Information processing method and device, electronic equipment and storage medium

Abstract

The invention provides an information processing method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a fractional flow reserve of a target area; acquiring at least two pieces of blood vessel information according to the multi-stage medical images; acquiring at least one piece of blood flow information corresponding to each piece of blood vessel information according to the blood vessel information and the medical image; according to the medical image, the at least one piece of blood flow information and the blood vessel information, the fractional flow reserve of the target area is obtained. The method can improve the calculation precision of the fractional flow reserve while guaranteeing the safety of the user.

Description

Technical Field

[0001] The present application relates to the field of information processing technology, and in particular to an information processing method, device, electronic device, and computer-readable storage medium. Background Art

[0002] Fractional Flow Reserve (FFR) is defined as the ratio of the maximum blood flow that a diseased vessel can provide to the maximum blood flow that the vessel can provide when it is completely normal. This indicator is considered the "gold standard" for judging the degree of ischemia in diseased vessels.

[0003] However, existing methods for calculating the blood flow reserve fraction include invasive and non-invasive measurements (such as CT scans).

[0004] However, either method of measurement can cause harm to the patient, and the accuracy of calculating the fractional flow reserve is limited. Summary of the Invention

[0005] The embodiments of the present application provide an information processing method, apparatus, electronic device, and computer-readable storage medium, which are intended to improve calculation accuracy while ensuring user safety.

[0006] In a first aspect, an embodiment of the present application provides an information processing method, comprising:

[0007] Obtain blood flow reserve fraction of target area;

[0008] Obtain information on at least two blood vessels based on multiple medical images;

[0009] acquiring, according to the blood vessel information and the medical image, at least one piece of blood flow information corresponding to each piece of blood vessel information;

[0010] A blood flow reserve fraction of a target area is acquired according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0011] Optionally, obtaining a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information includes:

[0012] determining a blood flow information field according to the medical image, the at least one piece of blood flow information, and the blood vessel information;

[0013] The blood flow reserve fraction of the target area is determined according to the blood flow information field.

[0014] Optionally, acquiring at least one piece of blood flow information corresponding to each piece of blood vessel information according to the blood vessel information and the medical image includes:

[0015] acquiring blood flow volume information of the target object according to position change information of the target object in the target area corresponding to the blood vessel information in the multiple phases of the medical images, wherein the target object is a blood image in the medical image processed with a contrast agent;

[0016] The blood flow information is acquired according to the position change information and the blood flow volume information of the target object, wherein the blood flow information includes the blood flow rate.

[0017] Optionally, obtaining at least two pieces of blood vessel information based on multiple medical images includes:

[0018] Acquire at least two target medical images of blood vessels through which blood flows from the multiple medical images;

[0019] According to the target medical image, the vascular images in the target medical image are segmented by a pre-trained segmentation model to obtain vascular information in each of the target medical images.

[0020] Optionally, the training step of the segmentation model includes:

[0021] Acquire a training image set, wherein the training image set includes a plurality of consecutive medical training images within a preset time period;

[0022] According to the physiological tissue features corresponding to the plurality of medical training images, the plurality of medical training images are spatially transformed so that the key points of the lesions in the plurality of medical training images after the spatial transformation correspond to each other;

[0023] The initial segmentation model is trained according to the medical training images after spatial transformation to obtain a segmentation model.

[0024] Optionally, obtaining at least two pieces of blood vessel information based on multiple medical images further includes:

[0025] According to the plurality of medical images, denoising the vascular images in the plurality of medical images using a pre-trained noise prediction model to obtain vascular information in each of the medical images;

[0026] The training step of the noise prediction model includes:

[0027] Obtain vascular noise data in medical training images;

[0028] An initial noise prediction model is trained according to the blood vessel noise data to obtain a noise prediction model.

[0029] Optionally, after obtaining the blood flow reserve fraction of the target area according to the medical image, the at least one blood flow information, and the blood vessel information, the method further includes:

[0030] determining a lesion location in the target area according to the blood flow reserve fraction;

[0031] The diseased blood vessels at the lesion location are displayed according to the preset markers.

[0032] In a second aspect, an embodiment of the present application provides an information processing device, including:

[0033] A first acquisition module is used to obtain the blood flow reserve fraction of the target area;

[0034] A second acquisition module is used to acquire information of at least two blood vessels based on multiple medical images;

[0035] a third acquisition module, configured to acquire at least one piece of blood flow information corresponding to each piece of blood vessel information based on the blood vessel information and the medical image;

[0036] A fourth acquisition module is configured to acquire a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0037] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps of the above-mentioned information processing method.

[0038] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps of the above-mentioned information processing method.

[0039] Beneficial effects of the embodiments of the present application:

[0040] In the embodiments of the present application, the blood flow reserve fraction of a target area is obtained, and further, information about at least two blood vessels in the target area and at least one blood flow information corresponding to each blood vessel information can be obtained based on medical images. Thus, the blood flow reserve fraction of the target area can be obtained based on the medical images, blood flow information, and the blood vessel information. As can be seen, compared to the prior art blood flow reserve fraction calculation methods that are harmful to patients, the present application can directly calculate the blood flow reserve fraction using medical images, blood vessel information, and blood flow information. This eliminates the need for invasive testing and does not cause radiation damage to patients. It also improves the accuracy of blood flow reserve fraction calculation, allowing the blood flow reserve fraction to guide subsequent diagnostic analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 This is a first schematic diagram of the information processing flow provided in the embodiments of the present application;

[0043] Figure 2 This is a first schematic diagram of blood flow information calculation provided in an embodiment of the present application;

[0044] Figure 3 This is a second schematic diagram of blood flow information calculation provided in an embodiment of the present application;

[0045] Figure 4 is a schematic diagram of the structure of an information processing device provided in an embodiment of the present application;

[0046] Figure 5 It is a structural diagram of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0047] The following will provide a clear and complete description of the technical solutions in the embodiments of this application, in conjunction with the accompanying drawings. Obviously, the described embodiments are only some of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments derived by persons skilled in the art without inventive effort are within the scope of protection of this application. Furthermore, it should be understood that the specific embodiments described herein are intended only to illustrate and explain this application and are not intended to limit this application. In this application, unless otherwise indicated, directional terms such as "upper" and "lower" generally refer to the upper and lower sides of the device in actual use or operation, specifically the directions in the drawings; while "inner" and "outer" refer to the outline of the device. Furthermore, in the description of the embodiments of this application, the terms "first" and "second" are used solely to distinguish descriptions and should not be construed as indicating or implying relative importance. Therefore, features defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise specifically defined.

[0048] According to the above background technology description,

[0049] Fractional Flow Reserve (FFR) is defined as the ratio of the maximum blood flow a diseased vessel can provide to the maximum blood flow a normal vessel can provide. It is commonly measured by measuring the ratio of arterial pressure distal to the stenosis and proximal to the stenosis under maximum hyperemia using a pressure interventional guidewire or microcatheter. This indicator is considered the "gold standard" for assessing the degree of ischemia in diseased vessels.

[0050] However, these measurement methods have limitations. First, pressure guidewires are invasive and expensive, adding to patient costs and prolonging the interventional procedure. Second, achieving maximum hyperemia requires the injection of vasodilators such as adenosine, which can be harmful to the body and unsuitable for certain patient groups (e.g., those with liver and kidney dysfunction or drug allergies).

[0051] Currently, non-invasive coronary angiography-based FFR calculation methods have been developed. This method uses CT medical images to reconstruct vascular geometry and then uses computational fluid dynamics to estimate FFR. However, CT scans are very harmful to the human body and can affect human health. In addition, CT images are static, making the blood flow data extracted from them inaccurate, which can significantly affect subsequent FFR predictions.

[0052] Therefore, in order to solve the above problems, and to improve the calculation accuracy of blood flow reserve FFR without causing losses to patients, so as to use FFR for diagnosis, treatment decision-making and prognosis evaluation of coronary heart disease, in the embodiments of the present application, an information processing method, device, electronic device and storage medium are proposed, which can be applied to a terminal device, and the terminal device can be equipped with a medical device for magnetic resonance imaging.

[0053] In one embodiment, if Figure 1 As shown, the information processing method in this application may include:

[0054] S10, obtaining the blood flow reserve fraction of the target area;

[0055] S20, obtaining information of at least two blood vessels based on multiple medical images;

[0056] S30, acquiring at least one piece of blood flow information corresponding to each piece of blood vessel information based on the blood vessel information and the medical image;

[0057] It should be noted that in this embodiment, the vascular information and blood flow information may be vascular information and blood flow information within a target region, where the target region may be a target region of a subject to be diagnosed, such as a coronary artery region of a heart. A doctor may control a medical device to perform magnetic resonance imaging of the target region to generate a corresponding medical image.

[0058] In this way, the medical device can obtain the blood flow reserve score of the target area. It can be understood that multi-phase medical images can effectively reflect the dynamic changes in blood flow.

[0059] The medical device can obtain information of at least two blood vessels based on multiple medical images.

[0060] It is understandable that each medical image may contain corresponding vascular information, wherein the vascular information may include vascular segmentation information, image information of the vascular area, etc., and may also include features extracted from vascular areas in multiple medical images through a model (such as a deep learning model, a deep neural network, etc.). The feature can specifically be the feature output by a sub-network of the above-mentioned model, wherein the sub-network can be the sub-network with the lowest error in the model.

[0061] Furthermore, at least one piece of blood flow information corresponding to each piece of blood vessel information can be obtained based on the blood vessel information and the medical image.

[0062] It is understandable that each piece of blood vessel information may correspond to at least one piece of blood flow information. For example, for a section of a blood vessel, the blood vessel information may include blood flow information at position A of the blood vessel and blood flow information at position B of the blood vessel.

[0063] The blood flow information may specifically include blood flow rate, flow velocity, and pressure.

[0064] S40: Acquire a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0065] After acquiring medical images, blood flow information, and vascular information, the medical device can obtain the Fractional Flow Reserve (FFR) of the target area based on the medical images, blood flow information, and vascular information.

[0066] It is understandable that the application of Fractional Flow Reserve (FFR) is mainly reflected in: guiding coronary revascularization, reducing unnecessary interventional treatment, improving prognosis (compared with vascular treatment guided by coronary angiography, FFR-based revascularization strategies have better short-term or long-term prognosis and lower incidence of adverse cardiac events), non-invasive evaluation and many other aspects.

[0067] Therefore, in embodiments of the present application, the medical device can obtain the blood flow reserve fraction of the target area, and further, can obtain information about at least two blood vessels in the target area and at least one blood flow information corresponding to each blood vessel information based on the medical image. Thus, the blood flow reserve fraction of the target area can be obtained based on the medical image, blood flow information, and the blood vessel information. As can be seen, compared to the prior art methods for calculating the blood flow reserve fraction, which are harmful to patients, the present application can directly calculate the blood flow reserve fraction using medical images, blood vessel information, and blood flow information. This eliminates the need for invasive testing and does not cause radiation damage to patients. It also improves the accuracy of the blood flow reserve fraction calculation, allowing the blood flow reserve fraction to guide subsequent diagnostic analysis.

[0068] In one embodiment, in the above S40, “obtaining a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information” may include:

[0069] S401, predicting the blood flow information field of the target area using a preset evaluation model based on the blood flow information, the blood vessel information, and the medical image;

[0070] S402: Calculate the blood flow reserve fraction of the acquisition target area according to the blood flow information field, wherein the blood flow reserve fraction includes a blood flow reserve fraction.

[0071] In this embodiment, after the medical device calculates the blood flow information, the blood vessel information and the medical image, it can calculate the blood flow information field of the target area based on the blood flow information, the blood vessel information and the medical image.

[0072] Specifically, for example, the medical device can input blood flow information, blood vessel information and medical images into a preset evaluation model, and the preset evaluation model can predict the blood flow information field of the target area based on the blood flow information, blood vessel information and medical images.

[0073] The blood flow information field refers to a set of data used in medical imaging technology, especially in the field of vascular imaging, to describe the spatial distribution and dynamic characteristics of blood flow within a blood vessel. This data may include the following aspects:

[0074] Hemodynamic parameters: including blood flow, blood flow resistance, blood pressure, etc. These parameters can be obtained through advanced imaging technologies such as computed tomography (CT) and magnetic resonance imaging (MRI), and can be analyzed in detail using computational fluid dynamics (CFD) methods.

[0075] High-resolution blood flow imaging: High-resolution blood flow imaging technology can clearly present the subtle structure and dynamic changes of blood flow, including laser blood flow imaging, ultrasound blood flow imaging and other methods.

[0076] Blood flow vector imaging technology: This is a non-invasive examination technology for evaluating the blood flow field state in the cardiac cavity. It can visualize the changes in hemodynamics and perform quantitative evaluation on them.

[0077] Micro-blood flow imaging technology: It can observe the tiny blood vessels and low-speed blood flow signals of the lesions without the use of contrast agents, providing more vascular and blood flow imaging details.

[0078] Color Doppler flow imaging (CDFI): A technology that uses the principle of the Doppler effect to detect blood flow information through an ultrasound probe and displays it in real time on the ultrasound image in a color-coded manner. It can intuitively show the direction and speed of blood flow.

[0079] Blood flow velocity field: refers to the spatial distribution of blood flow velocity on the radial section of the vascular cavity. During the blood flow process, due to the friction between the blood vessel wall and its own viscosity, the blood flows in layers in the radial direction, and the flow velocity of each layer is different.

[0080] Among them, the preset evaluation model in this embodiment can be a deep learning neural network.

[0081] Furthermore, the medical device can calculate the blood flow reserve fraction FFR of the target area based on the blood flow information field.

[0082] Specifically, for example, the Fractional Flow Reserve (FFR) is calculated by measuring the ratio of the maximum blood flow that can be obtained in the myocardial area supplied by the blood vessel when there is a stenotic lesion in the coronary artery to the maximum blood flow that can be obtained in the same area under normal conditions in theory.

[0083] The specific calculation formula is: FFR = P d / P a .

[0084] Where: P d It refers to the average pressure at the distal end of the coronary artery stenosis, that is, the pressure value measured at the distal end of the stenosis lesion, P a It refers to the average pressure of the aorta, that is, the pressure value measured at the proximal end (or mouth) of the stenosis. d and P a should be completely equal, so the FFR value is close to 1. When there is an obstructive lesion, P d The pressure value will decrease, and the corresponding FFR value will also decrease. A threshold can be set clinically. Usually, when the FFR value is lower than 0.80, it is believed that the obstruction will induce myocardial ischemia and surgical intervention may be required.

[0085] In one embodiment, in the above S30, “obtaining at least one piece of blood flow information corresponding to each piece of blood vessel information according to the blood vessel information and the medical image” may include:

[0086] S301, obtaining blood flow volume information of a target object based on position change information of the target object in a target area corresponding to the blood vessel information in the medical images of multiple phases, wherein the target object is a blood image in the medical image processed with a contrast agent;

[0087] S302: Acquire the blood flow information according to the position change information and blood flow volume information of the target object, wherein the blood flow information includes blood flow rate.

[0088] In this embodiment, the medical device can obtain blood flow volume information of the target object in the target area based on the position change information of the target object in the target area corresponding to the blood vessel information in multiple medical images, wherein the target object is a blood image processed by a contrast agent in the medical image.

[0089] It is understandable that contrast agents are special drugs used to help doctors observe the internal structures and abnormal lesions of the human body more clearly during imaging examinations. They are chemicals injected (or taken) into human tissues or organs to enhance the effect of imaging observation. The density of these products is higher or lower than that of the surrounding tissues, and the contrast formed is used to display images with certain instruments. There are various types of contrast agents. Based on different ingredients, uses and physical forms, doctors will choose suitable contrast agents to ensure the accuracy of the examination. In this way, by using contrast agents, the contrast of certain tissues or organs in imaging examinations can be enhanced, allowing doctors to observe and diagnose the disease more clearly, helping doctors to more accurately determine the location and range of lesions to evaluate the function of organs, such as cardiovascular function, kidney function, etc., providing important information for clinical practice.

[0090] On this basis, the medical device in this embodiment can obtain position change information of the blood flow process treated with contrast agents by comparing multiple medical images.

[0091] Furthermore, blood flow information of the target area may be acquired based on the position change information, blood flow volume information, and time information of the target object, wherein the blood flow information may specifically include blood flow rate.

[0092] In a specific embodiment, Figure 2 and Figure 3 The flow state of the contrast agent treated blood ( Figure 2 and Figure 3 The dark area in the middle blood vessels is the blood treated with contrast agent. Figure 2 The position in the Figure 3The medical device can extract blood flow information from dynamic angiographic images (e.g., arterial phase, venous phase, etc.). For example, the blood flow calculation process may include: calculating the blood flow volume based on the distance of the angiographic blood in multiple phases of medical images (i.e., the position change information in this embodiment), and then calculating the blood flow per unit time using the blood flow time, distance, and blood flow volume. In this way, this embodiment can directly obtain various blood flow-related information from multiple phases of medical images.

[0093] In addition, this embodiment can also utilize the reflection and scattering of ultrasound within blood vessels to measure the intensity and velocity of the reflected waves to calculate blood flow. Alternatively, the centerline of the main and branch vessels in each medical image can be extracted, and the length of the main and branch vessel centerline in each frame of the coronary angiography image can be calculated. A linear fit is then performed by automatically selecting multiple centerline length points corresponding to the blood filling process, and the average blood flow velocity in the main and branch vessels is calculated using the slope of the line.

[0094] In one embodiment, in S20 above, “obtaining at least two pieces of blood vessel information based on multiple medical images” may include:

[0095] S201, acquiring at least two target medical images of blood vessels through which blood flows from the multiple medical images;

[0096] S202, segmenting the blood vessel image in the medical image using a pre-trained segmentation model according to the medical image to obtain blood vessel information in the target information;

[0097] The training step of the segmentation model includes:

[0098] Acquire a training image set, wherein the training image set includes a plurality of consecutive medical training images within a preset time period;

[0099] According to the physiological tissue features corresponding to the plurality of medical training images, the plurality of medical training images are spatially transformed so that the key points of the lesions in the plurality of medical training images after the spatial transformation correspond to each other;

[0100] The initial segmentation model is trained according to the medical training images after spatial transformation to obtain a segmentation model.

[0101] In this embodiment, the medical device can deploy a pre-trained segmentation model in the cloud or locally.

[0102] In this way, the medical device can input multiple medical images into the segmentation model, and the segmentation model can segment the vascular area in the medical image to obtain vascular information, where the vascular information can include vascular morphology data, vascular diameter data, and vascular density data, etc.

[0103] Before using the segmentation model to segment the medical image, it is necessary to pre-build the segmentation model and then train the segmentation model. The training method of the segmentation model in this embodiment may specifically include: obtaining a training image set, wherein the training image set includes multiple continuous medical training images within a preset time period, and then the multiple medical training images can be spatially transformed according to the corresponding physiological tissue features in the multiple medical training images, so that the key points of the lesions in the multiple medical training images after the spatial transformation are aligned one by one.

[0104] It's worth noting that spatial transformation in this embodiment refers to the registration process between multiple medical training images. Medical image registration is the process of aligning medical images acquired at different times, using different imaging devices, or from different angles for comparison, analysis, and fusion. Specifically, medical image registration involves applying a spatial transformation (or series of spatial transformations) to one medical image so that its corresponding points on another medical image are spatially aligned. This alignment means that the same anatomical point on the human body has the same spatial location in both matched images.

[0105] In addition, the segmentation model in this embodiment may specifically include a network based on deep learning, such as:

[0106] Convolutional Neural Network (CNN): CNN can automatically extract image features and use the nonlinear characteristics of the network to perform boundary segmentation. For example, Nasr-Esfahani et al. proposed a patch-based convolutional neural network to extract blood vessels from X-ray angiography images.

[0107] Fully Convolutional Neural Network (FCN): FCN is an end-to-end pixel-level classification network that can be used for blood vessel segmentation;

[0108] U-Net: U-Net is a popular network structure for medical image segmentation, which uses symmetric multi-scale skip connections to enhance the integration of deep and shallow details;

[0109] Improved U-Net (SUNet): SUNet is improved based on the basic U-Net to improve the efficiency and performance of retinal vessel segmentation.

[0110] In this way, in this embodiment, blood vessel related data can be segmented from multiple medical images.

[0111] In one embodiment, in S20 above, “obtaining at least two pieces of blood vessel information based on multiple medical images” may include:

[0112] S203, performing noise reduction processing on the vascular images in the plurality of medical images using a pre-trained noise prediction model, to obtain vascular information in each of the medical images;

[0113] The training step of the noise prediction model includes:

[0114] Obtain vascular noise data in medical training images;

[0115] An initial noise prediction model is trained according to the blood vessel noise data to obtain a noise prediction model.

[0116] In this embodiment, the medical device can predict the blood vessel noise to obtain a noise prediction model, and then use the noise prediction model to perform noise reduction processing on a blood vessel image in a clear medical image to obtain blood vessel data.

[0117] It can be understood that the noise prediction model in this embodiment can be an EDCNN model, which is a medical image denoising model based on deep learning. It can adaptively obtain richer edge information of the input image through a designed edge enhancement module based on a trainable Sobel operator, thereby realizing end-to-end image denoising.

[0118] The noise prediction model in this embodiment can also denoise the vascular noise in the medical image based on traditional image processing techniques, such as Gaussian filtering, median filtering, bilateral filtering, histogram equalization and CLAHE (wherein histogram equalization is used to enhance image contrast, and CLAHE (contrast limited adaptive histogram equalization) is not specifically limited to this.

[0119] In one embodiment, after “obtaining the blood flow reserve fraction of the target area according to the medical image, the at least one blood flow information, and the blood vessel information” in S40 above, the following steps may also be performed:

[0120] S50, determining the lesion location of the target area according to the blood flow reserve fraction;

[0121] S60: Display the diseased blood vessel at the diseased position according to the preset mark.

[0122] In this embodiment, in combination with the above description, the medical device can determine the location of the lesion in the target area according to the blood flow reserve fraction, for example, the location of the lesioned blood vessel can be determined.

[0123] Then, the diseased blood vessels at the lesion location can be displayed according to the preset mark.

[0124] For example, the preset mark in this embodiment can be an arrow, a box, a highlight mark, etc., to remind the doctor that there is a lesion here, which requires special attention, and guide the doctor to make a diagnosis.

[0125] In one embodiment, in the above S10, “obtaining the blood flow reserve fraction of the target area” may include:

[0126] Responding to an image scanning operation, obtaining an initial medical image;

[0127] Optimizing the initial medical image according to the display characteristic parameters of the initial medical image;

[0128] According to the blood vessel characteristic parameters in the optimized initial medical image, the optimized initial medical image is cropped to obtain a medical image containing the target area.

[0129] In this embodiment, after scanning a patient, the medical device can acquire an initial medical image. The initial medical image can then be optimized based on the display characteristic parameters of the initial medical image. These display characteristic parameters can include parameters such as contrast, brightness, and clarity, thereby enhancing the quality of the initial medical image. The medical device can then crop the optimized initial medical image based on the vascular characteristic parameters within the optimized initial medical image to obtain a medical image encompassing the target region, thereby eliminating irrelevant physiological tissue and improving the efficiency of subsequent FFR calculations.

[0130] Therefore, in summary, in the embodiments of the present application, multi-phase MR medical images of a target region of the human body are acquired. Blood flow information is extracted from the multi-phase MR medical images. Combined with the multi-phase MR medical images, blood vessels are segmented to obtain vessel segmentation data. Using the MR images, vessel segmentation data, and blood flow information as input, a model is used to predict the blood flow information field, and the blood flow reserve fraction is obtained from the blood flow information field. This achieves accurate acquisition of the blood flow reserve fraction (FFR) of the target region while minimizing harm to the human body.

[0131] This embodiment also provides an information processing device, which can be integrated into a terminal medical device, for example, Figure 4 As shown, the information processing device may include:

[0132] A first acquisition module 1001 is used to acquire the blood flow reserve fraction of the target area;

[0133] A second acquisition module 1002 is configured to acquire information of at least two blood vessels based on multiple medical images;

[0134] A third acquisition module 1003 is configured to acquire at least one piece of blood flow information corresponding to each piece of blood vessel information based on the blood vessel information and the medical image;

[0135] The fourth acquisition module 1004 is configured to acquire a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0136] Optionally, the fourth obtaining module 1004 is further configured to:

[0137] determining a blood flow information field based on the medical image, the blood flow information, and the blood vessel information;

[0138] The blood flow reserve fraction of the target area is determined according to the blood flow information field.

[0139] Optionally, the fourth acquisition module is further configured to:

[0140] determining a blood flow information field according to the medical image, the at least one piece of blood flow information, and the blood vessel information;

[0141] The blood flow reserve fraction of the target area is determined according to the blood flow information field.

[0142] Optionally, the third acquisition module is further configured to:

[0143] acquiring blood flow volume information of the target object according to position change information of the target object in the target area corresponding to the blood vessel information in the multiple phases of the medical images, wherein the target object is a blood image in the medical image processed with a contrast agent;

[0144] The blood flow information is acquired according to the position change information and the blood flow volume information of the target object, wherein the blood flow information includes the blood flow rate.

[0145] Optionally, the second acquisition module is further configured to:

[0146] Acquire at least two target medical images of blood vessels through which blood flows from the multiple medical images;

[0147] According to the target medical image, the vascular images in the target medical image are segmented by a pre-trained segmentation model to obtain vascular information in each of the target medical images.

[0148] Optionally, the training of the segmentation model includes:

[0149] Acquire a training image set, wherein the training image set includes a plurality of consecutive medical training images within a preset time period;

[0150] According to the physiological tissue features corresponding to the plurality of medical training images, the plurality of medical training images are spatially transformed so that the key points of the lesions in the plurality of medical training images after the spatial transformation correspond to each other;

[0151] The initial segmentation model is trained according to the medical training images after spatial transformation to obtain a segmentation model.

[0152] Optionally, the second acquisition module is further configured to:

[0153] According to the plurality of medical images, denoising the vascular images in the plurality of medical images using a pre-trained noise prediction model to obtain vascular information in each of the medical images;

[0154] The training of the noise prediction model includes:

[0155] Obtain vascular noise data in medical training images;

[0156] An initial noise prediction model is trained according to the blood vessel noise data to obtain a noise prediction model.

[0157] Optionally, the information processing device in this application further includes:

[0158] a determination module, configured to determine a lesion location in the target area according to the blood flow reserve fraction;

[0159] The display module is used to display the diseased blood vessel at the diseased position according to a preset mark.

[0160] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0161] Accordingly, the embodiment of the present application further provides an electronic device, such as Figure 5 As shown, Figure 5 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. Those skilled in the art will understand that the vehicle structure shown in the figure does not constitute a limitation of the vehicle, and may include more or fewer components than shown, or combine certain components, or arrange the components differently.

[0162] The processor 1101 is the control center of the electronic device 1100. It connects the various parts of the entire electronic device 1100 using various interfaces and lines. By running or loading software programs and / or units stored in the memory 1102 and calling data stored in the memory 1102, it executes various functions of the electronic device 1100 and processes data, thereby monitoring the electronic device 1100 as a whole. The processor 1101 can be a processor (Central Processing Unit, CPU), a graphics processing unit (GPU), a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application.

[0163] In the embodiment of the present application, the processor 1101 in the electronic device 1100 loads instructions corresponding to one or more application processes into the memory 1102 according to the following steps, and the processor 1101 runs the application stored in the memory 1102 to implement various functions, such as:

[0164] Obtain blood flow reserve fraction of target area;

[0165] Obtain information on at least two blood vessels based on multiple medical images;

[0166] acquiring, according to the blood vessel information and the medical image, at least one piece of blood flow information corresponding to each piece of blood vessel information;

[0167] A blood flow reserve fraction of a target area is acquired according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0168] Optional, such as Figure 5 As shown, the electronic device 1100 further includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art will understand that Figure 5 The vehicle structure shown in the figure does not constitute a limitation to the vehicle, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0169] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle, which can be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect user touch operations on or near it (such as operations performed by the user using any suitable object or accessory such as a finger, stylus, etc. on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts: a touch display system and a touch controller. Among them, the touch display system detects the user's touch direction, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch display system, converts it into touch point coordinates, and then sends it to the processor 1101, and can receive commands sent by the processor 1101 and execute them. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. The processor 1101 then provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to realize the input function.

[0170] The RF circuit 1104 may be used to transmit and receive RF signals, thereby establishing wireless communication with network devices or other vehicles through wireless communication, and transmitting and receiving signals with network devices or other vehicles.

[0171] Audio circuit 1105 can be used to provide an audio interface between the user and the vehicle through a speaker and microphone. Audio circuit 1105 converts received audio data into electrical signals and transmits them to the speaker, which then converts them into sound signals for output. The microphone, on the other hand, converts collected sound signals into electrical signals, which are received by audio circuit 1105 and converted into audio data. This audio data is then output to processor 1101 for processing, then transmitted via RF circuit 1104 to, for example, another vehicle, or to memory 1102 for further processing. Audio circuit 1105 may also include an earphone jack to allow communication between an external headset and the vehicle.

[0172] The input unit 1106 may be configured to receive input digital, character information, or user feature information (such as fingerprint, iris, or facial information), and to generate keyboard, mouse, joystick, optical, or trackball signal input related to user settings and function control.

[0173] Power supply 1107 is used to supply power to various components of electronic device 1100. Optionally, power supply 1107 can be logically connected to processor 1101 via a power management device, thereby enabling the power management device to manage charging, discharging, and power consumption. Power supply 1107 can also include one or more DC or AC power supplies, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0174] although Figure 5 Not shown, the electronic device 1100 may further include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0175] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0176] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0177] To this end, an embodiment of the present application provides a computer-readable storage medium storing a plurality of computer programs. The computer programs can be loaded by a processor to execute any one of the information processing methods provided in the embodiments of the present application. The computer programs can execute the following steps of the information processing method:

[0178] Obtain blood flow reserve fraction of target area;

[0179] Obtain information on at least two blood vessels based on multiple medical images;

[0180] acquiring, according to the blood vessel information and the medical image, at least one piece of blood flow information corresponding to each piece of blood vessel information;

[0181] A blood flow reserve fraction of a target area is acquired according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

[0182] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0183] The computer-readable storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0184] Since the computer program stored in the computer-readable storage medium can execute any information processing method provided in the embodiments of the present application, the beneficial effects that can be achieved by any information processing method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0185] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0186] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0187] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0188] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0189] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0190] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0191] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated communication signals and carrier waves.

[0192] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0193] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0194] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0195] The above are merely preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, changes, and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. An information processing method, characterized in that: The method comprises: Obtain blood flow reserve fraction of target area; Obtain information on at least two blood vessels based on multiple medical images; acquiring, according to the blood vessel information and the medical image, at least one piece of blood flow information corresponding to each piece of blood vessel information; A blood flow reserve fraction of a target area is acquired according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

2. The information processing method according to claim 1, wherein: The obtaining of the blood flow reserve fraction of the target area according to the medical image, the at least one blood flow information, and the blood vessel information includes: determining a blood flow information field according to the medical image, the at least one piece of blood flow information, and the blood vessel information; The blood flow reserve fraction of the target area is determined according to the blood flow information field.

3. The information processing method according to claim 1, wherein: The acquiring, based on the blood vessel information and the medical image, at least one piece of blood flow information corresponding to each piece of blood vessel information includes: acquiring blood flow volume information of the target object according to position change information of the target object in the target area corresponding to the blood vessel information in the multiple phases of the medical images, wherein the target object is a blood image in the medical image processed with a contrast agent; The blood flow information is acquired according to the position change information and the blood flow volume information of the target object, wherein the blood flow information includes the blood flow rate.

4. The information processing method according to claim 1, wherein: The step of obtaining at least two pieces of vascular information based on multiple medical images includes: Acquire at least two target medical images of blood vessels through which blood flows from the multiple medical images; According to the target medical image, the vascular images in the target medical image are segmented by a pre-trained segmentation model to obtain vascular information in each of the target medical images.

5. The information processing method according to claim 4, characterized in that The training steps of the segmentation model include: Acquire a training image set, wherein the training image set includes a plurality of consecutive medical training images within a preset time period; According to the physiological tissue features corresponding to the plurality of medical training images, the plurality of medical training images are spatially transformed so that the key points of the lesions in the plurality of medical training images after the spatial transformation correspond to each other; The initial segmentation model is trained according to the medical training images after spatial transformation to obtain a segmentation model.

6. The information processing method according to claim 1, wherein: The step of obtaining information of at least two blood vessels based on multiple medical images further includes: According to the plurality of medical images, denoising the vascular images in the plurality of medical images using a pre-trained noise prediction model to obtain vascular information in each of the medical images; The training step of the noise prediction model includes: Obtain vascular noise data in medical training images; An initial noise prediction model is trained according to the blood vessel noise data to obtain a noise prediction model.

7. The information processing method according to any one of claims 1 to 6, characterized in that: After obtaining the blood flow reserve fraction of the target area according to the medical image, the at least one blood flow information, and the blood vessel information, the method further includes: determining a lesion location in the target area according to the blood flow reserve fraction; The diseased blood vessels at the lesion location are displayed according to the preset markers.

8. An information processing device, characterized in that include: A first acquisition module is used to obtain the blood flow reserve fraction of the target area; A second acquisition module is used to acquire information of at least two blood vessels based on multiple medical images; a third acquisition module, configured to acquire at least one piece of blood flow information corresponding to each piece of blood vessel information based on the blood vessel information and the medical image; A fourth acquisition module is configured to acquire a blood flow reserve fraction of a target area according to the medical image, the at least one piece of blood flow information, and the blood vessel information.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor is enabled to perform the steps of any one of the methods of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The method comprises a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any one of the methods of claims 1 to 7.

Images