implementation of this part of envelope extraction algorithm is as follows. First, lock is set to 1, when k=1, the upper envelope is extracted from top to bottom, unlock is performed if a pixel point of 0 axis range is identified when the envelope is extracted, and K is set to-1. The lower envelope is extracted from bottom to top when k= -1, and K is set to-K again when a pixel point of the 0-axis range is identified. The identification, inversion, extraction and seamless splicing of the upper envelope and the lower envelope are completed. The self-adaptive recognition extraction algorithm of different blood flow directions is realized, and an accurate brachial artery blood flow maximum speed curve is obtained.
Further as a preferred embodiment of the method, the ARX transfer function of the blood flow velocity spectrum is specifically a 12 th order ARX model, and the step of performing fitting analysis on the ARX transfer function of the blood flow velocity spectrum to obtain a transfer function feature specifically includes:
and carrying out fitting analysis on an ARX transfer function of the blood flow velocity spectrum based on a least square method, and extracting and obtaining coefficient characteristics, zero abscissa characteristics and pole abscissa characteristics of the transfer function.
According to the data quality screening, 50 groups of coronary heart diseases (CAD) are established based on the blood flow spectrum curves, and 50 groups of system transfer function data, namely blood flow velocity transfer functions from the common carotid artery to the brachial artery before and after EECP intervention, are compared; the order is finally chosen to be 12 according to the FPE precision judgment. The 12-order ARX model is based on extracting the characteristics of the coefficient of the transfer function, the abscissa of zero poles and the like, 73 characteristics are obtained in total, and 219 characteristics are obtained in three excitation states before, during and after EECP.
The ARX model can be expressed in the form of a linear regression equation, so that the parameters of the ARX model can be calculated through a least square method, and compared with other models, the ARX model is simple and convenient to calculate and widely applied; ARX is expressed as a differential equation:
where u is the system input, y is the system output, e is white noise, and is the system residual. This system can also be expressed as:
A(q)y(t)＝B(q)u(t)+e(t)
where q is the transfer operator and where,
the output y (t) of the system can be expressed as:
calculation of ARX model parameters is obtained from the above equation, estimation of output
Can be expressed as:
data vector now introduced into model
Sum parameter vector
The output quantity estimation value can be expressed as the following linear regression form
Solving by adopting a least square method to minimize the error of the system; the loss function, i.e. the 2-norm of the system residual e, is introduced here as an evaluation criterion for the system error:
wherein e can be expressed as
Thus, the parameters of the system can be calculated by the following formula
The QR decomposition is adopted to solve the above formula to obtain:
the above equation is called least squares estimation.
Further as a preferred embodiment of the method, the step of processing the transmission function features by using an SVM classifier to classify the blood flow spectrum signal specifically includes:
selecting transfer function features based on LASSO regression algorithm to obtain selected pole abscissa features;
classifying according to the selected zero-pole abscissa and ordinate features based on the SVM classifier to obtain a classification result;
and reflecting the corresponding blood flow spectrum signal classification according to the classification result.
And establishing a transfer function from the carotid artery to the peripheral brachial artery according to the obtained frequency spectrum curve of the blood velocity of the carotid artery. And (3) adopting an ARX model to carry out fitting analysis, wherein the fitting degree of blood flow spectrum curves before, during and after EECP is more than 80% at 12 th order. The transfer function features calculated in the model are used for classification. The response of the transfer function features under EECP excitation is different to distinguish CAD from control groups, and is used for assisting diagnosis of diseases.
As shown in fig. 2, a blood flow spectrum signal classification system includes:
the frequency spectrum curve extraction module is used for collecting an arterial blood vessel ultrasonic image and extracting an arterial blood flow frequency spectrum change curve;
the transfer function construction module is used for establishing an ARX transfer function of the blood flow velocity spectrum according to the arterial blood flow spectrum change curve;
the feature calculation module is used for carrying out fitting analysis based on an ARX transfer function of the blood flow velocity spectrum to obtain transfer function features;
and the classification module is used for processing the transmission function characteristics by adopting an SVM classifier to finish blood flow spectrum signal classification.
The content in the method embodiment is applicable to the system embodiment, the functions specifically realized by the system embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.
While the preferred embodiment of the present invention has been described in detail, the invention is not limited to the embodiment, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the invention, and these modifications and substitutions are intended to be included in the scope of the present invention as defined in the appended claims.
