Ultrasonic image processing method, device and equipment and readable storage medium

Abstract

The invention discloses an ultrasonic image processing method, device and equipment and a readable storage medium in the technical field of computer vision, and the method comprises the steps that an ultrasonic image of a target object is acquired, the ultrasonic image comprises a tissue gray-scale image and a color blood flow image, and the color blood flow image is superposed on the tissue gray-scale image; identifying a target structure area of the target object based on the tissue gray scale image; performing color segmentation by using the color blood flow image to obtain a reflux color area corresponding to the reflux color; determining the intersection of the target structure region and the reflux color region as a reflux region; slicing an imaging region of the ultrasonic image to obtain related slices of a reflux region; and calculating the reflux area of the reflux region based on the related slices of the reflux region. The method has the technical effects that the reflux area measurement value is more accurate, the limitation is less, and the measurement is more convenient and simpler.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to an ultrasonic image processing method, apparatus, device and readable storage medium. Background Art

[0002] Valvular heart disease is one of the common cardiovascular diseases, which can cause various health risks. Doppler ultrasound is the most effective examination method for the diagnosis and evaluation of valvular regurgitation. Among them, color Doppler blood flow observation is one of the most commonly used diagnostic methods for regurgitation at present. The regurgitation area is the main index for judging the severity of valvular stenosis. Generally, the larger the regurgitation area, the more severe the regurgitation degree.

[0003] At present, the quantitative evaluation methods for the regurgitation area are the manual tracing measurement method and the proximal isovelocity surface area method (PISA) of the blood flow convergence method. Among them, the manual tracing method is affected by the manual selection of the contour line of the regurgitation area, with large measurement errors, poor repeatability of measurement results, and cumbersome operation; while the PISA method requires a clear contour of the isovelocity hemispherical shape of blood flow convergence, and is affected by factors such as the Nyquist velocity, the hemispherical shape of blood flow convergence, and adjacent structures. In addition, inaccurate measurement of the radius of the blood flow convergence area will also lead to large errors in the results, and it is not applicable to multiple beam regurgitations. That is, the PISA method has strong limitations, high complexity and poor measurement accuracy.

[0004] In summary, how to effectively solve problems such as the determination of the regurgitation area is a technical problem that those skilled in the art urgently need to solve at present. Summary of the Invention

[0005] The purpose of the present application is to provide an ultrasonic image processing method, apparatus, device and readable storage medium, with more accurate measurement values of the regurgitation area, fewer limitations, and more convenient and simple measurement.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] An ultrasonic image processing method, comprising:

[0008] Obtaining an ultrasonic image of a target object, wherein the ultrasonic image includes a tissue grayscale image and a color blood flow image, and the color blood flow image is superimposed on the tissue grayscale image;

[0009] Identifying a target structure area of the target object based on the tissue grayscale image;

[0010] Performing color segmentation using the color blood flow image to obtain a regurgitation color region corresponding to the regurgitation color;

[0011] Determining the intersection of the target structure area and the regurgitation color region as the regurgitation area;

[0012] Slice the imaging region of the ultrasound image to obtain relevant slices of the regurgitation region;

[0013] Calculate the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region.

[0014] Preferably, the color segmentation using the color Doppler flow image to obtain the regurgitation color region corresponding to the regurgitation color includes:

[0015] Convert the color space of the color Doppler flow image to the HSV color space;

[0016] Use the HSV color space to perform color segmentation on the color Doppler flow image to obtain the regurgitation color region.

[0017] Preferably, the slicing the imaging region of the ultrasound image to obtain relevant slices of the regurgitation region includes:

[0018] Slice the imaging region according to the distribution of the ultrasound imaging scan lines and the distribution of the sampling points;

[0019] According to the position of the regurgitation region in the imaging region, obtain the relevant slices of the regurgitation region from each slice of the imaging region.

[0020] Preferably, the calculating the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region includes:

[0021] Calculate the slice area according to the angle between the scan lines and the distance between the sampling points;

[0022] Combine the slice area and calculate the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region.

[0023] Preferably, the combining the slice area and calculating the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region includes:

[0024] Obtain the proportion of the regurgitation area in each relevant slice of the regurgitation region;

[0025] Use the proportion of the regurgitation area to perform a weighted sum of the slice areas of each relevant slice of the regurgitation region to obtain the regurgitation area.

[0026] Preferably, obtaining the proportion of the regurgitation area in each relevant slice of the regurgitation region includes:

[0027] Obtain the proportion of the pixels of the regurgitation color in each relevant slice of the regurgitation region;

[0028] Determine the proportion of the pixels as the proportion of the regurgitation area.

[0029] Preferably, the recognition of the target structure region of the target object based on the tissue grayscale image includes:

[0030] Using a target detection algorithm to recognize the target structure region of the target object.

[0031] Preferably, the target object is the heart and the target structure region is the atrial region.

[0032] Preferably, the use of the target detection algorithm to recognize the target structure region of the target object includes:

[0033] For mitral regurgitation, use the target detection algorithm to recognize the left atrial region in the tissue grayscale image;

[0034] For tricuspid regurgitation, use the target detection algorithm to recognize the right atrial region in the tissue grayscale image.

[0035] An ultrasonic image processing device includes:

[0036] An image acquisition module for acquiring an ultrasonic image of a target object, where the ultrasonic image includes a tissue grayscale image and a color flow image, and the color flow image is superimposed on the tissue grayscale image;

[0037] An intelligent recognition module for recognizing the target structure region of the target object based on the tissue grayscale image;

[0038] A color segmentation module for performing color segmentation using the color flow image to obtain a regurgitation color region corresponding to the regurgitation color;

[0039] A regurgitation region determination module for determining the intersection of the target structure region and the regurgitation color region as the regurgitation region;

[0040] A slicing module for slicing the imaging region of the ultrasonic image to obtain relevant slices of the regurgitation region;

[0041] A regurgitation area calculation module for calculating the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region.

[0042] An electronic device includes:

[0043] A memory for storing a computer program;

[0044] A processor for implementing the steps of the above ultrasonic image processing method when executing the computer program.

[0045] Preferably, the electronic device is an ultrasonic device.

[0046] A readable storage medium stores a computer program thereon, and when the computer program is executed by a processor, the steps of the above ultrasonic image processing method are implemented.

[0047] Applying the method provided by the embodiments of the present application, an ultrasonic image of a target object is obtained, wherein the ultrasonic image includes a tissue gray-scale image and a color blood flow image, and the color blood flow image is superimposed on the tissue gray-scale image; the target structure region of the target object is recognized based on the tissue gray-scale image; color segmentation is performed using the color blood flow image to obtain a reflux color region corresponding to the reflux color; the intersection of the target structure region and the reflux color region is determined as the reflux region; the imaging region of the ultrasonic image is sliced to obtain relevant slices of the reflux region; and the reflux area of the reflux region is calculated based on the relevant slices of the reflux region.

[0048] In the present application, first, an ultrasonic image of a target object is obtained. The ultrasonic image includes a tissue gray-scale image and a color blood flow image superimposed on the tissue gray-scale image. The target structure region of the target object is recognized based on the tissue gray-scale image. Since different colors are used in the color blood flow image to represent different blood flow directions, the reflux color region corresponding to the reflux color can be obtained by performing color segmentation on the color blood flow image. Taking the intersection of the reflux color region and the target structure region can obtain the reflux region. After the reflux region is determined, to avoid the irregular shape of the reflux region making it difficult to calculate its area, the imaging region of the ultrasonic image can be sliced, and then the reflux area of the reflux region can be calculated based on the relevant slices of the reflux region.

[0049] Technical effects of the present application: The reflux region is automatically recognized through technologies such as color segmentation, and the phased array imaging region is sliced and the reflux area is calculated using the area slicing method. Compared with the manual tracing measurement method, the present application is faster, more accurate, and has better measurement repeatability, not only improving the measurement efficiency but also reducing the manual measurement error; compared with the PISA measurement method, the present application is not affected by the Nyquist velocity, the measured values of the hemispherical shape of blood flow convergence and the radius of the blood flow convergence region, and the influence of adjacent structures, etc. The reflux area region is closer to the real situation, the measured value is more accurate, the limitations are fewer, and the measurement is more convenient and simple.

[0050] Correspondingly, the embodiments of the present application also provide an ultrasonic image processing device, equipment, and readable storage medium corresponding to the above ultrasonic image processing method, which have the above technical effects and will not be elaborated herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] To more clearly illustrate the technical solutions in the embodiments of the present application or in the related art, the following will briefly introduce the drawings required for use in the description of the embodiments or the related art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a flowchart of an ultrasonic image processing method in an embodiment of the present application;

[0053] Figure 2 It is a schematic diagram of a phased imaging area slice in an embodiment of the present application;

[0054] Figure 3 It is a schematic diagram of a regurgitant area measurement in an embodiment of the present application;

[0055] Figure 4 It is a schematic diagram of the structure of an ultrasonic image processing device in an embodiment of the present application;

[0056] Figure 5 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0057] Figure 6 It is a schematic diagram of the specific structure of an electronic device in an embodiment of the present application. Detailed implementation manners

[0058] To enable those skilled in the art to better understand the solutions of the present application, the following will further elaborate on the present application in conjunction with the drawings and specific implementation manners. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0059] Please refer to Figure 1 , Figure 1 It is a flowchart of an ultrasonic image processing method in an embodiment of the present application. The method includes the following steps:

[0060] S100. Obtain the ultrasonic image of the target object.

[0061] Among them, the ultrasonic image includes a tissue grayscale image and a color blood flow image, and the color blood flow image is superimposed on the tissue grayscale image.

[0062] Specifically, the ultrasonic image of the target object can be obtained through an ultrasonic imaging device. Among them, the target object can be the tissue where blood flow regurgitation needs to be found. For example, the target object can be the heart.

[0063] In this embodiment, an ultrasonic image can be directly and real-time acquired by an ultrasonic probe of an ultrasonic imaging device, or obtained from other devices / platforms through communication with other devices / platforms, or the ultrasonic image stored in a readable storage medium can be directly read to obtain the ultrasonic image.

[0064] Generally, an ultrasonic imaging device is provided with a B mode and a color flow mode (i.e., C mode). A tissue gray-scale image can be obtained through the B mode, and a color flow image can be obtained through the C mode. The specific process is as follows:

[0065] The ultrasonic probe is excited by a first transmit pulse and a second transmit pulse to emit a first ultrasonic beam (B-mode scanning beam) and a second ultrasonic beam (Doppler scanning beam) to a scanned target object. After a period of time, the first ultrasonic echo (i.e., B-mode ultrasonic echo) and the second ultrasonic echo (Doppler ultrasonic echo) reflected from the target object are received, and the first ultrasonic echo and the second ultrasonic echo are converted into electrical signals; the receiving circuit receives the electrical signals generated by the conversion of the ultrasonic probe, obtains the first ultrasonic echo signal and the second ultrasonic echo signal, and performs beam synthesis on these first ultrasonic echo signals and second ultrasonic echo signals. The beam synthesis is specifically to perform corresponding focusing delay, weighting, channel summation and other processes on the first ultrasonic echo signal and the second ultrasonic echo signal; then the first ultrasonic echo signal and the second ultrasonic echo signal are sent to a processor to perform signal processing for B-mode and C-mode imaging respectively, so as to obtain a tissue gray-scale image and a color flow image superimposed and displayed on the tissue gray-scale image.

[0066] For example: when the target object is the heart and the target structural area is the atrial area, for valvular regurgitation of the heart, mitral regurgitation and tricuspid regurgitation are mainly considered, and the mitral and tricuspid regurgitation conditions are observed from, including but not limited to, the apical four-chamber view. Taking the apical four-chamber view as an example, in the process of acquiring an ultrasonic image, the probe can be placed in the anterior chest wall area at the 3-4th intercostal space on the left edge of the sternum, with the marking point facing the right shoulder, the detection plane is basically parallel to the line connecting the right shoulder and the left rib, the ultrasonic probe beam points towards the patient's back direction, and the ultrasonic probe can be slid to find the parasternal long-axis view of the left ventricle. Along the long-axis view, slide along the left ventricle towards the apex. When the interventricular septum just disappears, rotate the ultrasonic probe by 90°-120°, that is, place the probe at the apical beat point, and the probe beam points towards the patient's right shoulder and towards the heart base, then the apical four-chamber view can be located. After locating the standard apical four-chamber view, the user places a sampling frame. For observing the mitral regurgitation condition, the sampling frame position should cover the left atrium, left ventricle, and mitral valve area; for observing the tricuspid regurgitation condition, the sampling frame position should cover the right atrium, right ventricle, and tricuspid valve area. After placing the sampling frame, color Doppler blood flow observation can be performed, and it can be seen that a color flow image is superimposed and displayed on the standard apical four-chamber view image (B image).

[0067] S101. Identify the target structure region of the target object based on the tissue grayscale image.

[0068] In this embodiment, the target structure region of the target object can be identified based on the tissue grayscale image first. Specifically, the target structure region can be identified according to the image features presented by the target structure in the tissue grayscale image.

[0069] In a specific implementation manner of this application, identifying the target structure region of the target object based on the tissue grayscale image includes: using a target detection algorithm to identify the target structure region of the target object. That is to say, when identifying the target structure region based on the tissue grayscale image, a target detection algorithm can be used. For example, an artificial intelligence model (AI) algorithm can be used to extract image features and identify the target structure region based on these features. The target detection algorithm can include traditional image processing methods, target detection algorithms based on traditional machine learning, and target detection algorithms based on deep learning.

[0070] Based on the method of traditional machine learning, the machine learning model can be trained first based on the collected ultrasonic sample images and the annotation results of the interested structure regions therein. The machine learning model can be, but is not limited to, models such as SVM, K-Means, and C-Means; the machine learning model can perform binary classification on the gray value or texture value of pixel points, or divide the image into grids and perform binary classification on the small images within the grids. The region with the highest classification probability for the relevant pixel points or small images within the grids is used as the above-mentioned target structure region.

[0071] Based on the method of deep learning, the deep learning model can also be trained first based on the collected ultrasonic sample images and the annotation results of the interested structure regions therein. The deep learning model can adopt a neural network model, such as, but not limited to, models such as RCNN, Faster RCNN, SSD, and YOLO; during the network training stage, the error between the detection result and the annotation result of the interested structure region in the iterative process will be calculated, and the weights in the network will be continuously updated with the aim of minimizing the error. This process will be repeated continuously to make the detection result gradually approach the true value, and then a trained model can be obtained; afterwards, the ultrasonic image (such as the above-mentioned tissue grayscale image) can be input into the trained model to identify the target structure region.

[0072] The above artificial intelligence model can include traditional machine learning models and deep learning models. If the target object is the heart and the target structure region is the atrial region, then using the target detection algorithm to identify the target structure region of the target object includes:

[0073] For mitral regurgitation, the left atrial region in the tissue gray-scale image is identified using a target detection algorithm.

[0074] For tricuspid regurgitation, the right atrial region in the tissue gray-scale image is identified using a target detection algorithm.

[0075] For example, when the mitral valve or tricuspid valve is insufficient, it can cause blood to flow backward from the ventricle to the atrium during cardiac contraction, forming regurgitation. Therefore, after obtaining the above-mentioned apical four-chamber view image, the atrial region can be identified based on the AI model, thereby initially locating the approximate region where regurgitation occurs. Specifically, for mitral regurgitation, the left atrial region is initially located; for tricuspid regurgitation, the right atrial region is initially located.

[0076] S102. Perform color segmentation on the color flow image to obtain the regurgitation color region corresponding to the regurgitation color.

[0077] Color flow imaging technology displays blood flow signals in color, and the pseudo-color coding consists of three basic colors: red, blue, and green. For example, blood flow towards the probe can be represented by red, and blood flow away from the probe can be represented by blue. The brightness of the color signal is proportional to the increase in blood flow velocity until the velocity reaches the Nyquist limit. To represent faster blood flow velocities, three colors can also be used to indicate the speed of blood flow. Blood flow towards the probe is represented by signals ranging from dark red to bright red. If the blood flow is even faster, it changes from red to yellow (a mixture of red and green), then from yellow to green, and the coexistence of the three colors represents different flow velocities. Blood flow away from the probe is represented by cyan and green for faster velocities.

[0078] When performing color segmentation on the color flow image, only the color belonging to the regurgitation color needs to be determined to perform color segmentation, thereby obtaining the regurgitation color region corresponding to the regurgitation color.

[0079] For example, depending on different acquisition operations, the regurgitation color can be red or blue. When performing segmentation, if the regurgitation color is red, the red region is segmented out as the regurgitation color region; if the regurgitation color is blue, the blue region is segmented out as the regurgitation color region. Specifically, how to implement color segmentation can refer to relevant color segmentation techniques and will not be elaborated here one by one.

[0080] In a specific embodiment of the present application, color segmentation is performed on a color flow image to obtain a reflux color region corresponding to the reflux color, which may include: obtaining scanning direction information; then using the scanning direction information to determine the reflux color; then segmenting the region corresponding to the reflux color from the color flow image and determining this region as the reflux color region; that is to say, the determination of the reflux color can be based on the scanning direction information. For example, when the probe orientation is the same as the normal blood flow direction, the reflux color is blue; when the probe orientation is opposite to the normal blood flow direction, the reflux color is red.

[0081] In a specific embodiment of the present application, color segmentation is performed using a color flow image to obtain a reflux color region corresponding to the reflux color, including:

[0082] Convert the color space of the color flow image to the HSV color space;

[0083] Use the HSV color space to perform color segmentation on the color flow image to obtain the reflux color region.

[0084] Considering that color flow images are usually saved in three color components of R, G, and B, but the RGB color space (RGB Color Space) represents the three quantities of hue, brightness, and saturation together, which is difficult to distinguish. It is not conducive to color segmentation. The HSV (Hue, Saturation, Value) color space describes colors through three characteristics of hue, saturation, and value, which is more in line with the way humans perceive colors. Moreover, there is only one color channel in the HSV space, which is more conducive to segmenting the specified color.

[0085] Therefore, in this embodiment, the color flow image can be first converted to the HSV color space for representation, and then color segmentation is performed on the converted image, so that the reflux color region can be obtained quickly and accurately. Of course, in practical applications, it is not limited to using the HSV color segmentation technology for color segmentation, and other color segmentation technologies can also be used for segmentation, which will not be listed one by one here.

[0086] S103. Determine the intersection of the target structure region and the reflux color region as the reflux region.

[0087] The reflux color region is the reflux region. Considering that the reflux information within the target structure region has practical reference value, it is necessary to take the intersection of the target structure region and the reflux color region, and then determine this intersection as the reflux region.

[0088] For example, considering that only the regurgitation area in the atrium needs to be considered in the ultrasonic image, and the regurgitation area in the atrium is the important index for determining valvular regurgitation. Therefore, after obtaining the atrium area and the regurgitation color area, the intersection of the two is obtained, and this intersection area is the regurgitation area corresponding to the atrium. Therefore, in this embodiment, this intersection is determined as the regurgitation area. That is, this regurgitation area is the area of regurgitation caused by tricuspid or mitral insufficiency.

[0089] S104. Slice the imaging area of the ultrasonic image to obtain relevant slices of the regurgitation area.

[0090] Since there are irregular phenomena in the regurgitation area, for the convenience of calculation, the imaging area of the ultrasonic image can be sliced. The slices that have an intersection with the regurgitation area are determined as the relevant slices of this regurgitation area. That is to say, the relevant slices of the regurgitation area include the slices completely located inside the regurgitation area and the slices only partially located in the regurgitation area.

[0091] For the size of the slices, it can be set and adjusted according to actual application requirements, and no specific limitation is made in this embodiment.

[0092] In a specific implementation manner of this application, slicing the imaging area of the ultrasonic image to obtain relevant slices of the regurgitation area includes:

[0093] Slice the imaging area according to the distribution of the ultrasonic imaging scan lines and the distribution of the sampling points;

[0094] Obtain relevant slices of the regurgitation area from the slices of the imaging area according to the position of the regurgitation area in the imaging area.

[0095] That is to say, when slicing the imaging area, the imaging area can be sliced specifically according to the distribution of the scan lines and the sampling points. Based on the position of the regurgitation area in the imaging area, the relevant slices of the regurgitation area can be found from each slice of the imaging area. As Figure 2 shown, after slicing the phased imaging area based on the scan lines and the sampling points, multiple fan-shaped slices can be obtained. It can be seen from the figure that longitudinal cutting is performed based on the scan lines and latitude direction cutting is performed based on the number of sampling points, so as to achieve slicing.

[0096] S105. Calculate the regurgitation area of the regurgitation area based on the relevant slices of the regurgitation area.

[0097] Specifically, that is, how many slices the regurgitation area covers, and the regurgitation area is calculated based on that many slices.

[0098] After slicing the phased imaging region, regular slices with accurately calculable areas can be obtained. Based on the slices with accurately calculable areas, the regurgitant area can be calculated. That is, by superimposing the areas of the slices within the regurgitant region, the regurgitant area can be obtained.

[0099] In a specific embodiment of the present application, calculating the regurgitant area of the regurgitant region based on the relevant slices of the regurgitant region includes:

[0100] Calculating the slice area according to the angle between the scan lines and the distance between the sampling points;

[0101] Combining the slice area and calculating the regurgitant area of the regurgitant region based on the relevant slices of the regurgitant region.

[0102] As Figure 2 shown, after slicing the imaging region, all the sliced slices are fan-shaped. Therefore, the fan-shaped calculation formula can be used for calculation. Specifically, the slice area can be calculated according to the angle between the scan lines and the distance between the sampling points.

[0103] According to the angle between the scan lines and the distance between the sampling points, and using the fan-shaped area formula, the area of each slice region can be obtained. That is, the slice region area Ai in the figure:

[0104] where θ is the angle between the scan lines, R i is the distance corresponding to the distal scan point, and R j is the distance corresponding to the proximal scan point.

[0105] After the slice area of each slice is determined, the regurgitant area of the regurgitant region can be calculated by superimposing the relevant slices.

[0106] In a specific embodiment of the present application, combining the slice area and calculating the regurgitant area of the regurgitant region based on the relevant slices of the regurgitant region includes:

[0107] Obtaining the proportion of the regurgitant region in each relevant slice of the regurgitant region;

[0108] Using the proportion of the regurgitant region to perform weighted summation of the slice areas of each relevant slice of the regurgitant region to obtain the regurgitant area.

[0109] Please refer to Figure 3 , Figure 3 The area within the curve circle in is a schematic diagram of a regurgitant region. It can be seen that there are multiple slices inside this regurgitant region, and some of these slices are completely surrounded inside the regurgitant region (not marked on this part of the slice), but there are also some that overlap partially with the regurgitant region (the proportion of the regurgitant region a 1 to a i)。For the slices enclosed within the regurgitation region, the entire corresponding area is counted as the area of the regurgitation region. For the partial slices that intersect with the regurgitation region, the ratio of the intersection of the slice and the regurgitation region to the complete slice needs to be obtained. Then, the area of the slice is counted as part of the regurgitation region according to this ratio.

[0110] Specifically: Obtain the proportion of the regurgitation region in each relevant slice of the regurgitation region, including: obtaining the proportion of the pixels of the regurgitation color in each relevant slice of the regurgitation region; then determine the pixel proportion as the proportion of the regurgitation region. That is, by counting the proportion of the pixels of the regurgitation color in the slice, the ratio of the intersection of the slice and the regurgitation region to the slice can be determined, and further the proportion of the regurgitation region can be obtained.

[0111] As Figure 3 shown, the region enclosed by the curve is the segmented regurgitation region, and calculate the ratio of the regurgitation region to each slice region. For example, the proportion of the regurgitation region of the slices enclosed by the regurgitation region is all 1. Suppose the calculated areas are SA 1 、SA 2 、SA 3 、…、SA i ; the areas of the slices that intersect with the regurgitation region are SR 1 、SR 2 、SR 3 、…、SR j , and the ratios of the proportion of the regurgitation region are α 1 、α 2 、α 3 、…、α j , then the calculation formula for the regurgitation area S is as follows: S = (SA 1 + SA 2 + SA 3 + … + SA i ) + (α 1 × SR 1 + α 2 × SR 2 + α 3 × SR 3 + … + α j × SR j ). It should be noted that for the slices not marked in the figure, the proportion of the corresponding regurgitation region is 1.

[0112] After obtaining the regurgitation area, the severity of the regurgitation condition can be determined, and it serves as an important reference for further observation and treatment.

[0113] Apply the method provided in the embodiments of the present application to obtain an ultrasonic image of a target object, where the ultrasonic image includes a tissue grayscale image and a color blood flow image, and the color blood flow image is superimposed on the tissue grayscale image; identify the target structure area of the target object based on the tissue grayscale image; perform color segmentation on the color blood flow image to obtain a reflux color area corresponding to the reflux color; determine the intersection of the target structure area and the reflux color area as the reflux area; slice the imaging area of the ultrasonic image to obtain relevant slices of the reflux area; calculate the reflux area of the reflux area based on the relevant slices of the reflux area.

[0114] In the present application, first, an ultrasonic image of a target object is obtained. The ultrasonic image includes a tissue grayscale image and a color blood flow image superimposed on the tissue grayscale image. The target structure area of the target object is identified based on the tissue grayscale image. Since different colors are used in the color blood flow image to represent different blood flow directions, the reflux color area corresponding to the reflux color can be obtained by performing color segmentation on the color blood flow image. Taking the intersection of the reflux color area and the target structure area can obtain the reflux area. After clarifying the reflux area, to avoid the difficulty of calculating its area due to the irregular shape of the reflux area, the imaging area of the ultrasonic image can be sliced, and then the reflux area of the reflux area can be calculated based on the relevant slices of the reflux area.

[0115] Technical effects of the present application: The reflux area is automatically identified through technologies such as color segmentation, and the phased array imaging area is sliced by the area slicing method and the reflux area is calculated. Compared with the manual tracing measurement method, the present application is faster, more accurate, and has better measurement repeatability, not only improving the measurement efficiency but also reducing the manual measurement error; compared with the PISA measurement method, the present application is not affected by the Nyquist velocity, the measurement of the hemispherical shape of blood flow convergence and the radius of the blood flow convergence area, and the influence of adjacent structures, etc. The reflux area is closer to the real situation, the measurement value is more accurate, the limitations are less, and the measurement is more convenient and simple.

[0116] Corresponding to the above method embodiment, the embodiments of the present application also provide an ultrasonic image processing device, and the ultrasonic image processing device described below can be mutually referred to with the ultrasonic image processing method described above.

[0117] See Figure 4 As shown, the device includes the following modules:

[0118] An image acquisition module 100, configured to acquire an ultrasonic image of a target object, where the ultrasonic image includes a tissue grayscale image and a color blood flow image, and the color blood flow image is superimposed on the tissue grayscale image;

[0119] An intelligent recognition module 101, configured to identify the target structure area of the target object based on the tissue grayscale image;

[0120] A color segmentation module 102, configured to perform color segmentation on a color blood flow image to obtain a reflux color region corresponding to a reflux color;

[0121] A reflux region determination module 103, configured to determine an intersection of a target structure region and the reflux color region as a reflux region;

[0122] A slicing module 104, configured to slice an imaging region of an ultrasonic image to obtain relevant slices of the reflux region;

[0123] A reflux area calculation module 105, configured to calculate a reflux area of the reflux region based on the relevant slices of the reflux region.

[0124] By applying the device provided in the embodiment of the present application, an ultrasonic image of a target object is obtained, where the ultrasonic image includes a tissue gray-scale image and a color blood flow image, and the color blood flow image is superimposed on the tissue gray-scale image; a target structure region of the target object is recognized based on the tissue gray-scale image; color segmentation is performed on the color blood flow image to obtain a reflux color region corresponding to a reflux color; an intersection of the target structure region and the reflux color region is determined as a reflux region; the imaging region of the ultrasonic image is sliced to obtain relevant slices of the reflux region; and a reflux area of the reflux region is calculated based on the relevant slices of the reflux region.

[0125] In the present application, first, an ultrasonic image of a target object is obtained. The ultrasonic image includes a tissue gray-scale image and a color blood flow image superimposed on the tissue gray-scale image. A target structure region of the target object is recognized based on the tissue gray-scale image. Since different colors are used in the color blood flow image to represent different blood flow directions, the color blood flow image can be color-segmented to obtain a reflux color region corresponding to a reflux color. By taking the intersection of the reflux color region and the target structure region, the reflux region can be obtained. After the reflux region is determined, to avoid the difficulty of calculating the area due to the irregular shape of the reflux region, the imaging region of the ultrasonic image can be sliced, and then the reflux area of the reflux region can be calculated based on the relevant slices of the reflux region.

[0126] Technical effects of the present application: The reflux region is automatically recognized through technologies such as color segmentation, and the phased array imaging region is sliced by an area slicing method and the reflux area is calculated. Compared with the manual tracing measurement method, the present application is faster, more accurate, and has better measurement repeatability, which not only improves the measurement efficiency but also reduces the manual measurement error; compared with the PISA measurement method, the present application is not affected by the Nyquist velocity, the measured values of the hemispherical shape of blood flow convergence and the radius of the blood flow convergence region, and the influence of adjacent structures, etc. The reflux area region is closer to the real situation, the measured values are more accurate, the limitations are less, and the measurement is more convenient and simple.

[0127] In a specific embodiment of the present application, the color segmentation module includes:

[0128] A spatial conversion unit for converting the color space of the color blood flow image to the HSV color space;

[0129] A color segmentation unit for performing color segmentation on the color blood flow image using the HSV color space to obtain a regurgitation color region.

[0130] In a specific embodiment of the present application, the slicing module includes:

[0131] A cutting unit for slicing the imaging region according to the distribution of the ultrasound imaging scan lines and the distribution of the sampling points;

[0132] A relevant slice determination unit for obtaining relevant slices of the regurgitation region from the slices of the imaging region according to the position of the regurgitation region in the imaging region.

[0133] In a specific embodiment of the present application, the regurgitation area calculation module includes:

[0134] A slice area calculation unit for calculating the slice area according to the angle between the scan lines and the distance between the sampling points;

[0135] A regurgitation area calculation unit for combining the slice area and calculating the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region.

[0136] In a specific embodiment of the present application, the regurgitation area calculation unit includes:

[0137] A regurgitation area ratio determination subunit for obtaining the regurgitation area ratio of each relevant slice of the regurgitation region;

[0138] A weighted summation subunit for using the regurgitation area ratio to perform weighted summation on the slice areas of each relevant slice of the regurgitation region to obtain the regurgitation area.

[0139] In a specific embodiment of the present application, the regurgitation area ratio determination subunit is specifically configured to obtain the pixel ratio of the regurgitation color in each relevant slice of the regurgitation region;

[0140] Determine the pixel ratio as the regurgitation area ratio.

[0141] In a specific embodiment of the present application, the intelligent recognition module is specifically configured to identify the target structure region of the target object using a target detection algorithm.

[0142] In a specific embodiment of the present application, the target object is the heart and the target structure region is the atrial region.

[0143] In a specific embodiment of the present application, the intelligent recognition module includes:

[0144] A left atrium recognition unit for mitral regurgitation, which uses a target detection algorithm to recognize the left atrium region in the tissue gray-scale image;

[0145] A right atrium recognition unit for tricuspid regurgitation, which uses a target detection algorithm to recognize the right atrium region in the tissue gray-scale image.

[0146] Corresponding to the above method embodiment, the embodiment of the present application also provides an electronic device, and an electronic device described below can be correspondingly referred to with an ultrasonic image processing method described above.

[0147] See Figure 5 As shown, the electronic device includes:

[0148] A memory 332 for storing computer programs;

[0149] A processor 322 for implementing the steps of the ultrasonic image processing method in the above method embodiment when executing the computer program.

[0150] Specifically, please refer to Figure 6 , Figure 6 which is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device may have relatively large differences due to configuration or performance, and may include one or more processors (central processing units, CPU) 322 (for example, one or more processors) and a memory 332. The memory 332 stores one or more computer programs 342 or data 344. Among them, the memory 332 can be short-term storage or persistent storage. The program stored in the memory 332 may include one or more modules (not marked in the figure), and each module may include a series of instruction operations on the data processing device. Further, the processor 322 can be set to communicate with the memory 332 and execute a series of instruction operations in the memory 332 on the electronic device 301.

[0151] The electronic device 301 may further include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input / output interfaces 358, and / or one or more operating systems 341.

[0152] The steps in the ultrasonic image processing method described above can be implemented by the structure of the electronic device.

[0153] In a specific embodiment of the present application, the electronic device may specifically be an ultrasonic device, such as an ultrasonic diagnostic instrument or an ultrasonic imaging workstation.

[0154] Corresponding to the above method embodiments, an embodiment of the present application also provides a readable storage medium. A readable storage medium described below can be correspondingly referred to with an ultrasonic image processing method described above.

[0155] A readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the ultrasonic image processing method in the above method embodiments are implemented.

[0156] Specifically, the readable storage medium can be various readable storage media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0157] In the present specification, each embodiment is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple. For the relevant parts, reference can be made to the description in the method part.

[0158] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0159] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0160] Finally, it should also be noted that in this text, relationships such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "including", "comprising" or any other variants are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0161] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. An ultrasonic image processing method, characterized in that, it includes: Obtain the ultrasonic image of the target object, wherein the ultrasonic image includes a tissue gray-scale image and a color blood flow image, and the color blood flow image is superimposed on the tissue gray-scale image; Identify the target structure area of the target object based on the tissue gray-scale image; Perform color segmentation using the color blood flow image to obtain a reflux color area corresponding to the reflux color; Determine the intersection of the target structure area and the reflux color area as the reflux area; Slice the imaging area of the ultrasonic image to obtain relevant slices of the reflux area; Calculate the reflux area of the reflux area based on the relevant slices of the reflux area.

2. The method according to claim 1, characterized in that, The performing color segmentation using the color blood flow image to obtain a reflux color area corresponding to the reflux color includes: Convert the color space of the color blood flow image to the HSV color space; Perform color segmentation on the color blood flow image using the HSV color space to obtain the reflux color area.

3. The method according to claim 1, characterized in that, The slicing the imaging area of the ultrasonic image to obtain relevant slices of the reflux area includes: Slice the imaging area according to the distribution of the ultrasonic imaging scan lines and the distribution of the sampling points; Obtain the relevant slices of the reflux area from each slice of the imaging area according to the position of the reflux area in the imaging area.

4. The method according to claim 3, characterized in that, The calculating the reflux area of the reflux area based on the relevant slices of the reflux area includes: Calculate the slice area according to the angle between the scan lines and the distance between the sampling points; Combine the slice area and calculate the reflux area of the reflux area based on the relevant slices of the reflux area.

5. The method according to claim 4, characterized in that, The combining the slice area and calculating the reflux area of the reflux area based on the relevant slices of the reflux area includes: Obtain the reflux area proportion of each relevant slice of the reflux area; Use the reflux area proportion to perform weighted summation on the slice area of each relevant slice of the reflux area to obtain the reflux area.

6. The method according to claim 5, characterized in that, Obtaining the reflux area proportion of each relevant slice of the reflux area includes: Obtain the pixel proportion of the reflux color in each relevant slice of the reflux area; Determine the pixel proportion as the reflux area proportion.

7. The method according to any one of claims 1 to 6, characterized in that, The identifying the target structure area of the target object based on the tissue gray-scale image includes: Use a target detection algorithm to identify the target structure area of the target object.

8. The method according to claim 7, characterized in that, The target object is the heart, and the target structure area is the atrial area.

9. The method according to claim 8, characterized in that, The using a target detection algorithm to identify the target structure area of the target object includes: For mitral regurgitation, the left atrial region in the tissue gray-scale image is identified using the target detection algorithm; For tricuspid regurgitation, the right atrial region in the tissue gray-scale image is identified using the target detection algorithm.

10. An ultrasonic image processing device, characterized in that, it includes: An image acquisition module for acquiring an ultrasonic image of a target object, wherein the ultrasonic image includes a tissue gray-scale image and a color flow image, and the color flow image is superimposed on the tissue gray-scale image; An intelligent recognition module for identifying the target structure region of the target object based on the tissue gray-scale image; A color segmentation module for performing color segmentation using the color flow image to obtain a regurgitation color region corresponding to the regurgitation color; A regurgitation region determination module for determining the intersection of the target structure region and the regurgitation color region as the regurgitation region; A slicing module for slicing the imaging region of the ultrasonic image to obtain relevant slices of the regurgitation region; A regurgitation area calculation module for calculating the regurgitation area of the regurgitation region based on the relevant slices of the regurgitation region.

11. An electronic device, characterized in that, it includes: A memory for storing a computer program; A processor for implementing the steps of the ultrasonic image processing method according to any one of claims 1 to 9 when executing the computer program.

12. The electronic device according to claim 11, characterized in that, the electronic device is an ultrasonic device.

13. A readable storage medium, characterized in that, the readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the ultrasonic image processing method according to any one of claims 1 to 9 are implemented.

Images