CN113435444A - Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment - Google Patents

Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment Download PDF

Info

Publication number
CN113435444A
CN113435444A CN202110729178.XA CN202110729178A CN113435444A CN 113435444 A CN113435444 A CN 113435444A CN 202110729178 A CN202110729178 A CN 202110729178A CN 113435444 A CN113435444 A CN 113435444A
Authority
CN
China
Prior art keywords
quality control
region
image
gray
control line
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110729178.XA
Other languages
Chinese (zh)
Other versions
CN113435444B (en
Inventor
郭文胜
杨海
陈海梅
王海林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huazhong University of Science and Technology
GBA National Institute for Nanotechnology Innovation
Original Assignee
Huazhong University of Science and Technology
GBA National Institute for Nanotechnology Innovation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huazhong University of Science and Technology, GBA National Institute for Nanotechnology Innovation filed Critical Huazhong University of Science and Technology
Priority to CN202110729178.XA priority Critical patent/CN113435444B/en
Publication of CN113435444A publication Critical patent/CN113435444A/en
Application granted granted Critical
Publication of CN113435444B publication Critical patent/CN113435444B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
    • G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
    • G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
    • G01N33/558—Immunoassay; Biospecific binding assay; Materials therefor using diffusion or migration of antigen or antibody
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Hematology (AREA)
  • Urology & Nephrology (AREA)
  • Chemical & Material Sciences (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Molecular Biology (AREA)
  • Microbiology (AREA)
  • Cell Biology (AREA)
  • Biotechnology (AREA)
  • Food Science & Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides an immunochromatography detection method, a device, a storage medium and computer equipment, which are characterized in that firstly, an interested region of a quality control line and an interested region of a test line in a gray level image are determined, then, each interested region is respectively subjected to superpixel segmentation, and a plurality of superpixels obtained after the superpixel segmentation are clustered to obtain a clustered gray level image.