Claims (5)
1. A method for classifying a blood flow spectrum signal, comprising the steps of:
s1, collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve;
the step of collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve comprises the following steps of;
s11, collecting carotid artery blood vessel ultrasonic images and brachial artery blood vessel ultrasonic images;
s12, carrying out interference factor elimination treatment, binarization treatment, cavity filling treatment and cavity filling treatment on carotid artery blood vessel ultrasonic images
Performing edge detection processing on a Sobel operator to obtain a first Sobel gradient image;
s13, extracting the first Sobel gradient image to obtain a carotid blood flow spectrum change curve;
s14, performing interested region selection, binarization processing, cavity filling processing and Sobel operator edge detection processing on the brachial artery vessel ultrasonic image to obtain a second Sobel gradient image;
s15, identifying the 0-axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain a brachial artery blood flow spectrum change curve;
the step of identifying the 0-axis position in the second Sobel gradient image, locking the K value to search the upper envelope and the lower envelope, and obtaining a brachial artery blood flow spectrum change curve, which specifically comprises the steps of;
s151, globally searching pixel points with pixel values of 1 in the region of interest in the second Sobel gradient image to obtain a position set of white pixel values;
s152, determining the position of the 0 axis in the region of interest according to the four highest ordinate values in the position set;
s153, setting K as 1, and extracting an upper envelope from top to bottom until a pixel point in a 0-axis range is identified;
s154, setting K as-1, and extracting a lower envelope from bottom to top until a pixel point in a 0-axis range is identified;
s155, returning to the step S153 until all pixel points in the region of interest are identified, and obtaining a brachial artery blood flow frequency spectrum change curve;
s2, establishing an ARX transfer function of a blood flow velocity spectrum according to an arterial blood flow spectrum change curve;
s3, performing fitting analysis on an ARX transfer function of a blood flow velocity spectrum to obtain transfer function characteristics;
s4, processing the transmission function features by adopting an SVM classifier to finish blood flow spectrum signal classification.
2. The method for classifying blood flow spectrum signals according to claim 1, wherein the step of performing interference factor rejection processing, binarization processing, hole filling processing and Sobel operator edge detection processing on the carotid artery blood vessel ultrasound image to obtain a first Sobel gradient image specifically comprises:
s121, setting a pixel value of an interference factor in the carotid blood vessel ultrasonic image as background black to obtain a carotid blood flow spectrum image after interference factors are removed;
s122, converting the carotid blood flow spectrum image with interference factors removed into a binary image;
s123, performing hole filling processing on the binary image by adopting closed operation to obtain a filled image;
s124, respectively calculating gradients of the filled images in the horizontal direction and the vertical direction by adopting a Sobel operator, and synthesizing to obtain a first Sobel gradient image.
3. The method for classifying a blood flow spectrum signal according to claim 2, wherein the ARX transfer function of the blood flow velocity spectrum is specifically a 12 th order ARX model, and the step of fitting and analyzing the ARX transfer function of the blood flow velocity spectrum to obtain a transfer function feature is specifically as follows:
and carrying out fitting analysis on an ARX transfer function of the blood flow velocity spectrum based on a least square method, and extracting and obtaining coefficient characteristics, zero abscissa characteristics and pole abscissa characteristics of the transfer function.
4. A method for classifying a blood flow spectrum signal according to claim 3, wherein the step of processing the transfer function features by an SVM classifier to classify the blood flow spectrum signal comprises:
selecting transfer function features based on LASSO regression algorithm to obtain selected pole abscissa features;
classifying according to the selected zero-pole abscissa and ordinate features based on the SVM classifier to obtain a classification result;
and reflecting the corresponding blood flow spectrum signal classification according to the classification result.
