Non-invasive blood glucose concentration detection method based on near-infrared spectrum detection

Abstract

The application discloses a noninvasive blood glucose concentration detection method based on near-infrared spectrum detection and relates to the technical field of blood glucose concentration detection, and comprises the following steps: acquiring target near-infrared spectrum data and performing noise calibration; dividing the spectral domain band of the calibrated spectrum into a short-wave region sensitive to melanin and a long-wave region insensitive to melanin; estimating a first gain of each region based on a partition gain white balance; combining a priori function of melanin content-spectrum shape change fitted by an offline Monte Carlo library to constrain and optimize the first gain, limiting the gain to a low-dimensional projection of the a priori in real time to obtain a second gain, combining a preset cross-region smoothing function, outputting the spectrum after white balance correction as a first spectrum, and applying the first spectrum to blood glucose concentration detection, so that the problems of spectrum baseline deviation and blood glucose sensitive waveband peak shape distortion caused by individual melanin difference are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of blood glucose concentration detection, and more particularly to a non-invasive blood glucose concentration detection method based on near-infrared spectroscopy. BACKGROUND

[0002] The non-invasive blood glucose concentration detection method based on near-infrared spectroscopy obtains a near-infrared spectrum signal by irradiating the skin, and establishes a mapping relationship by using a statistical or machine learning model of the spectrum characteristics and the blood glucose concentration to realize the prediction of the blood glucose concentration. Such a method is widely used in the prior art and can avoid the discomfort and infection risk caused by traditional invasive blood sampling, and has the potential of non-invasive, rapid and continuous monitoring. The conventional process includes spectrum acquisition, preprocessing, feature extraction, modeling and blood glucose prediction, which is the core step of the existing non-invasive blood glucose detection system.

[0003] However, the prior art has significant deficiencies. Due to the difference in skin color of individuals, the difference in melanin content causes the difference in absorption of near-infrared light in the skin, which causes the baseline shift of the spectrum, especially in the short-wave region sensitive to melanin. This baseline shift interferes with the blood glucose sensitive feature signal and directly affects the accuracy of the blood glucose concentration prediction. In addition, the difference in response of different light sources and detectors and the change in environmental light conditions may also cause inconsistency in the spectrum signal, making it difficult for traditional spectrum processing methods to ensure the comparability and stability across individuals.

[0004] In other fields of optical imaging and signal processing, the white balance technique is often used to compensate for the overall brightness and color deviation in the image or spectrum signal, and by adjusting the gain or reference, the signal remains consistent under different acquisition conditions. The white balance method can quickly correct the overall spectrum intensity and reduce the signal shift caused by changes in external conditions, and is a mature technology in existing image processing and spectrum correction.

[0005] However, directly applying the white balance method to non-invasive blood glucose detection based on near-infrared spectroscopy has limitations. Traditional white balance usually processes the overall gain of the full spectrum and lacks a partition correction mechanism for individual melanin differences, which can easily cause local spectrum peak distortion, especially in the blood glucose sensitive band, which can affect the feature stability. In addition, the white balance freely adjusts the gain, which cannot constrain the physically feasible range of spectrum morphology, making it difficult to ensure the comparability of the spectrum between individuals with different skin colors and the detection accuracy. Therefore, it is necessary to combine skin color information and optical priors to perform customized gain constraint and partition smoothing optimization to realize reliable blood glucose concentration detection.

[0006] To solve the above problems, the present application provides a solution. SUMMARY

[0007] In order to overcome the above-mentioned defects of the prior art, embodiments of the present application provide a non-invasive blood glucose concentration detection method based on near-infrared spectrum detection, which solves the problems of spectral baseline offset and blood glucose sensitive band peak shape distortion caused by individual melanin difference by combining white balance based on partition gain with offline Monte Carlo prior function low-dimensional projection and cross-zone smoothing optimization.

[0008] To achieve the above object, the present application provides the following technical solutions:

[0009] The non-invasive blood glucose concentration detection method based on near-infrared spectrum detection comprises the following steps: acquiring target near-infrared spectrum data and performing noise calibration; dividing the spectral domain frequency band of the calibrated spectrum into a short-wave zone sensitive to melanin and a long-wave zone insensitive to melanin; estimating first gain for each zone based on partition gain white balance; combining a prior function of melanin content-spectrum shape change fitted by an offline Monte Carlo library to constrain and optimize the first gain, and limiting the gain to a low-dimensional projection of the prior function online to obtain second gain; combining the second gain with a preset cross-zone smoothing function, outputting the white balance corrected spectrum as a first spectrum, and applying it to blood glucose concentration detection.

[0010] In a preferred embodiment, the step of acquiring target near-infrared spectrum data and performing noise calibration specifically comprises: irradiating the surface of the measured skin with a near-infrared light source and receiving the reflection through a detector, amplifying and analog-to-digital converting the spectrum signal through an analog front-end circuit to obtain digitized spectrum data; performing noise calibration on the digitized spectrum data, which includes dark current correction, detector noise suppression, and system response normalization processing, thereby obtaining noise-calibrated target near-infrared spectrum data.