Description

Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment
Technical Field
The invention relates to the technical field of immunochromatography detection, in particular to an immunochromatography detection method, an immunochromatography detection device, a storage medium and computer equipment.
Background
Immunochromatography is a rapid immunoassay technology developed in the early eighties of the last century, and achieves the purpose of detection by generating antigen-antibody binding reaction in the process of chromatography. Because the operation is simple and rapid, the personnel do not need training, and do not need or only need advantages such as simple instrument, etc., the device is widely applied to a plurality of fields such as food detection, drug detection, environmental monitoring, clinical diagnosis, etc. The existing immunochromatography detection mainly comprises qualitative detection and quantitative detection, wherein the qualitative detection can determine whether an object to be detected is negative or positive, and the quantitative detection can determine the concentration of the object to be detected.
Therefore, it is necessary to provide a quantitative method for detecting the concentration of an analyte, so that the detection result of the concentration of the analyte is more accurate.
Disclosure of Invention
The present invention is directed to at least solve one of the above technical drawbacks, and particularly to a technical drawback that the prior art lacks a quantitative detection method for detecting the concentration of an analyte, so that the detection result of the concentration of the analyte is relatively accurate.
The invention provides an immunochromatography detection method, which comprises the following steps:
acquiring a gray image corresponding to an immunochromatographic test strip image of an object to be detected;
determining an interested region of a quality control line and an interested region of a test line in the gray level image;
respectively carrying out superpixel segmentation on each region of interest, and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image;
determining the characteristic values of the test line and the quality control line based on the clustered gray level image;
and determining the quantitative concentration of the object to be detected based on the respective characteristic values of the test line and the quality control line.
Optionally, the step of determining a region of interest of a quality control line and a region of interest of a test line in the gray-scale image includes:
carrying out similarity matching on the gray value in the gray image based on a set template to obtain a corresponding matching coefficient curve, wherein the abscissa of the matching coefficient curve is the position of the first row of the set template in the pixel row of the gray image, and the ordinate of the matching coefficient curve is the similarity of the overlapping area of the gray image and the set template;
determining whether a quality control line and a test line in the gray level image exist according to the matching coefficient curve;
if so, determining the interested region of the quality control line and the interested region of the test line in the gray level image based on the matching coefficient curve.
Optionally, the step of determining whether both a quality control line and a test line in the grayscale image exist according to the matching coefficient curve includes:
dividing the matching coefficient curve into a left area and a right area from the middle;
determining the peak height and the peak width of each peak in the left area and the right area based on the matching coefficient curve;
determining whether a peak with a peak height meeting the set peak height and a peak width meeting the set peak width exists in the left area and the right area;
and if the peaks meeting the conditions exist in the left area and the right area, determining that the quality control line and the test line in the gray level image both exist.
Optionally, after the step of determining whether both a quality control line and a test line in the grayscale image exist according to the matching coefficient curve, the method further includes:
and if the quality control line exists and the test line does not exist, determining a qualitative result corresponding to the object to be tested according to the type of the immunochromatography test paper card.
Optionally, the step of determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image based on the matching coefficient curve includes:
and determining a pixel interval of the quality control line and a pixel interval of the test line in the gray-scale image based on the peak with the peak height meeting the set peak height and the peak width meeting the set peak width in the left area and the right area, taking the pixel interval of the quality control line as the interested area of the quality control line, and taking the pixel interval of the test line as the interested area of the test line.
Optionally, the step of respectively performing superpixel segmentation on each region of interest, and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image includes:
respectively carrying out superpixel segmentation on each interested region based on set parameters to obtain a plurality of superpixels corresponding to each interested region;
determining a pixel point corresponding to each super pixel in the gray image, and the gray value of the pixel point and a pixel row where the pixel point is located;
determining a characteristic value corresponding to each super pixel based on the gray value of the pixel point and the pixel row where the pixel point is located;
and clustering the super pixels respectively based on the characteristic values to obtain a clustered gray level image.
Optionally, the step of determining the respective characteristic values of the test line and the quality control line based on the clustered grayscale images includes:
carrying out binarization on the clustered gray level image to obtain a binarized image; the binary image comprises a quality control line region, a test line region and a background region;
determining the number of pixel points and the pixel value of the quality control line region, the number of pixel points and the pixel value of the test line region, and the number of pixel points and the pixel value of the background region based on the gray level image and the binary image;
and determining the characteristic value of the quality control line region and the characteristic value of the test line region based on the number and the value of the pixel points of the quality control line region, the number and the value of the pixel points of the test line region, and the number and the value of the pixel points of the background region.
The invention also provides an immunochromatography detection device, comprising:
the image acquisition module is used for acquiring a gray image corresponding to the immunochromatography test strip image of the object to be detected;
the area determination module is used for determining an interested area of a quality control line and an interested area of a test line in the gray level image;
the segmentation and clustering module is used for respectively performing superpixel segmentation on each region of interest and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image;
the characteristic value determining module is used for determining the respective characteristic values of the test line and the quality control line based on the clustered gray level images;
and the concentration determination module is used for determining the quantitative concentration of the object to be detected based on the respective characteristic values of the test line and the quality control line.
The present invention also provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method as described in any one of the above embodiments.
The invention also provides a computer device having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method as in any one of the above embodiments.
According to the technical scheme, the embodiment of the invention has the following advantages:
the invention provides an immunochromatography detection method, a device, a storage medium and computer equipment, which are characterized in that firstly, an interested region of a quality control line and an interested region of a test line in a gray level image are determined, then, each interested region is respectively subjected to superpixel segmentation, and a plurality of superpixels obtained after the superpixel segmentation are clustered to obtain a clustered gray level image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a schematic flow chart of an immunochromatographic assay provided in an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an immunochromatographic test strip card and an immunochromatographic test strip provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of the image processing process of the sandwich method new crown antibody detection colloidal gold immunochromatographic test strip card provided in the embodiment of the present invention;
FIG. 4 is a schematic diagram of an image processing process of a competitive vomiting toxin colloidal gold immunochromatographic test strip card according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the competitive zearalenone colloidal gold immunochromatographic strip card image processing process according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of an immunochromatographic detection device according to an embodiment of the present invention;
fig. 7 is a schematic internal structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Immunochromatography is a rapid immunoassay technology developed in the early eighties of the last century, and achieves the purpose of detection by generating antigen-antibody binding reaction in the process of chromatography. Because the operation is simple and rapid, the personnel do not need training, and do not need or only need advantages such as simple instrument, etc., the device is widely applied to a plurality of fields such as food detection, drug detection, environmental monitoring, clinical diagnosis, etc. The existing immunochromatography detection mainly comprises qualitative detection and quantitative detection, wherein the qualitative detection can determine whether an object to be detected is negative or positive, and the quantitative detection can determine the concentration of the object to be detected.
Therefore, it is necessary to provide a quantitative detection method for detecting the concentration of an analyte, so that the detection result of the concentration of the analyte is relatively accurate, specifically referring to the following scheme:
in one embodiment, as shown in fig. 1, fig. 1 is a schematic flow chart of an immunochromatography detection method provided in an embodiment of the present invention; the invention provides an immunochromatography detection method, which specifically comprises the following steps:
s110: and obtaining a gray image corresponding to the immunochromatographic test strip image of the object to be detected.
In this step, when detecting the analyte, the immunochromatography can be used to qualitatively and/or quantitatively detect the analyte, and then the immunochromatography test strip image corresponding to the analyte is obtained.
It is understood that the immunochromatography method refers to that a specific antibody is firstly fixed to a certain zone of a nitrocellulose membrane, after one end of dried nitrocellulose is immersed into a sample (urine or serum), the sample moves forward along the nitrocellulose membrane due to capillary action, when the sample moves to a region where the antibody is fixed, a corresponding antigen in the sample specifically binds to the antibody, and if the sample is stained with immune colloidal gold or immune enzyme, the region can show a certain color, thereby realizing specific immunodiagnosis.
