CN111325202A - Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method - Google Patents

Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method Download PDF

Info

Publication number
CN111325202A
CN111325202A CN202010063353.1A CN202010063353A CN111325202A CN 111325202 A CN111325202 A CN 111325202A CN 202010063353 A CN202010063353 A CN 202010063353A CN 111325202 A CN111325202 A CN 111325202A
Authority
CN
China
Prior art keywords
blood flow
region
image
layer
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010063353.1A
Other languages
Chinese (zh)
Inventor
叶霖
韩斌
陈学东
杨新
龙绍军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tongji Medical College of Huazhong University of Science and Technology
Union Hospital Tongji Medical College Huazhong University of Science and Technology
Original Assignee
Union Hospital Tongji Medical College Huazhong University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Union Hospital Tongji Medical College Huazhong University of Science and Technology filed Critical Union Hospital Tongji Medical College Huazhong University of Science and Technology
Priority to CN202010063353.1A priority Critical patent/CN111325202A/en
Publication of CN111325202A publication Critical patent/CN111325202A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • 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
    • A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
    • A61B8/0891—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
    • A61B8/48—Diagnostic techniques
    • A61B8/488—Diagnostic techniques involving Doppler signals
    • 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
    • A61B8/5207—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of raw data to produce diagnostic data, e.g. for generating an image
    • 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
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G06F17/147—Discrete orthonormal transforms, e.g. discrete cosine transform, discrete sine transform, and variations therefrom, e.g. modified discrete cosine transform, integer transforms approximating the discrete cosine transform
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/40—Image enhancement or restoration using histogram techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • Animal Behavior & Ethology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Surgery (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Algebra (AREA)
  • Discrete Mathematics (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Vascular Medicine (AREA)
  • Hematology (AREA)
  • Ultra Sonic Daignosis Equipment (AREA)

Abstract

The invention provides a method for detecting the frequency spectrum blood flow of a color spectrogram based on ultrasonic Doppler, which comprises the following steps: firstly, obtaining a Doppler blood flow spectrogram by adopting an ultrasonic Doppler imaging technology, and measuring a blood flow velocity maximum value and a blood flow velocity minimum value in the Doppler blood flow spectrogram; performing edge extraction on the ultrasonic spectrogram to obtain an interested region; extracting the characteristics of the region of interest to obtain edge characteristics and area characteristics corresponding to the region of interest; constructing a radial basis function neural network model by taking the edge features and the region features as input layer vectors, and analyzing the input layer vector features in the neural network to obtain output quantity related to the vessel features; correcting the relevant output quantity of the blood vessel characteristic according to the maximum value and the minimum value of the blood flow velocity to obtain blood flow velocity output; the invention can accurately mark and distinguish the blood vessel region, correct the blood flow speed and is beneficial to the auxiliary diagnosis of exact illness state.

