High-sensitivity handheld multi-joint detection fluorescence immunoassay analyzer

Abstract

The invention discloses a high-sensitivity handheld multi-joint detection fluorescence immunoassay analyzer which comprises a reagent card, a detection module, a data processing module, a calibration verification module, a quantitative calculation module and an output and display module. Compressed sensing sparse sampling, signal reconstruction, calibration and adversarial verification are carried out on a fluorescent marker on the reagent card, and optimization is fed back according to an adversarial verification result, so that targeted enhancement of a fluorescent signal of an ultralow-concentration target substance is realized. According to the process, background noise is effectively reduced, the detection sensitivity of the handheld fluorescence immunoassay analyzer is improved through multiple technical means, and the handheld fluorescence immunoassay analyzer has a lower detection limit. Compared with the prior art, the invention solves the problem of insufficient detection sensitivity and accuracy caused by weak fluorescence signals when a handheld fluorescence immunoassay analyzer detects a low-concentration sample.

Description

Technical Field

[0001] The invention relates to the technical field of medical devices, and in particular to a high-sensitivity handheld multiple-detection fluorescent immunoassay analyzer. Background Art

[0002] Fluorescence immunoassay is a commonly used biological detection technology, widely used in medical diagnosis, food safety and other fields. Existing fluorescence immunoassay analyzers usually use LED as the excitation light source to detect the concentration of the target substance by exciting specific fluorescent markers. However, the traditional LED light source uses a constant light mode during the excitation cycle, which limits the current of the LED lamp and cannot provide sufficient excitation energy. Especially in the detection of low-concentration samples, the fluorescence signal is weak, which affects the sensitivity and accuracy of the detection.

[0003] In order to improve the detection sensitivity, some studies have tried to improve the excitation method of the light source, such as increasing the power of the LED or using a laser light source. However, these methods have problems such as high cost and complex operation, making them difficult to be widely used in portable devices.

[0004] Although there have been many improvement measures, how to improve the detection sensitivity while ensuring the portability of the portable fluorescent immunoassay analyzer is still an urgent problem to be solved. In the existing technology, the excitation energy of the constant-on LED light source is limited, resulting in weak fluorescence signals of low-concentration samples, which seriously affects the accuracy and reliability of the test results.

[0005] Therefore, it is necessary to provide a high-sensitivity handheld multi-detection fluorescent immunoassay analyzer to solve the above technical problems. Summary of the invention

[0006] The invention overcomes the deficiencies of the prior art and provides a high-sensitivity handheld multi-detection fluorescent immunoassay analyzer.

[0007] To achieve the above object, the technical solution adopted by the present invention is: a high-sensitivity handheld multi-detection fluorescent immunoassay analyzer, comprising: Reagent Card, A detection module, which obtains the compressed measurement signal in the reagent card through sparse sampling and image fusion; A data processing module, used for performing signal reconstruction processing on the compressed measurement signal to obtain a first enhanced signal; A calibration verification module, used to calibrate the first enhanced signal, verify the authenticity of the first enhanced signal through an adversarial verification algorithm, and obtain a second enhanced signal through feedback processing; A quantitative calculation module, used to calculate the concentration of the target substance corresponding to the second enhanced signal; The output and display module is used to output and display the concentration of the target substance through a visual interface.

[0008] In a preferred embodiment of the present invention, the detection module comprises: A card slot, used to insert the reagent card into a designated position; An excitation light source assembly, including a light source, a pulse modulation circuit and a light splitting system; An optical collection component, including a CMOS image sensor, for receiving and converting the fluorescence signal into an electrical signal; The pulse modulation circuit controls the light source to excite the fluorescent substance with a pulse with a pulse width of less than 10 ns.

[0009] In a preferred embodiment of the present invention, the sparse sampling comprises the following steps: Step 1: construct a sparse representation dictionary D based on the quantum dot fluorescence lifetime feature library; Step 2: Obtain the peak intensity V of the fluorescence signal through pre-scanning p , calculating the sampling rate, and controlling the CMOS image sensor to perform pixel-level random sampling, with the sampling window being synchronized with the quantum dot fluorescence lifetime window; Step 3: Using a pulse light source to synchronize with the global shutter of the CMOS image sensor to start imaging within the fluorescence lifetime window of the quantum dots on the reagent card; 5-10 frames of images were collected continuously, and the exposure time of each frame was between 10-100 μs.

[0010] In a preferred embodiment of the present invention, the image fusion is specifically as follows: N frames of fluorescence images acquired by sparse sampling , taking the first frame I1 as the reference image, for each frame I k , calculate its displacement vector field relative to I1 , by solving: ; in, is the pixel offset, constrained within ±5 pixels; is the coordinate position of the pixel in the image; The registration weights are calculated using the improved non-local homogeneity algorithm. , and perform multi-frame weighted fusion to generate a fused image I fusion : ; The weight w k Proportional to the square of the signal-to-noise ratio: , giving priority to preserving the information of high-quality frames.

[0011] In a preferred embodiment of the present invention, the signal reconstruction is based on a sparse representation dictionary D, and the Bregman algorithm is used to perform multiple iterations of optimization on the compressed measurement signal output by the detection module; The iterative refactoring process includes: The first enhanced signal S is obtained by minimizing the objective function, which is: ; Among them, Ψ is a single-substance-specific dictionary, M is a random sampling mask matrix, Y is the compressed measurement signal, and λ is a weight coefficient.

[0012] In a preferred embodiment of the present invention, the reagent card comprises: an observation area placed in the middle and reference areas on both sides; The reference area is equally divided into a plurality of sub-areas, each of which contains a standard substance of known concentration; The detection module collects the signal of the observation area and the fluorescence signal of the reference area at the same time, and records the fluorescence intensity value of each sub-area.

[0013] In a preferred embodiment of the present invention, the calibration verification module includes: an error factor calculation unit and a signal calibration unit; The error factor calculation unit calculates the error factor under the current detection conditions by the difference between the reference zone signal and the theoretical value. The error factor includes: Light source fluctuation compensation: ; Sensor drift compensation: ; A signal calibration unit is used to calibrate the first enhanced signal output by the data processing module using an error factor: .

[0014] In a preferred embodiment of the present invention, the calibration verification module further comprises: a confrontation verification unit, which detects anomalies or interferences in the calibrated first enhanced signal through a confrontation verification algorithm to ensure the authenticity of the measurement result; The specific testing process includes: Build an adversarial network architecture, including: A generator configured to generate a simulated abnormal signal for training the discriminator; A discriminator, configured to distinguish between real signals and generated anomaly signals and output a confidence score; The calibrated first enhanced signal is input into the discriminator to output the confidence score D score ; D score <θ, then the signal is judged to be abnormal; If D score >θ, the verification is passed.

[0015] In a preferred embodiment of the present invention, the objective function of iterative reconstruction is adjusted according to the output result of the calibration verification module against the verification, and the second enhanced signal is re-output. The adjusted objective function is: ; in, By penalizing signals that are far different from the true distribution, the reconstruction process is guided away from false features, and μ is the weight coefficient of the adversarial loss.

[0016] In a preferred embodiment of the present invention, the quantitative calculation module calculates the target substance concentration corresponding to the second enhanced signal according to an existing target substance concentration standard model.

[0017] The present invention solves the defects existing in the background technology and has the following beneficial effects: (1) The present invention provides a highly sensitive handheld multi-detection fluorescent immunoassay analyzer, which performs compressed sensing sparse sampling, signal reconstruction, calibration and adversarial verification on the fluorescent markers on the reagent card, and optimizes the feedback based on the adversarial verification results, thereby achieving targeted enhancement of the fluorescent signal of the ultra-low concentration target substance. This process not only effectively reduces the background noise, but also improves the detection sensitivity of the handheld fluorescent immunoassay analyzer through multiple technical means, and has a lower detection limit. Compared with the prior art, the present invention solves the problem of insufficient detection sensitivity and accuracy of the handheld fluorescent immunoassay analyzer when detecting low-concentration samples due to weak fluorescent signals.

[0018] (2) The present invention can effectively reduce random noise and improve the signal-to-noise ratio by sparse sampling and fusing multiple frames of images. Specifically, continuously collecting 5-10 frames of images and aligning and fusing these images through the non-local means (NLM) algorithm can significantly reduce noise interference. This method not only improves image quality, but also enhances the detection capability of low-concentration samples without increasing hardware complexity.

[0019] (3) Based on the sparse representation dictionary, the present invention uses the Bregman algorithm to perform multiple iterations of optimization on the compressed measurement signal output by the detection module, and recovers the high-resolution first enhanced signal from a small amount of compressed measurement signal. Especially in low-concentration detection scenarios (such as 0.01 ng / mL TSH detection), this method significantly reduces signal distortion caused by insufficient sampling. By optimizing the selection of the sparse representation dictionary and the setting of iterative parameters, the present invention can significantly reduce the computational complexity and processing time while ensuring high accuracy.

[0020] (4) The present invention uses the reference area at the edge of the reagent card to correct the light source fluctuation and sensor drift in real time, and uses the adversarial verification of the generative adversarial network (GAN) to ensure the authenticity of the first enhanced signal. When the statistical difference between the reconstructed signal and the true distribution is significant, the adversarial loss function will dynamically enhance the weight of the penalty term through the gradient backpropagation mechanism, forcing the iterative optimization process to adjust the core parameters. This feedback mechanism can effectively suppress the false features introduced by algorithmic deviations such as undersampling errors or excessive noise suppression during the reconstruction process by strengthening the constraints on distribution consistency, thereby improving the fitting accuracy of the reconstructed signal with the physical true value. This is particularly important in low-concentration detection, and can significantly reduce false positive or false negative results caused by algorithmic errors.

[0021] (5) The present invention maximizes the efficiency of generating fluorescent signals by precisely controlling the excitation conditions of the light source (such as pulse width, frequency and peak current) and combining the characteristics of quantum dot fluorescent markers. Secondly, sparse sampling technology and Bregman iterative algorithm are used to recover high-quality original signals from a small amount of compressed measurement signals, avoiding the high cost and complexity brought by traditional full sampling. In addition, abnormal signals are identified and eliminated through adversarial verification algorithms, ensuring the authenticity and reliability of the final detection results. Combining these technical means, the present invention exhibits excellent performance in low-concentration detection, can significantly reduce the detection limit, and meet the needs of high-sensitivity detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. Figure 1 is a schematic diagram of a handheld immunoassay analyzer body according to a preferred embodiment of the present invention; Figure 2 It is a block diagram of the handheld immunoassay analyzer body of a preferred embodiment of the present invention; Figure 3 It is the optical structure composition of the preferred embodiment of the present invention.

[0023] In the figure: 1. immunoassay analyzer body; 101. light source; 102. collimator; 103. dichroic mirror; 104. first condenser; 105. CMOS image sensor; 106. aperture; 107. second condenser; 108. filter. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0026] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the invention, unless otherwise specified, "multiple" means two or more.

[0027] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0028] like Figure 1 As shown, the present invention provides a high-sensitivity handheld multi-detection fluorescence immunoassay analyzer, which includes a reagent card and an immunoassay analyzer body 1 for acquiring fluorescence detection information in the reagent card and performing data processing to obtain the concentration of a target substance.

[0029] The reagent card uses quantum dots as fluorescent markers. After the sample to be tested is mixed with the fluorescent labeled antibody prefabricated on the binding pad, an immune reaction occurs to form a test substance-fluorescent labeled antibody complex. The complex is captured and enriched by the antibody coated on the NC membrane through the chromatography process, while the remaining components are separated and removed.

[0030] Specifically, the reagent card is designed with several drainage channels, which are connected to evenly arranged detection channels. The serum sample is dropped into the sample addition area of ​​the reagent card, and the sample flows along the drainage channel by capillary action, and reacts with the fluorescent labeled antibody in the detection channel. Above the detection channel, there is an observation area in the middle and reference areas on both sides.

[0031] It is worth noting that the reference area on the reagent card is set on both sides of the observation area. The reference area is equally divided into multiple sub-areas, each of which contains a standard substance of known concentration (such as 0.1, 1, and 10 ng / mL of TSH). The reference area uses the same fluorescent marker as the observation area, and the light source 101 and the sensor respond in the same way.

[0032] like Figure 2 As shown, the immunoassay analyzer body 1 includes: a detection module, a data processing module, a calibration verification module, a quantitative calculation module and an output and display module.

[0033] The detection module is used to obtain the compression measurement signal in the reagent card through the excitation light source 101. The detection module includes: a card slot, an excitation light source 101 component and an optical collection component, specifically: The card slot is provided on the immunoassay analyzer body 1 and is used to insert the reagent card. Observation The area is aligned with the optical collection component. Furthermore, an adjustable snap-on clamp is provided in the card slot to fix the reagent card through an elastic pressing sheet.

[0034] like Figure 3 As shown, the excitation light source assembly includes: a light source 101, a pulse modulation circuit and a spectroscopic system. Among them, the light source 101 is configured as a multi-wavelength LED array, integrating multi-wavelength light sources 101 such as 365nm ultraviolet LED (excitation quantum dots) and 650nm near-infrared LED (excitation fluorescent microspheres), supporting multi-joint detection requirements. The light source 101 irradiates the fluorescent substance with excitation light to excite the fluorescent signal, thereby completing the detection, and the wavelength of the light source 101 needs to be determined according to the fluorescent substance. The pulse modulation circuit is configured as a nanosecond pulse drive chip, preferably a PWM controller, to control the pulse excitation of the light source 101, and the pulse width is controlled to <10ns. The spectroscopic system includes: a collimator 102, a dichroic mirror 103, and a first condenser 104 arranged vertically to the dichroic mirror 103, wherein the dichroic mirror 103 is installed at a 45° angle, and the condenser is directly above the observation area of ​​the reagent card.

[0035] The optical collection assembly includes: a CMOS image sensor 105, an aperture 106, a second condenser 107 and a filter 108 arranged in sequence from top to bottom; the CMOS image sensor 105, the aperture 106, the second condenser 107 and the filter 108 are all arranged directly above the dichroic mirror 103, and the center points of the CMOS image sensor 105, the aperture 106, the second condenser 107, the filter 108, the dichroic mirror 103 and the first condenser 104 are on a vertical straight line. Among them, the CMOS image sensor 105 is used to realize the reception and conversion of optical signals, that is, to convert fluorescent signals into electrical signals.

[0036] In the optical design of the excitation light source component and the optical collection component, the reflection effect of the dichroic mirror 103 can change the path of the excitation light so that the excitation light is irradiated onto the reagent card, and the excited fluorescence can directly reach the optical collection component through the dichroic mirror 103 to complete the reception of the compressed measurement signal.

[0037] Furthermore, sparse sampling specifically includes the following steps: Step 1: Construct a sparse representation dictionary D based on the quantum dot fluorescence lifetime feature library, the dictionary includes multiple decay basis functions ,in, is the fluorescence lifetime related to the particle size of quantum dots, is the fluorescence oscillation frequency.

[0038] The basis functions in the sparse representation dictionary D need to match the fluorescence characteristics of the target substance. For example, when detecting TSH, the decay basis function closest to the lifetime (such as 50 ns) and oscillation frequency (such as 2 MHz) of the quantum dots bound to the TSH-labeled antibody is selected to ensure the accuracy of the subsequent reconstruction signal.

[0039] Step 2: Obtain the peak intensity V of the fluorescence signal through pre-scanning p , according to V p The intensity interval dynamically selects the construction mode of the observation matrix Φ: ; in, To preserve the low-frequency components, the Fourier measurement matrix is ​​generated by truncating the low-frequency coefficients in the frequency domain; The Bernoulli random matrix is ​​used to capture transient characteristics. Its elements are ±1 and are independent and identically distributed. The symbol ⊕ represents the cascade operation of the matrix, that is, a mixed sampling mode covering the entire frequency band.

[0040] For high signal intensity (Vp>1V), the Fourier low-frequency observation matrix is ​​used. Under strong signals, the main components of the fluorescence decay curve are concentrated in the low-frequency band (such as the exponential decay basis related to the lifetime of quantum dots). Through Fourier low-frequency sampling, the core energy of the signal can be efficiently captured, redundant data can be reduced, and high-frequency noise can be suppressed.

[0041] Medium signal strength (0.1V<V p ≤1V), using a hybrid observation matrix, medium-intensity signals need to take into account both low-frequency subjects and high-frequency details (such as transient oscillations caused by quantum dot agglomeration), the Fourier component retains the main attenuation trend, and the Bernoulli random matrix captures sparse high-frequency features with random projection, balancing the amount of data and information integrity.

[0042] Weak signal strength (V p ≤0.1V), using a full-band observation matrix. At extremely low concentrations, the high-frequency components of weak signals (such as single-molecule fluorescence flashes of quantum dots) may carry key information. The cascade observation matrix covers the entire frequency band, and by increasing the sampling rate, the loss of high-frequency features is avoided to ensure the detection limit.

[0043] The CMOS image sensor 105 is controlled by FPGA hardware to perform pixel-level random sampling, and the sampling window is synchronized with the quantum dot fluorescence lifetime window to generate a compressed measurement signal. , where x is the original fluorescence decay signal, ε is the measurement noise and satisfies .

[0044] Step 3: Use pulse light source 101 and CMOS image sensor 105 global shutter synchronization to start imaging within the fluorescence lifetime window of quantum dots on the reagent card. During imaging, continuously collect 5-10 frames of images, each frame exposure time is between 10-100 μs, frame interval is 2ms, and the tomographic flow velocity is matched.

[0045] Next, the N frames of fluorescence images collected are matched and fused. Specifically: For N consecutively acquired fluorescence images , taking the first frame I1 as the reference image, for each frame I k (k = 1 to N), calculate its displacement vector field relative to I1 , by solving: ,in, is the pixel offset, constrained within ±5 pixels; is the coordinate position of the pixel in the image; By minimizing the difference between the reference frame I1 and the kth frame I k The pixel difference is used to find the optimal displacement vector Δ to align the two frames.

[0046] The registration weights are calculated using the improved non-local homogeneity algorithm. , and perform multi-frame weighted fusion to generate a fused image I fusion : ; The weight w k Proportional to the square of the signal-to-noise ratio: , the information of high-quality frames is retained first, and multi-frame fusion improves the signal-to-noise ratio through weighted averaging to obtain a compressed measurement signal.

[0047] The data processing module is used to perform signal reconstruction processing on the compressed measurement signal to obtain a first enhanced signal.

[0048] Signal reconstruction is based on the sparse representation dictionary D, and uses the Bregman algorithm to perform multiple iterations of optimization on the compressed measurement signal output by the detection module. In the initial stage, the signal is assumed to be in a zero-value state, and the signal estimation value is gradually adjusted until the change between the two estimation values ​​is less than 0.01%, so as to achieve signal reconstruction and gradually approach the original signal. Specifically, this unit can recover high-resolution signals from the compressed measurement signal output by the detection module, especially under low concentration conditions, significantly reducing signal distortion caused by insufficient sampling.

[0049] It is worth noting that the iterative reconstruction process includes: Minimize the objective function to obtain the first enhanced signal S, the objective function is ; Where Ψ is a single-substance-specific dictionary (such as TSH corresponding to a specific basis function combination), M is a random sampling mask matrix, and Y is a compressed measurement signal. For example, quantum dots bound to TSH-labeled antibodies have specific fluorescence lifetimes (such as 50 ns) and oscillation frequencies (such as 2 MHz), and these features are encoded in the dictionary Ψ. The L1 norm encourages the solution S to be as sparse as possible under the dictionary Ψ, that is, as few basis functions as possible are involved in signal reconstruction, thereby removing redundant information. The parameter λ is a weight coefficient used to balance the relationship between sparsity and data fidelity.

[0050] Use Bregman iteration to minimize the objective function.

[0051] Initialization signal S （0） =0, that is, to build the signal from 0; at the same time, initialize the Bregman variable B (0) =0, this variable is used to store the accumulated error in each iteration.

[0052] Each iteration consists of: Update signal estimate S (K+1) : ; In each iteration, the current signal estimate S and the accumulated error B (k)After addition, it is used as the new input. Through the L1 norm constraint, the new signal is encouraged to estimate S (k+1) As sparse as possible under the dictionary Ψ. At the same time, through the L2 norm constraint, ensure that the new signal estimate S (k+1) As close as possible to the compressed measurement signal Y.

[0053] Update Bregman variable B (k+1) : ; Bregman variable B (k+1) The cumulative error in each iteration is recorded. After each iteration, update B (k+1) is the previous cumulative error plus the difference between the new and old signal estimates, that is, This helps to gradually correct biases in the signal estimate.

[0054] The iteration process continues until the following stopping conditions are met: ; in, is a preset small threshold (such as 0.01%). When the signal estimation change between two consecutive iterations is less than the threshold, the algorithm is considered to have converged and the final signal reconstruction result S, i.e., the first enhanced signal, is obtained.

[0055] Through the above iterative process, the Bregman algorithm can recover the high-resolution first enhanced signal S from a small amount of compressed measurement signal Y, especially in low-concentration detection scenarios (such as 0.01 ng / mL TSH detection), significantly reducing signal distortion caused by insufficient sampling. Due to the sparsity constraint of the L1 norm, the Bregman algorithm can effectively suppress noise, especially high-frequency noise that does not conform to the dictionary Ψ feature. At the same time, the data fidelity constraint of the L2 norm ensures the consistency of the reconstructed signal with the actual observed signal, avoiding the loss of effective signals caused by over-smoothing. In summary, the Bregman iterative reconstruction algorithm effectively recovers the original high-resolution signal from the compressed measurement signal by combining sparse representation and data fidelity constraints.

[0056] It is worth noting that, while the detection module collects the signal of the observation area, it also collects the fluorescence signal of the reference area and records the fluorescence intensity value of each sub-area.

[0057] The calibration verification module calibrates the first enhanced signal based on the reference zone signal, including compensation for light source fluctuation and sensor drift, and verifies the authenticity of the first enhanced signal through an adversarial verification algorithm, and obtains a second enhanced signal through feedback processing.

[0058] A concentration-fluorescence intensity calibration curve was established using the signals of standard substances with known concentrations.

[0059] The calibration verification module includes: an error factor calculation unit, a signal calibration unit, and an adversarial verification unit.

[0060] The error factor calculation unit calculates the error factor under the current detection conditions by the difference between the reference zone signal and the theoretical value. The error factor includes: Light source fluctuation compensation: ; If the intensity of the light source decays over time, light source fluctuation compensation is used to adjust the signal in the observation area; Sensor drift compensation: ; By comparing replicate measurements of a reference area, variations in sensor sensitivity are corrected.

[0061] The signal calibration unit calibrates the first enhanced signal output by the data processing module through an error factor: .

[0062] The adversarial verification unit detects anomalies or interference in the calibrated first enhanced signal through an adversarial verification algorithm to ensure the authenticity of the measurement result. The specific detection process includes: The calibrated first enhanced signal and the real signal of the reference area are respectively input into the adversarial network architecture.

[0063] The adversarial network architecture includes: The generator is configured to generate simulated abnormal signals (such as noise interference and concentration tampering) for training the discriminator. The input of the generator is the real signal of the reference area + random noise, and the output is a synthetic abnormal signal (such as signal intensity mutation and lifespan abnormality).

[0064] The discriminator is configured to distinguish between the real signal and the generated abnormal signal and output a confidence score (0-1). The input of the discriminator is the real signal of the reference area and the synthetic abnormal signal output by the generator. The discriminator determines whether the signal is real (0 for abnormality and 1 for real).

[0065] Based on the adversarial network architecture constructed above, pre-training and adversarial training are performed in sequence. In the pre-training stage, the discriminator is trained using the known concentration signal of the reference area to learn the distribution characteristics of the real signal (such as fluorescence lifetime, oscillation frequency, and intensity distribution). In the adversarial training stage, the generator continuously generates more realistic abnormal signals, and the discriminator continuously optimizes the classification ability until the Nash equilibrium is reached (the generator cannot interfere with the discriminator).

[0066] The calibrated first enhanced signal is input into the discriminator and the confidence score D is output. score If D score <θ, θ=0.8, then the signal is judged to be abnormal, that is, there is interference or measurement error; if D score>θ, the verification is passed and the signal is credible.

[0067] Furthermore, according to the adversarial verification result, the hyperparameters or optimization targets of the signal reconstruction unit for iterative reconstruction are adjusted, including: False features are noise misjudgments, so increasing λ can enhance data fidelity; The false features are signal distortions, and reducing λ allows more basis functions to participate in the reconstruction.

[0068] Specifically, the objective function of iterative reconstruction is adjusted according to the output result of the adversarial verification, and the second enhanced signal is re-output. The adjusted objective function is: ,in, By penalizing signals that are greatly different from the true distribution, the reconstruction process is guided away from false features, and μ is the weight coefficient of the adversarial loss, which needs to be adjusted according to the experiment.

[0069] By implementing an adversarial verification mechanism on the first enhanced signal, when the statistical difference between the reconstructed signal and the true distribution (defined by the reference area standard material) is significant, the adversarial loss function will dynamically enhance the weight of the penalty term through the gradient back-propagation mechanism, forcing the iterative optimization process to adjust the core parameters. This feedback mechanism can effectively suppress the false features (such as pseudo-lifetime signals or oscillation frequency distortion) introduced by algorithmic deviations such as undersampling errors or excessive noise suppression during the reconstruction process by strengthening the constraints on distribution consistency, thereby improving the fitting accuracy of the reconstructed signal and the physical true value. It is particularly important in low-concentration detection, which can significantly reduce false positive or false negative results caused by algorithmic errors.

[0070] The quantitative calculation module is used to calculate the target substance concentration corresponding to the second enhanced signal. Specifically, the target substance concentration corresponding to the second enhanced signal is calculated according to the existing target substance concentration standard model.

[0071] The output and display module is used to output and display the target substance concentration through a visual interface. Specifically, the output results of the quantitative calculation module (target substance concentration and auxiliary information) are displayed in real time in a user-friendly form, and support data recording and export.

[0072] The output and display module also includes: a visual interface provided on the immunoassay analyzer body 1, for displaying the target substance concentration and auxiliary information.

[0073] The present invention provides a highly sensitive handheld multi-detection fluorescent immunoassay analyzer, which performs compressed sensing sparse sampling, signal reconstruction, calibration and adversarial verification on fluorescent markers on reagent cards, and optimizes feedback based on adversarial verification results, thereby achieving targeted enhancement of the fluorescent signal of ultra-low concentration target substances. This process not only effectively reduces background noise, but also improves the detection sensitivity of the handheld fluorescent immunoassay analyzer through multiple technical means, and has a lower detection limit. Compared with the prior art, the present invention solves the problem of insufficient detection sensitivity and accuracy of the handheld fluorescent immunoassay analyzer when detecting low-concentration samples due to weak fluorescent signals.

[0074] In order to verify the performance of this handheld multi-detection fluorescence immunoassay analyzer in low-concentration detection, a gradient concentration test of thyroid stimulating hormone (TSH) was performed. TSH serum samples with a concentration range of 0.001 to 1 ng / mL were selected, and each group was tested 20 times and compared with the traditional fluorescence immunoassay analyzer. The experimental results showed: Higher sensitivity: At an ultra-low concentration of 0.01 ng / mL, the signal-to-noise ratio (SNR) of the present invention reaches 4.2±0.3, which is significantly higher than the 1.8±0.5 of the traditional instrument, indicating that the compressed sensing sparse sampling and Bregman iterative reconstruction technology effectively enhance weak signals; Lower detection limit: The calibration verification module dynamically compensates for light source fluctuations and sensor drift, and the countermeasure verification unit eliminates abnormal signals (the rejection rate is 100% when Dscore < 0.8). The LOD of the present invention is as low as 0.008 ng / mL (blank signal mean + 3σ), which is one order of magnitude lower than that of traditional instruments (LOD = 0.1 ng / mL). Moreover, in a complex matrix containing 1 mg / mL human serum albumin (HSA), the detection recovery rate of 0.01 ng / mL TSH was 97.5%-102.3%, confirming the inhibitory effect of multi-frame fusion algorithm and adversarial network on false features.

[0075] In summary, the present invention achieves a breakthrough in the sensitivity and reliability of the handheld fluorescent immunoassay analyzer in ultra-low concentration detection through a pulse excitation-sparse sampling-adversarial verification closed-loop technology chain.

[0076] The above is based on the ideal embodiment of the present invention. Through the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims

1. A highly sensitive handheld multi-detection fluorescent immunoassay analyzer, characterized in that: include: Reagent Card, A detection module, which obtains the compressed measurement signal in the reagent card through sparse sampling and image fusion; A data processing module, used for performing signal reconstruction processing on the compressed measurement signal to obtain a first enhanced signal; A calibration verification module, used to calibrate the first enhanced signal, verify the authenticity of the first enhanced signal through an adversarial verification algorithm, and obtain a second enhanced signal through feedback processing; A quantitative calculation module, used to calculate the concentration of the target substance corresponding to the second enhanced signal; The output and display module is used to output and display the concentration of the target substance through a visual interface.

2. A highly sensitive handheld multi-detection fluorescent immunoassay analyzer according to claim 1, characterized in that: The detection module comprises: A card slot, used to insert the reagent card into a designated position; An excitation light source assembly, including a light source, a pulse modulation circuit and a light splitting system; An optical collection component, including a CMOS image sensor, for receiving and converting the fluorescence signal into an electrical signal; The pulse modulation circuit controls the light source to excite the fluorescent substance with a pulse with a pulse width of less than 10 ns.

3. A highly sensitive handheld multi-detection fluorescent immunoassay analyzer according to claim 2, characterized in that: The sparse sampling comprises the following steps: Step 1: construct a sparse representation dictionary D based on the quantum dot fluorescence lifetime feature library; Step 2: Obtain the peak intensity V of the fluorescence signal through pre-scanning p , calculating the sampling rate, and controlling the CMOS image sensor to perform pixel-level random sampling, with the sampling window being synchronized with the quantum dot fluorescence lifetime window; Step 3: Using a pulse light source to synchronize with the global shutter of the CMOS image sensor to start imaging within the fluorescence lifetime window of the quantum dots on the reagent card; 5-10 frames of images were collected continuously, and the exposure time of each frame was between 10-100 μs.

4. A highly sensitive handheld multi-detection fluorescent immunoassay analyzer according to claim 1, characterized in that: The image fusion is specifically as follows: N frames of fluorescence images acquired by sparse sampling , taking the first frame I1 as the reference image, for each frame I k , calculate its displacement vector field relative to I1 , by solving: ; in, is the pixel offset, constrained within ±5 pixels; is the coordinate position of the pixel in the image; The registration weights are calculated using the improved non-local homogeneity algorithm. , and perform multi-frame weighted fusion to generate a fused image I fusion : ; The weight w k Proportional to the square of the signal-to-noise ratio: , giving priority to preserving the information of high-quality frames.

5. A high-sensitivity handheld multi-detection fluorescent immunoassay analyzer according to claim 3, characterized in that: The signal reconstruction is based on the sparse representation dictionary D, and the Bregman algorithm is used to perform multiple iterations of optimization on the compressed measurement signal output by the detection module; The iterative refactoring process includes: The first enhanced signal S is obtained by minimizing the objective function, which is: ； Among them, Ψ is a single-substance-specific dictionary, M is a random sampling mask matrix, Y is the compressed measurement signal, and λ is a weight coefficient.

6. A highly sensitive handheld multi-detection fluorescent immunoassay analyzer according to claim 1, characterized in that: The reagent card comprises: an observation area in the middle and reference areas on both sides; The reference area is equally divided into a plurality of sub-areas, each of which contains a standard substance of known concentration; The detection module collects the signal of the observation area and the fluorescence signal of the reference area at the same time, and records the fluorescence intensity value of each sub-area.

7. A high-sensitivity handheld multi-detection fluorescent immunoassay analyzer according to claim 6, characterized in that: The calibration verification module includes: an error factor calculation unit and a signal calibration unit; The error factor calculation unit calculates the error factor under the current detection conditions by the difference between the reference zone signal and the theoretical value. The error factor includes: Light source fluctuation compensation: ; Sensor drift compensation: ; A signal calibration unit is used to calibrate the first enhanced signal output by the data processing module using an error factor: .

8. A high-sensitivity handheld multi-detection fluorescent immunoassay analyzer according to claim 1, characterized in that: The calibration verification module further includes: a confrontation verification unit, which detects anomalies or interferences in the calibrated first enhanced signal through a confrontation verification algorithm to ensure the authenticity of the measurement result; The specific testing process includes: Build an adversarial network architecture, including: A generator configured to generate a simulated abnormal signal for training the discriminator; A discriminator, configured to distinguish between real signals and generated anomaly signals and output a confidence score; The calibrated first enhanced signal is input into the discriminator to output the confidence score D score ; D score <θ, then the signal is judged to be abnormal; If D score >θ, the verification is passed.

9. A high-sensitivity handheld multi-detection fluorescent immunoassay analyzer according to claim 5, characterized in that: The objective function of iterative reconstruction is adjusted according to the output result of the calibration verification module against the verification, and the second enhanced signal is re-output. The adjusted objective function is: ； in, By penalizing signals that are far different from the true distribution, the reconstruction process is guided away from false features, and μ is the weight coefficient of the adversarial loss.

10. A high-sensitivity handheld multi-detection fluorescent immunoassay analyzer according to claim 1, characterized in that: The quantitative calculation module calculates the target substance concentration corresponding to the second enhanced signal according to an existing target substance concentration standard model.

Images