CN110664435A - Method and device for acquiring cardiac data and ultrasonic imaging equipment - Google Patents
Method and device for acquiring cardiac data and ultrasonic imaging equipment Download PDFInfo
- Publication number
- CN110664435A CN110664435A CN201910899879.0A CN201910899879A CN110664435A CN 110664435 A CN110664435 A CN 110664435A CN 201910899879 A CN201910899879 A CN 201910899879A CN 110664435 A CN110664435 A CN 110664435A
- Authority
- CN
- China
- Prior art keywords
- image
- left ventricle
- edge contour
- heart
- dimensional echocardiogram
- 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
Images
Classifications
-
- 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
- A61B8/0883—Detecting organic movements or changes, e.g. tumours, cysts, swellings for diagnosis of the heart
-
- 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
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
Abstract
The embodiment of the invention provides a method and a device for acquiring cardiac data and ultrasonic imaging equipment. Embodiments of the present invention collect two-dimensional echocardiograms of a target object over a continuous period of time, the continuous time is longer than one cardiac cycle, the two-dimensional echocardiogram comprises a plurality of frames of images, the edge contour of the left ventricle of each image in the two-dimensional echocardiogram is determined by using a speckle tracking algorithm, determining a target cardiac data value for the target object based on an edge contour of a left ventricle of each image in the two-dimensional echocardiogram, acquiring a two-dimensional echocardiogram of more than one cardiac cycle during acquisition of cardiac data, automatically and intelligently determining a border contour of a left ventricle in each acquired image, the heart data is automatically determined according to the edge contour of the left ventricle, so that manual operation is reduced, the time of the whole measuring process is shortened, the measuring speed is improved, and errors caused by manual operation are reduced, so that the accuracy of the measuring result can be improved.
Description
Technical Field
The invention relates to the technical field of medical image processing, in particular to a method and a device for acquiring cardiac data and ultrasonic imaging equipment.
Background
The ultrasonic imaging equipment has the advantages of safety, real-time performance, low cost and the like, and is widely applied in the medical field. Among them, obtaining the left ventricular Ejection Fraction (EF) through a two-dimensional echocardiogram acquired by an ultrasound imaging apparatus is an important application direction of the ultrasound imaging apparatus.
The left ventricular ejection fraction EF is calculated as follows:
EF＝(EDV-ESV)/EDV (1)
where EDV (End-Diastolic Volume) is the left ventricular Volume at End-diastole and ESV (End-Systolic Volume) is the left ventricular Volume at End-systole.
In the related art, the left ventricular ejection fraction is measured in the following manner: acquiring a two-dimensional echocardiogram sequence of a period of continuous time, and manually selecting an image of the end diastole and an image of the end systole from the sequence; manually tracing the left ventricle contour in an image at the end diastole to obtain an EDV value; manually tracing the contour of the left ventricle in an image at the end of systole to obtain an ESV value; and finally, calculating according to a formula (1) to obtain a value of the left ventricular ejection fraction EF.
According to the scheme, a manual measurement mode is adopted, manual errors are introduced into an operation method, proficiency, selection accuracy of the end diastole image and the end systole image and the like of a user, so that the accuracy of a measurement result is low, and meanwhile, the measurement speed is low due to the fact that much time is needed for manual operation.
Disclosure of Invention
In order to overcome the problems in the related art, the invention provides a method and a device for acquiring cardiac data and ultrasonic imaging equipment, and the accuracy of a measurement result is improved.
According to a first aspect of embodiments of the present invention, there is provided a method of acquiring cardiac data, comprising:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining an edge contour of a left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
and determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
According to a second aspect of embodiments of the present invention, there is provided an apparatus for acquiring cardiac data, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
a contour determining module for determining a contour of a left ventricle edge of each image in the two-dimensional echocardiogram using a speckle tracking algorithm;
and the numerical value determining module is used for determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
According to a third aspect of embodiments of the present invention, there is provided an ultrasound imaging apparatus comprising a processor and a memory for storing executable instructions of the processor;
the processor is configured to:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining an edge contour of a left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
and determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, in the process of obtaining the left ventricular ejection fraction EF, the two-dimensional echocardiogram of more than one cardiac cycle is collected, the edge contour of the left ventricle in each image of the two-dimensional echocardiogram is automatically and intelligently determined, and the target heart data value is automatically determined according to the edge contour of the left ventricle. According to the embodiment of the invention, automatic and intelligent operation of the equipment is utilized, manual operation is reduced, on one hand, the time of the whole measuring process is shortened, the measuring speed is improved, on the other hand, errors caused by manual operation are reduced, and therefore, the accuracy of the measuring result can be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the specification.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present specification and together with the description, serve to explain the principles of the specification.
Fig. 1 is a flowchart illustrating a method for acquiring cardiac data according to an embodiment of the present invention.
Fig. 2 is a diagram illustrating another example of a flow chart of a method for acquiring cardiac data according to an embodiment of the present invention.
Fig. 3 is a functional block diagram of an apparatus for acquiring cardiac data according to an embodiment of the present invention.
Fig. 4 is a hardware configuration diagram of an ultrasound imaging apparatus provided in an embodiment of the present invention.
Fig. 5 is a graph of left ventricular volume versus time.
FIG. 6 is an exemplary edge view of the heart in a four chamber view of the apex of the heart.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of embodiments of the invention, as detailed in the following claims.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of embodiments of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used to describe various information in embodiments of the present invention, the information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of embodiments of the present invention. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
An ultrasonic imaging apparatus is an apparatus for performing detection using ultrasonic waves. The system controller and the ultrasonic probe (hereinafter referred to as probe) are two important components of the ultrasonic imaging apparatus. The process of ultrasonic imaging is: the system controller generates an electric signal according to set detection parameters, such as time delay, focusing parameters and the like, and sends the electric signal to the probe; the probe converts the electric signal sent by the system controller into ultrasonic waves and emits the ultrasonic waves; an ultrasonic wave is injected into a target internal structure, such as human tissue, which is aligned with a probe, and an ultrasonic echo is formed under the blockage of the target internal structure; the ultrasonic echo is received by the probe, and the probe converts the ultrasonic echo into an electric signal and sends the electric signal to the system controller; the system controller performs a series of processing such as amplification, analog-to-digital conversion, beam forming, filtering, envelope information extraction, logarithmic compression, downsampling and the like on the received electric signals to form an ultrasonic image.
When the target of the probe alignment is a heart region of a human body, an ultrasound image of the heart can be acquired. An ultrasound image of the heart includes two parts, a heart image and a background image. The heart image refers to the heart edge contour and the image area inside the heart edge contour, and the background image refers to the image area outside the heart edge contour.
In the acquisition process of the two-dimensional echocardiogram, ultrasonic sound beams generated by the probe enter the chest wall and then are scanned in a sector shape, and sectional views of different layers and directions of the heart can be obtained according to different positions and angles of the probe. Typically, a two-dimensional echocardiogram is an apical four-chamber view or an apical two-chamber view.
When the apical four-chamber image is collected, the probe is placed at the apical pulsation and points to the right sternoclavicular joint. The apical four-chamber view shows the structure of the left atrium, left ventricle, right atrium, and right ventricle, wherein the left ventricle is located at the upper right of the heart image.
