Device and electronic device for determining ventricular septum deviation parameters

Abstract

The present invention discloses a device and electronic device for determining ventricular septum offset parameters, which relate to the technical field of medical image processing, in order to solve the problems of health damage caused by invasive and invasive detection methods for patients and high requirements for doctors' experience level when evaluating pulmonary artery pressure. The device comprises: an acquisition module for obtaining a biological heart image; a processing module for determining the geometric parameters of at least one ventricle based on the biological heart part image; and a determination module for determining the actual offset parameters of the ventricular septum based on the geometric parameters of at least one ventricle. The readable storage medium and electronic device for ventricular offset parameters include those proposed in the above technical solution. The device for determining ventricular offset parameters provided by the present invention is used to measure biological pulmonary artery pressure.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to a device and electronic equipment for determining ventricular septum deviation parameters. Background Art

[0002] Pulmonary arterial hypertension (PAH) is a serious clinical symptom characterized by increased pulmonary vascular resistance and vascular remodeling, which can lead to right heart failure. Right ventricular dysfunction can predict the severity of PAH, exercise capacity, and survival, and even patients with right ventricular dysfunction have a faster clinical deterioration of PAH.

[0003] At present, the main method is to perform invasive measurement of the right heart through catheterization to obtain the mean pulmonary artery pressure, so as to diagnose pulmonary hypertension using the mean pulmonary artery pressure. However, the invasive measurement and diagnosis of living organisms requires a certain level of health status of the organism and the experience level of the doctor, and it is also easy to cause health damage to the patient. Summary of the invention

[0004] The purpose of the present invention is to provide a device for determining a ventricular septum excursion parameter, a readable storage medium and an electronic device, so as to determine the ventricular septum excursion parameter in a non-invasive manner, thereby determining the pulmonary artery pressure and avoiding health damage to biological bodies such as human bodies.

[0005] In a first aspect, the present invention provides a device for determining a ventricular septal excursion parameter, comprising:

[0006] An acquisition module, used for acquiring a biological heart image;

[0007] a processing module for determining geometric parameters of at least one ventricle based on the biological heart image;

[0008] A determination module is used to determine an actual ventricular septal excursion parameter based on at least one geometric parameter of the ventricle.

[0009] Compared with the prior art, in the device for determining the ventricular septum offset parameter provided by the present invention, the processing module can determine the geometric parameters of at least one ventricle based on the biological heart image. Since the geometric parameters of the ventricle can indirectly reflect the shape of the ventricle, the determination module can be used to determine the actual offset parameters of the ventricular septum based on the geometric parameters of at least one ventricle, thereby determining the actual offset parameters of the ventricular septum in a non-invasive manner. On this basis, the correlation between the offset parameters of the ventricular septum and the pulmonary artery pressure can be used to obtain the pulmonary artery pressure corresponding to the actual offset parameters. It can be seen that the present invention can indirectly determine the pulmonary artery pressure based on the determination of the ventricular septum offset parameters in a non-invasive manner, thereby avoiding health damage to biological bodies such as the human body.

[0010] In a second aspect, the present invention further provides an electronic device, comprising:

[0011] processor; and,

[0012] Memory for storing programs,

[0013] The program includes instructions, and when the instructions are executed by the processor, the processor performs the method for determining the ventricular septum excursion parameter, the method comprising:

[0014] obtaining biological heart images;

[0015] determining geometric parameters of at least one ventricle based on the image of the biological heart region;

[0016] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0017] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the device for determining the ventricular septum deviation parameters described in the above technical solution, which will not be described in detail here.

[0018] The present invention also provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method for determining the ventricular septum excursion parameter, the method comprising:

[0019] obtaining biological heart images;

[0020] determining geometric parameters of at least one ventricle based on the image of the biological heart region;

[0021] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0022] Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the device for determining the ventricular septum deviation parameters described in the above technical solution, and are not described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 It is a structural block diagram of a device for determining a ventricular septum excursion parameter in an exemplary embodiment of the present invention;

[0025] Figure 2 In an exemplary embodiment of the present invention, axial cardiac images of four groups of clinical trial subjects at different stages of disease are obtained by scanning with magnetic resonance movie sequences;

[0026] Figure 3 A modeling diagram of the ventricular septum of a clinical trial subject in an exemplary embodiment of the present invention;

[0027] FIG4 is a diagram showing the relationship between SSI, VMI, MPA and mPAP in an exemplary embodiment of the present invention;

[0028] Figure 5 is a Bland-Altman analysis diagram of an exemplary embodiment of the present invention;

[0029] Figure 6 The receiver operating characteristic curve (ROC) was used to predict pulmonary hypertension PH (mPAP ≥ 25 mm Hg);

[0030] Figure 7 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0032] It should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0033] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. The meaning of "several" is one or more, unless otherwise clearly and specifically defined.

[0034] In the description of the present invention, it is necessary to understand that the directions or positional relationships indicated by the terms "up", "down", "front", "back", "left", "right", etc. are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0035] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0036] At present, pulmonary arterial hypertension (PAH) is a serious clinical symptom characterized by increased pulmonary vascular resistance and vascular remodeling, leading to right heart failure. The current diagnosis of PAH is mainly invasively measured by right cardiac catheterization, which directly measures the mean pulmonary artery pressure. The mean pulmonary artery pressure of a normal person is between 18 and 25 mmHg. If the patient's mean pulmonary artery pressure is greater than or equal to 25 mmHg, a definite diagnosis of PAH can be obtained. However, this invasive method of invasive measurement and diagnosis using right cardiac catheterization causes certain damage to the health of organisms such as humans, and even requires high experience and level of diagnostic doctors.

[0037] Based on the above problems, an exemplary embodiment of the present invention provides a device for determining a ventricular septum excursion parameter, an electronic device and a computer-readable storage medium, so as to determine the ventricular septum excursion parameter in a non-invasive manner, thereby determining the pulmonary artery pressure and avoiding health damage to biological bodies such as human bodies.

[0038] In practical applications, the device for determining the ventricular septum offset parameter of the present invention can obtain the ventricular septum parameter in a non-invasive manner. On this basis, the pulmonary artery pressure of the patient can be used according to the relationship between the ventricular septum parameter and the pulmonary artery pressure.

[0039] Figure 1 FIG. 4 shows a structural block diagram of a device for determining a ventricular septum deviation parameter according to an exemplary embodiment of the present invention. Figure 1 As shown, the device for determining the ventricular septum excursion parameters of the exemplary embodiment of the present invention includes: an acquisition module, a processing module and a determination module.

[0040] The acquisition module can obtain a biological heart image. In terms of image dimension, the biological heart image can be a two-dimensional image of a biological heart image, or can be a three-dimensional image, a four-dimensional image, or other medical images. In terms of image acquisition method, the biological heart image can be a cardiac ultrasound image, a cardiac magnetic resonance film sequence image, a CT angiography image, etc., but is not limited thereto.

[0041] The above-mentioned biological heart image may include one biological heart image or multiple biological heart images. When the biological heart image includes multiple biological heart images, the multiple biological heart images may be arranged in a movie serialization manner. At the same time, each biological heart image may be composed of multiple heart section images of different sizes.

[0042] For example, when using a magnetic resonance imaging device to obtain an image of the human heart, the magnetic resonance imaging device can place the human body in the strong magnetic field of the magnetic resonance machine, use radio frequency pulses to excite the hydrogen nuclei in the cells of the tissue being examined, causing the hydrogen nuclei to resonate, thereby obtaining a complete image of some organs of the human body.

[0043] For example, the human heart may include a left ventricle, a left atrium, a right ventricle, and a right atrium, with four chambers. The left atrium and the left ventricle are interconnected, the right atrium and the right ventricle are interconnected, and the left atrium and the right atrium are separated by an atrial septum, and the left ventricle and the right ventricle are separated by a ventricular septum. The left ventricle is responsible for ejecting blood into the aorta and entering the systemic circulation; the right ventricle is responsible for ejecting blood into the pulmonary artery and entering the pulmonary circulation. For the ventricles of a biological heart, it may include two alternating working states, and two adjacent working states may be defined as a working cycle. The two working states within each working cycle may include diastole and systole. When the heart contracts, it is the systole of the heart, and when the heart relaxes, it is the diastole of the heart.

[0044] On this basis, magnetic resonance imaging equipment can be used to collect cardiac magnetic resonance movie sequence images. Based on the sequence scan, the long axis and short axis of the two chambers of the ventricle are selected with the heart axis as the center to obtain movie images of each section of the short axis and long axis, thereby forming multiple cardiac section images at multiple consecutive time points in a cardiac cycle. Each section image includes multiple section images formed by scanning the code layer by layer to accurately evaluate the heart structure.

[0045] For a ventricle, considering that the ventricular image is sensitive at the end of the ventricular systole and diastole, the contrast data is obvious. Based on this, the biological heart image of the embodiment of the present invention may include at least one biological heart image at the end of the working state,

[0046] When the biological heart image includes biological heart images at the end of multiple working states, the multiple working states may be of the same type or of different types.

[0047] When multiple working states are of the same type, these working states may be biological heart images at the end of systole. For example, three biological heart images at the end of diastole may be considered as biological heart images at the end of diastole contained in three consecutive cardiac working cycles. Of course, biological heart images at the end of diastole may also be selected regularly or irregularly from many cardiac working cycles.

[0048] When the multiple working states are of different types, these working states can be biological heart images at the end of systole and diastole, for example, they can be biological heart images at the end of diastole and biological heart images at the end of systole in the same cardiac working cycle. Of course, biological heart images at the end of systole and diastole can also be selected regularly or irregularly from many cardiac working cycles. In this case, the offset parameter of the interval between the left and right ventricles to the left ventricle side can be accurately determined.

[0049] The processing module can be used to determine the geometric parameters of at least one ventricle based on the biological heart image. The geometric parameters of the ventricle can be the geometric parameters of one ventricle or the geometric parameters of multiple ventricles, which can be selected according to actual conditions.

[0050] When the biological heart image is a biological heart image, the geometric parameters of at least one ventricle can be determined based on the biological heart image. For example, for a human heart, if it is a geometric parameter of a ventricle, then the geometric parameter of the ventricle can be a geometric parameter of the left ventricle or a geometric parameter of the right ventricle, and if it is a geometric parameter of two ventricles, then it can be a geometric parameter of the left ventricle and a geometric parameter of the right ventricle.

[0051] When the biological heart image is a plurality of biological heart images, the geometric parameters of a ventricle can be determined based on each biological heart image. Therefore, the geometric parameters of a plurality of ventricles can be determined based on the plurality of biological heart images. The geometric parameters of the plurality of ventricles can be the geometric parameters of the same ventricle or the geometric parameters of different ventricles. For example, for a human heart, if the geometric parameters of the plurality of ventricles are the geometric parameters of the same ventricle, they can be the geometric parameters of a plurality of left ventricles or the geometric parameters of the right ventricle. If the geometric parameters of the plurality of ventricles are the geometric parameters of two different types of ventricles, they can include respectively determining the geometric parameters of a left ventricle and a right ventricle from two biological heart images.

[0052] Exemplarily, at least one ventricle image can be separated from a biological heart image by image segmentation. At the same time, when separating the ventricle image, at least one ventricle geometric parameter can also be generated, and these geometric parameters can include the maximum section perimeter, the maximum section area or the ventricle volume of the ventricle. Image segmentation can be to automatically segment at least one ventricle image from a biological heart image by using an image segmentation algorithm, or to segment at least one ventricle image from a biological heart image by manual image segmentation.

[0053] In one example, when an image segmentation algorithm is used to automatically segment at least one ventricle image from a biological heart image, the biological heart image may be processed using a trained image segmentation model. The image segmentation model may be an existing image segmentation model such as a fully convolutional neural network, U-Net, or a traditional image segmentation algorithm such as threshold segmentation, edge-based segmentation, or wavelet transform-based segmentation.

[0054] For example, if the fully convolutional neural network can segment the left ventricle from the human heart image after training and generate the geometric parameters of the left and right ventricles, a large number of human heart images can be selected during the training phase, and the left ventricle contour and various geometric parameters of the left ventricle, such as the maximum section circumference, the maximum section area or the ventricular volume, can be marked on each human heart image to form training labels. Multiple labeled human heart images are input into the fully convolutional neural network in batches. The fully convolutional neural network performs multiple convolutions on the labeled human heart images to achieve pixel-level classification, and then uses up-pooling, deconvolution and other methods to restore the pixel-classified image resolution to the original resolution to obtain the prediction result. Then, the loss is determined based on the training label and the prediction result. If the loss is greater than the preset loss, the back-conduction algorithm is used to update the network parameters of the fully convolutional neural network, such as weights and offset values. If the loss is less than or equal to the preset loss, it means that the training of the fully convolutional neural network is completed and can be tested.

[0055] On this basis, the human heart image can be input into the trained fully convolutional neural network to output the left ventricle image and the geometric parameters of the left ventricle.

[0056] In one example, when at least one ventricular image is segmented from a biological heart image by manual image segmentation, the processing module is used to generate at least one ventricular region image and geometric parameters in response to an operation for the ventricular region in the biological heart region image.

[0057] In practical applications, the operation on the ventricular region in the biological heart region image is the operation on the contour line of the ventricular region in the biological heart image. For example, an experienced physician clicks, outlines, etc. on the contour line of the ventricular region in the computer software interactive interface to select the contour line of the ventricular region. After the contour line of the ventricular region is selected, the computer software can automatically generate the geometric parameters of the ventricle based on the contour line of the ventricular region.

[0058] The determination module is used to determine the actual displacement parameter of the ventricular septum based on the geometric parameters of the at least one ventricle, and the ventricular septum displacement parameter can accurately determine the displacement degree of the septum between the left and right ventricles toward the left ventricle. The ventricular septum displacement parameter can include: septum swing index (SSI).

[0059] Exemplarily, the biological heart image includes at least one biological heart image at the end of a working state, and the actual offset parameter may be an actual offset parameter determined by a septum swing index (SSI) of the biological heart at the end of at least one working state.

[0060] Taking the human heart as an example, the two working states of the heart are the diastole and the systole of the biological heart, so the diaphragm swing index can also include: the diastole diaphragm swing index SSI distolic , Systolic diaphragm swing index SSI systolic At least one of .

[0061] When the diastolic excursion index includes the diastolic diaphragm excursion index SSI distolic or systolic diaphragm swing index SSI systolic , the actual excursion parameter can reflect the degree of diastolic or systolic diaphragm excursion.

[0062] When the diastolic excursion index includes the diastolic diaphragm excursion index SSI distolic and systolic diaphragm swing index (SSI) systolic , the actual excursion parameters can fully reflect the degree of diastolic and systolic diastolic diastole.

[0063] When the biological heart image includes multiple biological heart images of the same type at the end of the working state, the actual offset parameter may include the average value of the diaphragm swing index of the biological heart at the end of the multiple working states. At this time, the diaphragm swing index can be determined for each biological heart image, and then the diaphragm swing indexes determined for all biological heart images are added and averaged, so that the same type of actual offset parameters can be accurately obtained. It should be understood that if the diaphragm swing index of the heart contraction period is determined for each biological heart image, then the average value of the diaphragm swing index of the biological heart at the end of the multiple working states is used as the actual offset parameter, so that the actual offset parameter of the heart contraction period can be accurately obtained.

[0064] When the biological heart image includes biological heart images at the end of two working states, the two working states include the end of diastole and the end of systole of the biological heart, therefore, the actual offset parameter is the weighted sum of the diaphragm swing index of the biological heart at the end of the two working states. At this time, the actual offset parameter can be determined by referring to the formula for calculating the mean arterial pressure by cardiac catheterization.

[0065] For example, the weight of the diastolic end-stage diaphragm swing index can be set to 2 / 3, and the weight of the diaphragm swing index at the systolic end-stage can be set to 1 / 3, so as to calculate the actual diaphragm swing index, and use the actual diaphragm swing index as the actual offset parameter. In other words, when the biological heart image includes two biological heart images at the end of different types of working states, the actual offset parameter satisfies:

[0066] SSI 实 Indicates the actual diaphragm swing index, SSI systolic represents the systolic diaphragm swing index, SSI distolic Represents the diastolic diaphragm swing index.

[0067] In one example, the geometric parameters of each ventricle are the geometric parameters of multiple ventricular sections at the end of the same working state. At this time, the determination module can be used to select the geometric parameters of at least two target ventricular sections from the geometric parameters of multiple ventricular sections at the end of the same working state based on the areas of each of the ventricular sections at the end of the same working state. Here, the area of ​​at least two target ventricular section images is larger than the area of ​​non-target ventricles in the multiple ventricular section images. Since the displacement of the ventricular septum is more obvious when the section area is the largest, when the determination module determines the corresponding diaphragm swing index based on the geometric parameters of each target ventricular section, the determined diaphragm swing index is more accurate.

[0068] In practical applications, a magnetic resonance imaging device can be used to scan the axial image of the human heart in layers in the axial direction. The acquired human heart image includes multiple layers (such as 8 layers) of cardiac axial section images. After that, the ventricular axial section image is separated from each layer of cardiac axial section image by image segmentation, and the geometric parameters of the ventricle are generated at the same time, thereby obtaining multiple layers of ventricular axial section images and their geometric parameters. For example, these geometric parameters may include ventricular volume, ventricular axial section area, and ventricular axial section circumference.

[0069] Next, the multi-layer ventricular axial section images are sorted according to the multi-layer ventricular axial section area, and the multi-layer ventricular axial section images ranked in the first few positions are selected for subsequent determination of actual offset parameters. For example, the first two ventricular axial section images with the largest area can be selected to determine the actual offset parameters. It can be understood that since the shape of the ventricle is approximately circular, when the two ventricular axial section images with the largest area are selected, the heart axial section images where the two ventricular axial section images are located are continuous.

[0070] In one example, when the geometric parameters of the ventricles include the volumes of the two ventricles, the actual excursion parameter includes the diaphragm excursion index, which is a ratio of the diaphragm excursion index to the volumes of the two ventricles.

[0071] When the two ventricles include the left ventricle and the right ventricle, the diaphragm sway index can be the ratio of the left ventricle volume to the right ventricle volume, or the ratio of the maximum cross-sectional area of ​​the left ventricle axial section image to the maximum cross-sectional area of ​​the right ventricle axial section image. It can be seen that the diaphragm sway index is related to the ratio of the volumes of the two ventricles, and the diaphragm sway index is related to the ratio of the maximum cross-sectional areas of the two ventricles.

[0072] When there is only one ventricle, the diaphragm swing index can be the ratio of the maximum section area of ​​the ventricular axial section to the square of the maximum section perimeter of the ventricular axial section. It can be seen that the diaphragm swing index is proportional to the maximum section area of ​​the ventricular axial section image, and the diaphragm swing index is inversely proportional to the square of the maximum section perimeter of the ventricular axial section image. The diaphragm swing index satisfies:

[0073]

[0074] Among them, SSI is the septal swing index, ventriculararea is the maximum section area of ​​the ventricular axial section image, ventricularperimeter is the maximum section circumference of the ventricular axial section image, and the maximum section area, maximum section area and maximum section circumference of the ventricular axial section image belong to the same ventricle.

[0075] In one example, when the septal swing index is the septal swing index of the left ventricle, the ratio of the maximum section area of ​​the left ventricle axial section image to the square of the maximum section perimeter of the left ventricle axial section image, the left ventricle septal swing index satisfies:

[0076]

[0077] Among them, SSI represents the left ventricular septum sway index, leftventriculararea represents the maximum section area of ​​the left ventricular axial section image, and leftventricularperimeter represents the maximum section circumference of the left ventricular axial section image.

[0078] In one example, it may be the ratio of the maximum section area of ​​the right ventricular axial section image to the square of the maximum section perimeter, and the right ventricular septum swing index satisfies:

[0079] Among them, SSI represents the right ventricular septum sway index, rightventriculararea represents the maximum section area of ​​the right ventricular axial section image, and righttventricularperimeter represents the maximum section circumference of the right ventricular axial section image.

[0080] As can be seen from the above, the exemplary embodiment of the present invention can determine the actual excursion parameter of the ventricular septum in a non-invasive manner to reflect the degree of excursion of the ventricular septum. Figure 2 The figure shows axial cardiac images of four groups of clinical trial subjects at different stages of the disease, obtained by scanning with magnetic resonance movie sequences. The axial cardiac images of each group of clinical trial subjects include axial images at the end of diastole and axial images at the end of systole.

[0081] like Figure 2 As shown, the first row is the end-diastolic images, including the axial image A1 of the end-diastolic heart of clinical trial subject A, the axial image B1 of the end-diastolic heart of clinical trial subject B, the axial image C1 of the end-diastolic heart of clinical trial subject C, and the axial image D1 of the end-diastolic heart of clinical trial subject D. The second row is the end-systolic images, including the axial image A2 of the end-systolic heart of clinical trial subject A, the axial image B2 of the end-systolic heart of clinical trial subject B, the axial image C2 of the end-systolic heart of clinical trial subject C, and the axial image D2 of the end-systolic heart of clinical trial subject D.

[0082] Along Figure 2From left to right, the mean pulmonary artery pressure (hereinafter referred to as mPAP) of clinical trial subjects A, clinical trial subjects B, clinical trial subjects C, and clinical trial subjects D gradually increased. Among them, clinical trial subject A had normal mPAP, clinical trial subject B had mPAP of 35 mm Hg, clinical trial subject C had mPAP of 56 mm Hg, and clinical trial subject D had mPAP of 81 mm Hg.

[0083] Figure 2 In each axial image of the heart at the end of diastole and systole, the left chamber is the right ventricle, the right chamber is the left ventricle, and the septum between the left and right ventricles is the interventricular septum. Figure 2 It can be seen that as the severity of pulmonary hypertension increases, the left ventricle changes from a round shape to a "D" shape, and the right ventricle changes from a crescent shape to a round shape. Therefore, pulmonary artery pressure is correlated with ventricular septal deviation.

[0084] Based on this, an embodiment of the present invention mathematically models the ventricular septum of clinical trial subjects at different stages of the disease based on the geometry of the heart, to illustrate that the ventricular septum swing index used by the embodiment of the present invention to determine the actual offset parameter is less affected by individual differences and has wide applicability in the process of evaluating pulmonary artery pressure.

[0085] Figure 3 A shows a modeling diagram of the ventricular septum of a clinical trial subject A according to an exemplary embodiment of the present invention. Figure 3 B shows the ventricular septum modeling diagram of clinical trial subject B according to an exemplary embodiment of the present invention. Figure 3 C shows a ventricular septum modeling diagram of clinical trial participant C according to an exemplary embodiment of the present invention. Figure 3 D shows the modeling diagram of the ventricular septum of clinical trial patient D according to an exemplary embodiment of the present invention. Figure 3 A~ Figure 3 As shown in D, the movement of the ventricular septum is approximated as the swing of an elastic rope connected to the two ends of a semicircle with a radius of R. The area formed by the elastic rope (solid line) and the semicircle corresponds to the area of ​​the left ventricle. During the swing of the ventricular septum, since the pressure distribution of the left and right ventricles is basically uniform, it can be assumed that the elastic rope (ventricular septum) is maintained in an arc shape. Let the distance from the midpoint of the elastic rope to the center of the semicircle be L, R be the radius of the left ventricle, d = L / R, θ = π-2atan(1 / d), and R = 2 / 3.

[0086] like Figure 3 A, when L=R, SSI=4π 2 / 4π 2 =1

[0087] like Figure 3 As shown in B, when the elastic rope is on the left side of the center of the circle, reference formula 2 can be calculated to get

[0088] like Figure 3 As shown in C, when the midpoint of the elastic rope is at the center of the circle, that is, L = 0, refer to formula 2 to calculate

[0089] like Figure 3 As shown in D, when the elastic rope is on the right side of the center of the circle, refer to formula 2 to calculate

[0090] When L=-R (not shown), SSI=0.

[0091] It can be seen that during the ventricular septum excursion, only d is related to the ventricular septum membrane swing index, but has nothing to do with the initial left ventricular radius R (solid line). Therefore, when the embodiment of the present invention uses formula 2 to determine SSI, individual differences of organisms can be ignored.

[0092] In order to verify the relationship between the diaphragm swing index SSI and pulmonary hypertension, the exemplary embodiment of the present invention also collected cardiac magnetic resonance images and pulmonary artery pressure measurement data of 109 patients to obtain the following Figure 4A Figure 2 shows the relationship between SSI and mPAP.

[0093] like Figure 4A As shown, curve a is the relationship curve between SSI and mPAP in patients with pulmonary hypertension, and dashed lines a1 and a2 are the 95% confidence intervals of curve a. Curve b is the relationship curve between SSI and mPAP in people with normal pulmonary artery pressure, and dashed lines b1 and b2 are the 95% confidence intervals of curve b. Figure 4A It can be seen that when mPAP is greater than 20 mmHg, the separation between curve a and curve b is relatively good. Since the mPAP of patients with pulmonary hypertension is greater than or equal to 25 mmHg, the mPAP of people with normal pulmonary artery pressure is between 18-25 mmHg. Therefore, statistical analysis has verified the effectiveness of the diaphragm swing index SSI in predicting patients' pulmonary hypertension. Therefore, when the actual offset parameters determined by the device for determining the ventricular septum offset parameters in an embodiment of the present invention include the diaphragm swing index SSI, patients with pulmonary hypertension can be screened relatively well.

[0094] Figure 4B Curve a is a common imaging assessment index for patients with pulmonary hypertension: the relationship curve between myocardial mass index VMI and mPAP, and the dotted lines a1 and a2 are the 95% confidence intervals of curve a. Curve b is the relationship curve between VMI and mPAP for people with normal pulmonary artery pressure, and the dotted lines b1 and b2 are the 95% confidence intervals of curve b. Figure 4AIt can be seen that when mPAP is greater than 20 mmHg, there is overlap between curve a and curve b and they are not completely separated. Therefore, the ventricular mass index of patients with pulmonary hypertension cannot well measure and predict the patient's mean pulmonary artery pressure.

[0095] Figure 4C The figure shows the relationship between the main pulmonary artery diameter MPA and mPAP, another common imaging evaluation index. Curve a is the relationship between MPA and mPAP in patients with pulmonary hypertension. The dotted lines a1 and a2 are the 95% confidence intervals of curve a. Curve b is the relationship between MPA and mPAP in people with normal pulmonary artery pressure. The dotted lines b1 and b2 are the 95% confidence intervals of curve b. Figure 4A It can be seen that when mPAP is greater than 20 mmHg, there is overlap between curve a and curve b and they are not completely separated. Therefore, the main pulmonary artery diameter of patients with pulmonary hypertension cannot be well measured to predict the patient's mean pulmonary artery pressure.

[0096] An exemplary embodiment of the present invention further provides an electronic device, Figure 7 FIG. 1 is a schematic diagram showing the structure of an electronic device according to an embodiment of the present invention. Figure 7 As shown, the electronic device of the embodiment of the present invention includes: at least one processor; and a memory connected to the at least one processor. The memory stores a computer program that can be executed by the at least one processor, and when the computer program is executed by the at least one processor, the electronic device executes the method for determining the ventricular septum offset parameter according to the embodiment of the present invention. The method includes:

[0097] obtaining biological heart images;

[0098] determining geometric parameters of at least one ventricle based on the biological heart image;

[0099] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0100] The exemplary embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method for determining a ventricular septal excursion parameter according to an embodiment of the present invention. The method comprises:

[0101] obtaining biological heart images;

[0102] determining geometric parameters of at least one ventricle based on the image of the biological heart region;

[0103] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0104] The exemplary embodiments of the present disclosure further provide a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to perform a method for determining a ventricular septal excursion parameter according to an embodiment of the present invention. The method includes:

[0105] obtaining biological heart images;

[0106] determining geometric parameters of at least one ventricle based on the image of the biological heart region;

[0107] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0108] refer to Figure 7 , a block diagram of an electronic device that can be used as a server or client of the present disclosure will now be described, which is an example of a hardware device that can be applied to various aspects of the present disclosure. The electronic device is intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0109] like Figure 7 As shown, the electronic device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0110] A plurality of components in the electronic device 700 are connected to the I / O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 may be any type of device capable of inputting information to the electronic device 700, and the input unit 706 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 707 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 704 may include, but is not limited to, a disk, an optical disk. The communication unit 709 allows the electronic device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0111] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 701 performs the various methods and processes described above. For example, in some embodiments, the method for determining the ventricular septal excursion parameters of an embodiment of the present invention may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 700 via the ROM 702 and / or the communication unit 709. In some embodiments, the computing unit 701 may be configured to perform the method for determining the ventricular septal excursion parameters of an embodiment of the present invention in any other appropriate manner (e.g., by means of firmware), the method comprising:

[0112] obtaining biological heart images;

[0113] determining geometric parameters of at least one ventricle based on the image of the biological heart region;

[0114] An actual excursion parameter of the interventricular septum is determined based on at least one geometric parameter of the ventricle.

[0115] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0116] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0117] As used in this disclosure, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., disk, optical disk, memory, programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0118] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0119] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0120] A computer system may include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship to each other.

[0121] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instruction is loaded and executed on a computer, the process or function described in the embodiment of the present disclosure is executed in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, a terminal, a user device or other programmable device. The computer program or instruction may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer program or instruction may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server, data center, etc. that integrates one or more available media. The available medium may be a magnetic medium, for example, a floppy disk, a hard disk, a tape; it may also be an optical medium, for example, a digital video disc (DVD); it may also be a semiconductor medium, for example, a solid state drive (SSD).

[0122] Although the present disclosure has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present disclosure. Accordingly, this specification and the drawings are merely exemplary illustrations of the present disclosure as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present disclosure. Obviously, those skilled in the art may make various modifications and variations to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A device for determining a ventricular septal excursion parameter, characterized in that: include: An acquisition module, used for acquiring a biological heart image; a processing module for determining geometric parameters of at least one ventricle based on the biological heart image; a determination module for determining an actual excursion parameter of the ventricular septum based on at least one geometric parameter of the ventricle; The biological heart image includes at least one biological heart image at the end of a working state, and the actual excursion parameter includes an actual excursion parameter determined by a diaphragm swing index of the biological heart at the end of at least one working state.

2. The device for determining the ventricular septum excursion parameter according to claim 1, characterized in that: The processing module is used for generating at least one ventricular region image and geometric parameters in response to an operation for targeting a ventricular region in the biological heart image.

3. The device for determining the ventricular septum excursion parameter according to claim 2, characterized in that: The operation on the ventricular region in the biological heart image is a contour line operation on the ventricular region in the biological heart image.

4. The device for determining the ventricular septum excursion parameter according to claim 1, characterized in that: The geometric parameters of each ventricle include the maximum section area and the maximum section circumference of the same ventricular axial section image, and the actual offset parameters include the diaphragm sway index, which is directly proportional to the maximum section area and inversely proportional to the square of the maximum section circumference.

5. The device according to claim 3, characterized in that The actual offset parameters satisfy: ； Where SSI is the diaphragm swing index, Ventriculararea is the maximum cross-sectional area, Ventricularperimeter is the maximum section perimeter, and the maximum section area and the maximum section perimeter belong to the same ventricle.

6. The device for determining the ventricular septum excursion parameter according to claim 1, characterized in that: When the geometrical parameter of the ventricle comprises the volumes of the two ventricles, the actual excursion parameter comprises a diaphragm excursion index, the diaphragm excursion index being related to the ratio of the volumes of the two ventricles; or, When the geometric parameters of the ventricle include the maximum cross-sectional area of ​​two axial cross-sectional images of the ventricle contained in the same heart cross-section separated from the biological heart image, the actual offset parameter includes a diaphragm swing index, which is related to the ratio of the maximum cross-sectional area of ​​the two axial cross-sectional images of the ventricle.

7. The device for determining the ventricular septal excursion parameter according to any one of claims 1 to 6, characterized in that: When the biological heart image includes a plurality of biological heart images of the same type at the end of a working state, the actual offset parameter includes an average value of diaphragm swing indexes of the biological heart at the end of the plurality of working states.

8. The device for determining the ventricular septal excursion parameter according to any one of claims 1 to 6, characterized in that: When the biological heart image includes biological heart images at the end of two working states, the actual offset parameter includes a weighted sum of diaphragm swing indices of the biological heart at the end of the two working states, and the two working state ends include the end of diastole and the end of systole of the biological heart.

9. The device for determining the ventricular septum excursion parameter according to any one of claims 1 to 6, characterized in that: The geometric parameters of each ventricle are geometric parameters of multiple ventricular sections at the end of the same working state; The determination module is used to select geometric parameters of at least two target ventricular sections from geometric parameters of multiple ventricular sections at the end of the same working state based on the areas of each of the ventricular sections at the end of the same working state, and determine a corresponding diaphragm swing index based on the geometric parameters of each target ventricular section; The areas of at least two of the target ventricle section images are larger than the areas of non-target ventricles in the multiple ventricle section images.

10. An electronic device, characterized in that: include: processor; as well as, Memory for storing programs, The program includes instructions, which, when executed by the processor, cause the processor to perform a method for determining a ventricular septal excursion parameter, the method comprising: obtaining biological heart images; determining geometric parameters of at least one ventricle based on the biological heart image; determining an actual excursion parameter of the ventricular septum based on at least one geometric parameter of the ventricle; The biological heart image includes at least one biological heart image at the end of a working state, and the actual excursion parameter includes an actual excursion parameter determined by a diaphragm swing index of the biological heart at the end of at least one working state.

11. A computer-readable storage medium, characterized in that: A computer instruction is stored, and the computer instruction is used to make a computer execute a method for determining a ventricular septal excursion parameter, the method comprising: obtaining biological heart images; determining geometric parameters of at least one ventricle based on the biological heart image; determining an actual excursion parameter of the ventricular septum based on at least one geometric parameter of the ventricle; The biological heart image includes at least one biological heart image at the end of a working state, and the actual excursion parameter includes an actual excursion parameter determined by a diaphragm swing index of the biological heart at the end of at least one working state.

Images