CN112971756A - Speckle blood flow imaging method, electronic device, and computer-readable storage medium - Google Patents
Speckle blood flow imaging method, electronic device, and computer-readable storage medium Download PDFInfo
- Publication number
- CN112971756A CN112971756A CN202110167490.4A CN202110167490A CN112971756A CN 112971756 A CN112971756 A CN 112971756A CN 202110167490 A CN202110167490 A CN 202110167490A CN 112971756 A CN112971756 A CN 112971756A
- Authority
- CN
- China
- Prior art keywords
- blood flow
- light intensity
- speckle
- original
- obtaining
- 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
- 230000017531 blood circulation Effects 0.000 title claims abstract description 122
- 238000003384 imaging method Methods 0.000 title claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims abstract description 66
- 238000000513 principal component analysis Methods 0.000 claims abstract description 12
- 238000000034 method Methods 0.000 claims description 33
- 239000013598 vector Substances 0.000 claims description 26
- 230000009467 reduction Effects 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 210000003743 erythrocyte Anatomy 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000000004 hemodynamic effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/026—Measuring blood flow
- A61B5/0261—Measuring blood flow using optical means, e.g. infrared light
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
Abstract
The application discloses a speckle blood flow imaging method, an electronic device and a computer readable storage medium, which relate to the field of image processing, wherein the speckle blood flow imaging method comprises the following steps: collecting raw blood flow speckle data of a sample; extracting a plurality of original light intensity matrixes according to the original blood flow speckle data; performing principal component analysis on each original light intensity matrix to obtain a corresponding component group; wherein the component groups correspond to the original light intensity matrix one to one; obtaining a blood flow light intensity signal and a tissue light intensity signal according to the component groups; and obtaining a blood flow distribution map according to the plurality of blood flow light intensity signals and the plurality of tissue light intensity signals. According to the speckle blood flow imaging method, the blood flow light intensity signal and the tissue light intensity signal are extracted by adopting principal component analysis for imaging, and the imaging speed is high and the accuracy is high.
Description
Technical Field
The present disclosure relates to the field of image processing, and in particular, to a speckle blood flow imaging method, an electronic device, and a computer-readable storage medium.
Background
The blood flow is used as an important parameter for reflecting the hemodynamic change of biological tissues, and the realization of the monitoring of the blood flow has important significance in the aspects of life science basic research, clinical diagnosis and treatment of diseases and the like. The general blood flow imaging method has the advantages of less acquired image frame number, lower time resolution and lower imaging accuracy.
Disclosure of Invention
The purpose of this application lies in solving one of the technical problem that exists among the prior art at least, provides a speckle blood flow imaging method, through adopting principal component analysis, draws blood flow light intensity signal and tissue light intensity signal, images, and imaging speed is fast, the accuracy is high.
The speckle blood flow imaging method according to the embodiment of the first aspect of the application comprises the following steps:
collecting raw blood flow speckle data of a sample;
extracting a plurality of original light intensity matrixes according to the original blood flow speckle data;
performing principal component analysis on each original light intensity matrix to obtain a corresponding component group; wherein the component groups correspond to the original light intensity matrix one to one;
obtaining a blood flow light intensity signal and a tissue light intensity signal according to the component groups;
and obtaining a blood flow distribution map according to the plurality of blood flow light intensity signals and the plurality of tissue light intensity signals.
The speckle blood flow imaging method according to the embodiment of the application has at least the following technical effects: performing principal component analysis on an original light intensity matrix extracted from original blood flow speckle data to extract blood flow light intensity signals generated by red blood cells and tissue light intensity signals generated by tissues, and calculating according to the blood flow light intensity signals and the tissue light intensity signals to obtain a blood flow distribution diagram; by the method, the accuracy of the blood flow distribution diagram is improved, and the imaging speed is high.
According to some embodiments of the present application, the performing principal component analysis on each of the original light intensity matrices to obtain a corresponding component group includes:
inputting each original light intensity matrix into a unified computing equipment architecture for multi-thread operation to obtain a corresponding covariance matrix;
obtaining a feature vector group according to the covariance matrix;
and multiplying the characteristic vector group by the original light intensity matrix to obtain the corresponding component group.
