Ultrasonic parameter measurement method and device and computer equipment

Abstract

The invention relates to an ultrasonic parameter measurement method and device and computer equipment. The method is based on a digital image processing technology and an image segmentation technology, and can automatically measure various parameters of a fetal heart ultrasonic image, including a mandrel angle, a heart transverse diameter, a thoracic cavity transverse diameter, a cardiothoracic transverse diameter ratio, a heart area, a thoracic cavity area, a heart perimeter, a thoracic cavity perimeter, a cardiothoracic area ratio, a cardiothoracic perimeter ratio, and thicknesses of a left ventricular wall and a right ventricular wall. The ventricular septum thickness, the left atrium, the right atrium, the left ventricle and the right ventricle front-back diameter, the left-right diameter, the left-right atrium ventricle area, the left lung area and the right lung area, the aorta inner diameter and the distance from the aorta to the left atrium are reduced. Compared with the result of manual measurement by a doctor, the ultrasonic parameter measurement method effectively improves the measurement precision and the measurement accuracy, and can meet the actual needs of the doctor.

Description

Technical Field

[0001] The present application relates to the technical field of ultrasonic image processing, and in particular to an ultrasonic parameter measurement method, device, computer equipment, storage medium and computer program product. Background Art

[0002] Congenital heart disease (CHD) is a serious fetal anomaly and the leading cause of perinatal and neonatal mortality worldwide. Ultrasound is the main method for prenatal screening of fetal heart defects. In fetal echocardiography, the four-chamber view is crucial.

[0003] Traditional four-chamber heart related parameter measurements require medical staff to manually perform operations such as positioning and connecting lines. The process is cumbersome and highly dependent on the doctor's professional level. Summary of the invention

[0004] Based on this, it is necessary to provide an ultrasonic parameter measurement method, device, computer equipment, computer-readable storage medium and computer program product that can improve inspection efficiency and accuracy in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for measuring ultrasonic parameters. The method comprises:

[0006] Obtain the first four-chamber ultrasound view of the fetus at the end of systole and the second four-chamber ultrasound view at the end of diastole;

[0007] Obtaining a first cardiac axis and a second cardiac axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section, and obtaining a cardiac axis angle according to the angle between the first cardiac axis and the second cardiac axis;

[0008] According to the segmentation result of the heart and the chest cavity of the first four-chamber cardiac ultrasound section, a first cardiothoracic parameter is measured;

[0009] According to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section, a second cardiothoracic parameter is measured;

[0010] According to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section, the ventricular wall thickness parameter and the ventricular septum thickness are measured;

[0011] According to the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section, atrial parameters and ventricular parameters are measured;

[0012] According to the segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, measuring the left lung area and the right lung area;

[0013] According to the segmentation result of the descending aorta in the first four-chamber echocardiogram section or the second four-chamber echocardiogram section, measuring the inner diameter of the descending aorta;

[0014] According to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, the distance from the descending aorta to the left atrium is measured.

[0015] In one embodiment,

[0016] The method of obtaining a first cardiac axis and a second cardiac axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section, and obtaining a cardiac axis angle according to the angle between the first cardiac axis and the second cardiac axis, comprises:

[0017] Segmenting the ventricular septum of the first four-chamber cardiac ultrasound view;

[0018] Skeletonizing the ventricular septum to obtain points on the central axis of the ventricular septum;

[0019] Fitting the points on the central axis of the ventricular septum to obtain a first cardiac axis;

[0020] Segmenting the spine and thoracic cavity of the first four-chamber ultrasound heart section, and obtaining a second cardiac axis according to a line connecting the centroids of the spine and the thoracic cavity, or segmenting the left lung and the right lung of the first four-chamber ultrasound heart section, and obtaining the second cardiac axis according to a perpendicular line of the midpoint of a line connecting the centers of the largest circular areas corresponding to the left lung and the right lung;

[0021] The heart axis angle is obtained according to the angle between the first heart axis and the second heart axis.

[0022] In one embodiment, the first cardiothoracic parameter includes: transverse diameter of the heart, transverse diameter of the thoracic cavity, and transverse diameter ratio of the heart and chest;

[0023] The first cardiothoracic parameter is measured based on the segmentation result of the heart and the chest cavity of the first four-chamber cardiac ultrasound section, including:

[0024] According to the segmentation result of the heart and the chest cavity of the first four-chamber heart ultrasound section, a heart contour and a chest cavity contour are obtained;

[0025] In the fitted ellipse corresponding to the heart contour, the maximum diameter line perpendicular to the first heart axis is taken to obtain the transverse diameter of the heart;

[0026] In the fitted ellipse corresponding to the chest contour, the maximum diameter line perpendicular to the second heart axis is taken to obtain the transverse diameter of the chest cavity;

[0027] The heart-to-chest diameter ratio is obtained according to the ratio of the heart transverse diameter to the chest cavity transverse diameter.

[0028] In one embodiment, the second cardiothoracic parameter includes: heart area, chest area, heart circumference, chest circumference, heart-to-chest area ratio and heart-to-chest circumference ratio;

[0029] The step of measuring the second cardiothoracic parameter according to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section includes:

[0030] According to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section, a heart contour and a chest cavity contour are obtained;

[0031] According to the area and perimeter of the fitted ellipse corresponding to the heart contour, the heart area and heart perimeter are obtained;

[0032] According to the area and perimeter of the fitted ellipse corresponding to the chest contour, the chest area and chest perimeter are obtained;

[0033] Obtaining a heart-to-chest area ratio according to a ratio of the heart area to the chest cavity area;

[0034] The heart-chest circumference ratio is obtained according to the ratio of the heart circumference to the chest cavity circumference.

[0035] In one embodiment, the ventricular wall thickness parameter includes left ventricular wall thickness and right ventricular wall thickness;

[0036] The step of measuring the ventricular wall thickness parameter and the ventricular septum thickness according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section includes:

[0037] Segmenting the left ventricular wall, the right ventricular wall and the interventricular septum of the second four-chamber heart ultrasound section to obtain the left ventricular arm contour, the right ventricular arm contour and the interventricular septum contour;

[0038] According to the ventricular septum contour, the centroid of the ventricular septum is taken, a straight line perpendicular to the first cardiac axis is drawn through the centroid, two intersection points of the straight line and the left ventricular wall contour are taken, and the two intersection points are connected to obtain the left ventricular wall thickness;

[0039] Take two intersection points of the straight line and the right ventricular wall contour, and connect the two intersection points to obtain the right ventricular wall thickness;

[0040] The centroid of the interventricular septum is taken, and a straight line perpendicular to the first cardiac axis is drawn through the centroid. Two intersection points of the straight line and the contour of the interventricular septum are taken, and the two intersection points are connected to obtain the interventricular septum thickness.

[0041] In one embodiment, the atrial parameters include: the anterior-posterior diameter of the left atrium, the anterior-posterior diameter of the right atrium, the left-right diameter of the left atrium, and the left-right diameter of the right atrium;

[0042] The ventricular parameters include: the anterior-posterior diameter of the left ventricle, the anterior-posterior diameter of the right ventricle, the left-right diameter of the left ventricle, and the left-right diameter of the right ventricle;

[0043] The step of measuring atrial parameters and ventricular parameters based on the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section includes:

[0044] Segmenting the atria and ventricles of the first four-chamber cardiac ultrasound section to obtain a left atrium contour, a right atrium contour, a left ventricle contour, and a right ventricle contour;

[0045] According to the left atrium contour and the right atrium contour, the left atrium mass center and the right atrium mass center are taken respectively, and a straight line parallel to the first heart axis is drawn through the left atrium mass center to obtain the left atrium anteroposterior diameter, and a straight line parallel to the first heart axis is drawn through the right atrium mass center to obtain the right atrium anteroposterior diameter;

[0046] According to the left ventricular contour and the right ventricular contour, respectively, the left ventricular mass center and the right ventricular mass center are taken, and a straight line parallel to the first heart axis is drawn through the left ventricular mass center to obtain the anteroposterior diameter of the left ventricle, and a straight line parallel to the first heart axis is drawn through the right ventricular mass center to obtain the anteroposterior diameter of the right ventricle;

[0047] A straight line is drawn through the center of mass of the left atrium, perpendicular to the anterior-posterior diameter of the left atrium, to obtain the left and right diameters of the left atrium; a straight line is drawn through the center of mass of the right atrium, perpendicular to the anterior-posterior diameter of the right atrium, to obtain the left and right diameters of the right atrium; a straight line is drawn through the center of mass of the left ventricle, perpendicular to the anterior-posterior diameter of the left ventricle, to obtain the left and right diameters of the left ventricle; a straight line is drawn through the center of mass of the right ventricle, perpendicular to the anterior-posterior diameter of the right ventricle, to obtain the left and right diameters of the right ventricle.

[0048] In one embodiment, the step of measuring the distance from the descending aorta to the left atrium according to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section comprises:

[0049] Obtaining the contour of the descending aorta and the contour of the left atrium according to the segmentation results of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section;

[0050] The distance between the outline of the descending aorta and the outline of the left atrium is calculated point by point, and the minimum value is taken as the distance from the descending aorta to the left atrium.

[0051] In one embodiment, the step of obtaining a first four-chamber ultrasound section of the fetus at the end of systole and a second four-chamber ultrasound section of the fetus at the end of diastole comprises:

[0052] Segmentation of four-chamber heart ultrasound images from fetal ultrasound images;

[0053] According to the current four-chamber ultrasound heart image and the two frames of four-chamber ultrasound heart images before and after it, a first four-chamber ultrasound heart section at the end of cardiac contraction and a second four-chamber ultrasound heart section at the end of cardiac diastole are identified.

[0054] In a second aspect, the present application also provides an ultrasonic parameter measurement device. The device comprises:

[0055] An image acquisition module, used for acquiring a first four-chamber heart ultrasound section of the fetus at the end of heart contraction and a second four-chamber heart ultrasound section at the end of heart diastole;

[0056] A heart axis angle measurement module, used to obtain a first heart axis and a second heart axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber heart ultrasound section, and obtain a heart axis angle according to the angle between the first heart axis and the second heart axis;

[0057] A first cardiothoracic measurement module, configured to measure and obtain first cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the first four-chamber cardiac ultrasound section;

[0058] A second cardiothoracic measurement module, configured to measure and obtain second cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the second four-chamber cardiac ultrasound section;

[0059] A ventricular wall parameter measurement module, used to measure the ventricular wall thickness parameter and the ventricular septum thickness according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section;

[0060] According to the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section, atrial parameters and ventricular parameters are measured;

[0061] According to the segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, measuring the left lung area and the right lung area;

[0062] According to the segmentation result of the descending aorta in the first four-chamber echocardiogram section or the second four-chamber echocardiogram section, measuring the inner diameter of the descending aorta;

[0063] According to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, the distance from the descending aorta to the left atrium is measured.

[0064] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the ultrasonic parameter measurement method of each embodiment described above are implemented.

[0065] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the ultrasonic parameter measurement method of each of the above embodiments are implemented.

[0066] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the ultrasonic parameter measurement method of each embodiment described above are implemented.

[0067] The above-mentioned ultrasound parameter measurement method, device, computer equipment, storage medium and computer program product, based on digital image processing technology and image segmentation technology, can automatically measure various parameters of fetal heart ultrasound images. Compared with the results of manual measurement by doctors, no human intervention is required, and the measurement precision and accuracy are effectively improved, which can meet the actual needs of doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 A diagram showing an application environment of an ultrasonic parameter measurement method in an embodiment;

[0069] Figure 2 A schematic flow chart of the steps of obtaining the mandrel angle in one embodiment;

[0070] Figure 3 is a schematic diagram of a first central axis in one embodiment;

[0071] Figure 4 is a schematic diagram of the first central axis, the second central axis and the spindle angle in another embodiment;

[0072] Figure 5 is a schematic diagram of a second central axis in another embodiment;

[0073] Figure 6 is a schematic diagram of an image of a second four-chamber heart ultrasound section according to an embodiment;

[0074] Figure 7 is a schematic diagram of a heart mask and a thoracic mask according to an embodiment;

[0075] Figure 8 is a schematic diagram of the heart contour and chest cavity contour extracted in an illustrative example;

[0076] Fig. 9 is a schematic diagram of ventricular wall thickness parameters and ventricular septum thickness measured in one embodiment;

[0077] Fig.10 is a schematic diagram of the anterior-posterior diameter and the left-right diameter of the left atrium, right atrium, left ventricle and right ventricle in one embodiment;

[0078] Fig.11 is a schematic diagram of a four-chamber heart ultrasound section in one embodiment;

[0079] Fig.12 is a schematic diagram of a segmentation mask of a left and right lung in one embodiment;

[0080] Fig.13 is a schematic diagram of the distance from the descending aorta to the left atrium in one embodiment;

[0081] Fig.14 is a structural block diagram of an ultrasonic parameter measuring device in one embodiment;

[0082] Fig.15 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0084] An ultrasonic parameter measurement method is applied to a terminal connected to an ultrasonic probe, the ultrasonic probe collects ultrasonic images and sends them to the terminal for measurement and processing. Figure 1 As shown, the method includes:

[0085] Step 102, obtaining a first four-chamber ultrasound section of the fetus at the end of systole and a second four-chamber ultrasound section of the fetus at the end of diastole.

[0086] The four-chamber echocardiogram is a standard four-chamber echocardiogram, which is in line with the cross-sectional images required for the clinical measurement of cardiac-related indicators. The cardiac cycle refers to the mechanical activity cycle of the heart completing one contraction and relaxation. For the various parameters that need to be measured for the heart, the first four-chamber echocardiogram at the end of cardiac contraction or the second four-chamber echocardiogram at the end of cardiac diastole can be used to measure them.

[0087] In the measurement of four-chamber cardiac ultrasound image parameters, the measurement parameters based on end-systole and end-diastole are different. Among them, the measurement of end-diastole mainly reflects the filling of the ventricles and atria, so it can be used to measure parameters such as cardiothoracic area and circumference, while the measurement of end-systole mainly reflects the contractile function of the ventricles and the structure of the ventricular wall, and can be used to measure parameters such as cardiac axis measurement and atrial measurement.

[0088] Step 104, obtaining a first cardiac axis and a second cardiac axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section, and obtaining a cardiac axis angle according to the angle between the first cardiac axis and the second cardiac axis.

[0089] The first cardiac axis and the second cardiac axis are used to calculate the cardiac axis angle. When a normal fetus is tested, the cardiac axis angle value is between 32.9 degrees and 49.3 degrees.

[0090] The measurement of the cardiac axis angle is mainly based on the accurate segmentation of the ventricular septum in the four-chamber view.

[0091] In one embodiment, if Figure 2 As shown, according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber heart ultrasound section, the first heart axis and the second heart axis are obtained, and according to the angle between the first heart axis and the second heart axis, the heart axis angle is obtained, including:

[0092] Step 201, segmenting the ventricular septum of the first four-chamber cardiac ultrasound section.

[0093] Specifically, based on a machine learning method, the model can be used to learn the image features of the ventricular septum, and the ventricular septum of the first four-chamber cardiac ultrasound section can be segmented using the model.

[0094] Step 202, skeletonize the ventricular septum to obtain points on the central axis of the ventricular septum.

[0095] Specifically, the ventricular septum is skeletonized and the algorithm is able to extract a set of points representing the median axis of the ventricular septum.

[0096] Step 203, fitting the points on the central axis of the ventricular septum to obtain a first cardiac axis.

[0097] Specifically, the points on the central axis of the ventricular septum are fitted into a straight line using the least squares method to obtain the first cardiac axis, which is displayed on the screen of the terminal, such as Figure 3 shown.

[0098] Step 204, segment the spine and thoracic cavity of the first four-chamber ultrasound heart section, and obtain the second cardiac axis according to the line connecting the centroid positions of the spine and the thoracic cavity, or segment the left lung and the right lung of the first four-chamber ultrasound heart section, and obtain the second cardiac axis according to the perpendicular line of the midpoint of the line connecting the centers of the maximum circular areas corresponding to the left lung and the right lung.

[0099] Specifically, the spine and the entire thoracic cavity of the first four-chamber echocardiogram are segmented to obtain the spine structure and the thoracic cavity structure, and the centroid positions of the spine and the thoracic cavity are determined using the moment function of Opencv. Then, the line connecting the two centroids is taken, and this line is defined as the second cardiac axis, such as Figure 4 Shown

[0100] For images without the spine, the maximum circular area of ​​the left and right lungs is determined based on the segmentation results of the left and right lungs. Then, the midpoint of the line connecting the centers of the two largest circular areas is selected, and a vertical line is drawn from the midpoint as the second heart axis, such as Figure 5 shown.

[0101] Step 205, obtaining the heart axis angle according to the angle between the first heart axis and the second heart axis.

[0102] In this embodiment, the terminal automatically identifies and segments the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section by using an image processing method, thereby obtaining the first cardiac axis and the second cardiac axis, and automatically calculates the cardiac axis angle based on the angle between the two, and visually displays it to the medical staff for reference. This method does not require the medical staff to manually locate points and connect lines, thereby improving the accuracy and efficiency of the measurement.

[0103] Furthermore, after step 104, the ultrasonic parameter measurement method further includes:

[0104] Step 106: Measure and obtain first cardiothoracic parameters according to the segmentation result of the heart and the chest cavity of the first four-chamber cardiac ultrasound section.

[0105] Specifically, the first cardiothoracic parameter includes: heart transverse diameter, chest cavity transverse diameter and heart-to-thoracic diameter ratio. The automatic measurement of the first cardiothoracic parameter is based on the accurate segmentation of the heart and chest cavity of the first four-chamber cardiac ultrasound section.

[0106] Specifically, according to the segmentation result of the heart and the chest cavity of the first four-chamber ultrasound heart section, the first cardiothoracic parameter is measured, including: according to the segmentation result of the heart and the chest cavity of the first four-chamber ultrasound heart section, the heart contour and the chest cavity contour are obtained; in the fitting ellipse corresponding to the heart contour, the maximum diameter perpendicular to the first heart axis is taken to obtain the transverse diameter of the heart; in the fitting ellipse corresponding to the chest cavity contour, the maximum diameter perpendicular to the second heart axis is taken to obtain the transverse diameter of the chest cavity; according to the ratio of the heart transverse diameter to the chest cavity transverse diameter, the heart-chest transverse diameter ratio is obtained.

[0107] Specifically, the segmented heart is fitted into an ellipse. In this ellipse, the maximum diameter perpendicular to the first axis of the heart in the above-mentioned heart axis measurement is taken as the transverse diameter of the heart. The chest cavity is also fitted into an ellipse, in which the maximum diameter perpendicular to the second axis of the heart is defined as the transverse diameter of the chest cavity. Finally, the ratio of the transverse diameter of the heart to the transverse diameter of the chest cavity is calculated, and the ratio obtained is the heart-chest transverse diameter ratio.

[0108] In this embodiment, the terminal automatically identifies and segments the heart and chest contours of the first four-chamber heart ultrasound section using an image processing method, and fits an ellipse, on which basis the transverse diameter of the heart and the transverse diameter of the chest are measured, thereby obtaining the heart-chest transverse diameter ratio, and visually displays it to medical staff for reference. This method does not require medical staff to manually locate points and connect lines, thereby improving the accuracy and efficiency of measurement.

[0109] Step 108: Measure and obtain second cardiothoracic parameters based on the segmentation result of the heart and chest cavity of the second four-chamber heart ultrasound section.

[0110] Specifically, the second cardiothoracic parameters include: heart area, chest area, heart circumference, chest circumference, heart-chest area ratio and heart-chest circumference ratio. The measurement of the second cardiothoracic parameters is based on the complete segmentation result of the heart and chest of the second four-chamber heart ultrasound section.

[0111] Specifically, according to the segmentation result of the heart and the chest cavity in the second four-chamber ultrasound heart section, the second cardiothoracic parameter is measured, including: obtaining the heart contour and the chest cavity contour according to the segmentation result of the heart and the chest cavity in the second four-chamber ultrasound heart section; obtaining the heart area and the heart circumference according to the area and circumference of the fitted ellipse corresponding to the heart contour; obtaining the chest cavity area and the chest cavity circumference according to the area and circumference of the fitted ellipse corresponding to the chest cavity contour; obtaining the heart-chest area ratio according to the ratio of the heart area to the chest cavity area; and obtaining the heart-chest circumference ratio according to the ratio of the heart circumference to the chest cavity circumference.

[0112] Specifically, for Figure 6 The second four-chamber ultrasound section image is shown, and the heart and chest cavity are segmented to obtain the heart mask and chest cavity mask as shown in FIG. Figure 7 As shown, based on the heart mask and chest mask fitting, the heart contour and chest contour are obtained as shown in Figure 8 As shown, the above parameters are calculated based on the heart contour and chest contour. The calculation formula is as follows:

[0113] E c =F(m c ), (1)

[0114] E t =F(m t ), (2)

[0115]

[0116]

[0117] Among them, m c and m t They represent the heart mask and the chest mask respectively. In these masks, a pixel value of 1 indicates the presence of an object, while a value of 0 indicates the background. F represents the ellipse of the fitted mask, A represents the area of ​​the ellipse, and L represents the circumference of the ellipse.

[0118] The process of fitting an ellipse includes extracting contour points to refine the mask image, and then using the fitEllipse method of OpenCV to obtain the center coordinates, major and minor axis lengths, and rotation angles of the ellipse. This technology uses the least squares method to minimize the sum of the distances from all contour points to the ellipse, thereby fitting the best ellipse.

[0119] In this embodiment, the terminal automatically identifies and segments the heart and chest contours of the second four-chamber heart ultrasound section by using an image processing method, and fits an ellipse, on which basis the heart area, chest area, heart circumference, chest circumference, heart-chest area ratio and heart-chest circumference ratio are measured and displayed visually for medical staff's reference. This method does not require medical staff to manually locate points and connect lines, thus improving the accuracy and efficiency of measurement.

[0120] Step 110, based on the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section, measure and obtain the ventricular wall thickness parameter and the ventricular septum thickness.

[0121] Specifically, the measurement of ventricular wall thickness parameters and interventricular septum thickness is mainly based on the accurate segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section. The ventricular wall thickness parameters include the left ventricular wall thickness and the right ventricular wall thickness.

[0122] Specifically, according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section, the ventricular wall thickness parameters and the ventricular septum thickness are measured as follows: Fig. 9 As shown. This step includes: segmenting the left ventricular wall, right ventricular wall and ventricular septum of the second four-chamber heart ultrasound section to obtain the left ventricular arm contour, right ventricular arm contour and ventricular septum contour; taking the centroid of the ventricular septum according to the ventricular septum contour, making a straight line perpendicular to the first heart axis through the centroid, taking two intersections of the straight line and the left ventricular wall contour, connecting the two intersections to obtain the left ventricular wall thickness; taking two intersections of the straight line and the right ventricular wall contour, connecting the two intersections to obtain the right ventricular wall thickness; taking the centroid of the ventricular septum, making a straight line perpendicular to the first heart axis through the centroid, taking two intersections of the straight line and the ventricular septum contour, connecting the two intersections to obtain the ventricular septum thickness.

[0123] Specifically, using image processing methods, the terminal automatically identifies and segments the left ventricular wall, right ventricular wall and interventricular septum of the second four-chamber heart ultrasound section, and on this basis measures the thickness of the left ventricular wall, right ventricular wall and interventricular septum, and displays them visually for medical staff's reference. This method does not require medical staff to manually locate points and connect lines, which improves the accuracy and efficiency of measurement.

[0124] Step 112: According to the segmentation results of the atria and ventricles of the first four-chamber heart ultrasound section, atrial parameters and ventricular parameters are measured.

[0125] Specifically, the atrial parameters include: the anterior-posterior diameter of the left atrium, the anterior-posterior diameter of the right atrium, the left-right diameter of the left atrium, and the left-right diameter of the right atrium.

[0126] The ventricular parameters include: the anteroposterior diameter of the left ventricle, the anteroposterior diameter of the right ventricle, the left-right diameter of the left ventricle, and the right-right diameter of the right ventricle.

[0127] The measurement of atrial and ventricular parameters is based on the accurate segmentation of the atria and ventricles in the first four-chamber echocardiographic view.

[0128] Specifically, based on the segmentation results of the atria and ventricles of the first four-chamber heart ultrasound section, the atrial parameters and ventricular parameters are measured, including: segmenting the atria and ventricles of the first four-chamber heart ultrasound section to obtain the left atrial contour, the right atrial contour, the left ventricular contour and the right ventricular contour; taking the left atrial centroid and the right atrial centroid according to the left atrial contour and the right atrial contour, and drawing a straight line parallel to the first cardiac axis through the left atrial centroid to obtain the anteroposterior diameter of the left atrium, and drawing a straight line parallel to the first cardiac axis through the right atrial centroid to obtain the anteroposterior diameter of the right atrium; taking the left ventricular contour and the right ventricular contour according to the left ventricular contour and the right ventricular contour ... left ventricular centroid to obtain the anteroposterior diameter of the right atrium. The center of mass of the ventricle and the center of mass of the right ventricle, draw a straight line parallel to the first cardiac axis through the center of mass of the left ventricle to obtain the anterior-posterior diameter of the left ventricle, and draw a straight line parallel to the first cardiac axis through the center of mass of the right ventricle to obtain the anterior-posterior diameter of the right ventricle; draw a straight line perpendicular to the anterior-posterior diameter of the left atrium through the center of mass of the left atrium to obtain the left and right diameters of the left atrium, draw a straight line perpendicular to the anterior-posterior diameter of the right atrium through the center of mass of the right atrium to obtain the left and right diameters of the right atrium, draw a straight line perpendicular to the anterior-posterior diameter of the left ventricle through the center of mass of the left ventricle to obtain the left and right diameters of the left ventricle, and draw a straight line perpendicular to the anterior-posterior diameter of the right ventricle through the center of mass of the right ventricle to obtain the left and right diameters of the right ventricle.

[0129] like Fig.10 As shown, by using the image processing method, the terminal automatically identifies and segments the left and right atria and left and right ventricles of the first four-chamber heart ultrasound section, and on this basis measures the anteroposterior diameter of the left atrium, the anteroposterior diameter of the right atrium, the left and right diameters of the left atrium, and the left and right diameters of the right atrium, as well as the anteroposterior diameter of the left ventricle, the anteroposterior diameter of the right ventricle, the left and right diameters of the left ventricle, and the left and right diameters of the right ventricle, and visualizes them for reference by medical staff. This method does not require medical staff to manually locate points and connect lines, which improves the accuracy and efficiency of measurement.

[0130] Step 114, measuring the left lung area and the right lung area according to the segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

[0131] Specifically, the measurement of the left lung area and the right lung area can be based on the accurate segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section. Specifically, the segmentation masks of the left and right lungs are obtained according to the segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section. Fig.11 The four-chamber ultrasound section shown in FIG. 1 shows the segmentation mask of the left and right lungs obtained by segmenting the left and right lungs. Fig.12As shown in the figure. The pixel value of 1 in the mask indicates that it belongs to the left and right lungs, while the value of 0 indicates the background. The count_nonzero function in the Numpy library is used to count the number of non-zero pixels to obtain the area of ​​the left and right lungs.

[0132] Step 116, measuring the inner diameter of the descending aorta according to the segmentation result of the descending aorta in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

[0133] Specifically, the method for calculating the inner diameter of the descending aorta is mainly based on the accurate segmentation result of the descending aorta by the first four-chamber echocardiogram or the second four-chamber echocardiogram. After the contour of the descending aorta is obtained by segmentation, the minimum circumscribed circle of the contour of the descending aorta is obtained by using the minEnclosingCircle function of OpenCV, and the diameter of the circle is used as the inner diameter of the descending aorta.

[0134] Step 118, measuring the distance from the descending aorta to the left atrium according to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

[0135] Specifically, the method for calculating the distance from the descending aorta to the left atrium is mainly based on the segmentation results of the descending aorta and the left atrium in the first four-chamber echocardiogram section or the second four-chamber echocardiogram section, and the segmentation mask of the descending aorta and the segmentation mask of the left atrium are obtained. According to the segmentation mask of the descending aorta and the segmentation mask of the left atrium, the contour of the descending aorta and the contour of the left atrium are respectively calculated. The distance between the contour of the descending aorta and the contour of the left atrium is calculated point by point, and the minimum value is taken as the distance from the descending aorta to the left atrium, such as Fig.13 shown.

[0136] The ultrasound parameter measurement method of the present application is based on digital image processing technology and image segmentation technology, and can automatically measure various parameters of fetal heart ultrasound images. Compared with the results of manual measurement by doctors, it does not require human intervention, effectively improves the measurement precision and accuracy, and can meet the actual needs of doctors.

[0137] In another embodiment, obtaining a first four-chamber ultrasound section of the fetus at the end of systole and a second four-chamber ultrasound section of the fetus at the end of diastole includes: segmenting the four-chamber ultrasound image from the ultrasound image of the fetus; and identifying the first four-chamber ultrasound section at the end of systole and the second four-chamber ultrasound section at the end of diastole based on the current four-chamber ultrasound image and the two frames of four-chamber ultrasound images before and after it.

[0138] That is, this step includes two steps, the first step is to segment the four-chamber heart ultrasound image from the fetal ultrasound image, and the second step is to identify the cardiac cycle, identifying the first four-chamber heart ultrasound section at the end of heart contraction and the second four-chamber heart ultrasound section at the end of diastole.

[0139] For the first step, the four-chamber ultrasound image is segmented from the fetal ultrasound image. Specifically, the NNUnetV2 framework is used to segment the four-chamber ultrasound image. GPU parallel computing is used to accelerate the model training and reasoning process. The specific strategy is as follows:

[0140] 1. Data parallelism. Data parallelism is a parallel training technology. Its core idea is to divide the training data into multiple subsets and assign each subset to a different computing node for training. Each computing node independently trains its own subset data and regularly exchanges model parameters with other nodes to ensure that the models trained by all nodes are consistent. The most intuitive way to implement data parallelism is to evenly divide the training data into multiple subsets, each containing the same number of data samples. Then, assign each subset to a computing node and let each node independently train its own subset data. During the training process, each node regularly exchanges its model parameters with other nodes to ensure that the models trained by all nodes are consistent.

[0141] 2. Convolution acceleration algorithm: Use the im2col+GEMM convolution acceleration algorithm to accelerate convolution.

[0142] First, use im2col to convert the input image into a matrix form so that convolution operations can be performed through matrix multiplication. This conversion can simplify the convolution operation process and also facilitate efficient calculations using basic linear algebra libraries (such as BLAS libraries). Assuming there is an input image, im2col converts the input image into a matrix according to parameters such as the convolution kernel size and stride. Each column of the matrix corresponds to the local area obtained after the convolution kernel slides on the input image.

[0143] After that, the convolution kernel is converted into a matrix using the GEMM algorithm. This matrix can be reused in convolution operations. An intermediate result matrix is ​​obtained by performing matrix multiplication operation between the matrix converted by im2col and the convolution kernel matrix. The intermediate result matrix is ​​reshaped into the shape of the output feature map.

[0144] Through the im2col and GEMM algorithms, convolution operations can be converted into efficient matrix multiplication operations, thereby accelerating the training and reasoning process of convolutional neural networks. This method is widely used in the implementation of deep learning frameworks and can significantly improve the computational efficiency of convolutional neural networks.

[0145] For the second step, cardiac cycle recognition, the measurement of cardiac parameters needs to be performed in a specific cardiac cycle, so it is first necessary to identify which cardiac cycle the heart is currently in. Yolov5 is used for cardiac cycle recognition.

[0146] In order to better identify the specific cardiac cycle, the training images need to be pre-processed. The specific method is: take the specific frame marked as "end systole" or "end diastole" by the doctor in the video and one frame before and after it, a total of three images. Convert the three images into single-channel images respectively, and then superimpose the three single-channel images into a three-channel image, so that the three-channel image contains the information of the three images, so that the deep learning network can learn the changes in the heartbeat information. Use the processed images as training data and use yolov5 for training.

[0147] At the same time, when using the model to identify targets in videos, the same processing is also required. After superimposing the image to be detected with its previous and subsequent frames, it is input into the trained yolov5 model to identify the first four-chamber cardiac ultrasound section at the end of cardiac contraction and the second four-chamber cardiac ultrasound section at the end of cardiac diastole.

[0148] In this embodiment, the method for identifying the cardiac cycle of the fetal heart ultrasound image based on yolov5 can meet the needs of real-time detection, and the processing speed can reach 30FPS.

[0149] The ultrasonic parameter measurement method of the present application, based on digital image processing technology and image segmentation technology, can automatically measure various parameters of fetal heart ultrasound images, including heart axis angle, heart transverse diameter, chest transverse diameter, heart-chest transverse diameter ratio, heart area, chest area, heart circumference, chest circumference, heart-chest area ratio and heart-chest circumference ratio, left ventricular wall and right ventricular wall thickness, ventricular septum thickness, left atrium, right atrium, left ventricle and right ventricle anterior-posterior diameter, left-right diameter, left-right atrium and ventricular area, left and right lung area, descending aorta inner diameter, and descending aorta to left atrium distance. Compared with the results of manual measurement by doctors, the ultrasonic parameter measurement method of the present application effectively improves the measurement precision and accuracy, and can meet the actual needs of doctors.

[0150] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application also provides an ultrasonic parameter measurement device for implementing the ultrasonic parameter measurement method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more ultrasonic parameter measurement device embodiments provided below can refer to the limitations of the ultrasonic parameter measurement method above, and will not be repeated here.

[0152] In one embodiment, Fig.14 As shown, an ultrasonic parameter measuring device is provided, comprising:

[0153] The image acquisition module 1401 is used to acquire the first four-chamber ultrasound section of the fetus at the end of systole and the second four-chamber ultrasound section of the fetus at the end of diastole.

[0154] The heart axis angle measurement module 1402 is used to obtain the first heart axis and the second heart axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber heart ultrasound section, and to obtain the heart axis angle according to the angle between the first heart axis and the second heart axis.

[0155] The first cardiothoracic measurement module 1403 is used to measure and obtain first cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the first four-chamber cardiac ultrasound section.

[0156] The second cardiothoracic measurement module 1404 is used to measure and obtain second cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the second four-chamber cardiac ultrasound section.

[0157] The ventricular wall parameter measurement module 1405 is used to measure the ventricular wall thickness parameter and the ventricular septum thickness according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section.

[0158] The atrioventricular parameter measurement module 1406 measures atrial parameters and ventricular parameters according to the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section.

[0159] The lung area measurement module 1407 is used to measure the left lung area and the right lung area according to the segmentation results of the left lung and the right lung of the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

[0160] The descending aorta inner diameter measurement module 1408 is used to measure the descending aorta inner diameter according to the segmentation result of the descending aorta in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

[0161] The distance measurement module 1409 is used to measure the distance from the descending aorta to the left atrium according to the segmentation results of the descending aorta and the left atrium of the first four-chamber ultrasound section or the second four-chamber ultrasound section. Each module in the above-mentioned ultrasound parameter measurement device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0162] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.15 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an ultrasonic parameter measurement method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0163] Those skilled in the art will understand that Fig.15 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0164] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps of the ultrasonic parameter measurement method of each of the above embodiments when executing the computer program.

[0165] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the ultrasonic parameter measurement method of each of the above embodiments are implemented.

[0166] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the ultrasound parameter measurement method of each of the above embodiments when executed by a processor.

[0167] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processors involved in each embodiment provided in this application may be general-purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, data processing logic devices based on quantum computing, etc., but are not limited thereto.

[0168] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0169] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for measuring ultrasonic parameters, characterized in that: include: Obtain the first four-chamber ultrasound view of the fetus at the end of systole and the second four-chamber ultrasound view at the end of diastole; Obtaining a first cardiac axis and a second cardiac axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section, and obtaining a cardiac axis angle according to the angle between the first cardiac axis and the second cardiac axis; According to the segmentation result of the heart and the chest cavity of the first four-chamber cardiac ultrasound section, a first cardiothoracic parameter is measured; According to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section, a second cardiothoracic parameter is measured; According to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section, the ventricular wall thickness parameter and the ventricular septum thickness are measured; According to the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section, atrial parameters and ventricular parameters are measured; According to the segmentation results of the left lung and the right lung in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, measuring the left lung area and the right lung area; According to the segmentation result of the descending aorta in the first four-chamber echocardiogram section or the second four-chamber echocardiogram section, measuring the inner diameter of the descending aorta; According to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section, the distance from the descending aorta to the left atrium is measured.

2. The method according to claim 1, characterized in that: The method of obtaining a first cardiac axis and a second cardiac axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber cardiac ultrasound section, and obtaining a cardiac axis angle according to the angle between the first cardiac axis and the second cardiac axis, comprises: Segmenting the ventricular septum of the first four-chamber cardiac ultrasound view; Skeletonizing the ventricular septum to obtain points on the central axis of the ventricular septum; Fitting the points on the central axis of the ventricular septum to obtain a first cardiac axis; Segmenting the spine and thoracic cavity of the first four-chamber ultrasound heart section, and obtaining a second cardiac axis according to a line connecting the centroids of the spine and the thoracic cavity, or segmenting the left lung and the right lung of the first four-chamber ultrasound heart section, and obtaining the second cardiac axis according to a perpendicular line of the midpoint of a line connecting the centers of the largest circular areas corresponding to the left lung and the right lung; The heart axis angle is obtained according to the angle between the first heart axis and the second heart axis.

3. The method according to claim 1, characterized in that: The first cardiothoracic parameter includes: heart transverse diameter, chest cavity transverse diameter and cardiothoracic transverse diameter ratio; The first cardiothoracic parameter is measured based on the segmentation result of the heart and the chest cavity of the first four-chamber cardiac ultrasound section, including: According to the segmentation result of the heart and the chest cavity of the first four-chamber heart ultrasound section, a heart contour and a chest cavity contour are obtained; In the fitted ellipse corresponding to the heart contour, the maximum diameter line perpendicular to the first heart axis is taken to obtain the transverse diameter of the heart; In the fitted ellipse corresponding to the chest contour, the maximum diameter line perpendicular to the second heart axis is taken to obtain the transverse diameter of the chest cavity; The heart-to-chest diameter ratio is obtained according to the ratio of the heart transverse diameter to the chest cavity transverse diameter.

4. The method according to claim 1, characterized in that: The second cardiothoracic parameters include: heart area, chest area, heart circumference, chest circumference, heart-to-chest area ratio and heart-to-chest circumference ratio; The step of measuring the second cardiothoracic parameter according to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section includes: According to the segmentation result of the heart and the chest cavity of the second four-chamber heart ultrasound section, a heart contour and a chest cavity contour are obtained; According to the area and perimeter of the fitted ellipse corresponding to the heart contour, the heart area and heart perimeter are obtained; According to the area and perimeter of the fitted ellipse corresponding to the chest contour, the chest area and chest perimeter are obtained; Obtaining a heart-to-chest area ratio according to a ratio of the heart area to the chest cavity area; The heart-chest circumference ratio is obtained according to the ratio of the heart circumference to the chest cavity circumference.

5. The method according to claim 1, characterized in that The ventricular wall thickness parameters include left ventricular wall thickness and right ventricular wall thickness; The step of measuring the ventricular wall thickness parameter and the ventricular septum thickness according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section includes: Segmenting the left ventricular wall, the right ventricular wall and the interventricular septum of the second four-chamber heart ultrasound section to obtain the left ventricular arm contour, the right ventricular arm contour and the interventricular septum contour; According to the ventricular septum contour, the centroid of the ventricular septum is taken, a straight line perpendicular to the first cardiac axis is drawn through the centroid, two intersection points of the straight line and the left ventricular wall contour are taken, and the two intersection points are connected to obtain the left ventricular wall thickness; Take two intersection points of the straight line and the right ventricular wall contour, and connect the two intersection points to obtain the right ventricular wall thickness; The centroid of the interventricular septum is taken, and a straight line perpendicular to the first cardiac axis is drawn through the centroid. Two intersection points of the straight line and the contour of the interventricular septum are taken, and the two intersection points are connected to obtain the interventricular septum thickness.

6. The method according to claim 1, characterized in that The atrial parameters include: the anterior-posterior diameter of the left atrium, the anterior-posterior diameter of the right atrium, the left-right diameter of the left atrium, and the left-right diameter of the right atrium; The ventricular parameters include: the anterior-posterior diameter of the left ventricle, the anterior-posterior diameter of the right ventricle, the left-right diameter of the left ventricle, and the left-right diameter of the right ventricle; The step of measuring atrial parameters and ventricular parameters based on the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section includes: Segmenting the atria and ventricles of the first four-chamber cardiac ultrasound section to obtain a left atrium contour, a right atrium contour, a left ventricle contour, and a right ventricle contour; According to the left atrium contour and the right atrium contour, the left atrium mass center and the right atrium mass center are taken respectively, and a straight line parallel to the first heart axis is drawn through the left atrium mass center to obtain the left atrium anteroposterior diameter, and a straight line parallel to the first heart axis is drawn through the right atrium mass center to obtain the right atrium anteroposterior diameter; According to the left ventricular contour and the right ventricular contour, respectively, the left ventricular mass center and the right ventricular mass center are taken, and a straight line parallel to the first heart axis is drawn through the left ventricular mass center to obtain the anteroposterior diameter of the left ventricle, and a straight line parallel to the first heart axis is drawn through the right ventricular mass center to obtain the anteroposterior diameter of the right ventricle; A straight line is drawn through the center of mass of the left atrium, perpendicular to the anterior-posterior diameter of the left atrium, to obtain the left and right diameters of the left atrium; a straight line is drawn through the center of mass of the right atrium, perpendicular to the anterior-posterior diameter of the right atrium, to obtain the left and right diameters of the right atrium; a straight line is drawn through the center of mass of the left ventricle, perpendicular to the anterior-posterior diameter of the left ventricle, to obtain the left and right diameters of the left ventricle; a straight line is drawn through the center of mass of the right ventricle, perpendicular to the anterior-posterior diameter of the right ventricle, to obtain the left and right diameters of the right ventricle.

7. The method according to claim 1, characterized in that The step of measuring the distance from the descending aorta to the left atrium according to the segmentation result of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section comprises: Obtaining the contour of the descending aorta and the contour of the left atrium according to the segmentation results of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section; The distance between the outline of the descending aorta and the outline of the left atrium is calculated point by point, and the minimum value is taken as the distance from the descending aorta to the left atrium.

8. The method according to any one of claims 1 to 7, characterized in that: The step of obtaining the first four-chamber ultrasound section of the fetus at the end of systole and the second four-chamber ultrasound section of the fetus at the end of diastole comprises: Segmentation of four-chamber heart ultrasound images from fetal ultrasound images; According to the current four-chamber ultrasound heart image and the two frames of four-chamber ultrasound heart images before and after it, a first four-chamber ultrasound heart section at the end of cardiac contraction and a second four-chamber ultrasound heart section at the end of cardiac diastole are identified.

9. An ultrasonic parameter measuring device, characterized in that: The device comprises: An image acquisition module, used for acquiring a first four-chamber heart ultrasound section of the fetus at the end of heart contraction and a second four-chamber heart ultrasound section at the end of heart diastole; A heart axis angle measurement module, used to obtain a first heart axis and a second heart axis according to the segmentation results of the ventricular septum, spine and thoracic cavity of the first four-chamber heart ultrasound section, and obtain a heart axis angle according to the angle between the first heart axis and the second heart axis; A first cardiothoracic measurement module, configured to measure and obtain first cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the first four-chamber cardiac ultrasound section; A second cardiothoracic measurement module, configured to measure and obtain second cardiothoracic parameters according to the segmentation result of the heart and the thoracic cavity of the second four-chamber cardiac ultrasound section; A ventricular wall parameter measurement module, used to measure the ventricular wall thickness parameter and the ventricular septum thickness according to the segmentation results of the left ventricular wall and the right ventricular wall of the second four-chamber heart ultrasound section; an atrioventricular parameter measurement module, which measures atrial parameters and ventricular parameters according to the segmentation results of the atria and ventricles of the first four-chamber cardiac ultrasound section; a lung area measurement module, configured to measure the left lung area and the right lung area according to the segmentation results of the left lung and the right lung of the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section; A descending aorta inner diameter measurement module, configured to measure the descending aorta inner diameter according to the segmentation result of the descending aorta in the first four-chamber echocardiogram section or the second four-chamber echocardiogram section; The distance measurement module is used to measure the distance from the descending aorta to the left atrium according to the segmentation results of the descending aorta and the left atrium in the first four-chamber ultrasound heart section or the second four-chamber ultrasound heart section.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images