Description

Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method
Technical Field
The invention relates to the field of medical ultrasonic imaging detection, in particular to a frequency spectrum blood flow detection method of a color spectrogram based on ultrasonic Doppler.
Background
Ultrasonic Doppler is the most advanced and precise image examination high-tech technology in the world, and the precise medical examination can be carried out on a patient by utilizing an ultrasonic Doppler system device so as to obtain exact disease information. In order to ensure the accuracy of the ultrasonic Doppler examination, the imaging parameters of the image need to be adjusted in a specialized manner manually in the whole detection process, which puts high professional requirements on professional literacy of users, and the complete adjustment process has extremely complex steps and also has high professional requirements on the concentration of the users. This causes that parameters of the ultrasonic doppler system device must be adjusted each time the user performs the ultrasonic doppler system detection, and the judgment of the result in the ultrasonic examination process is mostly related to the skill and practice of the doctor, which reduces the usability of the system.
The patent application document with the application number of 201810005469.2 discloses a Doppler blood flow velocity imaging method and system based on ultrasonic channel data, which can independently estimate the blood flow velocity through the channel data corresponding to different array elements, and then improve the signal-to-noise ratio of blood flow signals through the mode of angle phase alignment and superposition, thereby improving the accuracy of blood flow velocity estimation, but can not accurately mark and distinguish blood vessel regions, and is definitely not beneficial to auxiliary diagnosis of diseases.
Patent application No. 201510670863.4 discloses an automatic optimization method of ultrasonic spectrum doppler, which can realize the adjustment of angle and can also automatically and roughly identify the blood flow direction, thereby reducing the time spent in optimizing the ultrasonic spectrum image adjustment parameters, reducing the operation burden of doctors, improving the work efficiency, but not accurately marking and distinguishing the blood vessel region, and being not beneficial to the auxiliary diagnosis of exact disease conditions.
Disclosure of Invention
The invention provides a frequency spectrum blood flow detection method of a color spectrogram based on ultrasonic Doppler, which can construct a radial basis neural network blood vessel characteristic identification model by counting edge characteristics and regional characteristic parameters of blood vessels according to a preprocessed Doppler blood flow spectrogram, obtain output quantity related to the blood vessel characteristics in a detection region and further correct blood flow speed.
The technical scheme provided by the invention is as follows:
a method for detecting the spectral blood flow of a color spectrogram based on ultrasonic Doppler comprises the following steps:
firstly, obtaining a Doppler blood flow spectrogram by adopting an ultrasonic Doppler imaging technology, and preprocessing the Doppler blood flow spectrogram;
measuring a blood flow velocity maximum and a blood flow velocity minimum in the doppler flow spectrogram;
performing edge extraction on the preprocessed ultrasonic spectrogram, and searching to obtain an interested region;
extracting the characteristics of the region of interest to obtain edge characteristics and area characteristics corresponding to the region of interest;
constructing a radial basis function neural network model by taking the edge features and the region features as input layer vectors, and analyzing the input layer vector features in the neural network to obtain output quantity related to the vessel features;
correcting the relevant output quantity of the blood vessel characteristic according to the maximum value and the minimum value of the blood flow velocity to obtain blood flow velocity output;
wherein the vessel feature related output comprises: vessel diameter, vessel depth, and vessel wall thickness.
Preferably, the doppler flow spectrogram preprocessing process includes:
step a, carrying out binarization processing on the collected vein image,
Figure BDA0002375196080000021
in the formula, I (x, y) is a gray value of the (x, y) position, thresh is a preset threshold, and f (x, y) is a gray value of the (x, y) position of the binarized vein image;
step b, obtaining the mass center of the hand back area by utilizing the zero-order moment and the first-order moment, wherein the zero-order moment M00The calculation method satisfies the following conditions:
Figure BDA0002375196080000031
in the formula, m and n are respectively the number of rows and columns of the binarized vein image;
first moment M10And M01The calculation methods respectively satisfy:
Figure BDA0002375196080000032
Figure BDA0002375196080000033
step c, acquiring the center position of the back of the hand as follows:
Figure BDA0002375196080000034
obtaining an image of the region of interest based on a rectangular expansion strategy;
and d, respectively carrying out inversion and histogram equalization on the interested region image so as to obtain a preprocessed vein image L with the size of M × M pixels.