When the apical two-chamber image is collected, the probe is also placed at the apical pulsation position, and the inversion of the clock is carried out, so that the scanning plane does not pass through the ventricular septum. The apical two-chamber view shows the structure of the left atrium and the left ventricle, wherein the left ventricle is located above the heart image.
It should be noted that a two-dimensional echocardiogram acquired over a continuous period of time is a set of image sequences. Each image corresponds to a point in time of the cardiac cycle. The heart repeats a diastolic-systolic motion process, with a cardiac cycle being the time from one end diastole to the next, or from one end systole to the next.
In the related art, an image of the end diastole and an image of the end systole are selected from an image sequence of a two-dimensional echocardiogram by an artificial experience. The left ventricular contours are then manually traced on the selected image, resulting in corresponding left ventricular volumes from the left ventricular contours. In this way, errors are inevitably introduced in the selection of the image and the determination of the left ventricle contour, so that the accuracy of the measurement result of the left ventricle ejection fraction EF is affected. While also affecting the accuracy of other cardiac data measurements related to the left ventricular ejection fraction EF.
In the method for acquiring cardiac data provided by the embodiment of the invention, the speckle tracking technology is utilized to automatically and accurately acquire the left ventricle contour in each image of the two-dimensional echocardiogram, so that the acquisition time of the left ventricle contour can be shortened, the accuracy of the acquired left ventricle contour can be improved, and the accuracy of the value of the left ventricle ejection fraction EF acquired according to the left ventricle contour can be improved. On the basis of this, the accuracy of other cardiac data related to the left ventricular ejection fraction EF can also be improved.
The following describes the method for acquiring cardiac data according to the present invention by way of example.
Fig. 1 is a flowchart illustrating a method for acquiring cardiac data according to an embodiment of the present invention. The method for acquiring cardiac data can be applied to an ultrasonic imaging device. As shown in fig. 1, the method of acquiring cardiac data may include:
s101, acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images.
S102, determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm.
S103, determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
For example, the target cardiac data value may be a left ventricular ejection fraction value of the heart.
Before step S101 is performed, acquisition parameters may be set in advance. The acquisition parameters may include an acquisition time length (i.e., a continuous time length in step S101), a frame rate (i.e., the number of images acquired per second), a type of the two-dimensional echocardiogram, and the like.
In one example, the acquisition duration is 3 seconds, the frame rate is 30HZ/s (hertz per second), and the category of two-dimensional echocardiograms is apical four-chamber mapping. Thus, through step S101, a 90(3 × 30) frame ultrasound image can be acquired.
It should be noted that the acquisition period needs to be longer than one cardiac cycle. Thus, it can be ensured that the acquired image sequence can contain relatively accurate images of the end diastole and the end systole.
Since different persons may have different heart rates and heart cycles, to ensure that the acquisition duration can be greater than one heart cycle, the acquisition duration may be set to a value greater than the longest known heart cycle, or to a value much greater than the possible upper limit of the heart cycle.
Of course, the number of images to be processed is increased due to the long acquisition time, which affects the measurement speed, and the acquisition time can be limited within a reasonable range.
The cardiac cycle may be derived from the heart rate. For example, the heart rate is 75 beats per minute on average, and the average duration of each cardiac cycle is 0.8(60/75) seconds.
In an exemplary implementation process, before step S102, the method may further include:
based on a preset enhancement algorithm, increasing the gray difference between the heart edge area and the background area of each image in the two-dimensional echocardiogram to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram; step S102 then comprises: and determining the edge contour of the left ventricle of the enhanced image corresponding to each image in the two-dimensional echocardiogram by using a speckle tracking algorithm.
The enhancement algorithm may employ any image enhancement algorithm now or hereafter that may be present. For example, the enhancement algorithm may be a spatial domain enhancement algorithm or a frequency domain enhancement algorithm. The spatial domain enhancement algorithm directly processes the gray scale of pixels in the image, and the frequency domain enhancement algorithm processes coefficients in a certain transformation domain of the image, and then obtains an enhanced image through inverse transformation.
In one example, the enhancement algorithm may employ a contrast-boosting algorithm, a Gamma correction algorithm, a histogram equalization algorithm, a homomorphic filtering algorithm, or the like.
In another example, a histogram enhancement algorithm may be used to enhance the grayscale of the image.
Two concepts in the histogram enhancement algorithm are explained first: grey values and grey levels. The gray value is the value of a pixel point on the image, and the range of the value is 0-255. The gray scale is a gray scale, and the total number of the gray scale is 0 to 255 and 256 levels.
The process of the histogram enhancement algorithm is to transform an image with known gray scale probability distribution into a new image with uniform gray scale probability distribution. During processing, it assigns more gray levels where there are more pixels and fewer gray levels where there are fewer pixels, so that the contrast of the densest regions in the histogram increases, exposing the previously hidden details.
The process of the histogram enhancement algorithm is as follows:
(a) and calculating a histogram [ i ] of the original image f (x, y), wherein i is the gray level of the image.
For example, assuming that 90 frames of images D0 to D89 are captured in step S101, histograms corresponding to the images D0 to D89 are calculated using the images D0 to D89 as the original images f (x, y).
The abscissa of the histogram is gray level (0-255), and the ordinate is the number of pixels located at each gray level. For example, if there are 200 pixels located at a gray level of 100 in one graph, the value of the ordinate is 200 when the abscissa is 100 in the histogram.
(b) The scale factor α is calculated to be 255/N, N being the total number of pixels of the image, and 255 being the range of gray levels.
The gray values of pixel points in the image are uniformly distributed on 0-255 gray levels, and the level range alpha which should be distributed by each pixel point is calculated.
(c) For all gray levels i present, a cumulative histogram c i is calculated.
c[i]＝c[i-1]+α*histogram[i](2)
c[0]＝α*histogram[0]。
In this step, gray levels are redistributed to the image, and the number of pixels with gray value of 0 in the original image is histogram [0 ].
α is a range of gray levels to be assigned to one pixel, and c [0] ═ α histogram [0] is a gray level value of the pixel having a gray level value of 0 in the entire image after being reassigned. Assuming that the gray scale range allocated to the pixel with the gray scale value of 0 is c [0] ═ 5, then the gray scale value of c [1] is allocated to the gray scale levels after 5, c [1] + α histogram [1], and so on, and the gray scale range after each gray scale value is reallocated is obtained.
(d) And calculating the value of the gray level g (x, y) output by the pixel point (x, y).
g(x,y)＝c[(x,y)](3)
The step is to calculate the gray scale value after equalization, where f (x, y) is the gray scale value of the original image, and if f (x, y) is 100, the abscissa of the pixel point (x, y) in the histogram is 100, the gray scale value after redistribution of the pixel point (x, y) is c [100], that is, the gray scale value g (x, y) of the pixel point (x, y) after equalization is c [100 ].
After the enhancement processing, the edge characteristics of the image are more obvious, and the edge detection of the cardiac image is more facilitated.