According to some embodiments of the present application, said deriving a set of eigenvectors from said covariance matrix comprises:
inputting the covariance matrix into a unified computing equipment architecture to obtain a plurality of eigenvalues;
obtaining a corresponding feature vector according to each feature value;
and arranging the plurality of eigenvectors in a descending order according to the sizes of the corresponding eigenvalues to obtain the eigenvector group.
According to some embodiments of the present application, said multiplying said set of eigenvectors with said original light intensity matrix to obtain said corresponding set of components comprises:
multiplying each eigenvector in the eigenvector group by the original light intensity matrix respectively to obtain a plurality of components;
and sequencing the components according to the sequence of the feature vectors to obtain the component groups.
According to some embodiments of the application, said deriving a blood flow intensity signal and a tissue intensity signal from said set of components comprises:
obtaining a first component with the largest variance contribution rate in the component group;
obtaining the tissue light intensity signal according to the first component;
and inputting the components except the first component in the component group into a unified computing equipment mechanism for shared memory reduction summation to obtain the blood flow light intensity signal.
According to some embodiments of the present application, obtaining a blood flow distribution map according to a plurality of the blood flow intensity signals and a plurality of the tissue intensity signals in succession comprises:
inputting each blood flow light intensity signal and the corresponding tissue light intensity signal into a unified computing equipment framework for multi-thread operation to obtain a corresponding unit blood flow distribution value;
and integrating a plurality of continuous unit blood flow distribution values to obtain the blood flow distribution map.
According to some embodiments of the application, the acquiring raw blood flow speckle data of the sample comprises:
collecting a plurality of sample two-dimensional images of continuous unit time;
and integrating the plurality of sample two-dimensional images to obtain the original blood flow speckle data.
According to some embodiments of the application, extracting a plurality of raw light intensity matrices from the raw blood flow speckle data comprises:
splitting each sample two-dimensional image in the original blood flow speckle data into a plurality of light intensity data lines along the height direction of the sample two-dimensional image;
obtaining a light intensity data set according to a plurality of light intensity data lines;
and respectively arranging the light intensity data rows with the same height in the light intensity data set according to a time sequence to obtain a plurality of original light intensity matrixes.
An electronic device according to an embodiment of the second aspect of the present application includes:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions that, when executed by the at least one processor, cause the at least one processor to implement the method of speckle flow imaging according to the first aspect.
According to a third aspect of the present application, there is provided a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the speckle blood flow imaging method according to the first aspect.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The present application is further described with reference to the following figures and examples;
fig. 1 is a schematic flow chart of a speckle blood flow imaging method according to an embodiment of the present disclosure;
FIG. 2 is a schematic flow chart of a group of computer components according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating an embodiment of a method for determining a feature vector set;
FIG. 4 is a schematic flow chart of obtaining blood flow intensity signals and tissue intensity signals according to component groups according to an embodiment of the present application;
FIG. 5 is a schematic flow chart illustrating a blood flow distribution diagram obtained from the blood flow intensity signal and the tissue intensity signal according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of an electronic device according to another embodiment of the present application;
FIG. 7 is a schematic flow chart illustrating the process of collecting raw blood flow speckle data according to an embodiment of the present application;
fig. 8 is a schematic flowchart of extracting an original light intensity matrix according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the present embodiments of the present application, preferred embodiments of which are illustrated in the accompanying drawings, which are for the purpose of visually supplementing the description with figures and detailed description, so as to enable a person skilled in the art to visually and visually understand each and every feature and technical solution of the present application, but not to limit the scope of the present application.
In the description of the present application, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and larger, smaller, larger, etc. are understood as excluding the present number, and larger, smaller, inner, etc. are understood as including the present number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
A speckle blood flow imaging method according to an embodiment of the present application is described below with reference to the drawings.
As shown in fig. 1, a speckle blood flow imaging method according to an embodiment of the present application includes:
s100: collecting raw blood flow speckle data of a sample;
s200: extracting a plurality of original light intensity matrixes according to original blood flow speckle data;
s300: performing principal component analysis on each original light intensity matrix to obtain a corresponding component group; wherein, the component groups correspond to the original light intensity matrix one by one;
s400: obtaining a blood flow light intensity signal and a tissue light intensity signal according to the component groups;
s500: and obtaining a blood flow distribution diagram according to the plurality of blood flow light intensity signals and the plurality of tissue light intensity signals.
