Method and device for determining blood vessel age, electronic equipment and readable medium

Abstract

The invention belongs to the technical field of intelligent medical images, and particularly relates to a method and device for determining the age of a blood vessel, electronic equipment and a readable medium. The method comprises the following steps: acquiring a carotid intima-media membrane image; based on the carotid intima-media image, image processing is carried out on the carotid intima-media image to obtain carotid image features and intima-media thickness information, and the carotid image features are used for representing echo texture features of the carotid intima-media image; the intima-media thickness information is used for representing the thickness between the intima and the media of the carotid artery in the carotid intima-media image; based on the carotid artery image features and the intima-media thickness information, obtaining a corresponding blood vessel age calculation model; and inputting the carotid artery image features and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid artery intima-media image. The method is used for improving the accuracy of determining the blood vessel age.

Description

Technical Field

[0001] The present application belongs to the field of intelligent medical imaging technology, and specifically relates to a method, device, electronic device and readable medium for determining vascular age. Background Art

[0002] Vascular aging, also known as vascular degenerative changes, refers to the physiological process of functional degradation and structural aging of blood vessels as they age under the combined action of other factors.

[0003] Generally, the vascular age is predicted by pulse wave velocity and the thickness of the carotid intima-media layer. The estimation of vascular age can be used as a reference indicator. Pulse wave velocity requires the detection of multiple parameters, and the detection process is complicated; the thickness of the carotid intima-media layer generally needs to be obtained by ultrasound imaging, but the vascular age cannot be directly obtained, which leads to the problem of inaccurate determination of vascular age. Summary of the invention

[0004] The purpose of the present application is to provide a method, device, electronic device, and computer-readable medium for determining vascular age to improve the accuracy of determining vascular age.

[0005] According to one aspect of an embodiment of the present application, a method for determining vascular age is provided, the method comprising:

[0006] Obtain carotid intima-media images;

[0007] Based on the carotid intima-media image, performing image processing on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image;

[0008] Based on the carotid artery image features and the intima-media thickness information, obtaining a corresponding vascular age calculation model;

[0009] The carotid artery image features and / or the intima-media thickness information are input into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

[0010] According to one aspect of an embodiment of the present application, a device for determining vascular age is provided, the device comprising:

[0011] An image acquisition module, used for acquiring an image of the intima-media membrane of the carotid artery;

[0012] a vascular parameter acquisition module, configured to perform image processing on the carotid intima-media image based on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image;

[0013] A model acquisition module, used to acquire a corresponding vascular age calculation model based on the carotid artery image features and the intima-media thickness information;

[0014] The vascular age determination module is used to input the carotid artery image features and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

[0015] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method for determining vascular age as in the above technical solution by executing the executable instructions.

[0016] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining vascular age in the above technical solution is implemented.

[0017] According to one aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for determining vascular age as in the above technical solution.

[0018] In the technical solution provided in the embodiment of the present application, a carotid intima-media image is acquired and image processing is performed on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent the echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image. The carotid image features and / or the intima-media thickness information are input into a vascular age calculation model to calculate the vascular age. The carotid image features and the intima-media thickness information are used as indicators for calculating the vascular age, and the vascular age is calculated through multi-dimensional input data, thereby improving the efficiency of calculating the vascular age and ensuring the accuracy of the calculated vascular age. For projects that need to use the vascular age as a reference indicator, the reference value thereof can be improved.

[0019] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0020] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0022] Figure 1 A flow chart of a method for determining vascular age provided in an embodiment of the present application is shown.

[0023] Figure 2 A schematic diagram of the structure of a device for determining vascular age provided according to an embodiment of the present application is shown.

[0024] Figure 3 A schematic structural diagram of an ultrasonic imaging device provided in this embodiment is shown.

[0025] Figure 4 The structure block diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of example embodiments to those skilled in the art.

[0027] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0028] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0030] Vascular aging, also known as vascular degenerative changes, refers to the physiological and pathological process of functional degradation and structural aging of blood vessels due to the increase of age and the combined action of other factors. Vascular aging is of great significance as a reference indicator for cardiovascular and cerebrovascular diseases.

[0031] Generally, existing methods for calculating vascular age include pulse wave velocity measurement and carotid intima-media thickness.

[0032] Pulse wave velocity refers to the conduction velocity of the pressure wave that propagates along the walls of the aorta when each pulse of the heart sends blood to the whole body. It can reflect the stiffness and elasticity of the arterial blood vessels and is an independent predictor of cardiovascular events. This pressure wave conduction velocity can be converted into vascular age.

[0033] By detecting the pulse wave propagation velocity and ankle-brachial pressure index, the hardness of limb blood vessels can be measured, but the operation is complicated and requires measuring the pulse wave velocity and ankle / arm blood pressure of the blood vessels in the upper and lower limbs, and it is highly dependent on the measurement operator.

[0034] The way to calculate vascular age through the thickness of the carotid intima-media is that the vascular wall consists of three layers: the intima, the media, and the adventitia. The intima-media thickness (IMT) is the thickness of the intima and the media of the vascular wall. IMT will gradually increase with age, reflecting the age of the blood vessels. Studies have found that for every 10 years of average age increase, IMT will increase by 0.01CM, and if it exceeds 0.01CM, it is judged as intima-media thickening.

[0035] The method of measuring the thickness of the carotid intima-media is generally to first use ultrasonic imaging technology to capture vascular images, but current ultrasonic imaging can only obtain the thickness of the carotid intima-media and cannot quantify the age of the blood vessels.

[0036] Figure 1 FIG. 2 is a flow chart of a method for determining vascular age proposed in an embodiment of the present application. Figure 1As shown, the method for determining vascular age includes the following steps:

[0037] S100, obtaining the carotid artery intima-media image.

[0038] The carotid intima-media image refers to an image including the intima-media of the carotid artery. From the carotid intima-media image, a cross-section of the carotid artery wall can be seen, and the thickness difference between the intima and media of the carotid artery can be seen from the cross-section.

[0039] The image of the intima-media membrane of the carotid artery can be collected by ultrasonic imaging equipment. The ultrasonic imaging equipment mainly consists of two parts: the ultrasound host and the probe. The ultrasound host excites the probe to emit ultrasonic waves, irradiate the examined carotid artery, and obtain the echo signal of the carotid artery. The probe receives the echo signal and transmits it to the image processing module for signal processing to obtain the image of the intima-media membrane of the carotid artery.

[0040] S200, based on the carotid intima-media image, image processing is performed on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent the echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image.

[0041] Specifically, the echo texture feature of the carotid intima-media image refers to the texture of the cross-sectional image reflected by the ultrasonic echo signal to the human tissue, including echo texture features and grayscale information, etc., in the form of a two-dimensional cross-sectional image with different brightness and intensity of light spots.

[0042] Based on the carotid intima-media image, image recognition is performed on the carotid intima-media image to obtain carotid image features, which include echo texture features of the carotid artery region.

[0043] Specifically, if the carotid intima-media image is collected by ultrasonic imaging, the carotid image features also include echo texture information. The intima-media thickness information represents the thickness between the intima and the media of the carotid artery.

[0044] S300, based on the carotid artery image features and intima-media thickness information, obtain a corresponding vascular age calculation model.

[0045] Specifically, carotid artery image features and intima-media thickness information can be combined into multi-dimensional information to jointly determine the vascular age of the carotid artery.

[0046] Specifically, the vascular age of the carotid artery may be determined by one of the carotid artery image features and the intima-media thickness information or a combination of both.

[0047] The carotid artery image features or the intima-media thickness information are input into the vascular age calculation model, or the carotid artery image features and the intima-media thickness information are input into the vascular age calculation model.

[0048] It can be understood that different input information will result in different vascular age models used to calculate vascular age.

[0049] For example, taking the carotid artery image features as input, the vascular age calculation model is A; taking the intima-media thickness information as input, the vascular age calculation model is B; taking the carotid artery image features and the intima-media thickness information as input, the vascular age calculation model is C.

[0050] The vascular age calculation model is obtained by training the neural network.

[0051] Through training, the neural network establishes a fitting curve between carotid artery image features, intima-media thickness and vascular age. Therefore, when carotid artery image features, intima-media thickness information or a combination of carotid artery image features and intima-media thickness information is required to be input, the vascular age calculation model calculates the corresponding vascular age based on the input carotid artery image features and / or intima-media thickness information.

[0052] S400, inputting carotid artery image features and / or intima-media thickness information into a vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

[0053] Specifically, according to the type of the acquired vascular age calculation model, corresponding data is input to obtain the vascular age of the carotid artery.

[0054] Exemplarily, there are multiple types of vascular age models, and one of the vascular age calculation models is selected according to a preset type, and the vascular age of the carotid artery is determined by the selected vascular age calculation model.

[0055] In an embodiment of the present application, a carotid intima-media image is obtained, and a corresponding vascular age calculation model is obtained based on carotid image features and intima-media thickness information of the carotid intima-media image. The carotid image features and / or intima-media thickness information are input into the vascular age calculation model to determine the vascular age of the carotid artery. The carotid intima-media image is processed to obtain carotid image features and intima-media thickness information. The vascular age calculation model can convert the carotid image features and / or intima-media thickness information into vascular age. The calculation of vascular age is accurate for projects based on vascular age as a reference item, and its effectiveness can be guaranteed.

[0056] Further, S200, based on the carotid intima-media image, image processing is performed on the carotid intima-media image to obtain carotid image features and intima-media thickness information, including:

[0057] S210, performing image processing on the carotid intima-media image to obtain carotid image features.

[0058] S220, determining a carotid artery measurement region in the carotid intima-media image, measuring the thickness of the carotid artery measurement region, and obtaining intima-media thickness information.

[0059] Specifically, the method for determining the carotid artery measurement area can be semi-automatic or automatic. The semi-automatic method refers to manually selecting the carotid artery measurement area in the carotid intima-media image, determining the position of the carotid intima and media in the carotid artery measurement area, and further calculating the thickness between the intima and media to obtain the intima-media thickness information.

[0060] The automatic method refers to automatically selecting a carotid artery measurement area for measuring intima-media thickness information in the carotid intima-media image, performing image segmentation on the carotid artery in the carotid artery measurement area, obtaining the contours of the intima and media of the carotid artery, and automatically calculating the intima-media thickness information.

[0061] Further, S300, based on the carotid artery image features and the intima-media thickness information, a corresponding vascular age calculation model is obtained, including:

[0062] S310: Determine a vascular age determination parameter based on the carotid artery image feature and the intima-media thickness information, where the vascular age determination parameter includes one or both of the carotid artery image feature and the intima-media thickness information.

[0063] S320, determining parameters according to the vascular age, and obtaining a corresponding vascular age calculation model.

[0064] Further, S400, inputting the carotid artery image features and / or the intima-media thickness information into a vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image, including:

[0065] S410, inputting carotid artery image features into a first blood vessel age calculation model to obtain a first blood vessel age.

[0066] S420, inputting the intima-media thickness information into a second blood vessel age calculation model to obtain the second blood vessel age.

[0067] S430, inputting the carotid artery image features and the intima-media thickness information into a third blood vessel age calculation model to obtain the third blood vessel age.

[0068] Specifically, in S300, a preset vascular age calculation model may be selected, and then corresponding data may be input into the vascular age calculation model to obtain the vascular age.

[0069] In S410 - S420 , there are three different types of input information, and therefore the corresponding vascular age calculation models are also different.

[0070] It should be noted that the difference between the first vascular age calculation model and the second vascular age calculation model lies in their different inputs. In fact, the first vascular age calculation model and the second vascular age calculation model are obtained by training the neural network with carotid artery sample data, and by adjusting the linear relationship between the input and output, different inputs are used to finally calculate the vascular age.

[0071] It should be noted that the first vascular age calculation model, the second vascular age calculation model and the third vascular age calculation model can be trained using the same data set, or trained using data sets with different data volumes. Similarly, the third vascular age calculation model can be trained using the same type of neural network as the first vascular age calculation model and the second vascular age calculation model, which will not be described in detail here.

[0072] As an optional implementation, three vascular age calculation models are set in an ultrasonic imaging device, one of the vascular age calculation models is pre-selected, and the collected carotid intima-media image is processed by a data processing module of the ultrasonic imaging device to obtain input data of the corresponding vascular age calculation model, and the vascular age is determined by calculation of the vascular age calculation model.

[0073] The first vascular age calculation model, the second vascular age calculation model and the third vascular age calculation model are obtained by training a neural network.

[0074] S440: Obtain the vascular age of the carotid artery in the carotid intima-media image from the first vascular age, the second vascular age, and the third vascular age.

[0075] As an optional implementation, the vascular age may be calculated using three types of vascular age calculation models respectively, and the vascular ages calculated by the three vascular age calculation models are processed to output the final vascular age of the carotid artery.

[0076] Alternatively, the vascular age is calculated using only one of the vascular age calculation models, and the resulting vascular age is used as the final vascular age of the carotid artery.

[0077] In this embodiment, through multiple trainings, vascular age calculation models with different input types are obtained, and one of the vascular age calculation models is selected according to the needs to calculate the corresponding vascular age. The neural network is trained with a large number of carotid artery sample images to establish the corresponding relationship between the carotid artery image features and / or the intima-media thickness information and the vascular age, and then the vascular age of the carotid artery included in the collected carotid intima-media image is determined, which reduces the difficulty of calculating the vascular age and can improve the accuracy of the calculated vascular age.

[0078] As an optional implementation, the training process of the vascular age calculation model is as follows:

[0079] S30a, obtaining a carotid artery sample image, and obtaining sample image features and intima-media thickness information of the carotid artery based on the carotid artery sample image.

[0080] Furthermore, based on the structure of the carotid artery, sample image features at different positions of the carotid artery and intima-media thickness information are collected in the carotid artery sample image.

[0081] It should be noted that the structure of the carotid artery refers to the proximal, middle and distal ends of the carotid artery.

[0082] The proximal, middle and distal ends of the carotid artery are divided according to their relationship with the upper and lower poles of the thyroid gland. The proximal end refers to the part from the aortic arch or the innominate artery to the lower pole of the thyroid gland.

[0083] The middle end refers to the part between the upper and lower poles of the thyroid gland, and the distal end refers to the part from the upper pole of the thyroid gland to the level of the carotid bifurcation.

[0084] The three endpoints of the carotid artery can indicate the direction of the carotid artery on the one hand, and on the other hand, can divide the carotid artery into zones, and collect the intima-media thickness information at multiple locations in each zone, thereby enabling a more comprehensive assessment of vascular age.

[0085] Specifically, the partitions can be further subdivided based on the three endpoints to obtain N partitions, and the thicknesses can be measured in the N partitions to obtain multiple pieces of intima-media thickness information.

[0086] S30b, training the neural network through the sample image features to obtain a first vascular age calculation model.

[0087] S30c, training the neural network using the intima-media thickness information to obtain a second vascular age calculation model.

[0088] S30d, training the neural network through the sample image features and the intima-media thickness information to obtain a third blood vessel age calculation model.

[0089] A carotid artery sample image is obtained, and after image processing of the carotid artery sample image, the carotid artery sample image features and intima-media thickness information are obtained. The neural network is trained by the carotid artery image features and intima-media thickness information to obtain a vascular age calculation model.

[0090] Carotid artery sample images were obtained. The target population of the carotid artery sample images ranged from 20 to 80 years old. Every 5 years was used as an age group, and there were 12 groups in total. 100 female samples and 100 male samples were collected from each group.

[0091] The basic information of each subject, such as name, gender, age, height, weight, and blood pressure, was recorded. The basic information as well as the sample image features and intima-media thickness information obtained from the carotid artery sample images were input into the neural network as sample data for training to obtain a vascular age calculation model.

[0092] The first vascular age calculation model is obtained by training the neural network with sample image features, the second vascular age calculation model is obtained by training the neural network with intima-media thickness information, and the third vascular age calculation model is obtained by training the neural network with sample image features and intima-media thickness information.

[0093] It should be noted that the first vascular age calculation model, the second vascular age calculation model and the third vascular age calculation model may use the same sample data set.

[0094] Alternatively, the amount of sample data may be increased according to the specific training process of each vascular age calculation model.

[0095] Specifically, the parameter matrix is ​​generated during the training process. The carotid artery image features are input into the neural network, the features are extracted according to the feature extraction layer, the weight values ​​and the variation values ​​are defined, the linear combination values ​​of the input information and the weights are calculated, and then the activation function is applied to the linear combination values ​​to calculate the loss function.

[0096] Exemplarily, the parameter matrix may include weight values, activation functions, and loss functions of each layer.

[0097] The parameter matrix and intima-media thickness information were used to train the second vascular age calculation model.

[0098] The vascular age can be expressed in the form of XX years old. By acquiring sample images of the carotid arteries of various age groups, the neural network is trained according to the basic information of each sample object and the sample image features in the sample images of the carotid arteries, and the vascular age is obtained.

[0099] Vascular age is compared with people's actual age. The numbers reflected by vascular age can be used as an indicator to judge the condition of blood vessels.

[0100] The first vascular age calculation model inputs carotid artery image features and outputs vascular age, and the second vascular age calculation model inputs intima-media thickness information and outputs vascular age.

[0101] On this basis, a third vascular age calculation model can be obtained according to the carotid artery image features and the intima-media thickness information. The third vascular age calculation model inputs the carotid artery image features and the intima-media thickness information and outputs the vascular age.

[0102] It should be noted that the first vascular age calculation model, the second vascular age calculation model and the third vascular age calculation model can be obtained based on the same type of neural network training.

[0103] The model parameters of the second vascular age calculation model can be modified based on the model parameters of the first vascular age calculation model. Similarly, the third vascular age calculation model can be modified based on the model parameters of the first vascular age calculation model and the second vascular age calculation model.

[0104] In this embodiment, by dividing the vascular age calculation model into multiple sub-models, the corresponding vascular age calculation model can be selected according to different input data types, and the relationship between input data of multiple dimensions and vascular age is established, thereby enriching the calculation method of vascular age.

[0105] As an optional implementation, each vascular age calculation model is used to calculate the vascular age, and data processing is performed on multiple vascular ages to obtain the final vascular age.

[0106] Exemplarily, the intima-media thickness information is used as input data, and the vascular age is calculated using a vascular age calculation model.

[0107] Multiple intima-media thickness data are calculated based on the intima-media thickness information, and the intima-media thickness data can directly reflect the thickness between the intima and the media of the carotid artery. Multiple intima-media thickness information is input into the vascular age calculation model to obtain the vascular age of the carotid artery.

[0108] Further, at S400, after the carotid artery image features and / or intima-media thickness information are input into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image, the following steps are performed:

[0109] S500, calculating the thickness data of the carotid artery based on the intima-media thickness information.

[0110] S510, visualize the thickness data and vascular age.

[0111] Thickness data include the minimum thickness of the intima-media, the maximum thickness of the intima-media, the average thickness and the variance.

[0112] The minimum thickness of the intima-media membrane is calculated by the following formula:

[0113] minthick=min(X i )

[0114] The maximum thickness of the intima-media membrane can be calculated using the following formula:

[0115] maxthick=max(X i )

[0116] The average thickness is calculated by the following formula:

[0117]

[0118] The variance is calculated using the following formula:

[0119]

[0120] Among them, X i represents the intima-media thickness at the ith location, and n represents the number of measurements of the intima-media thickness of the blood vessel.

[0121] In this embodiment, vascular age is calculated by a vascular age calculation model, and a relationship between carotid artery image features and intima-media thickness information and vascular age is established. Vascular age is quantified by the vascular age calculation model, which can improve the accuracy of vascular age determination.

[0122] Figure 2 A structural block diagram of a device for determining vascular age provided in an embodiment of the present application is shown.

[0123] like Figure 2 As shown, the device for determining vascular age includes:

[0124] An image acquisition module, used for acquiring an image of the intima-media membrane of the carotid artery;

[0125] a vascular parameter acquisition module, configured to perform image processing on the carotid intima-media image based on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image;

[0126] A model acquisition module, used to acquire a corresponding vascular age calculation model based on the carotid artery image features and the intima-media thickness information;

[0127] The vascular age determination module is used to input the carotid artery image features and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

[0128] Furthermore, the vascular parameter acquisition module includes:

[0129] The image feature acquisition unit is used to process the carotid intima-media image to obtain the carotid image features.

[0130] The intima-media thickness information acquisition unit is used to determine the carotid artery measurement area in the carotid artery intima-media image, measure the thickness of the carotid artery measurement area, and obtain the intima-media thickness information.

[0131] Furthermore, the model acquisition module includes:

[0132] The age parameter acquisition unit is used to determine a vascular age determination parameter based on the carotid artery image characteristics and the intima-media thickness information, wherein the vascular age determination parameter includes one or both of the carotid artery image characteristics and the intima-media thickness information.

[0133] The model acquisition unit is used to determine parameters according to the vascular age and acquire the corresponding vascular age calculation model.

[0134] Furthermore, the vascular age determination module includes:

[0135] The first model acquisition unit is used to input the carotid artery image features into the first blood vessel age calculation model to obtain the first blood vessel age.

[0136] The second model acquisition unit is used to input the intima-media thickness information into the second vascular age calculation model to obtain the second vascular age.

[0137] The third model acquisition unit is used to input the carotid artery image features and the intima-media thickness information into the third blood vessel age calculation model to obtain the third blood vessel age.

[0138] The vascular age acquisition unit is used to obtain the vascular age of the carotid artery in the carotid intima-media image from the first vascular age, the second vascular age and the third vascular age.

[0139] Further, the device for determining vascular age includes:

[0140] The sample data acquisition module is used to acquire a carotid artery sample image, and acquire sample image features and intima-media thickness information of the carotid artery based on the carotid artery sample image.

[0141] The first model training module is used to train the neural network through sample image features to obtain a first vascular age calculation model.

[0142] The second model training module is used to train the neural network through the intima-media thickness information to obtain a second vascular age calculation model.

[0143] The third model training module is used to train the neural network through sample image features and intima-media thickness information to obtain a third vascular age calculation model.

[0144] The thickness data calculation module is used to calculate the thickness data of the carotid artery based on the intima-media thickness information.

[0145] The visualization display module is used to visualize the thickness data and vascular age.

[0146] Figure 3 A schematic structural diagram of an ultrasonic imaging device provided in this embodiment is shown.

[0147] like Figure 3 As shown, this embodiment provides an ultrasonic imaging device, including:

[0148] The time control circuit 310 is used to control the time of transmitting and receiving echo signals of the ultrasonic imaging device.

[0149] The transmit control circuit 320 is used to excite the array elements through a pulse voltage.

[0150] The probe 330 has a plurality of array elements at its front end, which transmit ultrasonic waves and receive returned echo signals through the excitation of the transmission control circuit.

[0151] The receiving control circuit 340 calculates the receiving signal of each array element respectively, and performs focusing control, filtering processing, and amplification gain on the alignment.

[0152] The receiving control circuit 340 also includes the function of adjusting the STC function. STC (sensitivity Time Control) refers to sensitivity time control, which is a signal gain control technology. The receiving control circuit 340 improves the contrast and resolution of the ultrasound image by adjusting the STC.

[0153] The beamforming module 350 includes a method for exciting the probe and generating ultrasonic waves, a method for receiving echo signals, and a corresponding image reconstruction method.

[0154] The beamforming model 350 is one of the core links of ultrasound imaging in the medical field.

[0155] The memory 360 stores the acquired carotid intima-media image.

[0156] The image processing model 370 performs smoothing and filtering on the collected carotid artery intima-media image.

[0157] The display module 380 is used to collect and display the carotid intima-media image.

[0158] Figure 4 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.

[0159] It should be noted that Figure 4 The computer system 700 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0160] like Figure 4 As shown, the computer system 700 includes a central processing unit 701 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 702 (ROM) or the program loaded from the storage part 708 to the random access memory 703 (RAM). Various programs and data required for system operation are also stored in the random access memory 703. The central processing unit 701, the read-only memory 702 and the random access memory 703 are connected to each other through a bus 704. An input / output interface 705 (Input / Output interface, i.e., I / O interface) is also connected to the bus 704.

[0161] The following components are connected to the input / output interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed so that a computer program read therefrom is installed into the storage section 708 as needed.

[0162] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processor 701, various functions defined in the system of the present application are executed.

[0163] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0164] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0165] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0166] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0167] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

[0168] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for determining vascular age, characterized in that: include: Obtain carotid intima-media images; Based on the carotid intima-media image, performing image processing on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image; Based on the carotid artery image features and the intima-media thickness information, obtaining a corresponding vascular age calculation model; The carotid artery image features and / or the intima-media thickness information are input into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

2. The method for determining vascular age according to claim 1, characterized in that: Based on the carotid intima-media image, image processing is performed on the carotid intima-media image to obtain carotid image features and intima-media thickness information, including: Performing image processing on the carotid intima-media image to obtain carotid image features; A carotid artery measurement region is determined in the carotid intima-media image, and thickness measurement is performed on the carotid artery measurement region to obtain the intima-media thickness information.

3. The method for determining vascular age according to claim 1, characterized in that: The step of obtaining a corresponding vascular age calculation model based on the carotid artery image features and the intima-media thickness information includes: Determining a vascular age determination parameter based on the carotid artery image feature and the intima-media thickness information, wherein the vascular age determination parameter includes one or both of the carotid artery image feature and the intima-media thickness information; Parameters are determined according to the vascular age, and a corresponding vascular age calculation model is obtained.

4. The method for determining vascular age according to claim 1, characterized in that: The step of inputting the carotid artery image feature and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image comprises: Inputting the carotid artery image features into a first blood vessel age calculation model to obtain a first blood vessel age; Inputting the intima-media thickness information into a second blood vessel age calculation model to obtain a second blood vessel age; Inputting the carotid artery image features and the intima-media thickness information into a third blood vessel age calculation model to obtain a third blood vessel age; Wherein, the first vascular age calculation model, the second vascular age calculation model and the third vascular age calculation model are obtained by training a neural network; The vascular age of the carotid artery in the carotid intima-media image is obtained from the first vascular age, the second vascular age, and the third vascular age.

5. The method for determining vascular age according to claim 4, characterized in that: Before inputting the carotid artery image features and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image, the method further includes: Acquire a carotid artery sample image, and acquire sample image features and intima-media thickness information of the carotid artery based on the carotid artery sample image; Training a neural network using the sample image features to obtain a first vascular age calculation model; The neural network is trained by using the intima-media thickness information to obtain a second vascular age calculation model; The neural network is trained by using the sample image features and the intima-media thickness information to obtain a third blood vessel age calculation model.

6. The method for determining vascular age according to claim 5, characterized in that: The step of acquiring a carotid artery sample image and acquiring a sample image feature and intima-media thickness information of the carotid artery based on the carotid artery sample image includes: Based on the structure of the carotid artery, sample image features and intima-media thickness information of different positions of the carotid artery are collected in the carotid artery sample image.

7. The method for determining vascular age according to claim 1, characterized in that: Inputting the carotid artery image feature and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image includes: Calculating the thickness data of the carotid artery according to the intima-media thickness information; The thickness data and vascular age are visualized.

8. A device for determining vascular age, characterized in that: include: An image acquisition module, used for acquiring an image of the intima-media membrane of the carotid artery; a vascular parameter acquisition module, configured to perform image processing on the carotid intima-media image based on the carotid intima-media image to obtain carotid image features and intima-media thickness information, wherein the carotid image features are used to represent echo texture features of the carotid intima-media image, and the intima-media thickness information is used to represent the thickness between the intima and the media of the carotid artery in the carotid intima-media image; A model acquisition module, used to acquire a corresponding vascular age calculation model based on the carotid artery image features and the intima-media thickness information; The vascular age determination module is used to input the carotid artery image features and / or the intima-media thickness information into the vascular age calculation model to obtain the vascular age of the carotid artery in the carotid intima-media image.

9. An electronic device, characterized in that: include: processor; A memory, configured to store executable instructions of the processor; The processor is configured to enable the electronic device to perform the method for determining vascular age as described in any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable medium, characterized in that The computer readable medium stores a computer program, and when the computer program is executed by a processor, the method for determining vascular age according to any one of claims 1 to 7 is implemented.

Images