Schematically, as shown in fig. 2, fig. 2 is a schematic structural diagram of an immunochromatographic test strip card and an immunochromatographic test strip provided in an embodiment of the present invention; wherein, the chart (a) is a structure chart of the immunochromatography test paper card, and the immunochromatography test paper card comprises 5 parts: 1-immunochromatography test paper card to be tested, 2-sample hole, 3-observation window, 4-quality control line and 5-test line; and (b) is a structural diagram of the immunochromatographic test strip, the immunochromatographic test strip is placed in a clamping groove of the immunochromatographic test strip card, and a test line and a quality control line on the immunochromatographic test strip can be observed through an observation window.
When the object to be detected needs to be detected, the object to be detected can be dripped into a sample hole of the immunochromatography test paper card for detection. For example, when detecting whether serum to be detected contains the new crown antibody, the serum to be detected can be dripped on a sample hole of the sandwich method new crown antibody detection colloidal gold immunochromatographic test paper card, after waiting for 5 minutes, the sandwich method new crown antibody detection colloidal gold immunochromatographic test paper card starts to develop color, and at the moment, an original image of a quality control line and a test line observed through an observation window can be captured through an image acquisition device, namely, an immunochromatographic test paper strip image in the application.
Because the obtained immunochromatography test strip image is a color image, in order to better confirm the quality control line and/or the area where the test line is located in the immunochromatography test strip image and obtain an accurate qualitative detection result and/or quantitative detection result, the immunochromatography test strip image can be converted from the color image into a gray image, whether the quality control line and the test line exist is judged by determining the specific position of the quality control line and/or the test line in the gray image, and then a corresponding qualitative detection result and/or quantitative detection result is given.
S120: and determining the interested area of the quality control line and the interested area of the test line in the gray level image.
In this step, after the gray level image corresponding to the immunochromatographic test strip image is obtained in step S110, if the object to be detected is to be quantitatively detected, the region of interest of the quality control line and the region of interest of the test line in the gray level image may be determined, and then the region of interest of the quality control line and the region of interest of the test line are correspondingly processed, so that the characteristic value corresponding to each region can be obtained, and the quantitative concentration of the object to be detected can be obtained.
It can be understood that the region of interest refers to selecting a certain image region from an image, and using the image region as a focus point to be focused in subsequent analysis, and after the image region is defined and further processed, not only the image processing time can be reduced, but also the image processing accuracy can be increased.
Further, when determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image, the gray-scale image may be precisely located using a template matching algorithm, so as to obtain the region of interest of the quality control line and the region of interest of the test line.
Wherein, the general processing steps of the template matching algorithm may include: 1. defining a template matching area; 2. carrying out template matching; 3. correcting a preset ROI according to a template matching result; 4. image processing is performed in the ROI.
Template matching algorithms include, but are not limited to, those based on gray-scale values, shapes, feature points, etc. For example, the gray-value-based template matching algorithm mainly calculates the absolute value or the sum of squares of the differences between the template and the image; the template matching algorithm based on the shape mainly takes the gradient correlation of the edge of an object as a matching criterion, can effectively deal with various linear and nonlinear illumination changes, has very strong resistance to shielding and partial deletion, and is most widely applied to practical engineering application.
It can be understood that, when determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image, the determination may also be performed through other algorithms or functions, for example, using the cvsetImageROI function to extract the region of interest of the quality control line and the region of interest of the test line in the gray-scale image, which is not limited herein.
S130: and respectively carrying out superpixel segmentation on each region of interest, and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image.
In this step, after the region of interest of the quality control line and the region of interest of the test line in the gray scale image are determined in step S120, the region of interest of the quality control line and the region of interest of the test line may be respectively subjected to superpixel segmentation, and then a plurality of superpixels obtained after the superpixel segmentation of each region of interest are clustered, so as to obtain a clustered gray scale image.
Superpixel segmentation herein refers to the process of tagging each superpixel in an image such that pixels with the same tag possess some common visual characteristic. The result of superpixel segmentation is a set of sub-regions on the image (the totality of these sub-regions covers the entire image), or a set of contour lines extracted from the image (e.g., edge detection).
It will be appreciated that the individual superpixels in the individual sub-regions are similar under some measure of property, or a calculated property, such as color, brightness, texture, etc., and that the adjacent regions may differ significantly under some measure of property.
According to the method, after the super-pixel segmentation is carried out on each region of interest, a plurality of super-pixels in each region of interest can be obtained, for each super-pixel, a pixel point of each super-pixel in a gray image can be determined, the gray value of the pixel point and a pixel line where the pixel point is located can be determined, then the characteristic value of each super-pixel is determined according to the gray value of the pixel point corresponding to each super-pixel and the pixel line where the pixel point is located, then the super-pixels are clustered according to the characteristic value of each super-pixel, and finally the clustered gray image is obtained.
It should be noted that, in each super pixel obtained by super pixel segmentation of each region of interest, the number of corresponding pixel points in the gray image of each super pixel is at least one, and may be multiple, and when the number of corresponding pixel points in the gray image of each super pixel is multiple, the gray average of multiple pixel points and the row number average of pixel rows where all the pixel points are located can be taken as the characteristic value of the super pixel.
In addition, when clustering is carried out on each super-pixel in each region of interest, a clustering algorithm, such as a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering algorithm and the like, can be used, each super-pixel in each region of interest is clustered by selecting a proper clustering algorithm, and finally the position of a quality control line and a test line in the gray level image can be more clearly expressed.
S140: and determining the respective characteristic values of the test line and the quality control line based on the clustered gray level image.
In this step, each region of interest is respectively subjected to superpixel segmentation in step S130, and a plurality of superpixels obtained after the superpixel segmentation are clustered to obtain a clustered gray image, and then the characteristic value of the test line and the characteristic value of the quality control line in the gray image can be determined through the clustered gray image.
The characteristic value of the test line refers to the gray level mean value of all pixel points in the test line area in the gray level image and the line number mean value of pixel rows in which all the pixel points are located in the test line area; the characteristic value of the quality control line refers to the gray level mean value of all pixel points in a quality control line area in the gray level image and the line number mean value of pixel rows in which all the pixel points in the quality control line area are located.
It can be understood that the test line region and the quality control line region in the gray-scale image include a plurality of pixel points, and therefore, for determining the characteristic values of the test line region and the quality control line region, the characteristic value of the test line and the characteristic value of the quality control line need to be determined by combining the number of pixel points in the test line region and the quality control line region, the gray-scale value corresponding to each pixel point, and the pixel row in which each pixel point is located.
Further, before determining the characteristic value of the test line and the characteristic value of the quality control line in the clustered gray-scale image, binarization processing can be performed on the clustered gray-scale image to obtain a binarized image corresponding to the clustered gray-scale image. When determining the characteristic value of the test line and the characteristic value of the quality control line in the gray-scale image, the binarized numerical value corresponding to the pixel point of the test line region, the binarized numerical value corresponding to the pixel point of the quality control line region, and the binarized numerical value corresponding to the pixel point of the background region in the binarized image may be referred to. The characteristic value of the test line and the characteristic value of the quality control line obtained by calculation can reflect the characteristics of the test line and the quality control line more accurately.
S150: and determining the quantitative concentration of the object to be detected based on the respective characteristic values of the test line and the quality control line.
In this step, after determining the respective characteristic values of the test line and the quality control line based on the clustered gray scale image in step S140, the quantitative concentration of the analyte may be determined based on the respective characteristic values of the test line and the quality control line.
For example, after obtaining the characteristic value of the test line and the characteristic value of the quality control line, the ratio between the characteristic value of the test line and the characteristic value of the quality control line may be determined, and then, a concentration value corresponding to a point equal to the characteristic value of the immunochromatographic test strip card is found in the characteristic value-concentration standard curve of the object to be tested, where the concentration value is the quantitative concentration of the object to be tested.
The method for obtaining the characteristic value-concentration standard curve of the object to be detected can be as follows: firstly, respectively detecting n kinds of solutions with known concentration of the object to be detected by using n immunochromatographic test paper cards which are the same as the immunochromatographic test paper cards of the object to be detected, wherein n is a natural number between 4 and 10; then obtaining characteristic values TV, CV and TC in the same way as the immunochromatography test paper card of the object to be detected; and finally fitting to obtain a standard curve of the TC value and the concentration of the substance to be detected.
It should be noted that, here, TV refers to a characteristic value of the test line, CV refers to a characteristic value of the quality control line, and TC refers to a ratio between the characteristic value of the test line and the characteristic value of the quality control line.
