Functional Evaluation Method, Device, Equipment and Storage Medium for Intracranial Artery Stenosis

Abstract

The present invention discloses a functional evaluation method, device, equipment and storage medium for intracranial artery stenosis. By processing the acquired intracranial artery angiography images, the two-dimensional centerline and two-dimensional contour line of the target blood vessel are obtained to determine the three-dimensional diameter of the target blood vessel; according to the gray value distribution on the two-dimensional centerline of the target blood vessel, the three-dimensional length of the target blood vessel is determined; according to the two-dimensional centerline of the target blood vessel, the image coordinates of the starting point and the ending point of the target blood vessel are determined, and finally the average blood flow velocity in the target blood vessel is obtained; based on the three-dimensional diameter, three-dimensional length and average blood flow velocity of the target blood vessel, the functional evaluation of intracranial artery stenosis is completed. The present invention uses a more concise method to directly calculate the three-dimensional length of the target blood vessel from the gray value distribution on the two-dimensional centerline. This method avoids complex three-dimensional reconstruction steps, simplifies the calculation process, and improves the evaluation accuracy and reliability at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a method, device, equipment and storage medium for functional evaluation of intracranial artery stenosis. Background Art

[0002] In recent years, the incidence of cerebrovascular diseases in China's clinical practice has been increasing year by year, and atherosclerotic stenosis ranks first globally among all cerebrovascular diseases. There are still certain controversies in the treatment plans for such diseases in current clinical practice. Usually, the diagnosis and treatment process will determine subsequent strategies such as drug treatment or interventional treatment according to the stenosis degree of intracranial arteries. However, the results of multiple large-scale clinical studies in recent years have all shown that even for patients with a relatively high degree of intracranial artery stenosis, interventional treatment has not shown significant prognostic advantages compared with drug treatment. This reveals that there are significant limitations in formulating treatment plans solely based on morphological features.

[0003] In view of the above challenges, it is particularly crucial to explore more accurate evaluation methods. Therefore, in dealing with intracranial artery stenosis, functional evaluation methods in the field of coronary artery stenosis have been gradually introduced. For example, Chinese Patent CN116616804A proposes a method for obtaining evaluation parameters of intracranial artery stenosis. By analyzing multiple frames of intracranial angiography images, it automatically segments the target blood vessel and reconstructs its three-dimensional model using a deep learning model, then determines the contrast agent flow time by automatically counting frames, and finally calculates multiple evaluation parameters including mean blood flow velocity by combining the three-dimensional model and the flow time, realizing the functional evaluation of intracranial artery stenosis. The CN116616804A uses a functional evaluation method, reducing manual intervention and improving the accuracy and repeatability of the evaluation. Nevertheless, due to the complex network structure, small diameter and fine branches of intracranial blood vessels, etc., it brings significant challenges to the three-dimensional reconstruction in the aforementioned functional evaluation. To ensure accuracy, precise projection correction coefficients must be used to compensate for the errors caused by single-angle projection, which increases the computational complexity and uncertainty. Summary of the Invention

[0004] Based on this, the present invention provides a method, device, equipment and storage medium for functional evaluation of intracranial artery stenosis to address the above technical problems.

[0005] On the one hand, the present invention provides a method for functional evaluation of intracranial artery stenosis, the method comprising:

[0006] Processing the obtained intracranial artery angiography image to obtain the two-dimensional centerline and two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel;

[0007] According to the gray value distribution on the two-dimensional center line of the target blood vessel, the two-dimensional center line of the target blood vessel is segmented into multiple two-dimensional center line segments. Based on the two-dimensional length and average gray value of each two-dimensional center line segment, and in combination with preset reference parameters, the three-dimensional length of each two-dimensional center line segment is calculated. Finally, the three-dimensional lengths of all two-dimensional center line segments are integrated to determine the three-dimensional length of the target blood vessel;

[0008] According to the two-dimensional center line of the target blood vessel, the image coordinates of the starting point and the ending point of the target blood vessel are determined. Combining with the intracranial arterial angiography image, the time-density curves corresponding to the starting point and the ending point of the target blood vessel are generated to obtain the time required for the contrast agent to flow through the entire target blood vessel. Then, in combination with the three-dimensional length of the target blood vessel, the average blood flow velocity in the target blood vessel is obtained;

[0009] Based on the three-dimensional diameter, three-dimensional length, and average blood flow velocity of the target blood vessel, the functional evaluation of intracranial artery stenosis is completed.

