Method, apparatus, device and medium for evaluating heart function

Abstract

An embodiment of the present invention provides a method, device, equipment and medium for evaluating cardiac function, which relates to the technical field of image processing. The method includes: obtaining multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and annotating the three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors for each two-dimensional intracardiac ultrasound image; segmenting the cardiac anatomical structures in each two-dimensional intracardiac ultrasound image according to the annotated three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors; correcting the sizes of the corresponding cardiac tissue structures in the three-dimensional cardiac model according to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images to obtain a corrected three-dimensional cardiac model; evaluating the function of the heart to be evaluated according to the relevant data of the corrected three-dimensional cardiac model. This solution can obtain a three-dimensional cardiac model with high precision by means of image annotation and model correction, and can accurately and conveniently obtain the three-dimensional cardiac model of the heart to be evaluated while reducing costs.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a method, device, equipment and medium for evaluating cardiac function. Background Art

[0002] Cardiovascular diseases are one of the major health threats globally. Early diagnosis and precise treatment are crucial for improving the prognosis of patients. Traditional clinical assessment methods for the heart include electrocardiogram, echocardiogram, and MRI, etc. Although these methods provide rich information, they still have limitations in comprehensively showing the complex three-dimensional structure and dynamic function of the heart. To solve these problems, the application of three-dimensional cardiac models has emerged. It constructs detailed three-dimensional cardiac structure and function models by integrating multiple data sources, providing a new perspective for clinical assessment.

[0003] Currently, the main methods for three-dimensional reconstruction of the human heart include computed tomography (CT), magnetic resonance imaging (MRI), intravascular (extravascular) ultrasound based on magnetic localization, etc. Although the accuracy of three-dimensional modeling of these methods meets the needs of evaluating the cardiac model, they require the use of expensive three-dimensional modeling equipment, resulting in high costs. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method for evaluating cardiac function to solve the technical problem in the prior art that the cardiac function evaluation scheme requires the use of expensive three-dimensional reconstruction equipment, resulting in high costs. The method includes:

[0005] Obtain multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and label the three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors for each of the two-dimensional intracardiac ultrasound images;

[0006] According to the labeled three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors, segment the cardiac anatomical structures in each of the two-dimensional intracardiac ultrasound images;

[0007] According to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images, correct the sizes of the corresponding cardiac tissue structures in the three-dimensional cardiac model to obtain a corrected three-dimensional cardiac model;

[0008] Evaluate the function of the heart to be evaluated according to the relevant data of the corrected three-dimensional cardiac model.

[0009] Embodiments of the present invention also provide a device for evaluating cardiac function to solve the technical problem in the prior art that the cardiac function evaluation scheme requires the use of expensive three-dimensional reconstruction equipment, resulting in high costs. The device includes:

[0010] A labeling module, configured to obtain multiple two-dimensional intracardiac ultrasound images of a heart to be evaluated, and label the three-dimensional spatial positions of two-dimensional intracardiac ultrasound sectors for each of the two-dimensional intracardiac ultrasound images;

[0011] An image processing module, configured to segment cardiac anatomical structures in each of the two-dimensional intracardiac ultrasound images according to the three-dimensional spatial positions of the labeled two-dimensional intracardiac ultrasound sectors;

[0012] A model correction module, configured to correct the structural dimensions of a three-dimensional cardiac model according to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images, to obtain a corrected three-dimensional cardiac model;

[0013] An evaluation module, configured to evaluate the function of the heart to be evaluated according to relevant data of the corrected three-dimensional cardiac model.

[0014] An embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned arbitrary method for evaluating cardiac function is implemented, so as to solve the technical problem in the prior art that the cardiac function evaluation scheme needs to use expensive three-dimensional reconstruction equipment, resulting in high costs.

[0015] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program for executing the above-mentioned arbitrary method for evaluating cardiac function, so as to solve the technical problem in the prior art that the cardiac function evaluation scheme needs to use expensive three-dimensional reconstruction equipment, resulting in high costs.

[0016] Compared with the prior art, the at least one technical solution adopted in the embodiments of the present specification can achieve at least the following beneficial effects: It is proposed to label the three-dimensional spatial positions of two-dimensional intracardiac ultrasound sectors for two-dimensional intracardiac ultrasound images, and then, based on the three-dimensional spatial positions of the labeled two-dimensional intracardiac ultrasound sectors, segment cardiac anatomical structures in each of the two-dimensional intracardiac ultrasound images, and correct the dimensions of the corresponding cardiac structures in the three-dimensional cardiac model according to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images, to obtain a corrected three-dimensional cardiac model, so as to obtain a three-dimensional cardiac model with the same tissue structure and size as the heart to be evaluated. Based on the relevant data of the corrected three-dimensional cardiac model, the cardiac function can be evaluated conveniently and accurately. By means of image labeling and model correction, a high-precision three-dimensional cardiac model with the same (or matching) tissue structure and size as the heart to be evaluated is obtained, avoiding the use of expensive three-dimensional reconstruction equipment such as computed tomography (CT), magnetic resonance imaging (MRI), and intracardiac (external) ultrasound based on magnetic positioning, so that while accurately and conveniently obtaining the three-dimensional cardiac model of the heart to be evaluated, the cost can also be reduced. Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0018] Figure 1 is a flowchart of a method for evaluating cardiac function provided by an embodiment of the present invention;

[0019] Figure 2 is a schematic flowchart of a method for implementing the evaluation of cardiac function provided by an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of a 3D-like Octree space of a cardiac model provided by an embodiment of the present invention;

[0021] Figure 4 is a schematic diagram of a fan-shaped range in a 3D-like Octree space provided by an embodiment of the present invention;

[0022] Figure 5 is a schematic diagram of the matching between an intracardiac ultrasound two-dimensional image and a template contour provided by an embodiment of the present invention;

[0023] Figure 6 is a schematic diagram of the segmentation of cardiac anatomical structures provided by an embodiment of the present invention;

[0024] Figure 7 is a schematic flowchart of the evaluation of cardiac function during systole and diastole provided by an embodiment of the present invention;

[0025] Figure 8 is a structural block diagram of a computer device provided by an embodiment of the present invention;

[0026] Figure 9 is a structural block diagram of an apparatus for evaluating cardiac function provided by an embodiment of the present invention. Detailed implementation manners

[0027] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0028] The following specific examples illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope protected by the present application.

[0029] In an embodiment of the present invention, a method for evaluating cardiac function is provided. As Figure 1 shown, the method includes:

[0030] Step S101: Obtain multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and label the three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors for each of the two-dimensional intracardiac ultrasound images;

[0031] Step S102: Segment the cardiac anatomical structures in each of the two-dimensional intracardiac ultrasound images according to the labeled three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors;

[0032] Step S103: Modify the sizes of the corresponding cardiac tissue structures in the three-dimensional cardiac model according to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images to obtain a modified three-dimensional cardiac model;

[0033] Step S104: Evaluate the function of the heart to be evaluated according to the relevant data of the modified three-dimensional cardiac model.

[0034] By Figure 1As can be seen from the flow shown, in the embodiment of the present invention, a three-dimensional spatial position of a two-dimensional intracardiac ultrasound fan surface is marked for a two-dimensional intracardiac ultrasound image. Then, based on the three-dimensional spatial position of the marked two-dimensional intracardiac ultrasound fan surface, a cardiac anatomical structure is segmented from each of the two-dimensional intracardiac ultrasound images, and according to the cardiac anatomical structures corresponding to multiple two-dimensional intracardiac ultrasound images, the sizes of the corresponding cardiac structures in the three-dimensional cardiac model are corrected to obtain a corrected three-dimensional cardiac model, so as to obtain a three-dimensional cardiac model with the same (or matching) tissue structure and size as the heart to be evaluated. Based on the relevant data of the corrected three-dimensional cardiac model, the cardiac function can be evaluated conveniently and accurately. By means of image annotation and model correction, a high-precision three-dimensional cardiac model with the same tissue structure and size as the heart to be evaluated is obtained, avoiding the use of expensive three-dimensional reconstruction devices such as computed tomography (CT), magnetic resonance imaging (MRI), and intracardiac (external) ultrasound based on magnetic positioning, so that while accurately and conveniently obtaining the three-dimensional cardiac model of the heart to be evaluated, the cost can also be reduced.

[0035] During specific implementation, as Figure 2 shown, it is necessary to obtain multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and this process can read multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated from an ultrasound device.

[0036] During specific implementation, the process of marking the three-dimensional spatial position of the two-dimensional intracardiac ultrasound fan surface for each of the two-dimensional intracardiac ultrasound images can be implemented by any means capable of marking. In order to improve the marking accuracy, a specific method based on the same three-dimensional cardiac model for marking is also proposed. For example, determining a three-dimensional cardiac model adapted to the cardiac-related information of the heart to be evaluated; constructing a three-dimensional space for the determined three-dimensional cardiac model; processing each of the two-dimensional intracardiac ultrasound images to obtain a contour image of the cardiac tissue; determining a preset fan surface in the three-dimensional space, converting the three-dimensional data of the preset fan surface into two-dimensional data and then matching it with the contour image to obtain a matching region, where the preset fan surface includes the cardiac tissue structure in the contour image; and calibrating the position of the two-dimensional intracardiac ultrasound fan surface in the three-dimensional space in the intracardiac ultrasound two-dimensional image according to the relevant position of the fan surface of the matching region in the three-dimensional space.

[0037] During specific implementation, the above cardiac-related information can be any information related to the cardiac tissue structure, for example, information such as the size and shape of the heart. Specifically, the process of determining a cardiac model adapted to the cardiac-related information can be a process of matching and selecting an existing 3D cardiac model in a database through the cardiac-related information.

[0038] In specific implementation, the process of processing each intracardiac ultrasound two-dimensional image to obtain the contour image of the heart tissue can be implemented by any method that can obtain a 2D contour image. It is necessary to fully annotate the entire image, that is, to distinguish the myocardial tissue and chambers on all ultrasound sectors and display the information of the two-dimensional ultrasound heart tissue contour. For example, the traditional threshold segmentation algorithm can be used to process this image.

[0039] In specific implementation, after obtaining the 2D contour image of the intracardiac ultrasound two-dimensional image, in order to ensure the accuracy of the positioning and calibration results, it is proposed that before matching the 2D contour image with the data in the three-dimensional space, the 2D contour image can also be corrected to ensure the accuracy of the 2D contour image. For example, before matching the converted two-dimensional data of the preset sector with the contour image after converting the three-dimensional data of the preset sector into two-dimensional data, the contour line in the contour image is converted into a polygon, and the vertices in the polygon are corrected to correct the contour image.

[0040] Specifically, it can be judged whether the 2D contour image is correct manually or by relevant software algorithms. If not, the 2D contour image can be corrected. During the correction process, correction operations such as deleting and modifying the vertices in the polygon can be performed to achieve the purpose of correcting and modifying the contour image.

[0041] In specific implementation, after determining the three-dimensional heart model, in order to accurately and conveniently obtain the position of the contour image in the 3D heart structure, it is proposed to construct a 3D-like Octree space of the heart model, as Figure 3 shown, and then match the relevant sectors of the 3D-like Octree space of the heart model with the contour image to locate and calibrate the position of the contour image in the 3D-like Octree space of the heart model. Specifically, in the process of constructing the 3D-like Octree space of the heart model, the 3D-like Octree space can be directly constructed based on the heart model without distinguishing the depth. However, in order to improve the accuracy of matching, positioning and calibration, it is proposed to construct 3D-like Octree spaces with different depths for the determined heart model, where the organizational structures at different levels of the heart model in the 3D-like Octree space have different depth values.

[0042] Specifically, the principle process of constructing 3D-like Octree spaces with different depths is to supplement the positions of other non-model voxels on the basis of the 3D structure constructed by the heart model voxels, and the organizational structures at different depths correspond to different depth values, so that the positions of the catheter and the sector can be more finely and accurately matched and located based on different depth values.

[0043] Specifically, during the process of constructing 3D Octree-like spaces with different depths, the magnitude and quantity of the depth values can be specifically determined according to factors such as the tissue structure characteristics, size of the heart model, and the accuracy requirements of positioning and calibration. For example, the deeper the position of the tissue structure in the heart model, the larger the corresponding depth value; the more depth values, the finer the 3D space of the tissue structure is divided and constructed, thereby making the matching and positioning calibration positions finer and more accurate.

[0044] During specific implementation, in order to improve the efficiency and accuracy of the matching process, it is proposed to first determine a preset fan-shaped surface in the 3D Octree-like space, as Figure 4 shown. This preset fan-shaped surface includes the heart tissue structure in the contour image, that is, first determine the approximate target matching fan-shaped surface, and then perform fine matching between the data of the preset fan-shaped surface and the contour image in a targeted manner to reduce the computational amount of matching, improve the matching speed, and improve the matching accuracy.

[0045] During specific implementation, in order to further improve the accuracy of positioning and calibration, it is proposed to determine multiple said preset fan-shaped surfaces. Each said preset fan-shaped surface is used as a template contour. After converting the three-dimensional data of each said template contour into two-dimensional data, in the progressive order of depth information, the two-dimensional data of each said template contour is matched with the contour image, and the template contour with the highest matching degree is determined as the matching area. For example, as Figure 5 shown, based on the relevant heart tissue structure in the intracardiac ultrasound two-dimensional image in Figure (a), a fan-shaped area including the corresponding heart tissue structure can be preliminarily and approximately determined in the 3D Octree-like space of the heart model, such as Figure 5 the dark fan-shaped area shown in Figure (b) below. The position of the catheter corresponds to the central angle of the fan-shaped area. Such a fan-shaped area can be used as a template contour to perform fine matching with the contour image, and the template contour with the highest matching degree (such as similarity, etc.) is determined among multiple template contours.

[0046] During specific implementation, in order to improve the accuracy of positioning and marking, after converting the three-dimensional data of each said template contour into two-dimensional data, the process of matching the two-dimensional data of each said template contour with the contour image in the progressive order of depth information, that is, in the progressive order of depth information, the two-dimensional data with the same depth value is sequentially matched with the contour image. For example, the depth values of the 3D Octree-like space of the heart model include 1, 2, 3, etc. The deeper the tissue structure, the larger the corresponding depth value. Then, the two-dimensional data with a depth value of 1 is first matched with the contour image, then the two-dimensional data with a depth value of 2 is matched with the contour image, and then the two-dimensional data with a depth value of 3 is matched with the contour image, and so on.

[0047] In the specific implementation, in the process of positioning and calibrating the two-dimensional intracardiac ultrasound sector by matching the contour image with the data in the 3D Octree-like space of the heart model, the vertex position of the sector in the matching region in the three-dimensional space (such as the 3D Octree-like space) is calibrated as the position of the sector corresponding to the two-dimensional intracardiac ultrasound image in the three-dimensional space, and the center position of the sector in the matching region in the three-dimensional space is calibrated as the position of the two-dimensional ultrasound catheter in the three-dimensional space.

[0048] In the specific implementation, after obtaining the positioning and calibration results, the positioning and calibration results can also be corrected. For example, Figure 2 as shown, if it is determined that the three-point positions (the center of the sector, the points on the arc of the two radius sides) in the positioning and calibration results are inaccurate, the process of re-matching, positioning, and marking can also be performed by moving the position of the catheter to slightly fine-tune these three points to the ideal positions.

[0049] In the specific implementation, when the number of two-dimensional intracardiac ultrasound images with three-dimensional space positions marked reaches a certain quantity (for example, usually the number of marked images of a heart is not less than 30), the dimensions of the corresponding heart tissue structures in the three-dimensional heart model can be corrected according to the heart anatomical structures corresponding to multiple two-dimensional intracardiac ultrasound images, and the corrected three-dimensional heart model can be obtained to obtain a three-dimensional heart model that matches the structure and dimensions of the heart to be evaluated. For example,

[0050] each heart anatomical structure in the two-dimensional intracardiac ultrasound image with the marked space position can be segmented by a pre-trained semantic segmentation model, as Figure 6 ( Figure 6 Figure (a) in Figure 6 is the two-dimensional intracardiac ultrasound image with the marked space position,

[0051] In specific implementation, in order to further improve the accuracy of the corrected three-dimensional cardiac model, a model region in the three-dimensional cardiac model that does not match the cardiac anatomical structure corresponding to all the two-dimensional intracardiac ultrasound images is proposed. According to the cardiac anatomical structure matched by the adjacent region of the model region, bilinear interpolation is performed on the model region to obtain the corrected three-dimensional cardiac model.

[0052] In specific implementation, after obtaining the corrected three-dimensional cardiac model, the function of the heart to be evaluated can be evaluated based on the obtained corrected three-dimensional cardiac model. For example, calculate the relevant parameters of cardiac function in the corrected three-dimensional cardiac model, and evaluate the function of the heart to be evaluated according to the relevant parameters of cardiac function; evaluate the valve function of the heart to be evaluated according to the valve structure in the corrected three-dimensional cardiac model.

[0053] Specifically, relevant parameter indicators of cardiac function such as the long-axis length, short-axis length, ejection fraction, mass index, volume, and stress of the left and right atria and ventricles can be identified and calculated in the corrected three-dimensional cardiac model through algorithms and models, and the function of the heart can be further evaluated through the obtained index values. It is also possible to identify and check the valve structure conditions such as whether there are defects in the mitral valve, tricuspid valve, atrial septum, and ventricular septum in the corrected three-dimensional cardiac model through algorithms and models, and then evaluate the valve function of the heart.

[0054] In specific implementation, in order to facilitate viewing and application of the above evaluation results of cardiac function, the evaluation results can be generated in the form of a report to provide a data basis for intelligent assisted diagnosis in clinical practice; the evaluation results can also be used as the input of a neural network (i.e., sample data), and the real clinical diagnosis can be used as the output (i.e., the label of the sample data), and these data are trained to obtain a more accurate evaluation result of cardiac function.

[0055] In specific implementation, taking the evaluation of the cardiac function in the systolic and diastolic phases as an example, the above method for evaluating cardiac function is introduced, such as Figure 7As shown, first, several frames of images in the systolic phase and several frames of images in the diastolic phase are respectively selected from the ultrasound images (for example, images including the left atrial structure, images including the right atrial structure, images including the left ventricular structure, images including the right ventricular structure). Through a three-dimensional annotation process, the several frames of images in the systolic phase and the several frames of images in the diastolic phase are annotated in three-dimensional space, and the anatomical structures of the atria and ventricles of the heart are segmented in the images according to the annotation results. Furthermore, based on the sizes of the anatomical structures of the atria and ventricles, the sizes of the atria and ventricles in the existing three-dimensional heart model are corrected, so as to create atrial and ventricular models in the systolic phase and the diastolic phase respectively (by correcting the existing three-dimensional heart model according to the cardiac ultrasound images in different stages or periods, a three-dimensional heart model matching the heart in different stages or periods can be obtained, enabling the functional evaluation of the heart in different stages or periods). Index data such as systolic volume, systolic surface area, and the perimeter of a specific section are measured in the atrial or ventricular systolic phase model, and index data such as diastolic volume, diastolic surface area, and the perimeter of a specific section are measured in the atrial or ventricular diastolic phase model. Furthermore, functional indexes such as ejection fraction, stress, volume index, and mass index of the atria or ventricles can be calculated based on the measured index data. Finally, the functions of each chamber in the heart can be evaluated through the functional indexes.

[0056] In this embodiment, a computer device is provided, as Figure 8 shown, including a memory 801, a processor 802, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned arbitrary method for evaluating cardiac function is implemented.

[0057] Specifically, the computer device may be a computer terminal, a server, or a similar computing device.

[0058] In this embodiment, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program for executing the above-mentioned arbitrary method for evaluating cardiac function.

[0059] Specifically, a computer-readable storage medium includes permanent and non-permanent, removable and non-removable media that can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device. As defined herein, a computer-readable storage medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0060] Based on the same inventive concept, an embodiment of the present invention also provides an apparatus for evaluating cardiac function, as described in the following embodiments. Since the principle of solving problems by the apparatus for evaluating cardiac function is similar to that of the method for evaluating cardiac function, the implementation of the apparatus for evaluating cardiac function can refer to the implementation of the method for evaluating cardiac function, and the repeated parts will not be described again. As used hereinafter, the term "unit" or "module" can be a combination of software and / or hardware that can implement a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0061] Figure 9 is a structural block diagram of the apparatus for evaluating cardiac function according to an embodiment of the present invention, as Figure 9 shown, the apparatus includes:

[0062] A labeling module 901, configured to obtain multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and label the three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors for each of the two-dimensional intracardiac ultrasound images;

[0063] An image processing module 902, configured to segment cardiac anatomical structures in each of the two-dimensional intracardiac ultrasound images according to the labeled three-dimensional spatial positions of the two-dimensional intracardiac ultrasound sectors;

[0064] A model correction module 903, configured to correct the structural dimensions of a three-dimensional cardiac model according to the cardiac anatomical structures corresponding to the multiple two-dimensional intracardiac ultrasound images to obtain a corrected three-dimensional cardiac model;

[0065] An evaluation module 904, configured to evaluate the function of the heart to be evaluated according to the relevant data of the corrected three-dimensional heart model.

[0066] In one embodiment, a labeling module is configured to determine a three-dimensional heart model adapted to the heart-related information of the heart to be evaluated; construct a three-dimensional space for the determined three-dimensional heart model; process each of the two-dimensional intracardiac ultrasound images to obtain a contour image of the heart tissue; determine a preset fan surface in the three-dimensional space, convert the three-dimensional data of the preset fan surface into two-dimensional data and match it with the contour image to obtain a matching region, where the preset fan surface includes the heart tissue structure in the contour image; calibrate the position of the two-dimensional intracardiac ultrasound fan surface in the three-dimensional space according to the relevant position of the fan surface of the matching region in the three-dimensional space.

[0067] In one embodiment, a labeling module is configured to construct 3D-like Octree spaces with different depths for the determined three-dimensional heart model, where different levels of tissue structures of the heart model in the 3D-like Octree space have different depth values.

[0068] In one embodiment, a labeling module is configured to determine a plurality of the preset fan surfaces, take each of the preset fan surfaces as a template contour, after converting the three-dimensional data of each template contour into two-dimensional data, match the two-dimensional data of each template contour with the contour image in the progressive order of depth information, and determine the template contour with the highest matching degree as the matching region.

[0069] In one embodiment, a model correction module is configured to sequentially adjust the sizes of the heart tissue structures in the three-dimensional heart model that match the heart anatomical structures corresponding to each of the two-dimensional intracardiac ultrasound images by means of non-rigid registration according to the sizes of the heart anatomical structures corresponding to each of the two-dimensional intracardiac ultrasound images, to obtain the corrected three-dimensional heart model, where the subsequent correction is performed based on the result of the three-dimensional heart model corrected in the previous correction.

[0070] In one embodiment, the model correction module is further configured to perform bilinear interpolation on the model region in the three-dimensional heart model that does not match the heart anatomical structures corresponding to all the two-dimensional intracardiac ultrasound images according to the heart anatomical structures matched by the adjacent regions of the model region, to obtain the corrected three-dimensional heart model.

[0071] In one embodiment, an evaluation module is configured to calculate relevant parameters of cardiac function in the corrected three-dimensional cardiac model, evaluate the function of the heart to be evaluated according to the relevant parameters of cardiac function; and evaluate the valve function of the heart to be evaluated according to the valve structure in the corrected three-dimensional cardiac model.

[0072] The embodiments of the present invention achieve the following technical effects: It is proposed to annotate the three-dimensional spatial position of the two-dimensional intracardiac ultrasound fan surface in the two-dimensional intracardiac ultrasound image, and then based on the three-dimensional spatial position of the annotated two-dimensional intracardiac ultrasound fan surface, the cardiac anatomical structure is segmented in each of the two-dimensional intracardiac ultrasound images, and according to the cardiac anatomical structures corresponding to multiple two-dimensional intracardiac ultrasound images, the size of the corresponding cardiac structure in the three-dimensional cardiac model is corrected to obtain a corrected three-dimensional cardiac model, so as to obtain a three-dimensional cardiac model with the same tissue structure and size as the heart to be evaluated. Based on the relevant data of the corrected three-dimensional cardiac model, the cardiac function can be evaluated conveniently and accurately. By means of image annotation and model correction, a high-precision three-dimensional cardiac model with the same (or matching) tissue structure and size as the heart to be evaluated is obtained, avoiding the use of expensive three-dimensional reconstruction devices such as computed tomography (CT), magnetic resonance imaging (MRI), and magnetic positioning-based intracardiac (extracardiac) ultrasound, so that while accurately and conveniently obtaining the three-dimensional cardiac model of the heart to be evaluated, the cost can also be reduced.

[0073] Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the embodiments of the present invention can be implemented by a general-purpose computing device. They can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Optionally, they can be implemented by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device. And in some cases, the steps shown or described can be executed in a different order from here, or they can be separately made into individual integrated circuit modules, or multiple modules or steps among them can be made into a single integrated circuit module to implement. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0074] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, various changes and modifications can be made to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for evaluating cardiac function, characterized in that: include: Acquire multiple two-dimensional intracardiac ultrasound images of the heart to be evaluated, and mark the three-dimensional spatial position of the two-dimensional intracardiac ultrasound sector on each of the two-dimensional intracardiac ultrasound images; Segmenting the cardiac anatomical structure in each of the two-dimensional intracardiac ultrasound images according to the three-dimensional spatial position of the marked two-dimensional intracardiac ultrasound sectors; According to the cardiac anatomical structures corresponding to the plurality of two-dimensional intracardiac ultrasound images, correcting the size of the corresponding cardiac tissue structure in the three-dimensional cardiac model to obtain a corrected three-dimensional cardiac model; evaluating the function of the heart to be evaluated according to the relevant data of the modified three-dimensional heart model; Using the same three-dimensional heart model to mark the three-dimensional spatial position of the two-dimensional intracardiac ultrasound sector on each of the two-dimensional intracardiac ultrasound images includes: Determine a three-dimensional heart model that matches the heart-related information of the heart to be evaluated; constructing a three-dimensional space for the determined three-dimensional heart model; Processing each of the two-dimensional intracardiac ultrasound images to obtain a contour image of the heart tissue; Determine a preset sector in the three-dimensional space, convert the three-dimensional data of the preset sector into two-dimensional data, and then match it with the contour image to obtain a matching area, wherein the preset sector includes the cardiac tissue structure in the contour image; Calibrate the position of the two-dimensional intracardiac ultrasound sector in the two-dimensional intracardiac ultrasound image in the three-dimensional space according to the relative position of the sector of the matching area in the three-dimensional space; According to the cardiac anatomical structures corresponding to the plurality of two-dimensional intracardiac ultrasound images, the size of the corresponding cardiac tissue structure in the three-dimensional cardiac model is corrected to obtain a corrected three-dimensional cardiac model, including: According to the size of the cardiac anatomical structure corresponding to each of the two-dimensional intracardiac ultrasound images, the sizes of the cardiac tissue structures in the three-dimensional heart model that match the cardiac anatomical structure corresponding to each of the two-dimensional intracardiac ultrasound images are adjusted in sequence through a non-rigid registration method to obtain the corrected three-dimensional heart model, wherein the latter correction is performed on the basis of the result of the previous corrected three-dimensional heart model.

2. The cardiac function evaluation method according to claim 1, characterized in that: Constructing a three-dimensional space for the determined three-dimensional heart model, including: A 3D Octree-like space of different depths is constructed for the determined three-dimensional heart model, wherein different levels of tissue structures of the heart model in the 3D Octree-like space have different depth values.

3. The cardiac function evaluation method according to claim 2, characterized in that: Converting the three-dimensional data of the preset sector into two-dimensional data and matching it with the contour image comprises: Determine a plurality of preset sectors, take each of the preset sectors as a template contour, convert the three-dimensional data of each template contour into two-dimensional data, match the two-dimensional data of each template contour with the contour image in a progressive order of depth information, and determine the template contour with the highest matching degree as the matching area.

4. The method for evaluating cardiac function according to claim 1, wherein: Also includes: For a model area in the three-dimensional heart model that does not match the cardiac anatomical structure corresponding to all the two-dimensional intracardiac ultrasound images, bilinear interpolation is performed on the model area based on the cardiac anatomical structure matched by adjacent areas of the model area to obtain the corrected three-dimensional heart model.

5. The method for evaluating cardiac function according to any one of claims 1 to 3, characterized in that: Evaluating the function of the heart to be evaluated according to the relevant data of the modified three-dimensional heart model, including: Calculating relevant parameters of cardiac function in the modified three-dimensional cardiac model, and evaluating the functional condition of the heart to be evaluated according to the relevant parameters of cardiac function; The valve function of the heart to be evaluated is evaluated according to the valve structure in the corrected three-dimensional heart model.

6. A cardiac function assessment device, characterized in that: include: a labeling module, used for acquiring a plurality of two-dimensional intracardiac ultrasound images of the heart to be evaluated, and labeling the three-dimensional spatial position of the two-dimensional intracardiac ultrasound sector on each of the two-dimensional intracardiac ultrasound images; An image processing module, configured to segment the cardiac anatomical structure in each of the two-dimensional intracardiac ultrasound images according to the three-dimensional spatial position of the annotated two-dimensional intracardiac ultrasound sectors; A model correction module, used to correct the structural dimensions of the three-dimensional heart model according to the cardiac anatomical structures corresponding to the plurality of two-dimensional intracardiac ultrasound images, so as to obtain a corrected three-dimensional heart model; An evaluation module, used for evaluating the function of the heart to be evaluated based on the relevant data of the modified three-dimensional heart model; The annotation module is used to determine a three-dimensional heart model that matches the heart-related information of the heart to be evaluated; and construct a three-dimensional space for the determined three-dimensional heart model; Processing each of the two-dimensional intracardiac ultrasound images to obtain a contour image of cardiac tissue; determining a preset sector in the three-dimensional space, converting the three-dimensional data of the preset sector into two-dimensional data and matching it with the contour image to obtain a matching area, wherein the preset sector includes the cardiac tissue structure in the contour image; calibrating the position of the two-dimensional intracardiac ultrasound sector in the two-dimensional intracardiac ultrasound image in the three-dimensional space according to the relative position of the sector in the matching area in the three-dimensional space; The model correction module is used to adjust the sizes of the cardiac tissue structures in the three-dimensional heart model that match the cardiac anatomical structures corresponding to each of the two-dimensional intracardiac ultrasound images in a non-rigid registration manner, respectively according to the sizes of the cardiac anatomical structures corresponding to each of the two-dimensional intracardiac ultrasound images, to obtain the corrected three-dimensional heart model, wherein the latter correction is performed on the basis of the results of the three-dimensional heart model corrected in the previous correction.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the cardiac function evaluation method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the cardiac function evaluation method according to any one of claims 1 to 5.

Images