[0011] In a preferred embodiment, the step of dividing the spectral domain frequency band of the calibrated spectrum into a short-wave zone sensitive to melanin and a long-wave zone insensitive to melanin specifically comprises: determining the short-wave zone sensitive to melanin and the long-wave zone insensitive to melanin in the spectrum according to a preset band division criterion; segmenting the calibrated spectrum data according to the boundary conditions of the short-wave zone and the long-wave zone to obtain short-wave zone spectrum and long-wave zone spectrum; introducing a transition band in the boundary, and performing smoothing processing on the data in the transition band.

[0012] In a preferred embodiment, the first gain of each region based on the partition gain white balance estimation is specifically: the first gain is the gain value after correction by the cross-region smoothing constraint on the basis of the normalized gain, respectively corresponding to the short-wave region and the long-wave region, used for white balance correction of the spectrum, specifically: the average spectral intensity of the short-wave region spectrum and the long-wave region spectrum is calculated respectively, used for representing the spectral response characteristics of each region; the corresponding initial white balance gain value is obtained by analyzing and calculating the difference between the spectral response characteristics and the preset reference benchmark; the initial white balance gain value of each region is normalized; the first gain of each region is obtained by introducing the cross-region smoothing constraint based on the continuity principle of the tissue spectrum in the wavelength dimension on the basis of the normalized gain.

[0013] In a preferred embodiment, the first gain is constrained and optimized by combining the prior function of the melanin content-spectral shape change of the offline Monte Carlo library fitting, and the gain is limited to the low-dimensional projection of the prior function online to obtain the second gain, specifically: the offline Monte Carlo photon transport library is used to simulate the optical response of the tissue for different melanin contents, and the prior function of the melanin content-spectral shape change is fitted; the first gain is projected to the low-dimensional basis function space of the prior function as a low-dimensional projection; the low-dimensional projection constrains that the online gain cannot deviate from the physically feasible spectral shape change range; a regularization term is introduced to limit the spectral gain of the glucose sensitive region; the gain after optimization of the low-dimensional projection and the regularization term is defined as the second gain.

[0014] In a preferred embodiment, the second gain combines a preset cross-region smoothing function, and outputs the white balance corrected spectrum as the first spectrum, specifically: the cross-region smoothing function is preset according to the short-wave region and long-wave region segmentation boundary of the calibrated spectrum and the continuity principle of the tissue spectrum in the wavelength dimension; the second gain is combined with the cross-region smoothing function to obtain a smoothed gain curve; the smoothed gain curve is applied to the corresponding wavelength points of the calibrated spectrum data to obtain the white balance corrected spectrum, that is, the first spectrum.

[0015] In a preferred embodiment, the application is applied to blood glucose concentration detection, specifically: the first spectrum is subjected to conventional spectral pretreatment; the pretreated spectral data is subjected to feature dimension reduction or screening; a blood glucose concentration prediction model is established based on the extracted spectral features, used for mapping the spectral features to the blood glucose concentration prediction value; and the predicted blood glucose concentration is output.

[0016] The non-invasive blood glucose concentration detection method based on near-infrared spectrum detection has the following technical effects and advantages:

[0017] 1.The present application solves the problem of near-infrared spectral baseline shift caused by the difference in melanin content of individuals with different skin colors by using a white balance method based on partition gain to estimate and correct the short-wave and long-wave region spectra respectively. By first calculating the average spectral intensity of each region, then comparing it with the reference spectrum to obtain the initial gain, and then normalizing and cross-region smoothing constraint processing to generate the first gain, the partition correction of white balance is realized. This step can effectively reduce the spectral baseline shift caused by the difference in melanin, so that the corrected spectra of individuals with different skin colors have comparability, and the stability of the blood glucose characteristic signal in the short-wave region is ensured, thereby providing consistent and reliable spectral input for subsequent blood glucose concentration detection. Through this method, the accuracy and applicability of non-invasive blood glucose detection in a multi-skin color population can be significantly improved, while maintaining the overall continuity of the spectrum and avoiding the baseline drift problem that occurs in traditional methods under skin color differences.

[0018] 2.The present application optimizes the white balance correction effect, combines the melanin content-spectral shape change prior function fitted by the off-line Monte Carlo photon transport library, and performs low-dimensional projection constraint on the first gain, and introduces a regularization term for the glucose sensitive region gain to obtain the second gain. At the same time, the second gain is combined with the preset cross-region smoothing function to act on the calibration spectrum, and a continuous and smooth white balance corrected spectrum is output. This step not only retains the correction effect of white balance on skin color differences, but also avoids the spectral peak shape distortion caused by the free adjustment of the first gain, ensuring the stability of the blood glucose sensitive band. Through this gain constraint optimization and cross-region smoothing processing, the present application effectively solves the local spectral mutation problem that may occur in the actual application of traditional white balance, so that the corrected spectrum not only meets the physical feasibility, but also enhances the accuracy and reliability of blood glucose concentration detection, and is suitable for non-invasive blood glucose detection scenarios with multiple skin colors and multiple tissue optical properties. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 The present application is based on the flowchart of the non-invasive blood glucose concentration detection method based on near-infrared spectral detection. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of protection of the present application.

