Method and system for target object positioning analysis, method and system for detecting analyte, computer-readable storage medium, and electronic device

Abstract

A method, system, media, and device for target location analysis include: irradiating a first region of the body surface with infrared light and imaging the first region to obtain a first image of the imaging region; dividing the imaging region into different gray-level regions based on the gray-level distribution in the first image; selecting a gray-level region whose gray-level value meets preset requirements as the region where blood vessels are located; selecting a gray-level region from the edge of the region where blood vessels are located that has a gray-level value within a preset deviation range as the region where skin is located; and irradiating the regions where blood vessels are located and the regions where skin is located with ultraviolet light to collect the fluorescent radiation signals emitted by the regions where blood vessels are located and the regions where skin is located, respectively. This application can accurately locate blood vessels in skin of different skin colors, improve the efficiency of blood vessel location, and reduce labor costs.

Description

[Technical Field]

[0001] This invention relates to the field of medical imaging, and more specifically, to a method, system, media, and device for target location analysis. [Previous Technology]

[0002] In blood glucose detection technologies, commonly used techniques include electrochemical and optical methods. Electrochemical methods target the subcutaneous surface and do not reach the depth of blood vessels, so there is no need to distinguish and locate blood vessels. However, the disadvantage is that this detection method is invasive. Optical methods require the location of blood vessels because the blood glucose content in blood vessels is higher than that in the skin. Traditional optical detection methods do not address how to distinguish between these two areas, which can lead to lower test results.

[0003] At the same time, different people have different skin colors, and even the skin color of the same person can change. When the skin color becomes darker, it will be difficult to locate the blood vessels under visible light.

[0004] Patent document CN112842257B discloses a method and apparatus for vascular localization. The method includes: acquiring a first infrared vascular image and a second infrared vascular image from at least two consecutively acquired infrared vascular images, wherein the acquisition time of the second infrared vascular image is later than that of the first infrared vascular image; determining a target vascular vessel in the first infrared vascular image; and determining the position of the target vascular vessel in the second infrared vascular image using a pyramid optical flow tracing method based on the target vascular vessel. The method identifies the target vascular vessel from the first infrared vascular image and then uses a pyramid optical flow tracing method to locate its position in the second infrared vascular image. Because the pyramid optical flow tracing method can adapt to large inter-frame variations, it can accurately determine the position of the target vascular vessel in the second infrared vascular image, thus ensuring accurate localization of the target vascular vessel. The advantage of this approach is that the pyramid optical flow tracing method can accurately determine the position of the target vascular vessel in the second infrared vascular image, thus ensuring accurate localization of the target vascular vessel. However, its drawback is that different people have different skin colors, making it difficult for the human eye or a camera to accurately locate the position of blood vessels in the skin. Patent document CN118078277A discloses a non-invasive blood glucose detection method based on hyperspectral data analysis, achieving non-invasive detection. This document employs absorption spectroscopy, but factors such as the excitation light source, skin color, and differences in epidermal thickness can affect the intensity of the spectral signal. Because blood glucose levels are higher in blood vessels than in the skin, traditional optical detection methods do not address how to distinguish between these two regions, leading to lower detection results.

[0005] Therefore, a new technical solution is needed to improve the above-mentioned technical problems. [Summary of the Invention]

[0006] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, media and device for target location analysis.

[0007] A method for target location analysis according to the present invention includes: a first imaging step: irradiating a first region of the body surface with infrared light and imaging the first region to obtain a first image of the imaging region; a division step: dividing the imaging region into different gray-level regions according to the gray-level distribution in the first image; a target location step: selecting a gray-level region whose gray-level value meets a preset requirement as the region where the target object is located; a non-target location step: selecting a gray-level region from the edge of the region where the target object is located that has a gray-level value within a preset deviation range from the region where the target object is located as the region where the non-target object is located; a second imaging step: irradiating the region where the target object is located and the region where the non-target object is located with ultraviolet light, and respectively collecting the fluorescent radiation signals emitted by the region where the target object is located and the region where the non-target object is located; wherein the target object is a vein and the non-target object is skin.

[0008] Preferably, the first imaging step includes: acquiring a first image under the illumination of infrared light in a first wavelength range; the first image includes data reflecting the distribution of reflected signals or excitation signals generated by the first region being illuminated by light in the imaging region.

[0009] Preferably, the division step includes: dividing the imaging area into a detection point candidate area and a reference point candidate area according to the grayscale distribution of pixels in the first image; selecting a detection point from the detection point candidate area; selecting a reference point from the reference point candidate area; and obtaining the spectral data of the detection point and the spectral data of the reference point, respectively.

[0010] Preferably, the second imaging step includes: acquiring a second image under illumination of light within a second wavelength range; the light within the second wavelength range includes ultraviolet light; based on the gray values ​​of pixels in the second image, selecting a pixel whose gray value meets a preset requirement from the candidate detection point region as a detection point or a combination of the pixel and its adjacent pixels as a detection point; selecting a pixel whose gray value is within a preset deviation range from the selected detection point from the candidate reference point region as a reference point or a combination of the pixel and its multiple adjacent pixels as a reference point; and calculating the fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point.

[0011] Preferably, the second wavelength range is 300-390 nanometers, and the second wavelength range is outside the effective response range of the imaging spectral detection device; the light in the second wavelength range can excite the analyte to emit a fluorescent radiation signal, and the main peak of the fluorescent radiation signal is within the effective response range of the imaging spectral detection device.

[0012] Preferably, the first imaging step includes: acquiring a first image under infrared light irradiation in the wavelength range of 800-1000 nanometers; the second imaging step includes: acquiring a second image under ultraviolet light irradiation in the wavelength range of 300-390 nanometers; the first image includes grayscale distribution data reflecting the reflection signal generated by the infrared light irradiation of the first region in the imaging region; the second image includes spectral data reflecting the fluorescence radiation signal excited by ultraviolet light irradiation of the target area and the non-target area in the imaging region; the division step includes: dividing the imaging region into a candidate region for detection points with smaller grayscale values ​​and a candidate region for reference points with larger grayscale values ​​according to the grayscale distribution data; selecting a pixel with a grayscale value that meets a preset requirement from the second image as a detection point or a combination of the pixel and adjacent pixels as a detection point according to the candidate region for detection points; selecting a pixel with a grayscale value within a preset deviation range from the grayscale value of the detection point from the second image as a reference point or a combination of the pixel and multiple adjacent pixels as a reference point according to the candidate region for reference points; Substitute the gray values ​​of the detection points in the second image into the spectral reconstruction algorithm to obtain the spectral data of the detection points. Substitute the gray values ​​of the reference points in the second image into the spectral reconstruction algorithm to obtain the spectral data of the reference points.

[0013] The present invention also provides a method for detecting an analyte, including the target analyte localization analysis method described above.

[0014] The present invention also provides a system for target location analysis, comprising: a first imaging module: irradiating a first region of the body surface with infrared light and imaging the first region to obtain a first image of the imaging region; a division module: dividing the imaging region into different gray-scale regions according to the gray-scale distribution in the first image; a target location module: selecting a gray-scale region whose gray-scale value meets preset requirements as the target location region; a non-target location module: selecting a gray-scale region whose gray-scale value is within a preset deviation range from the edge of the target location region as the non-target location region; and a second imaging module: irradiating the target location region and the non-target location region with ultraviolet light, and respectively collecting the fluorescent radiation signals emitted by the target location region and the non-target location region.

[0015] Preferably, the first imaging module includes: acquiring a first image under the illumination of infrared light in a first wavelength range; the first image includes data reflecting the distribution of reflected signals or excitation signals generated by the first region being illuminated by light in the imaging region.

[0016] Preferably, the division module includes: dividing the imaging area into a detection point candidate area and a reference point candidate area according to the grayscale distribution of pixels in the first image, selecting a detection point from the detection point candidate area, selecting a reference point from the reference point candidate area, and obtaining the spectral data of the detection point and the spectral data of the reference point respectively.

[0017] Preferably, the second imaging module includes: acquiring a second image under illumination of light within a second wavelength range; the light within the second wavelength range includes ultraviolet light; based on the grayscale value of the pixels in the second image, selecting a pixel whose grayscale value meets a preset requirement from the candidate region of detection points as a detection point or a combination of the pixel and its adjacent pixels as a detection point, selecting a pixel whose grayscale value is within a preset deviation range from the selected detection point from the candidate region of reference points as a reference point or a combination of the pixel and its multiple adjacent pixels as a reference point, and calculating the fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point.

[0018] Preferably, the second wavelength range is 300-390 nanometers, and the second wavelength range is outside the effective response range of the imaging spectral detection device; the light in the second wavelength range can cause the analyte to emit a fluorescent radiation signal, and the main peak of the fluorescent radiation signal is within the effective response range of the imaging spectral detection device.

[0019] Preferably, the first imaging module includes: acquiring a first image under infrared light irradiation in the wavelength range of 800-1000 nanometers; the second imaging module includes: acquiring a second image under ultraviolet light irradiation in the wavelength range of 300-390 nanometers; the first image includes grayscale distribution data reflecting the reflection signal generated by the infrared light irradiation of the first region in the imaging region; the second image includes spectral data reflecting the fluorescence radiation signal excited by ultraviolet light irradiation of the target area and the non-target area in the imaging region; the division module includes: dividing the imaging region into a candidate region for detection points with smaller grayscale values ​​and a candidate region for reference points with larger grayscale values ​​according to the grayscale distribution data; selecting a pixel with a grayscale value that meets a preset requirement from the second image as a detection point or a combination of the pixel and its adjacent pixels as a detection point according to the candidate region for detection points; selecting a pixel with a grayscale value within a preset deviation range from the grayscale value of the detection point from the second image as a reference point or a combination of the pixel and its multiple adjacent pixels as a reference point according to the candidate region for reference points; Substitute the gray values ​​of the detection points in the second image into the spectral reconstruction algorithm to obtain the spectral data of the detection points. Substitute the gray values ​​of the reference points in the second image into the spectral reconstruction algorithm to obtain the spectral data of the reference points.

[0020] The present invention also provides an analyte detection system, including the target analyte localization analysis system described above.

[0021] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the target location analysis method described above.

[0022] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the target location analysis method described above.

[0023] Compared with the prior art, the present invention has the following beneficial effects: 1. The technical solution of this application uses infrared light energy to accurately locate blood vessels in skin of different skin colors, improving the efficiency of blood vessel localization and reducing labor costs. 2. The technical solution of this application does not require electrochemical reaction with the analyte, making the detection method more convenient, especially when detecting analytes in living organisms, achieving the purpose of non-invasive detection. 3. By utilizing the non-uniform distribution of the analyte in the imaging area, this application can obtain spectral data from different regions. Since the distribution of other components besides the analyte in the imaging area is relatively uniform, the differences in spectral data from different regions can directly reflect the information related to the analyte and spectral data after basically excluding the influence of non-analytes, such as the concentration of the analyte. 4. This application uses fluorescence spectroscopy for detection, avoiding the traditional method of measuring analytes using Raman spectroscopy, thereby achieving low cost and miniaturization of the detection system, and achieving the purpose of real-time detection.

[0024] In order to make the above and other objects, features and advantages of the present invention more apparent and understandable, embodiments are described below in detail with reference to the accompanying drawings.

Implementation Method

[0026] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the present invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention. Embodiment 1

[0027] Figure 1 is a flowchart of this embodiment. This embodiment provides a method for detecting an analyte, including:

[0028] Imaging Step: The first region is illuminated by light within a preset wavelength range provided by a light source, and the first region is imaged by an imaging spectral detection device to obtain an image of the imaging region. Illumination with light within the preset wavelength range allows the image to reflect the distribution data and spectral data of the reflected or excitation signals generated by the analyte under light illumination within the imaging region. The first region can be a specific area on the surface of human skin. To avoid the influence of external light such as ambient light on the detection, the acquisition window of the imaging spectral detection device needs to be tightly attached to the surface of the human skin in the first region. The imaging region refers to the area within the lens range of the imaging spectral detection device. In general, the imaging region can be a part of the first region or the same region as the first region.

[0029] Since acquiring analyte distribution data and spectral data requires illumination from light sources with different wavelength ranges, there are two possible implementation methods: the light source can provide a single light source with a wider wavelength range, or two light sources can each provide light sources with smaller wavelength ranges. When there is only one light source, the wavelength range of the light provided by that light source needs to cover both the wavelength range required to acquire analyte distribution data and the wavelength range required to acquire analyte spectral data. When there are two light sources, the two light sources provide different light sources, with one light source covering the wavelength range required to acquire analyte distribution data and the other light source covering the wavelength range required to acquire analyte spectral data. Furthermore, when there is only one light source, the image is captured as one image; when there are two light sources, the image is captured as two images. For ease of processing, the imaging areas of the two images must be identical, meaning the acquisition window of the imaging spectral detection device must remain stationary on the surface of human skin.

[0030] In this application, the analyte can be glucose, ketones, alcohols, lactate, oxygen, hemoglobin A1C, acetylcholine, amylase, bilirubin, cholesterol, human chorionic gonadotropin, creatine kinase (e.g., CK-MB), creatine, creatinine, DNA, fructosamine, glutamine, growth hormone, hormones, peroxides, prostate-specific antigen, prothrombin, RNA, thyroid-stimulating hormone, or troponin, or it can be a drug such as antibiotics (e.g., gentamicin, vancomycin, etc.), digitalis, digoxin, abused drugs, theophylline, or warfarin. In embodiments that detect two or more analytes, the analytes can be monitored at the same or different times. In other embodiments, the analyte can also be other substances within the body surface, enabling non-invasive detection through this invention.

[0031] Spectral acquisition step: Spectral data reflecting the non-uniform distribution of reflected or excitation signals generated by the analyte under light illumination in the imaging region is acquired from the image using an imaging spectral detection device. Specifically, the imaging region can be divided into zones based on different distribution patterns to facilitate the selection of locations from which spectral data can be acquired.

[0032] Analysis Steps: Based on the acquired spectral data, information about the analytes in the imaging region is obtained. This information includes the correlation between the analytes and the spectral data. Since the distribution of analytes differs in different regions, the reflected or excitation signals generated by the analytes when exposed to light will also differ. Taking human skin as an example, it is divided into three parts: epidermis, dermis, and subcutaneous tissue. Veins and other blood vessels are located in the subcutaneous tissue. Ultraviolet light irradiation of skin areas with and without blood vessels can yield corresponding spectral data, as can skin areas with thicker blood vessels and skin areas with thinner blood vessels. The difference between these two spectral data can reflect the correlation between the analytes in the blood vessels and the spectral data, such as the degree of influence of the analytes on the spectral data, etc., for further analysis, or directly obtain information such as the concentration of the analytes through an analytical model. Example 2

[0033] This embodiment, based on Embodiment 1, takes the detection of glucose in human blood vessels as an example and provides a non-invasive glucose detection method, including:

[0034] Imaging steps: Irradiate the skin at the location of the vein, such as the wrist or back of the hand, with infrared light in the first wavelength range of 800-1000 nanometers, and acquire a first image of the imaging area. The first wavelength range is preferably the near-infrared band. Then irradiate the same location with ultraviolet light in the second wavelength range of 300-390 nanometers, and acquire a second image of the imaging area.

[0035] As shown in Figure 2, the horizontal axis represents the horizontal coordinate of the first image, and the vertical axis represents the vertical coordinate of the first image. The white boxes represent the selected detection point pixel blocks on the veins, and the black boxes represent the selected reference point pixel blocks on the surrounding skin. In the first image, part of the infrared light penetrates the human skin and part is absorbed by the human skin. At the same time, it is also largely absorbed by the veins. Therefore, the pixel gray values ​​in the vein areas are smaller, while the pixel gray values ​​in the non-vein areas are larger. This makes it easy to divide the imaging area into the vein area and the non-vein area.

[0036] As shown in Figure 3, the horizontal axis represents the horizontal coordinate of the second image, and the vertical axis represents the vertical coordinate of the second image. The white boxes represent the selected detection point pixel blocks on the veins, and the black boxes represent the selected reference point pixel blocks on the surrounding skin. In the second image, it is difficult to distinguish between the areas where veins are located and the areas where non-vein vessels are located, so the first image is needed for differentiation. An excitation light in the second wavelength range of 300-390 nanometers is used to obtain a high-quality effective fluorescence spectral signal. This is because the main response band of the imaging spectral detection device is located in the 400-800 nm range. When the wavelength of the excitation light used is less than 300 nm, the main peak of the fluorescence spectrum of the excited fluorescence radiation signal is located in the <400 nm band, making it difficult for the imaging spectral detection device to obtain a high-quality effective fluorescence spectral signal. When the wavelength of the excitation light used is greater than 390 nm, the excitation light itself is also visible light, and the spectral signal of the excitation light is superimposed on the fluorescence spectral signal, making it difficult to eliminate the interference of the spectral signal of the excitation light and extract the effective fluorescence spectral signal. After absorbing ultraviolet light in the 300-390 nm wavelength range, glucose in veins can emit fluorescent radiation signals in the 400-800 nm visible light band. This band is within the effective response range of the imaging spectral detection device. The characteristic spectral intensity of this fluorescent radiation signal is positively correlated with the glucose concentration and has high fluorescence excitation efficiency.

[0037] Spectral Acquisition Steps: Based on the grayscale distribution of pixels in the first image, the imaging area is divided into areas containing veins and areas not containing veins. Detection points are selected from the locations in the second image corresponding to the locations in the vein areas, and reference points are selected from the locations in the second image corresponding to the locations in the non-vein areas. The spectral data of the detection points and the spectral data of the reference points in the second image are acquired respectively. Specifically, based on the grayscale values ​​of pixels in the second image, a pixel whose grayscale value meets the preset requirements is selected from the vein areas as a detection point, or a combination of that pixel and its adjacent pixels is selected as a detection point. A pixel whose grayscale value is within the preset deviation range from the selected detection point is selected from the non-vein areas as a reference point, or a combination of that pixel and multiple adjacent pixels is selected as a reference point. The fluorescence spectral data of the detection points and the fluorescence spectral data of the reference points are calculated in the second image. Spectral data is taken from a single pixel or an average of multiple pixels at the detection point and reference point, which can be appropriately selected based on the blood vessel width. Averaging multiple pixels can improve the signal-to-noise ratio, but is limited by the blood vessel width, avoiding the capture of areas outside the blood vessel. Selecting a single pixel offers high spatial resolution and is suitable for thinner blood vessels, but has a lower signal-to-noise ratio. The preset requirement for grayscale values ​​could be to use the point with the smallest grayscale value as the detection point, but this application does not impose this restriction. The calculation results are shown in Figure 5, where the horizontal axis represents wavelength (in nm), the vertical axis represents relative radiance (in W / nm), the solid line represents the spectral data of the detection point, and the dashed line represents the spectral data of the reference point. The reason why the gray values ​​of the reference point and the selected detection point are within the preset deviation range is that the skin in the imaging area may have influencing factors such as skin color, spots, and cosmetics, which will directly affect the spectral data of the reference point. The first image cannot distinguish the areas with these influencing factors. By setting the preset deviation range of the gray values, these influencing factors can be effectively eliminated. In addition, the fact that the gray values ​​of the reference point and the selected detection point are within the preset deviation range can ensure that the selection of the reference point is close to the detection point. For example, if it is selected at the edge of the vein, it can ensure that the color, thickness and other parameters of the epidermis, dermis and subcutaneous tissue are as close as possible, except for the blood vessels. This makes the deviation between the spectral data of the detection point and the spectral data of the reference point minimize the influence of non-analytes.

[0038] In addition to spectral reconstruction algorithms, spectral data can also be obtained by generating radiometric calibration coefficients through prior radiometric calibration, and then calculating the spectral lines by multiplying the gray value by the radiometric calibration coefficients.

[0039] When selecting a combination of multiple pixels as the detection point, the fluorescence spectrum data of the detection point can be the average value of the fluorescence spectrum data of these pixels. Simultaneously, the number of detection points and reference points can be one or more. When there are multiple detection points and reference points, the average value of the fluorescence spectrum data of all detection points and the average value of the fluorescence spectrum data of all reference points can be calculated separately.

[0040] Analysis Steps: After preprocessing, the spectral data of the acquired detection points and reference points are input into the trained detection model, which outputs the glucose concentration or intermediate results relating glucose to the spectral data. During training, the detection model needs to simultaneously acquire the spectral data of the tested object and accurate test results, such as blood test results. The spectral data is used as the input to the detection model, and the blood test results are used as the output to train the detection model.

[0041] The detection model may be a convolutional neural network model, which sequentially includes an input layer, at least two convolutional layers, at least two activation function layers, a Flatten layer, a fully connected layer, and an output layer, wherein the convolutional layers and the activation function layers are distributed alternately; the activation function used in the activation function layers is the ReLU function.

[0042] In the convolutional neural network model, each convolutional kernel has a size of 1. The first convolutional layer has 32 kernels, and the second convolutional layer has 64 kernels, both used to extract blood glucose features. The output of the convolutional layer is non-linearly transformed through an activation function. The flatten layer flattens the output of the convolutional layer into a one-dimensional vector, facilitating connection to subsequent fully connected layers, resulting in a final output dimension of 1. During model training, the Adam optimizer is used for model training, and the mean squared error is used as the loss function. The mean absolute error is also calculated as the performance metric for model evaluation.

[0043] When the output of the detection model is glucose concentration, if the error between the output and the measured standard glucose concentration value meets a preset condition, training is stopped to obtain the detection model. When the output of the detection model is an intermediate result of the correlation between glucose and spectral data, such as the result of an interneuron, if the error between the output and the result of the interneuron meets a preset condition, training is stopped to obtain the detection model. Further model correction processing is performed on the interneuron result to obtain the glucose concentration.

[0044] As shown in Figure 4, the Input layer is the spectral data input layer, obtained after preprocessing the original spectral data. The Hidden layer is an intermediate hidden layer, which performs deep learning through convolution operations, combines features, and outputs the final predicted blood glucose concentration value. The Output layer can also perform deep learning through convolution operations, combine features, and output a neuron, Output1, as an intermediate result value. The intermediate result value Output1 and two infrared (IR) feature brightness values ​​are then used to train the model again to further correct the blood glucose prediction error and output the final predicted blood glucose concentration value, Output2. The training level of the detection model needs to be set with different parameters as required. The extracted glucose feature values ​​will continuously learn according to the different parameter settings until the error between the output result and the standard glucose value of the above label value meets the requirements, at which point training stops and the detection model is obtained.

[0045] Through multiple iterations of training, neurons learn the corresponding variation patterns between different glucose concentrations and glucose spectral characteristics of different samplers, thereby improving the universality of the detection model and enabling it to predict the glucose concentration of different users.

[0046] The entire glucose detection process does not require puncturing the skin to collect blood or implant a needle. It acquires the spectral information of the subject based on fluorescence spectroscopy and obtains the glucose detection result based on this spectral information, avoiding pain and discomfort and improving the comfort and convenience of the test. This method can precisely distinguish the spectral signals of blood vessels and skin sites, making it possible to accurately extract the glucose signal subsequently. At the same time, it also makes the spectral signal strongly correlated with glucose concentration, realizing accurate measurement of glucose concentration, resulting in more accurate detection results and more convenient processing.

[0047] Figure 6 shows a schematic diagram of the experimental results of the trained detection model. The horizontal axis represents the reference blood glucose concentration (in mmol / L) collected by the blood glucose meter, and the vertical axis represents the blood glucose concentration (in mmol / L) predicted using the method of this patent. The total sample size was 2037, including 1537 training samples and 500 prediction samples. The figure shows the distribution of the detection model's results. The MARD value of the predicted samples was 11.32%, with the vast majority of samples falling into regions A and B. Specifically, 87.03% of the samples fell into region A, and 12.77% fell into region B, indicating that the detection model has high accuracy. Example 3

[0048] This embodiment, based on Embodiment 2, replaces infrared light with visible light, providing another non-invasive glucose detection method, including:

[0049] Imaging steps: Illuminate the skin at the location of the vein, such as the wrist or back of the hand, with visible light to acquire a first image of the imaging area. Then, irradiate the same location with ultraviolet light in the second wavelength range of 300-390 nanometers to acquire a second image of the imaging area.

[0050] In the first image, since the color of the area where the veins are located differs from the color of the area where the non-vein vessels are located, the imaging area can be easily divided into the area where the veins are located and the area where the non-vein vessels are located.

[0051] In the second image, it is difficult to distinguish between areas containing veins and areas not containing veins, therefore the first image is needed for differentiation. Using excitation light in the second wavelength range of 300-390 nanometers is to obtain high-quality effective fluorescence spectral signals. This is because the main response band of the imaging spectral detection device is located in the 400-800 nm range. When the wavelength of the excitation light used is less than 300 nm, the main peak of the fluorescence spectrum of the excited fluorescence radiation signal is located in the <400 nm band, making it difficult for the imaging spectral detection device to obtain high-quality effective fluorescence spectral signals. When the wavelength of the excitation light used is greater than 390 nm, the excitation light itself is also visible light, and the spectral signal of the excitation light is superimposed on the fluorescence spectral signal, making it difficult to eliminate the interference of the spectral signal of the excitation light and extract the effective fluorescence spectral signal. After absorbing ultraviolet light in the 300-390 nm wavelength range, glucose in veins can emit fluorescent radiation signals in the 400-800 nm visible light band. This band is within the effective response range of the imaging spectral detection device. The characteristic spectral intensity of this fluorescent radiation signal is positively correlated with the glucose concentration and has high fluorescence excitation efficiency.

[0052] Spectral Acquisition Steps: Based on the grayscale distribution of pixels in the first image, the imaging area is divided into areas containing veins and areas not containing veins. Detection points are selected from the locations in the second image corresponding to the locations in the vein areas, and reference points are selected from the locations in the second image corresponding to the locations in the non-vein areas. The spectral data of the detection points and the spectral data of the reference points are acquired respectively. Specifically, based on the grayscale values ​​of pixels in the second image, a pixel with a grayscale value that meets preset requirements or a combination of that pixel and its adjacent pixels is selected from the vein areas as a detection point. A pixel with a grayscale value within a preset deviation range from the selected detection point or a combination of that pixel and multiple adjacent pixels is selected from the non-vein areas as a reference point. The fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point are calculated. The reason why the grayscale value of the reference point is within a preset deviation range from the grayscale value of the selected detection point is that the skin in the imaging area may have influencing factors such as skin color, spots, and cosmetics, which will directly affect the spectral data of the reference point. The first image cannot simultaneously distinguish the areas of all influencing factors. By setting a preset deviation range for the grayscale values, these influencing factors can be effectively eliminated.

[0053] When selecting a combination of multiple pixels as the detection point, the fluorescence spectrum data of the detection point can be the average value of the fluorescence spectrum data of these pixels. Simultaneously, the number of detection points and reference points can be one or more. When there are multiple detection points and reference points, the average value of the fluorescence spectrum data of all detection points and the average value of the fluorescence spectrum data of all reference points can be calculated separately.

[0054] Analysis steps: After preprocessing, the spectral data of the acquired detection points and reference points are input into the trained detection model, which outputs the glucose concentration. During training, the detection model needs to acquire both the spectral data of the tested object and accurate test results, such as blood test results. The spectral data is used as the input to the detection model, and the blood test results are used as the output to train the detection model.

[0055] The detection model may employ a convolutional neural network model, which sequentially includes an input layer, at least two convolutional layers, at least two activation function layers, a Flatten layer, a fully connected layer, and an output layer, wherein the convolutional layers and the activation function layers are distributed alternately; the activation function used in the activation function layers is the ReLU function.

[0056] In the convolutional neural network model, each convolutional kernel has a size of 1. The first convolutional layer has 32 kernels, and the second convolutional layer has 64 kernels, both used to extract blood glucose features. The output of the convolutional layers is non-linearly transformed through an activation function. The flatten layer flattens the output of the convolutional layers into a one-dimensional vector, facilitating connection to subsequent fully connected layers, resulting in a final output dimension of 1. During model training, the Adam optimizer is used for model training, and the mean squared error is used as the loss function. The mean absolute error is also calculated as the performance metric for model evaluation.

[0057] If the error between the output of the detection model and the standard glucose value meets the preset conditions, then training is stopped and the detection model is obtained.

[0058] The training level of the detection model needs to be set with different parameters as required. The extracted glucose feature values ​​will be continuously learned according to the different parameter settings until the error between the output result and the standard glucose value of the above label value meets the requirements. Then the training will stop and the detection model will be obtained.

[0059] Through multiple iterations of training, neurons learn the corresponding variation patterns between different glucose concentrations and glucose spectral characteristics of different samplers, thereby improving the universality of the detection model and enabling it to predict the glucose concentration of different users.

[0060] The entire glucose detection process does not require blood collection or skin puncture. It acquires the spectral information of the test subject based on fluorescence spectroscopy and obtains the glucose detection result based on this spectral information, avoiding pain and discomfort and improving the comfort and convenience of the test. This method can precisely distinguish the spectral signals of blood vessels and skin sites, making it possible to accurately extract the glucose signal subsequently. At the same time, it also makes the spectral signal strongly correlated with glucose concentration, realizing accurate measurement of glucose concentration, resulting in more accurate detection results and more convenient processing. Example 4

[0061] This embodiment provides an analyte detection system. The analyte detection system can be implemented by executing the steps of the analyte detection method. That is, those skilled in the art can understand the analyte detection method as a preferred embodiment of the analyte detection system. The analyte detection system includes:

[0062] Imaging Module: The light source provides light within a preset wavelength range to illuminate the first region, and the imaging spectral detection device images the first region to obtain an image of the imaging region. By illuminating the first region with light within the preset wavelength range, the image reflects the distribution data and spectral data of the reflected or excited signals generated by the analyte under light illumination within the imaging region. Since different wavelength ranges are required to obtain the distribution data and spectral data of the analyte, the light source can be two corresponding wavelength ranges, or it can be a single light source with a larger wavelength range covering both required wavelength ranges. When there are two types of light, two images are obtained. For ease of processing, it is usually required that the imaging areas of the two images are the same.

[0063] In this application, the analyte may be glucose, ketones, alcohols, lactate, oxygen, hemoglobin A1C, acetylcholine, amylase, bilirubin, cholesterol, human chorionic gonadotropin, creatine kinase (e.g., CK-MB), creatine, creatinine, DNA, fructosamine, glutamine, growth hormone, hormones, peroxides, prostate-specific antigen, prothrombin, RNA, thyroid-stimulating hormone, troponin, or drugs such as antibiotics (e.g., gentamicin, vancomycin, etc.), digitalis, digoxin, abused drugs, theophylline, and warfarin. In embodiments that detect more than one analyte, the analytes may be monitored at the same or different times. In other embodiments, the analyte may also be other substances in a liquid.

[0064] Spectral Acquisition Module: This module acquires spectral data from an image, reflecting the non-uniform distribution of reflected or excitation signals generated by light irradiation of the analyte within the imaging region, using an imaging spectral detection device. Specifically, the imaging region can be partitioned according to different data distribution patterns to facilitate the selection of locations from which spectral data can be acquired.

[0065] Analysis Module: Based on the acquired spectral data, information about the analytes in the imaging region is obtained. This information includes the correlation between the analytes and the spectral data. Because the distribution of analytes differs in different zones, the reflected or excitation signals generated by the analytes when illuminated will also differ. Utilizing this characteristic, the differences in spectral data between the two can be obtained, thereby accurately reflecting the correlation between the analytes and the spectral data, such as the concentration of the analytes.

[0066] Those skilled in the art will understand that, in addition to implementing the system and its various devices, modules, and units provided by the present invention in the form of logic gates, switches, dedicated integrated circuits, programmable logic controllers, and embedded microcontrollers, the same functions can be achieved entirely through logical programming of the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component. Example 5

[0067] Figure 7 shows an electronic device of this embodiment, specifically an analyte detection device 200. The detection device 200 is a portable non-invasive detection device for the human body. It can be a standalone detection device or integrated into a watch or mobile phone, thereby enabling convenient and quick detection of analytes on the body surface.

[0068] The detection device 200 includes: a light source 201, an imaging spectral detection device 202, a controller 203, a first bandpass filter 204, a second bandpass filter 206, and a lens 205. The controller 203 establishes an electrical connection or a communication connection with the light source 201 and the imaging spectral detection device 202, respectively.

[0069] Light source 201 is capable of providing light within a preset wavelength range. Since acquiring analyte distribution data and spectral data requires illumination from light sources with different wavelength ranges, there are two possible implementation methods: one light source capable of providing light with a wider wavelength range; or two light sources each providing light with a narrower wavelength range. When there is only one light source, the wavelength range of the light provided by that light source needs to simultaneously cover the wavelength range capable of acquiring analyte distribution data and the wavelength range capable of acquiring analyte spectral data, such as a halogen lamp. When there are two light sources, the two light sources provide different light, with one light covering the wavelength range capable of acquiring analyte distribution data and the other light covering the wavelength range capable of acquiring analyte spectral data, such as an infrared lamp combined with an ultraviolet lamp, or a visible light lamp combined with an ultraviolet lamp.

[0070] To ensure uniform illumination in the imaging area 100, a ring-shaped light source can be used. The light source has multiple light-emitting modules that are evenly distributed on the same circumference. When there are two types of light sources, the light-emitting modules of the two types of light sources are arranged alternately.

[0071] The imaging spectral detection device 202 is capable of imaging the imaging region 100 to obtain a corresponding image according to instructions, and is also capable of obtaining corresponding spectral data according to instructions. The imaging spectral detection device 202 includes a sensor and a periodic pixel-level filter structure disposed on the sensor surface. The periodic pixel-level filter structure is used to spectrally modulate the incoming light signal so that the sensor can generate an image containing the spectral information to be measured.

[0072] This periodic pixel-level filter structure includes multiple filter pixel channels with different shapes. These filter pixel channels have the same dimensions and are uniformly arranged, with their length and width being integer multiples of the pixel size within the image sensor. Different shapes of pixel-level filter channels correspond to different spectral filtering coefficients, and pixel-level filter structures with different spectral filtering coefficients are periodically arranged in a fixed order. The sensor modulates the received first detection light through the periodic pixel-level filter structure on its surface, forming a mosaic image containing spectral information. Subsequently, an algorithm is used to reconstruct a grayscale image containing the spectral information to be measured.

[0073] The controller 203 is configured to control the light source to provide light within a preset wavelength range to illuminate the first region, and to control the imaging spectral detection device to image the first region, thereby obtaining an image of the imaging region. The controller also controls the imaging spectral detection device to acquire spectral data from the image reflecting the non-uniform distribution of reflection or excitation signals generated by the analyte under light illumination within the imaging region. Based on the acquired spectral data, information about the analyte in the imaging region is obtained, including information relating the analyte to the spectral data. When there is only one type of light source 201, one image is formed; when there are two types of light sources 201, two images are formed. When the first type of light source is on, the second type of light source is off; similarly, when the second type of light source is on, the first type of light source is off, and the two do not interfere with each other.

[0074] The first bandpass filter 204 is located between the light source 201 and the imaging area 100. Its function is to allow light within a preset wavelength range to pass through, while blocking light outside the preset wavelength range, thereby reducing the influence of other external light on the detection results.

[0075] The second bandpass filter 206 is located between the imaging spectral detection device 202 and the lens 205. Its function is to allow light in the wavelength range of the reflected signal or excitation signal generated by the analyte when it is irradiated to pass through, while light in other wavelength ranges is blocked, thereby reducing the influence of the reflected signal or excitation signal of non-analytes on the detection results.

[0076] Lens 205 can be used for fixed-focusing in order to obtain a clear image. In other embodiments, the second bandpass filter 206 may also be located on the side of lens 205 away from imaging spectral detection device 202, and the present invention is not limited thereto.

[0077] As described above, Figure 9 shows an analytical substance detection watch provided in this embodiment. The front of the watch is a display, as shown in Figure 10. The back of the watch has a light-transmitting window and a built-in detection device 200. As shown in Figure 11, both the light source 201 and the first bandpass filter 204 are annular structures. The light-emitting modules of the light source 201 are arranged in a ring. The emitted light is filtered by the first bandpass filter 204 and outputs light with a wavelength that meets the requirements. This light is then irradiated onto the human body through the light-transmitting window on the back of the watch. The reflected signal or excitation signal from the human body enters the light-transmitting window, passes through the hollowed-out portion in the middle of the light source 201 and the first bandpass filter 204, passes through the lens 205, and enters the second bandpass filter 206. After being filtered by the second bandpass filter 206, the light enters the imaging spectral detection device 202. The imaging spectral detection device 202 is mounted on the circuit board 207. At the same time, the controller 203 (not shown in the figure) of the detection device 200 is also mounted on the circuit board 207. As shown in Figure 12, to more accurately identify the location of veins, the watch can be worn on the inside of the wrist. Example 6

[0078] Figure 8 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. As shown in Figure 8, it includes at least one processor 501; and a memory 502 communicatively connected to at least one processor 501. The memory 502 stores instructions that can be executed by at least one processor 501. The instructions are executed by at least one processor 501 so that at least one processor 501 can perform the above-mentioned method for detecting analytes.

[0079] The memory 502 and the processor 501 are connected via a bus. The bus may include any number of interconnected buses and bridges, connecting various circuits of one or more processors 501 and memory 502 together. The bus may also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be further described here. A bus interface provides an interface between the bus and the transceiver. The transceiver may be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by the processor 501 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to the processor 501.

[0080] The processor 501 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory 502 can be used to store the data used by the processor 501 during operation.

[0081] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for detecting analytes.

[0082] That is, those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing related hardware. The program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps 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 flash drives, removable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0083] Those skilled in the art will understand that the above embodiments are specific examples of implementing the present invention, and in practical applications, various changes can be made in form and detail without departing from the spirit and scope of the present invention.

[0084] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the substantive content of the present invention. Unless otherwise specified, the embodiments and features described in the embodiments of this application can be arbitrarily combined with each other. [Simplified Explanation of the Diagram]

[0025] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 is a flowchart of Embodiment 1; Figure 2 is a schematic diagram of a first image acquired in Embodiment 2; Figure 3 is a schematic diagram of a second image acquired in Embodiment 2; Figure 4 is a schematic diagram of the detection model of Embodiment 2; Figure 5 is a schematic diagram of the detection point-reference point spectral data obtained in Embodiment 2; Figure 6 is an experimental result of the accuracy of the analysis results of the analysis model; Figure 7 is a structural schematic diagram of an analyte detection device provided in Embodiment 5; Figure 8 is a structural schematic diagram of an electronic device provided in Embodiment 6; Figure 9 is a structural schematic diagram of an analyte detection watch provided in Embodiment 5; Figure 10 is a back view of the analyte detection watch; Figure 11 is an exploded view of the analyte detection watch; Figure 12 is a schematic diagram of the analyte detection watch in use.

Claims

1. A method for target location analysis, characterized in that it includes: First imaging step: Illuminate a first region of the body surface with infrared light and image the first region to obtain a first image of the imaging region; Segmentation step: Based on the grayscale distribution in the first image, the imaging area is divided into different grayscale regions; Target object localization step: Select a grayscale region whose grayscale value meets the preset requirements as the target object region; Non-target object localization step: Select a grayscale region from the edge of the target object region whose grayscale value is within the preset deviation range as the non-target object region; The second imaging step involves illuminating the area where the target object is located and the area where the non-target object is located with ultraviolet light, and then collecting the fluorescence radiation signals emitted by the areas where the target object is located and the non-target object is located, respectively.

2. The method for target location analysis as described in claim 1, characterized in that the first imaging step includes: The first image is acquired under the illumination of infrared light within a first wavelength range; the first image includes data reflecting the distribution of reflected or excitation signals generated by the first region being illuminated by light in the imaging region.

3. The method for target location analysis as described in claim 1, characterized in that the division step includes: The imaging region is divided into a candidate region for detection points and a candidate region for reference points based on the grayscale distribution of pixels in the first image. Detection points are selected from the candidate regions for detection points, and reference points are selected from the candidate regions for reference points. The spectral data of the detection points and the spectral data of the reference points are obtained respectively.

4. The method for target location analysis as described in claim 1, characterized in that the second imaging step includes: A second image is acquired under illumination within the second wavelength range; Light in the second wavelength range includes the ultraviolet light; Based on the grayscale values ​​of pixels in the second image, a pixel whose grayscale value meets the preset requirements is selected from the candidate detection point region corresponding to the position in the second image as a detection point, or a combination of the pixel and its neighboring pixels is selected as the detection point. A pixel whose grayscale value is within the preset deviation range from the selected detection point is selected from the candidate reference point region corresponding to the position in the second image as a reference point, or a combination of the pixel and its multiple neighboring pixels is selected as the reference point. The fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point are calculated.

5. The method for target location analysis as described in claim 4, characterized in that the second wavelength range is 300-390 nanometers, and the second wavelength range is outside the effective response range of the imaging spectral detection device; the light in the second wavelength range can cause the analyte to emit the fluorescence radiation signal, and the main peak of the fluorescence spectrum of the fluorescence radiation signal is within the effective response range of the imaging spectral detection device.

6. A method for detecting an analyte, comprising the method for target location analysis as described in any one of claims 1-5.

7. A system for target location analysis, characterized in that it comprises: First imaging module: Illuminates a first region of the body surface with infrared light and images the first region to obtain a first image of the imaging region; Segmentation Module: Based on the grayscale distribution in the first image, the imaging area is divided into different grayscale regions; Target Object Localization Module: Selects grayscale regions whose grayscale values ​​meet preset requirements as the target object's location region; Non-Target Object Localization Module: Selects grayscale regions whose grayscale values ​​are within a preset deviation range from the target object's location region from the edge of the target object's location region as non-target object's location region; The second imaging module: by illuminating the area where the target object is located and the area where the non-target object is located with ultraviolet light, it collects the fluorescent radiation signals emitted by the areas where the target object is located and the areas where the non-target object is located, respectively.

8. The system for target location analysis as described in claim 7, characterized in that the first imaging module comprises: The first image is acquired under the illumination of infrared light within a first wavelength range; the first image includes data reflecting the distribution of reflected or excitation signals generated by the first region being illuminated by light in the imaging region.

9. The system for target location analysis as described in claim 7, characterized in that the partitioning module comprises: The imaging region is divided into a candidate region for detection points and a candidate region for reference points based on the grayscale distribution of pixels in the first image. Detection points are selected from the candidate regions for detection points, and reference points are selected from the candidate regions for reference points. The spectral data of the detection points and the spectral data of the reference points are obtained respectively.

10. The system for target location analysis as described in claim 7, characterized in that the second imaging module comprises: A second image is acquired under illumination within the second wavelength range; Light in the second wavelength range includes the ultraviolet light; Based on the grayscale values ​​of pixels in the second image, a pixel whose grayscale value meets the preset requirements is selected from the candidate detection point region corresponding to the position in the second image as a detection point, or a combination of the pixel and its neighboring pixels is selected as the detection point. A pixel whose grayscale value is within the preset deviation range from the selected detection point is selected from the candidate reference point region corresponding to the position in the second image as a reference point, or a combination of the pixel and its multiple neighboring pixels is selected as the reference point. The fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point are calculated.

11. The system for target location analysis as claimed in claim 10, characterized in that the second wavelength range is 300-390 nanometers, the second wavelength range is outside the effective response range of the imaging spectral detection device; the light in the second wavelength range can cause the analyte to emit the fluorescent radiation signal, the main peak of the fluorescent spectrum of the fluorescent radiation signal being within the effective response range of the imaging spectral detection device.

12. An analyte detection system, comprising the target analyte localization analysis system as described in any one of claims 7-11.

13. A computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method for target location analysis as described in any one of claims 1 to 5.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when executed by the processor, the computer program implements the steps of the method for target location analysis as described in any one of claims 1 to 5.

Images