Heart image processing method, device and equipment

Abstract

The invention relates to a heart image processing method, device and equipment. The method comprises the steps that a first image used for calculating a myocardial scar and / or a gray area and a second image used for calculating a coronary artery tree are acquired; extracting three-dimensional image features of a myocardial scar area and / or a gray area in the first image; generating a heart three-dimensional model based on the plurality of first images, and generating a coronary artery tree three-dimensional model based on the plurality of second images; and performing visual display on the heart three-dimensional model and the coronary artery tree three-dimensional model. According to the method, the fibrous scar and the grey area in the cardiac muscle can be evaluated more comprehensively and accurately, and the accuracy of judging the lesion position is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of image processing technologies, and particularly to a method, apparatus, and device for processing cardiac images. Background Art

[0002] Cardiovascular Magnetic Resonance (CMR) is a non-invasive imaging evaluation method for assessing myocardial infarction. Currently, mainly Late Gadolinium Enhancement-Cardiovascular Magnetic Resonance (LGE-CMR) is used to perform two-dimensional image analysis on myocardial scars and gray zones; or, based on quality, texture features, and microstructural features, etc., to describe the heterogeneity of gray zones and predict cardiac adverse events in patients with different cardiovascular diseases. However, the above-mentioned cardiac MR processing and analysis technologies are mainly based on two-dimensional images. Due to the complexity of the cardiac structure and the diversity of myocardial lesions, two-dimensional images often cannot provide sufficient information to accurately judge the location and extent of lesions, resulting in the inability to comprehensively and accurately evaluate fibrotic scars and gray zones in the myocardium. Summary of the Invention

[0003] To solve the above technical problems, the present disclosure provides a method, apparatus, and device for processing cardiac images.

[0004] According to one aspect of the present disclosure, there is provided a method for processing cardiac images, the method comprising:

[0005] Obtaining a first image for calculating myocardial scars and / or gray zones and a second image for calculating a coronary artery tree;

[0006] Extracting three-dimensional image features of the myocardial scar region and / or gray zone in the first image;

[0007] Generating a three-dimensional cardiac model based on multiple first images and generating a three-dimensional coronary artery tree model based on multiple second images;

[0008] Performing visual display on the three-dimensional cardiac model and the three-dimensional coronary artery tree model.

[0009] According to another aspect of the present disclosure, there is further provided a device for processing cardiac images, the device comprising:

[0010] An image acquisition module, configured to obtain a first image for calculating myocardial scars and / or gray zones and a second image for calculating a coronary artery tree;

[0011] A feature extraction module, configured to extract three-dimensional image features of the myocardial scar region and / or gray zone in the first image;

[0012] A three-dimensional reconstruction module, configured to generate a three-dimensional model of the heart based on multiple pieces of the first images and generate a three-dimensional model of the coronary artery tree based on multiple pieces of the second images;

[0013] A visualization module, configured to visually display the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree.

[0014] According to another aspect of the present disclosure, there is also provided an electronic device, which includes:

[0015] A processor;

[0016] A memory for storing executable instructions executable by the processor;

[0017] The processor is configured to read the executable instructions from the memory and execute the instructions to implement the above method.

[0018] According to another aspect of the present disclosure, there is also provided a computer-readable storage medium, which stores a computer program for executing the above method.

[0019] The technical solution provided by the embodiments of the present disclosure has the following advantages compared with the prior art:

[0020] The technical solution provided by the embodiments of the present disclosure includes: obtaining a first image for calculating myocardial scar and / or gray zone and a second image for calculating the coronary artery tree; extracting three-dimensional image features of the myocardial scar region and / or gray region in the first image; generating a three-dimensional model of the heart based on multiple first images and generating a three-dimensional model of the coronary artery tree based on multiple second images; visually displaying the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree.

[0021] This technical solution extracts three-dimensional image features of the myocardial scar region and / or gray region in the first image. Using these three-dimensional image features can more comprehensively evaluate the fibrous scar and gray zone in the myocardium, and more accurately perform lesion localization, severity assessment, and adverse event prediction. Through three-dimensional reconstruction and visually displaying the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree, it can provide three-dimensional spatial distribution information such as the overall blood supply and fibrosis of the heart, improve the accuracy of lesion localization and the effectiveness of treatment planning, and provide a new method for the diagnosis and treatment of complex cardiovascular diseases. In short, through extracting three-dimensional image features and visually displaying the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree, the present disclosure can more comprehensively and accurately evaluate the fibrous scar and gray zone in the myocardium and improve the accuracy of judging the lesion location. Therefore, the present disclosure has important scientific research significance and broad clinical application value. Description of the Drawings

[0022] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure and, together with the specification, are used to explain the principles of the present disclosure.

[0023] To more clearly illustrate the technical solutions in the embodiments of the present disclosure or in the prior art, the following will briefly introduce the accompanying drawings required for use in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a flowchart of the method for processing a cardiac image according to an embodiment of the present disclosure;

[0025] Figure 2 It is a schematic diagram of a comprehensive cardiac model according to an embodiment of the present disclosure;

[0026] Figure 3 It is a block diagram of the structure of the device for processing a cardiac image according to an embodiment of the present disclosure;

[0027] Figure 4 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Detailed Embodiments

[0028] In order to be able to more clearly understand the above objects, features, and advantages of the present disclosure, the following will further describe the solutions of the present disclosure. It should be noted that, without conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other.

[0029] Many specific details are set forth in the following description to facilitate a thorough understanding of the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only a part of the embodiments of the present disclosure, rather than all of the embodiments.

[0030] Accurately evaluating the degree and scope of myocardial infarction is crucial for preventing the occurrence of adverse cardiac events and improving the survival rate of patients. Cardiovascular magnetic resonance imaging is a non-invasive imaging evaluation method for assessing myocardial infarction. Among them, delayed gadolinium-enhanced cardiovascular magnetic resonance imaging can be used to perform two-dimensional image analysis of myocardial scars and gray zones. There are also some evaluation methods that extract texture features, such as entropy and uniformity, from LGE-CMR images to describe the heterogeneity and homogeneity of gray zones. Or, there are some evaluation methods that focus on describing image microstructure features such as permeability, radiality, number of groups, and interface area, and these microstructure features are limited to describing the features of two-dimensional LGE images. Therefore, the existing cardiac MR processing and analysis techniques are mainly based on two-dimensional images. Due to the complexity of the cardiac structure and the diversity of myocardial lesions, two-dimensional images often cannot provide sufficient information to accurately judge the location and scope of lesions, resulting in the inability to comprehensively and accurately evaluate the fibrous scars and gray zones in the myocardium.

[0031] At the same time, the current cardiac post-processing software on the market mainly provides a view of the cardiac structure based on two-dimensional LGE-CMR images and can perform some simple slice reconstructions or two-dimensional image browsing. However, they are mainly limited to displaying two-dimensional images, and doctors need to manually switch on multiple planes to try to construct a three-dimensional concept of the heart. This process is both time-consuming and error-prone, especially in the evaluation of complex cardiac lesions, which is not conducive to doctors observing the cardiac structure from multiple angles and different depths and cannot assist doctors in better understanding the three-dimensional distribution of myocardial scars and gray zones.

[0032] To improve at least one of the above problems, the embodiments of the present disclosure provide a method, device, and equipment for processing cardiac images. For ease of understanding, the embodiments of the present disclosure are described below.

[0033] Figure 1 The flowchart of a method for processing cardiac images provided by the embodiments of the present disclosure can be executed by a processing device for cardiac images, and the device can be implemented by software and / or hardware. Refer to Figure 1 , the method for processing cardiac images may include the following steps.

[0034] S102, obtain a first image for calculating myocardial scars and / or gray areas and a second image for calculating the coronary artery tree.

[0035] Late gadolinium enhancement cardiovascular magnetic resonance imaging (LGE-CMR) is an important technique for evaluating myocardial scar and the grey zone (hereinafter referred to as the grey area). LGE is based on magnetic resonance T1 imaging technology. The T1 signal intensity of pure water with gadolinium added is lower than that of normal pure water. After injecting the contrast agent into the patient, gadolinium will quickly fill the extracellular space. When the gadolinium contrast agent passes through lesions with increased collagen deposition and reduced vascular structure (such as fibrotic scars), the penetration rate of the contrast agent decreases, and the location of myocardial perfusion defect can be judged through image discrimination. Through this imaging technique, doctors can identify and quantify the fibrotic area after myocardial infarction, which is crucial for the management and treatment of cardiovascular diseases. Based on the above LGE-CMR technology, in this embodiment, the first image used to calculate myocardial scar and / or grey area can be an LGE-CMR image.

[0036] In this embodiment, the second image used to calculate the coronary artery tree can be a CT (Computed Tomography) image based on CT technology, or an MRA (Magnetic Resonance Angiography) image based on magnetic resonance angiography (MRA) technology.

[0037] After obtaining multiple first images and second images, image preprocessing can be performed on the first images and second images. For the sake of easy understanding, the following takes any one of the first images as an example to describe the image preprocessing process.

[0038] The image preprocessing of the first image can include at least one of the following: (1) Normalize the size and brightness of the first image. (2) Perform denoising and contrast enhancement operations on the first image to improve the accuracy and stability of subsequent image processing. (3) Use filter techniques (such as median filtering, Gaussian filtering) and iterative reconstruction algorithms to perform noise reduction processing on the first image to reduce various noise interferences that the first image may be subject to during the acquisition process, and restore the true signal of the image. The above noise interferences include, for example, equipment noise, artifacts caused by patient breathing movement, etc. (4) Adjust the histogram equalization and dynamic range compression of the first image to improve the visibility of the region of interest in the first image, making the edges and structural features of myocardial tissue more clearly displayed; for the second image, it is to make the display of coronary blood vessels more clear. Through at least one of the above (1) to (4) image preprocessing, improve the image quality of the first image, support subsequent feature extraction algorithms, and improve the efficiency and accuracy of feature extraction.

[0039] The image preprocessing method for the second image is the same as that in the foregoing embodiment, and will not be elaborated here. This embodiment can perform subsequent steps based on the first image and the second image after image preprocessing.

[0040] S104, extract the three-dimensional image features of the myocardial scar region and / or grey area in the first image.

[0041] Under cardiac magnetic resonance imaging, normal myocardium appears black, necrotic myocardium appears bright / white, and the gray area (gray zone) between black and white is the slow conduction area, that is, myocardial scar and fibrotic myocardium. In other words, the myocardial scar area is within the gray area. Based on this, in this embodiment, the feature extraction network can extract the features of the region of interest from the first image to obtain the three-dimensional image features of the region of interest; the region of interest can include at least one of the myocardial scar area and the gray area.

[0042] The three-dimensional image features of the myocardial scar area and / or gray area extracted from the first image may include: volume, surface area, ratio of surface area to volume, contour features, regional features, moments and Hu moments, Euler number, centroid, and entropy value, etc.

[0043] In one embodiment, the three-dimensional image features include: volume, surface area, and ratio of surface area to volume; correspondingly, the following two implementation methods for extracting the three-dimensional image features of the myocardial scar area and / or gray area in the first image can be provided here.

[0044] One implementation method of feature extraction includes: segmenting the first region of interest in each first image and determining the two-dimensional area and contour perimeter of the first region of interest; wherein, the first region of interest includes: the myocardial scar area and / or the gray area. In this embodiment, ROI (region of interest) segmentation is performed on the two-dimensional first image, and the segmented first region of interest can include the myocardial scar area and / or the gray area, and the two-dimensional area and contour perimeter of the myocardial scar area, and / or the two-dimensional area and contour perimeter of the gray area are obtained.

[0045] Determine the volume of the first region of interest according to the scanning layer thickness corresponding to each first image and the sum of the two-dimensional areas of the first regions of interest in all first images. Specifically, when performing two-dimensional multi-layer imaging in LGE-CMR or CT, MRA, there is a certain layer interval between layers, that is, the scanning layer thickness. Based on this, in this embodiment, the sum of the two-dimensional areas of the first regions of interest in all first images is multiplied by the scanning layer thickness corresponding to the first image to estimate the three-dimensional volume of the first region of interest.

[0046] Determine the surface area of the first region of interest according to the scanning layer thickness corresponding to each first image and the sum of the contour perimeters of the first regions of interest in all first images. Specifically, the sum of the contour perimeters of the first regions of interest in all first images can be multiplied by the scanning layer thickness corresponding to the first image to estimate the three-dimensional surface area of the first region of interest.

[0047] By calculating the volume and surface area of the myocardial scar region and / or the gray region, it can be used to visually evaluate the size and extension of the lesion area.

[0048] Then, determine the ratio of the surface area to the volume; this ratio can reflect the complexity and irregularity of the lesion tissue. In the evaluation of myocardial scars, a higher ratio of surface area to volume may indicate more complex or extensive fibrosis.

[0049] Another implementation of feature extraction includes: reconstructing the three-dimensional volume data of the heart from multiple first images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional heart model; segmenting the second region of interest (Volume Of Interest, VOI) in the three-dimensional heart model; wherein, the second region of interest includes: the myocardial scar region and / or the gray region.

[0050] Determine the volume of the second region of interest according to the number of voxels and the voxel size within the second region of interest; specifically, the product of the number of voxels and the voxel size within the three-dimensional second region of interest can be calculated to obtain the volume of the second region of interest.

[0051] Draw a triangular patch model of the surface of the second region of interest, and determine the surface area of the second region of interest according to the number of triangular patches on the triangular patch model and the area of each triangular patch. Exemplarily, OpenGL surface rendering can be performed on the second region of interest to generate a triangular patch model of the surface of the second region of interest, and then the surface area of the second region of interest can be obtained by multiplying the number of triangular patches on the surface of the triangular patch model by the area of each triangular patch.

[0052] Then, determine the ratio of the surface area to the volume.

[0053] In one embodiment, the three-dimensional image features include: contour features and region features; correspondingly, an implementation method for extracting the three-dimensional image features of the myocardial scar region and / or the gray region in the first image can be provided, including:

[0054] Extract contour features according to the pixel intensity distribution of the contour of the myocardial scar region and / or the gray region in the first image; extract region features according to the pixel intensity distribution of the internal region of the myocardial scar region and / or the gray region in the first image.

[0055] Among them, the three-dimensional contour features include the shape tree of the contour, etc.; the three-dimensional region features include the uniformity of the region, texture analysis, etc.; by analyzing the contour features and internal region features of the myocardial scar region and / or the gray region, it can help doctors better understand the morphology and structure of the lesion area.

[0056] In one embodiment, the three-dimensional image features include: Hu moments; correspondingly, an implementation method for extracting the three-dimensional image features of the myocardial scar region and / or the gray region in the first image can be provided, including:

[0057] Calculate the moments on each of the first images, and then integrate the moments of all the first images to obtain the overall three-dimensional Hu moments. The Hu moments are invariant moments, which are invariant to the scaling, rotation, and translation of the image, and are very suitable for shape comparison and recognition.

[0058] Alternatively, another implementation method may include: reconstructing the three-dimensional volume data of the heart from multiple first images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional heart model; calculating the Hu moments on the VOI volume data of the three-dimensional heart model.

[0059] In one embodiment, the three-dimensional image features include: Euler number and centroid; correspondingly, an implementation method for extracting the three-dimensional image features of the myocardial scar region and / or the gray region in the first image can be provided, including:

[0060] Reconstruct the three-dimensional volume data of the heart from multiple first images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional heart model; calculate the holes and connected regions of the VOI volume data in the three-dimensional heart model to obtain the Euler number; the Euler number is calculated through the topological characteristics of the image and is used to describe the connectivity of the VOI (i.e., the myocardial scar region and / or the gray region) in the three-dimensional heart model.

[0061] Perform a weighted average on the centroids of all the two-dimensional first images to obtain the final centroid; the weight is the area of each first image; calculating the centroid can provide the spatial position of the lesion center.

[0062] In one embodiment, the three-dimensional image features include: entropy value; correspondingly, an implementation method for extracting the three-dimensional image features of the myocardial scar region and / or the gray region in the first image can be provided, including:

[0063] Calculate the entropy value according to the three-dimensional gray-level co-occurrence matrix of the myocardial scar region and / or the gray region in the first image. Specifically, the three-dimensional gray-level co-occurrence matrix can be obtained by sorting the frequencies and distributions of co-occurrences between different gray levels in three-dimensional space, and the sum of each element in the myocardial scar region and / or the gray region is calculated therein to obtain the overall entropy value. In the analysis of myocardial fibrosis, a higher entropy value indicates that the image content is more complex and irregular, which is associated with a more severe degree of the lesion.

[0064] S106, generate a three-dimensional heart model based on multiple first images, and generate a three-dimensional coronary artery tree model based on multiple second images.

[0065] In this embodiment, a three-dimensional model of the heart can be generated from multiple first images according to existing three-dimensional reconstruction algorithms, which may include: reconstructing three-dimensional volume data of the heart from multiple first images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional model of the heart. Also, a three-dimensional model of the coronary artery tree can be generated based on multiple second images, which may include: segmenting the coronary artery regions in each of the second images and reconstructing three-dimensional volume data of the coronary arteries of the heart from multiple second images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional model of the coronary artery tree of the heart.

[0066] In a specific example, the OpenGL surface rendering and volume rendering techniques, such as the Ray-casting algorithm, are used, and the absorption and emission model (Absorption plus emission) and alpha blending technique are used to reconstruct a three-dimensional model of the heart from multiple first images and a three-dimensional model of the coronary artery tree from multiple second images. To improve the realism of the models, lighting and texture mapping are performed on the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree. By simulating the lighting conditions in the real world, the structural characteristics of the myocardium, such as the direction and density of myocardial fibers, can be highlighted; texture mapping can give the models a more realistic appearance.

[0067] S108, visually display the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree.

[0068] Considering that existing cardiac MR processing and analysis techniques are mainly based on two-dimensional images, due to the complexity of the cardiac structure and the diversity of myocardial lesions, two-dimensional images often cannot provide sufficient information to accurately judge the location and extent of the lesions. To enable doctors to observe the cardiac structure from multiple angles and different depths to better understand the three-dimensional distribution of myocardial scars and gray zones, in this embodiment, after generating the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree, the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree can be visually displayed. By visually displaying the heart and the coronary artery tree in three-dimensional space, the diagnostic ability of doctors for heart disease states and the accuracy of treatment decisions can be significantly improved.

[0069] In one embodiment, the viewing process of visually displaying the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree can refer to the following content.

[0070] First, the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree are spatially registered, and the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree are superimposed into a comprehensive heart model according to the registration result; this comprehensive heart model can be referred to Figure 2 as shown.

[0071] The characteristics of myocardial scars and gray zones can be reflected in the three-dimensional model of the heart. The three-dimensional model of the coronary artery tree can represent the arterial system that supplies blood to the heart, and any abnormality in its structure may lead to changes in heart function or diseases. Therefore, in this embodiment, the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree are superimposed, so as to perform superimposed analysis on the distribution of myocardial scars in the three-dimensional model of the heart and the trend of coronary artery branches in the three-dimensional model of the coronary artery tree. This comparison can reveal the spatial relationship between the scar area and specific coronary artery branches, thereby helping doctors to more accurately identify and locate the lesions and being able to more precisely locate the lesions.

[0072] Secondly, the three-dimensional model of the heart, the three-dimensional model of the coronary artery tree, and the comprehensive heart model are respectively visualized.

[0073] Specifically, the three-dimensional model of the heart, the three-dimensional model of the coronary artery tree, and the comprehensive heart model can be respectively visualized, and the three-dimensional model of the heart, the three-dimensional model of the coronary artery tree, and the comprehensive heart model can be respectively displayed in different regions of the display interface, or only one of the three-dimensional model of the heart, the three-dimensional model of the coronary artery tree, and the comprehensive heart model can be displayed on the display interface.

[0074] In some visualization examples, the lesion area in the three-dimensional model of the heart can be highlighted to increase the contrast of the lesion area. For example, replacing the brightness value of each voxel point of the myocardial scar or gray zone with a normalized three-dimensional feature value will be more conducive to doctors visually distinguishing different diseases, different disease courses, treatment effects, risks, and prognosis predictions of diseases.

[0075] According to the above embodiments, the method provided by the present disclosure may further include: calculating the distance and connection relationship between the myocardial scar area and / or the gray area and the coronary artery branches in the three-dimensional model of the coronary artery tree in the comprehensive heart model.

[0076] In this embodiment, the distance and connection relationship between the myocardial scar area and / or the gray area and the coronary artery branches in the three-dimensional model of the coronary artery tree can be calculated according to the parameter measurement operation of the user on the comprehensive heart model; the calculated distance and connection relationship can be used to evaluate the severity of the structural abnormality (such as stenosis or occlusion) of the coronary artery tree and its impact on the myocardial scar. If a certain coronary artery branch is severely stenosed or occluded and corresponds to a large area of myocardial scar, this usually indicates that the myocardial injury is relatively severe.

[0077] The method provided by this embodiment may further include: passing through a preset machine learning model, and predicting the risk value of adverse cardiac events according to the coronary artery structure in the three-dimensional model of the coronary artery tree, the three-dimensional image features of the myocardial scar area and / or the gray area in the three-dimensional model of the heart, and the preset cardiac function data.

[0078] In a specific embodiment, a three-dimensional coronary artery tree model, a three-dimensional heart model, and pre-acquired heart function data can be input into a pre-trained machine learning model. The machine learning model is used to process and analyze a large amount of patient data, calculate the risk value or risk classification of a disease, and predict the risk value of an adverse cardiac event. Through the machine learning model, according to the coronary artery structure in the three-dimensional coronary artery tree model, the three-dimensional image features of the myocardial scar area and / or the gray area in the three-dimensional heart model, and the heart function data, the risk value of an adverse cardiac event is predicted. In this embodiment, by comprehensively analyzing the coronary artery structure, the distribution of myocardial scars, and the heart function data, the possible future adverse cardiac events and their risk values, such as myocardial infarction or heart failure, are predicted. Based on the prediction results, doctors can be assisted in taking preventive measures in advance, such as drug treatment or interventional surgery, to reduce the risk of patients.

[0079] The method provided in this embodiment may further include: in response to an interaction operation detected on the display interface, performing human-computer interaction on the three-dimensional heart model and the three-dimensional coronary artery tree model according to the interaction operation; wherein, the interaction operation includes but is not limited to: rotation operation, dragging operation, zooming operation, region marking operation, parameter measurement operation, visual adjustment operation, and export operation.

[0080] This embodiment can provide an intuitive and feature-rich user operation platform. Based on the user operation platform, doctors are allowed to perform all-round exploration and analysis on the reconstructed three-dimensional heart model, three-dimensional coronary artery tree model, and comprehensive heart model, as well as the three-dimensional features of local regions in the above three-dimensional models through simple interaction operations.

[0081] The following takes the three-dimensional heart model as an example to provide several examples of interaction operations.

[0082] In one example, the interaction operation includes a rotation operation. In response to the rotation operation, the three-dimensional heart model is freely rotated according to the rotation operation to facilitate doctors to observe various angles of the myocardium and ensure clear visual information can be obtained from any perspective.

[0083] In another example, the interaction operation includes a dragging operation. In response to the dragging operation, the three-dimensional heart model is moved in the virtual space according to the dragging operation, which can facilitate doctors to drag the region of interest in the three-dimensional heart model to the center of the field of view.

[0084] In another example, the interaction operation includes a zooming operation. In response to the zooming operation, the three-dimensional heart model is enlarged or reduced, so that doctors can enlarge a specific region as needed to observe fine structures, or reduce it to obtain an overall overview.

[0085] In another example, the interaction operation includes an area marking operation. In response to the area marking operation, the area corresponding to the area marking operation in the three-dimensional heart model is highlighted. Specifically, the display interface allows the doctor to select and highlight a specific area in the three-dimensional heart model, such as a scar area and a gray area, through the area marking operation for in-depth pathological analysis.

[0086] In another example, the interaction operation includes a parameter measurement operation. In response to the parameter measurement operation, key parameters are measured on the three-dimensional heart model, and three-dimensional feature calculation, selection, and display are provided. Specifically, a measurement tool can be built into the display interface. In response to the parameter measurement operation through the measurement tool, key parameters such as myocardial thickness and blood flow velocity are directly measured on the three-dimensional heart model, and three-dimensional feature calculation, selection, and display are provided at the same time.

[0087] In another example, the interaction operation includes a visual adjustment operation. In response to the visual adjustment operation, the visual display effect of the three-dimensional heart model is adjusted.

[0088] Specifically, a fine brightness adjustment slider can be provided on the display interface. Based on the brightness adjustment slider, a visual adjustment operation for brightness is initiated, whereby the brightness can be adjusted respectively for normal myocardium, fibrous scar, and gray area to highlight the contrast of different tissues and facilitate the doctor to identify the lesion area.

[0089] A transparency and color adjustment slider can be provided on the display interface. Based on the transparency and color adjustment slider, a visual adjustment operation for transparency and color is initiated, whereby the doctor can be allowed to select different three-dimensional features to adjust the transparency and color of the myocardial tissue to adapt to personal preferences or specific diagnostic needs and improve visual recognition.

[0090] A switch option can be provided on the display interface. Based on the switch option, a visual adjustment operation for display control is initiated, whereby it is possible to select whether to display the coronary artery vascular tree and myocardial structure so that the doctor can focus on the blood vessels or myocardial structure of the heart when needed.

[0091] In another example, the interaction operation includes an export operation. In response to the export operation, the three-dimensional heart model is exported as a specified image format. Specifically, the three-dimensional heart model is displayed in graphical form on the display interface, and through the export operation, the three-dimensional heart model is exported as a common medical image format, such as DICOM or STL, for further analysis and sharing by the doctor.

[0092] In summary, the method for processing cardiac images provided by the embodiments of the present disclosure includes: obtaining a first image for calculating myocardial scar and / or gray area and a second image for calculating coronary artery tree; extracting three-dimensional image features of the myocardial scar area and / or gray area in the first image; generating a three-dimensional cardiac model based on multiple first images and generating a three-dimensional coronary artery tree model based on multiple second images; and visually displaying the three-dimensional cardiac model and the three-dimensional coronary artery tree model.

[0093] This technical solution extracts the three-dimensional image features of the myocardial scar area and / or gray area in the first image. Using these three-dimensional image features can more comprehensively evaluate the fibrous scar and gray area in the myocardium, and more accurately perform lesion localization, severity assessment, and adverse event prediction. Through three-dimensional reconstruction and visually displaying the three-dimensional cardiac model and the three-dimensional coronary artery tree model, it can provide three-dimensional spatial distribution information such as the overall blood supply and fibrosis of the heart, improve the accuracy of lesion localization and the effectiveness of treatment planning, and provide a new method for the diagnosis and treatment of complex cardiovascular diseases. In short, the present disclosure can more comprehensively and accurately evaluate the fibrous scar and gray area in the myocardium by extracting three-dimensional image features and visually displaying the three-dimensional cardiac model and the three-dimensional coronary artery tree model, and improve the accuracy of judging the lesion location. Therefore, the present disclosure has important scientific research significance and broad clinical application value.

[0094] Figure 3 It is a structural block diagram of a device for processing cardiac images provided by the embodiments of the present disclosure. This device can be used to implement the above-mentioned method for processing cardiac images, and this device can be implemented by software and / or hardware. Refer to Figure 3 , the device for processing cardiac images may include the following modules.

[0095] An image acquisition module 210, configured to obtain a first image for calculating myocardial scar and / or gray area and a second image for calculating coronary artery tree;

[0096] A feature extraction module 220, configured to extract three-dimensional image features of the myocardial scar area and / or gray area in the first image;

[0097] A three-dimensional reconstruction module 230, configured to generate a three-dimensional cardiac model based on multiple first images and generate a three-dimensional coronary artery tree model based on multiple second images;

[0098] A visualization module 240, configured to visually display the three-dimensional cardiac model and the three-dimensional coronary artery tree model.

[0099] For the device provided in this embodiment, its implementation principle and the technical effects produced are the same as those of the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiment, reference may be made to the corresponding content in the foregoing method embodiments.

[0100] Figure 4 A structural schematic diagram of an electronic device provided by an embodiment of the present disclosure. As Figure 4 shown, the electronic device 300 includes one or more processors 301 and a memory 302.

[0101] The processor 301 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 300 to perform desired functions.

[0102] The memory 302 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage media, and the processor 301 may run the program instructions to implement the method for processing cardiac images in the embodiments of the present disclosure described above and / or other desired functions. Various contents such as input signals, signal components, noise components, etc. may also be stored in the computer-readable storage media.

[0103] In one example, the electronic device 300 may further include: an input device 303 and an output device 304, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown).

[0104] In addition, the input device 303 may further include, for example, a keyboard, a mouse, etc.

[0105] The output device 304 may output various information to the outside, including determined distance information, direction information, etc. The output device 304 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0106] Of course, for simplicity, Figure 4 only some of the components related to the present disclosure in the electronic device 300 are shown, and components such as buses, input / output interfaces, etc. are omitted. In addition, according to specific application scenarios, the electronic device 300 may further include any other appropriate components.

[0107] Furthermore, this embodiment also provides a computer-readable storage medium, and the storage medium stores a computer program, and the computer program is used to execute the above-mentioned method for processing cardiac images.

[0108] A computer program product of a method, apparatus, electronic device, and medium for processing cardiac images provided by an embodiment of the present disclosure includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the method described in the foregoing method embodiment. For specific implementation, reference can be made to the method embodiment, which will not be elaborated herein.

[0109] It should be noted that in this document, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0110] The above are only specific embodiments of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing a cardiac image, characterized in that, The method includes: Obtaining a first image for calculating myocardial scar and / or gray area and a second image for calculating the coronary artery tree; Extracting three-dimensional image features of the myocardial scar area and / or gray area in the first image; Generating a three-dimensional heart model based on multiple first images and generating a three-dimensional coronary artery tree model based on multiple second images; Visually displaying the three-dimensional heart model and the three-dimensional coronary artery tree model.

2. The method according to claim 1, wherein The three-dimensional image features include: volume, surface area, and the ratio of surface area to volume; the extracting of the three-dimensional image features of the myocardial scar area and / or gray area in the first image includes: Segmenting a first region of interest in each first image and determining the two-dimensional area and contour perimeter of the first region of interest; wherein, the first region of interest includes: the myocardial scar area and / or gray area; Determining the volume of the first region of interest according to the scan layer thickness corresponding to each first image and the sum of the two-dimensional areas of the first region of interest in all first images; Determining the surface area of the first region of interest according to the scan layer thickness corresponding to each first image and the sum of the contour perimeters of the first region of interest in all first images; Determining the ratio of the surface area to the volume.

3. The method according to claim 1, characterized in that, The generating of the three-dimensional heart model based on multiple first images includes: Reconstructing the three-dimensional volume data of the heart from multiple first images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional heart model; The generating of the three-dimensional coronary artery tree model based on multiple second images includes: Segmenting the coronary artery region in each second image and reconstructing the three-dimensional coronary artery volume data of the heart from multiple second images according to a preset three-dimensional reconstruction algorithm to obtain a three-dimensional coronary artery tree model of the heart.

4. The method according to claim 1, wherein The three-dimensional image features include: contour features and region features; the extracting of the three-dimensional image features of the myocardial scar area and / or gray area in the first image includes: Extracting the contour features according to the pixel intensity distribution of the contour of the myocardial scar area and / or gray area in the first image; Extracting the region features according to the pixel intensity distribution of the internal region of the myocardial scar area and / or gray area in the first image.

5. The method according to claim 1, characterized in that, The visually displaying of the three-dimensional heart model and the three-dimensional coronary artery tree model includes: Performing spatial registration on the three-dimensional heart model and the three-dimensional coronary artery tree model, and superimposing the three-dimensional heart model and the three-dimensional coronary artery tree model into a comprehensive heart model according to the registration result; Visually displaying the three-dimensional heart model, the three-dimensional coronary artery tree model, and the comprehensive heart model respectively.

6. The method according to claim 5, wherein The method further includes: Calculating the distance and connection relationship between the myocardial scar area and / or gray area and the coronary artery branches in the three-dimensional coronary artery tree model in the comprehensive heart model.

7. The method according to claim 1 or 5, characterized in that, The method further includes: Predicting the risk value of adverse cardiac events through a preset machine learning model and according to the coronary artery structure in the three-dimensional coronary artery tree model, the three-dimensional image features of the myocardial scar area and / or gray area in the three-dimensional heart model, and preset cardiac function data.

8. The method according to claim 1, characterized in that, The method further includes: responding to an interaction operation detected on a display interface, performing human-computer interaction on the three-dimensional heart model and the three-dimensional coronary artery tree model according to the interaction operation; wherein, the interaction operation includes: rotation operation, dragging operation, zooming operation, region marking operation, parameter measurement operation, visual adjustment operation, and export operation.

9. A processing device for cardiac images, characterized in that, The device includes: an image acquisition module, configured to acquire a first image for calculating myocardial scar and / or gray area and a second image for calculating the coronary artery tree; a feature extraction module, configured to extract three-dimensional image features of the myocardial scar area and / or gray area in the first image; a three-dimensional reconstruction module, configured to generate a three-dimensional heart model based on multiple first images and generate a three-dimensional coronary artery tree model based on multiple second images; a visualization module, configured to perform visualization display on the three-dimensional heart model and the three-dimensional coronary artery tree model.

10. An electronic device, characterized in that, The electronic device includes: a processor; a memory for storing executable instructions of the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method according to any one of claims 1-8 above.

Images