A method, apparatus, device, and storage medium for measuring vascular parameters.

Abstract

This application discloses a method, apparatus, device, and storage medium for measuring vascular parameters, comprising: acquiring a set of surface temperature signals of a target area under laser irradiation within a preset time period; preprocessing the surface temperature signal set to obtain a temperature time series sequence; and inputting the temperature time series sequence into a preset neural network model to obtain at least one vascular parameter among vascular temperature, depth, and thickness of the target area. The preset neural network model is obtained by training an initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes multiple sets of temperature time series sequences obtained after preprocessing the surface temperature signal set collected in historical measurement scenarios. This application measures vascular parameters by combining laser irradiation with the acquisition of surface temperature signals, without direct contact or damage to skin or vascular tissue, thus achieving non-invasive vascular parameter measurement.

Description

Technical Field

[0001] This application relates to the field of signal processing technology, and in particular to a method, apparatus, device, and storage medium for measuring vascular parameters. Background Technology

[0002] In existing technologies, the common method for obtaining parameters of subcutaneous blood vessels is to use laser-induced hyperthermia, which causes a rapid temperature increase due to the selective absorption of laser energy by hemoglobin in the blood vessels, thereby obtaining the parameters of the subcutaneous blood vessels. However, laser-induced hyperthermia can cause thermal damage to the capillaries in the skin, thus damaging the skin. To solve this problem, a non-invasive technical solution for obtaining subcutaneous blood vessel parameters is needed.

[0003] Therefore, how to obtain subcutaneous vascular parameters without damaging the skin or vascular tissue is an urgent problem to be solved. Summary of the Invention

[0004] In view of this, the method, apparatus, device, and storage medium for measuring vascular parameters provided in this application embodiment can obtain subcutaneous vascular parameters without damaging the skin or vascular tissue. The method, apparatus, device, and storage medium for measuring vascular parameters provided in this application embodiment are implemented as follows:

[0005] This application provides a method for measuring vascular parameters, comprising:

[0006] Acquire the set of surface temperature signals of the target area under laser irradiation within a preset time period;

[0007] The surface temperature signal set is preprocessed to obtain a temperature time series sequence;

[0008] The temperature time series is input into a preset neural network model to obtain at least one blood vessel parameter among the blood vessel temperature, depth, and thickness of the target area. The preset neural network model is obtained by training an initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes multiple sets of temperature time series obtained after preprocessing the surface temperature signal set collected in historical measurement scenarios.

[0009] In some embodiments, inputting the temperature time series into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region includes:

[0010] The low-level features and high-level features of the temperature time series are obtained. The low-level features include at least one of temperature peaks, valleys and temperature differences between adjacent sampling points within a preset time period. The high-level features include at least one of temperature distribution, temperature change and heat conduction features.

[0011] The low-level features and the high-level features are fused together to obtain the fused features.

[0012] The fused features are input into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region.

[0013] In some embodiments, the multiple sets of surface temperature signals include sets of surface temperature signals from different temperature acquisition scenarios. Sample data acquired in historical measurement scenarios are used to train the initial neural network model, including:

[0014] The first epidermal temperature, the second epidermal temperature, and the vascular parameters corresponding to the first epidermal temperature of the target area are obtained by vascular simulation model. The first epidermal temperature and the second epidermal temperature are used to characterize the skin temperature of the target area.

[0015] The training set is obtained based on the second epidermal temperature;

[0016] A validation set is obtained based on the first skin temperature and the corresponding vascular parameters.

[0017] The initial neural network model is trained based on the training set to obtain the blood vessel parameters of the training set;

[0018] The initial neural network model is calibrated based on the validation set and the vascular parameters of the training set. If the accuracy of the vascular parameters of the training set output by the initial neural network model meets a preset threshold, a second neural network model is obtained.

[0019] The multiple sets of surface temperature signals are input into the second neural network model to obtain the training results;

[0020] The training results are compared with preset vascular parameters. If the deviation between the training results and the preset vascular parameters is less than a preset threshold, a preset neural network model is obtained.

[0021] In some embodiments, acquiring the set of surface temperature signals of the target area under laser irradiation within a preset time period includes:

[0022] Acquire multiple temperature images of the target area under laser irradiation within a preset time period;

[0023] Extract multiple temperature signals corresponding to the multiple temperature images;

[0024] The multiple temperature signals are sorted according to the time sequence of the acquisition of the corresponding multiple temperature images to obtain the surface temperature signal set.

[0025] In some embodiments, the wavelength of the laser is 532 nm, and the measurement range is 0-100 degrees.

[0026] In some embodiments, multiple temperature images of the target area under laser irradiation within a preset time period are obtained by an infrared detector.

[0027] In some embodiments, the preset neural network model includes an input layer, a first convolutional layer, a pooling layer, fifteen residual layers, two fully connected layers, and an output layer. The residual layers include two batch normalization layers, two rectified linear unit activation function layers, two second convolutional layers, and a shortcut connection.

[0028] This application provides a device for measuring vascular parameters, comprising:

[0029] The acquisition module is used to acquire a set of surface temperature signals of the target area under laser irradiation within a preset time period;

[0030] The processing module is used to preprocess the surface temperature signal set to obtain a temperature time series sequence;

[0031] The input module is used to input the temperature time series into a preset neural network model to obtain at least one blood vessel parameter among the blood vessel temperature, depth, and thickness of the target area. The preset neural network model is obtained by training an initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes a set of multiple sets of surface temperature signals collected in historical measurement scenarios.

[0032] The computer device provided in this application includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements the method described in this application.

[0033] The computer-readable storage medium provided in this application embodiment stores a computer program thereon, which, when executed by a processor, implements the method described in this application embodiment.

[0034] The present application provides a method, apparatus, device, and storage medium for measuring vascular parameters. This involves acquiring a set of surface temperature signals of a target area under laser irradiation within a preset time period; preprocessing the surface temperature signal set to obtain a temperature time series; and inputting the temperature time series into a preset neural network model to obtain at least one vascular parameter among vascular temperature, depth, and thickness of the target area. Thus, by measuring vascular parameters through laser irradiation combined with the acquisition of surface temperature signals, direct contact or damage to skin or vascular tissue is not required, thereby achieving non-invasive vascular parameter measurement. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 A schematic diagram illustrating the implementation process of a method for measuring vascular parameters provided in this application embodiment;

[0037] Figure 2 A schematic diagram illustrating the specific implementation process of a method for measuring vascular parameters provided in this application embodiment;

[0038] Figure 3 A flowchart illustrating the model training process for a method of measuring vascular parameters provided in this application embodiment;

[0039] Figure 4 A schematic diagram illustrating the specific implementation process of a method for measuring vascular parameters provided in this application embodiment;

[0040] Figure 5 This is a schematic diagram of the structure of a vascular parameter measuring device disclosed in an embodiment of this application;

[0041] Figure 6 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0044] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0045] It should be noted that the terms "first, second, third" used in the embodiments of this application are used to distinguish similar or different objects and do not represent a specific order of objects. It can be understood that "first, second, third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0046] Figure 1 This is a schematic diagram illustrating the implementation process of a method for measuring vascular parameters provided in an embodiment of this application. Figure 1 As shown, the method may include the following steps 101 to 103:

[0047] Step 101: Obtain the set of surface temperature signals of the target area under laser irradiation within a preset time period.

[0048] In this embodiment, by selecting an appropriate laser type (such as near-infrared laser) and laser irradiation intensity, it is ensured that no damage is caused to the skin or tissue. The laser irradiation time, power, and frequency can be optimized according to the specific conditions of the target area to ensure that changes in the surface temperature of blood vessels are stimulated.

[0049] Use a high-precision infrared thermal imager or infrared sensor. The equipment needs to have high temporal resolution (at least capable of recording temperature data hundreds of times per second) to ensure accurate capture of temperature changes.

[0050] To improve measurement accuracy, multiple points in the target area can be simultaneously acquired, forming a spatial temperature signal set. This can be achieved by setting up multiple detection points or using a thermal imager with a wider field of view.

[0051] During the data acquisition process, environmental stability (such as temperature, humidity, and airflow) should be maintained to avoid interference from environmental factors on temperature measurement. Furthermore, software control or manual intervention can be used to ensure the synchronization of laser irradiation and temperature data acquisition.

[0052] A dataset containing time and corresponding surface temperature, in the form of a time series data matrix, where each row represents a time point and each column represents a different measurement point or channel.

[0053] Step 102: Preprocess the surface temperature signal set to obtain the temperature time series.

[0054] In this embodiment, since the temperature signal acquisition process may be subject to various interferences (such as equipment noise and changes in the external environment), filtering algorithms can be used to process the original signal. Commonly used filtering methods include: 1. Kalman filtering: suitable for dynamic noise suppression, effectively removing random noise from the signal. 2. Wavelet transform: capable of separating high-frequency noise and low-frequency signals in the signal, suitable for complex temperature signals.

[0055] To make the data more compatible with the input requirements of neural networks, the signal can be smoothed (e.g., by moving average) and normalized (e.g., standardized to the [0,1] range) to ensure that the temperature values ​​at each time point are processed on the same scale.

[0056] If data is lost or corrupted during signal acquisition, interpolation algorithms (such as linear interpolation, spline interpolation, etc.) are needed to fill in the missing data points.

[0057] Step 103: Input the temperature time series into the preset neural network model to obtain at least one of the blood vessel parameters, including blood vessel temperature, depth, and thickness in the target area.

[0058] In this embodiment, a Residual Network (ResNet) is used to process temperature time series. The ResNet structure has multiple "residual blocks", each containing skip connections. These "residual blocks" effectively alleviate the gradient vanishing or gradient exploding problems in deep neural networks.

[0059] The input layer is used to receive temperature time series, which can be temperature change data within a fixed-length time window (e.g., temperature signal within 10 seconds).

[0060] A combination of multiple convolutional layers and fully connected layers is used. The convolutional layers are used to extract features from time-series data, while the fully connected layers are used to integrate and classify the extracted features.

[0061] The output layer is a multidimensional regression problem that predicts parameters such as temperature, depth, and thickness of blood vessels. The specific output dimensions are set according to actual needs (e.g., outputting the temperature, depth, and thickness values ​​of blood vessels).

[0062] During training, input data is fed into the neural network in batches for forward and backward propagation, and the network weights are adjusted using gradient descent. Cross-validation or leave-one-out validation is used to verify the model's generalization ability.

[0063] A well-trained neural network model can accept temperature time series and output predicted parameters such as blood vessel temperature, depth, and thickness.

[0064] Based on the relationship between temperature signals and the temperature response of blood vessels, neural networks can estimate the temperature of blood vessels. There is usually a certain spatial and temporal delay between the temperature of blood vessels and the surface temperature.

[0065] By modeling the temporal decay and spatial distribution patterns of temperature signals, neural networks can infer the depth and thickness of blood vessels. This can be attributed to the spatial diffusion characteristics of the temperature signal; deeper blood vessels tend to cause delays or slower decay of the temperature signal.

[0066] This application embodiment can accurately obtain vascular parameters such as vascular temperature, depth, and thickness in the target area by inputting the surface temperature signal into a neural network model, without directly contacting or damaging the skin or vascular tissue, thus achieving non-invasive vascular parameter measurement.

[0067] In the above Figure 1 Based on this, this application also provides a schematic diagram of the specific implementation process of a method for measuring vascular parameters. For example... Figure 2 As shown, the temperature time series is input into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region, including the following steps 201 to 203:

[0068] Step 201: Obtain the low-level and high-level features of the temperature time series.

[0069] Specifically, the basic and intuitive temperature features are first extracted from the temperature time series. These include: temperature peaks, which are the maximum values ​​of the temperature signal within a preset time period; temperature valleys, which are the minimum values ​​of the temperature signal within a preset time period; and temperature differences, which are the temperature differences between adjacent sampling points within the preset time period.

[0070] More sophisticated signal processing methods are used to extract higher-level features from temperature time series. These include: temperature distribution, reflecting the thermal properties of blood vessels; temperature variation, analyzing the trend of temperature change over time to reveal the thermal conduction properties of blood vessels; and thermal conduction characteristics, extracting patterns of temperature change and their conduction properties in different materials (such as blood vessels and surrounding tissues) using thermal conduction or thermal diffusion models.

[0071] Step 202: The low-level features and high-level features are fused to obtain the fused features.

[0072] The extracted low-level features (such as temperature peaks, temperature valleys, and temperature differences) are fused with high-level features (such as temperature distribution, temperature changes, and heat conduction characteristics). The following methods can be used, and this application does not impose any restrictions: 1. Directly concatenate the low-level and high-level features along the feature dimension to form a richer feature vector. 2. Assign different weights to each feature based on its importance, and then fuse them after weighted summation. 3. Use a mapping method (such as Principal Component Analysis (PCA)) to map the low-level and high-level features into a unified feature space before further processing.

[0073] Step 203: Input the fused features into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region.

[0074] The fused feature vectors are input into a pre-defined neural network model. This neural network model is trained based on sample data from historical measurement scenarios.

[0075] This application uses a residual network to output vascular parameters of the target region based on the input fusion features. The obtained vascular parameters include: vascular temperature: the temperature level of the vascular region, reflecting the thermal characteristics of the blood vessel; vascular depth: the position of the blood vessel from the surface, which is related to the attenuation of the temperature signal; and vascular thickness: the thickness of the blood vessel wall, which can be calculated through thermal conductivity.

[0076] This application example, by fusing low-level and high-level features, can more comprehensively and accurately reflect the temperature characteristics of the target area, enhance the expressive power and adaptability of the neural network model, and thus improve the prediction accuracy and robustness of vascular parameters (such as vascular temperature, depth, and thickness).

[0077] This application also provides a model training flowchart for a method of measuring vascular parameters. For example... Figure 3 As shown, the multiple sets of surface temperature signals include surface temperature signal sets under different temperature acquisition scenarios. Sample data collected under historical measurement scenarios are used to train the initial neural network model, including the following steps 301 to 306:

[0078] Step 301: Obtain the first epidermal temperature, the second epidermal temperature, and the vascular parameters corresponding to the first epidermal temperature of the target area through a vascular simulation model. Both the first epidermal temperature and the second epidermal temperature are used to characterize the skin temperature of the target area.

[0079] Specifically, a vascular simulation model is used to simulate the relationship between skin surface temperature and vascular parameters. Through the simulation model, two sets of data can be obtained: a first epidermal temperature and its corresponding vascular parameters, and a second epidermal temperature.

[0080] Step 302: Obtain a training set based on the second skin temperature and a validation set based on the first skin temperature and the corresponding vascular parameters.

[0081] Specifically, a training set is constructed based on the second skin temperature data. This data is used to train a neural network model that can predict vascular parameters related to the first skin temperature.

[0082] A validation set was constructed based on the first skin temperature and its corresponding vascular parameters. The validation set was used to evaluate the model's generalization ability during prediction and to ensure that the model could effectively learn the relationship between vascular parameters and temperature signals.

[0083] Step 303: Process the initial neural network model based on the training set to obtain the blood vessel parameters of the training set.

[0084] The model takes the second skin temperature as input from the training set. The output of the model is vascular parameters, which are vascular information related to the surface temperature, such as the temperature, depth, and thickness of the blood vessels.

[0085] The model is trained using a neural network based on the training set data. During training, optimization algorithms (such as Adam) are used to minimize the loss function (e.g., mean squared error) so that the network predicts vascular parameters as close as possible to the true values. Throughout the training process, the network's weights and biases are continuously adjusted to optimize the model's performance.

[0086] Step 304: The initial neural network model is processed for accuracy based on the blood vessel parameters of the validation set and training set. If the accuracy meets the preset threshold, the second neural network model is obtained.

[0087] The accuracy of the model is evaluated using a validation set. Model performance can be assessed by calculating the loss function (e.g., mean squared error, MSE) and evaluation metrics (e.g., R-squared). 2 The accuracy is quantified by quantification. If the model's prediction results meet a preset accuracy threshold (e.g., the error on the training set and validation set is below a certain value), then the model is considered to have achieved the desired effect.

[0088] When the accuracy of the model meets the preset threshold, the second neural network model is obtained.

[0089] Step 305: Input multiple sets of surface temperature signals into the second neural network model to obtain the training results.

[0090] Multiple sets of surface temperature signals are input into a second neural network model. Surface temperature signals from different scenarios are processed by the network to predict vascular parameters.

[0091] The training results (i.e., the vascular parameters predicted by the model) are compared with the preset vascular parameters. At this point, the preset vascular parameters are the target output set based on the actual situation or standard data.

[0092] The actual performance of the model is evaluated by comparing its predictions with the preset results.

[0093] If the deviation between the training results and the preset blood vessel parameters is less than the preset threshold (e.g., the error is lower than a certain set tolerance), then the neural network model is considered to have achieved the expected performance and can be used in practical applications.

[0094] For example, if the deviation is less than 5%, the model's prediction performance can be considered to have met the standard, the model has been validated, and it meets the requirements of practical applications.

[0095] Step 306: Compare the training results with preset vascular parameters. If the deviation between the training results and the preset vascular parameters is less than a preset threshold, a preset neural network model is obtained.

[0096] Once the model has been tested and evaluated and meets the aforementioned deviation requirements, the second neural network model can be used as the final model for practical tasks. The model can then be used for prediction of new data and further optimization.

[0097] This application example, through optimized data acquisition, neural network training, and validation mechanisms, can effectively improve the accuracy, efficiency, and automation of vascular parameter prediction, and possesses good adaptability and generalization ability.

[0098] In the above Figure 1 Based on this, this application also provides a schematic diagram of the specific implementation process of a method for measuring vascular parameters. For example... Figure 4 As shown, acquiring the set of surface temperature signals of the target area under laser irradiation within a preset time period includes the following steps 401 to 403:

[0099] Step 401: Obtain multiple temperature images of the target area under laser irradiation within a preset time period.

[0100] Within a preset time period, a laser device is used to irradiate the target area. The surface temperature of the target area changes due to the thermal effect. Infrared lasers or other types of lasers are typically used. The surface temperature changes through the interaction between the laser and the target surface (such as absorption, reflection, and transmission).

[0101] Under laser irradiation, multiple temperature images of the target area are acquired within a preset time period using an infrared thermal imaging camera or other temperature sensing devices. These temperature images record the temperature distribution of the target area at different points in time. Each temperature image reflects the temperature field of the target area under laser irradiation at a specific moment.

[0102] Step 402: Extract multiple temperature signals from multiple temperature images.

[0103] Each temperature image is processed to extract the surface temperature signal of the target area. These temperature signals include the temperature value of each pixel, or the average temperature of a region can be obtained by aggregating the image regions.

[0104] If the target area is to be extracted as an average temperature signal of a region, the target area can be divided into multiple smaller areas (e.g., gridding), and then temperature data can be extracted from each smaller area.

[0105] Step 403: Sort the multiple temperature signals according to a preset time order to obtain a set of surface temperature signals.

[0106] All temperature signals acquired from different time points are sorted according to a preset time order to form a temperature time series. Each temperature signal corresponds to a time point, and the temperature signals in the series should be arranged in the order of acquisition time so that the temporal characteristics of temperature changes can be reflected in subsequent analysis.

[0107] Finally, through the above steps, a set of surface temperature signals is obtained, which serves as input data for subsequent analysis and model processing (such as training and inference in neural network models). This set of temperature signals reflects the thermal response changes of the target area under laser irradiation, providing data support for the measurement of vascular parameters.

[0108] This application example acquires multiple temperature images of a target area under laser irradiation, enabling continuous monitoring of temperature changes and obtaining high-precision, real-time temperature data. Each temperature image represents the temperature distribution at a specific point in time, comprehensively reflecting the thermal effects of laser irradiation on the target area. By sorting multiple temperature signals chronologically, a complete time-series temperature signal set is obtained. Thus, the temperature data is not merely a snapshot of a single moment, but comprehensively reflects the dynamic process of temperature change in the target area over time, facilitating in-depth analysis of the target area's thermal response characteristics.

[0109] As an example, the laser wavelength is 532nm, and the measurement range is 0-100 degrees.

[0110] The laser wavelength of 532nm is a typical wavelength for green lasers, commonly found in laser diodes or lasers. Laser sources with a wavelength of 532nm offer good beam quality, high brightness, and can effectively interact with many surface materials. The choice of laser wavelength directly affects the generation of thermal effects, the focusing performance of the beam, and the interaction mode with the target surface.

[0111] In practical applications, 532nm wavelength lasers can be effectively focused on the target area to generate a uniform heat distribution, making them suitable for scenarios such as material surface heating and laser heat treatment.

[0112] The temperature measuring device or system used in the method of this application embodiment can accurately measure the temperature range of the target area from 0°C to 100°C. To meet this requirement, a thermal imaging device or infrared thermometer suitable for low to medium temperature ranges needs to be selected. For example, an infrared thermal imager with a measurement range of 0-100°C can accurately capture temperature changes on the target surface within this temperature range.

[0113] This application example demonstrates that by employing a 532nm wavelength laser, it can provide high-precision temperature measurement, reduce external interference, ensure the accuracy of temperature data, and is suitable for a temperature range of 0-100 degrees Celsius. It meets the measurement needs for medium and low temperature ranges and has broad application prospects.

[0114] As an example, multiple temperature images of the target area under laser irradiation within a preset time period are obtained using an infrared detector.

[0115] Specifically, the first step is to select a suitable infrared detector. The operating wavelength range of the selected detector should match the radiation characteristics of the laser source. Based on the wavelength of the laser (e.g., infrared laser), an infrared detector, such as a thermal imager or a dedicated infrared detector array, can be selected. These detectors can sense temperature changes in the target area after laser irradiation and acquire temperature images at different time points.

[0116] The conditions for laser irradiation include laser power, duration, irradiation location, and irradiation angle. These parameters determine the temperature changes in the target area. The laser irradiation process may take place over a preset time period, during which the infrared detector needs to continuously record the temperature changes in the target area.

[0117] During laser irradiation, an infrared detector captures temperature images of the target area at different times. These temperature images are generated by an infrared camera, with each pixel representing the temperature of that area. To obtain multiple temperature images, the detector may take pictures at regular time intervals. For example, it might take one image every second, recording the temperature distribution changes in the target area under laser irradiation.

[0118] The infrared detector provided in this application example can measure the surface temperature of an object without contact and has high accuracy. Through infrared thermal imaging technology, it is possible to obtain an image of the temperature distribution of the target area under laser irradiation, providing detailed temperature data for subsequent analysis. This ensures accurate capture of temperature changes in the target area under laser irradiation, thereby improving the accuracy of the entire detection process.

[0119] As an example, the preset neural network model includes an input layer, a first convolutional layer, a pooling layer, fifteen residual layers, two fully connected layers, and an output layer. The residual layers include two batch normalization layers, two rectified linear unit activation function layers, two second convolutional layers, and a shortcut connection.

[0120] Specifically, the input layer is responsible for receiving external input data. In this example, the input data is a preprocessed temperature time series. The raw input data is then passed to subsequent layers in the neural network.

[0121] The first convolutional layer extracts local features through convolution operations. Its main function is to identify basic local features (such as temperature signal variation patterns) from the input data. This is achieved by performing convolution operations on the input using convolution kernels.

[0122] Pooling layers are used to reduce the spatial size of feature maps (e.g., dimensionality reduction), thereby reducing computational cost, extracting more representative features, and avoiding overfitting. By using methods such as max pooling or average pooling, the feature maps output by convolutional layers are reduced in size, thus decreasing the dimensionality of the data.

[0123] Fifteen residual layers alleviate the vanishing gradient problem during deep network training by introducing skip connections, enabling the model to learn more complex features. The core idea of ​​residual learning is to add the input and output signals through short-circuit connections, allowing information to flow more efficiently through multiple layers. Each residual layer contains multiple convolutional operations and activation functions, helping the model better capture and retain important features in the input signal.

[0124] Each residual layer contains the following sub-layers:

[0125] 1. Two second convolutional layers are used to further extract deeper features, typically for processing more complex features or for finer processing of the output of the previous layer.

[0126] 2. Two batch normalization layers are used to standardize the output of each layer, reduce internal covariate bias, and improve training efficiency.

[0127] 3. Two rectified linear unit activation function layers increase nonlinearity through activation functions, thereby improving the expressive power of the model.

[0128] 4. Shortcut connections are used to skip the computation of certain layers and pass the input directly to the next layer, which helps to reduce the training difficulty of deep neural networks.

[0129] Two fully connected layers integrate all the local features extracted earlier and output the final prediction result. Each neuron in each layer is connected to all neurons in the layer above.

[0130] Through multiple fully connected layers, the model is able to make a final prediction based on the extracted features (such as the temperature, depth, or thickness of blood vessels).

[0131] The output layer is responsible for providing the final result of the model, outputting the vascular parameters (such as temperature, depth, and thickness) of the target region. Based on the features extracted by the previous layers, it outputs the predicted values ​​of the vascular parameters.

[0132] The examples in this application, through the use of multi-layer convolution, residual learning, batch normalization, and rectified linear unit activation functions, significantly improve the performance of neural networks in complex tasks. They enhance the depth and accuracy of feature extraction and learning, reduce gradient problems during deep network training, and improve training stability and efficiency. They also improve the network's non-linear expressive power and computational efficiency, and strengthen the model's generalization ability, enabling it to achieve better performance on more diverse tasks and data.

[0133] Based on the foregoing embodiments, this application provides a vascular parameter measurement device, which includes various modules and units included in each module, and can be implemented by a processor; of course, it can also be implemented by specific logic circuits; in the implementation process, the processor can be a central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0134] Figure 5 A schematic diagram of a vascular parameter measuring device provided in this application embodiment is shown in the figure. The device 500 includes an acquisition module 501, a processing module 502, and an input module 503, wherein:

[0135] The acquisition module 501 is used to acquire a set of surface temperature signals of the target area under laser irradiation within a preset time period;

[0136] Processing module 502 is used to preprocess the surface temperature signal set to obtain a temperature time sequence;

[0137] The input module 503 is used to input the temperature time series into the preset neural network model to obtain at least one blood vessel parameter among the blood vessel temperature, depth and thickness of the target area. The preset neural network model is obtained by training the initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes multiple sets of temperature time series obtained after preprocessing the surface temperature signal set collected in historical measurement scenarios.

[0138] In some embodiments, the acquisition module 501 is further specifically used to acquire low-level features and high-level features of the temperature time series. The low-level features include at least one of temperature peaks, valleys and temperature differences between adjacent acquisition points within a preset time period. The high-level features include at least one of temperature distribution, temperature change and heat conduction features.

[0139] The processing module 502 is also specifically used to fuse low-level features and high-level features to obtain the fused features.

[0140] The input module 503 is also specifically used to input the fused features into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region.

[0141] In some embodiments, the acquisition module 501 is further specifically used to acquire the first epidermal temperature, the second epidermal temperature, and the vascular parameters corresponding to the first epidermal temperature of the target area through a vascular simulation model. The first epidermal temperature and the second epidermal temperature are used to characterize the skin temperature of the target area.

[0142] The acquisition module 501 is also specifically used to obtain the training set based on the temperature of the second epidermis;

[0143] The acquisition module 501 is also specifically used to obtain a validation set based on the first skin temperature and the vascular parameters corresponding to the first skin temperature;

[0144] The processing module 502 is also specifically used to train the initial neural network model based on the training set to obtain the blood vessel parameters of the training set;

[0145] The acquisition module 501 is also specifically used to calibrate the initial neural network model based on the blood vessel parameters of the validation set and the training set. If the accuracy of the blood vessel parameters of the training set output by the initial neural network model meets the preset threshold, a second neural network model is obtained.

[0146] The input module 503 is also specifically used to input multiple sets of surface temperature signals into the second neural network model to obtain training results;

[0147] The acquisition module 501 is also specifically used to compare the training results with preset vascular parameters, and obtain the preset neural network model when the deviation between the training results and the preset vascular parameters is less than a preset threshold.

[0148] In some embodiments, the acquisition module 501 is further specifically used to acquire multiple temperature images of the target area under laser irradiation within a preset time period;

[0149] The acquisition module 501 is also specifically used to extract multiple temperature signals corresponding to multiple temperature images;

[0150] The processing module 502 is also specifically used to sort multiple temperature signals according to the time sequence of the acquisition of the corresponding multiple temperature images to obtain a set of surface temperature signals.

[0151] The descriptions of the above device embodiments are similar to those of the above method embodiments, and have similar beneficial effects. For technical details not disclosed in the device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0152] It should be noted that, in the embodiments of this application... Figure 5 The module division of the vascular parameter measurement device shown is illustrative and represents only a logical functional division; in actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of this application can be integrated into a single processing unit, exist as separate physical units, or be integrated into a single unit with two or more units. The integrated units described above can be implemented in hardware, as software functional units, or a combination of both.

[0153] It should be noted that, in the embodiments of this application, if the above-described methods are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware and software combination.

[0154] This application provides a computer device, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the methods described above.

[0155] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method provided in the above embodiments.

[0156] This application provides a computer program product containing instructions that, when run on a computer, cause the computer to perform the steps in the method provided in the above-described method embodiments.

[0157] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0158] In one embodiment, the vascular parameter measuring device provided in this application can be implemented as a computer program, which can be configured as follows: Figure 6 The device operates on the computer device shown. The memory of the computer device can store the various program modules that make up the above-described apparatus. The computer program, composed of the various program modules, causes the processor to execute the steps of the methods in the various embodiments of this application described in this specification.

[0159] It should be noted that the descriptions of the storage medium and device embodiments above are similar to the descriptions of the method embodiments above, and have similar beneficial effects. For technical details not disclosed in the storage medium, storage medium, and device embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0160] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" mentioned throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above-described embodiments are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0161] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three kinds of relationships. For example, object A and / or object B can represent three situations: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0162] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple modules or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or modules can be electrical, mechanical, or other forms.

[0164] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0165] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0166] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0167] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause an electronic device to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROMs, magnetic disks, or optical disks.

[0168] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0169] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0170] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0171] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for measuring vascular parameters, characterized in that, include: Acquire the set of surface temperature signals of the target area under laser irradiation within a preset time period; The surface temperature signal set is preprocessed to obtain a temperature time series sequence; The temperature time series is input into a preset neural network model to obtain at least one blood vessel parameter among the blood vessel temperature, depth, and thickness of the target area. The preset neural network model is obtained by training an initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes multiple sets of temperature time series obtained after preprocessing the surface temperature signal set collected in historical measurement scenarios. The step of inputting the temperature time series into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region includes: The low-level features and high-level features of the temperature time series are obtained. The low-level features include at least one of temperature peaks, valleys and temperature differences between adjacent sampling points within a preset time period. The high-level features include at least one of temperature distribution, temperature change and heat conduction features. The low-level features and the high-level features are fused together to obtain the fused features. The fused features are input into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region. Multiple sets of surface temperature signals include sets of surface temperature signals from different temperature acquisition scenarios; The initial neural network model was trained using sample data collected from historical measurement scenarios, including: The first epidermal temperature, the second epidermal temperature, and the vascular parameters corresponding to the first epidermal temperature of the target area are obtained by vascular simulation model. The first epidermal temperature and the second epidermal temperature are used to characterize the skin temperature of the target area. The training set is obtained based on the second epidermal temperature; A validation set is obtained based on the first skin temperature and the corresponding vascular parameters. The initial neural network model is trained based on the training set to obtain the blood vessel parameters of the training set; The initial neural network model is calibrated based on the validation set and the vascular parameters of the training set. If the accuracy of the vascular parameters of the training set output by the initial neural network model meets a preset threshold, a second neural network model is obtained. The multiple sets of surface temperature signals are input into the second neural network model to obtain the training results; The training results are compared with preset vascular parameters. If the deviation between the training results and the preset vascular parameters is less than a preset threshold, a preset neural network model is obtained.

2. The method according to claim 1, characterized in that, The acquisition of the set of surface temperature signals of the target area under laser irradiation within a preset time period includes: Acquire multiple temperature images of the target area under laser irradiation within a preset time period; Extract multiple temperature signals corresponding to the multiple temperature images; The multiple temperature signals are sorted according to the time sequence of the acquisition of the corresponding multiple temperature images to obtain the surface temperature signal set.

3. The method according to claim 2, characterized in that, The wavelength of the laser is 532nm, and the measurement range is 0-100 degrees.

4. The method according to claim 2, characterized in that, Multiple temperature images of the target area under laser irradiation within the preset time period are obtained by an infrared detector.

5. The method according to claim 1, characterized in that, The preset neural network model includes an input layer, a first convolutional layer, a pooling layer, fifteen residual layers, two fully connected layers, and an output layer. The residual layers include two batch normalization layers, two rectified linear unit activation function layers, two second convolutional layers, and a shortcut connection.

6. A device for measuring vascular parameters, characterized in that, include: The acquisition module is used to acquire a set of surface temperature signals of the target area under laser irradiation within a preset time period; The processing module is used to preprocess the surface temperature signal set to obtain a temperature time series sequence; The input module is used to input the temperature time series into a preset neural network model to obtain at least one blood vessel parameter among the blood vessel temperature, depth, and thickness of the target area. The preset neural network model is obtained by training an initial neural network model based on sample data collected in historical measurement scenarios. The sample data includes a set of multiple sets of surface temperature signals collected in historical measurement scenarios. The processing module is further configured to input the temperature time series into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region, wherein: The low-level features and high-level features of the temperature time series are obtained. The low-level features include at least one of temperature peaks, valleys and temperature differences between adjacent sampling points within a preset time period. The high-level features include at least one of temperature distribution, temperature change and heat conduction features. The low-level features and the high-level features are fused together to obtain the fused features. The fused features are input into a preset neural network model to obtain at least one vascular parameter among the vascular temperature, depth, and thickness of the target region. The multiple sets of surface temperature signals include surface temperature signal sets from different temperature acquisition scenarios; the processing module is also used to train the initial neural network model using sample data acquired in historical measurement scenarios, wherein: The first epidermal temperature, the second epidermal temperature, and the vascular parameters corresponding to the first epidermal temperature of the target area are obtained by vascular simulation model. The first epidermal temperature and the second epidermal temperature are used to characterize the skin temperature of the target area. The training set is obtained based on the second epidermal temperature; A validation set is obtained based on the first skin temperature and the corresponding vascular parameters. The initial neural network model is trained based on the training set to obtain the blood vessel parameters of the training set; The initial neural network model is calibrated based on the validation set and the vascular parameters of the training set. If the accuracy of the vascular parameters of the training set output by the initial neural network model meets a preset threshold, a second neural network model is obtained. The multiple sets of surface temperature signals are input into the second neural network model to obtain the training results; The training results are compared with preset vascular parameters. If the deviation between the training results and the preset vascular parameters is less than a preset threshold, a preset neural network model is obtained.

7. A computer device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images