Microcirculatory resistance coefficient measurement method and device based on medical imaging

Abstract

This application relates to a method, apparatus, computer device, storage medium, and computer program product for measuring the microcirculatory resistance coefficient based on medical imaging. The method comprises: acquiring a medical image of a coronary region, identifying the myocardial lesion region within the medical image; identifying the lesion region corresponding to each coronary vessel within the myocardial lesion region based on the spatial geometric relationship between the coronary vessels in the medical image; and acquiring the microcirculatory resistance coefficient of each coronary vessel based on the lesion region corresponding to each coronary vessel. This method enables acquisition of the microcirculatory resistance coefficient from medical imaging, thereby avoiding damage to the patient's body during interventional surgery.

Description

Technical Field

[0001] The present application relates to the field of medical testing technology, and in particular to a method, device, computer equipment, storage medium and computer program product for measuring microcirculation resistance coefficient based on medical imaging. Background Art

[0002] The index of microcirculatory resistance (IMR) is an invasive indicator for quantitatively evaluating microcirculatory function. It can be defined as the product of the synchronously measured distal intracoronary pressure (Pd) and the mean transit time (Tmn) of a bolus injection of normal saline into the coronary artery under the state of maximum microcirculatory congestion.

[0003] Currently, IMR measurement methods are invasive, typically using Doppler flow measurement or thermodilution. Both methods are invasive and require insertion of a guidewire into the patient's coronary arteries in the catheterization laboratory. Both methods require an invasive procedure to obtain IMR values, placing a significant burden on the patient's body and potentially causing harm if not performed properly. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for measuring microcirculation resistance coefficient based on medical imaging without the need for interventional surgery to address the above technical problems.

[0005] In a first aspect, the present application provides a method for measuring microcirculation resistance coefficient based on medical imaging.

[0006] The method comprises:

[0007] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0008] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0009] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0010] In one embodiment, identifying the medical image to obtain the myocardial lesion area includes:

[0011] Processing the medical image based on a preset medical image processing method to obtain a myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method, and an artificial intelligence processing method;

[0012] Alternatively, corresponding texture features are acquired based on the medical image, and a myocardial lesion area is acquired based on the texture features.

[0013] In one embodiment, acquiring corresponding texture features based on the medical image, and acquiring a myocardial lesion area based on the texture features includes:

[0014] Performing image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image;

[0015] The texture feature to be detected is input into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture feature; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0016] In one embodiment, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical image includes:

[0017] Presetting a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter, and volume of each coronary vessel;

[0018] Obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by a weighted parameter of the coronary vessel;

[0019] Obtain the weighted distance between each myocardial point and each coronary vessel, and use the coronary vessel with the shortest weighted distance to each myocardial point as the coronary vessel corresponding to each myocardial point;

[0020] Based on the coronary vessels corresponding to each myocardial point, the lesion area corresponding to each coronary vessel is obtained.

[0021] In one embodiment, obtaining the microcirculatory resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery includes:

[0022] Based on a preset coronary artery microcirculation resistance coefficient calculation formula and the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained;

[0023] Alternatively, the lesion area corresponding to each coronary artery is input into a pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery; wherein, the microcirculation resistance coefficient calculation model is generated based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

[0024] In one embodiment, the lesion area corresponding to each coronary vessel is an absolute value or a relative value;

[0025] If it is an absolute value, the lesion area corresponding to each coronary vessel is the lesion myocardial volume or lesion myocardial mass;

[0026] If it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0027] In a second aspect, the present application also provides a device for measuring microcirculatory resistance coefficient based on medical imaging. The device comprises:

[0028] A first acquisition module is used to acquire a medical image of the coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0029] an identification module, configured to identify, in the myocardial lesion region, a lesion region corresponding to each coronary artery based on a spatial geometric relationship between the coronary arteries in the medical image;

[0030] The second acquisition module is used to acquire the microcirculation resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery.

