Vascular development evaluation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to a blood vessel development evaluation method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring an angiography image; based on a preset blood vessel extraction algorithm, performing extraction processing on the angiography image to obtain a blood vessel image; extracting blood vessel developing information of the blood vessel image from the blood vessel image; and inputting the blood vessel development information into a preset blood vessel development evaluation model to obtain a blood vessel development evaluation result. By adopting the method, the accuracy of vascular development evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical imaging technology, and in particular, to a method, device, computer device, readable storage medium, and program product for vascular imaging evaluation. Background Art

[0002] Ascending venography of the lower extremities is one of the main methods for examining lower extremity venous vascular diseases in clinical practice. In the related art, doctors observe and evaluate the imaging of blood vessels such as the lower extremity veins and iliac veins during the operation according to clinical experience, and manually continuously adjust the flow rate of the contrast agent to clearly and completely observe the condition of the lower extremity venous blood vessels. However, at present, the evaluation of the lower extremity venous imaging mainly relies on the subjective observation and clinical experience of doctors, and there is no objective standard for determining the flow rate of the contrast agent. If the flow rate is too large, small venous blood vessels may be damaged, and if the flow rate is too small, the lower extremity blood vessels cannot be completely imaged or the imaging quality is poor. Therefore, the accuracy of vascular imaging evaluation is relatively low. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, computer device, readable storage medium, and program product for vascular imaging evaluation that can improve the accuracy of vascular imaging evaluation in view of the above technical problems.

[0004] In a first aspect, the present application provides a method for vascular imaging evaluation, including:

[0005] Obtaining a vascular angiography image;

[0006] Performing extraction processing on the vascular angiography image based on a preset vascular extraction algorithm to obtain a vascular image; extracting vascular imaging information of the vascular image from the vascular image;

[0007] Inputting the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0008] In one embodiment, the vascular angiography image is obtained by injecting a contrast agent into a blood vessel based on a target flow rate, and the method further includes:

[0009] If the vascular imaging evaluation result does not meet the preset imaging evaluation conditions, adjusting the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate;

[0010] Injecting the contrast agent into the blood vessel based on the adjusted target flow rate, and continuing to execute the step of obtaining the vascular angiography image until the vascular imaging evaluation result meets the preset imaging evaluation conditions.

[0011] In one embodiment, the preset blood vessel extraction algorithm includes a segmentation algorithm and a morphological operation. Based on the preset blood vessel extraction algorithm, performing extraction processing on the angiography image to obtain a blood vessel image, including:

[0012] Performing segmentation processing on the angiography image based on the segmentation algorithm to obtain a segmented angiography image; performing morphological operations on the segmented angiography image to obtain complete blood vessel features, and determining the complete blood vessel features as the blood vessel image.

[0013] In one embodiment, the blood vessel development information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the blood vessel length of each hierarchical node, and the blood vessel perfusion information includes the contrast agent concentration value and the contrast agent flow rate value in the blood vessel.

[0014] In one embodiment, extracting the blood vessel structure information and the blood vessel perfusion information corresponding to the blood vessel image from the blood vessel image, including:

[0015] Extracting a blood vessel centerline from the blood vessel image based on a centerline extraction algorithm, searching for the root node and a plurality of leaf nodes corresponding to the blood vessel image based on the blood vessel centerline, the blood vessel diameter, and a preset prior rule, and constructing a blood vessel tree based on the root node and the plurality of leaf nodes;

[0016] Obtaining the number of blood vessels and the blood vessel length of each hierarchical node based on the blood vessel tree;

[0017] Obtaining the contrast agent concentration value from the blood vessel image, determining a blood vessel perfusion curve based on the correspondence between the contrast agent concentration value and time, and determining the slope of the blood vessel perfusion curve as the contrast agent flow rate value.

[0018] In one embodiment, the method further includes:

[0019] Obtaining a sample angiography image and a development evaluation label corresponding to the sample angiography image;

[0020] Performing extraction processing on the sample angiography blood vessel based on the preset blood vessel extraction algorithm to obtain a sample blood vessel image; extracting sample blood vessel information corresponding to the sample blood vessel image from the sample blood vessel image, where the sample blood vessel information includes sample structure information and sample blood vessel perfusion information;

[0021] Training an initial blood vessel development evaluation model based on the mapping relationship between the development evaluation label and the sample blood vessel information to obtain the preset blood vessel development evaluation model.

[0022] Second aspect, the present application further provides a vascular imaging evaluation device, including:

[0023] An acquisition module, configured to acquire angiography images;

[0024] An extraction module, configured to perform extraction processing on the angiography images based on a preset blood vessel extraction algorithm to obtain blood vessel images; and extract the vascular imaging information corresponding to the blood vessel images from the blood vessel images;

[0025] An input module, configured to input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0026] Third aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0027] Acquire angiography images;

[0028] Based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography images to obtain blood vessel images; and extract the vascular imaging information of the blood vessel images from the blood vessel images;

[0029] Input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0030] Fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0031] Acquire angiography images;

[0032] Based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography images to obtain blood vessel images; and extract the vascular imaging information of the blood vessel images from the blood vessel images;

[0033] Input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0034] Fifth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Acquire angiography images;

[0036] Based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography images to obtain blood vessel images; and extract the vascular imaging information of the blood vessel images from the blood vessel images;

[0037] Input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0038] The above-mentioned vascular imaging evaluation method, device, computer device, readable storage medium, and program product can automatically segment the developed venous blood vessels during the angiography process by extracting the vascular images from the angiography images, extracting the vascular imaging information from the vascular images, and inputting the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result. It can extract key information and features to evaluate the vascular imaging evaluation result and the vascular condition, improve the accuracy of vascular imaging evaluation, and thus achieve the purpose of optimizing the operation process, assisting doctors in diagnosis, improving angiography, and protecting patients. Description of the Drawings

[0039] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is a schematic flowchart of the vascular imaging evaluation method in an embodiment;

[0041] Figure 2 It is a schematic diagram of the angiography image of the lower limb venous orthograde blood vessels in an embodiment;

[0042] Figure 3 It is a schematic flowchart of the vascular imaging evaluation method in an embodiment;

[0043] Figure 4 It is a structural block diagram of the vascular imaging evaluation device in an embodiment;

[0044] Figure 5 It is an internal structure diagram of a computer device in an embodiment. Detailed Embodiments

[0045] To make the purpose, technical solutions, and advantages of the present application clearer, the following will further elaborate on the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In an exemplary embodiment, as Figure 1As shown, a method for vascular imaging evaluation is provided. In this embodiment, an example is given where this method is applied to a terminal. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0047] Step 101, obtain an angiography image.

[0048] Among them, the angiography image can be an image of blood vessels after injecting a contrast agent, and the angiography image can be a two-dimensional digital subtraction angiography (2D DSA) image. The blood vessels can be venous blood vessels of an organism, such as venous blood vessels in parts such as the thigh and arm. For example, the angiography image can be a lower limb venous anterograde angiography sequence.

[0049] Specifically, the terminal can inject the contrast agent into the blood vessels at a target flow rate. The terminal can collect the angiography image of the blood vessels injected with the contrast agent from a medical imaging device, such as Figure 2 as shown, Figure 2 is an angiography image of the lower limb venous anterograde blood vessels. Optionally, the target flow rate can be a preset default flow rate, or the contrast agent flow rate and flow volume are default set to the lowest, and the target flow rate can also randomly select a flow rate value from a preset flow rate range. The preset flow rate range can be set according to the normal operation of the blood vessels. For example, the preset flow rate range can be 0.6 ml / s to 1.6 ml / s.

[0050] Step 102, based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography image to obtain a blood vessel image; extract the vascular imaging information of the blood vessel image from the blood vessel image.

[0051] Among them, the blood vessel image can represent the blood vessel part in the angiography image. The vascular imaging information can reflect the structure of the blood vessels and / or the flow of the contrast agent in the blood vessels.

[0052] Specifically, the terminal can perform segmentation processing on the blood vessel part and the non-blood vessel part in the angiography image based on a preset blood vessel extraction algorithm, and extract and optimize the blood vessel part to obtain a blood vessel image. The terminal can extract the vascular imaging information corresponding to the blood vessel image from the structure of the blood vessels in the blood vessel image and the flow of the contrast agent in the blood vessels.

[0053] Step 103, input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0054] Among them, the preset vascular imaging evaluation model can be a machine learning model, such as a random forest, etc.

[0055] Specifically, the terminal can input the vascular imaging information into a preset vascular imaging evaluation model, process the vascular imaging information in the preset vascular imaging evaluation model, and obtain a vascular imaging evaluation result corresponding to the vascular imaging information.

[0056] In addition, if the vascular imaging evaluation result is that the imaging is too slow, the terminal determines that the vascular imaging evaluation result does not meet the preset imaging evaluation conditions, and the terminal controls the syringe to increase the flow rate and flow volume of the contrast agent until the vascular imaging evaluation result is complete imaging, then the acquisition of the angiography image is completed and the angiography image is output; if the vascular imaging evaluation result is vascular damage or abnormal flow rate, the terminal determines that the vascular imaging evaluation result does not meet the preset imaging evaluation conditions, and then the terminal controls the syringe to reduce the flow rate and flow volume of the contrast agent until the vascular imaging evaluation result is complete imaging, then the acquisition of the angiography image is completed and the angiography image is output.

[0057] The above-mentioned vascular imaging evaluation method can automatically segment the developed venous blood vessels during the angiography process by extracting the vascular images of the angiography images, extracting the vascular imaging information from the vascular images, and inputting the vascular imaging information into a preset vascular imaging evaluation model to obtain the vascular imaging evaluation result, and extract key information and features to evaluate the vascular imaging evaluation result and the vascular condition, improve the accuracy of vascular imaging evaluation, and thus achieve the purpose of optimizing the operation process, assisting doctors in diagnosis, improving angiography, and protecting patients.

[0058] In an exemplary embodiment, the vascular imaging evaluation method further includes:

[0059] If the vascular imaging evaluation result does not meet the preset imaging evaluation conditions, the target flow rate is adjusted based on a preset adjustment strategy to obtain an adjusted target flow rate; the contrast agent is injected into the blood vessel based on the adjusted target flow rate, and the step of obtaining the angiography image is continued until the vascular imaging evaluation result meets the preset imaging evaluation conditions.

[0060] Among them, the angiography image can be obtained by injecting the contrast agent into the blood vessel based on the target flow rate. The preset imaging evaluation condition can be that the vascular imaging evaluation result is complete imaging. The vascular imaging evaluation result can include complete imaging or incomplete imaging, and the reasons for incomplete imaging can include too slow imaging, vascular damage, or abnormal flow rate, etc.

[0061] Specifically, the terminal can determine whether the blood vessel imaging evaluation result is complete imaging. If the blood vessel imaging evaluation result is incomplete imaging, the terminal can determine the reason for the incomplete imaging based on the blood vessel imaging evaluation result, and adjust the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate. The terminal can inject the contrast agent into the blood vessel based on the adjusted target flow rate, and continue to execute the above-mentioned embodiment "acquire a blood vessel angiogram image" and subsequent steps. The terminal can determine whether the blood vessel imaging evaluation result corresponding to the adjusted target flow rate is complete imaging. If the blood vessel imaging evaluation result is still incomplete imaging, continue to adjust the flow rate of the contrast agent according to the preset adjustment strategy until the blood vessel imaging evaluation result is complete imaging. The terminal can output the blood vessel angiogram image, which can assist experts in diagnosis or can diagnose the blood vessel angiogram image based on a diagnosis model, etc.

[0062] Optionally, if the blood vessel imaging evaluation result is complete imaging, the terminal can output the blood vessel angiogram image, which can assist experts in diagnosis or can diagnose the blood vessel angiogram image based on a diagnosis model, etc.

[0063] Exemplarily, the preset adjustment strategy can be to increase or decrease the flow rate of the contrast agent. Adjusting the flow rate of the contrast agent needs to be carried out within a preset flow rate range, and the preset flow rate range can include multiple flow rates. For example, each gear can be set to 0.1 ml / s. If the terminal determines that the incomplete imaging is caused by too slow imaging of the blood vessels, it will increase one or more gears of the flow rate of the contrast agent and execute subsequent steps, and loop until the blood vessel imaging evaluation result is complete imaging. If the terminal determines that the blood vessel imaging evaluation result is blood vessel damage or abnormal flow rate, it will decrease one or more gears of the contrast agent flow rate and execute subsequent steps, and loop until the blood vessel imaging evaluation result is complete imaging. In addition, the operator can also determine whether to adjust the contrast agent parameters according to the actual situation, such as the position of the injection needle of the contrast agent, the Valsalva maneuver and other actual scenarios.

[0064] In this embodiment, by automatically adjusting the flow rate of the contrast agent and determining the optimal flow rate of the contrast agent through the blood vessel imaging evaluation result, the purpose of optimizing the operation process, assisting doctors in diagnosis, improving angiography and protecting users is achieved.

[0065] In an exemplary embodiment, the specific implementation process of the step "perform extraction processing on the blood vessel angiogram image based on a preset blood vessel extraction algorithm to obtain a blood vessel image" may include:

[0066] Perform segmentation processing on the blood vessel angiogram image based on a segmentation algorithm to obtain a segmented blood vessel angiogram image; perform morphological operations on the segmented blood vessel angiogram image to obtain complete blood vessel features, and determine the complete blood vessel features as the blood vessel image.

[0067] Among them, the preset blood vessel extraction algorithm includes a segmentation algorithm and morphological operations. The segmentation algorithm can be a threshold segmentation algorithm or a Frangi filtering algorithm, etc. The segmented angiography image can be the angiography image of the blood vessel part. The morphological operation can be operations such as dilation or erosion.

[0068] Specifically, the terminal can segment and extract the blood vessel part in the angiography image based on the segmentation algorithm to obtain the segmented angiography image. To ensure the continuity of the segmented angiography image, the terminal uses morphological operations to process the segmented angiography image to obtain the complete blood vessel features, and determines the complete blood vessel features as the blood vessel image.

[0069] Optionally, the terminal can select the corresponding segmentation algorithm based on the actual application scenario. For example, when the contrast of the angiography image is high, the terminal can select the threshold segmentation algorithm as the segmentation algorithm to extract the angiography image of the blood vessel part; when the angiography image is an image under a complex background, the terminal can select the Frangi filtering algorithm as the segmentation algorithm, which is not specifically limited here.

[0070] Optionally, the angiography image is a grayscale image. When the segmentation algorithm is the threshold segmentation algorithm, the terminal can use the preset threshold to judge the pixel points in the angiography image. For each pixel point, compare its grayscale value with the preset threshold. If the grayscale value of the pixel point is greater than or equal to the preset threshold, mark it as the blood vessel area; if the grayscale value of the pixel point is less than the preset threshold, mark it as the non-blood vessel area. Use the preset threshold to perform segmentation processing on the pixel points of the angiography image to obtain the segmented angiography image. The terminal can segment the non-blood vessel part and the blood vessel part in the angiography image to obtain the segmented angiography image. The preset threshold can be determined according to one of a fixed threshold, an adaptive threshold, or the Otsu's Method.

[0071] Optionally, the angiography image is a grayscale image. When the segmentation algorithm is the Frangi filtering algorithm, the terminal can perform Gaussian filtering on the angiography image to obtain the Gaussian-filtered blood vessel image, calculate the second-order partial derivatives of the pixel points in the Gaussian-filtered blood vessel image, calculate the Hessian matrix based on the second-order partial derivatives, and calculate the eigenvalues and eigenvectors of the Hessian matrix. The terminal can judge whether the pixel points of the blood vessel image belong to the blood vessel structure based on the eigenvalues. The terminal calculates the Frangi response based on the eigenvalues to obtain the enhanced blood vessel image, and determines the enhanced blood vessel image as the segmented angiography image.

[0072] Optionally, the terminal can customize a structural element and perform an erosion operation on the segmented angiography image based on the structural element to obtain an angiography image after the erosion operation, and determine the angiography image after the erosion operation as the blood vessel image. The terminal can also perform a dilation operation on the segmented angiography image based on the structural element to obtain an angiography image after the dilation operation, and determine the angiography image after the dilation operation as the blood vessel image. The terminal can also perform an operation of first dilating and then eroding or first eroding and then dilating on the segmented angiography graph.

[0073] In this embodiment, by segmenting and optimizing the angiography image, a blood vessel image is obtained, which is convenient for subsequent evaluation of the development condition of the blood vessel image and improves the usability of the image.

[0074] In an exemplary embodiment, the blood vessel development information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the length of blood vessels at each hierarchical node, and the blood vessel perfusion information includes the concentration value of the contrast agent and the flow rate value of the contrast agent in the blood vessels.

[0075] Among them, the blood vessel structure information can reflect the blood vessel structure, and the blood vessel perfusion information can reflect the flow condition of the contrast agent in the blood vessels.

[0076] Specifically, the terminal can extract the number of blood vessels at each hierarchical node and the length of blood vessels at each hierarchical node in the blood vessel structure from the blood vessel image. The terminal can obtain the concentration value of the contrast agent and the flow rate value of the contrast agent based on the blood vessel image.

[0077] In an exemplary embodiment, the specific implementation process of the step "extracting the blood vessel structure information and blood vessel perfusion information corresponding to the blood vessel image from the blood vessel image" may include:

[0078] Extracting the blood vessel centerline in the blood vessel image based on the centerline extraction algorithm, searching for the root node and multiple leaf nodes corresponding to the blood vessel image based on the blood vessel centerline, blood vessel diameter and preset prior rules, and constructing a blood vessel tree based on the root node and multiple leaf nodes; obtaining the number of blood vessels and the length of blood vessels at each hierarchical node based on the blood vessel tree; obtaining the contrast agent concentration value from the blood vessel image, and determining the blood vessel perfusion curve based on the corresponding relationship between the contrast agent concentration value and time, and determining the slope of the blood vessel perfusion curve as the flow rate value of the contrast agent.

[0079] Among them, the preset prior rules are rules preset based on the anatomical structure characteristics, growth rules, etc. of blood vessels. The contrast agent concentration can be determined by the intensity value of the contrast agent under X-ray.

[0080] Specifically, the terminal can extract the blood vessel centerline from the blood vessel image based on the centerline extraction algorithm. The terminal can use the edge detection algorithm to identify the edge contour of the blood vessel. The terminal can calculate the shortest distance from the pixel points on the blood vessel centerline to the edge contour to determine the blood vessel diameter. The terminal can specify the root node based on the preset prior rules and the blood vessel diameter, and search for each leaf node based on the root node. The terminal can traverse the blood vessel centerline layer by layer starting from the root node, and connect adjacent leaf nodes to construct a blood vessel tree. The terminal can traverse layer by layer starting from the root node and record the number of nodes in each layer. The number of nodes in each layer is the number of blood vessels in that layer. The terminal can superimpose the distances from the points on the centerline of each blood vessel in the same layer to the next adjacent node to obtain the blood vessel length of that layer. The terminal determines the number of blood vessels and the blood vessel length of each hierarchical node as the blood vessel structure information.

[0081] The terminal can obtain the contrast agent concentration value from the blood vessel image. The terminal can draw a real-time blood vessel perfusion curve based on the corresponding relationship between the contrast agent concentration value and time. The abscissa of the blood vessel perfusion curve is time, and the ordinate is the contrast agent concentration value. The terminal can determine the slope of the blood vessel perfusion curve as the contrast agent flow rate value. Additionally, the terminal can calculate the flow rate value of the contrast agent in the blood vessel by the optical flow method.

[0082] In this embodiment, the blood vessel structure information and the blood vessel perfusion information are extracted to realize the extraction of key information in the blood vessel image, so as to facilitate the evaluation of the blood vessel condition.

[0083] In an exemplary embodiment, the blood vessel imaging evaluation method further includes:

[0084] Obtain a sample blood vessel angiography image and the corresponding imaging evaluation label of the sample blood vessel angiography image; based on a preset blood vessel extraction algorithm, perform extraction processing on the sample blood vessel angiography to obtain a sample blood vessel image; extract the sample blood vessel information corresponding to the sample blood vessel image from the sample blood vessel image; train an initial blood vessel imaging evaluation model based on the mapping relationship between the imaging evaluation label and the sample blood vessel information to obtain a preset blood vessel imaging evaluation model.

[0085] Among them, the sample angiography image can be a developed image containing the contrast indwelling needle punctured at different positions, such as the superficial veins like the great saphenous vein, dorsal venous arch of foot, communicating vein, etc.; there are differences in the vascular development evaluation results at different puncture positions. For example, when punctured in the great saphenous vein, the contrast agent may directly flow back from the smooth great saphenous vein to the blood vessels above the knee, while the deep veins in the calf segment usually do not develop. The sample vascular information includes sample structure information and sample vascular perfusion information. The sample structure information includes the number of sample blood vessels and the length of sample blood vessels at each hierarchical node, and the sample vascular perfusion information includes the sample contrast agent concentration value and the sample contrast agent flow rate value in the blood vessels. The development evaluation label characterizes the development situation of the sample angiography image, and can include a fully developed label, a label indicating that the development is too slow and does not meet the requirements, a label for vascular injury or abnormal flow rate, etc.

[0086] Specifically, the terminal can obtain sample angiography images at various different positions and different contrast agent flow rates, and obtain the development evaluation labels corresponding to the sample angiography images. The terminal can perform segmentation processing on the sample angiography image based on a segmentation algorithm to obtain the segmented sample angiography image; perform morphological operations on the segmented sample angiography image to obtain the complete sample vascular characteristics, and determine the complete sample vascular characteristics as the sample vascular image. The terminal extracts the sample vascular centerline from the sample vascular image based on the centerline extraction algorithm, searches for the root node and multiple leaf nodes corresponding to the sample vascular image based on the sample vascular centerline, sample vascular diameter, and preset prior rules, constructs a sample vascular tree based on the root node and multiple leaf nodes; obtains the number of sample blood vessels and the length of sample blood vessels at each hierarchical node based on the sample vascular tree; obtains the sample contrast agent concentration value from the sample vascular image, and determines the sample vascular perfusion curve based on the corresponding relationship between the sample contrast agent concentration value and time, and determines the slope of the sample vascular perfusion curve as the sample contrast agent flow rate value. It should be understood that the specific processing process is the same as that in the above embodiment and will not be elaborated here.

[0087] The terminal can establish a mapping relationship between the development evaluation label and the sample vascular information. The terminal can use the sample vascular information as the input of the initial vascular development model to obtain the sample vascular development evaluation result, calculate the optimization parameters of the initial vascular development model based on the sample vascular development evaluation result and the development evaluation label, optimize the parameters of the initial vascular development model based on the optimization parameters, obtain the initial vascular development evaluation model trained based on the mapping relationship between the development evaluation label and the sample vascular information, and evaluate and optimize the model to obtain the preset vascular development evaluation model.

[0088] The terminal can input the vascular structure information and the vascular perfusion information into the preset vascular development evaluation model, and can output the corresponding vascular development evaluation result.

[0089] Optionally, when the preset vascular imaging evaluation model is a random forest, the random forest consists of multiple decision trees. The terminal can input the vascular feature vector composed of vascular structure information and vascular perfusion information into each decision tree of the forest. The decision tree starts from the root node, makes conditional judgments based on each feature value in the feature vector, and traverses downward along the matching branches. When each decision tree traverses to the leaf node, it outputs a classification result. The random forest can obtain the vascular imaging evaluation result through voting based on the classification results of all decision trees.

[0090] In this embodiment, by training the preset vascular evaluation model, the vascular imaging situation can be evaluated, and the automatic evaluation and classification of the vascular imaging evaluation result can be realized. Thus, the flow rate of the contrast agent can be adjusted according to the vascular imaging situation, achieving the purposes of optimizing the operation process, assisting doctors in diagnosis, improving angiography, and protecting patients.

[0091] In an exemplary embodiment, as Figure 3 shown, Figure 3 a flowchart of a method for evaluating vascular imaging is provided. The method specifically includes the following steps:

[0092] Step 301: The terminal injects the contrast agent into the blood vessel based on the target speed, and by default, sets the flow rate and flow volume of the contrast agent to the lowest, such as 0.6 ml / s.

[0093] Step 302: The terminal collects DSA images of the injected contrast agent.

[0094] Step 303: The terminal performs extraction processing on the angiography image based on the preset vascular extraction algorithm to obtain a vascular image; extracts the vascular structure information and vascular perfusion information of the vascular image from the vascular image.

[0095] Step 304: The terminal inputs the vascular structure information and the vascular perfusion information into the preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0096] Step 305: The terminal determines whether the imaging evaluation result meets the preset imaging evaluation conditions.

[0097] Step 306: If the vascular imaging evaluation result is complete imaging, the terminal automatically records information such as the flow rate and flow volume, archives the images, and the acquisition is completed.

[0098] Step 307: If the vascular imaging evaluation result shows that the imaging is too slow and does not meet the requirements, the terminal increases the flow rate and flow volume of the contrast agent by one level and returns to Step 302, and loops in this way until the vascular imaging evaluation result is complete imaging and meets the requirements.

[0099] Step 308: If the vascular imaging evaluation result is vascular injury or abnormal flow rate, the terminal reduces the contrast agent flow rate by one level and returns to Step 302, repeating this cycle until the vascular imaging evaluation result meets the requirement of complete imaging.

[0100] In this embodiment, by automatically adjusting parameters such as the contrast agent flow rate and flow volume, it is possible to automatically segment the developed venous blood vessels during the angiography process, extract key information and features to evaluate the vascular imaging result and the vascular condition, and determine the optimal contrast agent flow rate and flow volume according to the vascular imaging evaluation result, so as to achieve the purpose of optimizing the operation process, assisting doctors in diagnosis, improving angiography, and protecting patients.

[0101] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are displayed sequentially according to the arrows, these steps do not necessarily need to be executed sequentially in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily need to be executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least some of the steps or stages in other steps or other steps.

[0102] Based on the same inventive concept, the embodiments of the present application also provide a vascular imaging evaluation device for implementing the above-mentioned vascular imaging evaluation method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the vascular imaging evaluation device provided below can refer to the limitations on the vascular imaging evaluation method in the above text, and will not be repeated here.

[0103] In an exemplary embodiment, as Figure 4 shown, a vascular imaging evaluation device 40 is provided, including: an acquisition module 41, an extraction module 42, and an input module 43, where:

[0104] The acquisition module 41 is used to acquire angiography images;

[0105] The extraction module 42 is used to perform extraction processing on the angiography image based on a preset blood vessel extraction algorithm to obtain a blood vessel image; and extract the vascular imaging information corresponding to the blood vessel image from the blood vessel image;

[0106] The input module 43 is used to input the vascular imaging information into a preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0107] In one embodiment, the input module 43 is further configured to, if the blood vessel imaging evaluation result does not meet the preset imaging evaluation condition, adjust the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate;

[0108] Inject the contrast agent into the blood vessel based on the adjusted target flow rate, and continue to execute the step of acquiring the angiogram until the blood vessel imaging evaluation result meets the preset imaging evaluation condition.

[0109] In one embodiment, the extraction module 42 is specifically configured to perform segmentation processing on the angiogram based on a segmentation algorithm to obtain a segmented angiogram; perform morphological operations on the segmented angiogram to obtain complete blood vessel features, and determine the complete blood vessel features as the blood vessel image.

[0110] In one embodiment, the blood vessel imaging information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the length of blood vessels at each hierarchical node, and the blood vessel perfusion information includes the contrast agent concentration value and the contrast agent flow rate value in the blood vessel.

[0111] In one embodiment, the extraction module 42 is specifically configured to extract the blood vessel centerline from the blood vessel image based on a centerline extraction algorithm, search for the root node and multiple leaf nodes corresponding to the blood vessel image based on the blood vessel centerline, blood vessel diameter, and preset prior rules, and construct a blood vessel tree based on the root node and multiple leaf nodes;

[0112] Obtain the number of blood vessels and the length of blood vessels at each hierarchical node based on the blood vessel tree;

[0113] Obtain the contrast agent concentration value from the blood vessel image, determine the blood vessel perfusion curve based on the correspondence between the contrast agent concentration value and time, and determine the slope of the blood vessel perfusion curve as the contrast agent flow rate value.

[0114] In one embodiment, the training module is configured to obtain a sample angiogram and a development evaluation label corresponding to the sample angiogram;

[0115] Perform extraction processing on the sample angiogram blood vessel based on a preset blood vessel extraction algorithm to obtain a sample blood vessel image; extract sample blood vessel information corresponding to the sample blood vessel image from the sample blood vessel image, where the sample blood vessel information includes sample structure information and sample blood vessel perfusion information;

[0116] Train an initial blood vessel imaging evaluation model based on the mapping relationship between the development evaluation label and the sample blood vessel information to obtain a preset blood vessel imaging evaluation model.

[0117] Each module in the above-mentioned vascular imaging evaluation device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0118] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. 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 input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. The computer program, when executed by the processor, implements a vascular imaging evaluation method. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0119] Those skilled in the art can understand that Figure 5 the structure shown in

[0120] merely represents a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0120] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0121] Obtain an angiography image;

[0122] Based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography image to obtain a blood vessel image; extract the blood vessel development information of the blood vessel image from the blood vessel image;

[0123] Input the blood vessel development information into a preset blood vessel development evaluation model to obtain a blood vessel development evaluation result.

[0124] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0125] If the blood vessel development evaluation result does not meet the preset development evaluation conditions, then adjust the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate;

[0126] Inject the contrast agent into the blood vessel based on the adjusted target flow rate, and continue to execute the step of acquiring the angiography image until the blood vessel development evaluation result meets the preset development evaluation conditions.

[0127] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0128] Perform segmentation processing on the angiography image based on a segmentation algorithm to obtain a segmented angiography image; perform processing on the segmented angiography image using morphological operations to obtain complete blood vessel features, and determine the complete blood vessel features as the blood vessel image.

[0129] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0130] The blood vessel development information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the length of blood vessels at each hierarchical node. The blood vessel perfusion information includes the contrast agent concentration value and the contrast agent flow rate value in the blood vessel.

[0131] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0132] Extract the blood vessel centerline from the blood vessel image based on the centerline extraction algorithm, search for the root node and multiple leaf nodes corresponding to the blood vessel image based on the blood vessel centerline, blood vessel diameter, and preset prior rules, and construct a blood vessel tree based on the root node and multiple leaf nodes;

[0133] Obtain the number of blood vessels and the length of blood vessels at each hierarchical node based on the blood vessel tree;

[0134] Obtain the contrast agent concentration value from the blood vessel image, and determine the blood vessel perfusion curve based on the correspondence between the contrast agent concentration value and time, and determine the slope of the blood vessel perfusion curve as the contrast agent flow rate value.

[0135] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0136] Obtain a sample angiography image and a development evaluation label corresponding to the sample angiography image;

[0137] Based on a preset blood vessel extraction algorithm, perform extraction processing on the blood vessels in the sample angiography to obtain a sample blood vessel image; extract sample blood vessel information corresponding to the sample blood vessel image from the sample blood vessel image, where the sample blood vessel information includes sample structure information and sample blood vessel perfusion information;

[0138] Train an initial blood vessel development evaluation model based on the mapping relationship between the development evaluation label and the sample blood vessel information to obtain a preset blood vessel development evaluation model.

[0139] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0140] Obtain an angiography image;

[0141] Based on a preset blood vessel extraction algorithm, perform extraction processing on the angiography image to obtain a blood vessel image; extract the blood vessel development information of the blood vessel image from the blood vessel image;

[0142] Input the blood vessel development information into the preset blood vessel development evaluation model to obtain a blood vessel development evaluation result.

[0143] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0144] If the blood vessel development evaluation result does not meet the preset development evaluation condition, then adjust the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate;

[0145] Inject a contrast agent into the blood vessel based on the adjusted target flow rate, and continue to execute the step of obtaining the angiography image until the blood vessel development evaluation result meets the preset development evaluation condition.

[0146] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0147] Based on a segmentation algorithm, perform segmentation processing on the angiography image to obtain a segmented angiography image; perform morphological operations on the segmented angiography image to obtain complete blood vessel features, and determine the complete blood vessel features as the blood vessel image.

[0148] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0149] The vascular imaging information includes vascular structure information and vascular perfusion information. The vascular structure information includes the number of blood vessels and the length of blood vessels at each hierarchical node. The vascular perfusion information includes the concentration value of the contrast agent and the flow rate value of the contrast agent in the blood vessels.

[0150] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0151] Extract the vascular centerline from the vascular image based on the centerline extraction algorithm, search for the root node and multiple leaf nodes corresponding to the vascular image based on the vascular centerline, the vascular diameter, and the preset prior rules, and construct a vascular tree based on the root node and the multiple leaf nodes;

[0152] Obtain the number of blood vessels and the length of blood vessels at each hierarchical node based on the vascular tree;

[0153] Obtain the concentration value of the contrast agent from the vascular image, determine the vascular perfusion curve based on the corresponding relationship between the concentration value of the contrast agent and time, and determine the flow rate value of the contrast agent as the slope of the vascular perfusion curve.

[0154] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0155] Obtain a sample vascular angiography image and the corresponding imaging evaluation label of the sample vascular angiography image;

[0156] Based on the preset vascular extraction algorithm, perform extraction processing on the sample vascular angiography to obtain a sample vascular image; extract the sample vascular information corresponding to the sample vascular image from the sample vascular image, and the sample vascular information includes sample structure information and sample vascular perfusion information;

[0157] Train the initial vascular imaging evaluation model based on the mapping relationship between the imaging evaluation label and the sample vascular information to obtain a preset vascular imaging evaluation model.

[0158] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0159] Obtain a vascular angiography image;

[0160] Based on the preset vascular extraction algorithm, perform extraction processing on the vascular angiography image to obtain a vascular image; extract the vascular imaging information of the vascular image from the vascular image;

[0161] Input the vascular imaging information into the preset vascular imaging evaluation model to obtain a vascular imaging evaluation result.

[0162] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0163] If the angiography evaluation result does not meet the preset angiography evaluation criteria, the target flow rate is adjusted based on the preset adjustment strategy to obtain the adjusted target flow rate;

[0164] The contrast agent is injected into the blood vessel based on the adjusted target flow rate, and the step of acquiring the angiography image is continued until the angiography evaluation result meets the preset angiography evaluation criteria.

[0165] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0166] The angiography image is segmented based on the segmentation algorithm to obtain the segmented angiography image; the segmented angiography image is processed by morphological operations to obtain the complete blood vessel features, and the complete blood vessel features are determined as the blood vessel image.

[0167] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0168] The angiography information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the blood vessel length at each hierarchical node, and the blood vessel perfusion information includes the contrast agent concentration value and the contrast agent flow rate value in the blood vessel.

[0169] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0170] The blood vessel centerline is extracted from the blood vessel image based on the centerline extraction algorithm, the root node and multiple leaf nodes corresponding to the blood vessel image are searched based on the blood vessel centerline, blood vessel diameter and preset prior rules, and a blood vessel tree is constructed based on the root node and multiple leaf nodes;

[0171] The number of blood vessels and the blood vessel length at each hierarchical node are obtained based on the blood vessel tree;

[0172] The contrast agent concentration value is obtained from the blood vessel image, and the blood vessel perfusion curve is determined based on the correspondence between the contrast agent concentration value and time, and the slope of the blood vessel perfusion curve is determined as the contrast agent flow rate value.

[0173] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented:

[0174] The sample angiography image and the angiography evaluation label corresponding to the sample angiography image are obtained;

[0175] Based on the preset blood vessel extraction algorithm, the sample angiography blood vessels are extracted to obtain the sample blood vessel image; the sample blood vessel information corresponding to the sample blood vessel image is extracted from the sample blood vessel image, and the sample blood vessel information includes sample structure information and sample blood vessel perfusion information;

[0176] Training an initial vascular development evaluation model based on the mapping relationship between the development evaluation label and the sample vascular information to obtain a preset vascular development evaluation model.

[0177] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0178] 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, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., and are not limited thereto. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., and are not limited thereto.

[0179] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of 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 recorded in this application.

[0180] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. A method for evaluating vascular imaging, characterized in that: The method comprises: Obtaining angiographic images; Based on a preset blood vessel extraction algorithm, the angiography image is subjected to extraction processing to obtain a blood vessel image; and blood vessel development information of the blood vessel image is extracted from the blood vessel image; The vascular development information is input into a preset vascular development evaluation model to obtain a vascular development evaluation result.

2. The method according to claim 1, characterized in that The angiographic image is obtained by injecting a contrast agent into a blood vessel based on a target flow rate, and the method further comprises: If the vascular imaging evaluation result does not meet the preset imaging evaluation condition, adjusting the target flow rate based on a preset adjustment strategy to obtain an adjusted target flow rate; The contrast agent is injected into the blood vessel based on the adjusted target flow rate, and the step of acquiring the angiographic image is continuously performed until the blood vessel development evaluation result satisfies the preset development evaluation condition.

3. The method according to claim 1, characterized in that The preset blood vessel extraction algorithm includes a segmentation algorithm and a morphological operation. The extraction process is performed on the angiography image based on the preset blood vessel extraction algorithm to obtain a blood vessel image, including: The angiography image is segmented based on the segmentation algorithm to obtain a segmented angiography image; the segmented angiography image is processed using the morphological operation to obtain a complete blood vessel feature, and the complete blood vessel feature is determined as a blood vessel image.

4. The method according to claim 1, characterized in that The blood vessel development information includes blood vessel structure information and blood vessel perfusion information. The blood vessel structure information includes the number of blood vessels and the length of blood vessels at each level node. The blood vessel perfusion information includes the contrast agent concentration value and the contrast agent flow rate value in the blood vessel.

5. The method according to claim 4, characterized in that The extracting the vascular structure information and vascular perfusion information corresponding to the vascular image from the vascular image includes: extracting a blood vessel centerline from the blood vessel image based on a centerline extraction algorithm, searching for a root node and a plurality of leaf nodes corresponding to the blood vessel image based on the blood vessel centerline, the blood vessel diameter and a preset priori rule, and constructing a blood vessel tree based on the root node and the plurality of leaf nodes; Acquire the number of blood vessels and the length of blood vessels at each level node based on the blood vessel tree; The contrast agent concentration value is acquired from the blood vessel image, and a blood vessel perfusion curve is determined based on the corresponding relationship between the contrast agent concentration value and time, and the slope of the blood vessel perfusion curve is determined as the contrast agent flow rate value.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a sample angiography image and a development evaluation label corresponding to the sample angiography image; Based on the preset blood vessel extraction algorithm, the sample angiography blood vessel is extracted to obtain a sample blood vessel image; sample blood vessel information corresponding to the sample blood vessel image is extracted from the sample blood vessel image, wherein the sample blood vessel information includes sample structure information and sample blood vessel perfusion information; The initial blood vessel development assessment model is trained based on the mapping relationship between the development assessment label and the sample blood vessel information to obtain the preset blood vessel development assessment model.

7. A vascular imaging evaluation device, characterized in that: The device comprises: An acquisition module, used for acquiring angiography images; An extraction module, configured to extract the angiography image based on a preset blood vessel extraction algorithm to obtain a blood vessel image; and extract blood vessel development information corresponding to the blood vessel image from the blood vessel image; The input module is used to input the vascular development information into a preset vascular development evaluation model to obtain a vascular development evaluation result.

8. 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 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images