In some embodiments, two-dimensional images in a target time period of the sample are collected, wherein the image height of each two-dimensional image is P, the image width is L, the image size is P × L, the number of two-dimensional images in the target time period is N, and the two-dimensional images are sorted according to a time sequence to form original blood flow speckle data; sequentially extracting original light intensity data of pixel points in the same row (namely the same image height position) of each two-dimensional image in a target time period to form original light intensity vectors, wherein each original light intensity vector forms an original light intensity matrix in the time axis direction, the size of each original light intensity matrix is N x L, and the number of the original light intensity matrices corresponds to the number of rows (namely the image height) of the two-dimensional images; performing principal component analysis on each original light intensity matrix, taking a single original light intensity matrix as an example, calculating a covariance matrix of the original light intensity matrix, obtaining a characteristic value and a characteristic vector of covariance, sorting the characteristic vectors in a descending order according to the size of the characteristic value, multiplying each characteristic vector by the original light intensity matrix in sequence according to the sorting order respectively to obtain a plurality of components sorted according to the size of the corresponding characteristic value, namely grouping, repeating the steps, and obtaining a component group of each original light intensity matrix; obtaining corresponding blood flow light intensity signals and tissue light intensity signals according to the component groups, wherein each pair of blood flow light intensity signals and tissue light intensity signals correspond to the original light intensity matrix one by one; and finally, obtaining a blood flow distribution diagram according to the ratio of each pair of blood flow light intensity signals to the tissue light intensity signals. The process of obtaining blood flow intensity signals and tissue intensity signals according to the original intensity matrix is called principal component analysis.
According to the speckle blood flow imaging method, a blood flow intensity signal generated by red blood cells and a tissue intensity signal generated by tissues are obtained by extracting and analyzing principal components of an original light intensity matrix extracted from original blood flow speckle data, and a blood flow distribution diagram is obtained by calculating according to the blood flow intensity signal and the tissue intensity signal; by the method, the accuracy of the blood flow distribution diagram is improved, and the imaging speed is high.
As shown in fig. 2, in some embodiments of the present application, step S300: and (3) carrying out principal component analysis on each original light intensity matrix to obtain a corresponding component group, wherein the method comprises the following steps:
s310: inputting each original light intensity matrix into a unified computing equipment architecture for multi-thread operation to obtain a corresponding covariance matrix;
s320: solving a feature vector group according to the covariance matrix;
s330: and multiplying the characteristic vector group by the original light intensity matrix to obtain a corresponding component group.
The Unified computing Device architecture, cuda (computer Unified Device architecture), is an operating platform provided by the video card vendor NVIDIA. CUDATMIs a general-purpose parallel computing architecture derived from NVIDIA that enables a GPU (i.e., a graphics processor) to solve complex computational problems.
In some embodiments, the covariance matrix is obtained by the following equation:
wherein, Cxy(i) Is the element of the X row and y column of the covariance matrix C (i), X is less than or equal to N, y is less than or equal to N, Xxk(i) Denotes the X row and k column of the original light matrix X (i)yk(i) The y row and the k column of the original light intensity matrix x (i), L is the image width, and k is 1,2,3, … N; by opening N x N thread blocks in CUDA, each thread block process processes one thread block respectively
The operation of accumulation adopts the reduction and summation calculation of a shared memory, the time complexity is reduced by utilizing the divide and conquer thought, and the time loss of global memory index can be reduced by utilizing the shared memory, so that the covariance matrix of each original light intensity matrix can be rapidly obtained.
After the covariance matrix C (i) is obtained by calculation, the eigenvalue lambda of the covariance matrix C (i) is obtainedx(i) (x ═ 1, 2.., N) and eigenvector ax(i) (x ═ 1,2,. N); will be lambdax(i) In descending order, such that λ1(i)＞λ2(i)＞…＞λN(i) The feature vector ax(i) Sorting according to the corresponding characteristic values; feature vector ax(i) Is the basis of the original intensity matrix x (i) the xth component, the component group can be formulated as:
wherein, Fx(i) The ith component of the ith original intensity matrix is 1,2, …, P, x is 1,2, …, N.
As shown in fig. 3, in some embodiments of the present application, step S320: and solving a feature vector group according to the covariance matrix, wherein the step of solving comprises the following steps:
s321: inputting the covariance matrix into a unified computing equipment architecture to obtain a plurality of eigenvalues;
s322: obtaining a corresponding feature vector according to each feature value;
s323: and arranging the plurality of eigenvectors in a descending order according to the sizes of the corresponding eigenvalues to obtain an eigenvector group.
In some embodiments, after the covariance matrix is obtained in step S310, the obtained covariance matrix is input to the CUDA, the eigenvalues and eigenvectors are quickly obtained, and the eigenvectors are arranged in descending order according to the magnitude of the corresponding eigenvalues, i.e., the eigenvector group. The eigenvalue and the eigenvector of the covariance matrix can be solved through a cumriver library of a CUDA (unified computing device architecture), the covariance matrix is input into the CUDA, and the eigenvalue and the eigenvector of the covariance matrix can be quickly solved through the cumriver library.
In some embodiments of the present application, step S330: multiplying the feature vector group by the original light intensity matrix to obtain a corresponding component group, comprising:
multiplying each eigenvector in the eigenvector group by the original light intensity matrix respectively to obtain a plurality of components;
and sequencing the plurality of components according to the sequence of the eigenvectors to obtain component groups.
In some embodiments, after the feature vector set is obtained in step S323, each feature vector in the feature vector set is multiplied by the original light intensity matrix to obtain components, wherein the components correspond to the feature vectors one to one, and the obtained components are sorted according to the order of the feature vector set, as shown in the following formula:
wherein, Fx(i) The ith component of the ith original intensity matrix is 1,2, …, P, x is 1,2, …, N.
As shown in fig. 4, in some embodiments of the present application, step S400: obtaining a blood flow intensity signal and a tissue intensity signal based on the set of components, comprising:
s410: obtaining a first component with the largest variance contribution rate in the component group;
s420: obtaining a tissue light intensity signal according to the first component;
s430: and inputting the components except the first component in the component group into a unified computing equipment mechanism for shared memory reduction and summation to obtain a blood flow light intensity signal.
In some embodiments, after the component groups are obtained in step S332, since the ranks of the components in the component groups are arranged in descending order according to the magnitudes of the corresponding characteristic values, the first component in the component groups is the first component with the largest variance contribution rate, i.e. the tissue light intensity signal generated by the background tissue: i is0(i)＝F1(i) Wherein, I0(i) To organize the light intensity signal, F1(i) Is the first component of the group of components. The blood flow intensity signal generated by the moving red blood cells is the sum of the second to Nth components of the component group with smaller variance contribution rate:
wherein, IRBC(i) As a blood flow intensity signal, Fx(i) The xth component of the component group, i ═ 1,2, …, P, x ═ 2, …, N; wherein in the signal of the blood flow intensity
The accumulation of (1) can be carried out by sharing memory reduction summation through CUDA, thereby rapidly obtaining the blood flow light intensity signal.
As shown in fig. 5, in some embodiments of the present application, step S500: obtaining a blood flow distribution map according to the plurality of blood flow light intensity signals and the plurality of continuous tissue light intensity signals, comprising:
s510: inputting each blood flow light intensity signal and the corresponding tissue light intensity signal into a unified computing equipment framework for multi-thread operation to obtain a corresponding unit blood flow distribution value;
s520: and integrating the continuous unit blood flow distribution values to obtain a blood flow distribution map.
In some embodiments, after step S430, a unit blood flow distribution value is obtained according to the obtained tissue light intensity signal and the corresponding blood flow light intensity signal, as shown in the following formula:
wherein IP (I) is a unit blood flow distribution value, IRBC(i) As a blood flow intensity signal, I0(i) Organizing the light intensity signal; and (3) each original light intensity matrix can obtain a unit blood flow distribution value IP (i) with the size of 1 × L, wherein L is the width of the two-dimensional image, the steps are repeated to obtain P unit blood flow distribution values IP (i), and a blood flow distribution diagram with the image height of P and the image width of L is obtained through integration. When calculating the unit blood flow distribution value IP (I), starting 1X L threads and simultaneously calculating I0(i) And IRBC(i) Each element in the system is respectively correspondingly calculated to quickly obtain I0(i) And IRBC(i) The unit blood flow distribution value IP (i) is obtained.
As shown in fig. 7, in some embodiments of the present application, step S100: acquiring raw blood flow speckle data of a sample, comprising:
s110: collecting a plurality of sample two-dimensional images of continuous unit time;
s120: and integrating the two-dimensional images of the plurality of samples to obtain original blood flow speckle data.
In some embodiments, a plurality of sample two-dimensional images of continuous unit time are acquired, that is, a sample two-dimensional image of each time point in a target time period is acquired, the size of each sample two-dimensional image is P × L, P is the image height, L is the image width, and the number of time points and the number of sample two-dimensional images are N; and arranging the N sample two-dimensional images according to a time sequence to obtain original blood flow speckle data, wherein the size of the original blood flow speckle data is P x L x N.
As shown in fig. 8, in some embodiments of the present application, step S200: extracting a plurality of original light intensity matrices according to original blood flow speckle data, comprising:
s210: splitting each sample two-dimensional image in the original blood flow speckle data into a plurality of light intensity data lines along the height direction of the sample two-dimensional image;
s220: obtaining a light intensity data set according to the plurality of light intensity data lines;
s230: and respectively arranging the light intensity data rows belonging to the same height in the light intensity data set according to a time sequence to obtain a plurality of original light intensity matrixes.
In some embodiments, after step S120, each sample two-dimensional image in the original blood flow speckle data is split into P intensity data lines along the height direction thereof, each intensity data line including original intensity data corresponding to all pixel points in the ith line in the sample two-dimensional image, where i is 1,2, …, P; splitting each sample two-dimensional image to obtain a light intensity data set comprising P × N light intensity data lines; arranging N light intensity data rows with the same height in the light intensity data set according to a time sequence to obtain an original light intensity matrix, repeating the steps, and finally obtaining P original light intensity matrices with the size of N x L, wherein the P original light intensity matrices are shown as the following formula:
wherein X (I) is the original intensity matrix, Ii,j,kRepresenting the original light intensity data of all pixel points (i, j) in the ith row along the time axis k, wherein i is 1,2, …,P；j＝1,2,…,L；k＝1,2,…,N。
In a second aspect of the embodiments of the present application, an electronic device 600 is provided, where the electronic device may be any type of intelligent terminal, such as a mobile phone, a tablet computer, a personal computer, and the like.
As shown in fig. 6, according to some embodiments of the present application, the electronic device 600 includes: one or more processors 601 and memory 602, one processor 601 being illustrated in fig. 6.
The processor 601 and the memory 602 may be communicatively connected by a bus or other means, and fig. 6 illustrates a connection by a bus as an example.
The memory 602, which is a non-transitory computer readable storage medium, may be used for storing non-transitory software programs, non-transitory computer executable programs, and units, such as program instructions/units corresponding to the electronic device 600 in the embodiments of the present application. The processor 601 executes various functional applications and data processing, i.e., implementing the speckle blood flow imaging method of the above-described method embodiments, by executing non-transitory software programs, instructions and units stored in the memory 602.
The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to program instructions/units, and the like. Further, the memory 602 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 may optionally include memory located remotely from the processor 601, which may be connected to the electronic device 600 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more units are stored in the memory 602, and when executed by the one or more processors 601, perform the speckle flow imaging method in any of the method embodiments described above. For example, the above-described method steps S100 to S500 in fig. 1, method steps S310 to S330 in fig. 2, method steps S321 to S323 in fig. 3, method steps S410 to S430 in fig. 4, method steps S510 to S520 in fig. 5, method steps S110 to S120 in fig. 7, and method steps S210 to S230 in fig. 8 are performed.
In a third aspect of the embodiments of the present application, a computer-readable storage medium is further provided, where the computer-readable storage medium stores computer-executable instructions, which are executed by one or more processors 601, for example, by one of the processors 601 in fig. 6, and may cause the one or more processors 601 to perform the speckle blood flow imaging method in the above-described method embodiment, for example, to perform the above-described method steps S100 to S500 in fig. 1, method steps S310 to S330 in fig. 2, method steps S321 to S323 in fig. 3, method steps S410 to S430 in fig. 4, method steps S510 to S520 in fig. 5, method steps S110 to S120 in fig. 7, and method steps S210 to S230 in fig. 8.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
In the description herein, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples" or the like means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and alterations to these embodiments may be made without departing from the principles and spirit of this application, and are intended to be included within the scope of this application.
Claims (10)
1. A method of speckle blood flow imaging, comprising:
collecting raw blood flow speckle data of a sample;
extracting a plurality of original light intensity matrixes according to the original blood flow speckle data;
performing principal component analysis on each original light intensity matrix to obtain a corresponding component group; wherein the component groups correspond to the original light intensity matrix one to one;
obtaining a blood flow light intensity signal and a tissue light intensity signal according to the component groups;
and obtaining a blood flow distribution map according to the plurality of blood flow light intensity signals and the plurality of tissue light intensity signals.
2. The speckle blood flow imaging method of claim 1, wherein the principal component analysis of each of the raw intensity matrices to obtain corresponding component groups comprises:
inputting each original light intensity matrix into a unified computing equipment architecture for multi-thread operation to obtain a corresponding covariance matrix;
obtaining a feature vector group according to the covariance matrix;
and multiplying the characteristic vector group by the original light intensity matrix to obtain the corresponding component group.
3. The speckle blood flow imaging method of claim 2, wherein the deriving a set of eigenvectors from the covariance matrix comprises:
inputting the covariance matrix into a unified computing equipment architecture to obtain a plurality of eigenvalues;
obtaining a corresponding feature vector according to each feature value;
and arranging the plurality of eigenvectors in a descending order according to the sizes of the corresponding eigenvalues to obtain the eigenvector group.
4. The speckle blood flow imaging method of claim 3, wherein multiplying the set of eigenvectors by the original light intensity matrix to obtain the corresponding set of components comprises:
multiplying each eigenvector in the eigenvector group by the original light intensity matrix respectively to obtain a plurality of components;
and sequencing the components according to the sequence of the feature vectors to obtain the component groups.
5. The speckle blood flow imaging method according to claim 1 or 4, wherein the obtaining of the blood flow intensity signal and the tissue intensity signal from the group of components comprises:
obtaining a first component with the largest variance contribution rate in the component group;
obtaining the tissue light intensity signal according to the first component;
and inputting the components except the first component in the component group into a unified computing equipment mechanism for shared memory reduction summation to obtain the blood flow light intensity signal.
6. The speckle blood flow imaging method as claimed in claim 1, wherein the obtaining of the blood flow distribution map according to the plurality of blood flow intensity signals and the plurality of continuous tissue intensity signals comprises:
inputting each blood flow light intensity signal and the corresponding tissue light intensity signal into a unified computing equipment framework for multi-thread operation to obtain a corresponding unit blood flow distribution value;
and integrating a plurality of continuous unit blood flow distribution values to obtain the blood flow distribution map.
7. The speckle blood flow imaging method of claim 1, wherein the acquiring raw blood flow speckle data of the sample comprises:
collecting a plurality of sample two-dimensional images of continuous unit time;
and integrating the plurality of sample two-dimensional images to obtain the original blood flow speckle data.
8. The speckle blood flow imaging method of claim 7, wherein extracting a plurality of raw intensity matrices from the raw blood flow speckle data comprises:
splitting each sample two-dimensional image in the original blood flow speckle data into a plurality of light intensity data lines along the height direction of the sample two-dimensional image;
obtaining a light intensity data set according to a plurality of light intensity data lines;
and respectively arranging the light intensity data rows with the same height in the light intensity data set according to a time sequence to obtain a plurality of original light intensity matrixes.
9. An electronic device, comprising:
at least one processor, and,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions for execution by the at least one processor to cause the at least one processor, when executing the instructions, to implement the method of speckle flow imaging according to any one of claims 1 to 8.
10. A computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform the method of imaging speckle blood flow as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110167490.4A CN112971756A (en) | 2021-02-07 | 2021-02-07 | Speckle blood flow imaging method, electronic device, and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110167490.4A CN112971756A (en) | 2021-02-07 | 2021-02-07 | Speckle blood flow imaging method, electronic device, and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112971756A true CN112971756A (en) | 2021-06-18 |
Family
ID=76348744
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110167490.4A Pending CN112971756A (en) | 2021-02-07 | 2021-02-07 | Speckle blood flow imaging method, electronic device, and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112971756A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942788A (en) * | 2014-04-11 | 2014-07-23 | 中国科学院遥感与数字地球研究所 | Hyperspectral remote sensing image characteristic extraction method and device |
| CN107485383A (en) * | 2017-09-29 | 2017-12-19 | 佛山科学技术学院 | A kind of speckle blood flow imaging method and apparatus based on constituent analysis |
| CN108354626A (en) * | 2018-03-31 | 2018-08-03 | 华南理工大学 | A variety of MV high clearing systems fast medical ultrasonic image systems based on GPU |
| CN111652855A (en) * | 2020-05-19 | 2020-09-11 | 西安交通大学 | Point cloud simplification method based on survival probability |
-
2021
- 2021-02-07 CN CN202110167490.4A patent/CN112971756A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942788A (en) * | 2014-04-11 | 2014-07-23 | 中国科学院遥感与数字地球研究所 | Hyperspectral remote sensing image characteristic extraction method and device |
| CN107485383A (en) * | 2017-09-29 | 2017-12-19 | 佛山科学技术学院 | A kind of speckle blood flow imaging method and apparatus based on constituent analysis |
| CN108354626A (en) * | 2018-03-31 | 2018-08-03 | 华南理工大学 | A variety of MV high clearing systems fast medical ultrasonic image systems based on GPU |
| CN111652855A (en) * | 2020-05-19 | 2020-09-11 | 西安交通大学 | Point cloud simplification method based on survival probability |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3619711B1 (en) | Predicting quality of sequencing results using deep neural networks | |
| CN106815481B (en) | Lifetime prediction method and device based on image omics | |
| Svoboda et al. | MitoGen: a framework for generating 3D synthetic time-lapse sequences of cell populations in fluorescence microscopy | |
| EP2894577B1 (en) | Retrieving system, retrieving method, and security inspection device based on contents of fluoroscopic images | |
| Li et al. | A multi-scale cucumber disease detection method in natural scenes based on YOLOv5 | |
| RU2385494C1 (en) | Method for recognition of cell texture image | |
| CN105579847B (en) | Diseases analysis device, control method and program | |
| CN108875931A (en) | Neural metwork training and image processing method, device, system | |
| CN113053535B (en) | Medical information prediction system and medical information prediction method | |
| CN108664986B (en) | Based on lpNorm regularized multi-task learning image classification method and system | |
| JP6756339B2 (en) | Image processing device and image processing method | |
| CN111275717B (en) | Contrast display method for different stained sections, electronic device and readable medium | |
| Klyuchko | On the mathematical methods in biology and medicine | |
| CN111540467A (en) | Schizophrenia classification identification method, operation control device and medical equipment | |
| CN115004316A (en) | Multi-functional computer-assisted gastroscopy system and method employing optimized integrated AI solutions | |
| CN110827963A (en) | Semantic segmentation method for pathological image and electronic equipment | |
| Kwasigroch et al. | Deep neural network architecture search using network morphism | |
| CN112971756A (en) | Speckle blood flow imaging method, electronic device, and computer-readable storage medium | |
| JP5720351B2 (en) | Image analysis method and image analysis apparatus | |
| CN108876767B (en) | Sugarcane festival characteristic quick identification device | |
| CN108346471B (en) | Pathological data analysis method and device | |
| CN114387209A (en) | Method, apparatus, medium, and device for fundus structural feature determination | |
| Basu et al. | Segmentation in diabetic retinopathy using deeply-supervised multiscalar attention | |
| CN110517783A (en) | Model training method, device and heart disease diagnosis device, equipment, medium | |
| Talapatra et al. | Cellprofiler and weka tools: image analysis for fish erythrocytes shape and machine learning model algorithm accuracy prediction of dataset |
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: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |