An immunochromatographic detection method and system for a clinical laboratory

Abstract

The present invention relates to the technical field of image data processing, and particularly relates to an immunochromatographic detection method and system for a clinical laboratory, including: obtaining an observation area in a test strip image after immunochromatographic detection of a patient sample, dividing the observation area into a plurality of connected regions, determining the confidence level of each connected region as a color development region, so as to screen out two color development regions, obtaining the color development degree of each color development region, and determining a chromatographic result coefficient of the test strip according to the difference in color development degree and area difference between the color development regions, thereby obtaining a quantitative value of the chromatographic result of the test strip. The present invention qualitatively and quantitatively analyzes the chromatographic result by analyzing the existence of different color development regions on the test strip after chromatography and the difference in color development degree, so as to take corresponding preventive and treatment measures, improving the accuracy of chromatographic result detection and the prevention and treatment efficiency of the disease condition.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and particularly relates to an immunochromatographic detection method and system for a clinical laboratory. Background Technique

[0002] Immunochromatography is a biochemical detection technique based on antigen-antibody reactions, and is commonly used in fields such as medical diagnosis, food safety detection, and environmental detection. Its principle is to detect specific substances in a sample through the specific binding of antibodies and antigens, and usually uses markers (such as enzymes, fluorescent agents, or gold nanoparticles) to display the reaction results. It is used for rapid diagnosis and screening of diseases, especially infectious diseases, hormone levels, etc. Due to its simple operation, rapid results, and the need for no complex equipment, this technique has become the preferred method for many clinical laboratories and clinical departments.

[0003] Existing problems: Currently, immunochromatography is generally performed by using a test strip to perform chromatography on a patient's body sample, and then quickly screening the patient's condition based on the color development result of the test strip after chromatography. The results of immunochromatography are usually read by the naked eye. If the concentration of certain antigens in some patient samples is low and the color development signal intensity is weak, it is difficult for the naked eye to accurately distinguish positive, negative, or weak positive results, which easily leads to subjective errors. Summary of the Invention

[0004] The present invention provides an immunochromatographic detection method and system for a clinical laboratory to solve the existing problems.

[0005] The immunochromatographic detection method and system of the present invention adopt the following technical solutions:

[0006] An embodiment of the present invention provides an immunochromatographic detection method for a clinical laboratory, and the method includes the following steps:

[0007] Obtain the observation area in the test strip image after immunochromatographic detection of the patient sample, and the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip;

[0008] Divide the observation area into several connected domains; determine the confidence level of each connected domain as a color development area according to the difference between the gray values of the pixel points in the connected domain; and screen out two color development areas according to the size of the confidence level of each connected domain as a color development area;

[0009] Determine the color development degree of each color development area according to the difference between the gray values of the pixel points in each color development area and the confidence level of the color development area; determine the chromatography result coefficient of the test strip according to the difference in color development degree and area difference between the color development areas, in combination with the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip.

[0010] Obtain the chromatographic result quantization value of the test strip based on the magnitude of the chromatographic result coefficient of the test strip and in combination with the color development degree of each color development region.

[0011] Further, the determination of the confidence level of each connected domain as a color development region includes the following specific steps:

[0012] Calculate the mean value of the gray values of all pixel points within each connected domain as the gray mean value of each connected domain;

[0013] Calculate the ratio of the gray mean value of each connected domain except the th connected domain to the gray mean value of the th connected domain, and take the sum value of the ratios of the gray mean values of all connected domains except the th connected domain to the gray mean value of the th connected domain as the first sum value;

[0014] Perform principal component analysis on the th connected domain to calculate several principal component vectors of the th connected domain;

[0015] For the th connected domain, calculate the cosine similarity between the maximum principal component vector and each principal component vector except the maximum principal component vector, and take the sum value of the cosine similarities between the maximum principal component vector and all principal component vectors except the maximum principal component vector as the second sum value;

[0016] Determine the confidence level of the th connected domain as a color development region based on the first sum value and the second sum value.

[0017] Further, the determination of the confidence level of the th connected domain as a color development region based on the first sum value and the second sum value includes the following specific steps:

[0018] Take the normalized value of the product of the first sum value and the second sum value as the confidence level of the th connected domain as a color development region.

[0019] Further, the screening of two color development regions based on the magnitude of the confidence level of each connected domain as a color development region includes the following specific steps:

[0020] Record the first two connected domains with the largest confidence levels as color development regions.

[0021] Further, the determination of the color development degree of each color development region includes the following specific steps:

[0022] In the th color development region, calculate the absolute value of the difference in gray values between any two pixel points, and record the sum of the absolute values of the differences in gray values between all pairs of pixel points as the third sum value;

[0023] Take the ratio of the confidence level of the th color development region as the color development region to the maximum value among the confidence levels of all connected regions as the color development region, and record it as the first ratio;

[0024] Determine the color development degree of the th color development region according to the first ratio and the third sum value.

[0025] Further, the step of determining the color development degree of the th color development region according to the first ratio and the third sum value includes the following specific steps:

[0026] Take the ratio of the first ratio to the third sum value and record it as the color development degree of the th color development region.

[0027] Further, the step of determining the chromatographic result coefficient of the test strip includes the following specific steps:

[0028] Calculate the absolute value of the difference in color development degrees between two color development regions as the first difference;

[0029] Calculate the ratio of the area of each color development region to the total imaging area of the designed color development areas of the test line and the quality control line on the actual test strip in the test strip image as the second ratio of each color development region;

[0030] Take the absolute value of the difference between the second ratios of two color development regions as the second difference;

[0031] Determine the chromatographic result coefficient of the test strip according to the first difference and the second difference.

[0032] Further, the step of determining the chromatographic result coefficient of the test strip according to the first difference and the second difference includes the following specific steps:

[0033] Take the normalized value of the product of the first difference and the second difference as the chromatographic result coefficient of the test strip.

[0034] Further, the step of obtaining the quantified value of the chromatographic result of the test strip includes the following specific steps:

[0035] When the chromatographic result coefficient of the test strip is less than the preset positive threshold, set the quantified value of the chromatographic result of the test strip to the preset second constant; the preset second constant is greater than or equal to the positive integer 1;

[0036] When the chromatographic result coefficient of the test strip is greater than or equal to the preset positive threshold, the color development region with the minimum color development degree is recorded as the target color development region; in the RGB three channels, calculate the average value of the brightness values of all pixel points in the target color development region in each channel as the value of each channel of the target color development region; calculate the average value of the RGB three-channel values of the target color development region as the first average value, and take the normalized value of the product of the color development degree of the target color development region and the first average value as the chromatographic result quantization value of the test strip.

[0037] The present invention also provides an immunochromatographic detection system for a clinical laboratory, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned immunochromatographic detection method for a clinical laboratory.

[0038] The beneficial effects of the technical solution of the present invention are:

[0039] In the embodiment of the present invention, the observation region in the test strip image after immunochromatographic detection of the patient sample is obtained, the observation region is divided into several connected domains, and two color development regions are screened out, so as to determine the chromatographic result coefficient of the test strip, and the chromatographic result quantization value of the test strip is obtained. Thus, the target color development region is screened by analyzing the image features of the chromatographic strip, and the chromatographic result is qualitatively analyzed according to the color development degree difference of different color development regions. Finally, quantitative analysis is carried out based on the color development characteristics of the test strip, so as to accurately measure the color development intensity of the color development region in numerical form, reduce the artificial subjective error, provide higher accuracy and consistency, and finally relevant preventive and treatment measures can be taken for the patient according to the chromatographic result of the test strip, improving the prevention and treatment efficiency of the disease. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0041] Figure 1 is the flowchart of the steps of an immunochromatographic detection method for a clinical laboratory according to the present invention;

[0042] Figure 2 is a schematic diagram of the test strip. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following will, in conjunction with the accompanying drawings and preferred embodiments, detail the specific implementation manner, structure, features and effects of an immunochromatographic detection method and system for a clinical laboratory department proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0045] The following will specifically describe the specific solution of an immunochromatographic detection method and system for a clinical laboratory department provided by the present invention in conjunction with the accompanying drawings.

[0046] Please refer to Figure 1 , which shows a step flow chart of an immunochromatographic detection method for a clinical laboratory department provided by an embodiment of the present invention. The method includes the following steps:

[0047] Step S001: Obtain the observation area in the test strip image after immunochromatographic detection of the patient sample, and the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip.

[0048] Fix a high-resolution camera above the observation platform, and use the high-resolution camera to collect the test strip image of the patient sample in the observation platform from directly above in a top-down view after immunochromatographic detection.

[0049] In the technical specifications of the test strip provided by the manufacturer, obtain the designed color development areas of the test line and the quality control line on the actual test strip, so as to obtain the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip.

[0050] It should be noted that: in this embodiment, the test strip image is an RGB image, and each pixel point in the test strip image corresponds to the brightness value in the three RGB channels. The test strip image is grayscale processed to obtain the grayscale value of each pixel point in the test strip image. Then, wavelet transform is used to denoise the test strip image to ensure that the image is clear and the color development lines can be accurately identified. Using the perspective projection principle, according to the basic parameters of the high-resolution camera (obtained from the instruction manual of the high-resolution camera) and the distance from the high-resolution camera to the test strip (the position of the high-resolution camera above the observation platform is fixed), the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip is obtained. Among them, image grayscale processing, wavelet transform and perspective projection principle are all well-known technologies, and the specific methods are not introduced here.

[0051] It should be further noted that: The immunochromatographic detection method is a rapid detection technology based on antigen-antibody reactions. Generally, a sample is first collected from a patient and added to the corresponding test strip. A schematic diagram of the test strip is shown as Figure 2 shown. Figure 2 As shown in Figure 2 , the test strip includes a sample pad, a bottom plate, a fluorescence pad, a shielding wire, a test line, a quality control line, a nitrocellulose membrane, and an absorbent pad. The chromatography direction is from the sample pad to the absorbent pad. Among them, the sample pad is used to absorb the sample and filter large particle impurities. The fluorescence pad (also known as the binding pad) contains dried labeled antibodies, commonly colloidal gold or fluorescent dyes. The test line and the quality control line are fixed with specific antibodies or antigens, which are used to capture target molecules (antigens or antibodies) in the sample. The absorbent pad is used to absorb excess liquid to ensure that the sample smoothly passes through the entire test strip. After the sample is added to the sample pad, it diffuses to the fluorescence pad by capillary action. The labeled antibodies on the fluorescence pad bind to the target antigen (or antibody) in the sample to form a complex. Then it continues to move forward through the detection area (the corresponding area of the nitrocellulose membrane). If the complex contains target molecules, they will be captured by the fixed antibodies in the detection area and show a color development result. If both the test line and the quality control line show color, it indicates that there are target molecules in the sample and the result is positive. If only the quality control line shows color and the test line does not show color, it indicates that there are no target molecules in the sample and the result is negative. If the quality control line does not show color, regardless of whether the test line shows color or not, it indicates that the detection is invalid, which may be due to insufficient sample or improper operation.

[0052] It can be seen from this Figure 2 that the detection area corresponding to the nitrocellulose membrane of the test strip in Figure 2 is the observation area. In the embodiments of the present invention, a segmentation neural network is used to identify and segment the observation area in the test strip image.

[0053] The relevant content of the segmentation neural network is as follows:

[0054] The segmentation neural network used in this embodiment is the Mask R-CNN neural network; the dataset used is the enhanced image dataset. Among them, Mask R-CNN is a well-known technology, and the specific method will not be introduced here. The Chinese full name of Mask R-CNN is "Mask Region-based Convolutional Neural Network", and the English full name is "Mask Region-based Convolutional Neural Network".

[0055] The pixel points to be segmented are divided into 2 categories. That is, the labeling process for the corresponding labels in the training set is: for the single-channel semantic label, the pixel points at the corresponding positions labeled as belonging to the background area are 0, and those labeled as belonging to the observation area are 1.

[0056] The task of the network is classification, so the loss function used is the cross-entropy loss function.

[0057] The observation area in the test strip image is obtained by splitting the neural network. This process is a well-known technology, and the specific method will not be introduced here.

[0058] Step S002: Divide the observation area into several connected regions; determine the confidence level of each connected region as a color development region according to the difference between the gray values of the pixel points within the connected region; screen out two color development regions according to the magnitude of the confidence level of each connected region as a color development region.

[0059] It should be noted that: Since the color development degree of the test strips corresponding to some patient samples is relatively light and the nature of the disease cannot be determined by the naked eye, it is necessary to perform qualitative analysis on the chromatography results based on the color development characteristics of the test strip image to determine the nature of the disease of the patients corresponding to different test strips. At the same time, quantitative analysis is performed on the chromatography results in combination with the color saturation of the color development region, so as to accurately measure the color development intensity of the color development region in the form of a numerical value, reduce the error of manual recognition, and provide a theoretical basis for the evaluation of the patient's condition.

[0060] Generally, the color development regions of the test strip are the test line and the quality control line regions, and other regions of the test strip will not develop color. When developing color, the color development regions generally appear as thin strips and have a darker gray scale than other regions. Therefore, all connected regions in the captured test strip image can be screened based on the above characteristics to obtain possible color development regions.

[0061] Preferably, in an embodiment of the present invention, the method for obtaining the color development region includes:

[0062] Use the region growing algorithm to divide in the observation area in the test strip image to obtain several connected regions.

[0063] Taking the th connected region in the observation area as an example, perform principal component analysis (PCA, Principal Component Analysis) on the th connected region, and calculate several principal component vectors of the th connected region.

[0064] It should be noted that: Both the region growing algorithm and the principal component analysis are well-known technologies, and the specific methods will not be introduced here. In this embodiment, the gray value of the pixel point is used as the basic value for the region growing and the principal component analysis.

[0065] Calculate the mean value of the gray values of all pixel points within each connected region as the gray mean value of each connected region.

[0066] Calculate the ratio of the gray mean value of each connected region except the th connected region to the gray mean value of the th connected region. Excluding the The sum of the ratios of the grayscale means of all connected components outside the th connected component to the grayscale mean of the

[0067] For the th connected component, calculate the cosine similarity between the maximum principal component vector and each principal component vector except the maximum principal component vector. The sum of the cosine similarities between the maximum principal component vector and all principal component vectors except the maximum principal component vector is used as the second sum value.

[0068] The normalized value of the product of the first sum value and the second sum value is used as the confidence level that the th connected component is a color-developing region.

[0069] It should be noted that: for the normalized value of the product of the first sum value and the second sum value, in this embodiment, a linear normalization function is used to normalize the product of the first sum value and the second sum value to the interval. Since the color-developing region of the test strip will show a darker color after meeting the relevant conditions, if the average grayscale of the th connected component is smaller than that of other connected components, that is, the first sum value is larger, then the th connected component is more likely to be a color-developing region. The cosine similarity between two vectors is a well-known calculation. The larger the cosine similarity, the closer the directions of the two vectors are. Since the regions that can show color are long strips for both the test line and the control line, then PCA can be used to perform principal component decomposition on the th connected component. Since the largest principal component vector represents the overall extension trend of the connected component, if the directions of other principal component vectors are more similar to the largest principal component vector, that is, the second sum value is larger, it means that the extension trend is more obvious, then the possibility that it is a long strip region is greater, and the confidence level that the corresponding th connected component is a color-developing region is greater.

[0070] In the observation region, the top two connected components with the largest confidence levels that are color-developing regions are recorded as color-developing regions.

[0071] It should be noted that: taking the preset color development threshold as 0.85 and the preset first constant as 0 as an example for description. If the confidence levels of the two color development regions are both less than 0.85, it indicates that no conforming color development region is found in the test strip image, and it is determined that the chromatography result of the test strip is invalid. If only one of the confidence levels of the two color development regions is greater than or equal to 0.85, it indicates that there is only one true color development region in the test strip image, that is, the test result is negative, indicating that the sample does not contain the target molecule. Thus, the quantization value of the chromatography result of the test strip is set to the preset first constant 0. If the confidence levels of the two color development regions are both greater than or equal to 0.85, it indicates that there are two true color development regions in the test strip image. Generally, if there are two color development regions in the test strip image, the chromatography result is considered positive. At this time, further quantitative analysis of the positive result is required.

[0072] Step S003: Determine the color development degree of each color development region according to the difference between the gray values of the pixel points within each color development region and the confidence level of the non-color development region; according to the difference in color development degree and area difference between the color development regions, combined with the total imaging area of the designed color development areas of the test line and the quality control line on the actual test strip in the test strip image, determine the chromatography result coefficient of the test strip.

[0073] It should be noted that: due to the low antigen concentration of the patient sample, the actual chromatography result may show that the color development region is not as obvious and thick as that of the positive reaction, that is, although the color development of the test line is visible, it may be blurred, the edge is not clear or the color development is light, resulting in a weak positive result, which is prone to misjudgment when evaluated by the naked eye. Then, in order to more accurately evaluate the chromatography result, it is necessary to determine the corresponding color development degree for all color development regions, and then compare the color development degree differences of different color development regions to determine the chromatography result.

[0074] Since both weak positive and positive will have two color development regions, but the color depth of the color development region of the positive is deeper and more uniform, while the color depth of the color development region of the weak positive is shallower and uneven in depth, so the pixel gray uniformity of different color development regions can be analyzed for measurement. At the same time, the confidence level includes the overall color depth situation of the region. Therefore, the corresponding color development degree can be calculated for the color development region corresponding to the test strip image based on the above factors.

[0075] Preferably, in an embodiment of the present invention, the method for obtaining the chromatography result coefficient of the test strip includes:

[0076] Taking the th color development region in the observation region as an example, within the th color development region, calculate the absolute value of the difference between the gray values of any two pixel points, and record the sum value of the absolute values of the differences between the gray values of all any two pixel points as the third sum value.

[0077] The ratio of the confidence level of the th color display area to the maximum value of the confidence levels of all connected regions as color display areas is denoted as the first ratio. The ratio of the first ratio to the third sum value is denoted as the color display degree of the

[0078] It should be noted that: the smaller the third sum value, the more uniform the gray levels of the pixel points in the th color display area, and the greater the corresponding color display degree. And the greater the first ratio, the deeper the color depth of the th color display area, and then the greater the corresponding color display degree.

[0079] Thus, the corresponding color display degrees are obtained for all color display areas in the test strip image. Since the chromatography results may be positive, negative, and weakly positive, and there are differences in the color display degrees between weakly positive and positive on the test line, it is necessary to perform qualitative analysis on the chromatography results based on the color display degrees of different color display areas in the test strip image next.

[0080] The positive and negative of the chromatography results can be directly distinguished by the number of color display areas. There are differences in the color display degrees between positive and weakly positive, but there is no accurate distinguishing method. Therefore, it is necessary to perform qualitative analysis on the two results next. Generally, the positive chromatography result shows that the color display effects of the test line and the control line are clear and relatively deep, and both can fill the entire designed color display area. The color of the weakly positive test line is very light and cannot fill the entire designed color display area, but the control line is still clearly displayed. Therefore, it can be distinguished based on the color display degrees of different color display areas.

[0081] In the observation area, calculate the absolute value of the difference between the color display degrees of two color display areas as the first difference. Calculate the ratio of the area of each color display area to the total imaging area of the designed color display areas of the test line and the control line on the actual test strip in the test strip image as the second ratio of each color display area. Calculate the absolute value of the difference between the second ratios of the two color display areas as the second difference. Calculate the normalized value of the product of the first difference and the second difference as the chromatography result coefficient of the test strip.

[0082] It should be noted that: for the normalized value of the product of the above first difference and second difference, in this embodiment, a linear normalization function is used to normalize the product of the first difference and the second difference to Within the range. Since the color development degree of the test line for weak positive is smaller than that of the quality control line, the greater the first difference, the greater the possibility that the chromatographic result of this test strip is weak positive, and vice versa, the greater the possibility of positive. Since the test line for weak positive cannot fill the entire designed color development area, the greater the value of the second difference corresponding to weak positive, and vice versa, the smaller the value of the second difference corresponding to the positive result. Therefore, the greater the chromatographic result coefficient, the more likely it is to be weak positive.

[0083] Step S004: According to the magnitude of the chromatographic result coefficient of the test strip and in combination with the color development degree of each color development area, obtain the quantified value of the chromatographic result of the test strip.

[0084] Taking the preset positive threshold as 0.75 and the preset second constant as 1 as an example for description.

[0085] When the chromatographic result coefficient of the test strip is less than the preset positive threshold, it is determined that the immunochromatographic test is positive, and the quantified value of the chromatographic result of the test strip is set as the preset second constant 1.

[0086] When the chromatographic result coefficient of the test strip is greater than or equal to the preset positive threshold, it is determined that the immunochromatographic test is weak positive.

[0087] It should be noted that: the above conducts a qualitative analysis on the positive and weak positive of the chromatographic result, but weak positive only shows that the color development degree of the test line is relatively light, but still there is no way to measure how light it is, so there is a certain subjectivity in the observation results of different people. Therefore, it is necessary to conduct a quantitative analysis on the chromatographic result through specific values to assist relevant personnel in the assessment of the condition.

[0088] Since the positive and weak positive can be distinguished by the chromatographic result coefficient, then for different weak positive chromatographic results, due to the difference in color development degree, here the color development area with the lower color development degree can be set as the target color development area, that is, the color development area of the test line, and a quantitative analysis is carried out according to the proportion of its color channels.

[0089] In the observation area, the color development area with the smallest color development degree is recorded as the target color development area.

[0090] In the RGB three channels, calculate the average value of the brightness values of all pixel points in the target color development area in each channel as the value of each channel of the target color development area.

[0091] Calculate the average value of the RGB three-channel values of the target color development area as the first average value, and take the normalized value of the product of the color development degree of the target color development area and the first average value as the quantified value of the chromatographic result of the test strip.

[0092] It should be noted that: in this embodiment, the normalization value of the product of the color development degree of the above-mentioned target color development region and the first mean value is used a linear normalization function to normalize the product of the color development degree of the target color development region and the first mean value to the interval. The magnitude of the first mean value reflects the color depth saturation of the target color development region. Since the larger the color channel value of the target color development region, the greater the corresponding color saturation, it indicates that the color development effect of the target color development region is better, that is, the quantification value of weak positive is larger. At the same time, combined with the color development degree of the target color development region, that is, the greater the color development degree and color saturation, the better the color development effect of the target color development region, and the greater the quantification value of weak positive of the test strip.

[0093] Thus, through the above method, qualitative analysis is carried out on different test strip chromatography results, different types of chromatography results are distinguished by means of machine vision, and the chromatography results are specifically quantified numerically, reducing the artificial subjective error. Then the subsequent relevant staff can assist in the diagnosis and prevention and treatment of the patient's condition based on the quantification results.

[0094] It should be noted that: in this embodiment, when calculating the ratio, if the denominator of the ratio is 0, the denominator is set to 1 to ensure the establishment of the ratio, and this is used as an example for description.

[0095] The present invention also provides an immunochromatographic detection system for a clinical laboratory, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the above-mentioned immunochromatographic detection method for a clinical laboratory.

[0096] So far, the present invention is completed.

[0097] In summary, in the embodiment of the present invention, the observation region in the test strip image after immunochromatographic detection of the patient sample is obtained, the observation region is divided into several connected regions, the confidence level of each connected region as a color development region is determined to screen out two color development regions, the color development degree of each color development region is obtained, and according to the difference in color development degree and area difference between the color development regions, the chromatography result coefficient of the test strip is determined, so as to obtain the quantification value of the chromatography result of the test strip. The present invention qualitatively and quantitatively analyzes the chromatography result by analyzing the existence of different color development regions on the test strip after chromatography and the difference in color development degree, and thus takes corresponding preventive and treatment measures, improving the accuracy of chromatography result detection and the prevention and treatment efficiency of the disease.

[0098] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An immunochromatographic detection method for a clinical laboratory, characterized in that, The method includes the following steps: Obtain the observation area in the test strip image after immunochromatographic detection of a patient sample, and the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip; Divide the observation area into a number of connected regions; determine the confidence level of each connected region as a color development region according to the difference between the gray values of the pixel points within the connected region; screen out two color development regions according to the magnitude of the confidence level of each connected region as a color development region; Among them, the method for determining the confidence level is as follows: calculate the mean value of the gray values of all pixel points in each connected region as the gray mean value of each connected region; calculate the ratio of the gray mean value of each connected region except the th connected region to the gray mean value of the th connected region, and take the sum of the ratios of the gray mean values of all connected regions except the th connected region to the gray mean value of the th connected region as the first sum value; perform principal component analysis on the th connected region to calculate several principal component vectors of the th connected region; for the th connected region, calculate the cosine similarity between the maximum principal component vector and each principal component vector except the maximum principal component vector, and take the sum of the cosine similarities between the maximum principal component vector and all principal component vectors except the maximum principal component vector as the second sum value; take the normalized value of the product of the first sum value and the second sum value as the confidence level that the th connected region is a color display region; Determine the color development degree of each color development region according to the difference between the gray values of the pixel points within each color development region and the confidence level as a color development region; determine the chromatographic result coefficient of the test strip according to the difference in color development degree and area difference between the color development regions, in combination with the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip; Obtain the quantitative value of the chromatographic result of the test strip according to the magnitude of the chromatographic result coefficient of the test strip, in combination with the color development degree of each color development region.

2. The immunochromatographic detection method for a clinical laboratory according to claim 1, wherein The screening out of two color development regions according to the magnitude of the confidence level of each connected region as a color development region includes the following specific steps: Denote the top two connected regions with the highest confidence levels as color development regions.

3. The immuno-chromatographic detection method for the inspection department according to claim 1, wherein, The determination of the color development degree of each color development region includes the following specific steps: In the th color display area, calculate the absolute value of the difference in gray values between any two pixel points, and record the sum of the absolute values of the differences in gray values between all pairs of pixel points as the third sum value; Take the ratio of the confidence level of the th color display area as the color display area to the maximum value of the confidence levels of all connected regions as the color display area, and denote it as the first ratio; Determine the coloring degree of the coloring area according to the first ratio and the third sum value.

4. The immunochromatographic detection method for a clinical laboratory according to claim 3, wherein Determining the color rendering degree of the nth color rendering region based on the first ratio and the third sum value, includes the following specific steps: The ratio of the first ratio to the third sum value is denoted as the color development degree of the nth color development region.

5. The immuno-chromatographic detection method for a clinical laboratory according to claim 1, characterized in that, The determination of the chromatographic result coefficient of the test strip includes the following specific steps: Calculate the absolute value of the difference in color development degree between the two color development regions as the first difference; Calculate the ratio of the area of each color development region to the total imaging area in the test strip image of the designed color development areas of the test line and the quality control line on the actual test strip as the second ratio of each color development region; Calculate the absolute value of the difference in the second ratios of the two color development regions as the second difference; Determine the chromatographic result coefficient of the test strip according to the first difference and the second difference.

6. The immunochromatographic detection method for the inspection department according to claim 5, characterized in that, The determination of the chromatographic result coefficient of the test strip according to the first difference and the second difference includes the following specific steps: Take the normalized value of the product of the first difference and the second difference as the chromatographic result coefficient of the test strip.

7. The immunochromatographic detection method for the inspection department according to claim 1, characterized in that, The obtaining of the quantitative value of the chromatographic result of the test strip includes the following specific steps: When the chromatographic result coefficient of the test strip is less than the preset positive threshold, set the quantitative value of the chromatographic result of the test strip to the preset second constant; the preset second constant is greater than or equal to the positive integer 1; When the chromatographic result coefficient of the test strip is greater than or equal to the preset positive threshold, denote the color development region with the smallest color development degree as the target color development region; In the RGB three channels, calculate the mean value of the brightness values of all pixel points within the target color development region in each channel as the value of each channel of the target color development region; Calculate the mean value of the RGB three-channel values of the target color development region as the first mean value, and take the normalized value of the product of the color development degree of the target color development region and the first mean value as the quantitative value of the chromatographic result of the test strip.

8. An immunochromatographic detection system for a clinical laboratory department, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by a processor, it implements the steps of an immunochromatographic detection method for a clinical laboratory as described in any one of claims 1-7.

Images