[0021] Embodiment 1, Figure 1 The present application is based on the non-invasive blood glucose concentration detection method based on near-infrared spectral detection, which includes the following steps:

[0022] S1, obtain the target near-infrared spectral data and perform noise calibration.

[0023] In the embodiment, the target near-infrared spectrum data is acquired and noise calibration is performed, specifically as follows:

[0024] The skin surface to be measured is irradiated by a near-infrared light source, and a reflected or transmitted spectrum signal is received by a detector, the spectrum signal is amplified and analog-to-digital converted by an analog front-end circuit to obtain digitized spectrum data;

[0025] The digitized spectrum data is subjected to noise calibration, the noise calibration including dark current correction, detector background noise suppression and system response normalization processing, so as to obtain target near-infrared spectrum data subjected to noise calibration.

[0026] It should be noted that the near-infrared light source can be a wide-spectrum near-infrared light source or a narrow-band near-infrared laser light source, which is used to irradiate the skin surface to be measured. The wide-spectrum light source has the advantage of wide coverage, and multiple waveband information can be acquired at one time; the narrow-band light source has the characteristics of strong monochromaticity and high signal-to-noise ratio, which facilitates detection of specific sensitive wavebands.

[0027] It should be noted that the analog front-end circuit can use a transimpedance amplifier or a low-noise amplifier to convert and amplify the photoelectric current to a voltage signal, and a low-pass filter is used to suppress high-frequency noise to improve the signal-to-noise ratio. These circuit modules are common electronic signal conditioning methods.

[0028] It should be noted that the noise calibration further includes detector background noise suppression. The background noise can be reduced by repeated sampling and averaging, that is, using the statistical principle that "random noise tends to cancel out after multiple superimpositions", so as to improve the quality of the effective signal.

[0029] It should be noted that the noise calibration further includes system response normalization. Specifically, a reference spectrum is collected by using a reference standard (such as a white plate or a standard reflector), and the reference spectrum is used to normalize the target spectrum to eliminate the effects of light source spectral non-uniformity and detector response curve difference.

[0030] S2, the spectral domain band of the calibrated spectrum is divided into a short wave region sensitive to melanin and a long wave region not sensitive to melanin.

[0031] In the embodiment, the spectral domain band of the calibrated spectrum is divided into a short wave region sensitive to melanin and a long wave region not sensitive to melanin, specifically as follows:

[0032] According to a preset waveband division criterion, a short wave region sensitive to melanin and a long wave region not sensitive to melanin in the spectrum are determined;

[0033] According to the boundary condition of the short-wave region and the long-wave region, the calibrated spectral data is segmented to obtain a short-wave region spectrum and a long-wave region spectrum;

[0034] The boundary further comprises a transition zone, and the data in the transition zone is smoothed.

[0035] It should be noted that the "preset wavelength division criterion" can be obtained in various ways, such as referring to an existing tissue spectrum database or statistically summarizing the spectral data of different skin color populations through pre-experiment collection.

[0036] It should be noted that the boundary condition of the short-wave region and the long-wave region is not fixed and can be adjusted according to different application scenarios. For example, in a medical detection scenario, a waveband with significant melanin absorption can be selected as the short-wave region; and in a non-medical imaging or detection scenario, a region with a high signal-to-noise ratio can be selected as a preferred division basis.

[0037] It should be noted that the segmentation of the spectral data is realized by software, that is, after the data collection is completed, the programming algorithm is used to cut according to the wavelength index; or it can be realized by hardware, for example, different narrow-band optical filters are configured at the spectral collection end to divide the spectrum into a short-wave region and a long-wave region during the collection link.

[0038] It should be noted that the introduction of the transition zone is mainly used to reduce the influence of the boundary effect on the subsequent white balance calculation. The boundary effect can cause discontinuity or discontinuity when the short-wave region and the long-wave region are spliced, and by smoothing the data in the transition zone (for example, using a linear weighting or Gaussian weighting function), the continuity and stability of the spectral transition can be ensured.

[0039] It should be noted that the smoothing process is not limited to a single algorithm, and different methods such as mean filtering, wavelet denoising, and low-rank approximation can be used to adapt to different noise environments and computational resource constraints.

[0040] In this embodiment, the calibrated spectrum is divided into a short-wave region sensitive to melanin and a long-wave region not sensitive to melanin, which means that the part of the spectrum affected by the strong absorption of melanin and the relatively stable part can be distinguished. Due to the difference in skin color between individuals, the content of melanin is significantly different, which will cause the baseline of the spectrum to shift in the short-wave region, thereby seriously interfering with the accurate extraction of blood glucose concentration. By dividing the spectrum, on the one hand, a compensation mechanism can be established in the short-wave region to weaken the influence of the difference in melanin absorption, and on the other hand, the long-wave region can be used as a reference region to provide a stable reference for the calculation of the white balance gain. This step not only makes the subsequent white balance correction more targeted, but also significantly improves the consistency of spectral processing between individuals with different skin colors, thereby improving the reliability and universality of the blood glucose concentration detection result.