[0031] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are performed:

[0032] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0033] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0034] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0035] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0036] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0037] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0038] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the following steps:

[0040] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0041] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0042] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0043] The above-mentioned medical imaging-based microcirculation resistance coefficient measurement method, device, computer equipment, storage medium and computer program product obtain and identify medical imaging images of the coronary artery area, obtain the myocardial lesion area in the medical image, and identify the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical imaging image. Finally, the microcirculation resistance coefficient of each coronary artery is obtained based on the lesion area corresponding to each coronary artery, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 FIG2 is a diagram showing an application environment of a method for measuring microcirculation resistance coefficient based on medical imaging in one embodiment;

[0045] Figure 2 1 is a flow chart of a method for measuring microcirculation resistance coefficient based on medical imaging in one embodiment;

[0046] Figure 3 Schematic diagram of a flow chart of a method for measuring microcirculatory resistance coefficient based on medical images in another embodiment;

[0047] Figure 4 is a structural block diagram of a device for measuring microcirculation resistance coefficient based on medical imaging in one embodiment;

[0048] Figure 5 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0050] The microcirculation resistance coefficient measurement method based on medical imaging provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104 or placed on the cloud or other network servers.

[0051] Terminal 102 may include, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices may include smart speakers, smart TVs, smart air conditioners, and smart car devices. Portable wearable devices may include smart watches, smart bracelets, and head-mounted devices. Server 104 may be implemented as a standalone server or a server cluster consisting of multiple servers.

[0052] In one embodiment, Figure 2 As shown in the figure, a method for measuring microcirculatory resistance coefficient based on medical imaging is provided. Figure 1 The following steps are used as an example to illustrate the server in the example:

[0053] Step 202: Obtain a medical image of the coronary artery region, identify the medical image, and obtain a myocardial lesion region.

[0054] Specifically, the medical image of the coronary artery region may be a coronary CT angiography image or a magnetic resonance imaging image; the imaging region is the patient's coronary artery region, including the heart. The medical image of the coronary artery region may be a two-dimensional image or a three-dimensional image. The specific method for identifying the myocardial lesion region in the medical image may be to identify the myocardial lesion region based on the results of image texture analysis of the medical image or to identify the myocardial lesion region based on the original medical image.

[0055] Identifying the area of ​​myocardial lesions based on the results of image texture analysis includes, based on the extracted texture features of the medical image and / or the filtered image, using statistical methods or machine learning algorithms to link the results of the image texture analysis with the area of ​​myocardial lesions, thereby establishing a relationship between the texture and the myocardial lesions, and identifying the area of ​​myocardial lesions based on the relationship.

[0056] Methods for identifying myocardial lesion areas based on raw medical images include thresholding, filtering, traditional machine learning, and deep learning. The thresholding method involves selecting an appropriate intensity threshold interval based on the image intensity of the raw medical image. The selected intensity threshold interval is then used to segment the raw medical image into a foreground image and a background image. The segmented foreground image represents the myocardial lesion area.

[0057] Filtering involves filtering the original medical image with a filter. Depending on the filter, different features in the original medical image are enhanced, highlighting some of the original features, thereby better segmenting the original medical image. Filter types include, but are not limited to, median filters, mean filters, bilateral filters, Frangi filters, Gaussian filters, Laplacian filters, Sobel filters, Gabor filters, and Canny filters.

[0058] The gradient method is a type of filtering method. First, the original medical image is converted into a gradient distribution image using a gradient filter, and then the high gradient is segmented using the threshold method to obtain the contour. The foreground image and background image are then segmented based on the contour. The segmented foreground image is the myocardial lesion area.

[0059] Artificial intelligence methods include traditional machine learning and deep learning. Traditional machine learning involves manually extracting features from images, training a machine learning model with large amounts of data, and then using the trained machine learning model to predict results. Traditional machine learning methods include, but are not limited to, random forests, multi-layer perceptrons, Bayesian methods, and support vector machines.

[0060] Deep learning algorithms are similar to traditional machine learning algorithms, with the biggest difference being that they eliminate the need for manual feature extraction from images. Deep learning algorithms include, but are not limited to, CNNs, RNNs, and Transformers. Using neural networks, predictions are generated based on medical images. These predictions are then compared with manual annotations and fed back to the neural network, which is then updated to reduce prediction errors. This iterative process, using large amounts of data, is repeated thousands of times until the error of the trained deep learning model meets the required standard. Ultimately, the predictions are close to the manual standard. The trained deep learning model is then used to identify medical images and identify areas of myocardial lesions within them.