Preferably, the edge feature and the region feature corresponding to the region of interest include: the edge characteristic parameter and the region description characteristic parameter are formed by independent invariant moment parameters of the sub-numbers of the discrete cosine transform.
Preferably, the sub-numbers of the discrete cosine transform are calculated by the following formula:
C(k)＝|F(k)|/F(1)；
wherein C (k) is the number of discrete cosine transform subsystems,
Figure BDA0002375196080000035
k is the number of the discrete sub coefficients, and k is 1,2 … 8; f (k) ═ x (k) + jy (k);
Figure BDA0002375196080000036
Figure BDA0002375196080000037
j is the imaginary part N of the complex plane 1,2,3 … N-1; n is a variable of a feature point of a closed edge curve obtained by performing edge extraction after image segmentation, N is the number of the feature points of the closed edge curve obtained by performing edge extraction after image segmentation, and f (m) ═ x (m) + jy (m); m is more than or equal to 1 and less than or equal to n, and f (m) is a one-dimensional complex sequence.
Preferably, the independent invariant parameter calculation formula is:
Figure BDA0002375196080000041
wherein the content of the first and second substances,
Figure BDA0002375196080000042
is the coordinate of the center point of the region, mupqIs the central moment of the region of the binary image
Figure BDA0002375196080000043
m00Is the zero order geometric moment, m, of the region where the binary image is located01、m10Is the first-order geometric moment, m, of the region where the binary image is locatedpqIs the geometric moment of order p + q of the region of the binary image, p is the row order of the central moment of the binary image, and q is the column order of the central moment of the binary imageNext, the process is carried out.
Preferably, the radial basis function neural network model is a three-layer neural network model:
the first layer is an input layer and finishes inputting the feature vectors into the network;
the second layer is a hidden layer and can be completely connected with the input layer, the hidden layer node selects a Gaussian radial basis function as a transfer function, and the calculation formula is as follows:
Figure BDA0002375196080000044
wherein, | | xp-ciI is the European norm, ciIs the center of the Gaussian function, and sigma is the variance of the Gaussian function;
the third layer is an output layer, 2 output quantities are obtained by calculating the weight between the hidden layer and the output layer, and the vehicle target is identified; the output of the network, which can be derived from the structure of the radial basis function neural network, is:
Figure BDA0002375196080000045
in the formula (I), the compound is shown in the specification,
Figure BDA0002375196080000046
p is the P-th input sample, P is 1,2, …, P is the total number of samples; c. CiFor the centre of the hidden layer node of the network, omegaijThe connection weight from the hidden layer to the output layer is 1,2, …, h is the number of nodes in the hidden layer, yjJ is the actual output of the jth output node of the network for the input sample pair, j being 1,2, …, n;
Figure BDA0002375196080000051
wherein d isjIs the expected output value of the sample.
Preferably, the blood flow velocity correction formula is:
Figure BDA0002375196080000052
wherein v isxFor corrected blood flow rate, v is mean venous blood flow rate, vmaxMaximum flow velocity of blood, vminMinimum flow rate of blood, DrIs the diameter of the blood vessel, hrIs the depth of the blood vessel, hsTo mean depth, ThThe thickness of the vessel wall.
The invention has the advantages of
The invention provides a frequency spectrum blood flow detection method of a color spectrogram based on ultrasonic Doppler, which can construct a radial basis neural network blood vessel characteristic identification model by counting edge characteristics and regional characteristic parameters of blood vessels according to a preprocessed Doppler blood flow spectrogram, obtain output quantity related to the blood vessel characteristics in a detection region and further correct blood flow speed.
Drawings
Fig. 1 is a flowchart of a method for detecting a spectral blood flow based on a color spectrogram of ultrasonic doppler according to the present invention.
Detailed Description
As shown in fig. 1, the method for detecting a spectral blood flow of a color spectrogram based on ultrasonic doppler provided by the present invention includes:
firstly, obtaining a Doppler blood flow spectrogram by adopting an ultrasonic Doppler imaging technology, and preprocessing the Doppler blood flow spectrogram;
the Doppler blood flow spectrogram preprocessing process comprises the following steps:
step a, carrying out binarization processing on the collected vein image,
Figure BDA0002375196080000061
in the formula, I (x, y) is a gray value of the (x, y) position, thresh is a preset threshold, and f (x, y) is a gray value of the (x, y) position of the binarized vein image;
step b, obtaining the mass center of the hand back area by utilizing the zero-order moment and the first-order moment, wherein the zero-order moment M00Calculation methodSatisfies the following conditions:
Figure BDA0002375196080000062
in the formula, m and n are respectively the number of rows and columns of the binarized vein image;
first moment M10And M01The calculation methods respectively satisfy:
Figure BDA0002375196080000063
Figure BDA0002375196080000064
