Aortic dissection non-invasive blood flow rate measurement method, system, device and storage medium

Abstract

The application relates to the technical field of medical image processing, and relates to an aortic dissection noninvasive blood flow velocity measurement method, system, device and storage medium; the aortic dissection noninvasive blood flow velocity measurement method comprises the following steps: acquiring four-dimensional computed tomography angiography image data to be detected; analyzing the four-dimensional computed tomography angiography image data by using an optical flow method to obtain an aortic blood flow velocity field; analyzing the four-dimensional computed tomography angiography image data, segmenting an aortic image and extracting a center line of the aorta; determining the flow area of each position of the aorta according to the aortic image and the center line of the aorta; determining the instantaneous flow velocity of each position of the aorta according to the aortic blood flow velocity field and the flow area of each position of the aorta, and obtaining a blood flow velocity measurement result. The application can accurately identify the blood flow velocity of the aorta.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, and in particular to an aortic dissection non-invasive blood flow rate measurement method, system, device and storage medium. BACKGROUND

[0002] Aortic dissection (AD) is a serious cardiovascular disease, mainly due to the tear of the intima of the aorta, leading to the entry of blood into different layers of the aortic wall, forming a dissection. The formation of the intimal flap is a manifestation of the dissection, which is usually caused by the pressure change of the blood between the intima and the adventitia of the dissection. Aortic dissection is a kind of aortic disease with sudden onset and extremely high mortality. Patients may feel severe chest pain, back pain, and even syncope, and the consequences can be very serious if not treated in time.

[0003] Currently, the clinical classification of aortic dissection is mainly based on Stanford classification, and aortic dissection is divided into type A aortic dissection (TAAD) and type B aortic dissection (TBAD). Type A aortic dissection involving the ascending aorta is the most urgent and fatal type, and the dissection involving the ascending aorta is extremely easy to cause pericardial tamponade, aortic valve insufficiency, coronary artery involvement or poor cerebral perfusion, etc. Severe complications, the first choice is open surgical repair; type B aortic dissection does not involve the ascending aorta, usually takes intensive drug therapy, and if complications such as rupture, ischemia, persistent pain or uncontrolled hypertension occur, or there are high-risk characteristics such as aortic diameter >4cm, large tear, and significant expansion of the false lumen, then thoracic endovascular repair is recommended. However, whether it is drug conservative treatment, intervention or surgical treatment, the distal residual tear still has the risk of progression and rupture. Studies have shown that the risk of aortic dissection rupture is closely related to the pressure and hemodynamics in the false lumen, and high pressure and high-speed blood flow in the false lumen may increase the possibility of rupture. In patients with chronic aortic dissection in the descending aorta, the hemodynamic parameters of the false lumen are closely related to the presence and extent of thrombosis in the false lumen, so non-invasive measures are very important in patient management.

[0004] The complex pathological features and hemodynamic characteristics of aortic dissection disease pose a great challenge to the navigation of guide wires and catheters in implant surgery. Surgeons must accurately identify the true blood vessel lumen, and determine the position of the anatomical entrance, which is crucial for achieving accurate angiography and stent deployment. There are three major pain points in the current aortic dissection diagnosis and treatment system:

[0005] Firstly, the diagnosis mainly relies on computed tomography angiography (CTA) for anatomical morphology evaluation, which cannot quantify hemodynamic parameters.

[0006] Secondly, intraoperative decision-making lacks real-time blood perfusion data support, limiting the precision of treatment plan formulation and adjustment.

[0007] Thirdly, postoperative follow-up still highly depends on invasive digital subtraction angiography (DSA), increasing the burden on patients and medical risks.

[0008] Studies have shown that a true lumen blood flow velocity gradient (Δv) > 0.5 m / s can be used as an independent risk factor for predicting the progression of aortic dissection, but when the true lumen blood flow velocity gradient (Δv) > 0.5 m / s, the blood flow environment is usually complex, and traditional techniques cannot obtain the motion of the aortic wall, the changes in hemodynamics, and the expansion of the dynamic dissection through conventional imaging methods, so improvement is needed. SUMMARY

[0009] The present application aims to at least solve the technical problems existing in the prior art, and provides an aortic dissection non-invasive blood flow velocity measurement method, system, device and storage medium.

[0010] In a first aspect, the present application provides an aortic dissection non-invasive blood flow velocity measurement method, which comprises:

[0011] Obtaining four-dimensional computed tomography angiography image data to be detected;

[0012] Analyzing the four-dimensional computed tomography angiography image data using an optical flow method to obtain an aortic blood flow velocity field;

[0013] Analyzing the four-dimensional computed tomography angiography image data, segmenting the aortic image and extracting the centerline of the aorta;

[0014] Determining the flow area of each position of the aorta according to the aortic image and the centerline of the aorta;

[0015] Determining the instantaneous flow velocity of each position of the aorta according to the aortic blood flow velocity field and the flow area of each position of the aorta to obtain a blood flow velocity measurement result.

[0016] By adopting the technical scheme, the four-dimensional computer tomography angiography technology has the technical advantages of non-invasiveness, rapid scanning and high space-time resolution, the aortic blood flow velocity field can be estimated by analyzing the four-dimensional computer tomography angiography image data through the optical flow method, and the aortic blood flow velocity field can reflect the dynamic changes of blood flow in real time; the cross-sectional area of the aorta at each position is determined according to the aortic image and the center line of the aorta, and the instantaneous flow velocity at each position of the aorta can be accurately positioned according to the aortic blood flow velocity field and the cross-sectional area of the aorta at each position; by analyzing the four-dimensional computer tomography angiography image data to determine the blood flow velocity measurement result, the risk of infection, thrombosis and the like caused by traditional invasive catheter measurement can be avoided; in addition, the method integrates the anatomical information (such as the aortic morphology) of the four-dimensional computer tomography angiography image and the hemodynamic parameters (the aortic blood flow velocity field and the cross-sectional area), which can directly reflect the hemodynamic characteristics of the aorta, rather than indirectly estimating the blood flow velocity of the aorta, so that the measured blood flow velocity measurement result is closer to the true state of the aorta, and the accuracy of the blood flow velocity measurement result is improved.