[0010] In one embodiment, the determining the three-dimensional length of the target blood vessel according to the gray value distribution on the two-dimensional center line of the target blood vessel includes:

[0011] The two-dimensional center line of the target blood vessel is discretized into multiple two-dimensional center line segments, and the two-dimensional length and average gray value of the two-dimensional center line segments are calculated. The maximum value in the average gray value is defined as the reference gray value, and the corresponding two-dimensional length is defined as the reference two-dimensional length, which serves as the preset reference parameter;

[0012] The reference length is calculated according to the reference two-dimensional length and the projection parameters stored in the intracranial arterial angiography image data;

[0013] According to the two-dimensional length and average gray value of the two-dimensional center line segment, in combination with the reference two-dimensional length, reference length, and reference gray value, the three-dimensional length corresponding to the two-dimensional center line segment is calculated;

[0014] The three-dimensional lengths corresponding to all two-dimensional center line segments are summed to obtain the three-dimensional length of the target blood vessel.

[0015] In one embodiment, the calculating the three-dimensional length corresponding to the two-dimensional center line segment according to the two-dimensional length and average gray value of the two-dimensional center line segment, in combination with the reference two-dimensional length, reference length, and reference gray value includes:

[0016] According to the two-dimensional length of the two-dimensional center line segment and the reference two-dimensional length, the projection length correction coefficient of the two-dimensional center line segment is calculated;

[0017] According to the average gray value of the two-dimensional center line segment and the reference gray value, the projection reduction correction coefficient of the two-dimensional center line segment is calculated;

[0018] Calculate the three-dimensional length corresponding to the two-dimensional centerline segment based on the projection length correction coefficient, the projection reduction correction coefficient, and the reference length.

[0019] In one embodiment, the calculating the projection reduction correction coefficient of the two-dimensional centerline segment according to the average gray value and the reference gray value of the two-dimensional centerline segment includes:

[0020] Calculate the change in contrast agent concentration of the two-dimensional centerline segment according to the average gray value of the two-dimensional centerline segment and the background gray value;

[0021] Calculate the reference value of the change in contrast agent concentration according to the reference gray value and the background gray value;

[0022] Calculate the projection reduction correction coefficient of the two-dimensional centerline segment according to the change in contrast agent concentration of the two-dimensional centerline segment and the reference value of the change in contrast agent concentration.

[0023] In one embodiment, the processing the obtained intracranial arterial angiography image to obtain the two-dimensional centerline and the two-dimensional contour line of the target blood vessel to determine the three-dimensional diameter of the target blood vessel includes:

[0024] Process the obtained intracranial arterial angiography image, and select a frame of image with the clearest blood vessel visualization as the key frame;

[0025] Use a pre-trained AI model to segment the target blood vessel on the key frame to obtain a binary segmentation map of the target blood vessel, where the target blood vessel is one of MCA, ICA, BA, or VA;

[0026] Apply an erosion algorithm to refine the binary segmentation map of the target blood vessel, extract the two-dimensional centerline and the two-dimensional contour line of the target blood vessel, and determine the three-dimensional diameter of the target blood vessel according to the two-dimensional centerline and the contour line of the target blood vessel.

[0027] In one embodiment, the determining the three-dimensional diameter of the target blood vessel according to the two-dimensional centerline and the contour line of the target blood vessel includes:

[0028] Obtain the two-dimensional diameter on the two-dimensional centerline according to the distance between each discrete point on the two-dimensional centerline and the contour line;

[0029] Obtain the three-dimensional diameter of the target blood vessel according to the two-dimensional diameter and the projection parameters stored in the intracranial arterial angiography image data.

[0030] In one embodiment, the generating the time-density curves corresponding to the starting point and the ending point of the target blood vessel includes:

[0031] Taking the image coordinates of the starting point and the ending point of the target blood vessel as the center, establish an n*n sampling area;

[0032] On the intracranial artery angiography images, the average gray value within the sampling area is calculated frame by frame to generate the time-gray curves corresponding to the starting point and ending point of the target blood vessel;

[0033] According to the time-gray curves, the background gray value when the contrast agent has not flowed into the target blood vessel is calculated. The time-gray curves are translated downward by the magnitude of the background gray value and then flipped upward with the zero axis as the symmetry axis to obtain the time-density curves.

[0034] On the other hand, the present invention provides a functional evaluation device for intracranial artery stenosis, and the device includes:

[0035] A three-dimensional diameter determination module, configured to process the acquired intracranial artery angiography images to obtain the two-dimensional center line and two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel;

[0036] A three-dimensional length determination module, configured to divide the two-dimensional center line of the target blood vessel into multiple two-dimensional center line segments according to the gray value distribution on the two-dimensional center line of the target blood vessel. Based on the two-dimensional length and average gray value of each two-dimensional center line segment, and in combination with preset reference parameters, calculate the three-dimensional length of each two-dimensional center line segment, and finally integrate the three-dimensional lengths of all two-dimensional center line segments to determine the three-dimensional length of the target blood vessel;

[0037] A blood flow velocity calculation module, configured to determine the image coordinates of the starting point and ending point of the target blood vessel according to the two-dimensional center line of the target blood vessel, generate the time-density curves corresponding to the starting point and ending point of the target blood vessel in combination with the intracranial artery angiography images to obtain the time required for the contrast agent to flow through the entire target blood vessel, and then obtain the average blood flow velocity within the target blood vessel in combination with the three-dimensional length of the target blood vessel;

[0038] An evaluation module, configured to complete the functional evaluation of intracranial artery stenosis based on the three-dimensional diameter, three-dimensional length, and average blood flow velocity of the target blood vessel.

[0039] On yet another aspect, the present invention provides a computer device, including a memory and a processor. When the processor executes the computer program, the following steps are implemented:

[0040] Process the acquired intracranial artery angiography images to obtain the two-dimensional center line and two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel;

[0041] According to the gray value distribution on the two-dimensional center line of the target blood vessel, the two-dimensional center line of the target blood vessel is segmented into multiple two-dimensional center line segments. Based on the two-dimensional length and average gray value of each two-dimensional center line segment, and in combination with preset reference parameters, the three-dimensional length of each two-dimensional center line segment is calculated. Finally, the three-dimensional lengths of all two-dimensional center line segments are integrated to determine the three-dimensional length of the target blood vessel;

[0042] According to the two-dimensional center line of the target blood vessel, the image coordinates of the starting point and the ending point of the target blood vessel are determined. Combining with the intracranial arterial angiography image, the time-density curves corresponding to the starting point and the ending point of the target blood vessel are generated to obtain the time required for the contrast agent to flow through the entire target blood vessel. Then, in combination with the three-dimensional length of the target blood vessel, the average blood flow velocity in the target blood vessel is obtained;

[0043] Based on the three-dimensional diameter, three-dimensional length, and average blood flow velocity of the target blood vessel, the functional evaluation of intracranial artery stenosis is completed.

[0044] On the other hand, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0045] Process the obtained intracranial arterial angiography image to obtain the two-dimensional center line and two-dimensional contour line of the target blood vessel to determine the three-dimensional diameter of the target blood vessel;

[0046] According to the gray value distribution on the two-dimensional center line of the target blood vessel, the two-dimensional center line of the target blood vessel is segmented into multiple two-dimensional center line segments. Based on the two-dimensional length and average gray value of each two-dimensional center line segment, and in combination with preset reference parameters, the three-dimensional length of each two-dimensional center line segment is calculated. Finally, the three-dimensional lengths of all two-dimensional center line segments are integrated to determine the three-dimensional length of the target blood vessel;

[0047] According to the two-dimensional center line of the target blood vessel, the image coordinates of the starting point and the ending point of the target blood vessel are determined. Combining with the intracranial arterial angiography image, the time-density curves corresponding to the starting point and the ending point of the target blood vessel are generated to obtain the time required for the contrast agent to flow through the entire target blood vessel. Then, in combination with the three-dimensional length of the target blood vessel, the average blood flow velocity in the target blood vessel is obtained;

[0048] Based on the three-dimensional diameter, three-dimensional length, and average blood flow velocity of the target blood vessel, the functional evaluation of intracranial artery stenosis is completed.

[0049] Compared with the prior art, the present invention aims to calculate the three-dimensional length of the target blood vessel directly from the gray value distribution on the two-dimensional center line in a more concise manner. This method avoids complex three-dimensional reconstruction steps, simplifies the calculation process, and improves the evaluation accuracy and reliability at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 It is a logic block diagram of a functional evaluation method for intracranial artery stenosis in an embodiment.

[0051] Figure 2 It is a schematic flow diagram of a functional evaluation method for intracranial artery stenosis in an embodiment. Detailed implementation manners

[0052] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0053] As Figure 1 and Figure 2 shown, a functional evaluation method for intracranial artery stenosis of the present invention includes the following steps:

[0054] Step S100: Obtain intracranial artery angiography images, which are composed of a series of multi-frame angiography images at the same angiography angle.

[0055] Step S110: In the intracranial artery angiography images, select the frame with the clearest blood vessel visualization as the key frame, and use a pre-trained AI model to segment the target blood vessel on the key frame to obtain a binary segmentation map of the target blood vessel.

[0056] Step S120: Apply an erosion algorithm to refine the binary segmentation map of the target blood vessel, extract the two-dimensional center line and two-dimensional contour line of the target blood vessel, determine the three-dimensional length of the target blood vessel according to the gray value distribution on the two-dimensional center line of the target blood vessel, and determine the three-dimensional diameter of the target blood vessel according to the two-dimensional center line and the contour line.

