Multi-mycotoxin measurement test strip combined with multi-color fluorescent marker and measurement method

Abstract

The invention relates to the technical field of mycotoxin detection, and discloses a multi-mycotoxin measuring test strip combined with a multi-color fluorescent marker and a measuring method.The measuring method comprises the steps that analysis is conducted on the basis of a first surface image, a microsphere distribution value corresponding to the measuring test strip is obtained, and a particle size distribution value corresponding to the measuring test strip is determined according to optical scattering data; obtaining liquid diffusion characteristics according to the second surface image set, obtaining detection end time according to the liquid diffusion characteristics, and correcting the initial detection result according to the microsphere distribution value and the particle size distribution value to obtain a target detection result; the characteristics of the test strip are evaluated and measured, the liquid diffusion characteristics are obtained by utilizing the second surface image set in the detection process, and the detection ending time is dynamically predicted through the time prediction model, so that the sufficiency and the stability of the detection process are ensured; and the influence of the characteristics of the measurement test strip and the fluctuation in the detection process on the accuracy and precision of the detection result is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of mycotoxin detection, and more specifically to a multi-mycotoxin measurement test strip combined with multi-color fluorescent markers and a measurement method. Background Art

[0002] Mycotoxin contamination often manifests itself as a combination of multiple mycotoxins. If the planting, storage or processing links are not properly controlled, mycotoxins may exceed the standard in grain processing products. Although existing technologies such as chromatography, protein phosphatase inhibition and immunoassay have been used for mycotoxin detection, there are still certain problems.

[0003] In the prior art, a Chinese patent application with publication number CN118603969A discloses a rapid and sensitive method for detecting fungal toxins. The colorimetric sensor based on gold nanoparticles-aptamers can realize qualitative analysis visualized by naked eyes through the color change of the solution. Combined with the absorbance measurement by ultraviolet spectrophotometer, quantitative analysis of the solution can be realized. A Chinese patent application with publication number CN118258807A discloses a method for colorimetric analysis of fungal toxins by lateral flow chromatography test strips. After mixing fungal toxins of different concentrations with CuCo@PDA recognition probes and developing a color reaction, the color gray value of the T line is recorded to establish a standard curve for fungal toxin detection. According to the gray value of the sample to be tested, the corresponding fungal toxin concentration is calculated through the standard curve.

[0004] Although the prior art has disclosed relevant methods for mycotoxin detection, in the process of using test strips for detection, the accuracy and precision of the test results are reduced due to the failure to fully consider the impact of uneven distribution of microspheres and particle size differences on the test results, and the inability to insert the test strips into the fluorescence reader immediately after the test process.

[0005] In view of this, the present invention proposes a multi-fungal toxin measurement test strip and a measurement method combined with multi-color fluorescent markers to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a multi-fungal toxin measurement test strip combined with multi-color fluorescent markers and a measurement method.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a first aspect, a method for measuring multiple mycotoxins in combination with multi-color fluorescent markers is provided, comprising:

[0009] Before the test, a first surface image and optical scattering data of a measuring test strip are obtained, and an analysis is performed based on the first surface image to obtain a microsphere distribution value corresponding to the measuring test strip, and a particle size distribution value corresponding to the measuring test strip is determined according to the optical scattering data, wherein the surface of the measuring test strip is sprayed with a fluorescent microsphere marker for detecting fungal toxins;

[0010] During the detection process, a second surface image set of the measuring test strip is obtained, liquid diffusion characteristics are obtained according to the second surface image set, and the liquid diffusion characteristics are input into a pre-built time prediction model to obtain the detection end time;

[0011] When the test end time arrives, the measuring test strip is placed in a preset fluorescence reader to obtain an initial test result, which is then corrected according to the microsphere distribution value and the particle size distribution value to obtain the target test result.

[0012] Further, based on the analysis of the first surface image, the method for obtaining the microsphere distribution value corresponding to the measurement test strip includes:

[0013] The target detection area in the first surface image is divided into R detection sub-areas, and the number of fluorescent microspheres corresponding to each detection sub-area is obtained by an image segmentation algorithm. The standard deviation of the number of microspheres and the average number of microspheres corresponding to the R detection sub-areas are calculated based on the number of fluorescent microspheres. The standard deviation of the number of microspheres is divided by the average number of microspheres to obtain the microsphere aggregation degree, and the microsphere aggregation degree is used as the microsphere distribution value. The target detection area is the area sprayed with fluorescent microsphere markers.

[0014] Furthermore, the optical scattering data includes a scattering intensity value and a scattering deviation angle value, and the method for determining the particle size distribution value corresponding to the measuring test strip according to the optical scattering data includes:

[0015] According to the scattering offset angle value, P offset angle ranges are determined, and the light intensity cumulative value corresponding to each offset angle range is calculated according to the scattering intensity value. The light intensity standard deviation corresponding to the P offset angle ranges is calculated according to the light intensity cumulative value, and the light intensity standard deviation is used as the particle size distribution value.

[0016] Further, the method of calculating the light intensity accumulation value corresponding to each offset angle range according to the scattering intensity value includes:

[0017] ;

[0018] In the formula, For the The accumulated light intensity corresponding to the offset angle range is: Indicated in Within the range of offset angles, the scattering angle is The scattering intensity value at For the The starting angle of the offset angle range, For the The end angle of the offset angle range.

[0019] Furthermore, the method for acquiring liquid diffusion characteristics according to the second surface image set includes:

[0020] A diffusion area change sequence is determined based on adjacent frames of the second surface image set, a diffusion rate sequence is calculated based on the diffusion area change sequence and preset adjacent times, a fluctuation amplitude mean is determined based on the diffusion rate sequence, and the fluctuation amplitude mean is used as a liquid diffusion feature. Adjacent frames are two temporally adjacent images in the second surface image set continuously taken during the detection process, and adjacent time is the time interval for obtaining adjacent frames.

[0021] Furthermore, the method for determining the mean value of the fluctuation amplitude based on the diffusion rate sequence includes:

[0022] The rate differences between adjacent elements in the diffusion rate sequence are calculated, and the average rate difference is calculated based on all rate differences, and the average rate difference is used as the mean fluctuation amplitude.

[0023] Furthermore, the method for constructing the time prediction model includes:

[0024] A training sample set is obtained, which includes historical liquid diffusion characteristics and historical detection end time, a preset sliding step size and a sliding window length; the training sample set is converted into multiple training samples using a sliding window method, the training samples are used as the input of the initial model, the historical detection end time after the sliding step is predicted as the output of the initial model, the historical detection end time of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the initial model; a time prediction model is generated for predicting the detection end time based on the liquid diffusion characteristics.

[0025] Further, the method of correcting the initial detection result according to the microsphere distribution value and the particle size distribution value to obtain the target detection result includes:

[0026] The initial test results, microsphere distribution values, and particle size distribution values ​​were input into the pre-built test calibration model to obtain the target test results.

[0027] Furthermore, the method for constructing the detection and correction model includes:

[0028] Acquire a sample data set, wherein the sample data set includes historical initial detection results, historical microsphere distribution values, historical particle size distribution values, and historical target detection results;

[0029] Divide the sample data set into a sample training set and a sample test set, and build a regression network;

[0030] The historical initial detection results, historical microsphere distribution values ​​and historical particle size distribution values ​​in the sample training set are used as input data of the regression network, and the historical target detection results in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting target detection results.

[0031] The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a detection and correction model.

[0032] In a second aspect, a multi-mycotoxin measurement test strip combined with a multi-color fluorescent marker is provided, comprising a fluorescent marker conjugate pad, the surface of which is sprayed with fluorescent microsphere markers for detecting mycotoxins.

[0033] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned multi-fungal toxin measurement method combined with multi-color fluorescent markers when executing the computer program.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention firstly performs analysis based on a first surface image to obtain a microsphere distribution value corresponding to a measuring test strip, determines a particle size distribution value corresponding to the measuring test strip according to optical scattering data, obtains liquid diffusion characteristics according to a second surface image set, inputs the liquid diffusion characteristics into a pre-constructed time prediction model, obtains a detection end time, and finally places the measuring test strip into a preset fluorescence reader to obtain an initial detection result, corrects the initial detection result according to the microsphere distribution value and the particle size distribution value, and obtains a target detection result. The present invention obtains microsphere distribution values ​​and particle size distribution values ​​based on the first surface image and optical scattering data before detection, evaluates the characteristics of the measuring test strip, obtains liquid diffusion characteristics using the second surface image set during the detection process, dynamically predicts the detection end time through a time prediction model, ensures the adequacy and stability of the detection process, and finally corrects the initial detection result based on the microsphere distribution value and the particle size distribution value, thereby reducing the influence of the characteristics of the measuring test strip and the fluctuation of the detection process on the accuracy and precision of the detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the process of the multi-fungal toxin measurement method combined with multi-color fluorescent markers in the present invention;

[0037] Figure 2 It is a schematic diagram of the structure of the multi-fungal toxin measurement system combined with multi-color fluorescent markers in the present invention;

[0038] Figure 3It is a schematic diagram of the structure of the measuring test strip in the present invention;

[0039] Figure 4 It is a schematic flow chart of the method for determining the particle size distribution value corresponding to the measurement test strip according to the optical scattering data in the present invention.

[0040] Reference numerals:

[0041] 10. Measurement test strip body; 20. First test line; 30. Second test line; 40. Third test line; 50. Quality control line. DETAILED DESCRIPTION

[0042] 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.

[0043] Example 1

[0044] See also Figure 1 As shown, this embodiment discloses a method for measuring multiple fungal toxins combined with multi-color fluorescent markers, comprising:

[0045] S10: before the detection, obtaining a first surface image and optical scattering data of a measuring test strip, performing analysis based on the first surface image to obtain a microsphere distribution value corresponding to the measuring test strip, and determining a particle size distribution value corresponding to the measuring test strip according to the optical scattering data, wherein the surface of the measuring test strip is sprayed with a fluorescent microsphere marker for detecting fungal toxins;

[0046] It should be noted that the method for detecting mycotoxins in this embodiment is to drop a water sample containing mycotoxins to be tested into the detection hole of a measuring test strip, wait for several minutes, insert the measuring test strip into a fluorescence reader, press the reading key to read and automatically calculate, and the final concentration of the mycotoxins can be displayed on the LCD screen. The measuring test strip is sprayed with a mycotoxin antibody fluorescent microsphere marker, which refers to an antibody that specifically binds to mycotoxins (such as aflatoxin, ochratoxin, etc.), and fluorescent microspheres (fluorescent particles) are fixed on the surface of the antibody. These microspheres are used to bind to mycotoxins in the water sample to be tested in the detection hole of the measuring test strip and are detected by fluorescent labeling technology.

[0047] The method for obtaining the microsphere distribution value corresponding to the measuring test strip by analyzing the first surface image includes:

[0048] The target detection area in the first surface image is divided into R detection sub-areas, and the number of fluorescent microspheres corresponding to each detection sub-area is obtained by an image segmentation algorithm. The standard deviation of the number of microspheres and the average number of microspheres corresponding to the R detection sub-areas are calculated based on the number of fluorescent microspheres. The standard deviation of the number of microspheres is divided by the average number of microspheres to obtain the microsphere aggregation degree, and the microsphere aggregation degree is used as the microsphere distribution value. The target detection area is the area sprayed with fluorescent microsphere markers.

[0049] It can be understood that the first surface image can be the overall image of the measuring test strip, including the target detection area, the background area and the edge area, etc. The target detection area is the area sprayed with fluorescent microsphere markers, the background area is the area not sprayed with fluorescent microsphere markers, which is used for comparison and correction, and the edge area is the area where the water sample to be tested will diffuse subsequently. The above-mentioned image segmentation algorithm can be Canny edge detection or region growing algorithm, etc. The method for obtaining the number of fluorescent microspheres corresponding to each detection sub-area through the image segmentation algorithm can be, first, applying the Canny operator to extract the boundaries of the fluorescent microspheres, and then performing connected domain analysis, grouping the interconnected edge pixels, marking them as a complete fluorescent microsphere, counting the connected domain marks in each detection sub-area, and recording the number of fluorescent microspheres in each detection sub-area.

[0050] It should be added that the above calculation of the standard deviation of the number of microspheres is a prior art, and this embodiment will not go into details about it. It can be seen from the above content that the microsphere aggregation degree is used as the microsphere distribution value. The greater the microsphere aggregation degree, the more uneven the distribution of the fluorescent microspheres in the target detection area, and the presence of obvious local aggregation. Due to the uneven distribution of fluorescent microspheres, the signals in some areas are weakened or amplified, which reduces the sensitive detection ability of the test strip for low-concentration fungal toxins, resulting in a decrease in the accuracy and sensitivity of subsequent detection.

[0051] like Figure 4 As shown, in this embodiment, the optical scattering data includes a scattering intensity value and a scattering offset angle value, and the method for determining the particle size distribution value corresponding to the measuring test strip according to the optical scattering data includes:

[0052] According to the scattering offset angle value, P offset angle ranges are determined, and the light intensity cumulative value corresponding to each offset angle range is calculated according to the scattering intensity value. The light intensity standard deviation corresponding to the P offset angle ranges is calculated according to the light intensity cumulative value, and the light intensity standard deviation is used as the particle size distribution value.

[0053] The method for calculating the light intensity accumulation value corresponding to each offset angle range according to the scattered intensity value includes:

[0054] ;

[0055] In the formula, For the The accumulated light intensity corresponding to the offset angle range is: Indicated in Within the range of offset angles, the scattering angle is The scattering intensity value at For the The starting angle of the offset angle range, For the The end angle of the offset angle range.

[0056] In this embodiment, the scattering intensity value is closely related to the particle size of the fluorescent microspheres. Generally, the larger the particle size of the fluorescent microspheres, the higher the cumulative value of the light intensity in a small angle range, and the lower the cumulative value of the light intensity in a large angle range. For example, the small angle range can be 0 degrees to 30 degrees, and the large angle range can be 90 degrees to 180 degrees. The above-mentioned offset angles can be evenly divided to determine P offset angle ranges, or they can be unevenly divided. This embodiment does not limit this. It can be understood that since fluorescent microspheres of different particle sizes contribute differently to the angular distribution of scattered light intensity, the larger the standard deviation of the light intensity, the greater the difference in particle size of the fluorescent microspheres in the measuring test strip, and the greater the difference in particle size of the fluorescent microspheres, the greater the error affecting subsequent detection results.

[0057] S20: acquiring a second surface image set of the measuring test strip during the detection process, acquiring liquid diffusion characteristics according to the second surface image set, and inputting the liquid diffusion characteristics into a pre-built time prediction model to obtain a detection end time;

[0058] It should be noted that the above detection process refers to the whole process in which after the water sample containing fungal toxins is dropped into the detection hole of the measuring test strip, the measuring test strip begins to adsorb and diffuse the water sample, and at the same time the fluorescent microsphere marker reacts with the fungal toxins.

[0059] The method for obtaining liquid diffusion characteristics according to the second surface image set includes:

[0060] A diffusion area change sequence is determined based on adjacent frames of the second surface image set, a diffusion rate sequence is calculated based on the diffusion area change sequence and preset adjacent times, a fluctuation amplitude mean is determined based on the diffusion rate sequence, and the fluctuation amplitude mean is used as a liquid diffusion feature. Adjacent frames are two temporally adjacent images in the second surface image set continuously taken during the detection process, and adjacent time is the time interval for obtaining adjacent frames.

[0061] It can be understood that, during the detection process, several second surface images are continuously acquired to construct a second surface image set. The diffusion area refers to the total area of ​​the region where the liquid has diffused on the surface of the measuring test strip during the detection process. The diffusion area change sequence is a sequence composed of the diffusion area difference values ​​of consecutive adjacent frames, wherein each element represents the change in the diffusion area of ​​the liquid on the surface of the measuring test strip within adjacent time intervals. Specifically, it reflects the dynamic behavior of the diffusion of the liquid between two adjacent images (adjacent frames).

[0062] For example, Figure 3 As shown, Figure 3 The measuring test strip body 10, the first detection line 20, the second detection line 30, the third detection line 40 and the quality control line 50 are shown. Then, in this embodiment, when the liquid diffuses to the quality control line 50, the second surface image can be acquired starting from the beginning and the second surface image can be acquired ending when the liquid diffuses to the first detection line 20. When the liquid diffuses to the quality control line 50, it usually indicates that the liquid has begun to diffuse stably and enter the detection area. When the liquid diffuses to the first detection line 20, the diffusion process is basically completed. In this way, the liquid diffusion characteristics related to the detection results can be effectively acquired to avoid interference from irrelevant areas.

[0063] Methods for determining the mean fluctuation amplitude based on the diffusion rate series include:

[0064] The rate differences between adjacent elements in the diffusion rate sequence are calculated, and the average rate difference is calculated based on all rate differences, and the average rate difference is used as the mean fluctuation amplitude.

[0065] In this embodiment, each element in the diffusion rate sequence represents the rate at which the liquid diffuses on the surface of the measuring test strip within adjacent time intervals. Therefore, in this embodiment, the average value of the rate difference is used as the mean value of the fluctuation amplitude. The larger the mean value of the fluctuation amplitude, the more unstable the process of liquid diffusion on the surface of the measuring test strip. Therefore, in order to ensure the accuracy and stability of the test results, more time is required to wait for the diffusion rate to gradually decrease and stabilize. Therefore, it can be seen from the above content that when the liquid diffusion characteristic is larger, the detection end time needs to be postponed, and when the liquid diffusion characteristic is smaller, the detection end time can be appropriately ended in advance.

[0066] The construction method of the time prediction model includes:

[0067] A training sample set is obtained, which includes historical liquid diffusion characteristics and historical detection end time, preset sliding step size and sliding window length; the training sample set is converted into multiple training samples using a sliding window method, the training samples are used as the input of the initial model, the historical detection end time after the sliding step is predicted as the output of the initial model, the historical detection end time of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the initial model; a time prediction model is generated for predicting the detection end time based on the liquid diffusion characteristics, and the initial model is an LSTM model.

[0068] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:

[0069] Assume that we want to use the historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then 3 groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4] and [3,4,5] as training samples, and [4], [5] and [6] as prediction targets respectively.

[0070] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a time prediction model.

[0071] In this embodiment, the microsphere distribution value and the particle size distribution value corresponding to the measuring test strip are first obtained. According to the microsphere distribution value and the particle size distribution value, it can be determined whether the measuring test strip can be used for subsequent detection. When it is determined that the measuring test strip can be used for subsequent detection, the liquid diffusion characteristics are obtained, and the detection end time is predicted according to the liquid diffusion characteristics. This ensures the detection accuracy while optimizing the detection time, avoiding premature termination resulting in insufficient signal, and avoiding delayed termination resulting in decreased efficiency.

[0072] S30: When the detection end time arrives, the measuring test strip is placed in a preset fluorescence reader to obtain an initial detection result, and the initial detection result is corrected according to the microsphere distribution value and the particle size distribution value to obtain a target detection result.

[0073] In this embodiment, the initial detection result can be the fluorescence signal intensity value read by a fluorescence reader or the fungal toxin concentration value calculated based on the fluorescence signal. The fluorescence reader can be any existing fluorescence reader, such as PerkinElmer Victor Nivo or BioTek Synergy H1, etc. This embodiment is not limited to this.

[0074] The method of correcting the initial test result according to the microsphere distribution value and the particle size distribution value to obtain the target test result includes:

[0075] The initial test results, microsphere distribution values, and particle size distribution values ​​were input into the pre-built test calibration model to obtain the target test results.

[0076] The construction method of the detection and correction model includes:

[0077] Acquire a sample data set, wherein the sample data set includes historical initial detection results, historical microsphere distribution values, historical particle size distribution values, and historical target detection results;

[0078] Divide the sample data set into a sample training set and a sample test set, and build a regression network;

[0079] The historical initial detection results, historical microsphere distribution values ​​and historical particle size distribution values ​​in the sample training set are used as input data of the regression network, and the historical target detection results in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting target detection results.

[0080] The initial regression network is tested using a sample test set, and an initial regression network with an output smaller than a preset error value is used as a detection and correction model, wherein the regression network is a deep neural network model.

[0081] It should be added that, from the above content, it can be seen that the larger the microsphere distribution value, the more uneven the distribution of the fluorescent microspheres in the target detection area, resulting in a decrease in the accuracy of subsequent detection. The larger the particle size distribution value, the greater the difference in particle size of the fluorescent microspheres, and the greater the error affecting the subsequent detection results. Therefore, the larger the microsphere distribution value and the particle size distribution value, the more significant the detection error will be, and the greater the degree of correction required to ensure the accuracy of the test results will be.

[0082] In this embodiment, firstly, analysis is performed based on the first surface image to obtain the microsphere distribution value corresponding to the measuring test strip, and the particle size distribution value corresponding to the measuring test strip is determined according to the optical scattering data, and then the liquid diffusion characteristics are obtained according to the second surface image set, and the liquid diffusion characteristics are input into the pre-constructed time prediction model to obtain the detection end time, and finally the measuring test strip is placed in a preset fluorescence reader to obtain an initial detection result, and the initial detection result is corrected according to the microsphere distribution value and the particle size distribution value to obtain the target detection result. In this embodiment, the microsphere distribution value and the particle size distribution value are obtained based on the first surface image and the optical scattering data before detection to evaluate the characteristics of the measuring test strip, and the liquid diffusion characteristics are obtained by using the second surface image set during the detection process, and the detection end time is dynamically predicted by the time prediction model to ensure the adequacy and stability of the detection process, and finally the initial detection result is corrected based on the microsphere distribution value and the particle size distribution value, thereby reducing the influence of the characteristics of the measuring test strip and the fluctuation of the detection process on the accuracy and precision of the detection result.

[0083] Example 2

[0084] See also Figure 2 As shown, based on the same inventive concept, this embodiment discloses a multi-fungal toxin measurement system combined with a multi-color fluorescent marker. For details not provided in this embodiment, please refer to the description of the relevant part in Example 1. The system comprises:

[0085] Initial analysis module: used to obtain a first surface image and optical scattering data of a measuring test strip before detection, perform analysis based on the first surface image to obtain a microsphere distribution value corresponding to the measuring test strip, and determine a particle size distribution value corresponding to the measuring test strip according to the optical scattering data, wherein the surface of the measuring test strip is sprayed with a fluorescent microsphere marker for detecting fungal toxins;

[0086] It should be noted that the method for detecting mycotoxins in this embodiment is to drop a water sample containing mycotoxins to be tested into the detection hole of a measuring test strip, wait for several minutes, insert the measuring test strip into a fluorescent reader, press the reading key to read and automatically calculate, and the final concentration of the mycotoxins can be displayed on the LCD screen. The measuring test strip is sprayed with a mycotoxin antibody fluorescent microsphere marker, which refers to an antibody that specifically binds to mycotoxins (such as aflatoxin, ochratoxin, etc.), and fluorescent microspheres (fluorescent particles) are fixed on the surface of the antibody. These microspheres are used to bind to mycotoxins in the water sample to be tested in the detection hole of the measuring test strip and are detected by fluorescent labeling technology.

[0087] The method for obtaining the microsphere distribution value corresponding to the measuring test strip by analyzing the first surface image includes:

[0088] The target detection area in the first surface image is divided into R detection sub-areas, and the number of fluorescent microspheres corresponding to each detection sub-area is obtained by an image segmentation algorithm. The standard deviation of the number of microspheres and the average number of microspheres corresponding to the R detection sub-areas are calculated based on the number of fluorescent microspheres. The standard deviation of the number of microspheres is divided by the average number of microspheres to obtain the microsphere aggregation degree, and the microsphere aggregation degree is used as the microsphere distribution value. The target detection area is the area sprayed with fluorescent microsphere markers.

[0089] In this embodiment, the optical scattering data includes a scattering intensity value and a scattering offset angle value. The method for determining the particle size distribution value corresponding to the measuring test strip according to the optical scattering data includes:

[0090] According to the scattering offset angle value, P offset angle ranges are determined, and the light intensity cumulative value corresponding to each offset angle range is calculated according to the scattering intensity value. The light intensity standard deviation corresponding to the P offset angle ranges is calculated according to the light intensity cumulative value, and the light intensity standard deviation is used as the particle size distribution value.

[0091] The method for calculating the light intensity accumulation value corresponding to each offset angle range according to the scattered intensity value includes:

[0092] ;

[0093] In the formula, For the The accumulated light intensity corresponding to the offset angle range is: Indicated in Within the range of offset angles, the scattering angle is The scattering intensity value at For the The starting angle of the offset angle range, For the The end angle of the offset angle range.

[0094] Intermediate analysis module: used to obtain a second surface image set of the measuring test strip during the detection process, obtain liquid diffusion characteristics according to the second surface image set, input the liquid diffusion characteristics into a pre-built time prediction model, and obtain the detection end time;

[0095] It should be noted that the above detection process refers to the whole process in which after the water sample containing fungal toxins is dropped into the detection hole of the measuring test strip, the measuring test strip begins to adsorb and diffuse the water sample, and at the same time the fluorescent microsphere marker reacts with the fungal toxins.

[0096] The method for obtaining liquid diffusion characteristics according to the second surface image set includes:

[0097] A diffusion area change sequence is determined based on adjacent frames of the second surface image set, a diffusion rate sequence is calculated based on the diffusion area change sequence and preset adjacent times, a fluctuation amplitude mean is determined based on the diffusion rate sequence, and the fluctuation amplitude mean is used as a liquid diffusion feature. Adjacent frames are two temporally adjacent images in the second surface image set continuously taken during the detection process, and adjacent time is the time interval for obtaining adjacent frames.

[0098] Methods for determining the mean fluctuation amplitude based on the diffusion rate series include:

[0099] The rate differences between adjacent elements in the diffusion rate sequence are calculated, and the average rate difference is calculated based on all rate differences, and the average rate difference is used as the mean fluctuation amplitude.

[0100] The construction method of the time prediction model includes:

[0101] A training sample set is obtained, which includes historical liquid diffusion characteristics and historical detection end time, preset sliding step size and sliding window length; the training sample set is converted into multiple training samples using a sliding window method, the training samples are used as the input of the initial model, the historical detection end time after the sliding step is predicted as the output of the initial model, the historical detection end time of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the initial model; a time prediction model is generated for predicting the detection end time based on the liquid diffusion characteristics, and the initial model is an LSTM model.

[0102] Detection correction module: when the detection end time arrives, the measurement test strip is placed in a preset fluorescence reader to obtain the initial detection result, and the initial detection result is corrected according to the microsphere distribution value and the particle size distribution value to obtain the target detection result.

[0103] Example 3

[0104] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the multi-fungal toxin measurement method combined with multi-color fluorescent markers provided by the above methods is implemented.

[0105] Since the electronic device introduced in this embodiment is an electronic device used to implement the multi-fungal toxin measurement method combined with multi-color fluorescent markers in the embodiment of the present application, based on the multi-fungal toxin measurement method combined with multi-color fluorescent markers introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of the present application will not be introduced in detail here. As long as technical personnel in this field implement the electronic device used in the multi-fungal toxin measurement method combined with multi-color fluorescent markers in the embodiment of the present application, it belongs to the scope of protection of this application.

[0106] Example 4

[0107] Based on Example 1, this example discloses a multi-fungal toxin measurement test strip combined with a multi-color fluorescent marker, including a fluorescent marker conjugate pad, the surface of which is sprayed with fluorescent microsphere markers for detecting fungal toxins.

[0108] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0109] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0110] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0112] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0115] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0116] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for measuring multiple mycotoxins in combination with multicolor fluorescent markers, characterized in that: include: Before the test, a first surface image and optical scattering data of a measuring test strip are obtained, and an analysis is performed based on the first surface image to obtain a microsphere distribution value corresponding to the measuring test strip, and a particle size distribution value corresponding to the measuring test strip is determined according to the optical scattering data, wherein the surface of the measuring test strip is sprayed with a fluorescent microsphere marker for detecting fungal toxins; During the detection process, a second surface image set of the measuring test strip is obtained, liquid diffusion characteristics are obtained according to the second surface image set, and the liquid diffusion characteristics are input into a pre-built time prediction model to obtain the detection end time; When the test end time arrives, the measuring test strip is placed in a preset fluorescence reader to obtain an initial test result, which is then corrected according to the microsphere distribution value and the particle size distribution value to obtain the target test result.

2. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 1, characterized in that: The method for obtaining the microsphere distribution value corresponding to the measuring test strip by analyzing the first surface image comprises: The target detection area in the first surface image is divided into R detection sub-areas, and the number of fluorescent microspheres corresponding to each detection sub-area is obtained by an image segmentation algorithm. The standard deviation of the number of microspheres and the average number of microspheres corresponding to the R detection sub-areas are calculated based on the number of fluorescent microspheres. The standard deviation of the number of microspheres is divided by the average number of microspheres to obtain the microsphere aggregation degree, and the microsphere aggregation degree is used as the microsphere distribution value. The target detection area is the area sprayed with fluorescent microsphere markers.

3. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 1, characterized in that: The optical scattering data includes a scattering intensity value and a scattering deviation angle value. The method for determining the particle size distribution value corresponding to the measuring test strip according to the optical scattering data includes: According to the scattering offset angle value, P offset angle ranges are determined, and the light intensity cumulative value corresponding to each offset angle range is calculated according to the scattering intensity value. The light intensity standard deviation corresponding to the P offset angle ranges is calculated according to the light intensity cumulative value, and the light intensity standard deviation is used as the particle size distribution value.

4. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 3, characterized in that: The method for calculating the light intensity accumulation value corresponding to each offset angle range according to the scattering intensity value comprises: ； In the formula, For the The accumulated light intensity corresponding to the offset angle range is: Indicated in Within the range of offset angles, the scattering angle is The scattering intensity value at For the The starting angle of the offset angle range, For the The end angle of the offset angle range.

5. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 1, characterized in that: The method for acquiring liquid diffusion characteristics according to the second surface image set comprises: A diffusion area change sequence is determined based on adjacent frames of the second surface image set, a diffusion rate sequence is calculated based on the diffusion area change sequence and preset adjacent times, a fluctuation amplitude mean is determined based on the diffusion rate sequence, and the fluctuation amplitude mean is used as a liquid diffusion feature. Adjacent frames are two temporally adjacent images in the second surface image set continuously taken during the detection process, and adjacent time is the time interval for obtaining adjacent frames.

6. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 5, characterized in that: The method for determining the mean value of the fluctuation amplitude based on the diffusion rate sequence comprises: The rate differences between adjacent elements in the diffusion rate sequence are calculated, and the average rate difference is calculated based on all rate differences, and the average rate difference is used as the mean fluctuation amplitude.

7. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 1, characterized in that: The method for constructing the time prediction model includes: A training sample set is obtained, which includes historical liquid diffusion characteristics and historical detection end time, a preset sliding step size and a sliding window length; the training sample set is converted into multiple training samples using a sliding window method, the training samples are used as the input of the initial model, the historical detection end time after the sliding step is predicted as the output of the initial model, the historical detection end time of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the initial model; a time prediction model is generated for predicting the detection end time based on the liquid diffusion characteristics.

8. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 4, characterized in that: The method of correcting the initial detection result according to the microsphere distribution value and the particle size distribution value to obtain the target detection result includes: The initial test results, microsphere distribution values, and particle size distribution values ​​were input into the pre-built test calibration model to obtain the target test results.

9. The method for measuring multiple mycotoxins in combination with multicolor fluorescent markers according to claim 8, characterized in that: The method for constructing the detection and correction model comprises: Acquire a sample data set, wherein the sample data set includes historical initial detection results, historical microsphere distribution values, historical particle size distribution values, and historical target detection results; Divide the sample data set into a sample training set and a sample test set, and build a regression network; The historical initial detection results, historical microsphere distribution values ​​and historical particle size distribution values ​​in the sample training set are used as input data of the regression network, and the historical target detection results in the sample training set are used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting target detection results. The initial regression network is tested using a sample test set, and the initial regression network with an output smaller than a preset error value is used as a detection and correction model.

10. A multi-fungal toxin measurement test strip combined with a multi-color fluorescent marker, applied to the multi-fungal toxin measurement method combined with a multi-color fluorescent marker according to any one of claims 1 to 9, characterized in that: The invention comprises a fluorescent marker conjugate pad, the surface of which is sprayed with fluorescent microsphere markers for detecting fungal toxins.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the multi-mycotoxin measurement method combined with multi-color fluorescent markers according to any one of claims 1 to 9 is implemented.

Images