[0017] Optionally, the step of segmenting the aorta region from the four-dimensional computer tomography angiography image data comprises:

[0018] The four-dimensional computer tomography angiography image data is input into a blood vessel image segmentation model, the blood vessel image segmentation model analyzes the four-dimensional computer tomography angiography image data, and outputs a segmentation probability map of the four-dimensional computer tomography angiography image.

[0019] The segmentation probability map is thresholded to obtain a binary mask image of the aorta, and the aorta region is segmented from the four-dimensional computer tomography angiography image according to the binary mask image.

[0020] By adopting the technical scheme, the four-dimensional computer tomography angiography image data is analyzed by the blood vessel image segmentation model and the segmentation probability map is output, and the binary mask image of the aorta can be obtained by thresholding the segmentation probability map, so that the aorta region is accurately extracted.

[0021] Optionally, the four-dimensional computer tomography angiography image data comprises a continuous sequence of angiography images, and the spatial coordinates, time frames, spatial resolution and time resolution of the angiography images.

[0022] By adopting the technical scheme, the specific information content contained in the four-dimensional computer tomography angiography image data is clearly defined.

[0023] Optionally, the sequence of angiography images is a time sequence, and the step of extracting the center line of the aorta comprises:

[0024] A time-averaged image is calculated according to the spatial coordinates and time frames of the angiographic images, the time-averaged image being a three-dimensional image, each pixel point of the time-averaged image representing the average intensity of the signal at the position of the pixel point in the sequence of angiographic images;

[0025] The time-averaged image is sequentially subjected to denoising processing and enhancement processing to obtain a preprocessed time-averaged image;

[0026] The preprocessed time-averaged image is processed using a three-dimensional skeletonization algorithm to obtain a three-dimensional skeleton image of the aorta;

[0027] The three-dimensional skeleton image of the aorta is analyzed to identify pixel points corresponding to the center line of the aorta to obtain a set of aortic center line pixel points;

[0028] The pixel points in the set of aortic center line pixel points are sequentially connected to generate the center line of the aorta.

[0029] By adopting the above technical solution, the specific steps of extracting the center line of the aorta are clearly defined. Denoising processing of the time-averaged image can reduce the influence of noise on the skeletonization result. Enhancement processing of the time-averaged image can highlight the contrast between the aorta and the surrounding tissue, making the aorta region more obvious, thereby improving the accuracy of the three-dimensional skeleton image and further improving the extraction accuracy of the aortic center line.

[0030] Optionally, the calculation formula of the time-averaged image is:

[0031]

[0032] wherein, represents the time-averaged image, is the spatial coordinate of the angiographic image in the spatial coordinate system axis, is the spatial coordinate of the angiographic image in the spatial coordinate system axis, is the spatial coordinate of the angiographic image in the spatial coordinate system axis; is the total number of time frames in the time sequence corresponding to the four-dimensional computed tomography angiographic image data, is the time frame index.

[0033] By adopting the above technical solution, the calculation method of the time-averaged image is clearly defined.

[0034] Optionally, the four-dimensional computed tomography angiographic image data further includes a computed tomography scan amplitude value of each pixel point of the angiographic image, and the determination of the flow area of each position of the aorta according to the aortic image and the center line of the aorta includes:

[0035] ​A center line of the aorta is extracted, and a normal plane is reconstructed, the normal plane being a plane perpendicular to the aorta axial direction;

[0036] A mesh is constructed on the normal plane;

[0037] The flow area of each position of the aorta is determined according to the number and area of the mesh of the normal plane corresponding to each position of the aorta center line;

[0038] The calculation formula of the flow area of the aorta at the position of the sampling point is:

[0039] A[k,t]= ;

[0040] Wherein, A[k,t] represents the flow area of the sampling point of the aorta center line at time t; k represents the index of the sampling point of the aorta center line, and t represents the time frame index; and v are two orthogonal coordinate axes corresponding to the normal plane basis vector; is the total number of meshes in the normal plane coordinate axis direction, is the mesh index set along the normal plane coordinate axis direction; is the total number of meshes in the normal plane coordinate axis direction, is the mesh index set along the normal plane coordinate axis direction; is the resampled computer tomography amplitude value, represents the coordinate value of the mesh point in the normal plane coordinate axis direction, represents the coordinate value of the mesh point in the normal plane coordinate axis direction; represents the interval between the mesh points in the normal plane coordinate axis direction, represents the interval between the mesh points in the normal plane coordinate axis direction; represents the interval between the mesh points in the normal plane coordinate axis direction; represents the interval between the mesh points in the normal plane

[0041] ,

[0042] represents an interpolation function, represents the computer tomography amplitude value corresponding to the pixel point with spatial coordinates in the angiography image at time t; represents the coordinate value of the mesh point in the normal plane coordinate axis direction, a point, a grid corresponding to the point in the coordinate axis direction.

[0043] By adopting the technical scheme, the calculation manner of the flow area of each position of the aorta is determined.

[0044] Optionally, the calculation formula of the instantaneous flow of each position of the aorta is:

[0045]

[0046] wherein, [k,t] represents the instantaneous flow of the sampling point of the aorta center line at the time t; is the blood flow velocity component of the blood at the sampling point of the aorta center line in the direction of the normal plane basis vector at the time t;

[0047] The calculation expression of the instantaneous flow velocity of each position of the aorta center line is:

[0048] , is the instantaneous flow velocity of the sampling point of the aorta center line at the time t, and A[k,t] represents the flow area of the sampling point of the aorta center line at the time t.

[0049] By adopting the technical scheme, the calculation manner of the instantaneous flow of each position of the aorta is determined.

[0050] In a second aspect, the present application provides an aortic dissection noninvasive blood flow velocity measurement system, which comprises:

[0051] An acquisition module is configured to acquire four-dimensional computed tomography angiography image data to be detected, wherein the four-dimensional computed tomography angiography image data comprises a plurality of continuous angiography images.

[0052] A blood flow velocity field estimation module is configured to analyze the four-dimensional computed tomography angiography image data by using an optical flow method to obtain an aortic blood flow velocity field.

[0053] An image segmentation module is configured to parse the four-dimensional computed tomography angiography image data, segment out an aorta image, and extract a center line of the aorta.

[0054] A processing module is configured to determine a flow area of each position of the aorta according to the aorta image and the center line of the aorta, wherein the flow area is an area of a plane perpendicular to an axial direction of the aorta.