step c, acquiring the center position of the back of the hand as follows:
Figure BDA0002375196080000065
obtaining an image of the region of interest based on a rectangular expansion strategy;
and d, respectively carrying out inversion and histogram equalization on the interested region image so as to obtain a preprocessed vein image L with the size of M × M pixels.
Step two, measuring the maximum value and the minimum value of the blood flow velocity in the Doppler blood flow spectrogram;
step three, performing edge extraction on the preprocessed ultrasonic spectrogram, and searching to obtain an interested region;
extracting the characteristics of the region of interest to obtain edge characteristics and area characteristics corresponding to the region of interest;
the edge features and the region features corresponding to the region of interest include: the edge characteristic parameter and the region description characteristic parameter are formed by independent invariant moment parameters of the coefficient of the discrete cosine transform.
The calculation formula of the number of the subsystems of the discrete cosine transform is as follows:
C(k)＝|F(k)|/F(1)；
wherein, C(k) Is the number of sub-systems of the discrete cosine transform,
Figure BDA0002375196080000071
k is the number of the discrete sub coefficients, and k is 1,2 … 8; f (k) ═ x (k) + jy (k);
Figure BDA0002375196080000072
Figure BDA0002375196080000073
j is the imaginary part N of the complex plane 1,2,3 … N-1; n is a variable of a feature point of a closed edge curve obtained by performing edge extraction after image segmentation, N is the number of the feature points of the closed edge curve obtained by performing edge extraction after image segmentation, and f (m) ═ x (m) + jy (m); m is more than or equal to 1 and less than or equal to n, and f (m) is a one-dimensional complex sequence.
The independent invariant moment parameter calculation formula is as follows:
Figure BDA0002375196080000074
wherein the content of the first and second substances,
Figure BDA0002375196080000075
is the coordinate of the center point of the region, mupqIs the central moment of the region of the binary image
Figure BDA0002375196080000076
m00Is the zero order geometric moment, m, of the region where the binary image is located01、m10Is the first-order geometric moment, m, of the region where the binary image is locatedpqThe image is a binary image in the region of the geometric moment of order p + q, p is the row order of the central moment of the binary image, and q is the column order of the central moment of the binary image.
Constructing a radial basis function neural network model by taking the edge features and the region features as input layer vectors, and analyzing the input layer vector features in the neural network to obtain output quantity related to the vessel features;
the radial basis function neural network model is a three-layer neural network model:
the first layer is an input layer and finishes inputting the feature vectors into the network;
the second layer is a hidden layer and can be completely connected with the input layer, the hidden layer node selects a Gaussian radial basis function as a transfer function, and the calculation formula is as follows:
Figure BDA0002375196080000081
wherein, | | xp-ciI is the European norm, ciIs the center of the Gaussian function, and sigma is the variance of the Gaussian function;
the third layer is an output layer, 2 output quantities are obtained by calculating the weight between the hidden layer and the output layer, and the vehicle target is identified; the output of the network, which can be derived from the structure of the radial basis function neural network, is:
Figure BDA0002375196080000082
in the formula (I), the compound is shown in the specification,
Figure BDA0002375196080000083
p is the P-th input sample, P is 1,2, …, P is the total number of samples; c. CiFor the centre of the hidden layer node of the network, omegaijThe connection weight from the hidden layer to the output layer is 1,2, …, h is the number of nodes in the hidden layer, yjJ is the actual output of the jth output node of the network for the input sample pair, j being 1,2, …, n;
Figure BDA0002375196080000084
wherein d isjIs the expected output value of the sample.
Correcting the relevant output quantity of the blood vessel characteristic according to the maximum value and the minimum value of the blood flow velocity to obtain blood flow velocity output;
wherein the vessel feature related output comprises: vessel diameter, vessel depth, and vessel wall thickness.
The blood flow velocity correction formula is:
Figure BDA0002375196080000091
wherein v isxFor corrected blood flow rate, v is mean venous blood flow rate, vmaxMaximum flow velocity of blood, vminMinimum flow rate of blood, DrIs the diameter of the blood vessel, hrIs the depth of the blood vessel, hsTo mean depth, ThThe thickness of the vessel wall.
The invention provides a frequency spectrum blood flow detection method of a color spectrogram based on ultrasonic Doppler, which can construct a radial basis neural network blood vessel characteristic identification model by counting edge characteristics and regional characteristic parameters of blood vessels according to a preprocessed Doppler blood flow spectrogram, obtain output quantity related to the blood vessel characteristics in a detection region and further correct blood flow speed.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.