In an exemplary implementation process, based on a preset enhancement algorithm, before increasing a gray difference between a heart edge region and a background region of each image in the two-dimensional echocardiogram and obtaining an enhanced image corresponding to each image in the two-dimensional echocardiogram, the method may further include:
carrying out noise reduction processing on each image in the two-dimensional echocardiogram by adopting a preset denoising algorithm to obtain a denoised image corresponding to each image;
based on a preset enhancement algorithm, enhancing the gray scale of the heart edge area of each image in the two-dimensional echocardiogram to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram, wherein the method comprises the following steps:
and respectively carrying out image enhancement processing on each de-noised image by using a preset enhancement algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram.
Due to the specific imaging mechanism of the ultrasound and the detected tissue nonuniformity, the ultrasound image is interfered by various noises, and the detection judgment of the heart image edge is influenced. In this example, the ultrasound image is first denoised to remove background information and noise in the ultrasound image, so that the obtained cardiac ultrasound image is more obvious. And image enhancement processing is carried out on the basis of the de-noised image, so that more accurate heart edge contour can be obtained.
The denoising algorithm can adopt a spatial domain filtering algorithm or a frequency domain filtering algorithm. The spatial domain filtering algorithm comprises a mean filtering algorithm, a median filtering algorithm, a Gaussian filtering algorithm and the like. In the frequency domain filtering algorithm, wavelet transform is most typical. In the embodiment of the present invention, any denoising algorithm may be adopted, and the specific selection of the denoising algorithm in the present invention is not limited.
In step S102, the blob tracking algorithm tracks the change in location of the blob over each frame of image by identifying and extracting the characteristic blobs within the myocardium. Step S102 will be described in detail later herein.
In one example, the speckle tracking algorithm may be performed on the basis of images of a two-dimensional echocardiogram.
In another example, the speckle tracking algorithm may be based on an enhanced image of each image of the two-dimensional echocardiogram.
In another example, the speckle tracking algorithm may be based on de-noised, enhanced images of the two-dimensional echocardiogram.
Through the step S102, the left ventricle edge contour in each image of the two-dimensional echocardiogram can be automatically and intelligently determined, the left ventricle edge contour does not need to be manually traced, manual operation is reduced, time is saved, the accuracy of the left ventricle edge contour can be improved, and therefore the accuracy of the left ventricle ejection fraction calculated based on the left ventricle edge contour is higher.
In one exemplary implementation, the target cardiac data value is a left ventricular ejection fraction value, and step S103 includes:
acquiring the left ventricle volume in each image according to the edge contour of the left ventricle in each image;
finding out all left ventricle volumes of a complete cardiac cycle from the left ventricle volumes of the obtained images;
finding out the maximum volume value of the left ventricle and the minimum volume value of the left ventricle in all the left ventricle volumes of the found complete cardiac cycle, taking the found maximum volume value as an end diastole volume EDV value, and taking the found minimum volume value as an end systole volume ESV value;
and calculating the left ventricular ejection fraction value of the heart of the target object according to the calculation rule of the left ventricular ejection fraction value, the EDV value and the ESV value.
In one example, all left ventricular volumes of a complete cardiac cycle are found from the left ventricular volumes of the acquired images, including:
generating a curve graph of the change of the left ventricle volume along with time by using the left ventricle volume in each acquired image;
determining a curve section corresponding to a complete cardiac cycle on the generated curve graph;
all left ventricular volumes corresponding to the curve segment are determined as all left ventricular volumes of a complete cardiac cycle.
An example of generating a graph of left ventricular volume versus time using left ventricular volume in each acquired image is shown in fig. 5. Fig. 5 is a graph of left ventricular volume versus time. In fig. 5, the horizontal axis represents time, and the vertical axis represents left ventricular volume.
The calculation rule of the left ventricular ejection fraction value is shown in the foregoing formula (1).
The EDV value is the maximum value of the left ventricular volume in all images of a complete cardiac cycle and the ESV value is the minimum value of the left ventricular volume in all images of a complete cardiac cycle. Because the volume of the left ventricle is maximal at end diastole and minimal at end systole during a cardiac cycle.
It should be noted that the EDV value determined by the above steps may not be the actual EDV value, but is the volume value closest to the actual EDV value among the left ventricle volumes of all the acquired images. Similarly, the ESV value determined by the above steps is the volume value closest to the actual ESV value among the left ventricular volumes of all the acquired images.
The larger the frame rate when acquiring the two-dimensional echocardiogram, the closer the EDV value determined through the above steps is to the actual EDV value, and the closer the ESV value determined through the above steps is to the actual ESV value, and accordingly, the more accurate the value of the left ventricular ejection fraction EF obtained by measurement is. Thus, in one exemplary implementation, the frame rate at which the two-dimensional echocardiogram is acquired may be set according to the required accuracy of the measurements. I.e. if the accuracy of the required measurement results is high, a higher frame rate is set, e.g. greater than the first frame rate threshold; if the required accuracy of the measurement is not very high, a relatively small frame rate is set, e.g. greater than a second frame rate threshold, wherein the second frame rate threshold is smaller than the first frame rate threshold.
Through the steps, the obtained maximum volume value of the left ventricle is used as the EDV value, the minimum volume value is used as the ESV value, and the left ventricular ejection fraction EF is automatically obtained according to the EDV value and the ESV value. Because the accuracy of the EDV value and the ESV value in step S103 is higher than that of the EDV value and the ESV value obtained by artificially tracing the left ventricular outline, the accuracy of the measurement result of the left ventricular ejection fraction can be effectively improved.
In the embodiment shown in fig. 1, in the process of acquiring cardiac data, a two-dimensional echocardiogram of more than one cardiac cycle is acquired, the edge profile of the left ventricle in each image of the two-dimensional echocardiogram is automatically and intelligently determined, and target cardiac data values such as the left ventricle ejection fraction EF are automatically determined according to the edge profile of the left ventricle, and the automatic and intelligent operation of the device is utilized, so that the manual operation is reduced, on one hand, the time of the whole measurement process is shortened, the measurement speed is improved, and on the other hand, errors caused by human introduction are also reduced, and therefore, the accuracy of the measurement result can be improved.
The foregoing step S102 will be described in detail.
In an exemplary implementation, step S102 may include:
acquiring a heart edge contour in each image by using a speckle tracking algorithm;
and determining the edge contour of the left ventricle in each image according to the position relation between the edge contour of the left ventricle and the edge contour of the heart.
Fig. 2 is a diagram illustrating another example of a flow chart of a method for acquiring cardiac data according to an embodiment of the present invention. The present embodiment provides one exemplary implementation of obtaining a cardiac edge contour in each image using a speckle tracking algorithm. As shown in fig. 2, in this embodiment, acquiring the cardiac edge contour in each image by using the speckle tracking algorithm may include:
s201, extracting Feature points in each image based on a Scale Invariant Feature Transform (SIFT) algorithm, and generating SIFT Feature vectors of the Feature points, wherein the Feature points are located on the heart edge.
For example, suppose that the images D0 to D89 are subjected to denoising and enhancement processing to obtain images E0 to E89, and for the image E0, feature points G0 and G1 … … G20 of the center and the heart edge of the image E0 are extracted, and SIFT feature vectors T0 and T1 … … T20 of G0 and G1 … … G20 are generated, respectively. Similarly, for the images E1 to E89, feature points can be extracted and SIFT feature vectors can be generated by the same operation as for the image E0.