[0055] ​The blood flow velocity measurement result generation module is configured to determine the instantaneous flow velocity at each position of the aorta according to the aortic blood flow velocity field and the cross-sectional area of the aorta at each position, and obtain the blood flow velocity measurement result.

[0056] In a third aspect, the present application provides an electronic device, which comprises:

[0057] at least one processor; and

[0058] a memory connected to the at least one processor in communication; wherein

[0059] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the aortic dissection non-invasive blood flow velocity measurement method described above.

[0060] In a fourth aspect, the present application further provides a computer readable storage medium, which stores at least one computer program, and the at least one computer program is executed by a processor in an electronic device to implement the aortic dissection non-invasive blood flow velocity measurement method described above.

[0061] In summary, the present application has the following beneficial technical effects:

[0062] The four-dimensional computed tomography angiography technology has the technical advantages of non-invasiveness, rapid scanning and high spatio-temporal resolution. The aortic blood flow velocity field can be estimated by analyzing the four-dimensional computed tomography angiography image data using the optical flow method, and the aortic blood flow velocity field can reflect the dynamic changes of blood flow in real time. The cross-sectional area of the aorta at each position is determined according to the aortic image and the centerline of the aorta, and the instantaneous flow velocity at each position of the aorta can be accurately positioned according to the aortic blood flow velocity field and the cross-sectional area of the aorta at each position. By analyzing the four-dimensional computed tomography angiography image data to determine the blood flow velocity measurement result, the risks of infection and thrombosis caused by traditional invasive catheter measurement can be avoided. In addition, the present method integrates the anatomical information (such as the aortic morphology) of the four-dimensional computed tomography angiography image and the hemodynamic parameters (aortic blood flow velocity field and cross-sectional area), which can directly reflect the hemodynamic characteristics of the aorta, rather than indirectly estimating the blood flow velocity of the aorta, so that the measured blood flow velocity measurement result is closer to the true state of the aorta, and the accuracy of the blood flow velocity measurement result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 The flowchart of the aortic dissection non-invasive blood flow velocity measurement method provided by an embodiment of the present application is shown;

[0064] Figure 2An aorta region image segmented based on four-dimensional computed tomography angiography image data;

[0065] Figure 3 A schematic diagram of a transverse (normal) plane corresponding to different positions of a center line of the aorta;

[0066] Figure 4 A schematic diagram of an electronic device for implementing the method for non-invasive blood flow velocity measurement of the aortic dissection according to an embodiment of the present application.

[0067] Reference signs: 10, processor; 11, memory; 12, communication bus; 13, communication interface.

[0068] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments in conjunction with the accompanying drawings. DETAILED DESCRIPTION

[0069] The embodiments of the present application will be described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference signs represent the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be understood as a limitation of the present application.

[0070] In the description of the present application, it should be understood that the terms "longitudinal", "transverse", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and therefore cannot be understood as indicating or implying that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation of the present application.

[0071] In the description of the present application, unless otherwise specified and limited, it should be noted that the terms "mounting", "connection", "connection" should be understood broadly, for example, it can be a mechanical connection or an electrical connection, or a communication between two elements, or a direct connection, or an indirect connection through an intermediate medium, and the specific meaning of the above terms can be understood by a person of ordinary skill in the art according to the specific circumstances.

[0072] The complex pathological features and hemodynamic characteristics of aortic dissection disease bring great challenges to the navigation of guide wires and catheters in implantation surgery. Surgeons must accurately identify the true blood vessel lumen, and determine the position of the anatomical entrance, which is crucial for achieving accurate angiography and stent deployment.

[0073] Reference Figure 1As shown, it is a flowchart of the aortic dissection noninvasive blood flow rate measuring method provided by an embodiment of the present application. In this embodiment, the aortic dissection noninvasive blood flow rate measuring method comprises:

[0074] S1, acquiring four-dimensional computed tomography angiography image data to be detected.

[0075] The full name of four-dimensional computed tomography angiography in English is 4-dimensions-computed tomography angiography, which is abbreviated as 4D-CTA. The 4D-CTA technology realizes the recording of the flow process of contrast agent in blood vessels through the addition of a time dimension parameter, can dynamically observe cerebral blood vessels and vascular lesions, and can obtain multi-modal data such as plain CT, conventional CTA, CT perfusion imaging, etc.; the full name of CT in English is Computed Tomography, which means computed tomography; the full name of CTA in English is Computed Tomography Angiography, which means CT angiography.

[0076] The prior art usually predicts the blood flow rate of aortic dissection through three-dimensional CTA images or nuclear magnetic resonance images. In this embodiment, four-dimensional computed tomography angiography image data is used to measure the blood flow rate of aortic dissection.

[0077] The four-dimensional computed tomography angiography image data includes a sequence of continuous angiography images, and the spatial coordinates, time frames, spatial resolution, and time resolution of the angiography images, etc. The sequence of angiography images is a time sequence.

[0078] The spatial coordinates of the angiography images are the pixel point indexes on the four-dimensional computed tomography angiography image, and the expression of the spatial coordinates is (x, y, z), wherein, is the spatial coordinates of the four-dimensional computed tomography angiography image in the spatial coordinate system axis coordinates, is the spatial coordinates of the four-dimensional computed tomography angiography image in the spatial coordinate system axis coordinates, is the spatial coordinates of the four-dimensional computed tomography angiography image in the spatial coordinate system axis coordinates; , , It should be noted that, is the spatial coordinates of the four-dimensional computed tomography angiography image in the spatial coordinate system along axis (or The number of pixels in the direction of the axis, and length represents the number of slices along the long axis of the blood vessel. The specific value of length depends on the scanning range. The running direction of the aorta is basically consistent with the extension direction of the human spine. The long axis of the blood vessel refers to an axis consistent with the extension direction of the human spine.

[0079] The time phase of the four-dimensional computed tomography angiography image acquisition is represented by the symbol In this embodiment, , The value of t is 1 to 10 in order to correspond to 10 uniformly distributed phases of the cardiac cycle of the heart. The cardiac cycle of the heart is composed of a systole and a diastole. From the end of diastole to the end of systole, and back to the end of diastole, each stage has corresponding manifestations in electrocardiogram and heart sound. The four-dimensional computed tomography angiography image collected at the 10 uniformly distributed phases of the cardiac cycle of the heart can more comprehensively reflect the true situation of the aorta.

[0080] The spatial resolution expression of the angiography image is (unit: mm), and the time resolution expression of the angiography image is (unit: s); The role of the spatial resolution of the angiography image is to correspond the pixel space to the actual physical parameter space to obtain the physical parameters of the pixel points; The time resolution refers to the ability of the system to capture dynamic images at consecutive time points; Through high time resolution, the dynamic changes of the blood vessel in the cardiac cycle or respiratory motion can be accurately captured, and motion artifacts can be reduced.

[0081] Specifically, the spatial resolution of the angiography image needs to be obtained from the DICOM metadata. The full name of DICOM metadata in English is Digital Imaging and Communications in Medicine Metadata. The term "Metadata" specifically refers to the structured information related to medical images stored in the DICOM file, including patient information, device parameters, scanning protocol, etc.; Metadata is standardized information embedded in the medical image file, which is used to describe the technical parameters of the patient, the examination, the device and the image itself. respectively correspond to the Columns (Width), Rows (Height), and Pixel Spacing fields in the DICOM file; wherein Columns represents the number of columns, Rows represents the number of rows, Pixel Spacing represents the pixel spacing, Width represents the width, and Height represents the height.

[0082] Four-dimensional computed tomography angiography has the technical advantages of non-invasiveness, rapid scanning and high spatial and temporal resolution, which helps to observe the motion of the aortic wall, the changes of hemodynamics and the expansion of dynamic dissection. Four-dimensional computed tomography angiography has the potential to analyze complex aortic dissection by visualizing the spatial distribution of the intimal flap and evaluating the dissection risk in a complex and realistic blood flow environment.

[0083] Four-dimensional computed tomography angiography can display small tears through multi-planar reconstruction (MPR) technology, providing accurate tear location information for endovascular repair. The measurement of adjacent branch and proximal and distal blood flow velocity helps to evaluate the impact of stent implantation on the blood flow environment after sealing the tear.

[0084] Four-dimensional computed tomography angiography image data can be acquired by a multi-row spiral CT device, and the acquired four-dimensional computed tomography angiography image data can be manually imported from an external device by an inspector, or received through a cloud platform, or acquired in other ways. In this embodiment, the acquisition method of four-dimensional computed tomography angiography image data is not limited.

[0085] S2, analyze the four-dimensional computed tomography angiography image data using the optical flow method to obtain the aortic blood flow velocity field.

[0086] The steps of estimating the aortic blood flow velocity field from the four-dimensional computed tomography angiography image data using the optical flow method are as follows:

[0087] The expression of the angiography image acquired at time t is denoted as The expression of the aortic blood flow velocity field at time t is denoted as ; t represents the time phase of the cardiac cycle corresponding to the cardiac cycle when the angiography image is acquired.

[0088] Assuming that the brightness is conserved, then The aortic blood flow velocity field is solved using the optical flow method, which is to solve the velocity component .

[0089] For adjacent time frames t and t+1, calculate:

[0090]

[0091] wherein is the gradient of the angiography image in the axis direction, is the gradient of the angiography image in the axis direction, to the angiography image in the axial direction, to the time gradient of the angiography image, to the cumulative sign, denotes a matrix; the calculation is to determine the spatial gradient change of the angiography image in adjacent time frames t and t+1.

[0092] Through the spatial gradient change of the angiography image in adjacent time frames t and t+1, by solving the optical flow field of all pixels in the angiography image of the adjacent time frames, a continuous blood flow velocity distribution map is generated, so as to obtain the aortic blood flow velocity field .

[0093] In the preferred implementation of the present embodiment, after obtaining the aortic blood flow velocity field , the aortic blood flow velocity field is subjected to regularization processing, and the continuity of the aortic blood flow velocity field is constrained by adding a smoothing term, and the calculation expression for the regularization processing of the aortic blood flow velocity field is as follows:

[0094] ;

[0095] wherein, denotes the gradient of , the gradient is a vector, and points to the direction in which the function increases fastest, and the magnitude of the gradient indicates the rate of increase. In image processing, the gradient is usually used to represent the change of image brightness; denotes the partial derivative of with respect to time , indicating the rate of change of over time; “ ” denotes the dot product, that is, the sum of the corresponding components of two vectors after multiplication; λ is a smoothing coefficient, used to balance the weight between the data fidelity term and the smoothing term; denotes the square of the second norm (i.e., the Euclidean norm); denotes the partial derivative of the aortic blood flow velocity field ; denotes the minimum value of the expression in the parentheses with respect to the aortic blood flow velocity field .

[0096] Through the regularization processing of the aortic blood flow velocity field estimated by the optical flow method, an optimal velocity field is found as the final aortic blood flow velocity field, and this optimal velocity field satisfies the following conditions: and The correlation is related, and the smoothness is maintained as much as possible.

[0097] S3, analyze the four-dimensional computed tomography angiography image data, segment the aorta image and extract the center line of the aorta.

[0098] Specifically, the segmented aorta region image is as shown in the figure, wherein, Figure 2 The red curve in the middle aorta region is the center line of the aorta. Figure 2

[0099] Specifically, the step of segmenting the aorta region according to the four-dimensional computed tomography angiography image data comprises:

[0100] S301, input the four-dimensional computed tomography angiography image data into the blood vessel image segmentation model, and the blood vessel image segmentation model analyzes the four-dimensional computed tomography angiography image data and outputs a segmentation probability map of the four-dimensional computed tomography angiography image.

[0101] In this embodiment, the blood vessel image segmentation model is a deep learning model, which uses a deep learning model to sequentially extract features of the four-dimensional computed tomography angiography image, a segmentation probability map of the four-dimensional computed tomography angiography image, and a binary mask according to the segmentation probability map.

[0102] In some examples of this embodiment, the deep learning model can be nnUNet or U-Net, which is a symmetrical encoder-decoder architecture based on convolutional neural network, designed for biomedical image segmentation;‌nnUNet is the full name of Self-adapting Framework for U-Net-Based Medical Image Segmentation, which means U-Net-based self-adaptive medical image segmentation framework.

[0103] The blood vessel image segmentation model can be used to process the four-dimensional computed tomography angiography image data, or the model parameters of the blood vessel image segmentation model can be trained using a training data set before inputting the four-dimensional computed tomography angiography image data, which is not limited by the present application.

[0104] S302, threshold processing is performed on the segmentation probability map to obtain a binary mask image of the aorta, and the aorta region is segmented from the four-dimensional computed tomography angiography image according to the binary mask image.

[0105] ​Thresholding is applied to the probability map, and the probability value of each pixel in the 4D computed tomography angiography image is compared with a preset reference probability value. Pixels with probability values ​​greater than the preset reference probability value are marked as aortic regions, generating a binary mask for the aorta. The formula for comparing the probability value of each pixel in the 4D computed tomography angiography image with the preset reference probability value is as follows:

[0106] ;

[0107] in, This represents a four-dimensional computed tomography (CT) angiography image. Used to represent the spatial coordinates of pixels in a four-dimensional computed tomography angiography image. Indicates a time frame; express The spatial location in the 4D computed tomography angiography images acquired at different times is ( (pixels).

[0108] Post-processing operations, such as removing small isolated regions and filling holes, are performed on the generated binary mask to further improve the accuracy and completeness of the segmentation results, resulting in the final binary mask image of the aorta.

[0109] The steps for extracting the centerline of the aorta include:

[0110] S310. Calculate the time-averaged image based on the spatial coordinates and time frames of the angiography image.

[0111] The time-averaged image is a three-dimensional image, and each pixel in the time-averaged image represents the average signal intensity at the location of the pixel in the angiography image sequence.

[0112] The formula for calculating the time-averaged image is:

[0113] ;

[0114] in, Represents a time-averaged image. In the spatial coordinates of the angiography image Axis coordinates In the spatial coordinates of the angiography image Axis coordinates In the spatial coordinates of the angiography image Axis coordinates; This represents the total number of time frames in the time series corresponding to the four-dimensional computed tomography angiography image data. For time frame index.

[0115] S320, sequentially performing denoising processing and enhancement processing on the time-averaged image to obtain a preprocessed time-averaged image.

[0116] Specifically, Gaussian filtering, median filtering and the like are adopted to remove noise in the image, so as to reduce the influence of the noise on the skeletonization result; according to the need, contrast enhancement and the like are performed on the image, so as to highlight the contrast between the aorta and the surrounding tissue, and make the aorta region more obvious, to obtain the preprocessed time-averaged image. , to provide clearer image data for subsequent skeletonization operation.

[0117] S330, processing the preprocessed time-averaged image by using a three-dimensional skeletonization algorithm to obtain a three-dimensional skeleton image of the aorta.

[0118] Specifically, a suitable three-dimensional skeletonization algorithm is selected, such as a skeletonization algorithm based on distance transformation, a skeletonization algorithm based on thinning and the like. These algorithms remove foreground pixels in the image iteratively while maintaining the topological structure of the image, and finally obtain the skeleton of the image. The skeletonization algorithm based on distance transformation generates a distance transformation map by calculating the shortest distance (such as Euclidean distance or chessboard distance) from each foreground pixel in the binary image to the nearest background pixel. The skeletonization algorithm based on thinning iteratively deletes edge pixels, gradually reduces thick lines to single-pixel-width skeletons while maintaining the topological structure of the original shape.

[0119] A suitable skeletonization algorithm can be selected according to actual needs, and the present application does not make any limitation; the selected skeletonization algorithm is applied to process the preprocessed time-averaged image. The skeletonization algorithm will gradually remove non-key points in the preprocessed time-averaged image. In the skeletonization process, the skeletonization effect of the aorta region can be corrected by adjusting the parameters of the skeletonization algorithm to obtain an accurate center line.

[0120] The finally obtained three-dimensional skeleton image of the aorta contains the center line information of the aorta, and the center line is composed of a series of continuous pixel points, which constitute the center path of the aorta.

[0121] S340, analyzing the three-dimensional skeleton image of the aorta to identify the pixel points corresponding to the center line of the aorta, to obtain a set of aorta center line pixel points.

[0122] In the three-dimensional skeleton image of the aorta, all pixel points belonging to the center line are identified. These points usually have specific characteristics, such as having a specific pixel value distribution or connection relationship in their neighborhood; the identified center line pixel points are sorted according to their position coordinates in three-dimensional space to form a discrete point set. Each point can be represented by its coordinates (x, y, z) in the three-dimensional image.

[0123] S350, sequentially connecting the pixel points in the aortic center line pixel point set to generate the center line of the aorta.

[0124] The user can observe the structure of the aorta through a visualization software or graphical interface, set the starting point and ending point of the center line, and find the optimal path from the starting point of the aortic center line to the ending point of the aortic center line in three-dimensional space according to the Dijkstra algorithm. This optimal path is the center line path from the starting point to the ending point, which is composed of a series of consecutive pixel points that form the center line of the aorta. The Dijkstra algorithm, also known as Dijkstra's algorithm or Dijkstra's algorithm, is a greedy algorithm for the single-source shortest path problem in weighted graphs. Its core goal is to find the shortest path from the starting point to all other nodes in the graph, and the weight of the edge in the graph must be non-negative.

[0125] In this embodiment, the aortic center line path expression is , the aortic center line path includes consecutive pixel points, represents the pixel point in the aortic center line pixel point set, represents the number of pixel points that make up the aortic center line path, is the index of the pixel point at each position of the aortic center line path; is the three-dimensional coordinates corresponding to the pixel point on the aortic center line path.

[0126] S4, determining the cross-sectional area of the aorta at each position according to the aortic image and the center line of the aorta.

[0127] The cross-sectional area is the area of the plane perpendicular to the aortic axis. The four-dimensional computed tomography angiography image data also includes the computed tomography amplitude value of each pixel point of the angiography image. The computed tomography amplitude value, also known as the CT amplitude value, is a key indicator for quantifying tissue density, expressed in Hounsfield units (HU), with a range of -1000 to +1000.

[0128] Specifically, determining the cross-sectional area of the aorta at each position according to the aortic image and the center line of the aorta includes:

[0129] S41, selecting a sampling point from the center line of the aorta, and reconstructing a tangent plane.

[0130] The tangent plane is a plane perpendicular to the axial direction of the aorta, that is, the smallest aortic cross section passing through the sampling point of the center line of the aorta. Referring to Figure 3 , Figure 3 are schematic diagrams of the cross sections (i.e., tangent planes) corresponding to several important positions of the aorta; preferably, the present embodiment focuses on selecting the cross-sectional flow area of the cross section corresponding to the position of the aorta at the connection of the sinus and the tube (corresponding to the STJ in Figure 3 ), the position of the aortic arch (corresponding to the positions of AA1, AA2, and AA3 in Figure 3 ), the position of the dissection rupture (corresponding to the positions of RS1, RS2, and RS3 in Figure 3 ), the position of the celiac trunk (corresponding to the position of CT in Figure 3 ), the position of the renal artery (corresponding to the position of RA in Figure 3 ), and the position of the common iliac artery (corresponding to the position of CIA in Figure 3 ) to determine the blood flow velocity of the aorta.

[0131] Specifically, the calculation formula of the tangent vector of the tangent plane generated based on the first pixel point of the aorta center line is as follows:

[0132] ;

[0133] wherein, represents the tangent vector of the tangent plane generated based on the first pixel point of the aorta center line, represents the first pixel point in the pixel point set of the aorta center line, represents the first pixel point in the pixel point set of the aorta center line; represents the second norm. The calculation formula of the basis vector of the tangent plane generated based on the first pixel point of the aorta center line is as follows:

[0134]

[0135] ;

[0136] In the present embodiment, the basis vector and the basis vector are two orthogonal unit vectors of the tangent plane, the basis vector is defined as the horizontal axis of the aortic cross section corresponding to the tangent plane, which usually points to the left-right direction of the patient's body; and the basis vector is defined as the vertical axis of the cross section, which usually points to the front-back direction of the patient.​​ The sampling radius of the tangent plane is the sampling half-width of the tangent plane set to ensure complete coverage of the aortic cross-section. The sampling radius of the tangent plane is usually determined according to prior knowledge or the maximum aortic radius estimated from the time-averaged image. The maximum radius of the cross-section at each position of the aorta is determined according to experience, and a certain margin is left to generate the final sampling radius, ensuring that the resampled tangent plane covers the surrounding image pixels.

[0137] S42, constructing a grid on the tangent plane.

[0138] For each pixel point on the aortic centerline , , a grid point is generated on the tangent plane (u, v);

[0139] ;

[0140] represents the grid corresponding to the tangent plane coordinate axis at the first point of the tangent plane coordinate axis at the first point of the tangent plane coordinate axis at the first point of the tangent plane coordinate axis at the first point of the tangent plane is the grid index set along the tangent plane coordinate axis direction, is the grid index set along the tangent plane coordinate axis direction; represents the coordinate value of the grid point in the tangent plane coordinate axis direction, represents the coordinate value of the grid point in the tangent plane coordinate axis direction.

[0141] S43, determining the flow area of each position of the aorta according to the grid number and grid area of the tangent plane corresponding to each position of the aortic centerline.

[0142] The calculation formula of the flow area of the aorta at the position of the sampling point is:

[0143] A[k,t]= ;

[0144] where A[k,t] represents the flow area at the sampling point of the aortic centerline at time t; k represents the index of the sampling point on the aortic centerline, and t represents the time frame index; and v are two orthogonal coordinate axes corresponding to the tangent plane basis vectors; according to the coordinate axis and the v coordinate axis, the tangent plane is divided into several grids of the same size;​​ is the normal plane total number of grids in the direction of coordinate axis, is the normal plane grid point index in the direction of coordinate axis; is the normal plane total number of grids in the direction of coordinate axis, is the normal plane grid point index in the direction of coordinate axis, which can be obtained by value of and value of, that is, the grid point position coordinates on the normal plane (u, v); is the computed tomography magnitude value after resampling (i.e., based on the pixel point generating the normal plane on the center line of the aorta represents the normal plane coordinate axis direction, the grid point coordinate value, represents the normal plane coordinate axis direction, the grid point coordinate value; represents the normal plane interval between grid points in the direction of coordinate axis, represents the normal plane interval between grid points in the direction of coordinate axis; by calculating the area of all grid points of the normal plane after resampling and the aortic cross section overlap, the flow area of the aorta at the sampling point can be obtained.

[0145] using trilinear interpolation to obtain the velocity component and the computed tomography magnitude value corresponding to the normal plane after resampling (i.e., based on the pixel point generating the normal plane on the center line of the aorta

[0146] wherein the velocity component corresponding to the normal plane after resampling is represented as:

[0147] ;

[0148] represents an interpolation function, specifically, is a trilinear interpolation function for extracting an interpolation result at an arbitrary spatial point from three-dimensional grid data, which outputs the result of interpolation calculation by weighted average of the values corresponding to the eight grid points around the spatial point , and the weight of the weighted average is determined by the distance from the spatial point to each grid point; represents the spatial coordinates of the angiogram image at time t The velocity corresponding to the pixel point of the pixel point, and the velocity here refers to the velocity in the vertical aortic axis plane.

[0149] The computer tomography amplitude value corresponding to the normal plane after resampling is expressed as:

[0150] ;

[0151] The pixel point corresponding to the spatial coordinates of the angiogram image at time t is The computer tomography amplitude value corresponding to the pixel point, since the computer tomography amplitude value is a discrete four-dimensional matrix, when sampling to non-continuous values, the optimal approximation is obtained by trilinear interpolation.

[0152] S5, determining the instantaneous flow rate of each position of the aorta according to the aortic blood flow velocity field and the flow area of each position of the aorta, and obtaining the blood flow rate measurement result.

[0153] The calculation formula of the instantaneous flow of each position of the aorta is:

[0154]

[0155] Wherein, [k,t] represents the instantaneous flow at the sampling point of the aortic center line at time t ; is the blood flow velocity component of the blood along the normal plane base vector direction at the sampling point of the aortic center line at time t ;

[0156] ;

[0157] The calculation expression of the instantaneous flow rate of each position of the aortic center line is:

[0158] , is the instantaneous flow rate at the sampling point of the aortic center line at time t ; A[k,t] represents the flow area at the sampling point of the aortic center line at time t ; is the instantaneous flow of each position of the aorta, and the instantaneous flow rate of each position of the aortic center line is the blood flow rate measurement result.

[0159] The blood flow velocity measurement result determined according to the four-dimensional computer tomography angiography image data can accurately track the dynamic change of the false lumen and timely find the progress of thrombosis; through the monitoring of the blood flow velocity, whether the position of the stent is accurate, whether there is an internal leakage, and the aortic reconstruction condition can be determined, early accurate evaluation of postoperative recovery can be assisted, and long-term follow-up strategy can be optimized; the blood flow improvement condition can be directly and intuitively presented by using quantitative data, the treatment effect can be accurately evaluated, and strong support can be provided for subsequent treatment adjustment.

[0160] Based on the same inventive concept, an aortic dissection noninvasive blood flow velocity measurement system is provided in an embodiment of the present application.

[0161] The aortic dissection noninvasive blood flow velocity measurement system can be loaded in an electronic device. According to the functions implemented, the aortic dissection noninvasive blood flow velocity measurement system comprises:

[0162] An acquisition module is configured to acquire four-dimensional computer tomography angiography image data to be detected; the four-dimensional computer tomography angiography image data comprises a plurality of continuous angiography images;

[0163] A blood flow velocity field estimation module is configured to analyze the four-dimensional computer tomography angiography image data by using an optical flow method to obtain an aortic blood flow velocity field;

[0164] An image segmentation module is configured to parse the four-dimensional computer tomography angiography image data, segment an aortic image, and extract a center line of the aorta;

[0165] A processing module is configured to determine a flow area of each position of the aorta according to the aortic image and the center line of the aorta; the flow area is an area of a plane perpendicular to an axial direction of the aorta;

[0166] A blood flow velocity measurement result generation module is configured to determine an instantaneous flow velocity of each position of the aorta according to the aortic blood flow velocity field and the flow area of each position of the aorta to obtain a blood flow velocity measurement result.

[0167] The modules described in the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, and are stored in a memory of the electronic device.

[0168] The various change modes and specific examples in the aortic dissection noninvasive blood flow velocity measurement method provided in the above embodiments are also applicable to the aortic dissection noninvasive blood flow velocity measurement system of the present embodiment. Through the foregoing detailed description of the aortic dissection noninvasive blood flow velocity measurement method, those skilled in the art can clearly know the implementation method of the aortic dissection noninvasive blood flow velocity measurement system in the present embodiment. In order to make the description brief, the implementation method of the aortic dissection noninvasive blood flow velocity measurement system in the present embodiment will not be described in detail here.

[0169] The application also discloses an electronic device, such as Figure 4 Fig. 1 is a structural schematic diagram of an electronic device for the method of non-invasive blood flow velocity measurement of aortic dissection according to an embodiment of the application. The electronic device can include at least one processor 10, a memory 11 in communication with the at least one processor, a communication bus 12, and a communication interface 13, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a method program for non-invasive blood flow velocity measurement of aortic dissection.

[0170] In some embodiments, the processor 10 can be composed of integrated circuits, for example, composed of a single packaged integrated circuit, or composed of multiple packaged integrated circuits with the same function or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core of the electronic device, which connects all components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (for example, executes the method for non-invasive blood flow velocity measurement of aortic dissection), and calls data stored in the memory 11 to perform various functions of the electronic device and process data.

[0171] The memory 11 includes at least one type of readable storage medium, including flash memories, mobile hard disks, multimedia cards, card-type memories (for example, SD or DX memories, etc.), magnetic memories, magnetic disks, optical disks, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device, for example, a mobile hard disk of the electronic device. In other embodiments, the memory 11 can also be an external storage device of the electronic device, for example, a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 can include both an internal storage unit and an external storage device of the electronic device. The memory 11 can be used not only to store application software and various data installed in the electronic device, such as the code of the method program for non-invasive blood flow velocity measurement of aortic dissection, but also to temporarily store data that has been output or will be output.

[0172] The communication bus 12 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable connection and communication between the memory 11, the at least one processor 10, etc.

[0173] The communication interface 13 is configured to enable communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (e.g., a WI-FI interface, a Bluetooth interface, etc.), which is typically configured to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display, an input unit (e.g., a keyboard), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, an OLED (Organic Light-Emitting Diode) touch screen, etc. The display can also be appropriately referred to as a display screen or a display unit, which is configured to display information processed in the electronic device and to display a visualized user interface.

[0174] Figure 4 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 4 The structure shown does not constitute a limitation on the electronic device, and the electronic device can include fewer or more components than shown, or some components can be combined, or different components can be arranged.

[0175] For example, although not shown, the electronic device can further include a power supply (e.g., a battery) configured to supply power to each component. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, so that the power management device can be configured to perform functions such as charge management, discharge management, and power consumption management. The power supply can also include one or more DC or AC power sources, a recharging device, a power failure detection circuit, a power converter or inverter, a power status indicator, etc. The electronic device can also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which are not described here.

[0176] It should be understood that the embodiments are for illustration only and do not limit the scope of the patent application.

[0177] Further, the modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile.

[0178] The computer readable storage medium stores a computer program capable of being loaded by a processor and executing the aortic dissection non-invasive blood flow rate measurement method of the above-mentioned embodiments.

[0179] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", "an implementation", "a preferred implementation" or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0180] Although the embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made thereto without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. A non-invasive method for measuring blood flow velocity in aortic dissection, characterized in that, The method includes: The four-dimensional computed tomography angiography image data to be detected is obtained. The four-dimensional computed tomography angiography image data includes a continuous sequence of angiography images, as well as the spatial coordinates, time frame, spatial resolution, temporal resolution, and computed tomography scan amplitude value of each pixel of the angiography image. The angiography image sequence is a time series. The aortic blood flow velocity field was obtained by analyzing four-dimensional computed tomography angiography image data using optical flow method. Analyze four-dimensional computed tomography angiography image data, segment the aortic image and extract the centerline of the aorta; The flow area at various locations in the aorta is determined based on the aortic image and the aortic centerline; The instantaneous flow velocity at each location of the aorta is determined based on the aortic blood flow velocity field and the flow area at each location of the aorta, thus obtaining the blood flow velocity measurement results; The steps for extracting the centerline of the aorta include: The time-averaged image is calculated based on the spatial coordinates and time frames of the angiography images. The time-averaged image is a three-dimensional image, and each pixel of the time-averaged image represents the average signal intensity at the location of the pixel in the angiography image sequence. The time-averaged image is then subjected to denoising and enhancement processes to obtain a preprocessed time-averaged image. The three-dimensional skeleton image of the aorta is obtained by processing the preprocessed time-averaged image using a three-dimensional skeletonization algorithm. The three-dimensional skeleton image of the aorta is analyzed to identify the pixels corresponding to the center line of the aorta, thus obtaining the set of pixels of the aortic center line. Connect the pixels in the aortic centerline pixel set sequentially to generate the aortic centerline; The determination of the flow area at various locations of the aorta based on the aortic image and the aortic centerline includes: Sampling points are selected from the centerline of the aorta, and the normal plane is reconstructed, wherein the normal plane is a plane perpendicular to the aortic axis; Construct a mesh on the normal plane; The flow area at each location of the aorta is determined based on the number of grids and the grid area of ​​the normal plane corresponding to each location of the aortic centerline. The formula for calculating the flow area of ​​the aorta at the sampling point is: A[k,t]= ; Where A[k,t] represents the sampling point at time t on the aortic centerline. The flow area at the point; represents the index of the sampling point on the aortic centerline, and t represents the time frame index; v and v are two orthogonal coordinate axes corresponding to the basis vectors of the normal plane; normal plane The total number of grid cells along the coordinate axes. For the normal plane The grid index for setting the coordinate axis direction; normal plane The total number of grid cells along the coordinate axes. For the normal plane The grid index for setting the coordinate axis direction; This is the amplitude value of the computed tomography scan after resampling. Representation plane The first in the coordinate axis direction The coordinates of each grid point. Representation plane The first in the coordinate axis direction The coordinates of each grid point; Representation plane The spacing between grid points along the coordinate axes. Representation plane The spacing between grid points along the coordinate axes; ， Represents the interpolation function. The spatial coordinates of the angiographic image at time t are: The computed tomography amplitude value corresponding to each pixel; Representation plane The first in the coordinate axis direction One point, The first in the coordinate axis direction The grid corresponding to each point.

2. The non-invasive blood flow velocity measurement method for aortic dissection as described in claim 1, characterized in that, The steps for segmenting the aortic region based on four-dimensional computed tomography angiography image data include: The four-dimensional computed tomography angiography image data is input into the vascular image segmentation model. The vascular image segmentation model parses the four-dimensional computed tomography angiography image data and outputs the segmentation probability map of the four-dimensional computed tomography angiography image. Thresholding is applied to the segmentation probability map to obtain a binary mask image of the aorta. The aortic region is then segmented from the four-dimensional computed tomography angiography image based on the binary mask image.

3. The non-invasive blood flow velocity measurement method for aortic dissection as described in claim 1, characterized in that, The formula for calculating the time-averaged image is: ； in, Represents a time-averaged image. For angiography images in spatial coordinate system Axis coordinates For angiography images in spatial coordinate system Axis coordinates For angiography images in spatial coordinate system Axis coordinates; This represents the total number of time frames in the time series corresponding to the four-dimensional computed tomography angiography image data. For time frame index.

4. The non-invasive blood flow velocity measurement method for aortic dissection as described in any one of claims 1 to 3, characterized in that, The formula for calculating the instantaneous flow rate at various locations in the aorta is as follows: ； in, [k,t] represents the sampling point on the aortic centerline at time t. Instantaneous flow rate at the location; Sampling point at time t along the center line of the aorta The blood flow velocity component along the basis vector direction of the normal plane at the location; The formula for calculating the instantaneous flow velocity at various locations along the aortic centerline is as follows: , Sampling point at time t along the center line of the aorta The instantaneous flow velocity at point t, A[k,t] represents the sampling point on the aortic centerline at time t. The flow area at that point.

5. A non-invasive blood flow velocity measurement system for aortic dissection, used to implement the non-invasive blood flow velocity measurement method for aortic dissection as described in any one of claims 1 to 4, characterized in that, include: The acquisition module is used to acquire the four-dimensional computed tomography angiography image data to be detected. The four-dimensional computed tomography angiography image data includes a continuous sequence of angiography images, as well as the spatial coordinates, time frames, spatial resolution and temporal resolution of the angiography images. The angiography image sequence is a time series. The blood flow velocity field estimation module is used to analyze four-dimensional computed tomography angiography image data using optical flow method to obtain the aortic blood flow velocity field. The image segmentation module is used to parse four-dimensional computed tomography angiography image data, segment the aortic image, and extract the centerline of the aorta. The processing module is used to determine the flow area at various locations of the aorta based on the aortic image and the centerline of the aorta. The flow area is the area of ​​a plane perpendicular to the aortic axis. The blood flow velocity measurement result generation module is used to determine the instantaneous flow velocity at each location of the aorta based on the aortic blood flow velocity field and the flow area at each location of the aorta, and obtain the blood flow velocity measurement result. The steps for extracting the centerline of the aorta include: The time-averaged image is calculated based on the spatial coordinates and time frames of the angiography images. The time-averaged image is a three-dimensional image, and each pixel of the time-averaged image represents the average signal intensity at the location of the pixel in the angiography image sequence. The time-averaged image is then subjected to denoising and enhancement processes to obtain a preprocessed time-averaged image. The three-dimensional skeleton image of the aorta is obtained by processing the preprocessed time-averaged image using a three-dimensional skeletonization algorithm. The three-dimensional skeleton image of the aorta is analyzed to identify the pixels corresponding to the center line of the aorta, thus obtaining the set of pixels of the aortic center line. Connect the pixels in the aortic centerline pixel set sequentially to generate the aortic centerline.

6. An electronic device, characterized in that, The electronic device includes: At least one processor (10); and, A memory (11) communicatively connected to the at least one processor (10); The memory (11) stores a computer program that can be executed by the at least one processor (10) to enable the at least one processor (10) to perform the non-invasive blood flow velocity measurement method for aortic dissection as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program; when the computer program is executed by a processor, it implements the non-invasive blood flow velocity measurement method for aortic dissection as described in any one of claims 1 to 4.

Images