[0041] S3, estimating first gains of each region based on the partition gain white balance estimation.

[0042] In the embodiment, the estimating first gains of each region based on the partition gain white balance estimation specifically comprises:

[0043] The first gain is a gain value modified by the cross-region smoothing constraint on the basis of the normalized gain, respectively corresponding to the short-wave region and the long-wave region, and is used for white balance correction of the spectrum, and specifically comprises:

[0044] The average spectral intensity of the short-wave region spectrum and the long-wave region spectrum is calculated respectively, and is used for representing the spectral response characteristics of each region;

[0045] According to the difference between the spectral response characteristics and a preset reference benchmark, an initial white balance gain value corresponding to the difference is calculated and analyzed, and the reference benchmark is a standard spectrum obtained in advance;

[0046] The initial white balance gain value of each region is normalized;

[0047] On the basis of the normalized gain, a cross-region smoothing constraint is introduced based on the continuity principle of the tissue spectrum in the wavelength dimension, and the first gain of each region is obtained.

[0048] Further, the average spectral intensity is used for quantifying the overall spectral energy level of different wave bands, and the following is a specific calculation formula of the average spectral intensity:

[0049]

[0050] and

[0051] In the formula, is the short-wave region spectrum, is the long-wave region spectrum, and is the number of sampling points, and is the average spectral intensity, short and long are respectively the marks of the long-wave region and the short-wave region, and is the wavelength set, is the wavelength.

[0052] Further, the following is a specific calculation formula of the initial white balance gain:

[0053]

[0054] and

[0055] In the formula, and​​​​ respectively, the white balance gain ensures that the energy levels of the short-wave region and the long-wave region can be corrected to a uniform reference under different skin color individuals, and respectively, are the initial white balance gains of the short-wave region and the long-wave region.

[0056] Further, to avoid the overall correction imbalance caused by excessive or insufficient gain of individual intervals, the initial gain is normalized. The following is a specific calculation formula for the initial white balance gain normalization processing:

[0057]

[0058] In the formula, is the initial white balance gain of the k region, is the normalized initial white balance gain of the k region.

[0059] Further, on the basis of the normalized gain, a cross-region smoothing constraint is introduced to reduce the abrupt changes caused by independent estimation of different intervals. The cross-region smoothing constraint is introduced based on the continuity principle of tissue spectrum. The actual spectrum should remain smooth in the wavelength dimension, so after independent estimation of the gain of different intervals, a global mean gain is introduced as a regularization term to weight the interval gain, thereby avoiding unnatural abrupt changes caused by interval division. The constraint function can be expressed as:

[0060]

[0061] and

[0062] In the formula, and are the normalized short-wave region and long-wave region gains; is the global mean gain, that is, is a smoothing coefficient for controlling the trade-off between cross-region independence and overall continuity, and are the first gain of the short-wave region and the first gain of the long-wave region, respectively.

[0063] It should be noted that in the present embodiment, the average intensity of the short-wave region spectrum and the long-wave region spectrum is obtained by calculating the arithmetic mean of the spectrum values of all sampling wavelengths in the respective intervals. This step is used to quantify the overall spectral response characteristics of each region and provides basic data for subsequent white balance gain calculation. Through this processing, the spectral energy differences of different skin color individuals in different wavebands can be effectively characterized, providing an operable basis for subsequent gain correction.

[0064] ​​​It should be noted that the initial gain is calculated by the ratio of the average spectral intensity of each zone to the average intensity of the preset reference spectrum, wherein the reference spectrum can be measured by a standard light source or obtained by a large number of average human body spectra. This step is used for preliminary correction of each zone to compensate for the baseline shift of the short-wave zone caused by the difference in melanin absorption of different individuals, and lays a foundation for subsequent normalization and cross-zone smoothing processing.

[0065] It should be noted that the normalization processing is to divide the initial gain of each zone by the mean value or the preset normalization coefficient, so that the gains of each zone have relative comparability. This processing can avoid the imbalance of overall spectral correction caused by too large or too small gain of a certain zone, while ensuring the input stability of the cross-zone smoothing constraint, thereby providing a reliable foundation for generating a continuous and smooth first gain.

[0066] It should be noted that the setting of the cross-zone smoothing constraint is based on the continuity principle of tissue spectrum in the wavelength dimension, and the normalized gain is smoothed by using weighted average or regularization function. This step can eliminate the boundary mutation caused by the division of short-wave zone and long-wave zone, and ensure the continuous change of the gain of each zone, thereby improving the smoothness of the spectrum after white balance correction and the accuracy of blood glucose concentration detection.

[0067] It should be noted that the first gain of each zone after the correction of the cross-zone smoothing constraint is directly used for white balance correction of the corresponding zone spectrum, and the first spectrum is output. This step can effectively reduce the spectral baseline shift caused by individual differences in melanin, provide accurate and comparable spectral input for subsequent blood glucose concentration detection, and improve the reliability and accuracy of the non-invasive blood glucose detection method.

[0068] In the embodiment, the first gain of each zone spectrum is estimated by the white balance method based on the partition gain, and the core purpose is to solve the problem of spectral baseline shift caused by individual skin color difference. Since melanin obviously absorbs near-infrared light in the short-wave zone, the difference in melanin content of different individuals will cause the baseline of the short-wave zone spectrum to shift downward, and the long-wave zone is less affected, thereby affecting the consistency of the overall spectrum and the accuracy of blood glucose concentration detection. By calculating the average spectral intensity of each zone and comparing it with the reference spectrum, the initial gain is obtained, and then the first gain is obtained through normalization and cross-zone smoothing constraint processing. This step can correct the short-wave zone and the long-wave zone respectively, make the corrected spectral baseline consistent, reduce the influence of individual differences, thereby providing stable and comparable spectral data for subsequent blood glucose concentration analysis, and improving the reliability and accuracy of the non-invasive detection method.

[0069] S4, combining the prior function of melanin content-spectrum shape change fitted by the offline Monte Carlo library, the first gain is constrained and optimized, and the gain is limited to the low-dimensional projection of the prior online to obtain the second gain.

[0070] In the embodiment, the first gain is constrained and optimized in combination with the offline Monte Carlo library fitting of the prior function of the melanin content-spectral shape change, the gain is limited to a low-dimensional projection of the prior function online, and the second gain is obtained, specifically as follows:

[0071] The offline Monte Carlo photon transport library is used to simulate the optical response of the tissue for different melanin contents, and a prior function of the melanin content-spectral shape change is fitted;

[0072] The first gain is projected to a low-dimensional basis function space of the prior function as a low-dimensional projection;

[0073] Through the low-dimensional projection, the online gain is constrained not to deviate from the physically feasible spectral shape change range;

[0074] A regularization term is introduced to limit the spectral gain in the glucose-sensitive region;

[0075] The gain after the low-dimensional projection and the regularization term optimization is defined as the second gain.

[0076] Further, the offline Monte Carlo photon transport library is used to simulate the optical response of the tissue for different melanin contents, and a prior function of the melanin content-spectral shape change is fitted, specifically as follows:

[0077] For each melanin content , N is the total number of melanin, the Monte Carlo photon transport is used to simulate the scattering and absorption process of photons in the near-infrared band in the tissue, and the tissue transmission spectrum is obtained;

[0078] Each set of simulated spectra is normalized to eliminate the absolute intensity difference

[0079] The normalized spectrum and the melanin content are functionally fitted to obtain the melanin content-spectral shape change;

[0080] The following is an expression of the prior function of the feasible melanin content-spectral shape change:

[0081] ,

[0082] The following is an example of the normalization calculation of the feasible simulated spectrum: ;

[0083] In the formula, is the prior function, is the entire simulated wavelength set; is the fitting coefficient varying with the melanin content, and M is the polynomial order; usually 3-5, which can accurately fit the trend of the spectral shape change with the melanin content, is the normalized simulated spectrum.

[0084] It should be noted that the optical parameters of water, fat and hemoglobin in the tissue are considered in the tissue transmission spectrum simulation process to ensure that the spectral response approximates the actual human tissue characteristics.

[0085] It should be noted that in this embodiment, Monte Carlo photon transport is used to simulate the scattering and absorption of photons in the tissue to obtain the transmission spectrum under different melanin content conditions. This step can truly reflect the propagation behavior of light in the skin tissue, provide a physical basis for constructing the melanin content-spectral morphology prior function, and make the online gain constraint have a theoretical support.

[0086] It should be noted that each group of simulated spectra is normalized to eliminate absolute intensity differences. This step ensures that the spectra of different melanin contents can be compared and fitted in the same dimension, avoids interference of external factors such as light source power and detector sensitivity on the prior function fitting, and improves the usability and stability of the prior function.

[0087] It should be noted that the normalized spectrum is functionally fitted with the melanin content to obtain the melanin content-spectral shape change prior function. The prior function obtained by fitting can describe the influence trend of melanin content change on the spectral morphology, provide low-dimensional physical constraints for online gain projection, and prevent spectral peak shape distortion caused by the first gain adjustment.

[0088] It should be noted that the fitting of the melanin content-spectral shape change prior function reflects the change rule of the spectral shape in the short-wave region and the long-wave region under different melanin levels, and provides a theoretical basis for subsequent gain constraints.

[0089] Further, the first gain is projected into the low-dimensional basis function space of the prior function, which is a low-dimensional projection, specifically:

[0090] Extracting several dominant modes from the melanin content-spectral shape change prior function obtained by offline fitting as low-dimensional basis functions Where K is the number of basis functions, k is the basis function label, and is used to describe the main trend of the spectral morphology with the change of the melanin content;

[0091] The first gain is projected into the selected low-dimensional basis function space, and the low-dimensional coefficients are calculated;

[0092] The low-dimensional gain curve is reconstructed according to the projection coefficients, that is, the preliminary form of the second gain;

[0093] It should be noted that the following is a feasible low-dimensional coefficient calculation example:

[0094] ,

[0095] In the formula, is the projection coefficient of the first gain in the direction of the basis function, is the projection coefficient of the first gain in the direction of the basis function, is the first gain at wavelength .

[0096] The following is a preliminary form of the calculation of the feasible second gain:

[0097] ,

[0098] wherein, is the second gain at wavelength .

[0099] It should be noted that the low-dimensional projection retains the main component of the first gain in the physically feasible spectral form, while filtering out noise or deviations that do not conform to the priori. By projecting the first gain into the low-dimensional basis function space of the priori function, the gain change is constrained online to conform to the spectral form of the melanin physical priori, preventing spectral peak distortion caused by free gain adjustment, and ensuring the comparability and stability of the spectrum after white balance correction among different skin color individuals.

[0100] The low-dimensional projection constrains the online gain from deviating from the physically feasible spectral form variation range; the regularization term limits the spectral gain in the glucose sensitive region; the gain after low-dimensional projection and regularization optimization is defined as the second gain, which is specifically:

[0101] The first gain is projected into the low-dimensional basis function space of the offline Monte Carlo priori function to obtain a preliminary low-dimensional gain. During online optimization, the reconstructed gain curve is adjusted to fit the first gain as much as possible while ensuring the physical feasibility of the gain change, avoiding unreasonable spectral peaks or depressions. The optimization method can be realized by using existing least squares fitting or convex optimization technology with constraints.

[0102] During the optimization process, the spectral band sensitive to blood glucose is set with a constraint condition separately, so that the gain change in this region does not exceed the preset range, ensuring the stability of the blood glucose characteristic spectral peak. The specific implementation can use the method of weighted penalty term or threshold clipping to make the second gain smooth in the sensitive region, avoiding affecting the accuracy of blood glucose concentration detection.

[0103] The gain curve after low-dimensional projection optimization and sensitive region constraint processing is the second gain. The second gain can be directly used for spectral white balance correction, so that the corrected spectrum not only corrects the baseline shift caused by individual melanin difference, but also maintains the stability of the blood glucose characteristic signal, providing reliable spectral data for subsequent blood glucose concentration detection.

[0104] It should be noted that in the existing non-invasive blood glucose concentration detection method based on near-infrared spectrum, due to the difference in individual skin color, melanin absorption is different, and the spectrum baseline is obviously offset, which directly affects the stability of the blood glucose characteristic signal, and the traditional method is difficult to accurately correct. In order to alleviate this problem, the white balance technology is introduced, and the white balance is preliminarily corrected by partition gain, but in actual application, the first gain freedom is too high, which may cause local spectrum peak shape distortion, especially in the blood glucose sensitive band, which may affect the detection accuracy.

[0105] To solve the above problems, the melanin content-spectrum shape change prior function fitted by the off-line Monte Carlo photon transport library is combined to constrain and optimize the first gain, and the gain is limited to a low-dimensional prior projection online to obtain the second gain. In this way, the correction effect of white balance on the spectrum baseline of different skin color individuals is retained, and the spectrum peak shape distortion caused by gain free adjustment is effectively prevented, the stability and detection accuracy of the spectrum after white balance correction in the blood glucose sensitive band are improved, and reliable non-invasive blood glucose concentration detection in multiple skin color individuals is realized.

[0106] S5, the second gain combines a preset cross-zone smoothing function, outputs the white balance corrected spectrum as the first spectrum, and is applied to blood glucose concentration detection.

[0107] In this embodiment, the second gain combines a preset cross-zone smoothing function, and outputs the white balance corrected spectrum as the first spectrum, specifically:

[0108] According to the short-wave zone and long-wave zone segmentation boundary of the calibrated spectrum and the continuity principle of the tissue spectrum in the wavelength dimension, a preset cross-zone smoothing function is set;

[0109] The second gain is combined with the cross-zone smoothing function to obtain a smoothed gain curve;

[0110] The smoothed gain curve is applied to the corresponding wavelength points of the calibrated spectrum data to obtain the white balance corrected spectrum, that is, the first spectrum.

[0111] It should be noted that the smoothing function can be obtained by existing signal processing technology, for example, using polynomial fitting, moving average or Gaussian convolution method to smooth and fit the spectrum gain of the boundary transition zone, and the parameters of the smoothing function can be preset or adjusted according to the different individual skin color and tissue optical properties measured by experiment, to ensure the smooth and continuous cross-zone gain;

[0112] It should be noted that the gain curve processing makes the short-wave zone and long-wave zone gain smoothly transition in the boundary region, avoiding local jump or discontinuity causing spectrum distortion.

[0113] It should be noted that the following is a quantitative expression of the smoothed gain curve:

[0114] ,

[0115] wherein, is a cross-region smoothing function, is the value of the smoothed gain curve at .

[0116] It should be noted that the following is each wavelength of the first spectrum that is feasible :

[0117] ,

[0118] wherein, is the first spectrum, is the calibrated spectrum data.

[0119] It should be noted that in the present embodiment, the preset cross-region smoothing function is to ensure that the short-wave region and long-wave region gains are continuously transitioned in the boundary region, so as to avoid spectral distortion caused by gain mutation. The smoothing function can be obtained based on existing signal processing methods, such as polynomial fitting, moving average or Gaussian convolution, to perform smoothing processing on the gain curve of the boundary transition region. The parameters of the function can be preset or adjusted according to the different individual skin colors and tissue optical properties measured by experiments, so as to ensure that the gain is smooth and has strong operability.

[0120] By presetting the cross-region smoothing function and combining the second gain correction spectrum, the spectral jump problem caused by the discontinuity of the gain boundary can be effectively solved, the spectral continuity and blood glucose characteristic signal stability are enhanced, the correction effect of the white balance technology on the skin color difference is continued, and thus the accuracy and reliability of the non-invasive blood glucose concentration detection are improved.

[0121] In the present embodiment, by combining the second gain with the preset cross-region smoothing function and acting on the calibrated spectrum to obtain the first spectrum, the discontinuity or jump problem that may occur at the gain boundary of the short-wave region and the long-wave region can be effectively solved. This step not only maintains the correction effect of the white balance correction on the spectrum baseline of different skin color individuals, but also ensures the continuity and stability of the blood glucose sensitive band spectrum characteristics, so as to reduce the interference of skin color difference and local gain distortion on the detection accuracy of non-invasive blood glucose concentration, and to realize more reliable blood glucose feature extraction and detection in individuals with different skin colors and different tissue optical properties.

[0122] In the present embodiment, the application to blood glucose concentration detection is specifically:

[0123] performing conventional spectrum pretreatment on the first spectrum;

[0124] performing feature dimension reduction or screening on the pretreated spectrum data;

[0125] A blood glucose concentration prediction model is established based on the extracted spectral features, which is used to map the spectral features to blood glucose concentration prediction values.

[0126] The predicted blood glucose concentration is output.

[0127] It should be noted that the preprocessing can include multivariate scatter correction, standard normal transformation, and first or second derivative processing, etc. methods for eliminating spectral noise, baseline drift and scattering interference, thereby improving the distinguishability of blood glucose sensitive signal. This step ensures the stability and consistency of the spectral data, facilitating subsequent feature extraction. In the prior art, these spectral preprocessing methods have been widely used in near-infrared analysis and non-invasive blood glucose detection, and have operability and maturity.

[0128] It should be noted that this step can use principal component analysis (PCA), partial least squares regression (PLS) load analysis, sparse feature selection or other dimensionality reduction algorithms to compress high-dimensional spectral data into low-dimensional features while retaining blood glucose related information. The role of this step is to remove redundant information and noise, and to improve the stability and accuracy of the blood glucose prediction model. In the prior art, PCA and PLS have been widely used for near-infrared blood glucose detection spectral feature extraction, and have a mature theoretical and practical basis.

[0129] It should be noted that regression or machine learning models such as partial least squares regression (PLS), support vector regression (SVR), artificial neural network (NN) can be selected to map spectral features to blood glucose concentration prediction values. The role of this step is to realize the quantitative relationship between spectral signal and blood glucose concentration, and to provide reliable prediction for non-invasive blood glucose monitoring. In the prior art, these models have been proven to be feasible and accurate in spectral analysis and blood glucose prediction.

[0130] It should be noted that the blood glucose concentration prediction values obtained by the above modeling are used as the final detection results, which can be used for clinical or personal blood glucose monitoring. The role of this step is to convert spectral signals into quantifiable blood glucose concentration indicators, providing direct reference for non-invasive blood glucose detection. In the existing mature technology, non-invasive blood glucose detection systems usually realize the mapping from spectrum to blood glucose through similar modeling and output steps.

[0131] In the embodiment, for the problem of near-infrared spectral baseline shift caused by the difference in melanin content of individuals with different skin colors, a white balance method based on partition gain is used to estimate and correct the short-wave and long-wave region spectra respectively. By first calculating the average spectral intensity of each region, then comparing it with the reference spectrum to obtain the initial gain, and then through normalization and cross-region smoothing constraint processing to generate the first gain, the partition correction of white balance is realized. This step can effectively reduce the spectral baseline shift caused by the difference in melanin, so that the corrected spectra of individuals with different skin colors have comparability, and the stability of the blood glucose feature signal in the short-wave region is ensured, thereby providing consistent and reliable spectral input for subsequent blood glucose concentration detection. Through this method, the accuracy and applicability of non-invasive blood glucose detection in multi-skin color population can be significantly improved, while maintaining the overall continuity of the spectrum, avoiding the baseline drift problem caused by traditional methods under the difference in skin color.

[0132] In the embodiment, to further optimize the white balance correction effect, the first gain is constrained by low-dimensional projection combined with the melanin content-spectral shape change prior function fitted by the offline Monte Carlo photon transport library, and a regularization term is introduced to the glucose sensitive region gain to obtain the second gain. At the same time, the second gain is combined with the preset cross-region smoothing function to act on the calibration spectrum, and the continuous and smooth white balance corrected spectrum is output. This step not only retains the correction effect of white balance on skin color difference, but also avoids the spectral peak shape distortion caused by the free adjustment of the first gain, and ensures the feature stability of the blood glucose sensitive band. Through this gain constraint optimization and cross-region smoothing processing, the invention effectively solves the local spectral mutation problem that may occur in the actual application of traditional white balance, so that the corrected spectrum not only meets the physical feasibility, but also enhances the accuracy and reliability of blood glucose concentration detection, and is suitable for multi-skin color, multi-tissue optical property non-invasive blood glucose detection scene.

Claims

1. A non-invasive blood glucose concentration detection method based on near-infrared spectroscopy detection, characterized by, The method comprises the following steps: Obtaining target near-infrared spectrum data and performing noise calibration; Dividing the spectral domain band of the calibrated spectrum into a short-wave region sensitive to melanin and a long-wave region insensitive to melanin; Estimating first gains of each region based on zoned gain white balance; Constrained optimization of the first gains in combination with a prior function of melanin content-spectrum shape change fitted by an offline Monte Carlo library, and limiting the gain to a low-dimensional projection of the prior function online to obtain second gains; The second gains combine a preset cross-region smoothing function to output the white balance corrected spectrum as the first spectrum and apply it to blood glucose concentration detection.

2. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 1, characterized by, The method of obtaining target near-infrared spectrum data and performing noise calibration comprises the following steps: Irradiating the surface of the measured skin with a near-infrared light source, and receiving the reflected spectrum signal through a detector, the spectrum signal is amplified and analog-to-digital converted by an analog front-end circuit to obtain digitized spectrum data; Performing noise calibration on the digitized spectrum data, the noise calibration includes dark current correction, detector background noise suppression and system response normalization processing, thereby obtaining the target near-infrared spectrum data after noise calibration.

3. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 2, characterized by, The method of dividing the spectral domain band of the calibrated spectrum into a short-wave region sensitive to melanin and a long-wave region insensitive to melanin comprises the following steps: According to a preset band division criterion, determining the short-wave region sensitive to melanin and the long-wave region insensitive to melanin in the spectrum; According to the boundary conditions of the short-wave region and the long-wave region, segmenting the calibrated spectrum data to obtain short-wave region spectrum and long-wave region spectrum; The boundary also includes introducing a transition band, and the data in the transition band is smoothed.

4. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 3, characterized by, The method of estimating first gains of each region based on zoned gain white balance comprises the following steps: The first gain is a gain value corrected by cross-region smoothing on the basis of normalized gain, corresponding to the short-wave region and the long-wave region respectively, and is used for white balance correction of the spectrum, which comprises the following steps: Calculating the average spectrum intensity of the short-wave region spectrum and the long-wave region spectrum respectively, which is used to represent the spectrum response characteristics of each region; According to the difference between the spectrum response characteristics and a preset reference benchmark, the initial white balance gain value corresponding to the difference is calculated and analyzed, and the reference benchmark is a standard spectrum obtained in advance; Normalizing the initial white balance gain value of each region; On the basis of the normalized gain, introducing a cross-region smoothing constraint based on the continuity principle of tissue spectrum in the wavelength dimension to obtain the first gain of each region.

5. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 4, characterized by, The method of constrained optimization of the first gains in combination with a prior function of melanin content-spectrum shape change fitted by an offline Monte Carlo library, and limiting the gain to a low-dimensional projection of the prior function online to obtain second gains comprises the following steps: Using an offline Monte Carlo photon transport library to simulate the optical response of the tissue for different melanin contents, and fitting a prior function of melanin content-spectrum shape change; Projecting the first gain to the low-dimensional basis function space of the prior function as a low-dimensional projection; Through the low-dimensional projection, the online gain is constrained not to deviate from the physically feasible spectrum shape change range; Introducing a regularization term to limit the spectrum gain of the glucose sensitive region; Defining the gain after optimization of the low-dimensional projection and the regularization term as the second gain.

6. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 5, characterized by, The second gain is combined with a preset cross-region smoothing function to output a white balance corrected spectrum as a first spectrum, specifically: According to the short-wave region and long-wave region segmentation boundary of the calibrated spectrum and the continuity principle of the tissue spectrum in the wavelength dimension, a preset cross-region smoothing function is set; The second gain is combined with the cross-region smoothing function to obtain a smoothed gain curve; The smoothed gain curve is applied to the corresponding wavelength points of the calibrated spectrum data to obtain a white balance corrected spectrum, i.e., a first spectrum.

7. The noninvasive blood glucose concentration detecting method based on near-infrared spectroscopy detection according to claim 6, characterized by, The application is applied to blood glucose concentration detection, specifically: Performing conventional spectrum preprocessing on the first spectrum; Performing feature dimension reduction or screening on the preprocessed spectrum data; Based on the extracted spectrum features, a blood glucose concentration prediction model is established to map the spectrum features to a blood glucose concentration prediction value; Output the predicted blood glucose concentration.

Images