Method, device, equipment and storage medium for three-dimensional reconstruction of cardiac images

Abstract

The present invention belongs to the field of computer technology, and discloses a method, device, equipment and storage medium for three-dimensional reconstruction of a heart image. The present invention obtains the initial heart shape corresponding to the short-axis heart image, and performs image segmentation on the short-axis heart image to obtain three-dimensional contour points; performs a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape; transforms the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result. Because before performing three-dimensional modeling, the initial heart shape is also compositely transformed according to the three-dimensional contour points, so that the initial heart shape is close to the heart contour in the short-axis heart image, and then the transformed initial heart shape is transformed into the heart image coordinate system for three-dimensional modeling, thereby improving the accuracy of three-dimensional modeling of heart images.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, equipment and storage medium for three-dimensional reconstruction of cardiac images. Background Art

[0002] Clinically, the evaluation of cardiac ejection fraction and myocardial mass, as well as other functional parameters (such as ventricular wall motion and wall thickness), is one of the important means of early diagnosis of heart disease. However, the heart is a complex three-dimensional organ with contraction and relaxation movements, and clinically, cardiac motion parameters play a more obvious role in describing its local abnormalities and early microlesions. This requires accurate segmentation of the three-dimensional structure of cardiac images in different phases (at different times in diastole and systole), and three-dimensional modeling based on the segmentation results to obtain accurate static and dynamic parameters of the heart. However, with the substantial improvement in the temporal and spatial resolution of imaging equipment, the massive amount of image data has greatly increased the difficulty of segmentation.

[0003] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for three-dimensional reconstruction of cardiac images, aiming to solve the technical problems that the existing technology is difficult to accurately segment cardiac images and difficult to three-dimensional model.

[0005] To achieve the above object, the present invention provides a method for three-dimensional reconstruction of cardiac images, the method comprising the following steps:

[0006] Acquiring an initial heart shape corresponding to a short-axis heart image, and performing image segmentation on the short-axis heart image to obtain three-dimensional contour points;

[0007] Performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape;

[0008] The transformed initial heart shape is transformed into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result.

[0009] Optionally, the step of performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape comprises:

[0010] Traversing the shape contour points in the initial shape of the heart to obtain the traversed current shape contour points;

[0011] Calculating the relative distance between the current shape contour point and each of the three-dimensional contour points;

[0012] Selecting a number of adjacent contour points from the three-dimensional contour points according to the relative distance;

[0013] Determine a transformed contour point according to the current shape contour point and the adjacent contour point;

[0014] transforming the current shape contour points in the initial shape of the heart according to the transformed contour points;

[0015] At the end of the traversal, the transformed initial heart shape is obtained according to the transformed shape contour points.

[0016] Optionally, the step of determining the transformed contour point according to the current shape contour point and the adjacent contour point includes:

[0017] Determine the coordinate weight corresponding to each adjacent contour point according to the current shape contour point and the adjacent contour points;

[0018] The coordinates of the adjacent contour points are weightedly summed based on the coordinate weights to obtain transformed contour points.

[0019] Optionally, the step of selecting a plurality of adjacent contour points from the three-dimensional contour points according to the relative distance includes:

[0020] Constructing a set of adjacent contour points according to three-dimensional contour points whose relative distances to the current shape contour points are less than or equal to a preset distance threshold;

[0021] Sorting the three-dimensional contour points in the set of adjacent contour points according to the relative distance to obtain a sorting result;

[0022] A preset number of adjacent contour points are selected according to the sorting result.

[0023] Optionally, after the step of transforming the current shape contour points in the initial heart shape according to the transformed contour points, the method further includes:

[0024] The shape contour points in the initial shape of the heart are filtered by a preset filtering algorithm to make the contour surface of the initial shape of the heart smooth.

[0025] Optionally, the step of obtaining an initial heart shape corresponding to the short-axis heart image includes:

[0026] Acquiring a time phase corresponding to the short-axis cardiac image;

[0027] When the time phase corresponding to the short-axis cardiac image is not the first time phase, obtaining a three-dimensional reconstruction result corresponding to the previous time phase;

[0028] The three-dimensional reconstruction result is used as the initial heart shape corresponding to the short-axis heart image.

[0029] Optionally, after the step of acquiring the time phase corresponding to the short-axis cardiac image, the method further includes:

[0030] When the time phase corresponding to the short-axis heart image is the first time phase, searching for a standard heart shape in a preset standard organ library;

[0031] An initial heart shape corresponding to the short-axis heart image is determined according to the standard heart shape.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also proposes a three-dimensional reconstruction device for cardiac images, which includes the following modules:

[0033] An image segmentation module, used for acquiring an initial heart shape corresponding to a short-axis heart image, and performing image segmentation on the short-axis heart image to obtain three-dimensional contour points;

[0034] A shape transformation module, used for performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape;

[0035] The three-dimensional reconstruction module is used to transform the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result.

[0036] In addition, to achieve the above-mentioned purpose, the present invention also proposes a three-dimensional reconstruction device for cardiac images, which includes: a processor, a memory, and a three-dimensional reconstruction program for cardiac images stored in the memory and executable on the processor, and the three-dimensional reconstruction program for cardiac images implements the steps of the three-dimensional reconstruction method for cardiac images as described above when executed by the processor.

[0037] In addition, to achieve the above objectives, the present invention also proposes a computer-readable storage medium, on which a cardiac image three-dimensional reconstruction program is stored, and when the cardiac image three-dimensional reconstruction program is executed, the steps of the cardiac image three-dimensional reconstruction method as described above are implemented.

[0038] The present invention obtains the initial heart shape corresponding to the short-axis heart image, and performs image segmentation on the short-axis heart image to obtain three-dimensional contour points; performs a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape; and transforms the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result. Before three-dimensional modeling, the initial heart shape is compositely transformed according to the three-dimensional contour points, so that the initial heart shape is close to the heart contour in the short-axis heart image, and then the transformed initial heart shape is transformed into the heart image coordinate system for three-dimensional modeling, thereby improving the accuracy of three-dimensional modeling of heart images. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 It is a schematic diagram of the structure of an electronic device in a hardware operating environment involved in an embodiment of the present invention;

[0040] Figure 2 A schematic diagram of the flow chart of the first embodiment of the method for three-dimensional reconstruction of cardiac images of the present invention;

[0041] Figure 3 A schematic diagram of the flow chart of a second embodiment of a method for three-dimensional reconstruction of cardiac images according to the present invention;

[0042] Figure 4 FIG. 4 is a structural block diagram of a first embodiment of a device for 3D reconstruction of cardiac images according to the present invention.

[0043] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0045] Reference Figure 1 , Figure 1 The figure is a schematic diagram of the structure of a cardiac image three-dimensional reconstruction device in the hardware operating environment involved in the embodiment of the present invention.

[0046] like Figure 1As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0047] Those skilled in the art will understand that Figure 1 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0048] like Figure 1 As shown, the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and a cardiac image three-dimensional reconstruction program.

[0049] exist Figure 1 In the electronic device shown, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in a cardiac image three-dimensional reconstruction device, and the electronic device calls the cardiac image three-dimensional reconstruction program stored in the memory 1005 through the processor 1001, and executes the cardiac image three-dimensional reconstruction method provided in an embodiment of the present invention.

[0050] The embodiment of the present invention provides a method for three-dimensional reconstruction of a cardiac image, referring to Figure 2 , Figure 2 FIG. 4 is a flow chart of a first embodiment of a method for three-dimensional reconstruction of cardiac images according to the present invention.

[0051] In this embodiment, the method for three-dimensional reconstruction of cardiac images includes the following steps:

[0052] Step S10: acquiring an initial heart shape corresponding to the short-axis heart image, and performing image segmentation on the short-axis heart image to obtain three-dimensional contour points.

[0053] It should be noted that the executor of this embodiment can be the three-dimensional reconstruction device of the heart image, and the three-dimensional reconstruction device of the heart image can be an electronic device such as a personal computer or a server, or a device that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment and the following embodiments, the three-dimensional reconstruction of the heart image is taken as an example to illustrate the three-dimensional reconstruction method of the heart image of the present invention.

[0054] It should be noted that the short-axis heart image can be an image of the short axis of the heart, and the short-axis heart image can be input into the heart image three-dimensional reconstruction device by the user, or directly input into the heart image three-dimensional reconstruction device by the image acquisition device, wherein the image acquisition device can be a nuclear magnetic resonance imaging device, and the short-axis heart image can be input into the heart image three-dimensional reconstruction device in phase sequence for processing. The initial shape of the heart corresponding to the short-axis heart image can be obtained by searching the initial shape of the heart corresponding to the short-axis heart image in a preset shape library according to the image identifier of the short-axis heart image. The short-axis heart image can be segmented to obtain three-dimensional contour points by using a preset image segmentation model to segment the short-axis heart image, divide the heart regions in the short-axis heart image, and extract the contour points of each heart region to obtain three-dimensional contour points, wherein the preset image segmentation mode can be a neural network model pre-trained with a large number of samples.

[0055] Further, in order to quickly obtain the initial heart shape corresponding to the short-axis heart image, the step of obtaining the initial heart shape corresponding to the short-axis heart image in this embodiment may include:

[0056] Acquiring a time phase corresponding to the short-axis cardiac image;

[0057] When the time phase corresponding to the short-axis cardiac image is not the first time phase, obtaining a three-dimensional reconstruction result corresponding to the previous time phase;

[0058] The three-dimensional reconstruction result is used as the initial heart shape corresponding to the short-axis heart image.

[0059] It should be noted that, since the heart is a moving organ, the shape of the heart changes gradually with the sequence of time phases, and the three-dimensional reconstruction result constructed based on the short-axis heart image of the previous time phase can be used as the initial shape of the heart corresponding to the short-axis heart image of the current time phase. When obtaining the initial shape of the heart corresponding to the short-axis heart image, the time phase corresponding to the short-axis heart image can be obtained. When the time phase corresponding to the short-axis heart image is not the first time phase, the corresponding three-dimensional reconstruction result of the previous time phase is obtained, and the obtained three-dimensional reconstruction result is used as the initial shape of the heart corresponding to the short-axis heart image.

[0060] In actual use, the short-axis cardiac image can be input into the cardiac image three-dimensional reconstruction device for processing in phase order. Therefore, the short-axis cardiac image can have a corresponding phase identifier. According to the phase identifier corresponding to the short-axis cardiac image, it can be determined whether the phase corresponding to the short-axis cardiac image is the first phase.

[0061] It can be understood that if the time phase corresponding to the short-axis cardiac image is not the first time phase, directly obtaining the corresponding three-dimensional reconstruction result of the previous time phase and using the obtained three-dimensional reconstruction result as the initial shape of the heart corresponding to the current short-axis cardiac image can reduce unnecessary calculations, thereby quickly obtaining the initial shape of the heart corresponding to the short-axis cardiac image.

[0062] Furthermore, since when the time phase corresponding to the short-axis cardiac image is the first time phase, there is no previous time phase, and therefore, the three-dimensional reconstruction result corresponding to the previous time phase cannot be obtained. In order to perform three-dimensional reconstruction normally in this case, after the step of obtaining the time phase corresponding to the short-axis cardiac image in this embodiment, the following may also be included:

[0063] When the time phase corresponding to the short-axis heart image is the first time phase, searching for a standard heart shape in a preset standard organ library;

[0064] An initial heart shape corresponding to the short-axis heart image is determined according to the standard heart shape.

[0065] It should be noted that the preset standard organ library may be a database pre-set by the administrator of the cardiac image three-dimensional reconstruction device, and the preset standard organ library may include average shapes corresponding to various organs. The standard heart shape may be the average shape corresponding to the heart, and searching for the standard heart shape in the preset standard organ library may be searching for the average shape corresponding to the heart in the preset standard organ library, and processing the found standard heart shape to obtain the standard heart shape.

[0066] In actual use, since the standard heart shape is the average shape of the heart, it may not match the heart in the short-axis heart image. If it is directly used as the initial heart shape corresponding to the short-axis heart image, the accuracy of the final three-dimensional modeling result may be reduced. In order to avoid this situation, after obtaining the standard heart shape, the three-dimensional contour points corresponding to the standard heart image and the short-axis heart image are point cloud aligned, and the standard heart shape is transformed according to the alignment result, and the transformed standard heart shape is used as the initial heart shape corresponding to the short-axis heart image.

[0067] Step S20: performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape.

[0068] It should be noted that performing a composite transformation on shape contour points in the initial shape of the heart according to three-dimensional contour points may be performing multiple iterative transformations on the shape contour points in the initial shape of the heart according to the three-dimensional contour points, and continuously adjusting the shape contour points in the initial shape of the heart during the iterative process, so that the initial shape of the heart continuously approaches the heart contour in the short-axis heart image, and after multiple iterative transformations and adjustments, the transformed initial shape of the heart is obtained.

[0069] In actual use, in order to facilitate compound transformation, before the shape contour points in the initial shape of the heart are compound transformed according to the three-dimensional contour points, the bottom contour points of the heart can also be determined according to the three-dimensional contour points, and the heart image can be rotated and adjusted so that the plane where the new bottom contour points are located is in the horizontal direction, and the initial shape of the heart can be rotated and adjusted so that the bottom plane of the center of the initial shape of the heart is in the horizontal direction. After the adjustment is completed, the shape contour points in the initial shape of the heart are compound transformed according to the three-dimensional contour points.

[0070] Step S30: transforming the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result.

[0071] It should be noted that establishing a cardiac image coordinate system according to the short-axis cardiac image may be to select any point in the short-axis cardiac image as the coordinate origin, and to establish the cardiac image coordinate system according to the coordinate origin. Transforming the transformed initial heart shape into the cardiac image coordinate system may be to correspond the transformed initial heart shape to the cardiac region in the cardiac image one by one according to the cardiac region, perform an inverse coordinate transformation on the transformed initial heart shape, and transform it into the cardiac image coordinate system, thereby obtaining a three-dimensional reconstruction result, wherein the three-dimensional reconstruction result may be a three-dimensional reconstructed image.

[0072] This embodiment obtains the initial heart shape corresponding to the short-axis heart image and performs image segmentation on the short-axis heart image to obtain three-dimensional contour points; performs a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape; and transforms the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result. Because the initial heart shape is compositely transformed according to the three-dimensional contour points before three-dimensional modeling is performed, so that the initial heart shape is close to the heart contour in the short-axis heart image, and then the transformed initial heart shape is transformed into the heart image coordinate system for three-dimensional modeling, the accuracy of three-dimensional modeling of the heart image is improved.

[0073] refer to Figure 3 , Figure 3 FIG. 4 is a flow chart of a second embodiment of a method for three-dimensional reconstruction of cardiac images according to the present invention.

[0074] Based on the first embodiment, step S20 of the method for 3D reconstruction of cardiac images in this embodiment includes:

[0075] Step S201: traversing the shape contour points in the initial shape of the heart to obtain the traversed current shape contour points.

[0076] It should be noted that the initial heart shape may be composed of a large number of points, and the points that constitute the three-dimensional initial shape are shape contour points. Traversing the shape contour points in the initial heart shape is traversing the points that constitute the three-dimensional initial shape.

[0077] In actual use, in order to avoid repeatedly traversing the same shape contour point, a contour point set may be first constructed according to the shape contour points in the initial heart shape, and then the contour point set may be traversed.

[0078] Step S202: Calculate the relative distance between the current shape contour point and each of the three-dimensional contour points.

[0079] It should be noted that calculating the relative distance between the current shape contour point and each three-dimensional contour point may be calculating the relative distance between the coordinates of the current shape contour point and the coordinates of the three-dimensional contour point.

[0080] For example: Assuming the current shape contour point is P(x, y, z) and the three-dimensional contour point is Pi(xi, yi, zi), the relative distance can be expressed as:

[0081]

[0082] Where dx is the relative distance on the x-axis, dy is the relative distance on the y-axis, and dz is the relative distance on the z-axis.

[0083] Step S203: selecting a number of adjacent contour points from the three-dimensional contour points according to the relative distance.

[0084] It should be noted that selecting a number of adjacent contour points from the three-dimensional contour points according to the relative distance may be to calculate a relative distance value according to the relative distance, and taking the three-dimensional contour points whose relative distance values ​​are less than or equal to a preset distance threshold as adjacent contour points. The preset distance threshold may be pre-set by the manager of the cardiac image three-dimensional reconstruction device according to actual needs.

[0085] Furthermore, in the actual calculation process, the number of contour points whose relative distance is less than or equal to the preset distance threshold may be too large, and in the actual calculation, such a large number of adjacent contour points is not required. When the number of adjacent contour points is too large, the subsequent calculation speed may be too slow. In order to avoid this phenomenon, step S203 in this embodiment may include:

[0086] Constructing a set of adjacent contour points according to three-dimensional contour points whose relative distances to the current shape contour points are less than or equal to a preset distance threshold;

[0087] Sorting the three-dimensional contour points in the set of adjacent contour points according to the relative distance to obtain a sorting result;

[0088] A preset number of adjacent contour points are selected according to the sorting result.

[0089] It should be noted that the relative distance includes the relative distances of three different axes: the x-axis, the y-axis, and the z-axis. During the comparison process, the preset distance threshold can also be set by selecting one or more axes according to actual needs. For example, the preset distance threshold is set to only the z-axis, and the preset distance threshold is a. At this time, if dz≤a in the relative distance, it can be determined that the relative distance is less than or equal to the preset distance threshold.

[0090] In actual use, sorting the three-dimensional contour points in the adjacent contour point set according to the relative distance may be to calculate the Euclidean distance value according to the relative distance, and sorting the three-dimensional contour points in the adjacent contour point set from small to large according to the calculated Euclidean distance value, so as to obtain the sorting result. Selecting a preset number of adjacent contour points according to the sorting result may be to select a preset number of three-dimensional contour points in the sorting result as adjacent contour points. The preset number may be pre-set by the manager of the cardiac image three-dimensional reconstruction device according to actual needs.

[0091] It is understandable that if the number of 3D contour points in the adjacent contour point set is less than or equal to the preset number, then no sorting is required and all 3D contour points in the adjacent contour point set can be directly used as adjacent contour points.

[0092] Step S204: determining a transformed contour point according to the current shape contour point and the adjacent contour points.

[0093] It should be noted that determining the transformed contour point according to the current shape contour point and the adjacent contour points may be performing coordinate calculation according to the current shape contour point and the adjacent contour points, thereby obtaining the transformed contour point.

[0094] In a specific implementation, in order to reasonably determine the transformed contour points, step S204 in this embodiment may include:

[0095] Determine the coordinate weight corresponding to each adjacent contour point according to the current shape contour point and the adjacent contour points;

[0096] The coordinates of the adjacent contour points are weightedly summed based on the coordinate weights to obtain transformed contour points.

[0097] It should be noted that in actual coordinate calculation, the coordinates are composed of the coordinate values ​​of the x-axis, y-axis, and z-axis. Therefore, the coordinate weights can be calculated separately. If the current shape contour point is P(x, y, z), the adjacent contour points include P 1 (x 1 ,y 1 , z 1 )...P j (x j ,y j , z j )...P s (x s ,y s , z s ), a total of s, then the jth adjacent contour point P j The corresponding x-axis coordinate weight can be calculated by the x-axis weight formula, the y-axis coordinate weight can be calculated by the y-axis weight formula, and the z-axis coordinate weight can be calculated by the z-axis weight formula.

[0098] Among them, the x-axis weight formula is:

[0099]

[0100] The y-axis weight formula is:

[0101]

[0102] The formula for the z-axis weight is:

[0103]

[0104] In the formula, is the jth adjacent contour point P j The corresponding x-axis coordinate weight, is the jth adjacent contour point P j The corresponding y-axis coordinate weight, is the jth adjacent contour point P j The corresponding z-axis coordinate weight, ε is an infinitesimal quantity used to avoid the denominator being 0.

[0105] It can be understood that after the coordinate weights corresponding to each adjacent contour point are obtained, the coordinates of each adjacent contour point can be weightedly summed based on the coordinate weights to obtain the transformed contour point.

[0106] In actual use, the coordinate weighted sum of each adjacent contour point can be performed based on the coordinate weight through the coordinate weighted formula to obtain the transformed contour point, wherein the coordinate weighted formula can be:

[0107]

[0108] Where x' is the x-axis coordinate value of the transformed contour point, y' is the y-axis coordinate value of the transformed contour point, z' is the z-axis coordinate value of the transformed contour point, s is the total number of adjacent contour points, is the jth adjacent contour point P j The corresponding x-axis coordinate weight, is the jth adjacent contour point P j The corresponding y-axis coordinate weight, is the jth adjacent contour point P j The corresponding z-axis coordinate weight, x j is the x-axis coordinate value of the jth adjacent contour point, y j is the y-axis coordinate value of the jth adjacent contour point, z j is the z-axis coordinate value of the jth adjacent contour point.

[0109] Step S205: transforming the current shape contour points in the initial heart shape according to the transformed contour points.

[0110] It should be noted that transforming the current shape contour points in the initial heart shape according to the transformed contour points may be updating the coordinates of the current shape contour points in the initial heart shape to the coordinates of the transformed contour points.

[0111] Furthermore, in order to ensure that the transformed image of the initial shape of the heart is smooth, after step S205 in this embodiment, the following steps may be further included:

[0112] The shape contour points in the initial shape of the heart are filtered by a preset filtering algorithm to make the contour surface of the initial shape of the heart smooth.

[0113] It should be noted that the contour surface can be a surface composed of shape contour points. Since the transformation contour points are obtained by calculation, directly updating the current shape contour points in the initial shape of the heart according to the calculated transformation contour points may cause the surface composed of the contour points in the transformed initial shape of the heart to be not smooth. In order to avoid this situation, after the current shape contour points in the initial shape of the heart are transformed according to the transformation contour points, a preset filtering algorithm can be used to filter the shape contour points in the initial shape of the heart, so that the surface composed of the shape contour points in the initial shape of the heart is smooth. Among them, the preset filtering algorithm can be a Gaussian low-pass filtering algorithm, or other similar filtering algorithms, which is not limited in this embodiment.

[0114] Step S206: When the traversal is finished, the transformed initial shape of the heart is obtained according to the transformed shape contour points.

[0115] It can be understood that at the end of the traversal, all shape contour points in the initial shape of the heart have been traversed, that is, all shape contour points in the initial shape of the heart have been transformed, and the transformed initial shape of the heart can be determined based on all the transformed shape contour points.

[0116] In actual use, if the shape contour points in the initial shape of the heart are transformed only once, their contours are not very consistent with the heart contour in the short-axis heart image. In order to make the transformed initial shape of the heart fit the heart contour in the short-axis heart image as closely as possible, an iteration number threshold can be set in advance according to actual needs. At the end of the traversal, the number of transformations currently performed on the initial shape of the heart with a composite transformation is obtained. When the number of transformations is less than the iteration number threshold, the shape contour points after the current transformation can be used as the shape contour points in the initial shape of the heart that need to be further transformed. The process returns to the above step S201 to continue transforming the initial shape of the heart. When the number of transformations is greater than or equal to the iteration number threshold, the transformed initial shape of the heart is determined based on the transformed shape contour points.

[0117] This embodiment traverses the shape contour points in the initial shape of the heart; calculates the relative distance between the current shape contour point and each of the three-dimensional contour points; selects a number of adjacent contour points from the three-dimensional contour points according to the relative distance; determines the transformation contour points according to the current shape contour point and the adjacent contour points; transforms the current shape contour point in the initial shape of the heart according to the transformation contour points; and at the end of the traversal, obtains the transformed initial shape of the heart according to the transformed shape contour points. Since the shape contour points in the initial shape of the heart are traversed when transforming the initial shape of the heart, the shape contour points are traversed one by one during the traversal process, which effectively avoids the phenomenon of missing or repeated processing. When transforming the shape contour points, the adjacent contour points are selected by relative distance, which can avoid the influence of contour points with large errors on the transformation, making the transformation of the shape contour points more accurate.

[0118] In addition, an embodiment of the present invention further provides a storage medium on which a three-dimensional reconstruction program for cardiac images is stored. When the three-dimensional reconstruction program for cardiac images is executed by a processor, the steps of the three-dimensional reconstruction method for cardiac images described above are implemented.

[0119] Reference Figure 4 , Figure 4 FIG. 4 is a structural block diagram of a first embodiment of a device for 3D reconstruction of cardiac images according to the present invention.

[0120] like Figure 4 As shown, the cardiac image three-dimensional reconstruction device proposed in the embodiment of the present invention includes:

[0121] An image segmentation module 10 is used to obtain an initial heart shape corresponding to a short-axis heart image, and perform image segmentation on the short-axis heart image to obtain three-dimensional contour points;

[0122] A shape transformation module 20, configured to perform a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape;

[0123] The three-dimensional reconstruction module 30 is used to transform the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result.

[0124] This embodiment obtains the initial heart shape corresponding to the short-axis heart image and performs image segmentation on the short-axis heart image to obtain three-dimensional contour points; performs a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape; and transforms the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result. Because the initial heart shape is compositely transformed according to the three-dimensional contour points before three-dimensional modeling is performed, so that the initial heart shape is close to the heart contour in the short-axis heart image, and then the transformed initial heart shape is transformed into the heart image coordinate system for three-dimensional modeling, the accuracy of three-dimensional modeling of the heart image is improved.

[0125] Furthermore, the shape transformation module 20 is also used to traverse the shape contour points in the initial shape of the heart to obtain the traversed current shape contour points; calculate the relative distance between the current shape contour point and each of the three-dimensional contour points; select a number of adjacent contour points from the three-dimensional contour points according to the relative distance; determine the transformation contour point according to the current shape contour point and the adjacent contour point; transform the current shape contour point in the initial shape of the heart according to the transformation contour point; at the end of the traversal, obtain the transformed initial shape of the heart according to the transformed shape contour point.

[0126] Furthermore, the shape transformation module 20 is further used to determine the coordinate weight corresponding to each adjacent contour point according to the current shape contour point and the adjacent contour point; and perform weighted summation of the coordinates of the adjacent contour points based on the coordinate weight to obtain a transformed contour point.

[0127] Furthermore, the shape transformation module 20 is also used to construct a set of adjacent contour points based on three-dimensional contour points whose relative distance to the current shape contour point is less than or equal to a preset distance threshold; sort the three-dimensional contour points in the set of adjacent contour points according to the relative distance to obtain a sorting result; and select a preset number of adjacent contour points based on the sorting result.

[0128] Furthermore, the shape transformation module 20 is further configured to filter the shape contour points in the initial shape of the heart by using a preset filtering algorithm to make the contour surface of the initial shape of the heart smooth.

[0129] Furthermore, the image segmentation module 10 is also used to obtain the time phase corresponding to the short-axis cardiac image; when the time phase corresponding to the short-axis cardiac image is not the first time phase, obtain the three-dimensional reconstruction result corresponding to the previous time phase; and use the three-dimensional reconstruction result as the initial shape of the heart corresponding to the short-axis cardiac image.

[0130] Furthermore, the image segmentation module 10 is also used to search for a standard heart shape in a preset standard organ library when the time phase corresponding to the short-axis heart image is the first time phase; and determine the initial heart shape corresponding to the short-axis heart image according to the standard heart shape.

[0131] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0132] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0133] In addition, for technical details not fully described in this embodiment, reference may be made to the three-dimensional reconstruction method of cardiac images provided in any embodiment of the present invention, and will not be repeated here.

[0134] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0135] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0137] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for three-dimensional reconstruction of cardiac images, characterized in that: The method for three-dimensional reconstruction of cardiac images comprises the following steps: Acquiring an initial heart shape corresponding to a short-axis heart image, and performing image segmentation on the short-axis heart image to obtain three-dimensional contour points; Performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape; Transforming the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result; The step of performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain the transformed initial heart shape comprises: Traversing the shape contour points in the initial shape of the heart to obtain the traversed current shape contour points; Calculating the relative distance between the current shape contour point and each of the three-dimensional contour points; Selecting a number of adjacent contour points from the three-dimensional contour points according to the relative distance; Determine the coordinate weight corresponding to each adjacent contour point according to the current shape contour point and the adjacent contour points; Performing weighted summation of coordinates of the adjacent contour points based on the coordinate weights to obtain a transformed contour point; transforming the current shape contour points in the initial shape of the heart according to the transformed contour points; At the end of the traversal, the transformed initial heart shape is obtained according to the transformed shape contour points.

2. The method for three-dimensional reconstruction of cardiac images according to claim 1, characterized in that: The step of selecting a plurality of adjacent contour points from the three-dimensional contour points according to the relative distance comprises: Constructing a set of adjacent contour points according to three-dimensional contour points whose relative distances to the current shape contour points are less than or equal to a preset distance threshold; Sorting the three-dimensional contour points in the set of adjacent contour points according to the relative distance to obtain a sorting result; A preset number of adjacent contour points are selected according to the sorting result.

3. The method for three-dimensional reconstruction of cardiac images according to claim 1, characterized in that: After the step of transforming the current shape contour points in the initial heart shape according to the transformed contour points, the method further comprises: The shape contour points in the initial shape of the heart are filtered by a preset filtering algorithm to make the contour surface of the initial shape of the heart smooth.

4. The method for three-dimensional reconstruction of cardiac images according to claim 1, characterized in that: The step of obtaining the initial heart shape corresponding to the short-axis heart image comprises: Acquiring a time phase corresponding to the short-axis cardiac image; When the time phase corresponding to the short-axis cardiac image is not the first time phase, obtaining a three-dimensional reconstruction result corresponding to the previous time phase; The three-dimensional reconstruction result is used as the initial heart shape corresponding to the short-axis heart image.

5. The method for three-dimensional reconstruction of cardiac images according to claim 4, characterized in that: After the step of acquiring the time phase corresponding to the short-axis cardiac image, the method further includes: When the time phase corresponding to the short-axis heart image is the first time phase, searching for a standard heart shape in a preset standard organ library; An initial heart shape corresponding to the short-axis heart image is determined according to the standard heart shape.

6. A three-dimensional reconstruction device for cardiac images, characterized in that: The cardiac image three-dimensional reconstruction device comprises the following modules: An image segmentation module is used to obtain an initial heart shape corresponding to a short-axis heart image, and perform image segmentation on the short-axis heart image to obtain three-dimensional contour points; A shape transformation module, used for performing a composite transformation on the shape contour points in the initial heart shape according to the three-dimensional contour points to obtain a transformed initial heart shape; A three-dimensional reconstruction module, used for transforming the transformed initial heart shape into a heart image coordinate system established according to the short-axis heart image to obtain a three-dimensional reconstruction result; The shape transformation module is further used to traverse the shape contour points in the initial shape of the heart to obtain the traversed current shape contour points; Calculating the relative distance between the current shape contour point and each of the three-dimensional contour points; selecting a number of adjacent contour points from the three-dimensional contour points according to the relative distance; determining the coordinate weight corresponding to each adjacent contour point according to the current shape contour point and the adjacent contour points; performing weighted summation of the coordinates of the adjacent contour points based on the coordinate weights to obtain a transformed contour point; The current shape contour points in the initial heart shape are transformed according to the transformed contour points; and at the end of the traversal, a transformed initial heart shape is obtained according to the transformed shape contour points.

7. A cardiac image three-dimensional reconstruction device, characterized in that: The three-dimensional reconstruction device of cardiac images includes: a processor, a memory, and a three-dimensional reconstruction program of cardiac images stored in the memory and executable on the processor. When the three-dimensional reconstruction program of cardiac images is executed by the processor, the steps of the three-dimensional reconstruction method of cardiac images as described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a three-dimensional cardiac image reconstruction program, which, when executed, implements the steps of the three-dimensional cardiac image reconstruction method according to any one of claims 1 to 5.

Images