In the above embodiment, the region of interest of the quality control line and the region of interest of the test line in the gray level image are determined, then the superpixel segmentation is performed on each region of interest, and the multiple superpixels obtained after the superpixel segmentation are clustered to obtain the clustered gray level image.
The above embodiments describe the immunochromatography detection method in the present application, and how to determine the region of interest of the quality control line and the region of interest of the test line in the gray-scale image in detail will be described below.
In one embodiment, the step of determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image in step S120 may include:
s121: and performing similarity matching on the gray value in the gray image based on a set template to obtain a corresponding matching coefficient curve, wherein the abscissa of the matching coefficient curve is the position of the first row of the set template in the pixel row of the gray image, and the ordinate of the matching coefficient curve is the similarity of the overlapping area of the gray image and the set template.
S122: and determining whether the quality control line and the test line in the gray level image exist according to the matching coefficient curve, and if so, executing the step S123.
S123: and determining the interested region of the quality control line and the interested region of the test line in the gray level image based on the matching coefficient curve.
In this step, when performing similarity matching on the gray values in the gray image, a set template may be used to perform template matching, so as to obtain a corresponding matching coefficient curve.
For example, if the length of the immunochromatographic strip image obtained in the present application is L and the width thereof is W, the corresponding template length TL [ L/20] × 2+1 ("[ ]" indicates a rounding), the width TW of the template is W, and then the corresponding template, i.e., the setting template in the present application, is constructed according to the length and the width of the template.
It should be noted that, because the quality control lines, the test lines and the backgrounds of different types of immunochromatographic test paper cards are set differently, different types of immunochromatographic test paper cards correspond to different template formulas. For example, the corresponding template formula of the colloidal gold immunochromatographic test paper card is as follows:
Figure BDA0003138689480000101
the corresponding template formula of the fluorescence immunochromatographic test paper card is as follows:
Figure BDA0003138689480000102
and T (i, j) is the gray value corresponding to the pixel point with the coordinate (i, j) in the template.
Then, the gray level image is subjected to template matching by using a set template, and when the gray level image is matched, the gray level image can be subjected to normalization processing, wherein the formula is as follows:
Figure BDA0003138689480000111
wherein G (u, v) is a gray value corresponding to a pixel point with coordinates (u, v) in the gray image, GnewAnd (u, v) is a gray value corresponding to the pixel point with the coordinate (u, v) in the normalized gray image.
After the gray image is normalized, the setting template can be placed at the top end of the gray image, then the setting template is moved downwards along the vertical direction, the matching coefficient between the gray values of all pixel rows corresponding to the overlapped part of the setting template and the gray image is calculated every time the setting template is moved once, when the setting template is moved to the bottom end of the gray image, the matching coefficient curve between the setting template and the gray image is obtained, and the calculation formula of the matching coefficient curve is as follows:
Figure BDA0003138689480000112
wherein, f (x) is a matching coefficient curve, the abscissa in the matching coefficient curve is x, x refers to the position of the first row of the setting template in the pixel row of the grayscale image, and the ordinate is f (x), that is, the similarity of the overlapping area of the grayscale image and the setting template after each movement.
After the matching coefficient curve is obtained through calculation, whether the quality control line and the test line in the gray level image exist or not can be determined according to the matching coefficient curve, and if yes, the interested region of the quality control line and the interested region of the test line in the gray level image are determined based on the matching coefficient curve.
In addition, before the grayscale image is subjected to template matching, the position of the grayscale image can be subjected to tilt correction, so that when the grayscale image is subjected to similarity matching through the setting template, the relationship between the grayscale image and the setting template is vertically set, and the division accuracy of the region of interest of the quality control line and the region of interest of the test line in the grayscale image is improved.
The above embodiment describes in detail how to determine the region of interest of the quality control line and the region of interest of the test line in the gray scale image in the present application, and the following describes in detail how to determine whether both the quality control line and the test line in the gray scale image exist according to the matching coefficient curve in the present application.
In one embodiment, the step of determining whether the quality control line and the test line in the grayscale image exist according to the matching coefficient curve in step S122 may include:
s221: and dividing the matching coefficient curve into a left area and a right area from the middle.
S222: and determining the peak height and the peak width of each peak in the left area and the right area based on the matching coefficient curve.
S223: it is determined whether there are peaks in the left and right regions whose peak heights satisfy the set peak height and peak widths satisfy the set peak width, and if so, step S224 is performed.
S224: and determining that both a quality control line and a test line exist in the gray level image.
In this embodiment, since the grayscale image is converted from the original image obtained from the immunochromatographic test paper card, if the immunochromatographic test paper card includes a test line portion and a quality control line portion which are separated from each other, the grayscale image also includes a test line portion and a quality control line portion, the test line portion and the quality control line portion are located in an upper half portion and a lower half portion of the grayscale image, respectively, and when the grayscale image is subjected to similarity matching using the setting template, the setting template is moved from the top end of the grayscale image to the bottom end of the grayscale image. Therefore, when determining whether the quality control line and the test line both exist in the gray-scale image according to the matching coefficient curve, the matching coefficient curve can be divided into a left region and a right region from the middle, the left half part is an interested region where the test line may exist, and the right half part is an interested region where the quality control line may exist.
After an interesting area possibly existing in a test line and an interesting area possibly existing in a quality control line in a matching coefficient curve are determined, the peak height and the peak width of each peak in the left area and the right area can be determined based on the matching coefficient curve, whether a peak with the peak height meeting the set peak height and the peak width meeting the set peak width exists in the left area and the right area is judged, and if a peak with the peak height meeting the set peak height and the peak width meeting the set peak width exists, the fact that both the quality control line and the test line exist in the gray level image is indicated.
For example, the peak height of each peak in the left and right two regions can be found through the matching coefficient curve, the peak five before the peak height is obtained, then the peak height and the peak width corresponding to the peak five before the peak height are sequentially compared with the set peak height and the set peak width, and if the peak with the peak height meeting the set peak height and the peak width meeting the set peak width exists, it indicates that both the quality control line and the test line exist in the gray scale image.
Specifically, the manner of obtaining the first five peaks of the peak heights in the left and right two regions may be: the method comprises the steps of firstly finding the positions of all peaks of a left area and a right area in a mode of F (p-2) < F (p-1) < F (p) > 1) > F (p +2), then sorting according to the peak heights, finally selecting five points in the front of the peak heights and recording the positions and the peak heights of the five points, wherein the peak widths are the horizontal coordinate distance from the highest point to the first local minimum point on the left side, the peak widths are the horizontal coordinate distance from the highest point to the first local minimum point on the right side, the peak heights are the vertical coordinate distance from the highest point to the first local minimum point on the left side, the peak heights are the vertical coordinate distance from the right point to the first local minimum point on the right side, the initial point positions lp are the horizontal coordinate value of the first local minimum point on the left side, and the initial point positions rp are the horizontal coordinate value of the first local minimum point on the right side.
And traversing and judging the five points obtained in the previous step according to the peak heights from large to small, if a certain point meets the condition, terminating the judgment, and returning to the approximate position where the part of the signals exist, otherwise, the part of the signals does not exist.
Wherein, the judgment condition is as follows: firstly, whether the peak height of the point is more than 0.1, whether the width of the next left peak and the width of the right peak are more than 0.4 × TL and the smaller value of the width of the left peak and the width of the right peak is more than 0.8 times of the larger value, and finally whether the smaller value of the height of the left peak and the height of the right peak is more than 0.8 times of the larger value, if the above conditions are all satisfied, the signal corresponding to the point exists.
The above embodiment specifically describes how to determine whether both the quality control line and the test line exist in the grayscale image according to the matching coefficient curve in the present application, and the following describes how to determine whether the quality control line and the test line exist in the grayscale image according to the matching coefficient curve in the present application.
In one embodiment, after the step of determining whether both the quality control line and the test line exist in the grayscale image according to the matching coefficient curve in step S122, the method may further include:
and if the quality control line exists and the test line does not exist, determining a qualitative result corresponding to the object to be tested according to the type of the immunochromatographic test strip.
In this embodiment, after determining whether both the quality control line and the test line exist in the gray-scale image according to the matching coefficient curve, if the quality control line exists and the test line does not exist, the qualitative result corresponding to the object to be tested may be determined according to the type of the immunochromatographic test paper card.
