Method, apparatus and device for processing cardiac image

Abstract

The present disclosure relates to a method, device and equipment for processing a cardiac image, the method comprising: acquiring a first image for calculating myocardial scar and / or gray area and a second image for calculating a coronary tree; extracting a three-dimensional image feature of the myocardial scar area and / or the gray area of the first image; generating a three-dimensional model of a heart based on multiple first images and generating a three-dimensional model of a coronary tree based on multiple second images; and visually displaying the three-dimensional model of the heart and the three-dimensional model of the coronary tree. The present disclosure can more comprehensively and accurately evaluate the fiber scar and gray area in the myocardium, and improve the accuracy of judging the lesion position.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of image processing, and in particular to a method, device and equipment for processing cardiac images. BACKGROUND

[0002] Cardiovascular magnetic resonance imaging (CMR) is a non-invasive imaging method for evaluating myocardial infarction. At present, two-dimensional image analysis of myocardial scar and gray zone is mainly performed by using late gadolinium enhancement-cardiovascular magnetic resonance imaging (LGE-CMR); or the heterogeneity of the gray zone is described based on mass, texture features and microstructure features, and the cardiac adverse events of patients with different cardiovascular diseases are predicted. However, the above-mentioned 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 determine the location and range of lesions, resulting in that the fibrous scar and the gray zone in the myocardium cannot be comprehensively and accurately evaluated. SUMMARY

[0003] In order to solve the above technical problems, the present disclosure provides a method, device and equipment for processing cardiac images.

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

[0005] obtaining a first image for calculating myocardial scar and / or gray zone and a second image for calculating coronary tree;

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

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

[0008] visualizing the cardiac three-dimensional model and the coronary tree three-dimensional model.

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

[0010] an image acquisition module for obtaining a first image for calculating myocardial scar and / or gray zone and a second image for calculating coronary tree;

[0011] a feature extraction module for extracting three-dimensional image features of the myocardial scar and / or gray zone in the first image;

[0012] The 3D reconstruction module is used to generate a 3D model of the heart based on multiple first images and a 3D model of the coronary artery tree based on multiple second images.

[0013] The visualization module is used to visualize the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree.

[0014] According to another aspect of this disclosure, an electronic device is also provided, the electronic device comprising:

[0015] processor;

[0016] Memory used to store the processor's executable instructions;

[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 this disclosure, a computer-readable storage medium is also provided, the storage medium storing a computer program for performing the above-described method.

[0019] The technical solution provided in this disclosure has the following advantages compared with the prior art:

[0020] The technical solution provided in this disclosure includes: acquiring a first image for calculating myocardial scars and / or gray areas and a second image for calculating coronary artery trees; extracting three-dimensional image features of the myocardial scar region 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 visualizing the three-dimensional cardiac model and the three-dimensional coronary artery tree model.

[0021] This technical solution extracts three-dimensional image features of the myocardial scar region and / or gray area from the first image. Utilizing these three-dimensional image features, it is possible to more comprehensively assess fibrous scars and gray areas in the myocardium, and more accurately locate lesions, assess severity, and predict adverse events. By reconstructing the three-dimensional heart model and visualizing the coronary artery tree model, it is possible to provide three-dimensional spatial distribution information on the overall blood supply and fibrosis of the heart, improving the accuracy of lesion localization and the effectiveness of treatment planning, thus providing a novel method for the diagnosis and treatment of complex cardiovascular diseases. In short, this disclosure, by extracting three-dimensional image features and visualizing the three-dimensional heart model and coronary artery tree model, can more comprehensively and accurately assess fibrous scars and gray areas in the myocardium, improving the accuracy of lesion location determination. Therefore, this disclosure has significant scientific research value and broad clinical application value. Attached Figure Description

[0022] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0023] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

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

[0025] Figure 2 This is a schematic diagram of the integrated heart model described in the embodiments of this disclosure;

[0026] Figure 3 This is a structural block diagram of the cardiac image processing apparatus according to an embodiment of the present disclosure;

[0027] Figure 4 This is a schematic diagram of the structure of the electronic device described in an embodiment of this disclosure. Detailed Implementation

[0028] To better understand the above-mentioned objectives, features, and advantages of this disclosure, the solutions disclosed herein will be further described below. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other.

[0029] Numerous specific details are set forth in the following description in order to provide a full understanding of this disclosure, but this disclosure may also be implemented in other ways different from those described herein; obviously, the embodiments in the specification are only some, and not all, of the embodiments of this disclosure.

[0030] Accurate assessment of the severity and extent of myocardial infarction is crucial for preventing adverse cardiac events and improving patient survival. Cardiovascular magnetic resonance imaging (CMRI) is a non-invasive imaging method for assessing myocardial infarction. Delayed gadolinium-enhanced CMRI (LGE-CMR) can be used for two-dimensional image analysis of myocardial scarring and gray areas. Some assessment methods extract texture features, such as entropy and uniformity, from LGE-CMR images to describe the heterogeneity and homogeneity of gray areas. Alternatively, some methods focus on describing image microstructure features such as transmittance, radiality, cluster number, and interface area. These microstructure features are limited to describing two-dimensional LGE image features. Therefore, existing cardiac MR processing and analysis techniques are mainly based on two-dimensional images. Due to the complexity of cardiac structure and the diversity of myocardial lesions, two-dimensional images often cannot provide sufficient information to accurately determine the location and extent of lesions, resulting in an inability to comprehensively and accurately assess fibrous scarring and gray areas in the myocardium.

[0031] Meanwhile, current cardiac post-processing software on the market primarily provides views of the heart structure based on two-dimensional LGE-CMR images, enabling some simple layer reconstruction or two-dimensional image browsing. However, they are mainly limited to displaying two-dimensional images, requiring doctors to manually switch between multiple planes to attempt to construct a three-dimensional concept of the heart. This process is both time-consuming and error-prone, especially in complex cardiac lesion assessments. It hinders doctors from observing the heart structure from multiple angles and different depths, and cannot help doctors better understand the three-dimensional distribution of myocardial scars and gray areas.

[0032] To address at least one of the above-mentioned problems, this disclosure provides a method, apparatus, and device for processing cardiac images. For ease of understanding, embodiments of this disclosure are described below.

[0033] Figure 1 This is a flowchart illustrating a method for processing cardiac images according to an embodiment of the present disclosure. This method can be executed by a cardiac image processing device, which can be implemented using software and / or hardware. (Refer to...) Figure 1 The processing method for cardiac images may include the following steps.

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

[0035] Delayed gadolinium-enhanced cardiovascular magnetic resonance imaging (LGE-CMR) is an important technique for assessing myocardial scarring and gray areas (or gray regions). LGE is based on magnetic resonance T1 imaging technology; the T1 signal intensity of pure water with added gadolinium is lower than that of normal pure water. After injection of the contrast agent into the patient, gadolinium rapidly fills the extracellular space. When the gadolinium contrast agent passes through lesions with increased collagen deposition and reduced vascular structure (such as fibrous scars), the contrast agent penetration rate decreases, allowing for the identification of the location of myocardial perfusion defects through image differentiation. This imaging technique enables physicians to identify and quantify fibrotic areas after myocardial infarction, which is crucial for the management and treatment of cardiovascular diseases. Based on the above-mentioned LGE-CMR technology, the first image used in this embodiment to calculate myocardial scarring and / or gray areas can be an LGE-CMR image.

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

[0037] After acquiring multiple first and second images, image preprocessing can be performed on them. For ease of understanding, the image preprocessing process will be described below using any one of the first images as an example.

[0038] Image preprocessing of the first image may include at least one of the following: (1) normalizing the size and brightness of the first image. (2) performing denoising and contrast enhancement operations on the first image to improve the accuracy and stability of subsequent image processing. (3) using filter techniques (such as median filtering and Gaussian filtering) and iterative reconstruction algorithms to denoise the first image to reduce various noise interferences that the first image may be subjected to during the acquisition process and restore the true signal of the image. The aforementioned noise interferences include equipment noise, artifacts caused by the patient's respiratory movements, etc. (4) adjusting 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 edge and structural features of the myocardial tissue clearer; for the second image, it makes the coronary arteries clearer. Through at least one of the above image preprocessing steps (1) to (4), the image quality of the first image is improved, supporting subsequent feature extraction algorithms and improving the efficiency and accuracy of feature extraction.

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

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

[0041] Under cardiac magnetic resonance imaging, normal myocardium appears black, necrotic myocardium appears bright / white, and the gray area between black and white (the gray region) represents slow conduction areas, i.e., myocardial scarring and fibrotic myocardium. In other words, the myocardial scarring area lies within the gray region. Based on this, this embodiment can use a feature extraction network to extract features of the region of interest from the first image, obtaining the three-dimensional image features of the region of interest; the region of interest may include at least one of the myocardial scarring area and the gray region.

[0042] The three-dimensional image features of the myocardial scar region and / or gray region extracted from the first image may include: volume, surface area, surface area to volume ratio, contour features, region 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 the ratio of surface area to volume; correspondingly, the following two methods can be provided to extract the three-dimensional image features of the myocardial scar region and / or gray region in the first image.

[0044] One method for feature extraction includes: segmenting a first region of interest (ROI) in each first image, and determining the two-dimensional area and contour perimeter of the first ROI; wherein the first ROI includes a myocardial scar region and / or a gray region. This embodiment performs ROI segmentation on the two-dimensional first image, and the segmented first ROI may include a myocardial scar region and / or a gray region, and obtains the two-dimensional area and contour perimeter of the myocardial scar region, and / or the two-dimensional area and contour perimeter of the gray region.

[0045] The volume of the first region of interest (ROI) is determined based on the scan layer thickness corresponding to each first image and the sum of the two-dimensional areas of the first ROI in all first images. Specifically, in two-dimensional multi-layer imaging using LGE-CMR, CT, or MRA, a certain layer interval, i.e., scan layer thickness, is set between layers. Based on this, in this embodiment, the three-dimensional volume of the first ROI can be estimated by multiplying the sum of the two-dimensional areas of the first ROI in all first images by the scan layer thickness corresponding to the first image.

[0046] The surface area of ​​the first region of interest (ROI) is determined based on the scan layer thickness corresponding to each first image and the sum of the perimeters of the contours of the first ROI in all first images. Specifically, the three-dimensional surface area of ​​the first ROI can be estimated by multiplying the sum of the perimeters of the contours of the first ROI in all first images by the scan layer thickness corresponding to the first image.

[0047] By calculating the volume and surface area of ​​the myocardial scar region and / or gray region, the size and extent of the lesion region can be visually assessed.

[0048] Next, the surface area to volume ratio is determined; this ratio reflects the complexity and irregularity of the diseased tissue. In the assessment of myocardial scarring, a higher surface area to volume ratio may indicate more complex or extensive fibrosis.

[0049] Another method for 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 model of the heart; segmenting the second region of interest (VOI) in the three-dimensional model of the heart; wherein the second region of interest includes: myocardial scar region and / or gray region.

[0050] The volume of the second region of interest is determined based on the number and size of the voxels within it. Specifically, the volume of the second region of interest can be obtained by multiplying the number and size of the voxels within the three-dimensional region of interest.

[0051] A triangular facet model of the surface of the second region of interest (ROI) is drawn. The surface area of ​​the ROI is determined based on the number of triangular faces and the area of ​​each facet. For example, OpenGL surface drawing can be performed on the ROI to generate a triangular facet model of its surface. The surface area of ​​the ROI can then be obtained by multiplying the number of triangular faces on the model by the area of ​​each facet.

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

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

[0054] Contour features are extracted based on the pixel intensity distribution of the contours of the myocardial scar region and / or gray region in the first image; region features are extracted based on the pixel intensity distribution of the internal regions of the myocardial scar region and / or gray region in the first image.

[0055] Among them, the three-dimensional contour features include the shape tree of the contour; 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 gray region, doctors can better understand the morphology and structure of the lesion region.

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

[0057] Moments are calculated on each first image, and then the moments of all first images are integrated to obtain the overall three-dimensional Hu moments. Hu moments are invariant moments, which are invariant to image scaling, rotation and translation, making them 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 model of the heart; and calculating Hu moments on the VOI volume data of the three-dimensional model of the heart.

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

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

[0061] The centroids of all two-dimensional first images are weighted and averaged to obtain the final centroid; the weights are the areas of each first image; the spatial location of the lesion center can be provided by calculating the centroid.

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

[0063] Entropy values ​​are calculated based on the three-dimensional gray-level co-occurrence matrix of the myocardial scar region and / or gray region in the first image. Specifically, the three-dimensional gray-level co-occurrence matrix can be obtained by organizing the frequency and distribution of co-occurrence among different gray levels in three-dimensional space, and the sum of each element in the myocardial scar region and / or gray region is calculated to obtain the overall entropy value. In the analysis of myocardial fibrosis, higher entropy values ​​indicate more complex and irregular image content, which is associated with a more severe lesion.

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

[0065] This embodiment can generate a 3D model of the heart from multiple first images based on existing 3D reconstruction algorithms. This can include: reconstructing the 3D volume data of the heart from the multiple first images using a preset 3D reconstruction algorithm to obtain a 3D model of the heart. Additionally, generating a 3D model of the coronary artery tree based on multiple second images can include: segmenting the coronary artery regions in each second image, and reconstructing the 3D volume data of the coronary arteries of the heart from the multiple second images using a preset 3D reconstruction algorithm to obtain a 3D model of the coronary artery tree.

[0066] In a specific example, OpenGL surface rendering and volume rendering techniques, such as the Ray-casting algorithm, are used to reconstruct a 3D heart model from multiple first images and a 3D coronary artery tree model from multiple second images, employing an absorption plus emission model and alpha blending techniques. To enhance the realism of the models, lighting and texture mapping are applied to both the heart and coronary artery tree models. By simulating real-world lighting conditions, the structural features of the myocardium, such as the direction and density of myocardial fibers, can be highlighted; texture mapping gives the models a more realistic appearance.

[0067] S108 provides a visual representation of the 3D model of the heart and the 3D model of the coronary artery tree.

[0068] Given that existing cardiac MR processing and analysis techniques are primarily based on two-dimensional images, which often fail to provide sufficient information to accurately determine the location and extent of lesions due to the complexity of cardiac structure and the diversity of myocardial lesions, this embodiment aims to enable physicians to observe cardiac structures from multiple angles and depths to better understand the three-dimensional distribution of myocardial scars and gray areas. After generating a three-dimensional cardiac model and a three-dimensional coronary artery tree model, this embodiment allows for visualization of both models. Visualizing the heart and coronary artery tree in three-dimensional space significantly improves physicians' diagnostic capabilities for cardiac conditions and the accuracy of treatment decisions.

[0069] In one embodiment, the visualization process for the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree can be described below.

[0070] First, the 3D cardiac model and the 3D coronary artery tree model are spatially registered, and then, based on the registration results, the 3D cardiac model and the 3D coronary artery tree model are superimposed to form a comprehensive cardiac model; this comprehensive cardiac model can be referenced... Figure 2 As shown.

[0071] A three-dimensional model of the heart can depict the characteristics of myocardial scars and gray areas, while a three-dimensional model of the coronary artery tree can represent the arterial system supplying blood to the heart. Any structural abnormalities in these systems can lead to changes in cardiac function or disease. Therefore, this embodiment overlays the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree. This allows for the analysis of the distribution of myocardial scars in the three-dimensional model of the heart against the orientation of coronary artery branches in the three-dimensional model of the coronary artery tree. This comparison can reveal the spatial relationship between scar areas and specific coronary artery branches, thereby helping doctors to more accurately identify and locate lesions.

[0072] Secondly, the three-dimensional cardiac model, the three-dimensional coronary artery tree model, and the comprehensive cardiac model were visualized respectively.

[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 visualized separately and displayed in different areas of the display interface. Alternatively, 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, lesion areas in a 3D model of the heart can be highlighted to increase the contrast of these areas. For instance, replacing the brightness value of each voxel in a myocardial scar or gray area with a normalized 3D feature value would make it easier for doctors to visually distinguish different diseases, different disease stages, treatment efficacy, risks, and prognostic predictions.

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

[0076] This embodiment can calculate the distance and connectivity between the myocardial scar region and / or gray area and the coronary artery branches in the three-dimensional model of the coronary artery tree, based on the user's parameter measurement operations on the comprehensive cardiac model. The calculated distances and connectivity can be used to assess the severity of structural abnormalities in the coronary artery tree (such as stenosis or occlusion) and their impact on myocardial scarring. If a coronary artery branch is severely stenotic or occluded, and corresponds to a large area of ​​myocardial scarring, this usually indicates severe myocardial damage.

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

[0078] In a specific embodiment, a 3D model of the coronary artery tree, a 3D model of the heart, and pre-acquired cardiac function data can be input into a pre-trained machine learning model. This machine learning model is used to process and analyze large amounts of patient data, calculate disease risk values ​​or risk grading, and predict the risk value of adverse cardiac events. Through the machine learning model, based on the 3D image features of the coronary artery structure in the 3D coronary artery tree model, the myocardial scar region and / or gray area in the 3D heart model, and cardiac function data, the risk value of adverse cardiac events is predicted. This embodiment predicts potential future adverse cardiac events and their risk values, such as myocardial infarction or heart failure, by comprehensively analyzing coronary artery structure, myocardial scar distribution, and cardiac function data. Based on the prediction results, doctors can take preventative measures in advance, such as drug treatment or interventional surgery, to reduce patient risk.

[0079] The method provided in this embodiment may further include: responding to an interactive operation detected on the display interface, performing human-computer interaction on the cardiac 3D model and the coronary artery tree 3D model according to the interactive operation; wherein, the interactive operation includes, but is not limited to: rotation operation, drag operation, zoom operation, region marking operation, parameter measurement operation, visual adjustment operation, and export operation.

[0080] This embodiment provides an intuitive and feature-rich user operation platform, which allows doctors to conduct comprehensive exploration and analysis of the reconstructed 3D cardiac model, coronary artery tree 3D model, and comprehensive cardiac model, as well as the 3D features of local areas in the aforementioned 3D models, through simple interactive operations.

[0081] The following uses a 3D model of the heart as an example to provide several examples of interactive operations.

[0082] In one example, the interactive operation includes a rotation operation. In response to the rotation operation, the 3D model of the heart is freely rotated to allow doctors to observe the myocardium from various angles, ensuring clear visual information from any perspective.

[0083] In another example, the interactive operation includes a drag operation. In response to the drag operation, the 3D model of the heart is moved in virtual space, allowing doctors to easily drag areas of interest from the 3D model of the heart to the center of their field of vision.

[0084] In another example, the interactive action includes a zoom operation. In response to the zoom operation, the 3D model of the heart can be enlarged or reduced, allowing doctors to zoom in on specific areas to observe fine structures or zoom out for a global overview.

[0085] In another example, the interactive operation includes a region marking operation. In response to the region marking operation, the corresponding region in the 3D cardiac model is highlighted. Specifically, the display interface allows physicians to select and highlight specific regions in the 3D cardiac model, such as scar areas and gray areas, through the region marking operation for in-depth pathological analysis.

[0086] In another example, the interactive operation includes parameter measurement. In response to the parameter measurement operation, key parameters are measured on the 3D model of the heart, and 3D feature calculation, selection, and display are provided. Specifically, measurement tools can be built into the display interface. These tools respond to the parameter measurement operation and directly measure key parameters such as myocardial thickness and blood flow velocity on the 3D model of the heart, while simultaneously providing 3D feature calculation, selection, and display.

[0087] In another example, the interactive action includes a visual adjustment action. In response to the visual adjustment action, the visual display of the 3D model of the heart is adjusted.

[0088] Specifically, the display interface can provide a fine brightness adjustment slider. Based on the brightness adjustment slider, visual adjustment operations can be initiated for brightness. This allows for separate adjustment of brightness for normal myocardium, fibrous scars, and gray areas to highlight the contrast of different tissues and facilitate doctors in identifying lesion areas.

[0089] The display interface provides sliders for adjusting transparency and color. Based on these sliders, visual adjustments to transparency and color can be initiated. This allows doctors to select different three-dimensional features to adjust the transparency and color of myocardial tissue to suit individual preferences or specific diagnostic needs, thereby improving visual recognition.

[0090] The display interface can provide on / off options, based on which visual adjustments to the display control can be initiated, thereby selecting whether to display the coronary artery tree and myocardial structure, so that doctors can focus on the heart's blood vessels or myocardial structure when needed.

[0091] In another example, the interactive operation includes an export operation. In response to the export operation, the 3D model of the heart is exported to a specified image format. Specifically, the 3D model of the heart is displayed graphically on the interface, and the export operation exports the 3D model of the heart to common medical image formats, such as DICOM or STL, to facilitate further analysis and sharing by physicians.

[0092] In summary, the cardiac image processing method provided in this disclosure includes: acquiring a first image for calculating myocardial scars and / or gray areas and a second image for calculating coronary artery trees; extracting three-dimensional image features of the myocardial scar region 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 visualizing the three-dimensional cardiac model and the three-dimensional coronary artery tree model.

[0093] This technical solution extracts three-dimensional image features of the myocardial scar region and / or gray area from the first image. Utilizing these three-dimensional image features, it is possible to more comprehensively assess fibrous scars and gray areas in the myocardium, and more accurately locate lesions, assess severity, and predict adverse events. By reconstructing the three-dimensional heart model and visualizing the coronary artery tree model, it is possible to provide three-dimensional spatial distribution information on the overall blood supply and fibrosis of the heart, improving the accuracy of lesion localization and the effectiveness of treatment planning, thus providing a novel method for the diagnosis and treatment of complex cardiovascular diseases. In short, this disclosure, by extracting three-dimensional image features and visualizing the three-dimensional heart model and coronary artery tree model, can more comprehensively and accurately assess fibrous scars and gray areas in the myocardium, improving the accuracy of lesion location determination. Therefore, this disclosure has significant scientific research value and broad clinical application value.

[0094] Figure 3 This is a structural block diagram of a cardiac image processing apparatus provided in an embodiment of the present disclosure. This apparatus can be used to implement the aforementioned cardiac image processing method and can be implemented using software and / or hardware. (Refer to...) Figure 3 The cardiac image processing device may include the following modules.

[0095] Image acquisition module 210 is used to acquire a first image for calculating myocardial scars and / or gray areas and a second image for calculating coronary artery trees;

[0096] Feature extraction module 220 is used to extract three-dimensional image features of the myocardial scar region and / or gray region in the first image;

[0097] The three-dimensional reconstruction module 230 is used to generate a three-dimensional model of the heart based on multiple first images and to generate a three-dimensional model of the coronary artery tree based on multiple second images;

[0098] The visualization module 240 is used to visualize the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree.

[0099] The device provided in this embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0100] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Figure 4 As shown, the electronic device 300 includes one or more processors 301 and memory 302.

[0101] The processor 301 may be a central processing unit (CPU) or other form of processing unit with data processing 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, which 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. 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 medium, and the processor 301 may execute the program instructions to implement the cardiac image processing method of the embodiments of this disclosure described above and / or other desired functions. Various contents such as input signals, signal components, and noise components may also be stored in the computer-readable storage medium.

[0103] In one example, the electronic device 300 may also include an input device 303 and an output device 304, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

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

[0105] The output device 304 can 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 the sake of simplicity, Figure 4 Only some of the components of the electronic device 300 relevant to this disclosure are shown, omitting components such as buses, input / output interfaces, etc. In addition, the electronic device 300 may include any other suitable components depending on the specific application.

[0107] Furthermore, this embodiment also provides a computer-readable storage medium storing a computer program for executing the above-described cardiac image processing method.

[0108] The present disclosure provides a computer program product for processing cardiac images, including a method, apparatus, electronic device, and medium. The program includes a computer-readable storage medium storing program code. The instructions in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

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

[0110] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for processing cardiac images, characterized in that, The method includes: Acquire a first image for calculating myocardial scars and / or gray areas, and a second image for calculating the coronary tree; Extract the three-dimensional image features of the myocardial scar region and / or gray region in the first image; A three-dimensional model of the heart is generated based on multiple first images, and a three-dimensional model of the coronary artery tree is generated based on multiple second images; The three-dimensional model of the heart and the three-dimensional model of the coronary artery tree are visualized. The three-dimensional image features include: volume, surface area, and the ratio of surface area to volume; the extraction of three-dimensional image features of the myocardial scar region and / or gray region in the first image includes: Segment the first region of interest in each of the first images, and determine the two-dimensional area and contour perimeter of the first region of interest; wherein, the first region of interest includes: myocardial scar region and / or gray region; The volume of the first region of interest is determined based on the scanning layer thickness corresponding to each of the first images and the sum of the two-dimensional areas of the first region of interest in all the first images. The surface area of ​​the first region of interest is determined based on the scanning layer thickness corresponding to each of the first images and the sum of the contour perimeters of the first regions of interest in all the first images. Determine the ratio of the surface area to the volume; The three-dimensional image features include: contour features and region features; the extraction of three-dimensional image features of the myocardial scar region and / or gray region in the first image includes: The contour features are extracted based on the pixel intensity distribution of the contours of the myocardial scar region and / or gray region in the first image; Based on the pixel intensity distribution of the internal regions of the myocardial scar region and / or gray region in the first image, the region features are extracted; The visualization of the three-dimensional cardiac model and the three-dimensional coronary artery tree model includes: The three-dimensional cardiac model and the three-dimensional coronary artery tree model are spatially registered, and the three-dimensional cardiac model and the three-dimensional coronary artery tree model are superimposed into a comprehensive cardiac model based on the registration result; The three-dimensional cardiac model, the three-dimensional coronary artery tree model, and the integrated cardiac model are visualized respectively.

2. The method according to claim 1, characterized in that, The process of generating a three-dimensional heart model based on multiple of the first images includes: The three-dimensional volume data of the heart are reconstructed from multiple first images using a preset three-dimensional reconstruction algorithm to obtain a three-dimensional model of the heart. The generation of the coronary artery tree 3D model based on multiple second images includes: The coronary artery regions in each of the second images are segmented, and the three-dimensional volume data of the coronary arteries of the heart are reconstructed 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.

3. The method according to claim 1, characterized in that, The method further includes: In the comprehensive cardiac model, the distance and connection relationship between the myocardial scar region and / or gray region and the coronary artery branches in the three-dimensional coronary tree model are calculated.

4. The method according to claim 1, characterized in that, The method further includes: Using a pre-defined machine learning model, and based on the three-dimensional image features of the coronary artery structure in the coronary tree three-dimensional model, the myocardial scar area and / or gray area in the heart three-dimensional model, and pre-defined cardiac function data, the risk value of adverse cardiac events is predicted.

5. The method according to claim 1, characterized in that, The method further includes: In response to an interactive operation detected on the display interface, human-computer interaction is performed on the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree according to the interactive operation; wherein, the interactive operation includes: rotation operation, drag operation, zoom operation, region marking operation, parameter measurement operation, visual adjustment operation, and export operation.

6. A processing apparatus for cardiac images, characterized in that, The device includes: The image acquisition module is used to acquire a first image for calculating myocardial scars and / or gray areas and a second image for calculating the coronary artery tree; The feature extraction module is used to extract three-dimensional image features of the myocardial scar region and / or gray region in the first image; The 3D reconstruction module is used to generate a 3D model of the heart based on multiple first images and a 3D model of the coronary artery tree based on multiple second images. A visualization module is used to visualize the three-dimensional model of the heart and the three-dimensional model of the coronary artery tree; The three-dimensional image features include: volume, surface area, and the ratio of surface area to volume; the feature extraction module is also used for: Segment the first region of interest in each of the first images, and determine the two-dimensional area and contour perimeter of the first region of interest; wherein, the first region of interest includes: myocardial scar region and / or gray region; The volume of the first region of interest is determined based on the scanning layer thickness corresponding to each of the first images and the sum of the two-dimensional areas of the first region of interest in all the first images. The surface area of ​​the first region of interest is determined based on the scanning layer thickness corresponding to each of the first images and the sum of the contour perimeters of the first regions of interest in all the first images. Determine the ratio of the surface area to the volume; The three-dimensional image features include: contour features and region features; the feature extraction module is also used for: The contour features are extracted based on the pixel intensity distribution of the contours of the myocardial scar region and / or gray region in the first image; Based on the pixel intensity distribution of the internal regions of the myocardial scar region and / or gray region in the first image, the region features are extracted; The visualization module is also used for: The three-dimensional cardiac model and the three-dimensional coronary artery tree model are spatially registered, and the three-dimensional cardiac model and the three-dimensional coronary artery tree model are superimposed into a comprehensive cardiac model based on the registration result; The three-dimensional cardiac model, the three-dimensional coronary artery tree model, and the integrated cardiac model are visualized respectively.

7. An electronic device, characterized in that, The electronic device includes: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1-5.

Images