Fractional flow reserve score determination method and device, electronic equipment and readable storage medium

Abstract

The invention discloses a fractional flow reserve determination method and device, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining at least two stages of magnetic resonance medical images of a target blood vessel based on a time sequence; based on the magnetic resonance medical images, determining blood vessel form information of the target blood vessel and change information between the magnetic resonance medical images of two adjacent periods; and determining the fractional flow reserve corresponding to the target blood vessel by combining a preset calculation model according to the at least two stages of magnetic resonance medical images, the blood vessel form information and the change information. Based on the at least two stages of magnetic resonance medical images, determining blood vessel shape information of the target blood vessel and change information between the two adjacent stages of magnetic resonance medical images, and further determining a fractional flow reserve corresponding to the target blood vessel according to the at least two stages of magnetic resonance medical images, the blood vessel shape information and the change information. The accuracy of determining the fractional flow reserve can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and particularly relates to a method, device, electronic device and readable storage medium for determining fractional flow reserve. Background Art

[0002] Fractional flow reserve is considered the "gold standard" for judging the degree of ischemia of diseased blood vessels. Currently, a non-invasive method for calculating fractional flow reserve based on CT coronary angiography has been developed.

[0003] However, CT images are static images, and the blood flow data extracted from CT images is not accurate enough, which will have a greater impact on the subsequent prediction of fractional flow reserve. Summary of the Invention

[0004] Embodiments of the present application provide a method, device, electronic device and readable storage medium for determining fractional flow reserve. Based on at least two-phase magnetic resonance medical images, the vascular morphological information of a target blood vessel and the change information between two adjacent phases of magnetic resonance medical images are determined. Furthermore, according to at least two-phase magnetic resonance medical images, vascular morphological information and change information, the fractional flow reserve corresponding to the target blood vessel is determined, which can improve the accuracy of determining fractional flow reserve.

[0005] In a first aspect, an embodiment of the present application provides a method for determining fractional flow reserve, the method comprising:

[0006] Obtain at least two-phase magnetic resonance medical images of a target blood vessel based on the time sequence;

[0007] Based on the magnetic resonance medical images, determine the vascular morphological information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images;

[0008] According to at least two-phase magnetic resonance medical images, the vascular morphological information and the change information, and in combination with a preset calculation model, determine the fractional flow reserve corresponding to the target blood vessel.

[0009] Optionally, the determining the vascular morphological information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on at least two-phase magnetic resonance medical images includes:

[0010] Perform segmentation processing on the blood vessel regions in at least two-phase magnetic resonance medical images to obtain blood vessel region images corresponding to each phase of the magnetic resonance medical images;

[0011] Perform recognition processing on each blood vessel region image to determine the vascular morphological information of the target blood vessel;

[0012] Analyze the vascular region images corresponding to two adjacent periods of the magnetic resonance medical images to determine the change information between the two adjacent periods of the magnetic resonance medical images.

[0013] Optionally, the identifying and processing each of the vascular region images to determine the vascular morphology information of the target blood vessel includes:

[0014] For each of the vascular region images, preprocess the vascular region image to obtain a target vascular region image;

[0015] Perform morphological analysis on the target vascular region image to determine the vascular morphology information of the target blood vessel.

[0016] Optionally, the change information includes vascular morphology change information and vascular blood flow change information. The analyzing the vascular region images corresponding to two adjacent periods of the magnetic resonance medical images to determine the change information between the two adjacent periods of the magnetic resonance medical images includes:

[0017] Compare the vascular region images corresponding to two adjacent periods of the magnetic resonance medical images to determine the vascular morphology change information between the two adjacent periods of the magnetic resonance medical images;

[0018] Construct a vascular fluid model based on the vascular morphology change information, and perform simulation processing based on the vascular fluid model to determine the vascular blood flow change information between the two adjacent periods of the magnetic resonance medical images.

[0019] Optionally, the determining the fractional flow reserve corresponding to the target blood vessel according to at least two periods of the magnetic resonance medical images, the vascular morphology information, and the change information, in combination with a preset calculation model, includes:

[0020] Input at least two periods of the magnetic resonance medical images, the vascular morphology information, and the change information into a preset calculation model;

[0021] Determine the reference blood flow information corresponding to the vascular lesion region in the target blood vessel through the calculation model;

[0022] Determine the fractional flow reserve corresponding to the target blood vessel through the calculation model based on the reference blood flow information.

[0023] Optionally, the determining the reference blood flow information corresponding to the vascular lesion region in the target blood vessel through the calculation model includes:

[0024] Determine the vascular lesion region in the target blood vessel through the calculation model based on at least two periods of the magnetic resonance medical images and the vascular morphology information;

[0025] Based on the vascular morphological change information and the vascular blood flow change information through the calculation model, determine the reference blood flow information corresponding to the vascular lesion area.

[0026] Optionally, the reference blood flow information includes reference blood flow volume. The determining, through the calculation model, of the fractional flow reserve corresponding to the target blood vessel based on the reference blood flow information includes:

[0027] Obtain the target blood flow volume corresponding to the target blood vessel, where the target blood flow volume is the blood flow volume when there is no lesion in the target blood vessel;

[0028] Calculate, through the calculation model, the ratio of the reference blood flow volume to the target blood flow volume to determine the fractional flow reserve corresponding to the target blood vessel.

[0029] In a second aspect, an embodiment of the present application provides a fractional flow reserve determination device, where the fractional flow reserve determination device includes:

[0030] An acquisition unit, configured to acquire at least two-phase magnetic resonance medical images of a target blood vessel based on the time sequence;

[0031] A first determination unit, configured to determine the vascular morphological information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on at least two-phase magnetic resonance medical images;

[0032] A second determination unit, configured to determine the fractional flow reserve corresponding to the target blood vessel according to at least two-phase magnetic resonance medical images, the vascular morphological information, and the change information, in combination with a preset calculation model.

[0033] In a third aspect, an embodiment of the present application further provides an electronic device, including a memory storing a computer program; a processor loads the computer program from the memory to execute the steps of any one of the fractional flow reserve determination methods provided by the embodiments of the present application.

[0034] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of any one of the fractional flow reserve determination methods provided by the embodiments of the present application.

[0035] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program, where the computer program, when executed by a processor, implements the steps in any one of the fractional flow reserve determination methods provided by the embodiments of the present application.

[0036] Adopt the solution of the application embodiment, obtain at least two-phase magnetic resonance medical images of the target blood vessel based on the time sequence; determine the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on the magnetic resonance medical images; determine the fractional flow reserve corresponding to the target blood vessel according to at least two-phase magnetic resonance medical images, the blood vessel morphology information, and the change information, in combination with a preset calculation model. Determining the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on at least two-phase magnetic resonance medical images, and then determining the fractional flow reserve corresponding to the target blood vessel according to at least two-phase magnetic resonance medical images, blood vessel morphology information, and change information can improve the accuracy of determining the fractional flow reserve. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0038] Figure 1 It is a schematic flowchart of the first embodiment of the fractional flow reserve determination method provided by the present application;

[0039] Figure 2 It is a schematic flowchart of the second embodiment of the fractional flow reserve determination method provided by the present application;

[0040] Figure 3 It is a schematic flowchart of the third embodiment of the fractional flow reserve determination method provided by the present application;

[0041] Figure 4 It is a schematic structural diagram of the fractional flow reserve determination device provided by the embodiments of the present application;

[0042] Figure 5 It is a schematic structural diagram of the fractional flow reserve determination device provided by the embodiments of the present application. Detailed Embodiments

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application. At the same time, in the description of the embodiments of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0044] The embodiments of the present application provide a method, device, electronic device, and readable storage medium for determining fractional flow reserve.

[0045] Specifically, this embodiment will be described from the perspective of a fractional flow reserve determination device, which can be specifically integrated in a fractional flow reserve determination device, that is, the fractional flow reserve determination method in the embodiments of the present application can be executed by the fractional flow reserve determination device.

[0046] The fractional flow reserve determination method provided by the embodiments of the present application can be applied to a fractional flow reserve determination device, which can be a device such as a smart terminal, a PC terminal, or a mobile terminal.

[0047] The following will be described in detail with reference to the accompanying drawings. In this embodiment, the execution entity is a fractional flow reserve determination device as an example. It should be noted that the description order of the following embodiments does not limit the preferred order of the embodiments. Although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order from that shown in the drawings.

[0048] Please refer to Figure 1 , and a first embodiment of the fractional flow reserve determination method is proposed. The first embodiment includes the following steps:

[0049] Step 101, obtain at least two-phase magnetic resonance medical images of a target blood vessel based on the time sequence;

[0050] Step 102, determine the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on the magnetic resonance medical images;

[0051] Step 103, determine the fractional flow reserve corresponding to the target blood vessel according to at least two-phase magnetic resonance medical images, the blood vessel morphology information, and the change information, in combination with a preset calculation model.

[0052] In this embodiment, when performing a medical imaging examination on a patient, the fractional flow reserve determination device acquires at least two-phase magnetic resonance medical images of the target blood vessel of the patient, and determines the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of magnetic resonance medical images based on the at least two-phase magnetic resonance medical images; inputs the at least two-phase magnetic resonance medical images, the blood vessel morphology information, and the change information into a preset calculation model to determine the fractional flow reserve corresponding to the target blood vessel. It can be understood that the fractional flow reserve is obtained by analyzing from the morphological characteristics using at least two-phase magnetic resonance medical images, blood vessel morphology information, and change information. The target blood vessel is the blood vessel in the lesion area of the patient.

[0053] It should be noted that the lesion area of the patient may include the kidney area, liver area, heart area, intestinal area, etc., which is not limited herein.

[0054] Specifically, each step is described in detail as follows:

[0055] Step 101: Acquire at least two-phase magnetic resonance medical images of the target blood vessel based on the time sequence;

[0056] In this step, the fractional flow reserve determination device acquires at least two-phase magnetic resonance medical images of the target blood vessel based on the time sequence. Specifically, the doctor first injects a contrast agent into the patient's body, and the fractional flow reserve determination device starts to collect magnetic resonance medical images of the target blood vessel. Among all the collected magnetic resonance medical images, at least two-phase magnetic resonance medical images before and after the contrast agent flows through the target blood vessel are acquired.

[0057] Step 102: Determine the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on the magnetic resonance medical images;

[0058] In this step, after obtaining at least two-phase magnetic resonance medical images, the fractional flow reserve determination device inputs the at least two-phase magnetic resonance medical images into a pre-established segmentation model, and segments the at least two-phase magnetic resonance medical images through the segmentation model to determine the target blood vessel images in each phase of magnetic resonance medical images. Then, based on the target blood vessel images, the blood vessel morphology information of the target blood vessel is determined. At the same time, two adjacent phases of magnetic resonance medical images are compared to determine the change information between two adjacent phases of magnetic resonance medical images; optionally, the fractional flow reserve determination device compares two adjacent phases of target blood vessel images to determine the change information between two adjacent phases of target blood vessel images, and this change information is the morphological change information of the target blood vessel between two adjacent phases of target blood vessel images.

[0059] Exemplarily, the fractional flow reserve determination device may input three-phase magnetic resonance medical images into a pre-established segmentation model, segment the three-phase magnetic resonance medical images respectively through the segmentation model, determine the target blood vessel images in each phase of the magnetic resonance medical images, and then determine the blood vessel morphological information of the target blood vessels based on the target blood vessel images. The three-phase magnetic resonance medical images are sorted in chronological order as the first phase, the second phase, and the third phase. Among them, the first phase and the second phase are two adjacent phases of magnetic resonance medical images, and the second phase and the third phase are two adjacent phases of magnetic resonance medical images. The fractional flow reserve determination device compares the first phase and the second phase to determine the change information between the first phase and the second phase, and compares the second phase and the third phase to determine the change information between the second phase and the third phase.

[0060] Step 103, according to at least two phases of the magnetic resonance medical images, the blood vessel morphological information, and the change information, and in combination with a preset calculation model, determine the fractional flow reserve corresponding to the target blood vessel.

[0061] In this step, the fractional flow reserve determination device inputs at least two phases of magnetic resonance medical images, blood vessel morphological information, and change information into a preset calculation model. The calculation model analyzes based on the magnetic resonance medical images, blood vessel morphological information, and change information, and then determines the fractional flow reserve corresponding to the target blood vessel. Among them, the fractional flow reserve (FFR) is defined as the ratio of the maximum blood flow that the diseased blood vessel can provide to the maximum blood flow that the blood vessel can provide when it is completely normal.

[0062] Exemplarily, the fractional flow reserve determination device may input three-phase magnetic resonance medical images into a pre-established segmentation model, segment the three-phase magnetic resonance medical images respectively through the segmentation model, determine the target blood vessel images in each phase of the magnetic resonance medical images, and then determine the blood vessel morphological information of the target blood vessels based on each phase of the target blood vessel images. The three-phase target blood vessel images are sorted in chronological order as the first phase, the second phase, and the third phase. Among them, the first phase and the second phase are two adjacent phases of the target blood vessel images, and the second phase and the third phase are two adjacent phases of the target blood vessel images. The fractional flow reserve determination device compares the first phase and the second phase to determine the change information in the morphology of the target blood vessel between the first phase and the second phase, and compares the second phase and the third phase to determine the change information in the morphology of the target blood vessel between the second phase and the third phase. The calculation model outputs the fractional flow reserve corresponding to the target blood vessel according to the three-phase magnetic resonance medical images, the blood vessel morphological information of the target blood vessel in each phase of the target blood vessel images, the change information in the morphology of the target blood vessel between the first phase and the second phase, and the change information in the morphology of the target blood vessel between the second phase and the third phase.

[0063] The fractional flow reserve determination device of this embodiment acquires at least two - phase magnetic resonance medical images of a target blood vessel based on the time sequence; determines the blood vessel morphological information of the target blood vessel and the change information between two adjacent - phase magnetic resonance medical images based on the magnetic resonance medical images; and determines the fractional flow reserve corresponding to the target blood vessel according to the at least two - phase magnetic resonance medical images, the blood vessel morphological information, and the change information, in combination with a preset calculation model. Determining the blood vessel morphological information of the target blood vessel and the change information between two adjacent - phase magnetic resonance medical images based on at least two - phase magnetic resonance medical images, and then determining the fractional flow reserve corresponding to the target blood vessel according to the at least two - phase magnetic resonance medical images, the blood vessel morphological information, and the change information can improve the accuracy of determining the fractional flow reserve.

[0064] Further, referring to Figure 2 , a second embodiment of the fractional flow reserve determination method is proposed. The difference between the second embodiment and the first embodiment is that the step of determining the blood vessel morphological information of the target blood vessel and the change information between two adjacent - phase magnetic resonance medical images based on at least two - phase magnetic resonance medical images includes:

[0065] Step 201: Perform segmentation processing on the blood vessel regions in at least two - phase magnetic resonance medical images to obtain the blood vessel region images corresponding to each phase of the magnetic resonance medical images;

[0066] In this step, the fractional flow reserve determination device includes a pre - established segmentation model. The segmentation model is used to perform segmentation processing on the blood vessel regions in at least two - phase magnetic resonance medical images to obtain the blood vessel region images corresponding to each phase of the magnetic resonance medical images. Exemplarily, the fractional flow reserve determination device uses an algorithm based on image gradients or a convolutional neural network (CNN) for deep - learning training to identify the blood vessel regions in the magnetic resonance medical images, and then segment the blood vessel region images corresponding to each phase of the magnetic resonance medical images.

[0067] Step 202: Perform recognition processing on each blood vessel region image to determine the blood vessel morphological information of the target blood vessel;

[0068] In this step, the fractional flow reserve determination device performs recognition processing on each blood vessel region image to determine the blood vessel morphological information of the target blood vessel. Specifically, the fractional flow reserve determination device pre - processes each blood vessel region image, and the pre - processing includes noise removal, contrast enhancement, etc.; the fractional flow reserve determination device processes each pre - processed blood vessel region image based on a blood vessel extraction algorithm, accurately extracts the contour of the target blood vessel, and performs morphological analysis on the contour of the target blood vessel in each blood vessel region image to determine the blood vessel morphological information of the target blood vessel in each blood vessel region image.

[0069] In one embodiment, step 202 may include steps 2021 to 2022, specifically:

[0070] Step 2021, for each of the vascular region images, preprocess the vascular region image to obtain a target vascular region image;

[0071] In this step, for each vascular region image, the fractional flow reserve determination device preprocesses the vascular region image to obtain a target vascular region image. Specifically, 1. Preprocessing of vascular region images: Noise removal: Use filtering methods (such as Gaussian filtering, median filtering) to reduce noise in the image; Contrast enhancement: To display blood vessels more clearly, histogram equalization or other enhancement processes can be performed on the image; Image segmentation: Use segmentation techniques (such as threshold segmentation, region growing method, edge detection method, etc.) to extract the vascular region from the background. 2. Vessel extraction and identification: Extraction algorithm: Apply computer vision and image processing techniques, and use methods such as edge detection (such as Canny operator), region growing, active contour model (snake model), etc. to accurately extract the contour of the blood vessel. Vessel segmentation: For complex images, multi-level segmentation of the vascular region may be required. For example, use algorithms based on image gradients or convolutional neural networks (CNNs) for deep learning training to identify vascular regions.

[0072] Step 2022, perform morphological analysis on the target vascular region image to determine the vascular morphological information of the target blood vessel.

[0073] In this step, the fractional flow reserve determination device performs morphological analysis on the target vascular region image to determine the vascular morphological information of the target blood vessel. Specifically, the fractional flow reserve determination device performs morphological analysis on each vascular region image to determine the vascular morphological information of the target blood vessel, including: Vessel diameter: Measure the cross-sectional size of the blood vessel. The diameter of the blood vessel can be estimated by comparing the pixel density of the blood vessel part and its adjacent region in the image. Vessel length: Calculate the length of the blood vessel by tracing the path or direction of the blood vessel. Branch structure: Extract the branch points and branch angles of the blood vessel to judge the complexity of the blood vessel. Vessel curvature: Use mathematical methods (such as curve fitting) to calculate the curvature of the blood vessel. Path and direction of the blood vessel: Analyze the direction of the blood vessel to judge whether there are abnormalities such as stenosis, distortion, and fracture.

[0074] Step 203, analyze the vascular region images corresponding to two adjacent phases of the magnetic resonance medical images to determine the change information between the two adjacent phases of the magnetic resonance medical images.

[0075] In this step, the fractional flow reserve determination device analyzes the vascular region images corresponding to two adjacent phases of magnetic resonance medical images to determine the change information between the two adjacent phases of magnetic resonance medical images. Specifically, the analysis of the vascular region images of two adjacent phases mainly includes steps such as image registration, vascular region extraction, morphological feature extraction, change quantification, lesion detection, and change visualization. Through these techniques, the changes in blood vessels can be quantitatively analyzed to determine the change information between two adjacent phases of magnetic resonance medical images.

[0076] In one embodiment, the change information includes vascular morphological change information and vascular blood flow change information. Step 203 may include steps 2031 to 2032. Specifically:

[0077] Step 2031, compare the vascular region images corresponding to two adjacent phases of the magnetic resonance medical images to determine the vascular morphological change information between the two adjacent phases of the magnetic resonance medical images;

[0078] In this step, the fractional flow reserve determination device compares the vascular region images corresponding to two adjacent phases of magnetic resonance medical images to determine the vascular morphological change information between the two adjacent phases of magnetic resonance medical images. Specifically, the fractional flow reserve determination device performs image registration on the vascular region images corresponding to two adjacent phases of magnetic resonance medical images. Before analyzing the vascular changes, it is necessary to first ensure that the two-phase images can be correctly aligned. This process is called image registration, and its purpose is to align the same anatomical region in the two-phase images. The specific registration method can be: Rigid registration: If the displacement between the two-phase images is small, rigid registration (such as rotation, translation, etc.) can be used. Commonly used methods include the mutual information method (Mutual Information), the gradient method, etc. Non-rigid registration: If there are large deformations in the two-phase images (for example, deformations of blood vessels caused by tumors, thrombi, etc.), non-rigid registration methods such as B-spline registration and Demons algorithm can be used. The fractional flow reserve determination device performs comparative analysis based on the registered vascular region images of two adjacent phases to determine the vascular morphological change information between the two adjacent phases of magnetic resonance medical images, where the vascular morphological change information includes: changes in vascular diameter, changes in vascular length, changes in vascular branches, changes in vascular contour, etc.

[0079] Step 2032, construct a vascular fluid model based on the vascular morphological change information, and perform simulation processing based on the vascular fluid model to determine the vascular blood flow change information between the two adjacent phases of the magnetic resonance medical images.

[0080] In this step, the fractional flow reserve determination device constructs a vascular fluid model based on the vascular morphological change information, performs simulation processing based on the vascular fluid model, and determines the vascular blood flow change information between two adjacent phases of magnetic resonance medical images. Specifically, 1. The construction of the vascular morphological change model is a prerequisite for simulating blood flow. By segmenting the vascular region, vascular geometric information is extracted from two-phase images and converted into a three-dimensional model. The specific steps are as follows: Vascular segmentation: Use threshold segmentation, edge detection, or deep learning-based segmentation methods (such as U-Net) to extract the vascular contour. Three-dimensional reconstruction: Stack the segmented two-dimensional vascular slices to construct a three-dimensional vascular model, usually using medical image processing software (such as ITK-SNAP, 3D Slicer) or custom programming methods. Geometric feature extraction: Analyze the geometric changes of the blood vessels by extracting morphological features such as the diameter, curvature, and branch angle of the blood vessels. 2. Based on the vascular geometric model, a numerical simulation model of blood flow is constructed; the fluid model usually uses the Navier-Stokes equation to describe the dynamic characteristics of blood flow; the specific steps are as follows: Hydrodynamic model: Blood flow is usually modeled as an incompressible Newtonian fluid; Blood characteristics: Blood is regarded as having certain viscosity and elastic characteristics, and it is usually considered that blood is a non-Newtonian fluid. The Carreau model, etc., can be used to describe the shear thinning behavior of blood; Model of the blood vessel wall: The stiffness, elasticity, etc. of the blood vessel wall affect blood flow, and an elastic model (such as linear elasticity, hyperelasticity, etc.) is usually used to simulate the response of the blood vessel wall; Boundary conditions: Set the boundary conditions at the inlet and outlet, such as blood flow velocity, pressure, etc. The inlet is usually defined by a pulsatile flow velocity waveform (such as the cardiac cycle), and the outlet can be set to a pressure condition or zero pressure. 3. After constructing the vascular fluid model, use the computational fluid dynamics (CFD) method to numerically simulate blood flow. Commonly used software tools include ANSYS Fluent, COMSOL Multiphysics, OpenFOAM, etc.; the specific steps are as follows: Mesh generation: Discretize the vascular model to generate a suitable computational mesh; the refinement degree of the mesh should be able to fully capture the details in the blood vessels (such as small blood vessel branches, blood flow changes, etc.); Numerical solution: Use numerical methods (such as the finite element method, finite volume method) to solve the fluid equation to obtain the flow characteristics of blood in the blood vessels, including the velocity field, pressure field, shear stress, etc.; Time step selection: Considering the periodic change of blood flow, usually select a suitable time step for dynamic simulation. 4. By comparing the vascular geometry and blood flow models of two adjacent phases, analyze the impact of vascular morphological changes on blood flow; the specific steps are as follows: Blood flow velocity change: Compare the blood flow velocity fields in the vascular regions of the two-phase images to determine the impact of morphological changes such as vascular dilation, contraction, and stenosis on blood flow. Blood pressure change: Analyze the changes in blood pressure in the blood vessels, especially in the regions of vascular contraction or dilation, to see if there are significant pressure fluctuations.Shear stress change: The shear stress in blood vessels is crucial for the health of the vessel wall. Analyze whether there are significant changes in the shear stress on the inner wall of the blood vessel, especially in the area of vascular lesions. Flow pattern change: Analyze whether there are changes in flow patterns such as turbulence and backflow in the blood flow, which usually occur at blood vessel dilations, bifurcations, or stenoses.

[0081] For each of the vascular region images, the blood flow reserve fraction determination device in this implementation preprocesses the vascular region image to obtain a target vascular region image; performs morphological analysis on the target vascular region image to determine the vascular morphological information of the target blood vessel. This can improve the accuracy of determining the vascular morphological information. Compare the vascular region images corresponding to two adjacent phases of the magnetic resonance medical images to determine the vascular morphological change information between the two adjacent phases of the magnetic resonance medical images; construct a vascular fluid model based on the vascular morphological change information, and perform simulation processing based on the vascular fluid model to determine the vascular blood flow change information between the two adjacent phases of the magnetic resonance medical images. This can improve the accuracy of determining the change information between two adjacent phases of the magnetic resonance medical images. Furthermore, it helps to improve the accuracy of subsequently determining the blood flow reserve fraction corresponding to the target blood vessel based on at least two phases of the magnetic resonance medical images, the vascular morphological information, and the change information.

[0082] Further, referring to Figure 3 , a third embodiment of the blood flow reserve fraction determination method is proposed. The method of determining the blood flow reserve fraction corresponding to the target blood vessel by combining the at least two phases of the magnetic resonance medical images, the vascular morphological information, and the change information with a preset calculation model includes:

[0083] Step 301, input the at least two phases of the magnetic resonance medical images, the vascular morphological information, and the change information into a preset calculation model;

[0084] In this step, the fractional flow reserve determination device inputs at least two phases of magnetic resonance medical images, vascular morphology information, and change information into a preset calculation model. Exemplarily, the fractional flow reserve determination device may input three-phase magnetic resonance medical images into a pre-established segmentation model, and segment the three-phase magnetic resonance medical images through the segmentation model respectively to determine the target vascular images in each phase of the magnetic resonance medical images. Then, based on the target vascular images in each phase, the vascular morphology information of the target blood vessel is determined. The target vascular images in the three phases are sorted in chronological order as the first phase, the second phase, and the third phase. Among them, the first phase and the second phase are adjacent target vascular images, and the second phase and the third phase are adjacent target vascular images. The fractional flow reserve determination device compares the first phase and the second phase to determine the vascular morphology change information and vascular blood flow change information between the first phase and the second phase, compares the second phase and the third phase to determine the vascular morphology change information and vascular blood flow change information between the second phase and the third phase. Then, the three-phase magnetic resonance medical images, the vascular morphology information of the target blood vessel in each target vascular image, the vascular morphology change information and vascular blood flow change information between the first phase and the second phase, and the vascular morphology change information and vascular blood flow change information between the second phase and the third phase are input into the preset calculation model.

[0085] Step 302, determine the reference blood flow information corresponding to the vascular lesion area in the target blood vessel through the calculation model;

[0086] In this step, the fractional flow reserve determination device analyzes at least two phases of magnetic resonance medical images, vascular morphology information, and change information through the calculation model to determine the reference blood flow information corresponding to the vascular lesion area in the target blood vessel.

[0087] In one embodiment, step 302 may include steps 3021 to 3022, specifically:

[0088] Step 3021, determine the vascular lesion area in the target blood vessel through the calculation model based on at least two phases of the magnetic resonance medical images and the vascular morphology information;

[0089] In this step, the fractional flow reserve determination device determines the vascular lesion area in the target blood vessel through the calculation model based on at least two phases of magnetic resonance medical images and vascular morphology information. Exemplarily, the calculation model extracts the vascular geometric features in the three-phase images through an image processing method based on the three-phase magnetic resonance medical images and the vascular morphology information corresponding to each phase, compares the changes in vascular diameter, curvature, length, etc. at different time points, and combines the blood flow simulation results to analyze the changes in local flow velocity, pressure, and shear stress, and locates the areas with restricted or abnormal blood flow. Common methods include using the flow velocity field, pressure field, and shear stress field to identify the vascular lesion area.

[0090] Step 3022: Based on the blood vessel morphological change information and the blood vessel blood flow change information, determine the reference blood flow information corresponding to the blood vessel lesion area through the calculation model.

[0091] In this step, the fractional flow reserve determination device determines the reference blood flow information corresponding to the blood vessel lesion area through the calculation model based on the blood vessel morphological change information and the blood vessel blood flow change information. Specifically, after determining the blood vessel lesion area, detailed blood flow simulation needs to be performed according to the blood vessel geometric changes and blood flow changes. This is usually accomplished through numerical simulation, using CFD (Computational Fluid Dynamics) technology to simulate the blood flow characteristics and combining with actual physiological parameters to calculate the blood flow information. The specific steps are as follows: Three-dimensionally reconstruct the geometric shape of the blood vessel to ensure that the lesion area (such as stenosis, dilation, etc.) can be accurately described. Extract the geometric features of the lesion area from the MRI image data and adjust them in the model. After determining the lesion area, use hydrodynamic equations (such as the Navier-Stokes equation) to perform blood flow simulation to obtain parameters such as blood flow velocity, pressure distribution, and shear stress. For the blood flow simulation, a non-Newtonian fluid model can be selected because the blood flow characteristics change at different shear rates. The calculated flow velocity field, pressure field, and shear stress field help to reveal the fluid characteristics of the lesion area, and then determine the reference blood flow information corresponding to the blood vessel lesion area.

[0092] Step 303: Based on the reference blood flow information, determine the fractional flow reserve corresponding to the target blood vessel through the calculation model.

[0093] In this step, the fractional flow reserve determination device determines the fractional flow reserve corresponding to the target blood vessel through the calculation model based on the reference blood flow information.

[0094] In one embodiment, the reference blood flow information includes the reference blood flow volume, and step 303 may include steps 3031 to 3032. Specifically:

[0095] Step 3031: Obtain the target blood flow volume corresponding to the target blood vessel, where the target blood flow volume is the blood flow volume when there is no lesion in the target blood vessel.

[0096] In this step, the fractional flow reserve determination device obtains the target blood flow volume corresponding to the target blood vessel, where the target blood flow volume is the blood flow volume when there is no lesion in the target blood vessel. Specifically, the fractional flow reserve determination device stores in advance the blood flow volume when there is no lesion in the blood vessels of each part of the human body. When the fractional flow reserve determination device determines the target blood vessel, it can query and obtain the target blood flow volume corresponding to the target blood vessel from the pre-stored database.

[0097] Step 3032: Calculate the ratio of the reference blood flow and the target blood flow according to the calculation model, and determine the fractional flow reserve corresponding to the target blood vessel.

[0098] In this step, after determining the reference blood flow and the target blood flow of the target blood vessel, the fractional flow reserve determination device calculates the ratio of the reference blood flow and the target blood flow, and determines this ratio as the fractional flow reserve corresponding to the target blood vessel. Specifically, fractional flow reserve = reference blood flow / target blood flow.

[0099] The fractional flow reserve determination device of this embodiment inputs at least two periods of the magnetic resonance medical images, the blood vessel morphology information, and the change information into a preset calculation model; determines the reference blood flow information corresponding to the blood vessel lesion area in the target blood vessel through the calculation model; and determines the fractional flow reserve corresponding to the target blood vessel based on the reference blood flow information through the calculation model. Determining the fractional flow reserve corresponding to the target blood vessel through image analysis avoids using invasive methods to determine the fractional flow reserve, and at the same time can improve the accuracy of the determined fractional flow reserve.

[0100] This embodiment also provides a fractional flow reserve determination device, which can be specifically integrated in fractional flow reserve determination devices such as smart terminals, PC terminals, and mobile terminals. As Figure 4 shown, the fractional flow reserve determination device may include:

[0101] An acquisition unit 1001, configured to acquire at least two periods of magnetic resonance medical images of a target blood vessel based on the time sequence;

[0102] A first determination unit 1002, configured to determine the blood vessel morphology information of the target blood vessel and the change information between two adjacent periods of the magnetic resonance medical images based on at least two periods of the magnetic resonance medical images;

[0103] A second determination unit 1003, configured to determine the fractional flow reserve corresponding to the target blood vessel according to at least two periods of the magnetic resonance medical images, the blood vessel morphology information, and the change information, in combination with a preset calculation model.

[0104] In an optional example, the first determination unit is further configured to:

[0105] Perform segmentation processing on the blood vessel regions in at least two periods of the magnetic resonance medical images to obtain blood vessel region images corresponding to each period of the magnetic resonance medical images;

[0106] Perform recognition processing on each of the blood vessel region images to determine the blood vessel morphology information of the target blood vessel;

[0107] Analyze the vascular region images corresponding to two adjacent periods of the magnetic resonance medical images to determine the change information between the two adjacent periods of the magnetic resonance medical images.

[0108] In an optional example, the first determination unit is further configured to:

[0109] For each of the vascular region images, preprocess the vascular region image to obtain a target vascular region image;

[0110] Perform morphological analysis on the target vascular region image to determine the vascular morphological information of the target blood vessel.

[0111] In an optional example, the first determination unit is further configured to:

[0112] Compare the vascular region images corresponding to two adjacent periods of the magnetic resonance medical images to determine the vascular morphological change information between the two adjacent periods of the magnetic resonance medical images;

[0113] Construct a vascular fluid model based on the vascular morphological change information, and perform simulation processing based on the vascular fluid model to determine the vascular blood flow change information between the two adjacent periods of the magnetic resonance medical images. In an optional example, the second determination unit is further configured to:

[0114] Input at least two periods of the magnetic resonance medical images, the vascular morphological information, and the change information into a preset calculation model;

[0115] Determine the reference blood flow information corresponding to the vascular lesion region in the target blood vessel through the calculation model;

[0116] Determine the fractional flow reserve corresponding to the target blood vessel through the calculation model based on the reference blood flow information.

[0117] In an optional example, the second determination unit is further configured to:

[0118] Determine the vascular lesion region in the target blood vessel through the calculation model based on at least two periods of the magnetic resonance medical images and the vascular morphological information;

[0119] Determine the reference blood flow information corresponding to the vascular lesion region through the calculation model based on the vascular morphological change information and the vascular blood flow change information.

[0120] In an optional example, the second determination unit is further configured to:

[0121] Obtain the target blood flow corresponding to the target blood vessel, where the target blood flow is the blood flow when there is no lesion in the target blood vessel;

[0122] Calculating a ratio of the reference blood flow rate to the target blood flow rate through the calculation model, and determining a fractional flow reserve corresponding to the target blood vessel.

[0123] Adopting the solution of this embodiment, obtaining at least two-phase magnetic resonance medical images of a target blood vessel based on a time sequence; determining blood vessel morphology information of the target blood vessel and change information between two adjacent phases of the magnetic resonance medical images based on the magnetic resonance medical images; and determining a fractional flow reserve corresponding to the target blood vessel according to the at least two-phase magnetic resonance medical images, the blood vessel morphology information, and the change information by combining with a preset calculation model. Determining the blood vessel morphology information of the target blood vessel and the change information between two adjacent phases of the magnetic resonance medical images based on the at least two-phase magnetic resonance medical images, and then determining the fractional flow reserve corresponding to the target blood vessel according to the at least two-phase magnetic resonance medical images, the blood vessel morphology information, and the change information can improve the accuracy of determining the fractional flow reserve.

[0124] Correspondingly, an embodiment of the present application further provides a fractional flow reserve determination device, as Figure 5 shown, Figure 5 is a schematic structural diagram of the fractional flow reserve determination device provided by the embodiment of the present application. The fractional flow reserve determination 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. Among them, the processor 1101 is electrically connected to the memory 1102. Those skilled in the art can understand that the structural diagram of the fractional flow reserve determination device shown in the figure does not constitute a limitation on the fractional flow reserve determination device, and may include more or fewer components than shown in the figure, or combine some components, or arrange different components.

[0125] The processor 1101 is the control center of the fractional flow reserve determination device 1100, connecting various parts of the entire fractional flow reserve determination device 1100 through various interfaces and lines, and executing various functions of the fractional flow reserve determination device 1100 and processing data by running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, so as to perform overall monitoring of the fractional flow reserve determination device 1100. The processor 1101 may be a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc., and may implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0126] In the embodiment of the present application, the processor 1101 in the fractional flow reserve determination device 1100 loads the instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 runs the application programs stored in the memory 1102 to implement various functions. For specific implementation, reference can be made to the previous embodiments, which will not be elaborated here.

[0127] Optionally, as Figure 5 shown, the fractional flow reserve determination device 1100 further includes: a touch display 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 display 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 can understand that Figure 5 the structure of the fractional flow reserve determination device shown in

[0128] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by a 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, as well as various graphical user interfaces of the fractional flow reserve determination device. These graphical user interfaces 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), an organic light-emitting diode (OLED), etc. The touch panel can be used to collect touch operations of the user on or near it (such as operations of the user using any suitable object or accessory such as a finger or a stylus on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel can include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the touch position of the user and 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 detection device, converts it into contact coordinates, and then sends it to the processor 1101, and can receive and execute the commands sent by the processor 1101. The touch panel can cover the display panel. After 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. Subsequently, the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In the embodiments of the present application, the touch panel and the display panel can be integrated into the touch display screen 1103 to implement input and output functions. However, in some embodiments, the touch panel and the touch panel can be implemented as two independent components to implement input and output functions. That is, the touch display screen 1103 can also be used as part of the input unit 1106 to implement the input function.

[0129] The radio frequency circuit 1104 can be used to transmit and receive radio frequency signals to establish wireless communication with a network device or other fractional flow reserve determination devices through wireless communication, and transmit and receive signals with the network device or other fractional flow reserve determination devices.

[0130] The audio circuit 1105 can be used to provide an audio interface between the user and the fractional flow reserve determination device through a speaker and a microphone. The audio circuit 1105 can convert the received audio data into an electrical signal and transmit it to the speaker, which converts it into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and then converted into audio data. After the audio data is output and processed by the processor 1101, it is sent via the radio frequency circuit 1104 to, for example, another fractional flow reserve determination device, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earphone jack to provide communication between the peripheral earphone and the fractional flow reserve determination device.

[0131] The input unit 1106 can be used to receive input digital, character information or user characteristic information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0132] The power supply 1107 is used to supply power to each component of the fractional flow reserve determination device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management device, so as to implement functions such as management of charging, discharging, and power consumption management through the power management device. The power supply 1107 may also include any components such as one or more DC or AC power supplies, recharge devices, power failure detection circuits, power converters or inverters, and power status indicators.

[0133] Although Figure 5 not shown in the figure, the fractional flow reserve determination device 1100 may also include a camera, a sensor, a Wi-Fi module, a Bluetooth module, etc., which will not be elaborated here.

[0134] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0135] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. The instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0136] Therefore, an embodiment of the present application provides a computer-readable storage medium, in which multiple computer programs are stored. The computer programs can be loaded by a processor to execute any one of the fractional flow reserve determination methods provided by the embodiments of the present application. The computer programs can execute the fractional flow reserve determination method. For specific implementation, reference can be made to the previous embodiments, which will not be elaborated here.

[0137] Among them, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, optical disc, etc.

[0138] Since the computer program stored in the computer-readable storage medium can execute any one of the fractional flow reserve determination methods provided in the embodiments of the present application, the beneficial effects achievable by any one of the fractional flow reserve determination methods provided in the embodiments of the present application can be realized. For details, see the previous embodiments and will not be elaborated here.

[0139] According to one aspect of the present application, a computer program product or a computer program is further provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the fractional flow reserve determination device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the fractional flow reserve determination device executes the methods provided in various optional implementations in the above embodiments.

[0140] In the above embodiments of the fractional flow reserve determination device, computer-readable storage medium, fractional flow reserve determination device, and computer program product, the descriptions of each embodiment have their own emphases. For parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes and the beneficial effects that can be brought by the above-described fractional flow reserve determination device, computer-readable storage medium, computer program product, fractional flow reserve determination device and their corresponding units can refer to the description of the fractional flow reserve determination method in the above embodiments, and will not be elaborated here specifically.

[0141] The above has introduced in detail a fractional flow reserve determination method, device, electronic device, readable storage medium, and computer program product provided by the embodiments of the present application. Specific examples are used in this article to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for determining blood flow reserve fraction, characterized in that: The method for determining the blood flow reserve fraction comprises: Acquire at least two phases of magnetic resonance medical images of the target blood vessel based on a time sequence; Based on the magnetic resonance medical image, determining the vascular morphology information of the target blood vessel and the change information between the magnetic resonance medical images of two adjacent periods; The blood flow reserve fraction corresponding to the target blood vessel is determined based on at least two phases of the magnetic resonance medical images, the blood vessel morphology information and the change information in combination with a preset calculation model.

2. The method for determining blood flow reserve fraction according to claim 1, characterized in that: The determining, based on the magnetic resonance medical images of at least two phases, the vascular morphology information of the target blood vessel and the change information between the magnetic resonance medical images of two adjacent phases comprises: Segmenting the blood vessel regions in the magnetic resonance medical images of at least two phases to obtain blood vessel region images corresponding to the magnetic resonance medical images of each phase; Recognize and process each of the blood vessel region images to determine the blood vessel morphology information of the target blood vessel; The blood vessel region images corresponding to the magnetic resonance medical images of two adjacent periods are analyzed to determine the change information between the magnetic resonance medical images of two adjacent periods.

3. The method for determining blood flow reserve fraction according to claim 2, characterized in that: The step of performing image recognition processing on each of the blood vessel regions to determine the blood vessel morphology information of the target blood vessel includes: For each of the blood vessel region images, preprocessing the blood vessel region image to obtain a target blood vessel region image; Performing morphological analysis on the target blood vessel region image to determine the blood vessel morphological information of the target blood vessel.

4. The method for determining blood flow reserve fraction according to claim 2, characterized in that: The change information includes blood vessel morphology change information and blood vessel blood flow change information. The blood vessel region images corresponding to the magnetic resonance medical images of two adjacent periods are analyzed to determine the change information between the magnetic resonance medical images of two adjacent periods, including: Comparing the vascular region images corresponding to the magnetic resonance medical images of two adjacent periods to determine the vascular morphology change information between the magnetic resonance medical images of two adjacent periods; A vascular fluid model is constructed based on the vascular morphology change information, and simulation processing is performed based on the vascular fluid model to determine the vascular blood flow change information between the magnetic resonance medical images of two adjacent periods.

5. The method for determining blood flow reserve fraction according to any one of claims 1 to 4, characterized in that: The step of determining the blood flow reserve fraction corresponding to the target blood vessel based on the magnetic resonance medical images of at least two phases, the blood vessel morphology information and the change information in combination with a preset calculation model includes: Inputting at least two phases of the magnetic resonance medical images, the vascular morphology information and the change information into a preset calculation model; Determining reference blood flow information corresponding to the vascular lesion area in the target blood vessel by using the calculation model; The blood flow reserve fraction corresponding to the target blood vessel is determined by the calculation model based on the reference blood flow information.

6. The method for determining blood flow reserve fraction according to claim 5, characterized in that: The determining, by the calculation model, reference blood flow information corresponding to the vascular lesion area in the target blood vessel comprises: Determine the vascular lesion area in the target blood vessel based on the magnetic resonance medical images of at least two phases and the blood vessel morphology information by using the calculation model; The reference blood flow information corresponding to the vascular lesion area is determined by the calculation model based on the vascular morphology change information and the vascular blood flow change information.

7. The method for determining blood flow reserve fraction according to claim 5, characterized in that: The reference blood flow information includes a reference blood flow rate, and determining the blood flow reserve fraction corresponding to the target blood vessel based on the reference blood flow information by using the calculation model includes: Acquiring a target blood flow corresponding to the target blood vessel, wherein the target blood flow is the blood flow when no lesion exists in the target blood vessel; The blood flow reserve fraction corresponding to the target blood vessel is determined by calculating the ratio of the reference blood flow to the target blood flow through the calculation model.

8. A device for determining blood flow reserve fraction, characterized in that: The blood flow reserve fraction determination device comprises: An acquisition unit, configured to acquire at least two phases of magnetic resonance medical images of the target blood vessel based on a time sequence; A first determining unit is used to determine the vascular morphology information of the target blood vessel and the change information between the magnetic resonance medical images of two adjacent periods based on the magnetic resonance medical images of at least two periods; The second determination unit is used to determine the blood flow reserve fraction corresponding to the target blood vessel based on the magnetic resonance medical images of at least two phases, the blood vessel morphology information and the change information in combination with a preset calculation model.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program; the processor loads the computer program from the memory to execute the steps of the method for determining the blood flow reserve fraction according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps of the method for determining blood flow reserve fraction according to any one of claims 1 to 7.

Images