Schematically, as shown in fig. 3, fig. 3 is a schematic diagram of an image processing process of a sandwich method new crown antibody detection colloidal gold immunochromatographic test strip card provided in an embodiment of the present invention; when detecting whether serum to be detected contains the new crown antibody, the serum to be detected can be dripped on a sample hole of a sandwich method new crown antibody detection colloidal gold immunochromatographic test paper card, and after waiting for 5 minutes, an original image is captured by an image acquisition device, as shown in fig. 3 (a); then converting the original image into a gray image, as shown in fig. 3 (b); after the gray image is obtained, a template corresponding to the colloidal gold immunochromatographic test paper card can be constructed based on the gray image, as shown in fig. 3 (c); after the template is obtained, similarity matching can be performed on the template and the gray level image to obtain a matching coefficient curve, which is shown in (d) of fig. 3; and finally, judging whether the test line and the quality control line exist or not according to the matching coefficient curve, wherein as shown in (d) in fig. 3, only one highest peak exists in the matching coefficient curve, and the highest peak is in the left area, which indicates that the quality control line exists and the test line does not exist.
The above embodiment describes the case where the quality control line exists and the test line does not exist in the present application, and the following describes the steps of determining the region of interest of the quality control line and the region of interest of the test line in the gray scale image in the present application.
In one embodiment, the step of determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image based on the matching coefficient curve in step S123 may include:
and determining a pixel interval of the quality control line and a pixel interval of the test line in the gray-scale image based on the peak with the peak height meeting the set peak height and the peak width meeting the set peak width in the left area and the right area, taking the pixel interval of the quality control line as the interested area of the quality control line, and taking the pixel interval of the test line as the interested area of the test line.
In this embodiment, if there are peaks whose peak heights meet the set peak height and peak widths meet the set peak width in the left and right regions, the pixel regions of the quality control line and the test line in the gray-scale image are determined according to the peak widths corresponding to the peaks meeting the conditions, and then each pixel region is used as the region of interest of the quality control line and the test line.
For example, the peak satisfying the condition is that the peak height of the point is greater than 0.1 and the smaller value of the left and right peak heights is greater than 0.8 times the larger value, the left and right peak widths are greater than 0.4 × TL and the smaller value of the left and right peak widths is greater than 0.8 times the larger value, if all the above conditions are satisfied, the signal corresponding to the point exists, and the position of the interested region of the signal is [ lp +0.5 × TL ] line to [ rp +0.5 × TL ] line of the gray-scale image.
It can be understood that, since the setting template is moved from the top of the gray image to the bottom of the gray image when the setting template is used to perform similarity matching on the gray image, the left and right regions correspond to the upper half pixel row and the lower half pixel row of the gray image, respectively, and the upper half pixel row and the lower half pixel row of the gray image specifically correspond to the quality control line region or the test line region, respectively, which can be distinguished by the structure of the immunochromatographic test strip.
For example, when the C line and the T line on the immunochromatographic test strip are located in the upper half portion and the lower half portion, respectively, it indicates that the pixel interval corresponding to the peak width of the highest peak in the left region of the matching coefficient curve is the region of interest of the quality control line, and the pixel interval corresponding to the peak width of the highest peak in the right region of the matching coefficient curve is the region of interest of the test line.
The foregoing embodiment describes steps of determining an interesting region of a quality control line and an interesting region of a test line in a gray-scale image in the present application, and details of how to obtain a clustered gray-scale image in the present application are described below.
In an embodiment, the step of performing superpixel segmentation on each region of interest in step S130, and clustering a plurality of superpixels obtained by the superpixel segmentation to obtain a clustered gray image may include:
s131: and respectively carrying out superpixel segmentation on each interested region based on the set parameters to obtain a plurality of superpixels corresponding to each interested region.
S132: and determining a pixel point corresponding to each super pixel in the gray image, and the gray value of the pixel point and the pixel line where the pixel point is located.
S133: and determining a characteristic value corresponding to each super pixel based on the gray value of the pixel point and the pixel row where the pixel point is located.
S134: and clustering the super pixels respectively based on the characteristic values to obtain a clustered gray level image.
In this embodiment, when performing superpixel segmentation on the region of interest of the quality control line and the region of interest of the test line, corresponding parameters may be set for segmentation. According to the super-pixel segmentation method, a linear iterative clustering algorithm can be selected for super-pixel segmentation, the number of super-pixels is set to be K (the value range is 40-100) before segmentation, the compactness parameter is set to be m (the value range is 10-20), and the method comprises the following specific steps:
firstly, in order to better perform superpixel segmentation and clustering and enable a final clustering result to be more accurate, a color image corresponding to an immunochromatographic test strip image is converted from an RGB color space to a Lab color space, and the conversion formula is as follows:
Figure BDA0003138689480000151
Figure BDA0003138689480000161
Figure BDA0003138689480000162
Figure BDA0003138689480000163
Figure BDA0003138689480000164
wherein r, g, b are three channels of RGB color space, and L, a, b are three channels of Lab color space.
After converting the color image corresponding to the immunochromatographic test strip image from the RGB color space to the Lab color space, the following steps can be performed for superpixel segmentation:
(1) seed point initialization (cluster center): and uniformly distributing the seed points in the image according to the set number of the super pixels. Assuming that a picture has N pixel points in total and is pre-divided into K super pixels with the same size, the size of each super pixel is N/K, and the distance (step length) between adjacent seed points is approximately equal to S ═ sqrt (N/K).
(2) With the seed point as the center, reselecting the seed point in n × n neighborhood of the seed point (generally, taking n as 3); the specific method comprises the following steps: and calculating gradient values of all pixel points in the neighborhood, and moving the seed point to the place with the minimum gradient in the neighborhood. The purpose of this is to avoid the seed points falling on the contour boundary with larger gradient so as not to affect the subsequent clustering effect.
(3) And (3) distributing a class label to each pixel point in the neighborhood around each seed point, namely the seed point to which the pixel point belongs, wherein the searching range is 2S-2S, the distribution basis is distance measurement, and the pixel point is distributed to the seed point which is closest to the pixel point. The distance measure includes the color distance and the spatial distance, and for each searched pixel point, the distance between the pixel point and the seed point is calculated respectively. The distance calculation method is as follows:
Figure BDA0003138689480000171
wherein d iscIndicating the color distance, dsThe spatial distance is represented, L, a and b represent three channels of the Lab color space, x and y represent the spatial position of a pixel point, m represents the compactness parameter, and the S value is the maximum spatial distance within the class (S ═ sqrt (N/K)).
(4) And (3) updating seed points: the seed points are updated using the mean of the attached pixel points attributed to each seed point.
(6) Iterative optimization: and (4) repeating the steps (2) to (4) until the seed points are not changed any more.
In addition, in order to enhance the connectivity among the superpixels in the region of interest, a marking table can be newly established, the elements in the table are all-1, the discontinuous superpixels and the superpixels with the undersize size are redistributed to the adjacent superpixels according to the Z-shaped trend (from left to right and from top to bottom), and the traversed pixel points are distributed to the corresponding labels until all the points are traversed.
The method comprises the steps of respectively performing superpixel segmentation on each interested area based on set parameters, after obtaining a plurality of superpixels corresponding to each interested area, determining a pixel point corresponding to each superpixel in a gray image, a gray value of the pixel point and a pixel row where the pixel point is located, and then determining a characteristic value [ avergray, averrow ] corresponding to each superpixel based on the gray value of the pixel point of each superpixel and the pixel row where the pixel point is located, wherein avergray is a gray average value of all pixel points in one superpixel, and averrow is a row number average value of the pixel rows where all pixel points in one superpixel are located.
After the feature values corresponding to the super pixels in each region of interest are obtained, the super pixels can be respectively clustered based on the feature values corresponding to the super pixels, so that a clustered gray image is obtained.
Further, the clustering algorithm in the application can use K-means clustering, the number of clusters is set to 3, and the specific steps are as follows:
(1) 3 points were randomly selected as initial cluster centers.
(2) Calculating the distance between each super pixel point and each clustering center, and allocating each super pixel point to the clustering center closest to the super pixel point, wherein the distance calculation formula is as follows:
Figure BDA0003138689480000172
wherein [ averray, averrow ] is a characteristic value of each super pixel point, and [ cenray, cenrow ] is a value of a cluster center.
(3) Updating the clustering centers by using the characteristic value mean value of the auxiliary super pixel points of each clustering center;
(4) and (4) repeating the steps (2) and (3) until the cluster center is not changed any more.
The above embodiment describes in detail how to obtain the clustered gray scale image in the present application, and how to determine the respective characteristic values of the test line and the quality control line in the present application is described below.
In an embodiment, the step of determining the characteristic values of the test line and the quality control line based on the clustered gray scale images in step S140 may include:
s141: carrying out binarization on the clustered gray level image to obtain a binarized image; the binary image comprises a quality control line region, a test line region and a background region.
S142: and determining the number of pixel points and the pixel value of the quality control line region, the number of pixel points and the pixel value of the test line region, and the number of pixel points and the pixel value of the background region based on the grayscale image and the binary image.
S143: and determining the characteristic value of the quality control line region and the characteristic value of the test line region based on the number and the value of the pixel points of the quality control line region, the number and the value of the pixel points of the test line region, and the number and the value of the pixel points of the background region.
In this embodiment, after the clustering is completed, all the super pixel points are classified into 3 classes, so that the mean value of the eigenvalues averrow of the super pixel points included in each class can be calculated and recorded as avercluster; then, ordering averclusters corresponding to the 3 classes, and marking the largest and smallest corresponding averclusters as backgrounds, wherein when a binary image is generated, the values of all pixels contained in all super pixels belonging to the two classes are 0; and marking the class with the middle order corresponding to avercluster values as a signal, and when a binary image is generated, setting the values of all pixel points contained in all super pixel points belonging to the class as 1, thereby obtaining the binary image, wherein the binary image comprises a quality control line region, a test line region and a background region.
Then, when determining the characteristic value of the test line and the characteristic value of the quality control line in the grayscale image, the binarized values corresponding to the pixels in the test line region, the binarized values corresponding to the pixels in the quality control line region, and the binarized values corresponding to the pixels in the background region in the binarized image may be referred to. The characteristic value of the test line and the characteristic value of the quality control line obtained by calculation can reflect the characteristics of the test line and the quality control line more accurately.
The calculation formula of the characteristic value CV of the quality control line and the characteristic value TV of the test line is as follows:
Figure BDA0003138689480000191
Figure BDA0003138689480000192
wherein n iscIs the number of pixel points, n, of the quality control line region in the upper half of the Gray image GrayCBIs the number of pixels of the background area in the upper half of the Gray scale image Gray, nTIs the number of pixel points, n, of the test line region in the lower half of the Gray image GrayTBIs the number of background area pixel points in the lower half of the Gray image Gray.
Further, the immunochromatographic detection method of the present application will be described by the following two examples, as shown in fig. 4 and 5, fig. 4 is a schematic diagram of an image processing process of a competitive vomitoxin colloidal gold immunochromatographic strip card provided in an embodiment of the present invention, and fig. 5 is a schematic diagram of an image processing process of a competitive zearalenone colloidal gold immunochromatographic strip card provided in an embodiment of the present invention.
FIG. 4 is a schematic view of a competitive-method vomitoxin colloidal gold immunochromatographic test strip card to show details of the immunochromatographic detection method of the present invention. The specific implementation process is as follows:
(1) dropping a sample to be detected on a competitive vomitoxin colloidal gold immunochromatography test paper card sample hole, waiting for 5.5 minutes, and capturing an original image through an image acquisition device, as shown in (a) of fig. 4; the original image is then converted into a grayscale image, as in fig. 4 (b).
(2) And (3) constructing a template corresponding to the colloidal gold immunochromatographic test paper card based on the prior knowledge, as shown in (c) of fig. 4, and then performing template matching to obtain a matching coefficient curve as shown in (d) of fig. 4.
(3) Whether the test line and the quality control line exist is judged according to the matching coefficient curve, and the result shows that the quality control line and the test line both exist, and the approximate positions (the interested areas) where the quality control line and the test line exist are black frame areas in fig. 4 (e).
(4) And (3) performing superpixel segmentation on the interesting regions of the test lines and the quality control lines found in the step (3), selecting SLIC as a superpixel segmentation algorithm, setting the number K of superpixels to be 40 and the compactness parameter to be 10, and obtaining a segmentation result shown in (f) in FIG. 4.
(5) And (e) calculating a characteristic value of each super pixel in the interested regions of the test line and the quality control line, and performing K-means clustering on the two interested regions respectively according to the characteristic values to obtain accurate segmentation results of the test line and the quality control line, as shown in (g) of fig. 4.
(6) Based on the result of the segmentation of the test line and the quality control line obtained in step (5), TV is 10.53, CV is 60.27, and TC is 0.175 according to the formula.
(7) And (4) according to the TC value obtained in the step (6), comparing with the TC value-concentration standard curve of the vomitoxin, and calculating to obtain the quantitative concentration of the substance to be detected to be 22.5 ng/mL.
Wherein, the TC value-concentration standard curve of the vomitoxin is obtained by the following method: firstly, 6 kinds of vomitoxin solutions with known concentrations are respectively detected by 6 competitive vomitoxin colloidal gold immunochromatographic test paper cards, and the concentrations of the vomitoxin solutions are respectively 0.5, 1, 2.5, 5, 10 and 40 ng/mL; then obtaining a characteristic value TC in the same way as an immunochromatography test paper card corresponding to a sample to be detected; finally, a standard curve of the TC value and the concentration of the vomitoxin can be obtained by adopting four-parameter Logistic curve fitting, as shown in (h) of fig. 4.
FIG. 5 is a schematic view showing the details of the immunochromatography detection method of the present invention mainly by treating a competitive zearalenone colloidal gold immunochromatography test strip card. The specific implementation process is as follows:
(1) dropping a sample to be detected on a sample hole of a competitive zearalenone colloidal gold immunochromatography test paper card, waiting for 6 minutes, and capturing an original image through an image acquisition device, as shown in fig. 5 (a); the original image is then converted into a grayscale image, as in fig. 5 (b).
(2) And (3) constructing a template corresponding to the colloidal gold immunochromatographic test paper card based on the prior knowledge, as shown in (c) of fig. 5, and then performing template matching to obtain a matching coefficient curve as shown in (d) of fig. 5.
(3) The presence or absence of the test line and the quality control line is determined according to the matching coefficient curve, and the result indicates that both the quality control line and the test line are present, and the approximate positions (regions of interest) where they are located are the black frame regions in fig. 5 (e).
(4) And (3) performing superpixel segmentation on the interesting regions of the test lines and the quality control lines found in the step (3), selecting SLIC as a superpixel segmentation algorithm, setting the number K of superpixels as 100 and the compactness parameter as 20, and obtaining a segmentation result shown in (f) of FIG. 5.
(5) And (e) calculating the characteristic value of each super pixel in the region of interest of the test line and the quality control line, and performing K-means clustering on the two regions according to the characteristic values to obtain accurate segmentation results of the test line and the quality control line, as shown in (g) of fig. 5.
(6) Based on the result of the segmentation of the test line and the quality control line obtained in step (5), TV is 12.77, CV is 48.16, and TC is 0.265.
(7) And (4) comparing the TC value obtained in the step (6) with the TC value-concentration standard curve of the zearalenone, and calculating to obtain the quantitative concentration of the substance to be detected, which is 12.1 ng/mL.
The method for obtaining the TC value-concentration standard curve of the zearalenone comprises the following steps: firstly, respectively detecting 6 zearalenone solutions with known concentrations by 6 competitive zearalenone colloidal gold immunochromatographic test paper cards, wherein the concentrations of the zearalenone solutions are respectively 0.5, 1, 2.5, 5, 20 and 40 ng/mL; then obtaining a characteristic value TC in the same way as an immunochromatography test paper card corresponding to a sample to be detected; finally, a four-parameter Logistic curve fitting is adopted to obtain a standard curve of the TC value and the zearalenone concentration, as shown in (h) of fig. 5.
The immunochromatographic assay device provided in the embodiments of the present application is described below, and the immunochromatographic assay device described below and the immunochromatographic assay method described above are referred to in correspondence with each other.
In one embodiment, as shown in fig. 6, fig. 6 is a schematic structural diagram of an immunochromatography detection device according to an embodiment of the present invention; the invention also provides an immunochromatography detection device, which comprises an image acquisition module 210, a region determination module 220, a segmentation clustering module 230, a characteristic value determination module 240 and a concentration determination module 250, and specifically comprises the following components:
the image obtaining module 210 is configured to obtain a gray-scale image corresponding to the immunochromatographic test strip image of the object to be tested.
And the region determining module 220 is configured to determine a region of interest of the quality control line and a region of interest of the test line in the gray image.
And a segmentation and clustering module 230, configured to perform superpixel segmentation on each region of interest, and perform clustering on multiple superpixels obtained after the superpixel segmentation to obtain a clustered grayscale image.
And a characteristic value determining module 240, configured to determine characteristic values of the test line and the quality control line based on the clustered grayscale images.
And a concentration determining module 250, configured to determine the quantitative concentration of the analyte based on the respective characteristic values of the test line and the quality control line.
In the above embodiment, the region of interest of the quality control line and the region of interest of the test line in the gray level image are determined, then the superpixel segmentation is performed on each region of interest, and the multiple superpixels obtained after the superpixel segmentation are clustered to obtain the clustered gray level image.
In one embodiment, the region determining module 220 may include:
and the matching coefficient curve determining module is used for carrying out similarity matching on the gray value in the gray image based on a set template to obtain a corresponding matching coefficient curve, wherein the abscissa of the matching coefficient curve is the position of the first row of the set template in the pixel row of the gray image, and the ordinate of the matching coefficient curve is the similarity of the overlapping area of the gray image and the set template.
And the judging module is used for determining whether the quality control line and the test line in the gray level image exist according to the matching coefficient curve.
And the interested area determining module is used for determining the interested area of the quality control line and the interested area of the test line in the gray level image based on the matching coefficient curve if the gray level image is the gray level image.
In one embodiment, the determining module may include:
and the region dividing module is used for dividing the matching coefficient curve into a left region and a right region from the middle.
And the peak height and width determining module is used for determining the peak height and width of each peak in the left area and the right area based on the matching coefficient curve.
And the condition judgment module is used for determining whether peaks with peak heights meeting the set peak heights and peak widths meeting the set peak widths exist in the left area and the right area.
And the result determining module is used for determining that the quality control line and the test line in the gray level image exist if the peaks meeting the conditions exist in the left area and the right area.
In one embodiment, the determining module may further include:
and the qualitative result determining module is used for determining a qualitative result corresponding to the object to be tested according to the type of the immunochromatography test paper card if the quality control line exists and the test line does not exist.
In one embodiment, the region of interest determination module may include:
and the pixel interval determining module is used for determining the pixel interval of the quality control line and the pixel interval of the test line in the gray-scale image based on the peak with the peak height meeting the set peak height and the peak width meeting the set peak width in the left area and the right area, taking the pixel interval of the quality control line as the interested area of the quality control line, and taking the pixel interval of the test line as the interested area of the test line.
In one embodiment, the segmentation clustering module 230 may include:
and the superpixel segmentation module is used for respectively performing superpixel segmentation on each interested region based on the set parameters to obtain a plurality of superpixels corresponding to each interested region.
And the characteristic acquisition module is used for determining a pixel point corresponding to each super pixel in the gray image, the gray value of the pixel point and the pixel line where the pixel point is located.
And the characteristic determining module is used for determining a characteristic value corresponding to each super pixel based on the gray value of the pixel point and the pixel row where the pixel point is located.
And the clustering module is used for respectively clustering the super pixels based on the characteristic values to obtain clustered gray level images.
In one embodiment, the feature value determination module 240 may include:
a binarization module, configured to perform binarization on the clustered grayscale images to obtain binarized images; the binary image comprises a quality control line region, a test line region and a background region.
And the pixel information determining module is used for determining the pixel point number and the pixel value of the quality control line region, the pixel point number and the pixel value of the test line region and the pixel point number and the pixel value of the background region based on the gray level image and the binary image.
And the characteristic value calculation module is used for determining the characteristic value of the quality control line region and the characteristic value of the test line region based on the pixel point number and the pixel value of the quality control line region, the pixel point number and the pixel value of the test line region and the pixel point number and the pixel value of the background region.
In one embodiment, the present invention also provides a storage medium having stored therein computer readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method as in any one of the above embodiments.
In one embodiment, the invention also provides a computer device having stored therein computer readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method as in any one of the above embodiments.
Fig. 7 is a schematic diagram illustrating an internal structure of a computer device according to an embodiment of the present invention, and the computer device 300 may be provided as a server, as shown in fig. 7. Referring to fig. 7, computer device 300 includes a processing component 302 that further includes one or more processors and memory resources, represented by memory 301, for storing instructions, such as application programs, that are executable by processing component 302. The application programs stored in memory 301 may include one or more modules that each correspond to a set of instructions. Further, the processing component 302 is configured to execute instructions to perform the immunochromatographic detection method of any of the embodiments described above.
The computer device 300 may also include a power component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input output (I/O) interface 305. The computer device 300 may operate based on an operating system stored in memory 301, such as Windows Server, Mac OS XTM, Unix, Linux, Free BSDTM, or the like.
Those skilled in the art will appreciate that the architecture shown in fig. 7 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, the embodiments may be combined as needed, and the same and similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. An immunochromatographic assay method, comprising:
acquiring a gray image corresponding to an immunochromatographic test strip image of an object to be detected;
determining an interested region of a quality control line and an interested region of a test line in the gray level image;
respectively carrying out superpixel segmentation on each region of interest, and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image;
determining the characteristic values of the test line and the quality control line based on the clustered gray level image;
and determining the quantitative concentration of the object to be detected based on the respective characteristic values of the test line and the quality control line.
2. The immunochromatographic detection method according to claim 1, wherein the step of determining a region of interest of a quality control line and a region of interest of a test line in the gray-scale image comprises:
carrying out similarity matching on the gray value in the gray image based on a set template to obtain a corresponding matching coefficient curve, wherein the abscissa of the matching coefficient curve is the position of the first row of the set template in the pixel row of the gray image, and the ordinate of the matching coefficient curve is the similarity of the overlapping area of the gray image and the set template;
determining whether a quality control line and a test line in the gray level image exist according to the matching coefficient curve;
if so, determining the interested region of the quality control line and the interested region of the test line in the gray level image based on the matching coefficient curve.
3. The immunochromatography detection method according to claim 2, wherein the step of determining whether both a quality control line and a test line exist in the gray-scale image from the matching coefficient curve includes:
dividing the matching coefficient curve into a left area and a right area from the middle;
determining the peak height and the peak width of each peak in the left area and the right area based on the matching coefficient curve;
determining whether a peak with a peak height meeting the set peak height and a peak width meeting the set peak width exists in the left area and the right area;
and if the peaks meeting the conditions exist in the left area and the right area, determining that the quality control line and the test line in the gray level image both exist.
4. The immunochromatography detection method according to claim 2, further comprising, after the step of determining whether both a quality control line and a test line exist in the gray-scale image from the matching coefficient curve:
and if the quality control line exists and the test line does not exist, determining a qualitative result corresponding to the object to be tested according to the type of the immunochromatography test paper card.
5. The immunochromatography detection method according to claim 3, wherein the step of determining the region of interest of the quality control line and the region of interest of the test line in the gray-scale image based on the matching coefficient curve includes:
and determining a pixel interval of the quality control line and a pixel interval of the test line in the gray-scale image based on the peak with the peak height meeting the set peak height and the peak width meeting the set peak width in the left area and the right area, taking the pixel interval of the quality control line as the interested area of the quality control line, and taking the pixel interval of the test line as the interested area of the test line.
6. The immunochromatography detection method according to claim 1, wherein the step of performing superpixel segmentation on each region of interest respectively and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image comprises:
respectively carrying out superpixel segmentation on each interested region based on set parameters to obtain a plurality of superpixels corresponding to each interested region;
determining a pixel point corresponding to each super pixel in the gray image, and the gray value of the pixel point and a pixel row where the pixel point is located;
determining a characteristic value corresponding to each super pixel based on the gray value of the pixel point and the pixel row where the pixel point is located;
and clustering the super pixels respectively based on the characteristic values to obtain a clustered gray level image.
7. The immunochromatography detection method according to claim 1, wherein the step of determining the characteristic values of the test line and the quality control line based on the clustered grayscale images comprises:
carrying out binarization on the clustered gray level image to obtain a binarized image; the binary image comprises a quality control line region, a test line region and a background region;
determining the number of pixel points and the pixel value of the quality control line region, the number of pixel points and the pixel value of the test line region, and the number of pixel points and the pixel value of the background region based on the gray level image and the binary image;
and determining the characteristic value of the quality control line region and the characteristic value of the test line region based on the number and the value of the pixel points of the quality control line region, the number and the value of the pixel points of the test line region, and the number and the value of the pixel points of the background region.
8. An immunochromatographic detection device, comprising:
the image acquisition module is used for acquiring a gray image corresponding to the immunochromatography test strip image of the object to be detected;
the area determination module is used for determining an interested area of a quality control line and an interested area of a test line in the gray level image;
the segmentation and clustering module is used for respectively performing superpixel segmentation on each region of interest and clustering a plurality of superpixels obtained after the superpixel segmentation to obtain a clustered gray image;
the characteristic value determining module is used for determining the respective characteristic values of the test line and the quality control line based on the clustered gray level images;
and the concentration determination module is used for determining the quantitative concentration of the object to be detected based on the respective characteristic values of the test line and the quality control line.
9. A storage medium, characterized by: the storage medium having stored therein computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method of any one of claims 1 to 7.
10. A computer device, characterized by: the computer device has stored therein computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of the immunochromatographic detection method of any one of claims 1 to 7.
CN202110729178.XA 2021-06-29 2021-06-29 Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment Active CN113435444B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110729178.XA CN113435444B (en) 2021-06-29 2021-06-29 Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110729178.XA CN113435444B (en) 2021-06-29 2021-06-29 Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment

Publications (2)

Publication Number Publication Date
CN113435444A true CN113435444A (en) 2021-09-24
CN113435444B CN113435444B (en) 2022-11-01

Family

ID=77757729

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110729178.XA Active CN113435444B (en) 2021-06-29 2021-06-29 Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment

Country Status (1)

Country Link
CN (1) CN113435444B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115994907A (en) * 2023-03-22 2023-04-21 济南市莱芜区综合检验检测中心 Intelligent processing system and method for comprehensive information of food detection mechanism

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104101704A (en) * 2014-07-02 2014-10-15 华中科技大学 Method for quantitative detection of immunochromatographic test card
CN106168578A (en) * 2016-06-14 2016-11-30 福州大学 Golden immunity-chromatography test strip image detecting method based on MTK platform
CN107328776A (en) * 2017-06-23 2017-11-07 华中科技大学 A kind of quick determination method of immune chromatography test card
CN108133481A (en) * 2017-12-22 2018-06-08 必欧瀚生物技术（合肥）有限公司 A kind of image processing algorithm for fluorescence immune chromatography strip imaging system
CN109035273A (en) * 2018-08-08 2018-12-18 华中科技大学 A kind of picture signal fast partition method of immune chromatography test card
CN110161233A (en) * 2018-02-12 2019-08-23 华中科技大学 A kind of fast quantitative measurement method for detecting of immune chromatography test card

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104101704A (en) * 2014-07-02 2014-10-15 华中科技大学 Method for quantitative detection of immunochromatographic test card
CN106168578A (en) * 2016-06-14 2016-11-30 福州大学 Golden immunity-chromatography test strip image detecting method based on MTK platform
CN107328776A (en) * 2017-06-23 2017-11-07 华中科技大学 A kind of quick determination method of immune chromatography test card
CN108133481A (en) * 2017-12-22 2018-06-08 必欧瀚生物技术（合肥）有限公司 A kind of image processing algorithm for fluorescence immune chromatography strip imaging system
CN110161233A (en) * 2018-02-12 2019-08-23 华中科技大学 A kind of fast quantitative measurement method for detecting of immune chromatography test card
CN109035273A (en) * 2018-08-08 2018-12-18 华中科技大学 A kind of picture signal fast partition method of immune chromatography test card

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
WENSHENG GUO 等: "Region Growing Algorithm Combined With Fast Peak Detection for Segmenting Colloidal Gold Immunochromatographic Strip Images", 《IEEEACCESS》 *
曾念寅等: "纳米金免疫层析试条定量检测的研究", 《生物医学工程研究》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115994907A (en) * 2023-03-22 2023-04-21 济南市莱芜区综合检验检测中心 Intelligent processing system and method for comprehensive information of food detection mechanism

Also Published As

Publication number Publication date
CN113435444B (en) 2022-11-01

Similar Documents

Publication Publication Date Title
US20230383232A1 (en) Method and system for automated microbial colony counting from streaked sample on plated media
US20220383498A1 (en) Colony contrast gathering
CN107977671B (en) Tongue picture classification method based on multitask convolutional neural network
CN102308306B (en) A constraint generator for use in image segregation
US11977984B2 (en) Using a first stain to train a model to predict the region stained by a second stain
US7136524B1 (en) Robust perceptual color identification
CN102687007B (en) High-throughput biomarker segmentation utilizing hierarchical normalized cuts
CN110161233B (en) Rapid quantitative detection method for immunochromatography test paper card
CN104598886B (en) A kind of method that utilization near-infrared high spectrum image recognizes the oil crops that go mouldy
CN105279772B (en) A kind of trackability method of discrimination of infrared sequence image
CN110853006B (en) Method for evaluating quality of digital pathological image acquired by scanner
CN107328776A (en) A kind of quick determination method of immune chromatography test card
CN106557740B (en) The recognition methods of oil depot target in a kind of remote sensing images
CN110472081B (en) Shoe picture cross-domain retrieval method based on metric learning
CN113569724B (en) Road extraction method and system based on attention mechanism and dilation convolution
US11790673B2 (en) Method for detection of cells in a cytological sample having at least one anomaly
CN111126393A (en) Vehicle appearance refitting judgment method and device, computer equipment and storage medium
CN112613410B (en) Parasite egg identification method based on transfer learning
CN105974120A (en) Automatic detection device and method for C-reactive protein chromaticity
CN112037221B (en) Multi-domain co-adaptation training method for cervical cancer TCT slice positive cell detection model
CN106971397A (en) Based on the city high-resolution remote sensing image dividing method for improving JSEG algorithms
CN113435444B (en) Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment
CN117542301A (en) Display screen detection method and system
Wang et al. Local defect detection and print quality assessment
CN113537203A (en) Test paper identification method and device, storage medium and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant