CN112862827A

CN112862827A - Method, device, terminal and storage medium for determining opening parameters of left atrial appendage

Info

Publication number: CN112862827A
Application number: CN202110453334.4A
Authority: CN
Inventors: 高琪; 鲁云霞; 魏润杰
Original assignee: Hangzhou Shengshi Technology Co ltd
Current assignee: Hangzhou Shengshi Technology Co ltd
Priority date: 2021-04-26
Filing date: 2021-04-26
Publication date: 2021-05-28
Anticipated expiration: 2041-04-26
Also published as: CN112862827B

Abstract

The embodiment of the application provides a method, a device, a terminal and a storage medium for determining an opening parameter of a left atrial appendage, wherein the method comprises the following steps: acquiring left atrium point cloud data and left auricle point cloud data in a three-dimensional space based on the acquired thoracic cavity tomography image; determining an intersecting curved surface where the left atrium and the left auricle intersect on the basis of the left atrium point cloud data and the left auricle point cloud data; determining at least two intersecting planes based on a central point of an intersecting surface in a three-dimensional space, a first target point on the intersecting surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting surface in upper and lower spaces of the three-dimensional space; based on the at least two intersecting planes, an opening parameter of the left atrial appendage is determined.

Description

Method, device, terminal and storage medium for determining opening parameters of left atrial appendage

Technical Field

The present application relates to, but not limited to, the field of medical image processing technologies, and in particular, to a method, an apparatus, a terminal, and a storage medium for determining an opening parameter of a left atrial appendage.

Background

Atrial Fibrillation (AF) is one of the most common cardiac arrhythmias, in terms of AF disease. Atrial fibrillation forms many thrombi in the left atrium, and atrial fibrillation often causes ischemic stroke, in which more than ninety percent of emboli originate from the left atrial appendage, and embolic events occur. Therefore, various parameter indexes of the left auricle, such as the opening position of the left auricle, the opening area of the left auricle, the volume of the left auricle, the parting dimension of the left auricle and the like, are combined with the three-dimensional structure in the left atrial cavity and pulmonary veins, and the blood flow characteristic in the auricle is analyzed to measure the risk degree of thrombosis in the auricle, so that comprehensive, reliable and intuitive reference data are provided for left auricle plugging, and a clinician can conveniently and rapidly evaluate the risk of cerebral apoplexy of a patient. It can be seen that the calculation of the left atrial appendage opening area provides a powerful basis for the clinician to quickly assess the risk of stroke in a patient.

In the related art, when determining parameters of the left atrial appendage opening, such as the opening area, the determination can be achieved only in a single mode that the longest diameter and the shortest diameter of the intersecting plane of the left atrial appendage and the left atrium are obtained, and the longest diameter and the shortest diameter are input into an ellipse formula. The application provides a novel method for determining the opening parameter of the left atrial appendage.

Disclosure of Invention

The embodiment of the application provides a method, a device, a terminal and a storage medium for determining an opening parameter of a left atrial appendage.

The technical scheme of the embodiment of the application is realized as follows:

in a first aspect, an embodiment of the present application provides a method for determining an opening parameter of a left atrial appendage, where the method includes:

acquiring left atrium point cloud data and left auricle point cloud data in a three-dimensional space based on the acquired thoracic cavity tomography image;

determining an intersecting curved surface where the left atrium and the left auricle intersect based on the left atrial point cloud data and the left auricle point cloud data;

determining at least two intersecting planes based on a central point of the intersecting curved surface in the three-dimensional space, a first target point on the intersecting curved surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting curved surface in upper and lower spaces of the three-dimensional space;

Determining an opening parameter of the left atrial appendage based on the at least two intersecting planes.

In a second aspect, an embodiment of the present application provides an apparatus for determining an opening parameter of a left atrial appendage, the apparatus including:

the acquisition module is used for acquiring left atrium point cloud data and left auricle point cloud data in a three-dimensional space based on the acquired thoracic cavity tomography image;

the processing unit is used for determining an intersecting curved surface where the left atrium and the left auricle intersect on the basis of the left atrium point cloud data and the left auricle point cloud data;

the processing unit is further configured to determine at least two intersecting planes based on a center point of the intersecting curved surface in the three-dimensional space, a first target point on the intersecting curved surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting curved surface in upper and lower spaces of the three-dimensional space;

the processing unit is further configured to determine an opening parameter of the left atrial appendage based on the at least two intersecting planes.

In a third aspect, an embodiment of the present application provides a terminal, where the terminal includes:

a memory for storing executable instructions;

and the processor is used for executing the executable instructions stored in the memory so as to realize the opening parameter determination method of the left atrial appendage.

In a fourth aspect, embodiments of the present application provide a storage medium storing one or more programs, which are executable by one or more processors to implement the steps of the above-mentioned method for determining an opening parameter of a left atrial appendage.

The application of the embodiment of the application realizes the following beneficial effects: based on the medical heart model, a plurality of intersecting planes are determined based on the intersecting curved surfaces which are intersected in the obtained three-dimensional space, so that opening parameters of the left auricle are determined according to the plurality of intersecting planes, and accurate and reliable reference data are provided for left auricle occlusion.

According to the method, the device, the terminal and the storage medium for determining the opening parameter of the left auricle, the left atrial appendage point cloud data and the left auricle point cloud data in the three-dimensional space are acquired based on the acquired thoracic cavity tomography image; determining an intersecting curved surface where the left atrium and the left auricle intersect on the basis of the left atrium point cloud data and the left auricle point cloud data; determining at least two intersecting planes based on a central point of an intersecting surface in a three-dimensional space, a first target point on the intersecting surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting surface in upper and lower spaces of the three-dimensional space; determining an opening parameter of the left atrial appendage based on the at least two intersecting planes; that is, left atrial appendage point cloud data and left atrial appendage point cloud data in a three-dimensional space are obtained based on a thoracic tomography image, and opening parameters of the left atrial appendage are determined by determining at least two intersecting planes on an intersecting curved surface where the left atrial appendage and the left atrial appendage intersect; so, provide accurate intersection plane for the opening parameter of calculation left atrial appendage to calculate accurate left atrial appendage opening parameter, further, can provide comprehensive, reliable reference data for left atrial appendage shutoff art, be favorable to clinician to carry out quick aassessment to patient's cerebral apoplexy's risk.

Drawings

Fig. 1 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present disclosure;

fig. 2A is a schematic view of a thoracic tomography image in a far field provided by an embodiment of the present application;

FIG. 2B is a schematic view of a thoracic tomography image in a near field provided by an embodiment of the present application;

FIG. 3A is a schematic representation of the aorta position provided by an embodiment of the present application;

fig. 3B is a schematic diagram of a partial image in a thoracic tomography image captured based on an aorta position according to an embodiment of the present application;

fig. 3C is a schematic diagram of an embodiment of an atrial appendage tag made according to the present disclosure;

FIG. 4 is a schematic view of the intersecting curved surface of the left atrium and the left atrial appendage provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of a cutting plane and an intersecting plane provided by an embodiment of the present application;

fig. 6 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

fig. 7 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

fig. 8 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

FIG. 9 is a schematic view of normal vector determination of the intersection plane of the left atrium and the left atrial appendage provided by an embodiment of the present application;

FIG. 10 is a schematic view of an intersection plane of a left atrial model and a left atrial appendage model provided by an embodiment of the present application;

fig. 11 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

fig. 12 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

fig. 13 is a schematic diagram of a left atrial appendage model and a cutting plane provided in an embodiment of the present application;

FIG. 14 is a schematic diagram of a left atrial model, a left atrial appendage model, and an aorta model provided by an embodiment of the present disclosure;

fig. 15 is a schematic flow chart of an alternative method for determining an opening parameter of a left atrial appendage according to an embodiment of the present application;

fig. 16 is a schematic structural diagram of an apparatus for determining an opening parameter of a left atrial appendage according to an embodiment of the present disclosure;

fig. 17 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the attached drawings, the described embodiments should not be considered as limiting the present application, and all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the present application only and is not intended to be limiting of the application.

In the field of medical Imaging and computer tomography, several technologies such as color ultrasound cardiovascular Imaging, Magnetic Resonance Imaging (MRI), and Digital Subtraction Angiography (DSA) are in succession. The medical image digitization degree is higher and higher, and the variety is more diversified. Medical imaging techniques and computed tomography have not only provided reconstructive models of various human organs, but have also demonstrated hemodynamic changes through time-series blood flow velocity fields. The development of the technologies greatly improves the diagnosis efficiency and accuracy of doctors, and simultaneously provides powerful basis for rapid evaluation of the stroke risk of patients.

In the case of atrial fibrillation disease, atrial fibrillation is one of the most common cardiac arrhythmias. Atrial fibrillation tends to accumulate in the left atrium, forming many thrombi, and often resulting from ischemic stroke, an embolic event may occur. More than ninety percent of emboli in stroke patients originate from the left atrial appendage. Therefore, calculating the left atrial appendage opening area provides a powerful basis for clinicians to quickly assess the risk of stroke in patients. In the related art, when determining parameters of the left atrial appendage opening, such as the opening area, the determination can be achieved only in a single mode that the longest diameter and the shortest diameter of the intersecting plane of the left atrial appendage and the left atrium are obtained, and the longest diameter and the shortest diameter are input into an ellipse formula. The application provides a novel method for determining the opening parameter of the left atrial appendage.

The embodiment of the application provides a method for determining an opening parameter of a left atrial appendage, which is applied to a terminal and shown in fig. 1, and the method comprises the following steps:

step 101, acquiring left atrium point cloud data and left auricle point cloud data in a three-dimensional space based on the acquired thoracic cavity tomography image.

In the embodiment of the present application, the three-dimensional space includes three axes, an X axis, a Y axis, and a Z axis, where the X axis represents a left-right space, the Y axis represents a front-back space, and the Z axis represents an up-down space.

In the embodiment of the present application, the thoracic cavity tomographic image is a Computed Tomography Angiography (CTA) image, and the CTA image may be obtained by performing scanning on a cardiac region by using a multi-row spiral CT machine after injecting a suitable contrast medium intravenously. The CTA image is three-dimensionally reconstructed to obtain an organ model of a tissue organ included in the heart. Here, the CTA image is typically stored in a Digital Imaging and Communications in Medicine (DICOM) file format. This format contains Protected Health Information (PHI) about the patient, such as name, gender, age, and other image-related Information such as device Information for capturing and generating images, some context-related Information for medical treatment, etc.

In the embodiment of the application, the thoracic cavity sectional image is obtained by shooting the region containing the thoracic cavity according to the positive direction or negative direction sequence of the axial position; here, in the supine position, the direction of the head is the positive direction of the Z axis. The chest tomography image can be an image of the terminal taken under different visual fields; for example, the chest tomographic image may be an image captured by the terminal in a far field, as shown in fig. 2A, such as the chest tomographic image including a complete bone region; the thoracic tomography image may also be an image taken by the terminal in a near field, as shown in fig. 2B, such as a thoracic tomography image containing only the region around the heart. The image size of the thoracic cavity tomographic image is [ N, P, Q ], where N is the number of slices in the thoracic cavity tomographic image, and P × Q is the size of each slice; the acquired thoracic tomographic image is a two-dimensional image.

In the embodiment of the present application, the obtaining of the thoracic cavity tomographic image is to extract a complete and stereoscopic heart image, and the heart image obtained by using the method of the present embodiment is not a complete and stereoscopic heart image, and the complete and stereoscopic heart image can be obtained only by performing three-dimensional reconstruction on all heart pictures corresponding to the thoracic cavity tomographic image.

In the embodiment of the application, after three-dimensional reconstruction is performed on a thoracic cavity tomography image, the thoracic cavity tomography image is input into an image segmentation model, and a three-dimensional image including target tissue organs such as an aorta, a left atrium, a left atrial appendage and a left ventricle is obtained.

In one implementation, the image segmentation model is obtained by training a plurality of original chest tomography images as training sample images based on a depth network model. Here, the deep network model may be a Convolutional neural network (e.g., 3D-uet) model, and of course, the deep network model may also be a Full Convolutional Network (FCN) model. Here, the plurality of original chest tomographic images include a marked original chest tomographic image and an unmarked original chest tomographic image, wherein the marked original chest tomographic image is an image in which an image region where a target object such as an aorta, a left ventricle, a left atrium, and an atrial appendage is marked; the marked original chest tomography image is an image shot by the terminal in a near vision field, and the unmarked original chest tomography image can be an image shot by the terminal in the near vision field or an image shot by the terminal in a far vision field.

In one implementation, the image segmentation model may be trained by: first, 440 unlabeled original chest tomographic images and 550 labeled original chest tomographic images are acquired as training sample images, where a training set of the training sample images is [ N, P, Q ], and the training set includes N slice images of the original chest tomographic images, each of which has a size of P × Q, such as 512 × 512. And then, carrying out data preprocessing on the training sample image, such as random overturning, random translation or random rotation, to obtain a preprocessed training sample image, so as to increase the data volume of the training sample. And then, carrying out normalization processing on the gray values of the pixel points in the preprocessed training sample image. Further, the normalized image is converted into a three-dimensional image [ a, B, C, D ], where a × B × C is the size of the three-dimensional image and D is the number of channels of the three-dimensional image, and the three-dimensional image may be, for example, an input image parameter of [128, 128, 128, 1] and an output image parameter of [128, 128, 128, 4], as the first network parameter; here, since the input image is a grayscale image, the number D of channels of the input image parameter is 1; since the aorta, left ventricle, left atrial appendage, and left atrium in the image need to be predicted, the number of output images is four, and the number of channels D of the output image parameters is 4. And finally, inputting the first network parameters into the 3D-Unet network model, and outputting the position of the target object, namely predicting the position of the aorta, the position of the left ventricle, the position of the left atrial appendage, the position of the left atrium and the target three-dimensional image of the target object. It should be noted that, since the position of the aorta is relatively obvious in the original chest tomographic image in the far field, the position of the aorta and the three-dimensional image of the aorta are easily confirmed, and other organs such as the left atrial appendage are relatively small, and have a high complexity, and it is difficult to determine the position of the organ and the three-dimensional image thereof, so that after the position of the aorta is determined, the positions of the left atrial appendage, the left atrium, and the like need to be further determined based on the position of the aorta.

In one implementation mode, the thoracic cavity tomography image is a cross-sectional image obtained through section scanning processing, and after the terminal acquires the thoracic cavity tomography image, the thoracic cavity tomography image is subjected to data preprocessing such as random overturning, random translation or random rotation to obtain a preprocessed image; then, performing normalization processing on the gray value of the preprocessed image to obtain a normalized image, converting the image data of the normalized image into a first input network parameter of the target three-dimensional image, inputting the first input network parameter to the image segmentation model, and obtaining the position of the aorta, determined by the image segmentation model, in the cross-sectional image, as shown in fig. 3A, where a white circle in fig. 3A is a schematic cross-sectional view of the aorta.

In one implementation, the terminal captures a first partial image of a chest tomographic image of a subject based on a position of an aorta, the subject including at least an aorta, a left ventricle, a left atrial appendage, and a left atrium, the first partial image including at least all tissue organs near the heart, as shown in fig. 3B.

In one implementation, the terminal inputs the first partial image into an image segmentation model, and determines the position of the target object and the model of the target object, that is, determines the aorta position and the aorta model image, the left ventricle position and the left ventricle model image, the left atrial appendage position and the first left atrial appendage model image, and the position of the left atrium and the first left atrial model image.

In one implementation, the terminal performs a first dilation convolution process on the first left atrial appendage model image to obtain a second left atrial appendage model image; the first dilation convolution is used for increasing the receptive field area of the convolution kernel of the image under the condition that the number of parameters is kept unchanged, and each convolution output contains information in a large range. Illustratively, the terminal processes the first left atrial appendage model image by expanding for 2 circles with a kernel size of 11, resulting in a second left atrial appendage model image. And then, the terminal intercepts a second local image of the left auricle in a second backup image of the thoracic cavity tomography image based on the position of the left auricle and the second left auricle model image. Then, the terminal carries out pretreatment such as random overturning, random translation or random rotation on the second local image to obtain a pretreated image; and then, carrying out normalization processing on the gray value of the preprocessed image to obtain an image after the normalization processing, and converting the image data of the image after the normalization processing into input network parameters of the three-dimensional image of the left auricle. And finally, inputting the input network parameters of the left auricle three-dimensional image into the auricle model to obtain a third left auricle model image, and thus, performing expansion processing on the auricle model image to solve the problem of inaccurate reconstructed edge of the auricle.

In one implementation, the auricle model is obtained by training a plurality of original auricle three-dimensional model images serving as training sample images based on a depth network model. The multiple original auricle three-dimensional model images comprise marked original auricle three-dimensional model images, and the training of the auricle model can be corrected by calculating a function loss value so as to realize more accurate detail description of tissues and organs. The function loss value can be calculated by the following formula,

wherein X is the true value of the pixel points included in the left auricle three-dimensional model image, Y is the predicted value of the pixel points included in the left auricle three-dimensional model image,

and the similarity between the real value and the predicted value of the pixel points included in the left atrial appendage three-dimensional model image is represented. Here, the greater the similarity, the smaller the function loss value, and the more accurate the auricle network model describes the details of the auricle tissue organ. Referring to fig. 3C, an atrial appendage signature for a three-dimensional model of the left atrial appendage predicted for an atrial appendage model is shown.

In one implementation, the terminal performs a second dilation convolution process on the first left atrium model image to obtain a second left atrium model image; the second dilation convolution has the same function as the first dilation convolution, namely the method is used for increasing the receptive field area of a convolution kernel under the condition of keeping the number of parameters unchanged, and each convolution output contains information in a larger range. Exemplarily, the terminal processes the first left atrium model image by expanding the first left atrium model image by 1 circle with the nucleus size of 3 to obtain a second left atrium model image; in this way, the problem of inaccurate left atrium reconstruction edges is solved by performing expansion processing on the left atrium model image.

In the embodiment of the application, the terminal acquires left atrium point cloud data in a three-dimensional space based on the second left atrium model image; and acquiring left atrial appendage point cloud data in a three-dimensional space based on the third left atrial appendage model image.

In one implementation, the terminal may also derive a left atrial appendage volume based on the left atrial appendage point cloud data multiplied by the pixel pitch and the layer pitch.

Step 102, determining an intersecting curved surface where the left atrium and the left auricle intersect based on the left atrial point cloud data and the left auricle point cloud data.

In the embodiment of the application, the intersecting curved surface is a plane formed by a point set formed by left atrial point cloud data and left atrial appendage point cloud data.

In the embodiment of the application, after the terminal acquires the left atrial point cloud data and the left atrial appendage point cloud data, the intersecting curved surface of the intersection of the left atrial appendage and the left atrial appendage is determined based on the left atrial point cloud data and the left atrial appendage point cloud data. It should be noted that, the terminal is based on the left atrial point cloud data and the left atrial appendage point cloud data, and due to the pixel level error, the formed intersecting curved surface is a stepped curved surface, as shown in fig. 4.

Step 103, determining at least two intersecting planes based on the central point of the intersecting curved surface in the three-dimensional space, the first target point on the intersecting curved surface in the front and rear spaces of the three-dimensional space, and the at least two second target points on the intersecting curved surface in the upper and lower spaces of the three-dimensional space.

In the embodiment of the application, the central point of the intersecting curved surface is a coordinate point obtained by obtaining the pixel coordinates of all the pixel points on the intersecting curved surface and averaging the pixel coordinates of all the pixel points.

In an embodiment of the present application, the intersection plane is a plane formed by points having an intersection between the left atrial appendage and the left atrium in three-dimensional space. Referring to fig. 5, reference numeral 51 in fig. 5 is an intersecting plane.

In the embodiment of the application, after determining the intersecting curved surface where the left atrium and the left atrial appendage intersect, the terminal determines at least two intersecting planes based on a central point of the intersecting curved surface in a three-dimensional space, a first target point on the intersecting curved surface in a front space and a rear space of the three-dimensional space, for example, in a Y-axis direction, and at least two second target points on the intersecting curved surface in an up-and-down space of the three-dimensional space, for example, in a Z-axis direction.

Step 104, determining an opening parameter of the left atrial appendage based on the at least two intersecting planes.

In the embodiment of the present application, the opening parameter of the left atrial appendage includes an opening area of the left atrial appendage, an opening position of the left atrial appendage, and a volume of the left atrial appendage.

In the embodiment of the application, the terminal determines the target intersecting plane based on at least two intersecting planes, and further determines the opening area of the left atrial appendage.

The embodiment of the present application provides a method for determining an opening parameter of a left atrial appendage, where the method is applied to a terminal, and as shown in fig. 6, the method includes:

step 201, acquiring left atrium point cloud data and left auricle point cloud data in a three-dimensional space based on the acquired thoracic cavity tomography image.

Step 202, determining an intersecting curved surface where the left atrium and the left atrial appendage intersect based on the left atrial appendage point cloud data and the left atrial appendage point cloud data.

Step 203, determining at least two intersecting planes based on the central point of the intersecting curved surface in the three-dimensional space, the first target point on the intersecting curved surface in the front space and the rear space of the three-dimensional space, and the at least two second target points on the intersecting curved surface in the upper space and the lower space of the three-dimensional space.

In this embodiment of the application, referring to fig. 7, step 203 determines at least two intersecting planes based on a central point of an intersecting surface in a three-dimensional space, a first target point on the intersecting surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting surface in upper and lower spaces of the three-dimensional space, and may be implemented by the following steps:

step a1, determining a first vector based on the central point and the at least two second target points.

In the embodiment of the present application, referring to fig. 8, the step a1 determines the first vector based on the central point and the at least two second target points, and may be implemented by the following steps:

Step B1, determining each third vector starting from the center point and ending at each second target point.

And step B2, determining the unit vector in the average direction of all the third vectors as the first vector.

In the embodiment of the present application, the third vector is a unit vector of vectors obtained by using the central point as a starting point and using each of the second target points as an end point; here, the direction of a line segment formed by connecting lines from the central point to all points in the intersecting curved surface may be divided into an upward direction or a downward direction, with the Z-axis direction as a reference in the three-dimensional space; here, the point set is formed by points of the intersecting curved surface, which are downward in the direction of the line segment formed by the connecting line with the central point, and the second target point is any point in the point set.

In the embodiment of the application, the terminal determines each third vector taking the central point as a starting point and each second target point as an end point to obtain at least two third vectors; and taking a unit vector in the average direction of at least two third vectors as a first vector.

Step a2, determining a unit vector of the vector with the center point as a starting point and the first target point as an end point as a second vector.

In this embodiment of the application, the first target point is any point in a point set of points included in the intersection curved surface in the Y-axis direction in the three-dimensional space.

The second vector is a unit vector of a vector obtained by taking the central point as a starting point and the first target point as an end point.

Step A3, determining a normal vector based on the first vector and the second vector.

In one implementation, the first vector is used

Representing, the second vector by

For normal vectors

And (4) showing. Wherein the content of the first and second substances,

then normal vector

Can be obtained by the following formula,

wherein the content of the first and second substances,

is a unit vector in the positive direction of the X axis,

is a unit vector in the positive direction of the Y axis,

referring to fig. 9, a normal vector of a plane is denoted by 91 in fig. 9 as a unit vector in the positive direction of the Z axis.

In the embodiment of the application, the terminal determines a first vector based on the central point and at least two second target points, and determines a normal vector based on the first vector and the second vector when a unit vector of a vector taking the central point as a starting point and the first target point as a midpoint is a second vector.

And A4, determining a reference intersecting plane corresponding to the normal vector based on the central point and the normal vector.

In one implementation, the center point is represented by M and the normal vector by

Representation based on center point M, normal vector

And a plane equation, namely the reference intersecting plane can be determined. Specifically, the coordinates of the first target point M are

Assuming that any point O except the center point in the intersecting plane of the reference is

Then the plane equation of the obtained reference intersecting plane is

。

In the embodiment of the application, when the terminal determines the normal vector based on the first vector and the second vector, the reference intersecting plane corresponding to the normal vector is determined based on the central point and the normal vector.

Step a5, determining at least one reference intersection plane based on the center point, the normal vector, and the base intersection plane.

Wherein the at least two intersecting planes include a base intersecting plane and at least one reference intersecting plane.

In this embodiment of the application, the step a5 determines at least one reference intersecting plane based on the central point, the normal vector and the reference intersecting plane, and may be implemented as follows:

and determining at least one reference intersecting plane along the direction of the normal vector by taking the reference intersecting plane as a starting plane. And the distance between the reference intersecting plane with the minimum distance to the reference intersecting plane and the reference intersecting plane in the at least two reference intersecting planes is equal to the distance between every two adjacent planes in the at least two reference intersecting planes.

In the embodiment of the application, the terminal determines at least two reference intersecting planes along the direction of the normal vector by using the reference intersecting plane as a starting plane, and the distance between every two adjacent planes in the at least two reference intersecting planes is the same as the distance between the reference intersecting plane with the smallest distance with the reference intersecting plane in the at least two reference intersecting planes and the reference intersecting plane.

In one implementation manner, after the terminal determines the reference intersecting plane, the terminal determines at least two reference center points at intervals of a first threshold value along the direction of the normal vector by using the reference intersecting plane as an initial plane and using a center point in the reference intersecting plane as a starting point. Then, the terminal determines each reference intersecting plane corresponding to each reference central point based on each reference central point and the normal vector; here, the at least two reference intersecting planes include each reference intersecting plane.

Step 204, determining a first cutting plane from the at least two intersecting planes, wherein the parameters of the cutting plane of the left atrium and the left atrial appendage meet the first screening condition.

In an embodiment of the application, the first cutting plane is a local plane formed by a point in the intersection plane having an intersection between the left atrium and the left atrial appendage. Referring to fig. 5, the first cutting plane is indicated at 52 in fig. 5.

In one embodiment, the first screening criteria for meeting the parameters of the cutting plane of the left atrium and the left atrial appendage comprises: the pixel point areas corresponding to the cutting planes of the left atrium and the left auricle accord with the area screening condition.

In one implementation, referring to fig. 10, fig. 10 is a schematic view of the intersection plane of the left atrial appendage model and the left atrial model, where 61 in fig. 10 refers to the left atrial appendage model, 62 in fig. 10 refers to the left atrial model, and 63 in fig. 10 refers to the intersection plane between the left atrial appendage model 61 and the left atrial model 62.

In an embodiment of the present application, referring to fig. 11, the step 204 of determining a first cutting plane from at least two intersecting planes, wherein the parameters of the cutting planes of the left atrium and the left atrial appendage meet the first screening condition, may be implemented by:

and step C1, determining the area of each pixel point corresponding to the cutting plane of the left atrium and the left atrial appendage in each intersecting plane.

In the embodiment of the application, the terminal obtains each pixel point area corresponding to the cutting plane of the left atrium and the left atrial appendage in each intersecting plane, and here, the pixel point area corresponding to the cutting plane can be represented by the number of the pixel points in the cutting plane.

And C2, screening out the partial intersecting planes where the cutting planes with the pixel point areas meeting the second screening condition are located from at least two intersecting planes.

In one embodiment, the step of matching the pixel point area of the partially intersected plane with the second screening condition includes: and subtracting the difference value of the first mean values of the pixel point areas corresponding to all the cutting planes in at least two intersecting planes from the pixel point area corresponding to the cutting plane in any intersecting plane in part of the intersecting planes, so as to accord with the difference value screening condition.

In the embodiment of the present application, the difference filtering condition is a condition that satisfies an error of the pixel area, and for example, the difference filtering condition may be within a difference threshold range, and the difference threshold range may be 100.

In the embodiment of the application, the terminal screens out the pixel areas corresponding to the cutting planes in the two intersecting planes, and the difference value of the first mean values of the pixel areas corresponding to all the cutting planes in at least two intersecting planes is subtracted from the pixel areas corresponding to the cutting planes in the two intersecting planes, wherein the difference value is within the range of the difference threshold value.

Step C3, from the partially intersecting planes, determines a first cutting plane.

In the embodiment of the present application, referring to fig. 12, the step C3 is to determine the first cutting plane from the partially intersecting planes, and may be implemented by the following steps:

and D1, determining a second average value of the pixel point areas corresponding to all the cutting planes in the partial intersection plane.

And D2, screening out the cutting planes with the difference value between the pixel point area corresponding to the cutting plane and the second average value meeting the difference value threshold from all the cutting planes in the partial intersection planes as the first cutting plane.

In the embodiment of the application, the terminal determines second average values of pixel point areas corresponding to all cutting planes in the partial intersecting plane, and selects the cutting plane, of which the difference value between the pixel point area corresponding to the cutting plane and the second average value meets the difference value threshold range, as the first cutting plane from all cutting planes in the partial intersecting plane.

In one implementation, the terminal screens out a first cutting plane from all cutting planes in the partial intersection plane, and then displays the left atrial appendage model and the first cutting plane; referring to fig. 13, fig. 13 shows a schematic view of a left atrial appendage model 1301 and a first cutting plane 1302.

Step 205, determining an opening parameter of the left atrial appendage based on the first cutting plane and an intersecting plane where the first cutting plane is located.

In the embodiment of the application, firstly, after a terminal determines a first cutting plane and an intersecting plane where the first cutting plane is located, the area of a pixel point of the first cutting plane is obtained; and then, the terminal intercepts a first area plane including the first cutting plane in the intersecting plane and acquires the pixel point area of the first area plane. And then, the terminal calculates the area ratio of the pixel area of the first cutting plane to the pixel area of the first area plane. And thirdly, converting the first area plane into a second area plane under the space physical coordinate, and calculating the area of the second area plane. And finally, the product of the area ratio determined by the terminal and the area of the second area plane is the area of the first cutting plane under a space physical coordinate system, namely the opening parameter of the left atrial appendage and the opening area of the left atrial appendage. It should be noted that the first area plane is generally a square plane, and after the first area plane is converted into a second area plane in the space physical coordinate, the second area plane is a parallelogram. If four vertices of the parallelogram are respectively

Can be obtained by

Is a directional parallelogram, the area of the parallelogram

. And the terminal determines the product of the area S of the parallelogram and the area ratio as the area of the first cutting plane under the space physical coordinate system.

Based on the above steps performed by the terminal, referring to fig. 14, a schematic diagram of the connection of the left atrial appendage model, the left atrial model and the aorta model shown in fig. 14 is obtained, and the terminal can output the model data.

It should be noted that, for the descriptions of the same steps and the same contents in this embodiment as those in other embodiments, reference may be made to the descriptions in other embodiments, which are not described herein again.

As can be seen from the above, in the embodiment of the present application, the terminal determines the intersecting curved surface where the left atrium and the left atrial appendage intersect based on the left atrial point cloud data and the left atrial appendage point cloud data in the three-dimensional space, and based on the central point of the intersecting surface in the three-dimensional space, the first target point on the intersecting surface in the front and back space of the three-dimensional space, and the specific points on the intersecting curved surfaces in the upper and lower spaces of the three-dimensional space, determining at least two intersecting curved surfaces, determining the area of each pixel point corresponding to the cutting planes of the left atrium and the left atrial appendage in each intersecting plane from at least two intersecting curved surfaces, wherein the cutting plane meeting the area screening condition is the first cutting plane, further determining the opening parameter of the left atrial appendage based on the intersecting plane of the first cutting plane and the first cutting plane, so, can provide comprehensive, reliable reference data for left atrial appendage shutoff art, be favorable to clinician to carry out quick aassessment to patient's cerebral apoplexy's risk.

With reference to fig. 15, a method for determining an opening parameter of a left atrial appendage provided by an embodiment of the present invention is further described, where the method is applied to a terminal, and the method includes:

step 301, acquiring a thoracic cavity tomography image.

Here, the thoracic tomographic image is a CTA image, and includes a CTA image in a far field and a CTA image in a near field.

Step 302, inputting the thoracic cavity tomography image into an image segmentation model, and determining the position of the aorta.

Here, the image segmentation model may be a 3D-Unet network model, and the 3D-Unet network model is a network model trained in advance based on a plurality of original chest tomographic images.

Step 303, a first partial image including a first receptive field region in the chest tomographic image is intercepted based on the position of the aorta.

Here, the first receptive field region includes a target object including at least an aorta, a left ventricle, a left auricle, and a left atrium, and the first partial image includes at least all tissue organs in the vicinity of the heart.

Step 304, performing data preprocessing on the first partial image, and inputting the processed first partial image into an image segmentation model to obtain a first left atrial appendage model image and a first left atrial model image.

Step 305, preprocessing the first left atrial appendage model image, inputting the processed left atrial appendage model image into an atrial appendage model, and obtaining a second left atrial appendage model image.

Step 306, determining a first left atrium model based on the first left atrium model image, and performing expansion convolution processing on the first left atrium model to obtain a second left atrium model image.

It should be noted that, in the embodiment of the present application, the execution sequence of step 305 and step 306 may be random, for example, step 305 may be executed before step 306, and step 305 may also be executed after step 306; of course, in the embodiment of the present application, the execution sequence of step 305 and step 306 may also be executed simultaneously, and this is not specifically limited in the present application.

And 307, acquiring left atrial point cloud data and left atrial appendage point cloud data in a three-dimensional space based on the second left atrial model image and the second left atrial appendage model image, and determining an intersecting plane where the left atrium and the left atrial appendage intersect.

Here, the terminal determines an intersecting curved surface where the left atrium and the left atrial appendage intersect based on the left atrial point cloud data and the left atrial appendage point cloud data, and determines at least two intersecting planes based on a center point of the intersecting curved surface in the three-dimensional space, a first target point on the intersecting curved surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting curved surface in upper and lower spaces of the three-dimensional space. And then, screening out the intersection planes of which the pixel point areas corresponding to the cutting planes of the left atrium and the left atrial appendage accord with the area screening conditions from the at least two intersection planes.

Step 308, determining the area of the left atrial appendage opening based on the intersecting planes.

As can be seen from the above, in the embodiment of the present application, the terminal processes the left atrial appendage model image for multiple times and inputs the processed image into the atrial appendage model, so as to solve the problem of inaccurate edge in the reconstructed left atrial appendage model, and determines the area ratio of the pixel area of the cutting plane to the pixel area of the intersecting plane through the determined intersecting plane; and then, calculating the area of the intersecting plane under the space physical coordinate system, and determining the product of the area ratio and the area of the intersecting plane under the space physical coordinate system as the opening area of the left atrial appendage, so that comprehensive and reliable reference data can be provided for left atrial appendage occlusion, and the rapid assessment of the risk of stroke of a patient by a clinician is facilitated.

An embodiment of the present application provides an apparatus for determining an opening parameter of a left atrial appendage, which may be applied to a method for determining an opening parameter of a left atrial appendage provided in embodiments corresponding to fig. 1, 6-8, and 11-12, and as shown in fig. 16, the apparatus 16 for determining an opening parameter of a left atrial appendage includes:

an acquiring module 1601, configured to acquire left atrial appendage point cloud data and left atrial appendage point cloud data in a three-dimensional space based on an acquired thoracic tomography image;

A processing module 1602, configured to determine an intersecting curved surface where the left atrium and the left atrial appendage intersect based on the left atrial appendage point cloud data and the left atrial appendage point cloud data;

the processing module 1602 is further configured to determine at least two intersecting planes based on a central point of an intersecting surface in the three-dimensional space, a first target point on the intersecting surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting surface in upper and lower spaces of the three-dimensional space;

the processing module 1602 is further configured to determine an opening parameter of the left atrial appendage based on the at least two intersecting planes.

In other embodiments of the present application, the processing module 1602 is further configured to determine a first vector based on the central point and the at least two second target points; determining a unit vector of a vector taking the central point as a starting point and the first target point as an end point as a second vector; determining a normal vector based on the first vector and the second vector; determining a reference intersecting plane corresponding to the normal vector based on the central point and the normal vector; determining at least one reference intersection plane based on the center point, the normal vector, and the reference intersection plane, wherein the at least two intersection planes include the reference intersection plane and the at least one reference intersection plane.

In other embodiments of the present application, the processing module 1602 is further configured to determine at least one reference intersecting plane along the direction of the normal vector with the reference intersecting plane as a starting plane, wherein a distance between a reference intersecting plane with a smallest distance from the reference intersecting plane among the at least two reference intersecting planes and the reference intersecting plane is equal to a distance between every two adjacent planes among the at least two reference intersecting planes.

In other embodiments of the present application, the processing module 1602 is further configured to determine each third vector with the central point as a starting point and each second target point as an ending point; the unit vector in the average direction of all the third vectors is determined to be the first vector.

In other embodiments of the present application, the processing module 1602 is further configured to determine, from the at least two intersecting planes, a first cutting plane in which parameters of the cutting planes of the left atrium and the left atrial appendage meet the first screening condition; based on the first cutting plane and an intersection plane where the first cutting plane is located, an opening parameter of the left atrial appendage is determined.

In other embodiments of the present application, the meeting the first screening criteria for the parameters of the cutting plane of the left atrium and the left atrial appendage comprises: the pixel point areas corresponding to the cutting planes of the left atrium and the left auricle accord with the area screening condition.

In other embodiments of the present application, the processing module 1602 is further configured to determine an area of each pixel point corresponding to a cutting plane of the left atrium and the left atrial appendage in each intersecting plane; screening out a part of intersected planes where the cutting planes with the pixel point areas meeting the second screening condition are located from at least two intersected planes; from the partially intersecting planes, a first cutting plane is determined.

In other embodiments of the present application, the area of the pixel point of the partially intersected plane meeting the second screening condition includes: and subtracting the difference value of the first mean values of the pixel point areas corresponding to all the cutting planes in at least two intersecting planes from the pixel point area of any intersecting plane in part of the intersecting planes, so as to accord with the difference value screening condition.

In other embodiments of the present application, the processing module 1602 is further configured to determine a second average value of pixel areas corresponding to all cutting planes in the partially intersected plane; and screening out the cutting planes with the difference values between the pixel point areas corresponding to the cutting planes and the second mean value meeting the difference value threshold value from all the cutting planes in the partial intersecting planes as first cutting planes.

Embodiments of the present application provide a terminal, which may be applied to the method for determining the opening parameter of the left atrial appendage provided in the embodiments corresponding to fig. 1, fig. 6 to fig. 8, and fig. 11 to fig. 12, and as shown in fig. 17, the terminal 17 includes (the terminal in fig. 17 corresponds to the opening parameter determining device 16 of the left atrial appendage in fig. 16): a memory 1701 and a processor 1702, wherein the memory 1701 is used for storing executable instructions; a processor 1702 for executing the executable instructions stored in the memory 1701 to perform the following steps:

determining an intersecting curved surface where the left atrium and the left auricle intersect on the basis of the left atrium point cloud data and the left auricle point cloud data;

determining at least two intersecting planes based on a central point of an intersecting surface in a three-dimensional space, a first target point on the intersecting surface in front and rear spaces of the three-dimensional space, and at least two second target points on the intersecting surface in upper and lower spaces of the three-dimensional space;

based on the at least two intersecting planes, an opening parameter of the left atrial appendage is determined.

In other embodiments of the present application, the processor 1702 is configured to execute a program stored in the memory 1701 to perform the following steps:

determining a first vector based on the center point and the at least two second target points; determining a unit vector of a vector taking the central point as a starting point and the first target point as an end point as a second vector; determining a normal vector based on the first vector and the second vector; determining a reference intersecting plane corresponding to the normal vector based on the central point and the normal vector; determining at least one reference intersection plane based on the center point, the normal vector, and the reference intersection plane, wherein the at least two intersection planes include the reference intersection plane and the at least one reference intersection plane.

and determining at least one reference intersecting plane along the direction of the normal vector by taking the reference intersecting plane as a starting plane, wherein the distance between the reference intersecting plane with the minimum distance to the reference intersecting plane in the at least two reference intersecting planes is equal to the distance between every two adjacent planes in the at least two reference intersecting planes.

determining each third vector taking the central point as a starting point and each second target point as an end point; the unit vector in the average direction of all the third vectors is determined to be the first vector.

determining a first cutting plane from the at least two intersecting planes, wherein the parameters of the cutting planes of the left atrium and the left atrial appendage meet the first screening condition; based on the first cutting plane and an intersection plane where the first cutting plane is located, an opening parameter of the left atrial appendage is determined.

the parameters of the cutting plane of the left atrium and left atrial appendage meeting the first screening criteria include: the pixel point areas corresponding to the cutting planes of the left atrium and the left auricle accord with the area screening condition.

determining the area of each pixel point corresponding to the cutting plane of the left atrium and the left auricle in each intersecting plane; screening out a part of intersected planes where the cutting planes with the pixel point areas meeting the second screening condition are located from at least two intersected planes; from the partially intersecting planes, a first cutting plane is determined.

the pixel point area of the part of the intersecting planes meets the second screening condition, and the method comprises the following steps: and subtracting the difference value of the first mean values of the pixel point areas corresponding to all the cutting planes in at least two intersecting planes from the pixel point area of any intersecting plane in part of the intersecting planes, so as to accord with the difference value screening condition.

determining a second average value of pixel point areas corresponding to all cutting planes in the partially intersected plane; and screening out the cutting planes with the difference values between the pixel point areas corresponding to the cutting planes and the second mean value meeting the difference value threshold value from all the cutting planes in the partial intersecting planes as first cutting planes.

It should be noted that, for a specific implementation process of the steps executed by the processor in this embodiment, reference may be made to an implementation process in the method for determining an opening parameter of a left atrial appendage provided in the embodiments corresponding to fig. 1, fig. 6 to fig. 8, and fig. 11 to fig. 12, and details are not repeated here.

Embodiments of the present application provide a storage medium storing one or more programs executable by one or more processors to perform the steps of:

In other embodiments of the present application, the one or more programs are executable by the one or more processors to perform the steps of:

In other embodiments of the present application, the step of matching the area of the pixel point of the partially intersected plane with the second filtering condition includes: and subtracting the difference value of the first mean values of the pixel point areas corresponding to all the cutting planes in at least two intersecting planes from the pixel point area of any intersecting plane in part of the intersecting planes, so as to accord with the difference value screening condition.

Here, it should be noted that: the above description of the storage medium and device embodiments is similar to the description of the method embodiments above, with similar advantageous effects as the method embodiments. For technical details not disclosed in the embodiments of the storage medium and apparatus of the present application, reference is made to the description of the embodiments of the method of the present application for understanding.

The computer storage medium/Memory may be a Read Only Memory (ROM), a Programmable Read Only Memory (PROM), an Erasable Programmable Read Only Memory (EPROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a magnetic Random Access Memory (FRAM), a Flash Memory (Flash Memory), a magnetic surface Memory, an optical Disc, or a Compact Disc Read-Only Memory (CD-ROM), and the like; but may also be various terminals such as mobile phones, computers, tablet devices, personal digital assistants, etc., that include one or any combination of the above-mentioned memories.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment of the present application" or "a previous embodiment" or "some embodiments" or "some implementations" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present application. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" or "an embodiment of the present application" or "the preceding embodiments" or "some implementations" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of a unit is only one logical function division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, all functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.

The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.

Features disclosed in several of the product embodiments provided in the present application may be combined in any combination to yield new product embodiments without conflict.

The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.

Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as a removable Memory device, a Read Only Memory (ROM), a magnetic disk, or an optical disk.

Alternatively, the integrated units described above in the present application may be stored in a computer-readable storage medium if they are implemented in the form of software functional modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially implemented or portions thereof contributing to the related art may be embodied in the form of a software product stored in a storage medium, and including several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, a ROM, a magnetic or optical disk, or other various media that can store program code.

It should be noted that the drawings in the embodiments of the present application are only for illustrating schematic positions of the respective devices on the terminal device, and do not represent actual positions in the terminal device, actual positions of the respective devices or the respective areas may be changed or shifted according to actual conditions (for example, a structure of the terminal device), and a scale of different parts in the terminal device in the drawings does not represent an actual scale.

The above description is only for the embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining parameters of an opening of a left atrial appendage, the method comprising:

2. The method of claim 1, wherein determining at least two intersecting planes based on a center point of the intersecting surface in the three-dimensional space, a first target point on the intersecting surface in a front space and a back space of the three-dimensional space, and at least two second target points on the intersecting surface in a top space and a bottom space of the three-dimensional space comprises:

determining a first vector based on the center point and the at least two second target points;

determining a unit vector of a vector taking the central point as a starting point and the first target point as an end point as a second vector;

determining a normal vector based on the first vector and the second vector;

determining a reference intersecting plane corresponding to the normal vector based on the central point and the normal vector;

Determining at least one reference intersection plane based on the center point, the normal vector, and the reference intersection plane, wherein the at least two intersection planes include the reference intersection plane and the at least one reference intersection plane.

3. The method of claim 2, the determining at least one reference intersection plane based on the center point, the normal vector, and the reference intersection plane, comprising:

and determining at least one reference intersecting plane along the direction of the normal vector by taking the reference intersecting plane as a starting plane, wherein the distance between the reference intersecting plane with the smallest distance with the reference intersecting plane and the reference intersecting plane in the at least two reference intersecting planes is equal to the distance between every two adjacent planes in the at least two reference intersecting planes.

4. The method of claim 2, wherein determining a first vector based on the center point and the at least two second target points comprises:

determining each third vector taking the central point as a starting point and each second target point as an end point;

determining a unit vector in an average direction of all the third vectors as the first vector.

5. The method according to claim 2, wherein said determining opening parameters of the left atrial appendage based on the at least two intersecting planes comprises:

determining, from the at least two intersecting planes, a first cutting plane for which parameters of cutting planes of the left atrium and the left atrial appendage meet first screening criteria;

determining an opening parameter of the left atrial appendage based on the intersection plane of the first cutting plane and the first cutting plane.

6. The method of claim 5, wherein the parameters of the cutting plane of the left atrium and the left atrial appendage meeting a first screening condition comprises: and the areas of pixel points corresponding to the cutting planes of the left atrium and the left auricle accord with area screening conditions.

7. The method according to claim 5, wherein said determining, from the at least two intersecting planes, a first cutting plane for which parameters of the cutting planes of the left atrium and the left atrial appendage meet first screening criteria comprises:

determining the area of each pixel point corresponding to the cutting plane of the left atrium and the left atrial appendage in each intersecting plane;

screening out the partial intersected planes where the cutting planes with the pixel point areas meeting the second screening condition are located from the at least two intersected planes;

From the partially intersecting planes, the first cutting plane is determined.

8. The method of claim 7, wherein the step of determining the pixel area of the partially intersected plane meets a second filtering condition comprises: and subtracting the difference value of the first mean values of the pixel point areas corresponding to all the cutting planes in the at least two intersecting planes from the pixel point area of any intersecting plane in part of the intersecting planes, so as to accord with the difference value screening condition.

9. The method of claim 7, wherein said determining the first cutting plane from the partially intersecting plane comprises:

determining a second average value of pixel point areas corresponding to all cutting planes in the partially intersected plane;

and screening out the cutting planes, of which the difference values between the pixel point areas corresponding to the cutting planes and the second mean values meet the difference value threshold, from all the cutting planes in the partial intersection planes as the first cutting planes.

10. An apparatus for determining parameters of the opening of the left atrial appendage, the apparatus comprising:

11. A terminal, characterized in that the terminal comprises:

a memory for storing executable instructions;

a processor for executing executable instructions stored in the memory to implement the method of opening parameter determination of a left atrial appendage as claimed in any one of claims 1 to 9.

12. A storage medium, characterized in that the storage medium stores one or more programs executable by one or more processors to implement the method of determining an opening parameter of a left atrial appendage as claimed in any one of claims 1 to 9.