Claims (7)

1. A method for detecting the spectral blood flow of a color spectrogram based on ultrasonic Doppler is characterized by comprising the following steps:
firstly, obtaining a Doppler blood flow spectrogram by adopting an ultrasonic Doppler imaging technology, and preprocessing the Doppler blood flow spectrogram;
measuring a blood flow velocity maximum and a blood flow velocity minimum in the doppler flow spectrogram;
performing edge extraction on the preprocessed ultrasonic spectrogram, and searching to obtain an interested region;
extracting the characteristics of the region of interest to obtain edge characteristics and area characteristics corresponding to the region of interest;
constructing a radial basis function neural network model by taking the edge features and the region features as input layer vectors, and analyzing the input layer vector features in the neural network to obtain output quantity related to the vessel features;
correcting the relevant output quantity of the blood vessel characteristic according to the maximum value and the minimum value of the blood flow velocity to obtain blood flow velocity output;
wherein the vessel feature related output comprises: vessel diameter, vessel depth, and vessel wall thickness.
2. The method of claim 1, wherein the doppler flow spectrogram preprocessing comprises:
step a, carrying out binarization processing on the collected vein image,
Figure FDA0002375196070000011
in the formula, I (x, y) is a gray value of the (x, y) position, thresh is a preset threshold, and f (x, y) is a gray value of the (x, y) position of the binarized vein image;
step b, obtaining the centroid of the image area by utilizing the zero order moment and the first order moment, wherein the zero order moment M00The calculation method satisfies the following conditions:
Figure FDA0002375196070000012
in the formula, m and n are respectively the number of rows and columns of the binarized vein image;
first moment M10And M01The calculation methods respectively satisfy:
Figure FDA0002375196070000021
Figure FDA0002375196070000022
step c, obtaining the position of the centroid of the image as follows:
Figure FDA0002375196070000023
obtaining an image of the region of interest based on a rectangular expansion strategy;
and d, respectively carrying out inversion and histogram equalization on the interested region image so as to obtain a preprocessed vein image L with the size of M × M pixels.
3. The method of claim 1, wherein the edge and region features corresponding to the region of interest comprise: the edge characteristic parameter and the region description characteristic parameter are formed by independent invariant moment parameters of the sub-numbers of the discrete cosine transform.
4. The method of claim 2, wherein the sub-system calculation formula of the discrete cosine transform is:
C(k)＝|F(k)|/F(1)；
wherein C (k) is the number of discrete cosine transform subsystems,
Figure FDA0002375196070000024
k is the number of the discrete sub coefficients, and k is 1,2 … 8; f (k) ═ x (k) + jy (k);
Figure FDA0002375196070000025
Figure FDA0002375196070000026
j is the imaginary part N of the complex plane 1,2,3 … N-1; n is a characteristic point variable of a closed edge curve obtained by performing edge extraction after image segmentation, and N is edge extraction after image segmentationTaking the number of characteristic points of the obtained closed edge curve, wherein f (m) is x (m) + jy (m); m is more than or equal to 1 and less than or equal to n, and f (m) is a one-dimensional complex sequence.
5. The method of claim 2, wherein the independent invariant moment parameter calculation formula is:
Figure FDA0002375196070000031
wherein the content of the first and second substances,
Figure FDA0002375196070000032
Figure FDA0002375196070000033
is the coordinate of the center point of the region, mupqIs the central moment of the region of the binary image
Figure FDA0002375196070000034
m00Is the zero order geometric moment, m, of the region where the binary image is located01、m10Is the first-order geometric moment, m, of the region where the binary image is locatedpqThe image is a binary image in the region of the geometric moment of order p + q, p is the row order of the central moment of the binary image, and q is the column order of the central moment of the binary image.
6. The method of claim 5, wherein the radial basis function neural network model is a three-layer neural network model:
the first layer is an input layer and finishes inputting the feature vectors into the network;
the second layer is a hidden layer and can be completely connected with the input layer, the hidden layer node selects a Gaussian radial basis function as a transfer function, and the calculation formula is as follows:
Figure FDA0002375196070000035
wherein, | | xp-ciI is the European norm, ciIs the center of the Gaussian function, and sigma is the variance of the Gaussian function;
the third layer is an output layer, 2 output quantities are obtained by calculating the weight between the hidden layer and the output layer, and the vehicle target is identified; the output of the network, which can be derived from the structure of the radial basis function neural network, is:
Figure FDA0002375196070000036
in the formula (I), the compound is shown in the specification,
Figure FDA0002375196070000037
p is the P-th input sample, P is 1,2, …, P is the total number of samples; c. CiFor the centre of the hidden layer node of the network, omegaijThe connection weight from the hidden layer to the output layer is 1,2, …, h is the number of nodes in the hidden layer, yjJ is the actual output of the jth output node of the network for the input sample pair, j being 1,2, …, n;
Figure FDA0002375196070000041
wherein d isjIs the expected output value of the sample.
7. The method of claim 6, wherein the formula of the blood flow velocity correction is:
Figure FDA0002375196070000042
wherein v isxFor corrected blood flow rate, v is mean venous blood flow rate, vmaxMaximum flow velocity of blood, vminMinimum flow rate of blood, DrIs the diameter of the blood vessel, hrIs a blood vesselDepth, hsTo mean depth, ThThe thickness of the vessel wall.
CN202010063353.1A 2020-01-19 2020-01-19 Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method Pending CN111325202A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010063353.1A CN111325202A (en) 2020-01-19 2020-01-19 Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010063353.1A CN111325202A (en) 2020-01-19 2020-01-19 Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method

Publications (1)

Publication Number Publication Date
CN111325202A true CN111325202A (en) 2020-06-23

Family

ID=71168662

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010063353.1A Pending CN111325202A (en) 2020-01-19 2020-01-19 Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method

Country Status (1)

Country Link
CN (1) CN111325202A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113393452A (en) * 2021-06-28 2021-09-14 什维新智医疗科技(上海)有限公司 Thyroid nodule blood vessel number detection device
CN113724208A (en) * 2021-08-13 2021-11-30 中山大学附属第八医院（深圳福田） Blood flow frequency spectrum signal classification method and system
CN114469176A (en) * 2021-12-31 2022-05-13 深圳度影医疗科技有限公司 Detection method and related device for fetal heart ultrasonic image

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106887000A (en) * 2017-01-23 2017-06-23 上海联影医疗科技有限公司 The gridding processing method and its system of medical image
CN208659421U (en) * 2017-11-28 2019-03-29 中国人民解放军总医院 A kind of blood flow limiter based near infrared ray Detection Techniques
CN110013275A (en) * 2019-05-20 2019-07-16 深圳市贝斯曼精密仪器有限公司 A kind of color frequency spectrum figure and frequency spectrum blood flow detection method based on ultrasonic Doppler

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106887000A (en) * 2017-01-23 2017-06-23 上海联影医疗科技有限公司 The gridding processing method and its system of medical image
CN208659421U (en) * 2017-11-28 2019-03-29 中国人民解放军总医院 A kind of blood flow limiter based near infrared ray Detection Techniques
CN110013275A (en) * 2019-05-20 2019-07-16 深圳市贝斯曼精密仪器有限公司 A kind of color frequency spectrum figure and frequency spectrum blood flow detection method based on ultrasonic Doppler

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113393452A (en) * 2021-06-28 2021-09-14 什维新智医疗科技(上海)有限公司 Thyroid nodule blood vessel number detection device
CN113393452B (en) * 2021-06-28 2023-04-07 什维新智医疗科技(上海)有限公司 Thyroid nodule blood vessel number detection device
CN113724208A (en) * 2021-08-13 2021-11-30 中山大学附属第八医院（深圳福田） Blood flow frequency spectrum signal classification method and system
CN113724208B (en) * 2021-08-13 2023-06-06 中山大学附属第八医院（深圳福田） Blood flow spectrum signal classification method and system
CN114469176A (en) * 2021-12-31 2022-05-13 深圳度影医疗科技有限公司 Detection method and related device for fetal heart ultrasonic image

Similar Documents

Publication Publication Date Title
CN104834922B (en) Gesture identification method based on hybrid neural networks
CN111325202A (en) Ultrasonic Doppler-based color spectrogram frequency spectrum blood flow detection method
CN111212379A (en) Novel CSI indoor positioning method based on convolutional neural network
CN108257135A (en) The assistant diagnosis system of medical image features is understood based on deep learning method
CN110837768B (en) Online detection and identification method for rare animal protection
CN111784721B (en) Ultrasonic endoscopic image intelligent segmentation and quantification method and system based on deep learning
CN108537751B (en) Thyroid ultrasound image automatic segmentation method based on radial basis function neural network
CN107729926B (en) Data amplification method and machine identification system based on high-dimensional space transformation
CN107169998A (en) A kind of real-time tracking and quantitative analysis method based on hepatic ultrasound contrast enhancement image
CN108492300B (en) Lung blood vessel tree segmentation method combining tubular structure enhancement and energy function
CN107292835B (en) Method and device for automatically vectorizing retinal blood vessels of fundus image
KB et al. Convolutional neural network for segmentation and measurement of intima media thickness
Lan et al. Run: Residual u-net for computer-aided detection of pulmonary nodules without candidate selection
CN110021019B (en) AI-assisted hair thickness distribution analysis method for AGA clinical image
CN112348883A (en) Interventional instrument endpoint real-time positioning system, method and device in vascular interventional operation
CN113034528A (en) Target area and organ-at-risk delineation contour accuracy testing method based on image omics
CN112750137A (en) Liver tumor segmentation method and system based on deep learning
CN110188684B (en) Face recognition device and method
Liu et al. Automatic muscle fiber orientation tracking in ultrasound images using a new adaptive fading Bayesian Kalman smoother
Li et al. MDTL: a novel and model-agnostic transfer learning strategy for cross-subject motor imagery BCI
CN113516643A (en) Method for detecting retinal vessel bifurcation and intersection points in OCTA image
CN109886320B (en) Human femoral X-ray intelligent recognition method and system
CN111325282A (en) Mammary gland X-ray image identification method and device suitable for multiple models
CN110619633A (en) Liver image segmentation method based on multi-path filtering strategy
WO2020140380A1 (en) Method and device for quickly dividing optical coherence tomography image

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20200623

RJ01 Rejection of invention patent application after publication