Method and apparatus for determining cardiac risk parameters

Abstract

The application provides a method and device for determining a cardiac risk parameter, the method comprising: obtaining a plurality of lead electrocardio vector signals of a target entity; converting the plurality of lead electrocardio vector signals into a plurality of time domain waveform graphs; obtaining a waveform difference value between a waveform maximum value and a waveform minimum value of each time domain waveform graph to obtain a plurality of waveform difference values; obtaining a time cost for each time domain waveform graph to reach the waveform maximum value to obtain a plurality of time costs; obtaining a time interval between two adjacent waveform maximum values on each time domain waveform graph to obtain a plurality of time intervals; determining an electrocardiogram risk parameter based on a standard deviation and a maximum value of the plurality of waveform maximum values, a standard deviation and a maximum value of the plurality of waveform difference values, a standard deviation and a mean value of the plurality of time intervals, and a standard deviation and a mean value of the plurality of time costs; and determining the cardiac risk parameter based on the electrocardiogram risk parameter. The application can improve the determination accuracy of the cardiac risk parameter.

Description

Methods and devices for determining cardiac risk parameters Technical Field

[0001] This application mainly relates to the field of image processing technology, and specifically to a method and apparatus for determining cardiac risk parameters. Background Technology

[0002] For gastroenterologists, assessing cardiac function using imaging data such as electrocardiograms, echocardiograms, and coronary angiography requires specialized interdisciplinary knowledge in cardiology, thus consuming a significant amount of time and effort in clinical practice. Current technology primarily relies on physicians manually observing electrocardiograms to determine cardiac risk parameters, which cannot accurately pinpoint these parameters.

[0003] In other words, the accuracy of existing methods for determining cardiac risk parameters is relatively low. Summary of the Invention

[0004] This application provides a method and apparatus for determining cardiac risk parameters, aiming to solve the problem of low accuracy in existing methods for determining cardiac risk parameters.

[0005] In a first aspect, this application provides a method for determining cardiac risk parameters, the method comprising:

[0006] Acquire multiple lead ECG vector signals of the target entity;

[0007] The multiple lead ECG vector signals are converted into multiple time-domain waveforms;

[0008] Obtain the waveform difference between the maximum and minimum values ​​of each time-domain waveform to obtain multiple waveform differences;

[0009] Obtain the time taken for each time-domain waveform to reach its maximum value, resulting in multiple time take-up values;

[0010] Obtain the time interval between the maximum values ​​of two adjacent waveforms on each time-domain waveform graph to obtain multiple time intervals;

[0011] ECG risk parameters are determined based on the standard deviation and maximum value of multiple waveform maximums, the standard deviation and maximum value of multiple waveform differences, the standard deviation and mean of multiple time intervals, and the standard deviation and mean of multiple time periods.

[0012] Cardiac risk parameters are determined based on electrocardiogram risk parameters.

[0013] Optionally, the determination of cardiac risk parameters based on electrocardiogram risk parameters includes:

[0014] Acquire multiple coronary angiography images of the target entity;

[0015] Multiple coronary angiography images are input into the coronary artery vascular tree segmentation model to obtain the vascular segmentation region on each coronary angiography image;

[0016] Three-dimensional reconstruction of segmented vascular regions from multiple coronary angiography images was performed to obtain a three-dimensional vascular model;

[0017] Obtain the centerline of the blood vessel in the 3D model of the blood vessel;

[0018] Corner point detection is performed on the blood vessel centerline, and the blood vessel centerline is broken at the detected corner points to obtain multiple blood vessel centerline segments and corresponding blood vessel lumen segments, wherein the blood vessel centerline segment is the centerline of the blood vessel lumen segment;

[0019] Multiple points on the central line segment of the blood vessel are respectively identified as target points. A cross-section of the blood vessel lumen segment is drawn through the target points to obtain the cross-sectional area of ​​multiple cross-sections corresponding to multiple points.

[0020] The ratio of the minimum value among multiple cross-sectional areas to the average value among multiple cross-sectional areas is determined as the vascular stenosis coefficient of the vascular segment, thus obtaining the vascular stenosis coefficients of multiple vascular segments.

[0021] Coronary angiography risk parameters are determined based on the stenosis coefficient of multiple vascular segments;

[0022] Cardiac risk parameters are determined based on coronary angiography risk parameters and electrocardiogram risk parameters.

[0023] Optionally, the determination of coronary angiography risk parameters based on the vascular stenosis coefficient of multiple vascular segments includes:

[0024] Multiple coronary angiography images were input into the coronary artery lesion morphology detection model to obtain multiple abnormal regions;

[0025] Images from multiple abnormal regions are input into a coronary artery lesion morphology classification model to obtain the abnormality coefficients for each abnormal region. Different abnormality coefficients correspond to different abnormal categories output by the coronary artery lesion morphology classification model.

[0026] Coronary angiography risk parameters were determined based on the standard deviation of the stenosis coefficients of multiple vascular segments and the standard deviation of the abnormal coefficients of multiple abnormal regions.

[0027] Optionally, the determination of cardiac risk parameters based on coronary angiography risk parameters and electrocardiogram risk parameters includes:

[0028] Obtain echocardiographic images of the target entity;

[0029] Echocardiogram images are input into a cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region and the atrioventricular cavity wall region that surrounds the cardiac atrioventricular region;

[0030] Obtain the outer and inner contours of the cavity wall region of the chamber;

[0031] By passing through multiple outer contour points on the outer contour of the cavity wall and intersecting the inner contour of the cavity wall with the lines, multiple intersection points corresponding to the multiple outer contour points are obtained;

[0032] Obtain the first straight-line distance between each outer contour point and its corresponding intersection point, thus obtaining multiple first straight-line distances corresponding to multiple outer contour points;

[0033] The maximum value among multiple first linear distances is determined as the thickness of the cardiac atrioventricular cavity wall region;

[0034] Echocardiographic risk parameters are determined based on the thickness of the cardiac atrioventricular cavity wall region.

[0035] Cardiac risk parameters are determined based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0036] Optionally, determining the echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region includes:

[0037] Obtain the minimum circumcircle of the atrioventricular region of the heart;

[0038] Obtain the atrioventricular contour of the cardiac atrioventricular region;

[0039] Calculate the second straight-line distance between multiple room contour points on the room contour and the center of the smallest circumcircle to obtain multiple second straight-line distances corresponding to multiple room contour points;

[0040] The characterization value of cardiac atrioventricular irregularity is determined based on the standard deviation of multiple second straight-line distances;

[0041] Echocardiographic risk parameters are determined based on the thickness of the atrioventricular cavity wall region and the atrioventricular irregularity characterization value.

[0042] Optionally, determining the cardiac atrioventricular irregularity characterization value based on the standard deviation of multiple second straight-line distances includes:

[0043] The minimum circumscribed circle is divided into multiple sector regions to obtain room-room sub-regions within the multiple sector regions;

[0044] Obtain the area difference between the sector region and the corresponding room sub-region to obtain the area difference between multiple sector regions;

[0045] The area standard deviation is determined based on the area of ​​the multiple room-divided sub-regions and the multiple area differences;

[0046] The sum of the standard deviation of the area and the standard deviation of the distances between multiple second lines was determined as the characterization value of cardiac atrioventricular irregularities.

[0047] Optionally, the determination of cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters includes:

[0048] Obtain multiple baseline features of the target entity, including age, gender, history of heart disease, history of heart surgery, whether smoking, and whether drinking alcohol;

[0049] Input multiple baseline features of the target entity into a pre-defined decision tree model to obtain baseline risk parameters;

[0050] Cardiac risk parameters were determined based on baseline risk parameters, echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0051] Secondly, this application provides a device for determining cardiac risk parameters, the device comprising:

[0052] The first acquisition unit is used to acquire multiple lead ECG vector signals of the target entity;

[0053] A conversion unit is used to convert the multiple lead ECG vector signals into multiple time-domain waveforms;

[0054] The second acquisition unit is used to acquire the waveform difference between the maximum and minimum values ​​of each time-domain waveform, and obtain multiple waveform differences.

[0055] The third acquisition unit is used to acquire the time taken for each time domain waveform to reach the maximum value of the waveform, and obtain multiple acquisition times;

[0056] The fourth acquisition unit is used to acquire the time interval between the maximum values ​​of two adjacent waveforms on each time-domain waveform graph, thus obtaining multiple time intervals;

[0057] The first determining unit is used to determine electrocardiogram risk parameters based on the standard deviation and maximum value of multiple waveform maximum values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and average value of multiple time intervals, and the standard deviation and average value of multiple time periods.

[0058] The second determining unit is used to determine cardiac risk parameters based on electrocardiogram risk parameters.

[0059] Optionally, the determination of cardiac risk parameters based on electrocardiogram risk parameters includes:

[0060] Acquire multiple coronary angiography images of the target entity;

[0061] Multiple coronary angiography images are input into the coronary artery vascular tree segmentation model to obtain the vascular segmentation region on each coronary angiography image;

[0062] Three-dimensional reconstruction of segmented vascular regions from multiple coronary angiography images was performed to obtain a three-dimensional vascular model;

[0063] Obtain the centerline of the blood vessel in the 3D model of the blood vessel;

[0064] Corner point detection is performed on the blood vessel centerline, and the blood vessel centerline is broken at the detected corner points to obtain multiple blood vessel centerline segments and corresponding blood vessel lumen segments, wherein the blood vessel centerline segment is the centerline of the blood vessel lumen segment;

[0065] Multiple points on the central line segment of the blood vessel are respectively identified as target points. A cross-section of the blood vessel lumen segment is drawn through the target points to obtain the cross-sectional area of ​​multiple cross-sections corresponding to multiple points.

[0066] The ratio of the minimum value among multiple cross-sectional areas to the average value among multiple cross-sectional areas is determined as the vascular stenosis coefficient of the vascular segment, thus obtaining the vascular stenosis coefficients of multiple vascular segments.

[0067] Coronary angiography risk parameters are determined based on the stenosis coefficient of multiple vascular segments;

[0068] Cardiac risk parameters are determined based on coronary angiography risk parameters and electrocardiogram risk parameters.

[0069] Optionally, the determination of coronary angiography risk parameters based on the vascular stenosis coefficient of multiple vascular segments includes:

[0070] Multiple coronary angiography images were input into the coronary artery lesion morphology detection model to obtain multiple abnormal regions;

[0071] Images from multiple abnormal regions are input into a coronary artery lesion morphology classification model to obtain the abnormality coefficients for each abnormal region. Different abnormality coefficients correspond to different abnormal categories output by the coronary artery lesion morphology classification model.

[0072] Coronary angiography risk parameters were determined based on the standard deviation of the stenosis coefficients of multiple vascular segments and the standard deviation of the abnormal coefficients of multiple abnormal regions.

[0073] Optionally, the determination of cardiac risk parameters based on coronary angiography risk parameters and electrocardiogram risk parameters includes:

[0074] Obtain echocardiographic images of the target entity;

[0075] Echocardiogram images are input into a cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region and the atrioventricular cavity wall region that surrounds the cardiac atrioventricular region;

[0076] Obtain the outer and inner contours of the cavity wall region of the chamber;

[0077] By passing through multiple outer contour points on the outer contour of the cavity wall and intersecting the inner contour of the cavity wall with the lines, multiple intersection points corresponding to the multiple outer contour points are obtained;

[0078] Obtain the first straight-line distance between each outer contour point and its corresponding intersection point, thus obtaining multiple first straight-line distances corresponding to multiple outer contour points;

[0079] The maximum value among multiple first linear distances is determined as the thickness of the cardiac atrioventricular cavity wall region;

[0080] Echocardiographic risk parameters are determined based on the thickness of the cardiac atrioventricular cavity wall region.

[0081] Cardiac risk parameters are determined based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0082] Optionally, determining the echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region includes:

[0083] Obtain the minimum circumcircle of the atrioventricular region of the heart;

[0084] Obtain the atrioventricular contour of the cardiac atrioventricular region;

[0085] Calculate the second straight-line distance between multiple room contour points on the room contour and the center of the smallest circumcircle to obtain multiple second straight-line distances corresponding to multiple room contour points;

[0086] The characterization value of cardiac atrioventricular irregularity is determined based on the standard deviation of multiple second straight-line distances;

[0087] Echocardiographic risk parameters are determined based on the thickness of the atrioventricular cavity wall region and the atrioventricular irregularity characterization value.

[0088] Optionally, determining the cardiac atrioventricular irregularity characterization value based on the standard deviation of multiple second straight-line distances includes:

[0089] The minimum circumscribed circle is divided into multiple sector regions to obtain room-room sub-regions within the multiple sector regions;

[0090] Obtain the area difference between the sector region and the corresponding room sub-region to obtain the area difference between multiple sector regions;

[0091] The area standard deviation is determined based on the area of ​​the multiple room-divided sub-regions and the multiple area differences;

[0092] The sum of the standard deviation of the area and the standard deviation of the distances between multiple second lines was determined as the characterization value of cardiac atrioventricular irregularities.

[0093] Optionally, the determination of cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters includes:

[0094] Obtain multiple baseline features of the target entity, including age, gender, history of heart disease, history of heart surgery, whether smoking, and whether drinking alcohol;

[0095] Input multiple baseline features of the target entity into a pre-defined decision tree model to obtain baseline risk parameters;

[0096] Cardiac risk parameters were determined based on baseline risk parameters, echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0097] Thirdly, this application provides a computer device, the computer device comprising:

[0098] One or more processors;

[0099] Memory; and

[0100] One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for determining cardiac risk parameters as described in any one of the first aspects.

[0101] Fourthly, this application provides a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to perform the steps in the method for determining cardiac risk parameters as described in any one of the first aspects.

[0102] This application provides a method and apparatus for determining cardiac risk parameters. The method includes: acquiring multiple lead electrocardiogram (ECG) vector signals of a target entity; converting the multiple lead ECG vector signals into multiple time-domain waveforms; acquiring the waveform difference between the maximum and minimum values ​​of each time-domain waveform, obtaining multiple waveform differences; acquiring the time taken for each time-domain waveform to reach its maximum value, obtaining multiple time takes; acquiring the time interval between two adjacent maximum values ​​on each time-domain waveform, obtaining multiple time intervals; determining ECG risk parameters based on the standard deviation and maximum value of the multiple waveform maximum values, the standard deviation and maximum value of the multiple waveform differences, the standard deviation and average value of the multiple time intervals, and the standard deviation and average value of the multiple time takes; and determining cardiac risk parameters based on the ECG risk parameters. This application can improve the accuracy of determining cardiac risk parameters. Attached Figure Description

[0103] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0104] Figure 1 is a schematic diagram of a system for determining cardiac risk parameters provided in an embodiment of this application;

[0105] Figure 2 is a flowchart illustrating an embodiment of the method for determining cardiac risk parameters provided in this application.

[0106] Figure 3 is a schematic diagram of coronary angiography image segmentation in one embodiment of the method for determining cardiac risk parameters provided in this application;

[0107] Figure 4 is a schematic diagram of an embodiment of the cardiac risk parameter determination device provided in this application.

[0108] Figure 5 is a schematic diagram of an embodiment of the computer device provided in this application. Detailed Implementation

[0109] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0110] In the description of this application, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are used only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0111] In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0112] This application provides a method and apparatus for determining cardiac risk parameters, which will be described in detail below.

[0113] Please refer to Figure 1. Figure 1 is a schematic diagram of a system for determining cardiac risk parameters provided in an embodiment of this application. The system for determining cardiac risk parameters may include a computer device 100, which integrates a device for determining cardiac risk parameters.

[0114] In this embodiment, the computer device 100 can be a standalone server, a server network, or a server cluster. For example, the computer device 100 described in this embodiment includes, but is not limited to, a computer, a network host, a single network server, a set of multiple network servers, or a cloud server composed of multiple servers. The cloud server is composed of a large number of computers or network servers based on cloud computing.

[0115] In this embodiment, the computer device 100 described above can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device 100 can be a desktop computer, a portable computer, a network server, a handheld computer (Personal Digital Assistant, PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc. This embodiment does not limit the type of computer device 100.

[0116] Those skilled in the art will understand that the application environment shown in Figure 1 is only one application scenario of the present application and does not constitute a limitation on the application scenario of the present application. Other application environments may include more or fewer computer devices than those shown in Figure 1. For example, only one computer device is shown in Figure 1. It is understood that the cardiac risk parameter determination system may also include one or more other computer devices capable of processing data, which are not specifically limited here.

[0117] In addition, as shown in Figure 1, the system for determining cardiac risk parameters may also include a memory 200 for storing data.

[0118] It should be noted that the schematic diagram of the cardiac risk parameter determination system shown in Figure 1 is merely an example. The cardiac risk parameter determination system and scenario described in this application embodiment are for the purpose of more clearly illustrating the technical solution of this application embodiment and do not constitute a limitation on the technical solution provided in this application embodiment. As those skilled in the art will know, with the evolution of the cardiac risk parameter determination system and the emergence of new business scenarios, the technical solution provided in this application embodiment is also applicable to similar technical problems.

[0119] First, this application provides a method for determining cardiac risk parameters. The method includes: acquiring multiple lead electrocardiogram (ECG) vector signals of a target entity; converting the multiple lead ECG vector signals into multiple time-domain waveforms; acquiring the waveform difference between the maximum and minimum values ​​of each time-domain waveform to obtain multiple waveform differences; acquiring the time taken for each time-domain waveform to reach its maximum value to obtain multiple time takes; acquiring the time interval between two adjacent maximum values ​​of each time-domain waveform to obtain multiple time intervals; determining ECG risk parameters based on the standard deviation and maximum value of the multiple waveform maximum values, the standard deviation and maximum value of the multiple waveform differences, the standard deviation and average value of the multiple time intervals, and the standard deviation and average value of the multiple time takes; and determining cardiac risk parameters based on the ECG risk parameters.

[0120] As shown in Figure 2, Figure 2 is a schematic flowchart of an embodiment of the method for determining cardiac risk parameters in this application. The method for determining cardiac risk parameters includes the following steps S201-S207:

[0121] S201. Obtain multiple lead ECG vector signals of the target entity.

[0122] In this embodiment, the target entity can be any patient or entity whose electrocardiogram (ECG) is being collected. A vector ECG signal acquisition system is used to collect the raw 12-lead ECG vector signal of the target entity. This raw 12-lead ECG vector signal is then amplified and interference signals are filtered to obtain the final 12-lead ECG vector signal. Electrodes are placed at different locations on the body and connected to the positive and negative terminals of the electrocardiograph's galvanometer via lead wires. This circuit connection method for recording an ECG is called an ECG lead. The widely adopted internationally accepted lead system is called the conventional 12-lead system, which includes limb leads connected to the limbs and chest leads connected to the chest.

[0123] S202. Convert multiple lead ECG vector signals into multiple time-domain waveforms.

[0124] Specifically, the twelve-lead ECG vector signal is converted into twelve time-domain waveforms, i.e., twelve time-domain waveforms. The functions corresponding to each time-domain waveform are shown in the following formulas.

[0125]

[0126] S203. Obtain the waveform difference between the maximum and minimum waveform values ​​of each time-domain waveform graph to obtain multiple waveform differences.

[0127] Specifically, extract the maximum value of each time-domain waveform and compile it into a list, using the following formula: list1 = [max(f1(t), max(f2(t)...max(f...]] 12 (t)].

[0128] Extract the difference between the maximum and minimum values ​​of each time-domain waveform and compile them into a list, as shown in the following formula:

[0129] list2=[max(f1(t))-min(f1(t)),max(f2(t))-min(f2(t))…max(f 12 (t))-min(f 12 (t))]

[0130] S204. Obtain the time taken for each time-domain waveform to reach its maximum value, thus obtaining multiple time-taking times.

[0131] In this embodiment of the application, the time taken for the time-domain waveform to reach its maximum value from time 0 is obtained, resulting in multiple time values ​​maxt. iThe following list is created: list4 = [maxt1, maxt2, ..., maxt...] 12 ].

[0132] S205. Obtain the time interval between the maximum values ​​of two adjacent waveforms on each time-domain waveform graph to obtain multiple time intervals.

[0133] The curves on the time-domain waveform graph cycle according to a certain period. The time intervals between the maximum values ​​of two adjacent waveforms on each time-domain waveform graph are obtained, resulting in multiple time intervals. These multiple time intervals are compiled into a list as follows: list3 = [Δt1, Δt2…Δt…] 12 ].

[0134] S206. Determine ECG risk parameters based on the standard deviation and maximum value of multiple waveform maximum values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and maximum value of multiple time intervals, and the standard deviation and maximum value of multiple time periods.

[0135] In this embodiment, the electrocardiogram risk parameter label1 is obtained by summing the ratio of the standard deviation of multiple waveform maximum values ​​to the maximum value, the ratio of the standard deviation of multiple waveform differences to the maximum value, the ratio of the standard deviation of multiple time intervals to the mean, and the ratio of the standard deviation of multiple time periods to the mean. The formula is as follows:

[0136]

[0137] Among them, list1 contains multiple waveform maximum values, list2 contains multiple waveform differences, list3 contains multiple time intervals, and list4 contains multiple time elapsed values.

[0138] S207. Determine cardiac risk parameters based on electrocardiogram risk parameters.

[0139] In this embodiment of the application, the cardiac risk parameter δ is determined based on the electrocardiogram risk parameter label1, including:

[0140] (1) Obtain multiple coronary angiography images of the target entity.

[0141] (2) Input multiple coronary angiography images into the coronary artery vascular tree segmentation model to obtain the vascular segmentation region on each coronary angiography image.

[0142] The coronary artery tree segmentation model was trained using the Unet++ model as the basic neural network structure.

[0143] Specifically, a deep learning model is used to filter multiple coronary angiography images, retaining clear images. The filtered coronary angiography images are then input into the coronary artery vascular tree segmentation model to obtain the vascular segmentation region on each coronary angiography image.

[0144] (3) Three-dimensional reconstruction of the segmented vascular regions on multiple coronary angiography images was performed to obtain a three-dimensional vascular model.

[0145] (4) Obtain the center line of the blood vessel in the three-dimensional model of the blood vessel.

[0146] Specifically, the centerline of the blood vessel in the 3D model is obtained based on the VMTK algorithm. Points on the centerline are the centers of the cross-sections of the 3D blood vessel model.

[0147] (5) Detect the corner points of the blood vessel centerline and break the blood vessel centerline at the detected corner points to obtain multiple blood vessel centerline segments and corresponding blood vessel lumen segments, wherein the blood vessel centerline segment is the centerline of the blood vessel lumen segment.

[0148] The 3D model of a blood vessel consists of multiple blood vessels. The 3D model of a blood vessel is broken into multiple central line segments of blood vessels and corresponding vascular lumen segments.

[0149] (6) Determine multiple points on the central line segment of the blood vessel as target points, draw cross-sections of the blood vessel lumen through the target points, and obtain the cross-sectional areas of multiple cross-sections corresponding to multiple points.

[0150] (7) The ratio of the minimum value among multiple cross-sectional areas to the average value among multiple cross-sectional areas is determined as the vascular stenosis coefficient of the vascular segment, thus obtaining the vascular stenosis coefficient of multiple vascular segments.

[0151] Specifically, the formula for calculating the stenosis coefficient F(it) of vascular segment i is as follows:

[0152] F(it)=S(1-i)min / S(1-i)ave

[0153] Wherein, S(1-i)min is the minimum value among multiple cross-sectional areas on the vascular segment i, and S(1-i)ave is the average value of multiple cross-sectional areas on the vascular segment i.

[0154] (8) Determine coronary angiography risk parameters based on the stenosis coefficient of multiple vascular segments.

[0155] In one specific embodiment, the standard deviation of the stenosis coefficient of multiple vascular segments is determined as the coronary angiography risk parameter label2.

[0156] In another specific embodiment, coronary angiography risk parameters are determined based on the stenosis coefficients of multiple vascular segments, including: inputting multiple coronary angiography images into a coronary artery lesion morphology detection model to obtain multiple abnormal regions; inputting images within the multiple abnormal regions into a coronary artery lesion morphology classification model to obtain the abnormality coefficients of each abnormal region, wherein different abnormality coefficients correspond to different abnormal categories output by the coronary artery lesion morphology classification model; and determining the coronary angiography risk parameters based on the standard deviations of the stenosis coefficients of multiple vascular segments and the standard deviations of the abnormality coefficients of multiple abnormal regions.

[0157] Specifically, a coronary artery lesion morphology detection model was trained, with three cardiovascular experts annotating the acquired coronary angiography images, preferentially using the YOLOv3 object detection model. A coronary artery lesion morphology classification model was trained, preferentially using Rsenet152, with labels R(i) of 1, 2, 3, 4, 5, 6, and 7, corresponding to the categories of stenosis, occlusion, calcification, thrombosis, dissection, aneurysm, and other, with multiple lesions within the same category.

[0158] In this embodiment, the sum of the standard deviations of the stenosis coefficients of multiple vascular segments and the standard deviations of the abnormal coefficients of multiple abnormal regions is determined as the coronary angiography risk parameter. The formula for calculating the coronary angiography risk parameter label2 is as follows:

[0159] label2=std(R(i))+std(F(1-i))

[0160] Where F(1-i) is the stenosis coefficient of vascular segment i, and R(i) is the abnormality coefficient of the abnormal region on vascular segment i.

[0161] (9) Determine cardiac risk parameters based on coronary angiography risk parameters and electrocardiogram risk parameters.

[0162] In one specific embodiment, the coronary angiography risk parameter label2 and the electrocardiogram risk parameter label1 are weighted and summed to obtain the cardiac risk parameter δ.

[0163] In another specific embodiment, cardiac risk parameters are determined based on coronary angiography risk parameters and electrocardiogram risk parameters, including:

[0164] (1) Obtain echocardiographic images of the target entity.

[0165] The standard size for echocardiogram images is 224*224.

[0166] (2) Input the echocardiogram image into the cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region and the atrioventricular cavity wall region that surrounds the cardiac atrioventricular region.

[0167] Specifically, a cardiac atrioventricular structure segmentation model was trained, with a cardiovascular expert annotating the contours of the cardiac atrioventricular walls. The Unet++ target segmentation model was preferentially selected as the cardiac atrioventricular structure segmentation model.

[0168] As shown in Figure 3, the echocardiogram image is input into the cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region 15 and the atrioventricular cavity wall region 16 that surrounds the cardiac atrioventricular region 15.

[0169] (3) Obtain the outer contour and inner contour of the cavity wall region of the atrioventricular cavity.

[0170] (4) The lines through multiple outer contour points on the outer contour of the cavity wall intersect with the inner contour of the cavity wall to obtain multiple intersection points corresponding to multiple outer contour points.

[0171] (5) Obtain the first straight-line distance between each outer contour point and its corresponding intersection point, and obtain multiple first straight-line distances corresponding to multiple outer contour points.

[0172] (6) The maximum value among multiple first straight-line distances is determined as the thickness of the atrioventricular cavity wall region.

[0173] (7) Determine echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region.

[0174] In one specific embodiment, the thickness of the atrioventricular cavity wall region is determined as the echocardiographic risk parameter label3. The thickness of the atrioventricular cavity wall region is Δdr.

[0175] In another specific embodiment, determining echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region includes: obtaining the minimum circumcircle of the atrioventricular region; obtaining the atrioventricular contour of the atrioventricular region; calculating the second straight-line distances between multiple atrioventricular contour points on the atrioventricular contour and the center of the minimum circumcircle, obtaining multiple second straight-line distances corresponding to multiple atrioventricular contour points; determining the atrioventricular irregularity characterization value based on the standard deviation of the multiple second straight-line distances; and determining the echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region and the atrioventricular irregularity characterization value. The atrioventricular contour is the inner contour of the cavity wall. As shown in Figure 3, the minimum circumcircle 17 is obtained.

[0176] In another specific embodiment, the difference between the radius of the smallest circumcircle and each of the second straight-line distances is determined as a plurality of third straight-line distances, and the cardiac atrioventricular irregularity characterization value is determined based on the standard deviation of the plurality of third straight-line distances.

[0177] Furthermore, the characterization value of cardiac atrioventricular irregularity is determined based on the standard deviation of multiple second straight-line distances, including: dividing the smallest circumcircle into multiple sector regions to obtain atrioventricular sub-regions within the multiple sector regions; obtaining the area difference between the sector regions and the corresponding atrioventricular sub-regions to obtain the area difference values ​​corresponding to the multiple sector regions; determining the area standard deviation based on the area of ​​the multiple atrioventricular sub-regions and the multiple area differences; and determining the sum of the area standard deviation and the standard deviation of the multiple second straight-line distances as the characterization value of cardiac atrioventricular irregularity.

[0178] Specifically, there are 8 sector-shaped regions, but other numbers are also possible. These sector-shaped regions and their corresponding room / chamber sub-regions (Area) are also represented. j The area difference is calculated using the following formula:

[0179]

[0180] Where, r max The radius of the smallest circumcircle

[0181] The formula for calculating the area standard deviation (stdm) is as follows:

[0182]

[0183] Specifically, the differences between the radius of the smallest circumcircle and each of the second straight-line distances are determined as multiple third straight-line distances. The area standard deviation is determined based on the area of ​​multiple atrioventricular sub-regions and the differences between these areas. The sum of the area standard deviation and the standard deviations of the multiple third straight-line distances is determined as the characteristic value of cardiac atrioventricular irregularity. As shown in Figure 3, the multiple third straight-line distances are d... i The formula for calculating the cardiac atrioventricular irregularity characteristic value S is as follows:

[0184]

[0185] Specifically, the echocardiographic risk parameter label3 is obtained by weighted summation of the thickness of the atrioventricular cavity wall region and the characterization values ​​of atrioventricular irregularities. The formula for calculating the echocardiographic risk parameter label3 is as follows:

[0186] label3=θ1Δdr+θ2·S

[0187] Where Δdr is the thickness of the atrioventricular cavity wall region, and S is the value representing the irregularity of the atrioventricular cavity.

[0188] (8) Determine cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters and electrocardiogram risk parameters.

[0189] Furthermore, cardiac risk parameters are determined based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiographic risk parameters, including:

[0190] (1) Obtain multiple baseline features of the target entity, including age, gender, history of heart disease, history of heart surgery, smoking, and drinking.

[0191] Specifically, the collected patient baseline information will be processed as follows:

[0192]

[0193]

[0194]

[0195]

[0196]

[0197]

[0198] (2) Input multiple baseline features of the target entity into a preset decision tree model to obtain baseline risk parameters.

[0199] Specifically, the baseline risk parameter is label4.

[0200] (3) Determine cardiac risk parameters based on baseline risk parameters, echocardiographic risk parameters, coronary angiography risk parameters and electrocardiogram risk parameters.

[0201] In this embodiment of the application, the cardiac risk parameters are obtained by weighted summation of the baseline risk parameter label3, the echocardiographic risk parameter, the coronary angiography risk parameter, and the electrocardiogram risk parameter.

[0202] The formula for calculating the cardiac risk parameter δ is as follows:

[0203]

[0204] Where, λ i The weight parameters are obtained by training machine learning models such as decision trees and random forests.

[0205] Furthermore, the preoperative cardiac risk level is determined based on the cardiac risk parameter δ. The determination method is as follows:

[0206]

[0207] To better implement the method for determining cardiac risk parameters in the embodiments of this application, based on the method for determining cardiac risk parameters, this application also provides a device for determining cardiac risk parameters, as shown in Figure 4. The device for determining cardiac risk parameters includes:

[0208] The first acquisition unit 301 is used to acquire multiple lead ECG vector signals of the target entity;

[0209] The conversion unit 302 is used to convert the multiple lead ECG vector signals into multiple time-domain waveforms;

[0210] The second acquisition unit 303 is used to acquire the waveform difference between the maximum and minimum values ​​of each time-domain waveform graph, and obtain multiple waveform differences.

[0211] The third acquisition unit 304 is used to acquire the time taken for each time domain waveform to reach the maximum value of the waveform, and obtain multiple time taken.

[0212] The fourth acquisition unit 305 is used to acquire the time interval between the maximum values ​​of two adjacent waveforms on each time domain waveform diagram, thereby obtaining multiple time intervals;

[0213] The first determining unit 306 is used to determine electrocardiogram risk parameters based on the standard deviation and maximum value of multiple waveform maximum values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and average value of multiple time intervals, and the standard deviation and average value of multiple time periods.

[0214] The second determining unit 307 is used to determine cardiac risk parameters based on electrocardiogram risk parameters.

[0215] Optionally, the determination of cardiac risk parameters based on electrocardiogram risk parameters includes:

[0216] Acquire multiple coronary angiography images of the target entity;

[0217] Multiple coronary angiography images are input into the coronary artery vascular tree segmentation model to obtain the vascular segmentation region on each coronary angiography image;

[0218] Three-dimensional reconstruction of segmented vascular regions from multiple coronary angiography images was performed to obtain a three-dimensional vascular model;

[0219] Obtain the centerline of the blood vessel in the 3D model of the blood vessel;

[0220] Corner point detection is performed on the blood vessel centerline, and the blood vessel centerline is broken at the detected corner points to obtain multiple blood vessel centerline segments and corresponding blood vessel lumen segments, wherein the blood vessel centerline segment is the centerline of the blood vessel lumen segment;

[0221] Multiple points on the central line segment of the blood vessel are respectively identified as target points. A cross-section of the blood vessel lumen segment is drawn through the target points to obtain the cross-sectional area of ​​multiple cross-sections corresponding to multiple points.

[0222] The ratio of the minimum value among multiple cross-sectional areas to the average value among multiple cross-sectional areas is determined as the vascular stenosis coefficient of the vascular segment, thus obtaining the vascular stenosis coefficients of multiple vascular segments.

[0223] Coronary angiography risk parameters are determined based on the stenosis coefficient of multiple vascular segments;

[0224] Cardiac risk parameters are determined based on coronary angiography risk parameters and electrocardiogram risk parameters.

[0225] Optionally, the determination of coronary angiography risk parameters based on the vascular stenosis coefficient of multiple vascular segments includes:

[0226] Multiple coronary angiography images were input into the coronary artery lesion morphology detection model to obtain multiple abnormal regions;

[0227] Images from multiple abnormal regions are input into a coronary artery lesion morphology classification model to obtain the abnormality coefficients for each abnormal region. Different abnormality coefficients correspond to different abnormal categories output by the coronary artery lesion morphology classification model.

[0228] Coronary angiography risk parameters were determined based on the standard deviation of the stenosis coefficients of multiple vascular segments and the standard deviation of the abnormal coefficients of multiple abnormal regions.

[0229] Optionally, the determination of cardiac risk parameters based on coronary angiography risk parameters and electrocardiogram risk parameters includes:

[0230] Obtain echocardiographic images of the target entity;

[0231] Echocardiogram images are input into a cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region and the atrioventricular cavity wall region that surrounds the cardiac atrioventricular region;

[0232] Obtain the outer and inner contours of the cavity wall region of the chamber;

[0233] By passing through multiple outer contour points on the outer contour of the cavity wall and intersecting the inner contour of the cavity wall with the lines, multiple intersection points corresponding to the multiple outer contour points are obtained;

[0234] Obtain the first straight-line distance between each outer contour point and its corresponding intersection point, thus obtaining multiple first straight-line distances corresponding to multiple outer contour points;

[0235] The maximum value among multiple first linear distances is determined as the thickness of the cardiac atrioventricular cavity wall region;

[0236] Echocardiographic risk parameters are determined based on the thickness of the cardiac atrioventricular cavity wall region.

[0237] Cardiac risk parameters are determined based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0238] Optionally, determining the echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region includes:

[0239] Obtain the minimum circumcircle of the atrioventricular region of the heart;

[0240] Obtain the atrioventricular contour of the cardiac atrioventricular region;

[0241] Calculate the second straight-line distance between multiple room contour points on the room contour and the center of the smallest circumcircle to obtain multiple second straight-line distances corresponding to multiple room contour points;

[0242] The characterization value of cardiac atrioventricular irregularity is determined based on the standard deviation of multiple second straight-line distances;

[0243] Echocardiographic risk parameters are determined based on the thickness of the atrioventricular cavity wall region and the atrioventricular irregularity characterization value.

[0244] Optionally, determining the cardiac atrioventricular irregularity characterization value based on the standard deviation of multiple second straight-line distances includes:

[0245] The minimum circumscribed circle is divided into multiple sector regions to obtain room-room sub-regions within the multiple sector regions;

[0246] Obtain the area difference between the sector region and the corresponding room sub-region to obtain the area difference between multiple sector regions;

[0247] The area standard deviation is determined based on the area of ​​the multiple room-divided sub-regions and the multiple area differences;

[0248] The sum of the standard deviation of the area and the standard deviation of the distances between multiple second lines was determined as the characterization value of cardiac atrioventricular irregularities.

[0249] Optionally, the determination of cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters includes:

[0250] Obtain multiple baseline features of the target entity, including age, gender, history of heart disease, history of heart surgery, whether smoking, and whether drinking alcohol;

[0251] Input multiple baseline features of the target entity into a pre-defined decision tree model to obtain baseline risk parameters;

[0252] Cardiac risk parameters were determined based on baseline risk parameters, echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

[0253] This application also provides a computer device that integrates any of the cardiac risk parameter determination devices provided in this application. The computer device includes:

[0254] One or more processors;

[0255] Memory; and

[0256] One or more applications, wherein the applications are stored in memory and configured to be executed by a processor, wherein the steps of the method for determining cardiac risk parameters in any of the embodiments described above are performed.

[0257] Figure 5 shows a schematic diagram of the computer device involved in the embodiments of this application. Specifically:

[0258] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that the computer device structure shown in the figures does not constitute a limitation on the computer device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0259] Processor 401 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in memory 402, and by calling data stored in memory 402, thereby providing overall monitoring of the computer device. Optionally, processor 401 may include one or more processing cores; processor 401 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. Preferably, processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the aforementioned modem processor may not be integrated into processor 401.

[0260] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0261] The computer device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0262] The computer device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0263] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0264] Acquire multiple lead ECG vector signals of the target entity; convert the multiple lead ECG vector signals into multiple time-domain waveforms; obtain the waveform difference between the maximum and minimum waveform values ​​of each time-domain waveform, resulting in multiple waveform differences; obtain the time taken for each time-domain waveform to reach its maximum waveform value, resulting in multiple time takes; obtain the time interval between two adjacent maximum waveform values ​​on each time-domain waveform, resulting in multiple time intervals; determine ECG risk parameters based on the standard deviation and maximum value of multiple waveform maximum values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and average value of multiple time intervals, and the standard deviation and average value of multiple time takes; determine cardiac risk parameters based on the ECG risk parameters.

[0265] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0266] Therefore, embodiments of this application provide a computer-readable storage medium, which may include: read-only memory (ROM), random access memory (RAM), a disk, or an optical disk, etc. A computer program is stored thereon, and the computer program is loaded by a processor to execute the steps in any of the methods for determining cardiac risk parameters provided in embodiments of this application. For example, the computer program loaded by the processor can execute the following steps:

[0267] Acquire multiple lead ECG vector signals of the target entity; convert the multiple lead ECG vector signals into multiple time-domain waveforms; obtain the waveform difference between the maximum and minimum waveform values ​​of each time-domain waveform, resulting in multiple waveform differences; obtain the time taken for each time-domain waveform to reach its maximum waveform value, resulting in multiple time takes; obtain the time interval between two adjacent maximum waveform values ​​on each time-domain waveform, resulting in multiple time intervals; determine ECG risk parameters based on the standard deviation and maximum value of multiple waveform maximum values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and average value of multiple time intervals, and the standard deviation and average value of multiple time takes; determine cardiac risk parameters based on the ECG risk parameters.

[0268] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0269] In practice, each of the above units or structures can be implemented as an independent entity or can be arbitrarily combined to be implemented as the same or several entities. For the specific implementation of each of the above units or structures, please refer to the previous method embodiments, which will not be repeated here.

[0270] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0271] The above provides a detailed description of a method and apparatus for determining cardiac risk parameters provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for determining cardiac risk parameters, characterized in that, The method for determining cardiac risk parameters includes: acquiring multiple lead electrocardiogram (ECG) vector signals of the target entity; converting the multiple lead ECG vector signals into multiple time-domain waveforms; acquiring the waveform difference between the maximum and minimum waveform values ​​of each time-domain waveform, obtaining multiple waveform differences; acquiring the time taken for each time-domain waveform to reach its maximum waveform value, obtaining multiple time takes; acquiring the time interval between two adjacent maximum waveform values ​​on each time-domain waveform, obtaining multiple time intervals; determining ECG risk parameters based on the standard deviation and maximum value of the multiple waveform values, the standard deviation and maximum value of the multiple waveform differences, the standard deviation and average value of the multiple time intervals, and the standard deviation and average value of the multiple time takes; and determining cardiac risk parameters based on ECG risk parameters. The determination of cardiac risk parameters based on ECG risk parameters includes: acquiring multiple coronary angiography images of the target entity; inputting the multiple coronary angiography images into a coronary artery tree segmentation model. The process involves obtaining segmented vascular regions from each coronary angiography image; performing 3D reconstruction of the segmented vascular regions from multiple coronary angiography images to obtain a 3D vascular model; acquiring the vascular centerline of the 3D vascular model; performing corner detection on the vascular centerline and breaking the vascular centerline at the detected corners to obtain multiple vascular centerline segments and corresponding vascular lumen segments, where the vascular centerline segment is the centerline of the vascular lumen segment; determining multiple points on the vascular centerline segment as target points, constructing cross-sections of the vascular lumen segment through the target points to obtain the cross-sectional areas of multiple cross-sections corresponding to multiple points; determining the vascular stenosis coefficient of the vascular lumen segment by the ratio of the minimum value to the average value of the multiple cross-sectional areas; determining coronary angiography risk parameters based on the vascular stenosis coefficients of multiple vascular lumen segments; and determining cardiac risk parameters based on the coronary angiography risk parameters and electrocardiogram risk parameters.

2. The method for determining cardiac risk parameters according to claim 1, characterized in that, The method of determining coronary angiography risk parameters based on the stenosis coefficient of multiple vascular segments includes: inputting multiple coronary angiography images into a coronary artery lesion morphology detection model to obtain multiple abnormal regions; inputting images within the multiple abnormal regions into a coronary artery lesion morphology classification model to obtain the abnormality coefficient of each abnormal region, wherein different abnormality coefficients correspond to different abnormal categories output by the coronary artery lesion morphology classification model; and determining the coronary angiography risk parameters based on the standard deviation of the stenosis coefficient of multiple vascular segments and the standard deviation of the abnormality coefficient of multiple abnormal regions.

3. The method for determining cardiac risk parameters according to claim 1, characterized in that, The method for determining cardiac risk parameters based on coronary angiography risk parameters and electrocardiogram risk parameters includes: acquiring echocardiographic images of the target entity; inputting the echocardiographic images into a cardiac atrioventricular structure segmentation model to obtain the cardiac atrioventricular region and the atrioventricular cavity wall region surrounding the cardiac atrioventricular region; acquiring the outer contour and inner contour of the cavity wall region; intersecting the inner contour of the cavity wall with a line through multiple outer contour points on the outer contour of the cavity wall to obtain multiple intersection points corresponding to multiple outer contour points; acquiring a first straight-line distance between each outer contour point and its corresponding intersection point to obtain multiple first straight-line distances corresponding to multiple outer contour points; determining the maximum value among the multiple first straight-line distances as the thickness of the cardiac atrioventricular cavity wall region; determining echocardiographic risk parameters based on the thickness of the cardiac atrioventricular cavity wall region; and determining cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

4. The method for determining cardiac risk parameters according to claim 3, characterized in that, The method for determining echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region includes: obtaining the minimum circumcircle of the atrioventricular region; obtaining the atrioventricular contour of the atrioventricular region; calculating the second straight-line distances between multiple atrioventricular contour points on the atrioventricular contour and the center of the minimum circumcircle, thereby obtaining multiple second straight-line distances corresponding to the multiple atrioventricular contour points; determining the atrioventricular irregularity characterization value based on the standard deviation of the multiple second straight-line distances; and determining the echocardiographic risk parameters based on the thickness of the atrioventricular cavity wall region and the atrioventricular irregularity characterization value.

5. The method for determining cardiac risk parameters according to claim 4, characterized in that, The method of determining the cardiac atrioventricular irregularity characterization value based on the standard deviation of multiple second straight-line distances includes: dividing the minimum circumcircle into multiple sector regions to obtain atrioventricular segmentation sub-regions within the multiple sector regions; obtaining the area difference between the sector regions and the corresponding atrioventricular segmentation sub-regions to obtain the area difference values ​​corresponding to the multiple sector regions; determining the area standard deviation based on the area of ​​the multiple atrioventricular segmentation sub-regions and the multiple area differences; and determining the sum of the area standard deviation and the standard deviation of the multiple second straight-line distances as the cardiac atrioventricular irregularity characterization value.

6. The method for determining cardiac risk parameters according to claim 3, characterized in that, The method for determining cardiac risk parameters based on echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters includes: acquiring multiple baseline features of the target entity, including age, gender, history of heart disease, history of cardiac surgery, smoking status, and alcohol consumption; inputting the multiple baseline features of the target entity into a preset decision tree model to obtain baseline risk parameters; and determining cardiac risk parameters based on the baseline risk parameters, echocardiographic risk parameters, coronary angiography risk parameters, and electrocardiogram risk parameters.

7. A device for determining cardiac risk parameters, characterized in that, The device for determining cardiac risk parameters includes: a first acquisition unit for acquiring multiple lead ECG vector signals of the target entity; a conversion unit for converting the multiple lead ECG vector signals into multiple time-domain waveforms; a second acquisition unit for acquiring the waveform difference between the maximum and minimum waveform values ​​of each time-domain waveform, obtaining multiple waveform differences; a third acquisition unit for acquiring the time taken for each time-domain waveform to reach its maximum waveform value, obtaining multiple time taken; a fourth acquisition unit for acquiring the time interval between two adjacent maximum waveform values ​​on each time-domain waveform, obtaining multiple time intervals; a first determination unit for determining ECG risk parameters based on the standard deviation and maximum value of multiple waveform values, the standard deviation and maximum value of multiple waveform differences, the standard deviation and average value of multiple time intervals, and the standard deviation and average value of multiple time taken; a second determination unit for determining cardiac risk parameters based on the ECG risk parameters; wherein, the second determination unit is further used to acquire multiple coronary angiography images of the target entity; Multiple coronary angiography images are input into a coronary artery segmentation model to obtain segmented vascular regions on each coronary angiography image. Three-dimensional reconstruction is performed on the segmented vascular regions from the multiple coronary angiography images to obtain a three-dimensional vascular model. The vascular centerline of the three-dimensional vascular model is obtained. Corner detection is performed on the vascular centerline, and the vascular centerline is broken at the detected corners to obtain multiple vascular centerline segments and corresponding vascular lumen segments, where the vascular centerline segment is the centerline of the vascular lumen segment. Multiple points on the vascular centerline segment are determined as target points, and cross-sections of the vascular lumen segment are drawn through the target points to obtain the cross-sectional areas of multiple cross-sections corresponding to multiple points. The ratio of the minimum value to the average value of the multiple cross-sectional areas is determined as the vascular stenosis coefficient of the vascular lumen segment, resulting in multiple vascular lumen stenosis coefficients. Coronary angiography risk parameters are determined based on the vascular stenosis coefficients of multiple vascular lumen segments. Cardiac risk parameters are determined based on the coronary angiography risk parameters and electrocardiogram risk parameters.

8. A computer device, characterized in that, The computer device includes: one or more processors; memory; and one or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to implement the method for determining cardiac risk parameters according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It contains a computer program that is loaded by a processor to perform the steps in the method for determining cardiac risk parameters according to any one of claims 1 to 6.

Images