Wherein the heart margin includes the margin of the outer contour of the heart and the margin of the inner structure of the heart the cross-shaped structure inside the heart for separating the two atria and ventricles in an apical four-chamber diagram-see for example fig. 6, fig. 6 is an exemplary diagram of the heart margin of an apical four-chamber diagram, and in fig. 6, the heart margin of an apical four-chamber diagram includes the margin of the outer contour of the heart and the cross-shaped structure inside the heart for separating the two atria and ventricles. The area enclosed by the dashed line in fig. 6 is the left ventricle.
S202, two frames of images are selected from all the images and are respectively used as a first image to be matched and a second image to be matched.
S203, for each feature point in the first image to be matched, calculating Euclidean distances between the feature point and each feature point in the second image to be matched according to the SIFT feature vector of the feature point and the SIFT feature vector of each feature point in the second image to be matched, and determining the matching feature point of the feature point in the second image to be matched based on the minimum Euclidean distance and the next minimum Euclidean distance.
S204, after the feature points of all the images are matched, the feature points with the number of the matched feature points larger than a preset value are searched, and the searched feature points and the matched feature points thereof are used as tracking points.
And S205, extracting the outline of the heart edge by using the tracking points in the image for each frame of image.
The SIFT algorithm has strong matching capability, can extract stable characteristics, and can better solve the matching problem between two images under the conditions of translation, rotation, affine transformation, visual angle transformation and illumination intensity transformation.
In an exemplary implementation, step S201 may include the following sub-steps:
(1) extracting feature points of cardiac edges
Taking the image E0 as an example, the process of extracting the feature points of the heart edge is as follows:
performing convolution operation on the image E0 and Gaussian kernels under multiple different scale space factors to obtain n scale spaces (each scale space can be represented by a scale space function, and each scale space corresponds to one image) of the image E0, wherein the n scale spaces are sequentially arranged to form a Gaussian pyramid of the image E0, and the number of layers of the Gaussian pyramid is the same as the number of the scale spaces;
subtracting images corresponding to two adjacent scale spaces in the Gaussian pyramid to obtain n-1 difference images (the difference images can be represented by functions), and arranging the difference images in sequence to form the Gaussian difference pyramid of the image E0; for example, the layer 2 image in the Gaussian pyramid is subtracted from the layer 1 image in the Gaussian pyramid to obtain a layer 1 differential image in the Gaussian differential pyramid, the layer 2 image in the Gaussian pyramid is subtracted from the layer 3 image in the Gaussian pyramid to obtain a layer 2 differential image in the Gaussian Differential (DOG) pyramid, and so on;
detecting extreme points in the Gaussian difference pyramid by using the Gaussian difference pyramid, wherein the method comprises the following steps: comparing DOG values of each pixel point with all adjacent points of the pixel point, if the DOG values of all the adjacent points are larger than or smaller than the DOG value of the pixel point, the pixel point is a local extreme point, and the position and the scale of the pixel point are recorded, wherein the adjacent points comprise the adjacent point of the image of the layer of the pixel point and the adjacent point of the image of the adjacent layer of the image of the layer;
and removing the extreme points with low contrast and unstable edge response points from all the extreme points of the Gaussian difference pyramid, and taking the residual extreme points as feature points. Thus, the matching stability can be enhanced, and the anti-noise capability can be improved.
Assigning each feature point a principal direction; for example, the direction can be assigned to the feature points by using an image gradient method: acquiring a gaussian image (obtained by convolving a scale-variable gaussian function with an original image (such as the image E0) closest to the scale-space factor according to the scale-space factor of the feature point; in the Gaussian image, the amplitude (gradient direction) and amplitude (gradient module value) and gradient of the image gradient in a region which takes the characteristic point as the center and takes a specified value as the radius are calculated by using finite difference, and the gradient direction is determined as the main direction of the characteristic point;
generating SIFT feature vectors (SIFT feature vectors are a group of vectors used for describing feature points), and the method comprises the following steps: and partitioning the image region around the feature point, calculating a gradient histogram in each block region image, and generating a unique vector.
And finishing the feature point extraction. Each feature point has three pieces of information: position, scale, orientation, while the feature points possess translation, scaling and rotation invariance.
Steps S202 and S203 describe a matching process of feature points between images of the enhanced image sequence, for which the following is explained:
taking images E0 to E89 as an example, feature point matching between images means that feature point matching is performed between 90 frames of images E0 to E89.
In one example, the feature point matching between images may be sequential matching, i.e., matching in image sequence order. For example, for images E0 through E89, the image E1 is subjected to feature point matching with the image E0, the image E2 is subjected to feature point matching with the image E1, the image E3 is subjected to feature point matching with the image E2 … …, and so on until the images E89 and E88 are completely matched.
In another example, the feature point match between images may be a reverse order match, similar to the order match, but in reverse order. For example, for images E0 through E89, the image E89 is subjected to feature point matching with the image E88, the image E88 is subjected to feature point matching with the image E87, the image E87 is subjected to feature point matching with the image E86 … …, and so on until the images E1 and E0 are completely matched.
In another example, the feature point matching between the images may also be template matching, that is, taking a certain image as a matching template, and matching the template image with other images one by one to obtain a final matching result. For example, with respect to the images E0 to E89, the image E0 is used as a matching template, and the image E1 and the image E0 are subjected to feature point matching, the image E2 and the image E0 are subjected to feature point matching, and the image E89 and the image E0 are subjected to feature point matching by … …. It should be noted that the suitability of the template selection directly affects the matching quality.
In one example, the matching between the two images is performed based on the feature vectors of the feature points. Generally, the euclidean distance of the feature vectors of the feature points is used as the similarity determination measure of the feature points in the two images. If two feature points A and B are a pair of matching points, the Euclidean distance corresponding to the feature vectors of the two feature points A and B is the minimum firstly; secondly, the euclidean distance is still small to a certain extent, and needs to be significantly smaller than the distance from a to any feature vector except B, so as to represent the unique uniqueness of the correct matching. Therefore, the commonly used SIFT feature matching strategy is: determining a matching point pair according to the ratio of the closest distance to the next closest distance, which is as follows:
assuming that two images to be matched are respectively M and N, after feature points of the two images are extracted by SIFT algorithm, the sets of the feature points are respectively FmAnd FnThe dimension of the feature vector of the points is k, the feature vector of a feature point A in an image M is f (M)iThe feature vector of one feature point B in the image N is f (N)iWhere i ═ 1, 2.., k. The euclidean distance from the feature vector of point a to the feature vector of point B is:
finding the nearest distance point and the next nearest distance point P of the characteristic point A in the graph M by adopting a K-D tree (K in the K-D tree represents K dimensions) search algorithm1And P2，P1And P2Located in graph N.
The K-D tree algorithm can simplify the search process and improve the matching speed.
Suppose feature points A to P1Has an Euclidean distance of d1To P2Has an Euclidean distance of d2Definition of d1And d2The distance ratio function of (d) is:
ratio＝d1/d2(5)
if the ratio is less than epsilon, the matching is successful; if ratio is larger than or equal to epsilon, matching fails.