[0061] Step 204 : Based on the spatial geometric relationship between the coronary vessels in the medical image, the lesion area corresponding to each coronary vessel is identified in the myocardial lesion area.

[0062] Specifically, based on the shape and spatial geometric relationship of each coronary artery in the medical image, the lesion area corresponding to each coronary artery is identified within the myocardial lesion area. The lesion area corresponding to each coronary artery can be an absolute value (e.g., myocardial volume, myocardial mass) or a relative value (e.g., proportion of myocardial volume, proportion of myocardial mass). Specific methods for identifying the lesion area corresponding to each coronary artery within the myocardial lesion area include, but are not limited to, the nearest neighbor method and the weighted nearest neighbor method.

[0063] The nearest neighbor method maps each point on the myocardium to each coronary artery based on the distance from each myocardial point to the blood vessel in the medical image, thereby obtaining the corresponding lesion area of ​​each coronary artery. The specific formula for identifying the corresponding lesion area of ​​each coronary artery using the nearest neighbor method can be found as follows:

[0064] P_Mi=argmin(d(V1,Mi),d(V2,Mi),...,d(Vi,Mi),...,d(Vn,Mi))

[0065] Where Mi represents the i-th myocardial point, P_Mi represents the vessel number corresponding to Mi; Vi represents the i-th vessel, d(Vi,Mi) represents the minimum distance between the i-th vessel and the i-th myocardial point, and argmin represents the vessel number corresponding to the minimum value.

[0066] Step 206: Obtain the microcirculatory resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery.

[0067] Specifically, after obtaining the lesion area corresponding to each coronary artery, the microcirculatory resistance coefficient of each coronary artery is obtained based on the lesion area corresponding to each coronary artery. Methods for calculating the microcirculatory resistance coefficient of each coronary artery include empirical formula calculation and artificial intelligence methods. The empirical formula is obtained by substituting the lesion area corresponding to each coronary artery into a pre-established empirical formula; the artificial intelligence method is to input the lesion area corresponding to each coronary artery into a pre-trained microcirculatory resistance coefficient calculation model, and obtain the output value of the microcirculatory resistance coefficient calculation model as the microcirculatory resistance coefficient of each coronary artery. In addition to the microcirculatory resistance coefficient, other microcirculatory resistances of each coronary artery can also be calculated based on the lesion area corresponding to each coronary artery, including but not limited to: CFR (Coronary Flow Reserve), HMR (Hyperemic Microvascular Resistance, microcirculatory resistance under maximum hyperemia), BMR (Basal / Baseline Microvascular Resistance, microcirculatory resistance under resting state), and CFVR (Coronary Flow Velocity Reserve).

[0068] In the above-mentioned method for measuring the microcirculation resistance coefficient based on medical imaging, a medical imaging image of the coronary artery area is obtained and identified, and the myocardial lesion area in the medical image is obtained. Based on the spatial geometric relationship of each coronary artery in the medical imaging image, the lesion area corresponding to each coronary artery is identified in the myocardial lesion area. Finally, based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery.

[0069] In one embodiment, identifying the medical image to obtain the myocardial lesion area includes:

[0070] Processing the medical image based on a preset medical image processing method to obtain a myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method, and an artificial intelligence processing method;

[0071] Alternatively, corresponding texture features are acquired based on the medical image, and a myocardial lesion area is acquired based on the texture features.

[0072] Specifically, Figure 3 FIG. 1 is a flow chart of a method for measuring microcirculatory resistance coefficient based on medical imaging in another embodiment. Figure 3 As shown, specific methods for identifying and obtaining myocardial lesion regions in medical images include directly obtaining the myocardial lesion region from the medical image, and obtaining the myocardial lesion region from the medical image based on texture features in the medical image. Methods for directly obtaining myocardial lesion regions from medical images include at least one of a threshold method, a filtering method, and an artificial intelligence processing method. The threshold method involves selecting an appropriate image intensity threshold interval based on the image intensity of the original medical image, and then segmenting the original medical image into a foreground image and a background image based on the selected image intensity threshold interval. The segmented foreground image is the myocardial lesion region.

[0073] Filtering involves filtering the original medical image with a filter. Depending on the filter, different features in the original medical image are enhanced, highlighting some of the original features, thereby better segmenting the original medical image. Filter types include, but are not limited to, median filters, mean filters, bilateral filters, Frangi filters, Gaussian filters, Laplacian filters, Sobel filters, Gabor filters, and Canny filters.

[0074] The gradient method is a type of filtering method. First, the original medical image is converted into a gradient distribution image using a gradient filter, and then the high gradient is segmented using the threshold method to obtain the contour. The foreground image and background image are then segmented based on the contour. The segmented foreground image is the myocardial lesion area.

[0075] Artificial intelligence methods include traditional machine learning and deep learning. Traditional machine learning involves manually extracting features from images, training a machine learning model with large amounts of data, and then using the trained machine learning model to predict results. Traditional machine learning methods include, but are not limited to, random forests, multi-layer perceptrons, Bayesian methods, and support vector machines.

[0076] Deep learning algorithms are similar to traditional machine learning algorithms, with the biggest difference being that they eliminate the need for manual feature extraction from images. Deep learning algorithms include, but are not limited to, CNNs, RNNs, and Transformers. Using neural networks, predictions are generated based on medical images. These predictions are then compared with manual annotations and fed back to the neural network, which is then updated to reduce prediction errors. This iterative process, using large amounts of data, is repeated thousands of times until the error of the trained deep learning model meets the required standard. Ultimately, the predictions are close to the manual standard. The trained deep learning model is then used to identify medical images and identify areas of myocardial lesions within them.

[0077] Acquiring the myocardial lesion area in the medical image based on the texture features in the medical image is to use statistical methods or machine learning algorithms to link the image texture and the myocardial lesion area based on the texture features extracted from the medical image and / or the filtered image, establish the relationship between the texture and the myocardial lesion, and thus identify the myocardial lesion area.

[0078] In this embodiment, the medical image is processed based on a preset medical image processing method to obtain the myocardial lesion area, or the corresponding texture features are obtained based on the medical image, and the myocardial lesion area in the medical image is obtained based on the texture features, thereby realizing the acquisition of the myocardial lesion area from the medical image and improving the recognition speed of the myocardial lesion area.

[0079] In one embodiment, acquiring corresponding texture features based on the medical image, and acquiring a myocardial lesion area based on the texture features includes:

[0080] Performing image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image;

[0081] The texture feature to be detected is input into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture feature to be detected; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0082] Specifically, image texture recognition is performed on medical images to obtain the texture features to be detected in the medical images. Image texture recognition methods use mathematical operations to extract texture features from images. These features include, but are not limited to, image histograms, gray-level co-occurrence matrices, absolute gradients, autoregressive models, and wavelet transforms.

[0083] The texture features to be detected are input into a pre-trained myocardial lesion region recognition model, and the myocardial lesion region corresponding to the texture features is generated through recognition by the myocardial lesion region recognition model. The myocardial lesion region recognition model is generated based on sample texture features and the sample lesion regions corresponding to the sample texture features.

[0084] In this embodiment, image texture recognition is performed on medical images to obtain texture features to be detected in the medical image, and the texture features to be detected are input into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture features, thereby achieving the acquisition of the myocardial lesion area based on the texture features and improving the recognition speed of the myocardial lesion area.

[0085] In one embodiment, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical image includes:

[0086] Presetting a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter, and volume of each coronary vessel;

[0087] Obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by a weighted parameter of the coronary vessel;

[0088] Obtain the weighted distance between each myocardial point and each coronary vessel, and use the coronary vessel with the shortest weighted distance to each myocardial point as the coronary vessel corresponding to each myocardial point;

[0089] Based on the coronary vessels corresponding to each myocardial point, the lesion area corresponding to each coronary vessel is obtained.

[0090] Specifically, a weighting parameter is preset for each coronary vessel; the weighting parameter is generated based on at least one factor among the grade, length, diameter, and volume of each coronary vessel, and can be generated based on one of the grade, length, diameter, and volume of the coronary vessel, or based on a combination of multiple factors. Based on the medical image, the distance between each myocardial point and each coronary vessel is obtained, and the distance between each myocardial point and each coronary vessel is multiplied by the weighting parameter of the coronary vessel. The weighting parameter preset for each coronary vessel can be the same parameter or a different parameter. The weighted distance between each myocardial point and each coronary vessel is obtained, and the coronary vessel with the shortest weighted distance from each myocardial point is determined as the coronary vessel corresponding to each myocardial point. Based on the coronary vessel corresponding to each myocardial point, the myocardial points corresponding to the same coronary vessel are combined to obtain the lesion area corresponding to each coronary vessel.

[0091] In this embodiment, the method for obtaining the lesion area corresponding to each coronary vessel is the weighted nearest neighbor method. Based on the aforementioned nearest neighbor method, the myocardial points are mapped to the coronary vessels by comparing the weighted distances between each myocardial point and the vessel. The specific formula for identifying the lesion area corresponding to each coronary vessel using the weighted nearest neighbor method can be referred to as follows:

[0092] P_Mi=argmin(a1*d(V1,Mi),a2*d(V2,Mi),...,ai*d(Vi,Mi),...,an*d(Vn,Mi))

[0093] Where Mi represents the i-th myocardial point, P_Mi represents the vessel number corresponding to Mi; Vi represents the i-th vessel, d(Vi,Mi) represents the minimum distance between the i-th vessel and the i-th myocardial point, argmin represents the vessel number corresponding to the minimum value, and ai represents the weighting parameter of the i-th distance.

[0094] In this embodiment, a weighting parameter is preset for each coronary artery, and the distance between each myocardial point and each coronary vessel is obtained. The distance between each myocardial point and each coronary vessel is multiplied by the weighting parameter of the coronary vessel. By obtaining the weighted distance between each myocardial point and each coronary vessel, the coronary vessel with the shortest weighted distance from each myocardial point is used as the coronary vessel corresponding to each myocardial point. Finally, based on the coronary vessel corresponding to each myocardial point, the lesion area corresponding to each coronary vessel is obtained, thereby achieving the acquisition of the lesion area corresponding to each coronary vessel based on the spatial geometric relationship of each coronary vessel in the medical image.

[0095] In one embodiment, obtaining the microcirculatory resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery includes:

[0096] Based on a preset coronary artery microcirculation resistance coefficient calculation formula and the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained;

[0097] Alternatively, the lesion area corresponding to each coronary artery is input into a pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery; wherein, the microcirculation resistance coefficient calculation model is generated based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

[0098] Specifically, the specific methods for obtaining the microcirculatory resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery include an empirical formula method and an artificial intelligence method. Among them, the empirical formula method obtains the microcirculatory resistance coefficient of each coronary artery based on a preset coronary artery microcirculatory resistance coefficient calculation formula and the lesion area corresponding to each coronary artery. The preset coronary artery microcirculatory resistance coefficient calculation formula is:

[0099] IMR=a*(1+M b )

[0100] Among them, a and b are preset coefficients, and M is the myocardial mass of the lesion area.

[0101] The artificial intelligence method is based on a pre-trained microcirculation resistance coefficient calculation model. The lesion area corresponding to each coronary artery is input into the pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery. The microcirculation resistance coefficient calculation model is based on the sample lesion area and the sample coefficient corresponding to the sample lesion area, and is generated through thousands of repeated iterative processes.

[0102] In this embodiment, the microcirculation resistance coefficient of each coronary artery is obtained according to the lesion area corresponding to each coronary artery through the empirical formula and artificial intelligence methods, thereby avoiding damage to the patient's body caused by interventional surgery.

[0103] In one embodiment, the lesion area corresponding to each coronary vessel is an absolute value or a relative value;

[0104] If it is an absolute value, the lesion area corresponding to each coronary vessel is the lesion myocardial volume or lesion myocardial mass;

[0105] If it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0106] Specifically, the lesion area corresponding to each coronary artery is an absolute value or a relative value. If the lesion area corresponding to each coronary artery is an absolute value, the lesion area corresponding to each coronary artery is the lesion myocardial volume or lesion myocardial mass. If the lesion area corresponding to each coronary artery is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass. Both absolute and relative values ​​can be used to obtain the microcirculatory resistance coefficient of each coronary artery.

[0107] In this embodiment, by setting the lesion area corresponding to each coronary artery to an absolute value or a relative value, it is convenient to use different methods such as the empirical formula method and the artificial intelligence method to obtain the microcirculation resistance coefficient of each coronary artery, thereby avoiding damage to the patient's body caused by interventional surgery.

[0108] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0109] Based on the same inventive concept, embodiments of the present application also provide a medical imaging-based microcirculation resistance coefficient measurement device for implementing the aforementioned medical imaging-based microcirculation resistance coefficient measurement method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the medical imaging-based microcirculation resistance coefficient measurement device provided below can be found in the above-mentioned limitations of the medical imaging-based microcirculation resistance coefficient measurement method and will not be further elaborated here.

[0110] In one embodiment, Figure 4 As shown, a microcirculation resistance coefficient measurement device 400 based on medical imaging is provided, comprising: a first acquisition module 401, an identification module 402, and a second acquisition module 403, wherein:

[0111] The first acquisition module 401 is configured to acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0112] an identification module 402 for identifying, based on the spatial geometric relationship of the coronary vessels in the medical image, a lesion region corresponding to each coronary vessel in the myocardial lesion region;

[0113] The second acquisition module 403 is configured to acquire the microcirculation resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery.

[0114] In one embodiment, the first acquisition module 401 is specifically used to: process the medical image based on a preset medical image processing method to obtain the myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method and an artificial intelligence processing method; or obtain corresponding texture features based on the medical image, and obtain the myocardial lesion area based on the texture features.

[0115] In one embodiment, the first acquisition module 401 is further used to: perform image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image; input the texture features to be detected into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture features; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0116] In one embodiment, the identification module 402 is specifically used to: preset a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter and volume of each coronary vessel; obtain the distance between each myocardial point and each coronary vessel, and multiply the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtain the weighted distance between each myocardial point and each coronary vessel, and use the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtain the lesion area corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point.

[0117] In one embodiment, the second acquisition module 403 is specifically used to: obtain the microcirculation resistance coefficient of each coronary artery based on a preset microcirculation resistance coefficient calculation formula of the coronary artery and the lesion area corresponding to each coronary artery; or input the lesion area corresponding to each coronary artery into a pre-trained microcirculation resistance coefficient calculation model to obtain the output value of the microcirculation resistance coefficient calculation model as the microcirculation resistance coefficient of each coronary artery; wherein the microcirculation resistance coefficient calculation model is generated based on sample lesion areas and sample coefficients corresponding to the sample lesion areas.

[0118] In one embodiment, the lesion area corresponding to each coronary artery in the medical imaging-based microcirculation resistance coefficient measurement device 400 is an absolute value or a relative value; if it is an absolute value, the lesion area corresponding to each coronary artery is the lesion myocardial volume or the lesion myocardial mass; if it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0119] The above-mentioned microcirculation resistance coefficient measurement device based on medical imaging obtains and identifies medical imaging images of the coronary artery area, obtains the myocardial lesion area in the medical image, and identifies the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical imaging image. Finally, the microcirculation resistance coefficient of each coronary artery is obtained based on the lesion area corresponding to each coronary artery, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery.

[0120] Each module in the aforementioned medical imaging-based microcirculatory resistance coefficient measurement device can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0121] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for measuring microcirculatory resistance coefficient based on medical images is implemented.

[0122] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0123] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0124] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0125] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0126] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0127] In one embodiment, when the processor executes the computer program, it also implements the following steps: based on a preset medical image processing method, processing the medical image to obtain the myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method and an artificial intelligence processing method; or obtaining corresponding texture features based on the medical image, and obtaining the myocardial lesion area based on the texture features.

[0128] In one embodiment, when the processor executes the computer program, it also implements the following steps: performing image texture recognition and texture analysis on the medical image to obtain the texture features to be detected in the medical image; inputting the texture features to be detected into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture features; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0129] In one embodiment, when the processor executes the computer program, the following steps are further implemented: presetting a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter and volume of each coronary vessel; obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtaining the weighted distance between each myocardial point and each coronary vessel, and using the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtaining the lesion area corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point.

[0130] In one embodiment, when the processor executes the computer program, it further implements the following steps: based on a preset microcirculation resistance coefficient calculation formula for the coronary arteries and the lesion area corresponding to each coronary artery, obtaining the microcirculation resistance coefficient of each coronary artery; or inputting the lesion area corresponding to each coronary artery into a pre-trained microcirculation resistance coefficient calculation model, obtaining the output value of the microcirculation resistance coefficient calculation model as the microcirculation resistance coefficient of each coronary artery; wherein the microcirculation resistance coefficient calculation model is generated by training based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

[0131] In one embodiment, when the processor executes the computer program, the lesion area corresponding to each coronary artery is an absolute value or a relative value; if it is an absolute value, the lesion area corresponding to each coronary artery is the lesion myocardial volume or the lesion myocardial mass; if it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0132] The above-mentioned computer equipment obtains and identifies medical imaging images of the coronary artery area, obtains the myocardial lesion area in the medical image, identifies the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical imaging image, and finally obtains the microcirculation resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0134] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0135] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0136] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on a preset medical image processing method, the medical image is processed to obtain the myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method and an artificial intelligence processing method; or based on the medical image, corresponding texture features are obtained, and the myocardial lesion area is obtained based on the texture features.

[0138] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image; inputting the texture features to be detected into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture features; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0139] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: presetting a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter and volume of each coronary vessel; obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtaining the weighted distance between each myocardial point and each coronary vessel, and taking the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtaining the lesion area corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point.

[0140] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on a preset microcirculation resistance coefficient calculation formula for the coronary arteries and the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained; or the lesion area corresponding to each coronary artery is input into a pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery; wherein the microcirculation resistance coefficient calculation model is generated by training based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

[0141] In one embodiment, when the computer program is executed by a processor, the lesion area corresponding to each coronary artery is an absolute value or a relative value; if it is an absolute value, the lesion area corresponding to each coronary artery is the lesion myocardial volume or the lesion myocardial mass; if it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0142] The above-mentioned storage medium obtains and identifies medical imaging images of the coronary artery region, obtains the myocardial lesion region in the medical image, identifies the lesion region corresponding to each coronary artery in the myocardial lesion region based on the spatial geometric relationship of each coronary artery in the medical imaging image, and finally obtains the microcirculation resistance coefficient of each coronary artery based on the lesion region corresponding to each coronary artery, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery.

[0143] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0144] Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region;

[0145] Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area;

[0146] Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: based on a preset medical image processing method, the medical image is processed to obtain the myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method and an artificial intelligence processing method; or based on the medical image, corresponding texture features are obtained, and the myocardial lesion area is obtained based on the texture features.

[0148] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: performing image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image; inputting the texture features to be detected into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture features; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: presetting a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter and volume of each coronary vessel; obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtaining the weighted distance between each myocardial point and each coronary vessel, and taking the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtaining the lesion area corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point.

[0150] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: based on a preset microcirculation resistance coefficient calculation formula for the coronary arteries and the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained; or the lesion area corresponding to each coronary artery is input into a pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery; wherein the microcirculation resistance coefficient calculation model is generated by training based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

[0151] In one embodiment, when the computer program is executed by a processor, the lesion area corresponding to each coronary artery is an absolute value or a relative value; if it is an absolute value, the lesion area corresponding to each coronary artery is the lesion myocardial volume or the lesion myocardial mass; if it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

[0152] The above-mentioned computer program product obtains and identifies medical imaging images of the coronary artery region, obtains the myocardial lesion area in the medical image, identifies the lesion area corresponding to each coronary artery in the myocardial lesion area based on the spatial geometric relationship of each coronary artery in the medical imaging image, and finally obtains the microcirculation resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery, thereby realizing the acquisition of the microcirculation resistance coefficient through medical imaging images and avoiding damage to the patient's body caused by interventional surgery.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0154] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0155] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for measuring microcirculatory resistance coefficient based on medical imaging, characterized in that: The method comprises: Acquire a medical image of a coronary artery region, identify the medical image, and acquire a myocardial lesion region; The identifying the medical image to obtain the myocardial lesion area includes: selecting an image intensity threshold interval based on the image intensity of the medical image; segmenting the medical image into a foreground image and a background image based on the image intensity threshold interval, and determining the foreground image as the myocardial lesion area; Based on the spatial geometric relationship of each coronary artery in the medical image, identifying the lesion area corresponding to each coronary artery in the myocardial lesion area; The method of identifying the lesion region corresponding to each coronary vessel in the myocardial lesion region based on the spatial geometric relationship of each coronary vessel in the medical image includes: presetting a weighting parameter for each coronary vessel; the weighting parameter being generated based on at least one factor of the grade, length, diameter, and volume of each coronary vessel; obtaining the distance between each myocardial point and each coronary vessel, and multiplying the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtaining the weighted distance between each myocardial point and each coronary vessel, and selecting the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtaining the lesion region corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point. Based on the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained.

2. The method according to claim 1, characterized in that The identifying the medical image to obtain the myocardial lesion area includes: Processing the medical image based on a preset medical image processing method to obtain a myocardial lesion area; the preset medical image processing method includes at least one of a threshold method, a filtering method, and an artificial intelligence processing method; Alternatively, corresponding texture features are acquired based on the medical image, and a myocardial lesion area is acquired based on the texture features.

3. The method according to claim 2, characterized in that The acquiring of corresponding texture features based on the medical image and the acquiring of a myocardial lesion area based on the texture features include: Performing image texture recognition and texture analysis on the medical image to obtain texture features to be detected in the medical image; The texture feature to be detected is input into a pre-trained myocardial lesion area recognition model to generate a myocardial lesion area corresponding to the texture feature; wherein the myocardial lesion area recognition model is generated based on sample texture features and sample lesion areas corresponding to the sample texture features.

4. The method according to claim 1, wherein The obtaining of the microcirculatory resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery includes: Based on a preset coronary artery microcirculation resistance coefficient calculation formula and the lesion area corresponding to each coronary artery, the microcirculation resistance coefficient of each coronary artery is obtained; Alternatively, the lesion area corresponding to each coronary artery is input into a pre-trained microcirculation resistance coefficient calculation model, and the output value of the microcirculation resistance coefficient calculation model is obtained as the microcirculation resistance coefficient of each coronary artery; wherein, the microcirculation resistance coefficient calculation model is generated based on the sample lesion area and the sample coefficient corresponding to the sample lesion area.

5. The method according to claim 1, wherein The lesion area corresponding to each coronary vessel is an absolute value or a relative value; If it is an absolute value, the lesion area corresponding to each coronary vessel is the lesion myocardial volume or lesion myocardial mass; If it is a relative value, the lesion area corresponding to each coronary artery is the ratio of the lesion myocardial volume to the total myocardial volume or the ratio of the lesion myocardial mass to the total myocardial mass.

6. A device for measuring microcirculation resistance coefficient based on medical imaging, characterized in that: The device comprises: A first acquisition module is used to acquire a medical image of the coronary artery region, identify the medical image, and acquire a myocardial lesion region; The first acquisition module is further configured to select an image intensity threshold interval based on the image intensity of the medical image; segment the medical image into a foreground image and a background image based on the image intensity threshold interval, and determine the foreground image as the myocardial lesion area; an identification module, configured to identify, in the myocardial lesion region, a lesion region corresponding to each coronary artery based on a spatial geometric relationship between the coronary arteries in the medical image; The identification module is further configured to preset a weighting parameter for each coronary vessel; the weighting parameter is generated based on at least one factor of the grade, length, diameter, and volume of each coronary vessel; obtain the distance between each myocardial point and each coronary vessel, and multiply the distance between each myocardial point and each coronary vessel by the weighting parameter of the coronary vessel; obtain the weighted distance between each myocardial point and each coronary vessel, and select the coronary vessel with the shortest weighted distance from each myocardial point as the coronary vessel corresponding to each myocardial point; and obtain the lesion area corresponding to each coronary vessel based on the coronary vessel corresponding to each myocardial point; The second acquisition module is used to acquire the microcirculation resistance coefficient of each coronary artery based on the lesion area corresponding to each coronary artery.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images