[0057] Step S130: According to the two-dimensional center line of the target blood vessel, determine the image coordinates of the starting point and the ending point of the target blood vessel. Combine with the intracranial artery angiography images to generate time-density curves corresponding to the starting point and the ending point of the target blood vessel. Obtain the time when the contrast agent flows into the target blood vessel according to the time-density curve of the starting point of the target blood vessel, and obtain the time when the contrast agent flows out of the target blood vessel according to the time-density curve corresponding to the ending point of the target blood vessel.

[0058] Step S140: According to the time when the contrast agent flows into the target blood vessel and the time when the contrast agent flows out of the target blood vessel, obtain the time required for the contrast agent to flow through the entire target blood vessel. Combine with the three-dimensional length of the target blood vessel to obtain the average blood flow velocity in the target blood vessel.

[0059] Step S150: Obtain functional evaluation parameters for intracranial artery stenosis according to the three-dimensional length, three-dimensional diameter and average blood flow velocity of the target blood vessel.

[0060] In step S100, the intracranial arterial angiography images obtained are image data taken at the same angiographic angle and consist of a series of multiple frames in time, covering the entire angiographic process of the contrast agent flowing into and out of the target blood vessel.

[0061] In one embodiment, the method provided by the present invention only needs to import one angiographic image to achieve the functional evaluation of intracranial artery stenosis, without using a pressure wire, reducing the trauma to the patient and saving medical costs.

[0062] In step S110, the target blood vessel is segmented on the key frame using a pre-trained AI model, and a binary segmentation map of the target blood vessel can be obtained. This process can achieve a high degree of automation, avoiding manual delineation of the blood vessel boundary, and having higher repeatability, providing strong support for subsequent analysis processes.

[0063] In one embodiment, the target blood vessel segmentation method consists of the following steps:

[0064] Use the first AI model to perform category judgment on the key frame to determine the category of the intracranial artery developed in the key frame. The categories include anterior circulation arteries, posterior circulation arteries, and non-intracranial arteries.

[0065] Use the second AI model to segment the target blood vessel to obtain a binary segmentation map of the target blood vessel. The second AI model consists of two independent models, namely the anterior circulation segmentation model and the posterior circulation segmentation model. The anterior circulation includes MCA and ICA, and the posterior circulation includes BA and VA.

[0066] In step S120, an erosion algorithm is applied to refine the binary segmentation map of the target blood vessel to extract the two-dimensional centerline and two-dimensional contour line of the target blood vessel. The three-dimensional length of the target blood vessel is determined according to the gray value distribution on the two-dimensional centerline of the target blood vessel, and the three-dimensional diameter of the target blood vessel is determined according to the two-dimensional centerline and the contour line. This process realizes the acquisition of three-dimensional data of the target blood vessel, including three-dimensional diameter and three-dimensional length information, providing essential morphological information for subsequent calculation of functional parameters.

[0067] In one embodiment, determining the three-dimensional length of the target blood vessel according to the gray value distribution on the two-dimensional centerline of the target blood vessel includes:

[0068] Discretize the two-dimensional centerline of the target blood vessel into multiple two-dimensional centerline segments, calculate the two-dimensional length and average gray value of the two-dimensional centerline segments, define the maximum value in the average gray value as the reference gray value, and define the corresponding two-dimensional length as the reference two-dimensional length.

[0069] Calculate the reference length according to the reference two-dimensional length and the projection parameters saved in the intracranial arterial angiography image data.

[0070] According to the two-dimensional length and average gray value of the two-dimensional centerline segment, combined with the reference two-dimensional length, reference length, and reference gray value, the three-dimensional length corresponding to the two-dimensional centerline segment is calculated.

[0071] Sum up the three-dimensional lengths corresponding to all two-dimensional centerline segments to obtain the three-dimensional length of the target blood vessel.

[0072] Specifically, the two-dimensional centerline of the target blood vessel is discretized into n two-dimensional centerline segments, and the two-dimensional length L of each two-dimensional centerline segment is calculated. 2D,i and the average gray value I i .

[0073] Denote the maximum value in the average gray value as the reference gray value I ref , and the corresponding two-dimensional length is the reference two-dimensional length L 2D,ref .

[0074] Denote the three-dimensional length corresponding to the reference two-dimensional length as the reference length L 3D,ref , and according to the similar triangle relationship in the projection principle, its calculation formula is:

[0075] L 3D,ref = L 2D,ref * SOD / SID

[0076] where SOD is the patient's distance from the radiation source, and SID is the distance from the imaging plane to the radiation source.

[0077] Denote the three-dimensional length corresponding to the i-th two-dimensional centerline segment as L 3D,i , first calculate the projection length correction coefficient according to the two-dimensional length of the two-dimensional centerline segment and the reference two-dimensional length, denoted as a, and its calculation method is:

[0078] a = L 2D,i / L 2D,ref

[0079] This parameter corrects the non-uniformity of blood vessel discretization;

[0080] Secondly, according to the average gray value of the two-dimensional centerline segment and the reference gray value, calculate the projection reduction correction coefficient of the two-dimensional centerline segment, denoted as b, and its calculation method is:

[0081] b = (I B - I i ) / (I B - I ref )

[0082] where I Bis the background gray value, and this parameter corrects the uneven reduction of projection caused by blood vessel distortion.

[0083] Finally, the calculation formula for the three-dimensional length corresponding to the i-th two-dimensional centerline segment is:

[0084] L 3D,i = a * b * L 3D,ref

[0085] Denote the total three-dimensional length of the target blood vessel as L, and its calculation formula is:

[0086] L = L 3D,1 + L 3D,2 +... + L 3D,n

[0087] In one embodiment, determining the three-dimensional diameter of the target blood vessel according to the two-dimensional centerline and the contour line of the target blood vessel includes:

[0088] Obtain the two-dimensional diameter on the two-dimensional centerline according to the distance between each discrete point on the two-dimensional centerline and the contour line.

[0089] Obtain the three-dimensional diameter of the target blood vessel according to the two-dimensional diameter and the projection parameters stored in the intracranial arterial angiography image data.

[0090] In step S130, according to the two-dimensional centerline of the target blood vessel, determine the image coordinates of the starting point and the ending point of the target blood vessel, combine with the intracranial arterial angiography image, generate the time-density curves corresponding to the starting point and the ending point of the target blood vessel, obtain the time when the contrast agent flows into the target blood vessel according to the time-density curve of the starting point of the target blood vessel, and obtain the time when the contrast agent flows out of the target blood vessel according to the time-density curve corresponding to the ending point of the target blood vessel. This step realizes the acquisition of the blood flow time in the target blood vessel. Combining with the three-dimensional length of the target blood vessel, the blood flow velocity information can be further obtained.

[0091] In one embodiment, determining the image coordinates of the starting point and the ending point of the target blood vessel according to the two-dimensional centerline of the target blood vessel, and generating the time-density curves corresponding to the starting point and the ending point of the target blood vessel in combination with the intracranial arterial angiography image includes:

[0092] Taking the image coordinates of the starting point and the ending point of the target blood vessel as the center, establish an n * n sampling area, and the size of n is adaptively adjusted according to the type of the target blood vessel and the blood vessel diameter.

[0093] On the intracranial arterial angiography image, calculate the average gray value in the sampling area frame by frame to generate the time-gray curves corresponding to the starting point and the ending point of the target blood vessel.

[0094] According to the time-gray scale curve, the background gray scale value when the contrast agent has not flowed into the target blood vessel is calculated. The time-gray scale curve is translated downward by the magnitude of the background gray scale value and then flipped upward with the zero axis as the axis of symmetry to obtain the time-density curve.

[0095] In step S140, according to the time when the contrast agent flows into the target blood vessel and the time when the contrast agent flows out of the target blood vessel, the time required for the contrast agent to flow through the entire target blood vessel is obtained. Combining with the three-dimensional length of the target blood vessel, the average blood flow velocity in the target blood vessel is obtained. This step realizes the calculation of the average blood flow velocity in the target blood vessel and provides the essential blood flow state information for the subsequent calculation of functional parameters.

[0096] In one embodiment, denote the time when the contrast agent flows into the target blood vessel as t in , the time when the contrast agent flows out of the target blood vessel as t out , the three-dimensional length of the target blood vessel as L, the volume of the target blood vessel as V, and the calculation formula for the blood flow state is:

[0097] v = L / (t out - t in ), Q = V / (t out - t in )

[0098] where v is the average blood flow velocity and Q is the average blood flow rate.

[0099] In step S150, based on the three-dimensional length, three-dimensional diameter, and average blood flow velocity of the target blood vessel, functional evaluation parameters for intracranial artery stenosis are obtained. The functional evaluation parameters include: blood pressure gradient, blood flow fraction, etc. This step finally obtains the functional parameters of intracranial artery stenosis, providing further reference for the ischemic evaluation of intracranial artery stenosis on the basis of morphological evaluation, and has potential clinical value.

[0100] In one embodiment, using morphological information such as the three-dimensional length and three-dimensional diameter of the target blood vessel and blood state information such as average blood flow velocity and average blood flow rate, hemodynamic simulation of the target blood vessel can be performed. The core parameter of hemodynamic simulation is the perfusion pressure loss situation in the target blood vessel, and viscous loss and dilation loss need to be considered emphatically. Specifically, its calculation formula is:

[0101] ΔP = α * v + β * v 2

[0102] where ΔP is the pressure gradient in the target blood vessel, α is the viscous loss coefficient, which is generated by the fluid viscosity of the blood itself and is related to the three-dimensional blood vessel diameter, etc., β is the dilation loss coefficient, which is generated by the eddy current in the blood flow and is related to the stenosis degree of the target blood vessel, etc., and v is the average blood flow velocity.

[0103] In one embodiment, the formula for calculating the fractional flow in the target blood vessel is as follows:

[0104] FF = (Pa - ΔP) / Pa

[0105] Where FF is the fractional flow of the target blood vessel, Pa is the pressure at the starting point of the target blood vessel, which can be obtained on a physiological monitor in the catheterization laboratory, and ΔP is the pressure gradient of the target blood vessel, which can be obtained by the method in the previous embodiment.

[0106] In one embodiment, the method is implemented according to the following process steps.

[0107] Obtain intracranial arterial angiography images, which are composed of a series of multi-frame angiography images at the same angiographic angle.

[0108] In the intracranial arterial angiography images, select the frame with the clearest blood vessel visualization as the key frame, and use a pre-trained AI model to segment the target blood vessel on the key frame to obtain a binary segmentation map of the target blood vessel. The target blood vessel is one of MCA, ICA, BA, or VA.

[0109] Apply an erosion algorithm to refine the binary segmentation map of the target blood vessel, and extract the two-dimensional centerline and two-dimensional contour line of the target blood vessel.

[0110] Determine the three-dimensional length of the target blood vessel according to the gray value distribution on the two-dimensional centerline of the target blood vessel, and determine the three-dimensional diameter of the target blood vessel according to the two-dimensional centerline and contour line.

[0111] According to the two-dimensional centerline of the target blood vessel, determine the image coordinates of the starting point and ending point of the target blood vessel, and combine with the intracranial arterial angiography images to generate time-density curves corresponding to the starting point and ending point of the target blood vessel.

[0112] Obtain the time when the contrast agent flows into the target blood vessel according to the time-density curve of the starting point of the target blood vessel, and obtain the time when the contrast agent flows out of the target blood vessel according to the time-density curve corresponding to the ending point of the target blood vessel.

[0113] According to the time when the contrast agent flows into the target blood vessel and the time when the contrast agent flows out of the target blood vessel, obtain the time required for the contrast agent to flow through the entire target blood vessel, and combine with the three-dimensional length of the target blood vessel to obtain the average blood flow velocity in the target blood vessel.

[0114] Obtain the functional evaluation parameters of intracranial arterial stenosis according to the three-dimensional length, three-dimensional diameter, and average blood flow velocity of the target blood vessel.

[0115] It should be understood that although Figure 2The steps in the flow chart are shown in sequence according to the indication of the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 at least a part of the steps in Figure 2 may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0116] In one embodiment, the present invention provides a functional evaluation device for intracranial artery stenosis, including: a three-dimensional diameter determination module, a three-dimensional length determination module, a blood flow velocity calculation module, and an evaluation module, where:

[0117] The three-dimensional diameter determination module is used to process the acquired intracranial artery angiography image to obtain the two-dimensional center line and two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel.

[0118] The three-dimensional length determination module is used to divide the two-dimensional center line of the target blood vessel into multiple two-dimensional center line segments according to the gray value distribution on the two-dimensional center line of the target blood vessel. Based on the two-dimensional length and average gray value of each two-dimensional center line segment, and in combination with preset reference parameters, calculate the three-dimensional length of each two-dimensional center line segment, and finally integrate the three-dimensional lengths of all two-dimensional center line segments to determine the three-dimensional length of the target blood vessel.

[0119] The blood flow velocity calculation module is used to determine the image coordinates of the starting point and ending point of the target blood vessel according to the two-dimensional center line of the target blood vessel, generate the time-density curve corresponding to the starting point and ending point of the target blood vessel in combination with the intracranial artery angiography image, so as to obtain the time required for the contrast agent to flow through the entire target blood vessel, and then combine the three-dimensional length of the target blood vessel to obtain the average blood flow velocity in the target blood vessel.

[0120] The evaluation module is used to complete the functional evaluation of intracranial artery stenosis based on the three-dimensional diameter, three-dimensional length, and average blood flow velocity of the target blood vessel.

[0121] For the specific limitations of the functional evaluation device for intracranial artery stenosis, reference can be made to the limitations of the functional evaluation method for intracranial artery stenosis in the above text, which will not be elaborated here. Each module in the above functional evaluation device for intracranial artery stenosis can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0122] In one embodiment, a computer device is provided. The computer device may be a terminal, which includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a functional evaluation method for intracranial artery stenosis. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

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

[0124] Process the acquired intracranial artery angiography image to obtain the two-dimensional centerline and the two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel.

[0125] According to the gray value distribution on the two-dimensional centerline of the target blood vessel, divide the two-dimensional centerline of the target blood vessel into multiple two-dimensional centerline segments. Based on the two-dimensional length and the average gray value of each two-dimensional centerline segment, and in combination with preset reference parameters, calculate the three-dimensional length of each two-dimensional centerline segment. Finally, integrate the three-dimensional lengths of all two-dimensional centerline segments to determine the three-dimensional length of the target blood vessel.

[0126] Determine the image coordinates of the starting point and the ending point of the target blood vessel according to the two-dimensional centerline of the target blood vessel. Combine the intracranial artery angiography image to generate the time-density curves corresponding to the starting point and the ending point of the target blood vessel, so as to obtain the time required for the contrast agent to flow through the entire target blood vessel. Then, in combination with the three-dimensional length of the target blood vessel, obtain the average blood flow velocity in the target blood vessel.

[0127] Based on the three-dimensional diameter, the three-dimensional length, and the average blood flow velocity of the target blood vessel, complete the functional evaluation of intracranial artery stenosis.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented:

[0129] Process the acquired intracranial arterial angiography images to obtain the two-dimensional centerline and two-dimensional contour line of the target blood vessel, so as to determine the three-dimensional diameter of the target blood vessel.

[0130] According to the gray value distribution on the two-dimensional centerline of the target blood vessel, divide the two-dimensional centerline of the target blood vessel into multiple two-dimensional centerline segments. Based on the two-dimensional length and average gray value of each two-dimensional centerline segment, and in combination with preset reference parameters, calculate the three-dimensional length of each two-dimensional centerline segment. Finally, integrate the three-dimensional lengths of all two-dimensional centerline segments to determine the three-dimensional length of the target blood vessel.

[0131] Determine the image coordinates of the starting point and ending point of the target blood vessel according to the two-dimensional centerline of the target blood vessel. Combine the intracranial arterial angiography images to generate the time-density curves corresponding to the starting point and ending point of the target blood vessel, so as to obtain the time required for the contrast agent to flow through the entire target blood vessel. Then, combine the three-dimensional length of the target blood vessel to obtain the average blood flow velocity in the target blood vessel.

[0132] Based on the three-dimensional diameter, three-dimensional length and average blood flow velocity of the target blood vessel, complete the functional evaluation of intracranial artery stenosis.

[0133] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium used in the various embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0134] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0135] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent should be subject to the appended claims.

Claims

1. A functional assessment method for intracranial artery stenosis, characterized in that: The method comprises: Processing the acquired intracranial artery angiography images to obtain the two-dimensional center line and two-dimensional contour line of the target blood vessel to determine the three-dimensional diameter of the target blood vessel; According to the gray value distribution on the two-dimensional centerline of the target blood vessel, the two-dimensional centerline of the target blood vessel is divided into multiple two-dimensional centerline segments, and based on the two-dimensional length and average gray value of each two-dimensional centerline segment and combined with preset reference parameters, the three-dimensional length of each two-dimensional centerline segment is calculated, and finally the three-dimensional lengths of all two-dimensional centerline segments are integrated to determine the three-dimensional length of the target blood vessel; The image coordinates of the starting point and the ending point of the target blood vessel are determined according to the two-dimensional center line of the target blood vessel, and the time-density curves corresponding to the starting point and the ending point of the target blood vessel are generated in combination with the intracranial arterial angiography images to obtain the time required for the contrast agent to flow through the entire target blood vessel, and then the average blood flow velocity in the target blood vessel is obtained in combination with the three-dimensional length of the target blood vessel; Functional assessment of intracranial artery stenosis is completed based on the three-dimensional diameter, three-dimensional length and average blood flow velocity of the target vessel.

2. The functional assessment method for intracranial artery stenosis according to claim 1, characterized in that: Determining the three-dimensional length of the target blood vessel according to the gray value distribution on the two-dimensional center line of the target blood vessel includes: The two-dimensional centerline of the target blood vessel is discretized into a plurality of two-dimensional centerline segments, and the two-dimensional lengths and average grayscale values ​​of the two-dimensional centerline segments are calculated, and the maximum value of the average grayscale value is defined as the reference grayscale value, and the corresponding two-dimensional length is defined as the reference two-dimensional length, which is used as the preset reference parameter; The reference length is calculated based on the reference two-dimensional length and the projection parameters stored in the intracranial artery angiography image data; According to the two-dimensional length and the average gray value of the two-dimensional centerline segment, combined with the reference two-dimensional length, the reference length and the reference gray value, the three-dimensional length corresponding to the two-dimensional centerline segment is calculated; The three-dimensional lengths corresponding to all two-dimensional centerline segments are summed to obtain the three-dimensional length of the target blood vessel.

3. The functional assessment method for intracranial artery stenosis according to claim 2, characterized in that: The three-dimensional length corresponding to the two-dimensional centerline segment is calculated based on the two-dimensional length and the average gray value of the two-dimensional centerline segment, combined with the reference two-dimensional length, the reference length and the reference gray value, including: According to the two-dimensional length of the two-dimensional centerline segment and the reference two-dimensional length, a correction coefficient of the projection length of the two-dimensional centerline segment is calculated; The projection reduction correction coefficient of the two-dimensional centerline segment is calculated according to the average gray value and the reference gray value of the two-dimensional centerline segment; The three-dimensional length corresponding to the two-dimensional centerline segment is calculated based on the projection length correction factor, the projection reduction correction factor and the reference length.

4. The functional assessment method for intracranial artery stenosis according to claim 3, characterized in that: The projection reduction correction coefficient of the two-dimensional center line segment is calculated based on the average gray value and the reference gray value of the two-dimensional center line segment, including: The contrast agent concentration change of the two-dimensional centerline segment is calculated according to the average gray value of the two-dimensional centerline segment and the background gray value; The contrast agent concentration change reference value is calculated according to the reference gray value and the background gray value; The projection reduction correction coefficient of the two-dimensional centerline segment is calculated according to the contrast agent concentration change of the two-dimensional centerline segment and the contrast agent concentration change reference value.

5. The functional assessment method for intracranial artery stenosis according to claim 1, characterized in that: The step of processing the acquired intracranial artery angiography image to obtain a two-dimensional center line and a two-dimensional contour line of the target blood vessel to determine the three-dimensional diameter of the target blood vessel includes: Process the acquired intracranial artery angiography images and select the frame with the clearest blood vessel development as the key frame; Use the pre-trained AI model to segment the target blood vessel on the key frame to obtain a target blood vessel segmentation binary image, where the target blood vessel is one of the MCA, ICA, BA or VA; The erosion algorithm is used to refine the target blood vessel segmentation binary image, extract the two-dimensional center line and two-dimensional contour line of the target blood vessel, and determine the three-dimensional diameter of the target blood vessel based on the two-dimensional center line and contour line of the target blood vessel.

6. The functional assessment method for intracranial artery stenosis according to claim 5, characterized in that: Determining the three-dimensional diameter of the target blood vessel according to the two-dimensional center line and contour line of the target blood vessel includes: According to the distance between each discrete point on the two-dimensional center line and the contour line, the two-dimensional diameter on the two-dimensional center line is obtained; The three-dimensional diameter of the target blood vessel is obtained according to the two-dimensional diameter and the projection parameters stored in the intracranial artery angiography image data.

7. The functional assessment method for intracranial artery stenosis according to claim 1, characterized in that: The generating of the time-density curve corresponding to the starting point and the ending point of the target blood vessel comprises: Establish an n*n sampling area with the image coordinates of the starting point and the ending point of the target blood vessel as the center; On the intracranial artery angiography images, the average grayscale value in the sampling area is calculated frame by frame to generate the time-grayscale curve corresponding to the starting point and the ending point of the target blood vessel; According to the time-grayscale curve, the background grayscale value before the contrast agent flows into the target blood vessel is calculated, the time-grayscale curve is translated downward by the size of the background grayscale value, and then flipped upward with the zero axis as the symmetry axis to obtain the time-density curve.

8. A functional assessment device for intracranial artery stenosis, characterized in that: The device comprises: A three-dimensional diameter determination module is used to process the acquired intracranial artery angiography image to obtain a two-dimensional center line and a two-dimensional contour line of the target blood vessel to determine the three-dimensional diameter of the target blood vessel; A three-dimensional length determination module is used to divide the two-dimensional centerline of the target blood vessel into multiple two-dimensional centerline segments according to the grayscale value distribution on the two-dimensional centerline of the target blood vessel, calculate the three-dimensional length of each two-dimensional centerline segment based on the two-dimensional length and average grayscale value of each two-dimensional centerline segment and in combination with preset reference parameters, and finally integrate the three-dimensional lengths of all two-dimensional centerline segments to determine the three-dimensional length of the target blood vessel; The blood flow velocity calculation module is used to determine the image coordinates of the starting point and the ending point of the target blood vessel according to the two-dimensional center line of the target blood vessel, and generate the time-density curve corresponding to the starting point and the ending point of the target blood vessel in combination with the intracranial arterial angiography image, so as to obtain the time required for the contrast agent to flow through the entire target blood vessel, and then obtain the average blood flow velocity in the target blood vessel in combination with the three-dimensional length of the target blood vessel; The evaluation module is used to complete the functional evaluation of intracranial artery stenosis based on the three-dimensional diameter, three-dimensional length and average blood flow velocity of the target blood vessel.

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

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images