In step S204, the number of matched feature points refers to the number of feature points matched with each other, and the matched feature points are located on different enhanced images.
For example, for images E0-E89, A00、B00、C00Is the feature point in the image E0, and if matching is performed by template matching, image E0 is used as the matching template, A00Corresponding matching points A are respectively arranged on E1-E6001、A02……A60，B00Corresponding matching points B are respectively arranged on E1-E6901、B02……B69，C00Corresponding matching points C are respectively arranged on E1-E5001、C02……C50。A00、B00、C00The corresponding number of matching feature points is 61, 70, 51 respectively. Assuming a preset value of 58, in image E0, A00、B00To trace a point, C00Not a tracking point. Similarly, other tracking points in image E0 may be determined. In image E1, A01、B01To trace a point, C01Not a tracking point.
In step S205, the cardiac edge contour may be extracted by using the tracking points in the image: and for each frame of image, connecting all the tracking points in the frame of image according to a preset connecting rule to obtain the heart edge contour of the frame of image.
For example, for each frame of image, each tracking point is traversed from top to bottom and from left to right, the tracking point is directly connected with the tracking point in the neighborhood of the tracking point, and the heart edge contour of the frame of image is obtained after all the tracking points are connected.
In one exemplary implementation, determining the edge contour of the left ventricle in each image according to the position relationship between the edge contour of the left ventricle and the edge contour of the heart includes:
if the image is an apical four-chamber heart image, determining that the contour of a first region in the image is the edge contour of a left ventricle, wherein the first region is positioned at the upper right part of the image; alternatively, the first and second electrodes may be,
and if the image is the apical bicentric image, determining that the contour of a second region in the image is the edge contour of the left ventricle, wherein the second region is positioned at the upper part of the image.
Based on the above method embodiment, the embodiment of the present invention further provides corresponding apparatus, device, and storage medium embodiments. For detailed implementation of the embodiments of the apparatus, device and storage medium of the embodiments of the present invention, please refer to the corresponding descriptions in the foregoing method embodiments.
Fig. 3 is a functional block diagram of an apparatus for acquiring cardiac data according to an embodiment of the present invention. As shown in fig. 3, in this embodiment, the apparatus for acquiring cardiac data may include:
the acquisition module 310 is configured to acquire a two-dimensional echocardiogram of the target object within a continuous time period, where the continuous time period is longer than one cardiac cycle, and the two-dimensional echocardiogram includes multiple frames of images;
a contour determination module 320 for determining an edge contour of the left ventricle of each image in the two-dimensional echocardiogram using a speckle tracking algorithm;
and the numerical value determining module 330 is configured to determine a target cardiac data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
In one exemplary implementation, the contour determination module 320, when configured to determine the edge contour of the left ventricle of each image in the two-dimensional echocardiogram using the speckle tracking algorithm, is specifically configured to:
acquiring a heart edge contour in each image by using a speckle tracking algorithm;
and determining the edge contour of the left ventricle in each image according to the position relation between the edge contour of the left ventricle and the edge contour of the heart.
In an exemplary implementation, the contour determination module 320, when configured to obtain the cardiac edge contour in each image using the speckle tracking algorithm, is specifically configured to:
extracting feature points in each image based on a Scale Invariant Feature Transform (SIFT) algorithm, and generating SIFT feature vectors of the feature points, wherein the feature points are located at the edge of the heart;
selecting two frames of images from all the images to be used as a first image to be matched and a second image to be matched respectively;
calculating Euclidean distances between the feature points in the first image to be matched and the feature points in the second image to be matched according to the SIFT feature vectors of the feature points and the SIFT feature vectors of the feature points in the second image to be matched, and determining the matching feature points of the feature points in the second image to be matched based on the minimum Euclidean distance and the next minimum Euclidean distance;
after the matching of the feature points of all the images is finished, searching the feature points with the number of the matched feature points larger than a preset value, and taking the searched feature points and the matched feature points thereof as tracking points;
for each frame of image, the edge contour of the heart is extracted by using the tracking points in the image.
In an exemplary implementation, the contour determining module 320, when configured to extract the edge contour of the heart using the tracking points in the image for each frame of image, is specifically configured to:
and for each frame of image, connecting all the tracking points in the frame of image according to a preset connecting rule to obtain the heart edge contour of the frame of image.
In an exemplary implementation, the contour determining module 320 is specifically configured to, when configured to determine the edge contour of the left ventricle in each image according to the position relationship between the edge contour of the left ventricle and the edge contour of the heart:
if the image is an apical four-chamber heart image, determining that the contour of a first region in the image is the edge contour of a left ventricle, wherein the first region is positioned at the upper right part of the image; alternatively, the first and second electrodes may be,
and if the image is the apical bicentric image, determining that the contour of a second region in the image is the edge contour of the left ventricle, wherein the second region is positioned at the upper part of the image.
In one exemplary implementation, the apparatus further comprises:
the enhancement module is used for increasing the gray difference between the heart edge area and the background area of each image in the two-dimensional echocardiogram based on a preset enhancement algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram; the contour determination module 320 is specifically configured to determine an edge contour of the left ventricle of the enhanced image corresponding to each image in the two-dimensional echocardiogram using a speckle tracking algorithm.
In one exemplary implementation, the apparatus further comprises:
the denoising module is used for performing denoising processing on each image in the two-dimensional echocardiogram by adopting a preset denoising algorithm to obtain a denoised image corresponding to each image; the enhancement module is specifically configured to perform image enhancement processing on each denoised image by using a preset enhancement algorithm, so as to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram.
In one exemplary implementation, the target cardiac data value is a left ventricular ejection fraction value; the numerical value determination module 330 is specifically configured to:
acquiring the left ventricle volume in each image according to the edge contour of the left ventricle in each image;
finding out all left ventricle volumes of a complete cardiac cycle from the left ventricle volumes of the obtained images;
searching a maximum volume value and a minimum volume value from all left ventricle volumes of a found complete cardiac cycle, taking the maximum volume value as an end diastole volume EDV value, and taking the minimum volume value as an end systole volume ESV value;
and calculating the left ventricular ejection fraction value of the heart of the target object according to the calculation rule of the left ventricular ejection fraction value, the EDV value and the ESV value.
The embodiment of the invention also provides ultrasonic imaging equipment. Fig. 4 is a hardware configuration diagram of an ultrasound imaging apparatus provided in an embodiment of the present invention. As shown in fig. 4, the ultrasonic imaging apparatus includes: an internal bus 401, and a memory 402, a processor 403, and an external interface 404 connected through the internal bus.
The processor 403 is configured to read the machine-readable instructions in the memory 402 and execute the instructions to implement the following operations:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
target cardiac data values for the target object are determined from edge contours of the left ventricle of each image in the two-dimensional echocardiogram.
In one exemplary implementation, the determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram using a speckle tracking algorithm includes:
acquiring a heart edge contour in each image by using a speckle tracking algorithm;
and determining the edge contour of the left ventricle in each image according to the position relation between the edge contour of the left ventricle and the edge contour of the heart.