5. A system for classifying a blood flow spectrum signal, comprising:
the frequency spectrum curve extraction module is used for collecting an arterial blood vessel ultrasonic image and extracting an arterial blood flow frequency spectrum change curve;
the step of collecting an arterial vessel ultrasonic image and extracting an arterial blood flow spectrum change curve comprises the following steps of;
s11, collecting carotid artery blood vessel ultrasonic images and brachial artery blood vessel ultrasonic images;
s12, carrying out interference factor elimination treatment, binarization treatment, cavity filling treatment and cavity filling treatment on carotid artery blood vessel ultrasonic images
Performing edge detection processing on a Sobel operator to obtain a first Sobel gradient image;
s13, extracting the first Sobel gradient image to obtain a carotid blood flow spectrum change curve;
s14, performing interested region selection, binarization processing, cavity filling processing and Sobel operator edge detection processing on the brachial artery vessel ultrasonic image to obtain a second Sobel gradient image;
s15, identifying the 0-axis position in the second Sobel gradient image, and locking the K value to search the upper envelope and the lower envelope to obtain a brachial artery blood flow spectrum change curve;
the step of identifying the 0-axis position in the second Sobel gradient image, locking the K value to search the upper envelope and the lower envelope, and obtaining a brachial artery blood flow spectrum change curve, which specifically comprises the steps of;
s151, globally searching pixel points with pixel values of 1 in the region of interest in the second Sobel gradient image to obtain a position set of white pixel values;
s152, determining the position of the 0 axis in the region of interest according to the four highest ordinate values in the position set;
s153, setting K as 1, and extracting an upper envelope from top to bottom until a pixel point in a 0-axis range is identified;
s154, setting K as-1, and extracting a lower envelope from bottom to top until a pixel point in a 0-axis range is identified;
s155, returning to the step S153 until all pixel points in the region of interest are identified, and obtaining a brachial artery blood flow frequency spectrum change curve;
the transfer function construction module is used for establishing an ARX transfer function of the blood flow velocity spectrum according to the arterial blood flow spectrum change curve;
the feature calculation module is used for carrying out fitting analysis based on an ARX transfer function of the blood flow velocity spectrum to obtain transfer function features;
and the classification module is used for processing the transmission function characteristics by adopting an SVM classifier to finish blood flow spectrum signal classification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110928460.0A CN113724208B (en) | 2021-08-13 | 2021-08-13 | Blood flow spectrum signal classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110928460.0A CN113724208B (en) | 2021-08-13 | 2021-08-13 | Blood flow spectrum signal classification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724208A CN113724208A (en) | 2021-11-30 |
| CN113724208B true CN113724208B (en) | 2023-06-06 |
Family
ID=78675731
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110928460.0A Active CN113724208B (en) | 2021-08-13 | 2021-08-13 | Blood flow spectrum signal classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724208B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664414B (en) * | 2022-03-28 | 2024-04-26 | 中国人民解放军总医院第三医学中心 | Method and device for generating blood flow spectrum envelope curve and readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049766A (en) * | 2012-12-27 | 2013-04-17 | 中国科学院遥感应用研究所 | Ultrasonic image renal artery blood flow spectrum signal curve classification method |
| CN104095656A (en) * | 2014-07-25 | 2014-10-15 | 声泰特（成都）科技有限公司 | Colorful blood flow imaging based on ultrasonic Doppler frequency spectrum and display method thereof |
| CN104182984A (en) * | 2014-09-01 | 2014-12-03 | 云南大学 | Method and system for rapidly and automatically collecting blood vessel edge forms in dynamic ultrasonic image |
| CN105105741A (en) * | 2015-07-15 | 2015-12-02 | 无锡海鹰电子医疗系统有限公司 | Envelope line extracting and feature point tracking method of pulse wave image |
| WO2018058606A1 (en) * | 2016-09-30 | 2018-04-05 | 深圳迈瑞生物医疗电子股份有限公司 | Method for displaying ultrasonic blood flow motion spectrum and ultrasonic imaging system thereof |
| CN107992452A (en) * | 2017-12-12 | 2018-05-04 | 北京动亮健康科技有限公司 | Calculate method, apparatus, storage medium and the equipment of central hemodynamics index |
| WO2019195156A1 (en) * | 2018-04-03 | 2019-10-10 | The Children' S Mercy Hospital | Systems and methods for detecting flow of biological fluids |
| CN111325202A (en) * | 2020-01-19 | 2020-06-23 | 华中科技大学同济医学院附属协和医院 | Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method |
-
2021
- 2021-08-13 CN CN202110928460.0A patent/CN113724208B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049766A (en) * | 2012-12-27 | 2013-04-17 | 中国科学院遥感应用研究所 | Ultrasonic image renal artery blood flow spectrum signal curve classification method |
| CN104095656A (en) * | 2014-07-25 | 2014-10-15 | 声泰特（成都）科技有限公司 | Colorful blood flow imaging based on ultrasonic Doppler frequency spectrum and display method thereof |
| CN104182984A (en) * | 2014-09-01 | 2014-12-03 | 云南大学 | Method and system for rapidly and automatically collecting blood vessel edge forms in dynamic ultrasonic image |
| CN105105741A (en) * | 2015-07-15 | 2015-12-02 | 无锡海鹰电子医疗系统有限公司 | Envelope line extracting and feature point tracking method of pulse wave image |
| WO2018058606A1 (en) * | 2016-09-30 | 2018-04-05 | 深圳迈瑞生物医疗电子股份有限公司 | Method for displaying ultrasonic blood flow motion spectrum and ultrasonic imaging system thereof |
| CN107992452A (en) * | 2017-12-12 | 2018-05-04 | 北京动亮健康科技有限公司 | Calculate method, apparatus, storage medium and the equipment of central hemodynamics index |
| WO2019195156A1 (en) * | 2018-04-03 | 2019-10-10 | The Children' S Mercy Hospital | Systems and methods for detecting flow of biological fluids |
| CN111325202A (en) * | 2020-01-19 | 2020-06-23 | 华中科技大学同济医学院附属协和医院 | Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method |
Non-Patent Citations (3)
| Title |
|---|
| HAYIT GREENSPAN 等.DOPPLER ECHOCARDIOGRAPHY FLOW-VELOCITY IMAGE ANALYSIS FOR PATIENTS WITH ATRIAL FIBRILLATION.《Original Contribution》.2005,1031-1040. * |
| Juerg Tschirren 等.Determination of the envelope function (maximum velocity curve) in Doppler ultrasound flow velocity diagrams.《PROCEEDINGS OF SPIE》.2000,1516-1527. * |
| 税雪 等.基于区域生长超声图像分割血管边界反映血管病变.《中国组织工程研究与临床康复》.2011,第15卷(第30期),5607-5610. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724208A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194937B (en) | Traditional Chinese medicine tongue picture image segmentation method in open environment | |
| WO2018120942A1 (en) | System and method for automatically detecting lesions in medical image by means of multi-model fusion | |
| CN111340789A (en) | Method, device, equipment and storage medium for identifying and quantifying eye fundus retinal blood vessels | |
| WO2022001571A1 (en) | Computing method based on super-pixel image similarity | |
| CN107169998A (en) | A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image | |
| Zhang et al. | LU-NET: An improved U-Net for ventricular segmentation | |
| US8948484B2 (en) | Method and system for automatic view planning for cardiac magnetic resonance imaging acquisition | |
| CN107292835B (en) | Method and device for automatically vectorizing retinal blood vessels of fundus image | |
| CN100577103C (en) | Image processing device and method which use two images | |
| CN110796612B (en) | Image enhancement method and system | |
| CN113724208B (en) | Blood flow spectrum signal classification method and system | |
| CN116664462B (en) | Infrared and visible light image fusion method based on MS-DSC and I_CBAM | |
| WO2022086910A1 (en) | Anatomically-informed deep learning on contrast-enhanced cardiac mri | |
| CN117764917A (en) | Yolov 8-based lung nodule image detection method | |
| CN109034256B (en) | LTP and HOG feature fused breast tumor detection system and method | |
| CN114862799B (en) | Full-automatic brain volume segmentation method for FLAIR-MRI sequence | |
| CN113222985B (en) | Image processing method, image processing device, computer equipment and medium | |
| CN115841472A (en) | Method, device, equipment and storage medium for identifying high-density characteristics of middle cerebral artery | |
| KR101830512B1 (en) | Optimized Image Segmentation Methods and System with DL and PDE | |
| CN112734770B (en) | Multi-sequence fusion segmentation method for cardiac nuclear magnetic images based on multilayer cascade | |
| CN118298412B (en) | Visual function electronic detection system of automatic same-vision machine | |
| CN116433795B (en) | Multi-mode image generation method and device based on countermeasure generation network | |
| CN116439743A (en) | Blood flow spectrum contour extraction system based on ultrasonic image and deep learning | |
| CN116597041B (en) | Nuclear magnetic image definition optimization method and system for cerebrovascular diseases and electronic equipment | |
| CN112102243B (en) | Active contour segmentation method and system combining general energy function and priori information item |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |