Analyte detection method and system, photographing parameter adjustment method and system, medium and equipment

Abstract

The invention provides an analyte detection and photographing parameter adjustment method and system, a medium and equipment, and belongs to the field of optical analys.The method comprises the steps that under multiple different exposure times, a first light source is used for exposing and imaging a first area to obtain a first image, and a second light source is used for exposing and imaging the first area to obtain a second image; obtaining a second image; respectively calculating an average gray value of pixels in the reference area according to the reference area; respectively constructing a linear function relationship between the exposure time and the average gray value; and inputting the gray value of the first image into the linear function relation to obtain the exposure time after the first light source is adjusted, and inputting the gray value of the second image into the linear function relation to obtain the exposure time after the second light source is adjusted. According to the invention, self-adaptive photographing parameter adjustment can be conveniently carried out for different users in real time, so that the influence of the human skin color and the use scene on the image gray level can be effectively reduced, and the detection accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of optical analysis, and more specifically, to a method, system, medium, and device for detecting and adjusting photographic parameters of an analyte. Background Technology

[0002] Among the detection technologies for analytes, commonly used methods include electrochemical and optical methods. Taking the detection of glucose in the human body as an example: Patent document US20100065441A1 discloses an analyte monitoring system, device, and method that implants a sensor under the skin to react electrochemically with glucose in the subcutaneous tissue, thereby obtaining glucose levels. The advantage of this approach is that it can collect glucose data in real time throughout the day as needed, without requiring multiple blood punctures, greatly facilitating user operation. However, its drawback is that it uses an invasive method by implanting the sensor under the skin. Patent document US20160287147A1 discloses a device for non-invasive in vivo measurement using Raman spectroscopy, measuring in vivo blood glucose concentration using Raman spectroscopy. The advantage of this approach is that the non-invasive detection method is more popular with users; however, its drawback is that it currently relies on a laboratory-grade Raman spectroscopy system, which is bulky and difficult to carry around and perform real-time detection.

[0003] In addition, patent document CN118078277A discloses a non-invasive blood glucose detection method based on hyperspectral data analysis. However, different human skin colors and detection scenarios will result in different gray levels of the acquired images, and different image gray levels will directly affect the accuracy of spectral data analysis. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the present invention aims to provide a method, system, medium, and device for detecting and adjusting photographic parameters of analytes.

[0005] A method for adjusting imaging parameters in analyte detection according to the present invention includes:

[0006] Image acquisition steps: Expose and image the first region using a first light source at two or more different exposure times to obtain the corresponding first image; then expose and image the first region using a second light source to obtain the corresponding second image.

[0007] The steps for calculating the average gray value are as follows: Extract the same region as the reference region from all the first and second images, and calculate the average gray value of the pixels within the reference region respectively.

[0008] Relationship construction steps: Based on the average gray value and the corresponding exposure time, construct the linear function relationship between the exposure time and the average gray value of the first light source, and the linear function relationship between the exposure time and the average gray value of the second light source, respectively.

[0009] Parameter confirmation steps: Input the grayscale value of the first image required for analyte detection into the linear function relationship, and use the exposure time required for the first light source as the adjusted exposure time of the first light source. Input the grayscale value of the second image required for analyte detection into the linear function relationship, and use the exposure time required for the second light source as the adjusted exposure time of the second light source.

[0010] Furthermore, the first light source is infrared light, and the first image is an infrared grayscale image; the second light source is ultraviolet light, and the second image is an ultraviolet grayscale image.

[0011] Furthermore, the linear functional relationship includes:

[0012] Gray value = slope * exposure time + intercept. The slope represents the rate of change of gray value when the exposure time increases by a unit. The intercept represents the gray value when the exposure time is 0.

[0013] The present invention provides a method for detecting an analyte, including a method for adjusting photographic parameters during the analyte detection process.

[0014] A photographic parameter adjustment system for analyte detection according to the present invention includes:

[0015] Image acquisition module: Exposes and images the first region using a first light source at two or more different exposure times to obtain a corresponding first image; and exposes and images the first region using a second light source to obtain a corresponding second image.

[0016] Average gray value calculation module: Extract the same region as a reference region in all first and second images, and calculate the average gray value of the pixels in the reference region respectively.

[0017] Relationship building module: Based on the average gray value and the corresponding exposure time, construct the linear function relationship between the exposure time and the average gray value of the first light source, and the linear function relationship between the exposure time and the average gray value of the second light source, respectively.

[0018] Parameter confirmation module: Input the grayscale value of the first image required for analyte detection into the linear function relationship, and use the exposure time required for the first light source as the adjusted exposure time of the first light source. Input the grayscale value of the second image required for analyte detection into the linear function relationship, and use the exposure time required for the second light source as the adjusted exposure time of the second light source.

[0019] Furthermore, the first light source is infrared light, and the first image is an infrared grayscale image; the second light source is ultraviolet light, and the second image is an ultraviolet grayscale image.

[0020] Furthermore, the linear functional relationship includes:

[0021] Gray value = slope * exposure time + intercept. The slope represents the rate of change of gray value when the exposure time increases by a unit. The intercept represents the gray value when the exposure time is 0.

[0022] The present invention provides an analyte detection system, including an image parameter adjustment system for analyte detection.

[0023] According to the present invention, a computer-readable storage medium storing a computer program is provided, wherein when the computer program is executed by a processor, the steps of the method for detecting the analyte are implemented.

[0024] An electronic device according to the present invention includes 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 method for detecting the analyte.

[0025] Compared with the prior art, the present invention has the following beneficial effects:

[0026] 1. This application can conveniently and in real time adjust the shooting parameters adaptively for different users, thereby effectively reducing the impact of human skin color and usage scene on image grayscale and improving the accuracy of detection.

[0027] 2. The detection method of this application does not require electrochemical reaction with the analyte, making the detection method more convenient. In particular, when detecting analytes in living organisms, it can achieve the purpose of non-invasive detection.

[0028] 3. The detection method of this application utilizes the non-uniform distribution of analytes in the imaging area to obtain spectral data of different regions. Since the distribution of other components besides analytes in the imaging area is relatively uniform, the differences in spectral data of different regions can directly reflect the information of the correlation between analytes and spectral data after the influence of non-analytes has been basically eliminated, such as the concentration of analytes.

[0029] 4. The detection method of 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 realizing the purpose of real-time detection. Attached Figure Description

[0030] 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:

[0031] Figure 1 This is a flowchart of Example 1;

[0032] Figure 2 This is a schematic diagram of the first image acquired in Example 2;

[0033] Figure 3 This is a schematic diagram of the second image acquired in Example 2;

[0034] Figure 4 This is a schematic diagram of the detection model in Example 2;

[0035] Figure 5 This is a schematic diagram of the detection point-reference point spectral data obtained in Example 2;

[0036] Figure 6 Experimental results to assess the accuracy of the analytical results of the model;

[0037] Figure 7 This is a schematic diagram of the structure of an analyte detection device provided in Example 5;

[0038] Figure 8 This is a schematic diagram of the structure of the electronic device provided in Example 6;

[0039] Figure 9 This is a schematic diagram of the structure of an analyte detection watch provided in Example 5;

[0040] Figure 10 A schematic diagram of the back of the watch used for analyte testing;

[0041] Figure 11 Exploded view of the watch for analysis;

[0042] Figure 12 A schematic diagram illustrating the usage status of a watch used for analyzing substances.

[0043] In the picture:

[0044] 100: Imaging area; 200: Detection equipment;

[0045] 201: Light source; 202: Imaging spectral detection device;

[0046] 203: Controller; 204: First bandpass filter;

[0047] 205: Lens; 206: Second bandpass filter;

[0048] 207: Circuit board; 501: Processor;

[0049] 502: Memory. Detailed Implementation

[0050] 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 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.

[0051] Example 1

[0052] Figure 1 This is a flowchart of this embodiment, which describes a method for detecting an analyte, including:

[0053] Imaging Steps: A light source provides light within a preset wavelength range to illuminate the first region, and an imaging spectral detection device images the first region, obtaining an image of the imaging area. The preset wavelength range of light illumination allows the image to reflect the distribution and spectral data of the reflected or excitation signals generated by the analyte under light illumination within the imaging area. 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 area refers to the area within the lens range of the imaging spectral detection device. In general, the imaging area can be a portion of the first region or the same region as the first region.

[0054] Since acquiring analyte distribution and spectral data requires illumination from light sources with varying wavelengths, there are two possible implementation methods: using a single light source with a wide wavelength range, or using two light sources, each with a smaller wavelength range. When using a single light source, the wavelength range of the light provided must simultaneously cover both the wavelength range needed to acquire analyte distribution and the wavelength range needed to acquire analyte spectral data. When using two light sources, each source provides different wavelengths; one wavelength covers the wavelength range needed to acquire analyte distribution data, and the other covers the wavelength range needed to acquire analyte spectral data. Furthermore, with a single light source, only one image is captured; with two light sources, two images are captured. 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 human skin surface.

[0055] In this application, the analytes 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 drugs such as antibiotics (e.g., gentamicin, vancomycin, etc.), digitalis, digoxin, abused drugs, theophylline, or warfarin. In embodiments detecting two or more analytes, the analytes can be monitored at the same or different times. In other embodiments, the analytes can also be other substances within the body surface, enabling non-invasive detection through this invention.

[0056] Spectral acquisition steps: An imaging spectral detection device acquires spectral data from the image, reflecting the non-uniform distribution of reflected or excitation signals generated by light irradiation of the analyte within the imaging region. Specifically, the imaging region can be divided into zones based on different data distribution patterns, facilitating the selection of locations from which spectral data can be acquired.

[0057] 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. Because the distribution of analytes varies 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: the epidermis, dermis, and subcutaneous tissue. Veins and other blood vessels are located in the subcutaneous tissue. Irradiating skin areas with and without blood vessels with ultraviolet light will yield corresponding spectral data, as will irradiating skin areas with thicker blood vessels and those with thinner blood vessels. The difference between these two spectral data points reflects 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, providing intermediate information for further analysis, or directly obtaining information such as the concentration of the analytes through an analytical model.

[0058] Example 2

[0059] 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:

[0060] 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 nm to acquire a first image of the imaging area. The first wavelength range is preferably in the near-infrared band. Then, irradiate the same location with ultraviolet light in the second wavelength range of 300-390 nm to acquire a second image of the imaging area.

[0061] like Figure 2 As shown, the horizontal axis represents the horizontal coordinate of the first image, and the vertical axis represents the vertical coordinate of the first image. White boxes represent selected detection point pixels on the veins, and black boxes represent selected reference point pixels on the surrounding skin. In the first image, some infrared light penetrates the skin, while some is absorbed. Simultaneously, the veins also absorb a significant amount of infrared light, resulting in lower pixel grayscale values ​​in vein areas and higher grayscale values ​​in non-vein areas. This allows for easy division of the imaging region into vein and non-vein areas.

[0062] like Figure 3 As shown, the horizontal axis represents the horizontal coordinate of the second image, and the vertical axis represents the vertical coordinate of the second image. White boxes represent selected detection point pixels on the veins, and black boxes represent selected reference point pixels on the surrounding skin. 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. Excitation light in the second wavelength range of 300-390 nm is used 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 excitation light's spectral signal and extract the effective fluorescence spectral signal. After absorbing ultraviolet light in the wavelength range of 300-390 nm, glucose in veins can emit fluorescence radiation signals in the visible light band of 400-800 nm. This band is within the effective response range of the imaging spectral detection device. The characteristic spectral intensity of this fluorescence radiation signal is positively correlated with the concentration of glucose and has high fluorescence excitation efficiency.

[0063] Spectral acquisition steps: Based on the grayscale distribution of pixels in the first image, the imaging area is divided into regions containing veins and regions not containing veins. Detection points are selected from the locations in the second image corresponding to the locations in the vein regions, and reference points are selected from the locations in the second image corresponding to the locations in the non-vein regions. The spectral data of the detection points and the reference points in the second image are then acquired respectively. Specifically, based on the grayscale values ​​of pixels in the second image, a pixel with a grayscale value meeting preset requirements is selected as a detection point from the vein regions, or a combination of that pixel and its adjacent pixels is selected as a detection point. A pixel with a grayscale value within a preset deviation range from the selected detection point is selected from the non-vein regions, 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 then calculated in the second image. The spectral data is taken from a single pixel of the detection point or reference point, or an average of multiple pixels, which can be appropriately selected according to the width of the blood vessel. Averaging multiple pixels can improve the signal-to-noise ratio, but is limited by the width of the blood vessel, avoiding the capture of areas outside the blood vessel. Selecting a single pixel has high spatial resolution and is suitable for thinner blood vessels, but the signal-to-noise ratio is lower. 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 as follows: Figure 5 As shown, the horizontal axis represents wavelength (in nm), and 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 grayscale value of the reference point and the grayscale value of the selected detection point are within a preset deviation range is that the skin in the imaging area may have influencing factors such as skin color, blemishes, and cosmetics, which can directly affect the spectral data of the reference point. The first image cannot distinguish areas with these influencing factors. By setting a preset deviation range for the grayscale value, these influencing factors can be effectively eliminated. Furthermore, ensuring that the grayscale value is within the preset deviation range ensures that the reference point is close to the detection point. For example, selecting it at the edge of a vein ensures that, apart from blood vessels, the color, thickness, and other parameters of the epidermis, dermis, and subcutaneous tissue are as close as possible, thus minimizing the influence of non-analytes on the deviation between the spectral data of the detection point and the spectral data of the reference point.

[0064] Besides 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.

[0065] When selecting a combination of multiple pixels as the detection point, the fluorescence spectrum data of that detection point can be the average of the fluorescence spectrum data of these pixels. Similarly, the number of detection points and reference points can be one or more. When there are multiple detection points and reference points, the average of the fluorescence spectrum data of all detection points and the average of the fluorescence spectrum data of all reference points can be calculated separately.

[0066] 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 model.

[0067] The detection model can 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. The convolutional layers and the activation function layers are distributed alternately. The activation function used in the activation function layers is the ReLU function.

[0068] In this convolutional neural network model, each convolutional kernel has a size of 1. The first convolutional layer has 32 kernels, and the second layer has 64 kernels, both used to extract blood glucose features. An activation function is used to non-linearly transform the output of each convolutional layer. The flatten layer flattens the output of the convolutional layers into a one-dimensional vector, facilitating connections to subsequent fully connected layers, resulting in a final output dimension of 1. During model training, the Adam optimizer is used, with mean squared error as the loss function, and mean absolute error is calculated as the performance metric for model evaluation.

[0069] When the output of the detection model is glucose concentration, training stops if the error between the output and the measured standard glucose concentration value meets a preset condition. When the output of the detection model is an intermediate result relating glucose and spectral data, such as an interneuron result, training stops if the error between the output and the interneuron result meets a preset condition. Further model correction is then performed on the interneuron result to obtain the glucose concentration.

[0070] like Figure 4As shown, 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 uses convolutional deep learning to combine features and output the final predicted blood glucose concentration value. The Output layer can also use convolutional deep learning to combine features and output a neuron as an intermediate result value (Output1). 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 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.

[0071] Through multiple iterations of training, neurons learn the corresponding changes in glucose concentration 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.

[0072] The entire glucose testing process eliminates the need for skin puncture for blood collection or implantation. It utilizes fluorescence spectroscopy to acquire the spectral information of the test subject and obtains the glucose test result based on this information, avoiding pain and discomfort and improving the comfort and convenience of the test. This method can precisely distinguish spectral signals from vascular and skin sites, enabling accurate extraction of subsequent glucose signals. Furthermore, it establishes a strong correlation between the spectral signal and glucose concentration, achieving precise measurement of glucose concentration. The test results are more accurate and easier to process.

[0073] Figure 6 The diagram shows 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. A total of 2037 participants were collected, including 1537 in the training set and 500 in the prediction set. 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.

[0074] Furthermore, before the imaging step, the imaging parameters need to be adjusted to improve the accuracy of the test; therefore, the present invention also provides a method for adjusting imaging parameters in analyte detection, including:

[0075] Image acquisition steps: At two or more different exposure times, in this embodiment, that is, at exposure times of 100ms, 200ms, 300ms, 400ms, 500ms, 600ms, and 700ms respectively, the first region is exposed and imaged using ultraviolet (UV) to obtain the corresponding ultraviolet grayscale image, and the first region is exposed and imaged using infrared (IR) to obtain the corresponding infrared grayscale image;

[0076] The steps for calculating the average gray value are as follows: Extract the same region as the reference region from all ultraviolet gray-scale images and infrared gray-scale images, and calculate the average gray value of the pixels within the reference region respectively.

[0077] Relationship construction steps: Based on the average gray value and the corresponding exposure time, construct linear function relationships between exposure time and average gray value for ultraviolet (UV) and infrared (IR), respectively.

[0078] Parameter confirmation steps: Input the grayscale value of the ultraviolet grayscale image required for analyte detection into the linear function relationship, and use the obtained exposure time required for ultraviolet UV as the ultraviolet UV adjusted exposure time. Input the grayscale value of the infrared grayscale image required for analyte detection into the linear function relationship, and use the obtained exposure time required for infrared IR as the infrared IR adjusted exposure time.

[0079] Specifically, the imaging parameters include gain and exposure time. When taking pictures with both ultraviolet (UV) and infrared (IR) light sources, the gain parameter is set to 1, and the exposure time of the two light sources needs to establish different functional relationships with grayscale.

[0080] Specifically, grayscale images of two light sources with different exposure times are taken in advance, with parameters of 100ms, 200ms, 300ms, 400ms, 500ms, 600ms, and 700ms, respectively, in order to ensure that clear, high-quality grayscale images are captured under different exposure times.

[0081] Specifically, in the average gray value calculation step, for all original ultraviolet grayscale images and infrared grayscale images, regions of the same size are extracted as reference regions, and the average gray value of pixels within the reference regions is calculated under different exposure times.

[0082] Specifically, a linear function relationship between exposure time and grayscale is constructed based on the grayscale value and exposure time parameters. The slope and intercept can be calculated using simple linear regression analysis. The general form of the linear function is: Grayscale = Slope * Exposure Time + Intercept. The specific values ​​of the slope and intercept are obtained from the fitted linear function.

[0083] The slope represents the rate of change of grayscale value as the unit exposure time increases; the intercept represents the grayscale value when the exposure time is 0.

[0084] Specifically, based on the slope and intercept values ​​obtained from the regression analysis, the target exposure time is calculated, and exposure and shooting are performed according to this set time.

[0085] Specifically, the exposure time parameter is adjusted according to the actual application to make the grayscale value suitable for people with different skin conditions.

[0086] Example 3

[0087] This embodiment, based on Embodiment 2, replaces infrared light with visible light, providing another non-invasive glucose detection method, including:

[0088] Imaging steps: First, a first image of the imaging area is acquired by illuminating the skin at the location of the vein, such as the wrist or back of the hand, with visible light. Second, a second image of the imaging area is acquired by illuminating the same location with ultraviolet light in the second wavelength range of 300-390 nanometers.

[0089] In the first image, the imaging area can be easily divided into areas containing veins and areas not containing veins because the colors of the areas containing veins differ from those of the areas not containing veins.

[0090] 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 nm 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 excitation light wavelength is less than 300 nm, the main peak 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 excitation light wavelength 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 excitation light spectral signal and extract the effective fluorescence spectral signal. After absorbing ultraviolet light in the 300-390 nm wavelength range, glucose in veins can emit fluorescence radiation signals in the 400-800 nm visible light band. This band is within the effective response range of the imaging spectral detection device, and the characteristic spectral intensity of this fluorescence radiation signal is positively correlated with the glucose concentration, exhibiting high fluorescence excitation efficiency.

[0091] 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 areas containing veins, and reference points are selected from the areas not containing veins. The spectral data of the detection points and the spectral data of the reference points are then acquired. 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 neighboring pixels, is selected from the areas containing veins 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 several neighboring pixels, is selected from the areas not containing veins as a reference point. The fluorescence spectral data of the detection point and the fluorescence spectral data of the reference point are then calculated. The reason why the grayscale value of the reference point is within the 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, pigmentation, and cosmetics, which will directly affect the spectral data of the reference point. The first image cannot simultaneously distinguish areas with all influencing factors. By setting a preset deviation range for the grayscale values, these influencing factors can be effectively eliminated.

[0092] When selecting a combination of multiple pixels as the detection point, the fluorescence spectrum data of that detection point can be the average of the fluorescence spectrum data of these pixels. Similarly, the number of detection points and reference points can be one or more. When there are multiple detection points and reference points, the average of the fluorescence spectrum data of all detection points and the average of the fluorescence spectrum data of all reference points can be calculated separately.

[0093] 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 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.

[0094] The detection model can 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. The convolutional layers and the activation function layers are distributed alternately. The activation function used in the activation function layers is the ReLU function.

[0095] In this convolutional neural network model, each convolutional kernel has a size of 1. The first convolutional layer has 32 kernels, and the second layer has 64 kernels, both used to extract blood glucose features. An activation function is used to non-linearly transform the output of each convolutional layer. The flatten layer flattens the output of the convolutional layers into a one-dimensional vector, facilitating connections to subsequent fully connected layers, resulting in a final output dimension of 1. During model training, the Adam optimizer is used, with mean squared error as the loss function, and mean absolute error is calculated as the performance metric for model evaluation.

[0096] 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.

[0097] 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. Then the training stops and the detection model is obtained.

[0098] Through multiple iterations of training, neurons learn the corresponding changes in glucose concentration 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.

[0099] The entire glucose testing process requires no blood sampling or skin puncture. It acquires the spectral information of the test subject based on fluorescence spectroscopy and obtains the glucose test result from this information, avoiding pain and discomfort and improving the comfort and convenience of the test. This method can precisely distinguish spectral signals from vascular and skin sites, enabling accurate extraction of subsequent glucose signals. It also establishes a strong correlation between the spectral signal and glucose concentration, achieving precise measurement of glucose concentration, resulting in more accurate test results and easier processing.

[0100] Example 4

[0101] This embodiment provides a detection system for an analyte. The 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:

[0102] 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 area. By illuminating the area with light within the preset wavelength range, the image reflects the distribution data and spectral data of the reflected or excitation signals generated by the analyte under light illumination within the imaging area. 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 two types of light are used, two images are obtained. For ease of processing, it is usually required that the imaging areas of the two images are identical.

[0103] 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, troponin, or drugs such as antibiotics (e.g., gentamicin, vancomycin, etc.), digitalis, digoxin, abused drugs, theophylline, and warfarin. In embodiments detecting more than one analyte, the analytes can be monitored at the same or different times. In other embodiments, the analyte can also be other substances in a liquid.

[0104] Spectrum acquisition module: This module acquires spectral data from images using an imaging spectral detection device. This data reflects the non-uniform distribution of reflected or excitation signals generated by light irradiation of the analyte within the imaging region. Specifically, the imaging region can be partitioned based on different data distribution patterns, allowing for the selection of locations from which to acquire spectral data.

[0105] Analysis Module: Based on the acquired spectral data, this module obtains information about the analytes in the imaging region. This information includes the correlation between the analyte and the spectral data. Because the distribution of analytes varies 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, thus accurately reflecting the correlation between the analyte and the spectral data, such as the analyte concentration.

[0106] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this 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.

[0107] Example 5

[0108] Figure 7 The illustration 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.

[0109] 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 or communication connection with the light source 201 and the imaging spectral detection device 202, respectively.

[0110] Light source 201 provides 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 providing a wider wavelength range; or two light sources, each providing a narrower wavelength range. When using only one light source, the wavelength range of the light provided must simultaneously cover the wavelength range required to acquire analyte distribution data and the wavelength range required to acquire analyte spectral data, such as a halogen lamp. When using two light sources, the two light sources provide different wavelengths; one wavelength covers the wavelength range required to acquire analyte distribution data, and the other wavelength covers the wavelength range required to acquire analyte spectral data, such as an infrared lamp combined with an ultraviolet lamp, or a visible light lamp combined with an ultraviolet lamp.

[0111] To ensure uniform illumination across the imaging area (100°), a ring-shaped light source can be used. This light source has multiple light-emitting modules evenly distributed around 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.

[0112] The imaging spectral detection device 202 is capable of imaging the imaging region 100 to obtain a corresponding image according to instructions, and can also obtain 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.

[0113] This periodic pixel-level filter structure comprises multiple filter pixel channels with different shapes. These channels are of uniform size and arranged evenly, 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 these structures are arranged periodically in a fixed order. The sensor modulates the received first detection light through this periodic pixel-level filter structure on its surface, forming a mosaic image containing spectral information. Subsequently, an algorithm reconstructs the spectral data.

[0114] 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, 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 captured; when there are two types of light sources 201, two images are captured. When the first light source is on, the second light source is off; similarly, when the second light source is on, the first light source is off, and the two do not interfere with each other.

[0115] 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.

[0116] 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 illuminated 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.

[0117] Lens 205 can be used for fixed-focusing 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 the imaging spectral detection device 202, which is not a limitation of the present invention.

[0118] Based on the above explanation, Figure 9 The image shown is an analyte detection watch provided in this embodiment. The front of the watch is a display screen, as shown... Figure 10 As shown, the back of the watch has a light-transmitting window and a built-in detection device 200. (As indicated...) Figure 11 As shown, both the light source 201 and the first bandpass filter 204 are ring-shaped 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 the required wavelength, which shines 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 part 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, it 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. Figure 12 As shown, to more accurately identify the location of veins, the watch can be worn on the inside of the wrist.

[0119] Example 6

[0120] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 8 As shown, it includes at least one processor 501; and a memory 502 communicatively connected to at least one processor 501; wherein the memory 502 stores instructions executable by at least one processor 501, the instructions being executed by at least one processor 501 to enable at least one processor 501 to perform the above-described method for detecting the analyte.

[0121] The memory 502 and processor 501 are connected via a bus, which may include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors 501 and memory 502 together. The bus can 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 can 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 processor 501 is transmitted over a wireless medium via an antenna, which further receives data and transmits it to processor 501.

[0122] Processor 501 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces,

[0123] Voltage regulation, power management, and other control functions are included. The memory 502 can be used to store data used by the processor 501 during operation.

[0124] 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.

[0125] 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. This 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 a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0126] 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 in form and detail may be made without departing from the spirit and scope of the present invention.

[0127] 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 essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for adjusting a photographing parameter in analyte detection, characterized in that, The method comprises the following steps: An image acquisition step: using a first light source to expose and image a first region at two or more different exposure times to obtain corresponding first images, and using a second light source to expose and image the first region to obtain corresponding second images; An average gray value calculation step: extracting the same region as a reference region from all the first images and second images, and calculating the average gray value of the pixels in the reference region; A relationship construction step: constructing a linear function relationship between the exposure time and the average gray value of the first light source, and a linear function relationship between the exposure time and the average gray value of the second light source according to the average gray value and the corresponding exposure time; A parameter confirmation step: inputting the gray value of the first image required for analyte detection into the linear function relationship, taking the obtained exposure time required for the first light source as the adjusted exposure time of the first light source, inputting the gray value of the second image required for analyte detection into the linear function relationship, and taking the obtained exposure time required for the second light source as the adjusted exposure time of the second light source.

2. The method of claim 1, wherein, The first light source is infrared light, and the first image is an infrared gray image; the second light source is ultraviolet light, and the second image is an ultraviolet gray image. 3.The method of claim 1, wherein, The linear function relationship comprises: Gray value = slope * exposure time + intercept, the slope represents the change rate of the gray value when the unit exposure time increases, and the intercept represents the gray value when the exposure time is 0.

4. A method of detecting an analyte, characterized by, The method comprises the following steps:

5. A system for adjusting photographic parameters in analyte detection, characterized in that, An image acquisition module: using a first light source to expose and image a first region at two or more different exposure times to obtain corresponding first images, and using a second light source to expose and image the first region to obtain corresponding second images; An average gray value calculation module: extracting the same region as a reference region from all the first images and second images, and calculating the average gray value of the pixels in the reference region; A relationship construction module: constructing a linear function relationship between the exposure time and the average gray value of the first light source, and a linear function relationship between the exposure time and the average gray value of the second light source according to the average gray value and the corresponding exposure time; A parameter confirmation module: inputting the gray value of the first image required for analyte detection into the linear function relationship, taking the obtained exposure time required for the first light source as the adjusted exposure time of the first light source, inputting the gray value of the second image required for analyte detection into the linear function relationship, and taking the obtained exposure time required for the second light source as the adjusted exposure time of the second light source. The first light source is infrared light, and the first image is an infrared gray image; the second light source is ultraviolet light, and the second image is an ultraviolet gray image.

6. The system of claim 5, wherein, The linear function relationship comprises:

7. The system of claim 5, wherein, Gray value = slope * exposure time + intercept, the slope represents the change rate of the gray value when the unit exposure time increases, and the intercept represents the gray value when the exposure time is 0. The system comprises the following steps:

8. A system for detecting an analyte, characterized by An image acquisition module: using a first light source to expose and image a first region at two or more different exposure times to obtain corresponding first images, and using a second light source to expose and image the first region to obtain corresponding second images; An average gray value calculation module: extracting the same region as a reference region from all the first images and second images, and calculating the average gray value of the pixels in the reference region; A relationship construction module: constructing a linear function relationship between the exposure time and the average gray value of the first light source, and a linear function relationship between the exposure time and the average gray value of the second light source according to the average gray value and the corresponding exposure time; A parameter confirmation module: inputting the gray value of the first image required for analyte detection into the linear function relationship, taking the obtained exposure time required for the first light source as the adjusted exposure time of the first light source, inputting the gray value of the second image required for analyte detection into the linear function relationship, and taking the obtained exposure time required for the second light source as the adjusted exposure time of the second light source.

9. A computer readable storage medium storing a computer program, characterized in that, The computer program, which is executed by a processor, implements the steps of the method for detecting an analyte according to any one of claims 1 to 3.

10. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program, which is executed by a processor, implements the steps of the method for detecting an analyte according to any one of claims 1 to 3.

Images