In one exemplary implementation, the obtaining a cardiac edge contour in each image using a speckle tracking algorithm includes:
extracting feature points in each image based on a Scale Invariant Feature Transform (SIFT) algorithm, and generating SIFT feature vectors of the feature points, wherein the feature points are located at the edge of the heart;
selecting two frames of images from all the images to be used as a first image to be matched and a second image to be matched respectively;
calculating Euclidean distances between the feature points in the first image to be matched and the feature points in the second image to be matched according to the SIFT feature vectors of the feature points and the SIFT feature vectors of the feature points in the second image to be matched, and determining the matching feature points of the feature points in the second image to be matched based on the minimum Euclidean distance and the next minimum Euclidean distance;
after the matching of the feature points of all the images is finished, searching the feature points with the number of the matched feature points larger than a preset value, and taking the searched feature points and the matched feature points thereof as tracking points;
for each frame of image, the edge contour of the heart is extracted by using the tracking points in the image.
In an exemplary implementation, for each frame of image, extracting an edge contour of the heart using the tracking points in the image includes:
and for each frame of image, connecting all the tracking points in the frame of image according to a preset connecting rule to obtain the heart edge contour of the frame of image.
In an exemplary implementation, the determining an edge contour of the left ventricle in each image according to a position relationship between the edge contour of the left ventricle and the edge contour of the heart includes:
if the image is an apical four-chamber heart image, determining that the contour of a first region in the image is the edge contour of a left ventricle, wherein the first region is positioned at the upper right part of the image; alternatively, the first and second electrodes may be,
and if the image is an apical bicentric image, determining that the contour of a second region in the image is a left ventricle edge contour, wherein the second region is positioned at the upper part of the image.
In an exemplary implementation, before determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using the speckle tracking algorithm, the method further includes:
based on a preset enhancement algorithm, increasing the gray difference between the heart edge area and the background area of each image in the two-dimensional echocardiogram to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram;
the determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm comprises the following steps:
and determining the edge contour of the left ventricle of the enhanced image corresponding to each image in the two-dimensional echocardiogram by using a speckle tracking algorithm.
In an exemplary implementation process, before increasing a gray difference between a heart edge region and a background region of each image in the two-dimensional echocardiogram based on a preset enhancement algorithm and obtaining an enhanced image corresponding to each image in the two-dimensional echocardiogram, the method further includes:
performing noise reduction processing on each image in the two-dimensional echocardiogram by adopting a preset denoising algorithm to obtain a denoised image corresponding to each image;
the enhancing the gray scale of the heart edge region of each image in the two-dimensional echocardiogram based on a preset enhancing algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram comprises:
and respectively carrying out image enhancement processing on each de-noised image by utilizing a preset enhancement algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram.
In one exemplary implementation, the target cardiac data value is a left ventricular ejection fraction value;
determining a target cardiac data value of the target object from an edge contour of a left ventricle of each image in the two-dimensional echocardiogram, comprising:
acquiring the left ventricle volume in each image according to the edge contour of the left ventricle in each image;
finding out all left ventricle volumes of a complete cardiac cycle from the left ventricle volumes of the obtained images; searching a maximum volume value and a minimum volume value from all left ventricle volumes of a found complete cardiac cycle, taking the maximum volume value as an end diastole volume EDV value, and taking the minimum volume value as an end systole volume ESV value;
and calculating the left ventricular ejection fraction value of the heart of the target object according to the calculation rule of the left ventricular ejection fraction value, the EDV value and the ESV value.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the program, when executed by a processor, implements the following operations:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
target cardiac data values for the target object are determined from edge contours of the left ventricle of each image in the two-dimensional echocardiogram.
In one exemplary implementation, the determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram using a speckle tracking algorithm includes:
acquiring a heart edge contour in each image by using a speckle tracking algorithm;
and determining the edge contour of the left ventricle in each image according to the position relation between the edge contour of the left ventricle and the edge contour of the heart.
In one exemplary implementation, the obtaining a cardiac edge contour in each image using a speckle tracking algorithm includes:
extracting feature points in each image based on a Scale Invariant Feature Transform (SIFT) algorithm, and generating SIFT feature vectors of the feature points, wherein the feature points are located at the edge of the heart;
selecting two frames of images from all the images to be used as a first image to be matched and a second image to be matched respectively;
calculating Euclidean distances between the feature points in the first image to be matched and the feature points in the second image to be matched according to the SIFT feature vectors of the feature points and the SIFT feature vectors of the feature points in the second image to be matched, and determining the matching feature points of the feature points in the second image to be matched based on the minimum Euclidean distance and the next minimum Euclidean distance;
after the matching of the feature points of all the images is finished, searching the feature points with the number of the matched feature points larger than a preset value, and taking the searched feature points and the matched feature points thereof as tracking points;
for each frame of image, the edge contour of the heart is extracted by using the tracking points in the image.
In an exemplary implementation, for each frame of image, extracting an edge contour of the heart using the tracking points in the image includes:
and for each frame of image, connecting all the tracking points in the frame of image according to a preset connecting rule to obtain the heart edge contour of the frame of image.
In an exemplary implementation, the determining an edge contour of the left ventricle in each image according to a position relationship between the edge contour of the left ventricle and the edge contour of the heart includes:
if the image is an apical four-chamber heart image, determining that the contour of a first region in the image is the edge contour of a left ventricle, wherein the first region is positioned at the upper right part of the image; alternatively, the first and second electrodes may be,
and if the image is an apical bicentric image, determining that the contour of a second region in the image is a left ventricle edge contour, wherein the second region is positioned at the upper part of the image.
In an exemplary implementation, before determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using the speckle tracking algorithm, the method further includes:
based on a preset enhancement algorithm, increasing the gray difference between the heart edge area and the background area of each image in the two-dimensional echocardiogram to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram;
the determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm comprises the following steps:
and determining the edge contour of the left ventricle of the enhanced image corresponding to each image in the two-dimensional echocardiogram by using a speckle tracking algorithm.
In an exemplary implementation process, before increasing a gray difference between a heart edge region and a background region of each image in the two-dimensional echocardiogram based on a preset enhancement algorithm and obtaining an enhanced image corresponding to each image in the two-dimensional echocardiogram, the method further includes:
performing noise reduction processing on each image in the two-dimensional echocardiogram by adopting a preset denoising algorithm to obtain a denoised image corresponding to each image;
the enhancing the gray scale of the heart edge region of each image in the two-dimensional echocardiogram based on a preset enhancing algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram comprises:
and respectively carrying out image enhancement processing on each de-noised image by utilizing a preset enhancement algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram.
In one exemplary implementation, the target cardiac data value is a left ventricular ejection fraction value;
determining a target cardiac data value of the target object from an edge contour of a left ventricle of each image in the two-dimensional echocardiogram, comprising:
acquiring the left ventricle volume in each image according to the edge contour of the left ventricle in each image;
finding out all left ventricle volumes of a complete cardiac cycle from the left ventricle volumes of the obtained images; searching a maximum volume value and a minimum volume value from all left ventricle volumes of a found complete cardiac cycle, taking the maximum volume value as an end diastole volume EDV value, and taking the minimum volume value as an end systole volume ESV value;
and calculating the left ventricular ejection fraction value of the heart of the target object according to the calculation rule of the left ventricular ejection fraction value, the EDV value and the ESV value.
For the device and apparatus embodiments, as they correspond substantially to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution in the specification. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Other embodiments of the present description will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the specification being indicated by the following claims.
It will be understood that the present description is not limited to the precise arrangements described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present description is limited only by the appended claims.
The above description is only a preferred embodiment of the present disclosure, and should not be taken as limiting the present disclosure, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (10)
1. A method of acquiring cardiac data, the method comprising:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining an edge contour of a left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
and determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
2. The method according to claim 1, wherein said determining the edge contour of the left ventricle for each image in the two-dimensional echocardiogram using a speckle tracking algorithm comprises:
acquiring a heart edge contour in each image by using a speckle tracking algorithm;
and determining the edge contour of the left ventricle in each image according to the position relation between the edge contour of the left ventricle and the edge contour of the heart.
3. The method of claim 2, wherein obtaining the cardiac edge contour in each image using a speckle tracking algorithm comprises:
extracting feature points in each image based on a Scale Invariant Feature Transform (SIFT) algorithm, and generating SIFT feature vectors of the feature points, wherein the feature points are located at the edge of the heart;
selecting two frames of images from all the images to be used as a first image to be matched and a second image to be matched respectively;
calculating Euclidean distances between the feature points in the first image to be matched and the feature points in the second image to be matched according to the SIFT feature vectors of the feature points and the SIFT feature vectors of the feature points in the second image to be matched, and determining the matching feature points of the feature points in the second image to be matched based on the minimum Euclidean distance and the next minimum Euclidean distance;
after the matching of the feature points of all the images is finished, searching the feature points with the number of the matched feature points larger than a preset value, and taking the searched feature points and the matched feature points thereof as tracking points;
for each frame of image, the edge contour of the heart is extracted by using the tracking points in the image.
4. The method according to claim 3, wherein for each frame of image, extracting the edge contour of the heart by using the tracking points in the image comprises:
and for each frame of image, connecting all the tracking points in the frame of image according to a preset connecting rule to obtain the heart edge contour of the frame of image.
5. The method according to claim 2, wherein determining the edge contour of the left ventricle in each image according to the position relationship between the edge contour of the left ventricle and the edge contour of the heart comprises:
if the image is an apical four-chamber heart image, determining that the contour of a first region in the image is the edge contour of a left ventricle, wherein the first region is positioned at the upper right part of the image; alternatively, the first and second electrodes may be,
and if the image is an apical bicentric image, determining that the contour of a second region in the image is a left ventricle edge contour, wherein the second region is positioned at the upper part of the image.
6. The method according to claim 1, wherein prior to determining the edge contour of the left ventricle in each image of the two-dimensional echocardiogram using a speckle tracking algorithm, further comprising:
based on a preset enhancement algorithm, increasing the gray difference between the heart edge area and the background area of each image in the two-dimensional echocardiogram to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram;
the determining the edge contour of the left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm comprises the following steps:
and determining the edge contour of the left ventricle of the enhanced image corresponding to each image in the two-dimensional echocardiogram by using a speckle tracking algorithm.
7. The method according to claim 6, wherein before the increasing the gray scale difference between the heart edge region and the background region of each image in the two-dimensional echocardiogram based on the preset enhancement algorithm to obtain the enhanced image corresponding to each image in the two-dimensional echocardiogram, the method further comprises:
performing noise reduction processing on each image in the two-dimensional echocardiogram by adopting a preset denoising algorithm to obtain a denoised image corresponding to each image;
the enhancing the gray scale of the heart edge region of each image in the two-dimensional echocardiogram based on a preset enhancing algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram comprises:
and respectively carrying out image enhancement processing on each de-noised image by utilizing a preset enhancement algorithm to obtain an enhanced image corresponding to each image in the two-dimensional echocardiogram.
8. The method of any one of claims 1 to 7, wherein the target cardiac data value is a left ventricular ejection fraction value;
determining a target cardiac data value of the target object from an edge contour of a left ventricle of each image in the two-dimensional echocardiogram, comprising:
acquiring the left ventricle volume in each image according to the edge contour of the left ventricle in each image;
finding out all left ventricle volumes of a complete cardiac cycle from the left ventricle volumes of the obtained images; searching a maximum volume value and a minimum volume value from all left ventricle volumes of a found complete cardiac cycle, taking the maximum volume value as an end diastole volume EDV value, and taking the minimum volume value as an end systole volume ESV value;
and calculating the left ventricular ejection fraction value of the heart of the target object according to the calculation rule of the left ventricular ejection fraction value, the EDV value and the ESV value.
9. An apparatus for obtaining cardiac data, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
a contour determination module for determining an edge contour of a left ventricle of each image in the two-dimensional echocardiogram using a speckle tracking algorithm;
and the numerical value determining module is used for determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
10. An ultrasound imaging device comprising a processor and a memory for storing executable instructions of the processor;
the processor is configured to:
acquiring a two-dimensional echocardiogram of a target object in a section of continuous time length, wherein the continuous time length is more than one cardiac cycle, and the two-dimensional echocardiogram comprises a plurality of frames of images;
determining an edge contour of a left ventricle of each image in the two-dimensional echocardiogram by using a speckle tracking algorithm;
and determining a target heart data value of the target object according to the edge contour of the left ventricle of each image in the two-dimensional echocardiogram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899879.0A CN110664435A (en) | 2019-09-23 | 2019-09-23 | Method and device for acquiring cardiac data and ultrasonic imaging equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899879.0A CN110664435A (en) | 2019-09-23 | 2019-09-23 | Method and device for acquiring cardiac data and ultrasonic imaging equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110664435A true CN110664435A (en) | 2020-01-10 |
Family
ID=69077558
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910899879.0A Pending CN110664435A (en) | 2019-09-23 | 2019-09-23 | Method and device for acquiring cardiac data and ultrasonic imaging equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110664435A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112656445A (en) * | 2020-12-18 | 2021-04-16 | 青岛海信医疗设备股份有限公司 | Ultrasonic device, ultrasonic image processing method and storage medium |
| CN113951928A (en) * | 2020-12-31 | 2022-01-21 | 深圳北芯生命科技股份有限公司 | System and method for measuring heart rate value by using ultrasonic image |
| CN114758159A (en) * | 2022-06-13 | 2022-07-15 | 迪非液压科技江苏有限公司 | Cutting control method for hydraulic brake cutting process |
| US11610312B2 (en) | 2021-03-10 | 2023-03-21 | Acer Incorporated | Image processing apparatus for evaluating cardiac images and ventricular status identification method |
| US11744542B2 (en) | 2021-03-17 | 2023-09-05 | Acer Incorporated | Method for evaluating movement state of heart |
| US11844655B2 (en) | 2021-03-17 | 2023-12-19 | Acer Incorporated | Method for estimating ventricular volume |
| CN117243637B (en) * | 2023-10-19 | 2024-04-19 | 河北港口集团有限公司秦皇岛中西医结合医院 | Method for identifying echocardiography images |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6674879B1 (en) * | 1998-03-30 | 2004-01-06 | Echovision, Inc. | Echocardiography workstation |
| US20070167809A1 (en) * | 2002-07-22 | 2007-07-19 | Ep Medsystems, Inc. | Method and System For Estimating Cardiac Ejection Volume And Placing Pacemaker Electrodes Using Speckle Tracking |
| CN101404940A (en) * | 2006-03-21 | 2009-04-08 | 皇家飞利浦电子股份有限公司 | Echocardiographic apparatus and method for analysis of cardiac dysfunction |
| CN101527047A (en) * | 2008-03-05 | 2009-09-09 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for detecting tissue boundaries by use of ultrasonic images |
| US20110310964A1 (en) * | 2010-06-19 | 2011-12-22 | Ibm Corporation | Echocardiogram view classification using edge filtered scale-invariant motion features |
| CN103429164A (en) * | 2012-03-30 | 2013-12-04 | 东芝医疗系统株式会社 | Ultrasonic diagnostic device, image processing device, and image processing method |
| CN103648402A (en) * | 2012-03-30 | 2014-03-19 | 株式会社东芝 | Ultrasonic diagnostic device, image processing device, and image processing method |
| CN106651827A (en) * | 2016-09-09 | 2017-05-10 | 浙江大学 | Fundus image registering method based on SIFT characteristics |
| CN108882917A (en) * | 2016-05-30 | 2018-11-23 | 深圳迈瑞生物医疗电子股份有限公司 | A kind of heart volume discriminance analysis system and method |
| CN109414205A (en) * | 2016-02-24 | 2019-03-01 | 顾昊天 | The measurement of heart first stage ejection fraction |
-
2019
- 2019-09-23 CN CN201910899879.0A patent/CN110664435A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6674879B1 (en) * | 1998-03-30 | 2004-01-06 | Echovision, Inc. | Echocardiography workstation |
| US20070167809A1 (en) * | 2002-07-22 | 2007-07-19 | Ep Medsystems, Inc. | Method and System For Estimating Cardiac Ejection Volume And Placing Pacemaker Electrodes Using Speckle Tracking |
| CN101404940A (en) * | 2006-03-21 | 2009-04-08 | 皇家飞利浦电子股份有限公司 | Echocardiographic apparatus and method for analysis of cardiac dysfunction |
| CN101527047A (en) * | 2008-03-05 | 2009-09-09 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for detecting tissue boundaries by use of ultrasonic images |
| US20110310964A1 (en) * | 2010-06-19 | 2011-12-22 | Ibm Corporation | Echocardiogram view classification using edge filtered scale-invariant motion features |
| CN103429164A (en) * | 2012-03-30 | 2013-12-04 | 东芝医疗系统株式会社 | Ultrasonic diagnostic device, image processing device, and image processing method |
| CN103648402A (en) * | 2012-03-30 | 2014-03-19 | 株式会社东芝 | Ultrasonic diagnostic device, image processing device, and image processing method |
| CN109414205A (en) * | 2016-02-24 | 2019-03-01 | 顾昊天 | The measurement of heart first stage ejection fraction |
| CN108882917A (en) * | 2016-05-30 | 2018-11-23 | 深圳迈瑞生物医疗电子股份有限公司 | A kind of heart volume discriminance analysis system and method |
| CN106651827A (en) * | 2016-09-09 | 2017-05-10 | 浙江大学 | Fundus image registering method based on SIFT characteristics |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112656445A (en) * | 2020-12-18 | 2021-04-16 | 青岛海信医疗设备股份有限公司 | Ultrasonic device, ultrasonic image processing method and storage medium |
| CN112656445B (en) * | 2020-12-18 | 2023-04-07 | 青岛海信医疗设备股份有限公司 | Ultrasonic device, ultrasonic image processing method and storage medium |
| CN113951928A (en) * | 2020-12-31 | 2022-01-21 | 深圳北芯生命科技股份有限公司 | System and method for measuring heart rate value by using ultrasonic image |
| CN113951928B (en) * | 2020-12-31 | 2023-08-18 | 深圳北芯生命科技股份有限公司 | System and method for measuring heart rate value by utilizing ultrasonic image |
| US11610312B2 (en) | 2021-03-10 | 2023-03-21 | Acer Incorporated | Image processing apparatus for evaluating cardiac images and ventricular status identification method |
| US11744542B2 (en) | 2021-03-17 | 2023-09-05 | Acer Incorporated | Method for evaluating movement state of heart |
| US11844655B2 (en) | 2021-03-17 | 2023-12-19 | Acer Incorporated | Method for estimating ventricular volume |
| CN114758159A (en) * | 2022-06-13 | 2022-07-15 | 迪非液压科技江苏有限公司 | Cutting control method for hydraulic brake cutting process |
| CN117243637B (en) * | 2023-10-19 | 2024-04-19 | 河北港口集团有限公司秦皇岛中西医结合医院 | Method for identifying echocardiography images |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110664435A (en) | Method and device for acquiring cardiac data and ultrasonic imaging equipment | |
| JP4427548B2 (en) | Apparatus and method for analyzing locally deformable motion | |
| US8050478B2 (en) | Method and apparatus for tissue border detection using ultrasonic diagnostic images | |
| Detmer et al. | Matched filter identification of left-ventricular endocardial borders in transesophageal echocardiograms | |
| EP2392942B1 (en) | Cardiac flow quantification with volumetric imaging data | |
| US9147258B2 (en) | Methods and systems for segmentation in echocardiography | |
| KR20110128197A (en) | Automatic analysis of cardiac m-mode views | |
| Alessandrini et al. | A new technique for the estimation of cardiac motion in echocardiography based on transverse oscillations: A preliminary evaluation in silico and a feasibility demonstration in vivo | |
| Mazaheri et al. | Echocardiography image segmentation: A survey | |
| Cheng et al. | Watershed-presegmented snake for boundary detection and tracking of left ventricle in echocardiographic images | |
| CN106910194B (en) | Method for segmenting endocardium and epicardium in cardiac functional magnetic resonance image | |
| Yue et al. | Speckle tracking in intracardiac echocardiography for the assessment of myocardial deformation | |
| Skalski et al. | Heart segmentation in echo images | |
| Bosch et al. | Active appearance motion models for endocardial contour detection in time sequences of echocardiograms | |
| Maes et al. | Automated contour detection of the left ventricle in short axis view in 2D echocardiograms | |
| Skalski et al. | Left ventricle USG image segmentation using active contour model | |
| Lin et al. | Combinative multi-scale level set framework for echocardiographic image segmentation | |
| Choy et al. | Extracting endocardial borders from sequential echocardiographic images | |
| Bosch et al. | Overview of automated quantitation techniques in 2D echocardiography | |
| Ahn | Robust myocardial motion tracking for echocardiography: variational framework integrating local-to-global deformation | |
| Deopujari et al. | Left Ventricular segmentation of 2-D echocardiographic image: A survey | |
| Balaji et al. | Automatic border detection of the left ventricle in parasternal short axis view of echocardiogram | |
| Anwar et al. | Automatic Segmentation of Heart Cavity in Echocardiography Images: Two & Four-Chamber View Using Iterative Process Method | |
| Bosch et al. | Fully automated endocardial contour detection in time sequences of echocardiograms by three-dimensional active appearance models | |
| Morda et al. | Left-ventricular cavity automated-border detection using an autocovariance technique in echocardiography |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |