CN116203253B - AI analysis system and method for detecting interleukin concentration - Google Patents
AI analysis system and method for detecting interleukin concentration Download PDFInfo
- Publication number
- CN116203253B CN116203253B CN202310472438.9A CN202310472438A CN116203253B CN 116203253 B CN116203253 B CN 116203253B CN 202310472438 A CN202310472438 A CN 202310472438A CN 116203253 B CN116203253 B CN 116203253B
- Authority
- CN
- China
- Prior art keywords
- interleukin
- colored product
- model
- antigen
- antibody
- 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.)
- Active
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
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
- G01N33/6863—Cytokines, i.e. immune system proteins modifying a biological response such as cell growth proliferation or differentiation, e.g. TNF, CNF, GM-CSF, lymphotoxin, MIF or their receptors
- G01N33/6869—Interleukin
-
- 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
- G01N33/543—Immunoassay; Biospecific binding assay; Materials therefor with an insoluble carrier for immobilising immunochemicals
- G01N33/54306—Solid-phase reaction mechanisms
-
- 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
- G01N33/58—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving labelled substances
- G01N33/581—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving labelled substances with enzyme label (including co-enzymes, co-factors, enzyme inhibitors or substrates)
-
- 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
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
- G01N33/6854—Immunoglobulins
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30024—Cell structures in vitro; Tissue sections in vitro
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/30—Against vector-borne diseases, e.g. mosquito-borne, fly-borne, tick-borne or waterborne diseases whose impact is exacerbated by climate change
Abstract
An AI analysis system and a method for detecting the concentration of interleukin belong to the technical field of artificial intelligent detection. The system comprises: the carrier pushing mechanism is used for pushing a single solid carrier to the position right below the liquid dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody; and the AI analysis equipment is used for establishing an AI analysis model based on the BP neural network so as to intelligently analyze the concentration of the interleukin antibody or antigen in the tested sample according to the set volume, the first set time length, the second set time length and the RGB color channel value of each pixel point of the colored product imaging region. According to the invention, on the basis of hardware of an automated detection process, an AI analysis model based on a BP neural network is adopted to execute intelligent analysis of the interleukin concentration, so that the reliability of a detection result is ensured while the detection process is automatically completed.
Description
Technical Field
The invention relates to the technical field of artificial intelligence detection, in particular to an AI analysis system and method for detecting the concentration of interleukin.
Background
Interleukins are a class of cytokines that are produced by and act on a variety of cells. Since they are produced by leukocytes and act between leukocytes, they have been known and used. Initially, it refers to cytokines produced by and regulated between leukocytes, and now refers to a class of cytokines which have a well defined molecular structure and biological function, have important regulatory effects and are uniformly named, and are of the same genus as blood cell growth factors. The two are coordinated and interacted to jointly complete the functions of hematopoiesis and immunoregulation. Interleukins play an important role in the transmission of information, the activation and regulation of immune cells, the mediation of T, B cell activation, proliferation and differentiation, and in inflammatory responses.
Interleukin, abbreviated as IL, is involved in the expression and regulation of immune responses in functional relation, and this regulation is mediated by a number of factors derived from lymphocytes or macrophages, etc. Lymphokines derived from lymphocytes and macrophages are collectively referred to as monokines, and the biological activities of the individual factors vary (e.g., macrophage activation, promotion of T cell proliferation, etc.), and the physicochemical properties of the factors themselves are not known.
During the course of the study of the immune response, many bioactive molecules were found in mitogen-stimulated cell culture supernatants, and researchers each named for their own measured activities reported nearly hundred factors over a decade. Later comparative studies with the aid of molecular biology techniques have found that many of the factors named for biological activity in the past are actually the same substance with pleiotropic properties.
In the detection process of each examined specimen containing the interleukin antibody or antigen, the concentration of the interleukin antibody or antigen in the examined specimen is detected, so that the immunity and the invasion degree of the human body or animal which is taken as the examined specimen source can be judged in a targeted manner, the health state of the human body or animal which is taken as the examined specimen source can be primarily known, and key information is provided for the subsequent diagnosis and treatment scheme establishment.
For example, a method for detecting the content of avian interleukin 10 and a special kit thereof are proposed in Chinese patent publication CN 107266570A. The invention establishes a double-sandwich ELISA detection method aiming at chIL-10 on the protein level by utilizing a chIL-10 monoclonal antibody. Experiments prove that: the anti-chIL-10 monoclonal antibody has good specificity and affinity, can accurately reflect the content of chIL-10 in serum or cell supernatant, is quick, efficient and accurate, solves the problems of complex operation, time and labor consumption, easy operation and other external conditions influence caused by adopting a fluorescent quantitative PCR detection method in the prior art, is beneficial to evaluating the dynamic change level of chIL-10 in a human body, provides good reference for preventing and treating diseases, and is beneficial to understanding the occurrence, development and prognosis of infectious diseases of poultry and the dynamic state of protective immune response of the human body.
For example, a method for detecting serum protein factor for judging schizophrenia proposed in chinese patent publication CN104330573 a, the method comprises the following steps: 1) Extracting blood of suspected patients, and separating serum proteins; 2) Detecting the level of Nerve Growth Factor (NGF), interleukin (IL-6), calbindin S100B, interferon (IFN- γ), tumor necrosis factor (TNF- α), brain Derived Neurotrophic Factor (BDNF), glial Fibrillary Acidic Protein (GFAP), basic myelin protein (MBP) 8 protein factor from the isolated serum proteins; 3) Comparing the detected protein factor content with a normal reference value, and scientifically classifying and judging the schizophrenia. The invention is applied to the concentration of serum protein factors which are selected as the diagnosis markers of the schizophrenia, and the five factors of NGF, IL-6, S100deg.P, MBP and GFAP are found to have larger contribution rate to assisting in diagnosing the schizophrenia, and the diagnosis value is higher than that of any single protein factor.
However, in the prior art, the specific processing and sequential setting of each detection procedure are mainly completed through a manual operation mode, so that the speed and efficiency of each detection of the interleukin concentration are seriously affected, and meanwhile, in the process of judging the color depth of a finally obtained colored product to obtain the interleukin concentration, the method relies on manual judgment or a simple electronic judgment mechanism, the former is too dependent on manual work, the latter judgment mechanism is rough, so that the deviation of detection data of the interleukin concentration is larger, and the immunity or the invasion degree of a human body or an animal cannot be truly reflected.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides an AI analysis system and a method for detecting the concentration of the interleukin, which are characterized in that AI analysis equipment is introduced on the basis of hardware of an automated detection process, and the AI analysis equipment is used for establishing an AI analysis model based on a BP neural network to execute intelligent analysis of the concentration of the interleukin, so that the speed and the efficiency of the whole detection process are improved while the immunity or the invasion degree of a real human body or an animal are obtained.
According to a first aspect of the present invention, there is provided an AI analysis system for interleukin concentration detection, the system comprising:
the carrier pushing mechanism is used for pushing a single solid carrier to the position right below the liquid dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody;
the dropping execution mechanism is arranged at the dropping station and is used for executing the dropping treatment of a set volume of the sample to be detected containing the interleukin antibody or the antigen after each single solid-phase carrier is pushed to the position right below the dropping station so as to drop the set volume of the sample to be detected containing the interleukin antibody or the antigen into the surface of the solid-phase carrier;
the washing and separating mechanism is used for executing washing and separating operation to separate antigen-antibody complex formed on the surface of the solid phase carrier from other substances in the liquid on the surface of the solid phase carrier obtained by the drip treatment by adopting a washing mode after the drip execution mechanism finishes the drip treatment of the tested specimen for a first set time length;
an addition processing means for adding an enzyme-labeled interleukin antigen or antibody to the antigen-antibody complex formed on the surface of the solid carrier and binding to the surface of the solid carrier by a reaction after detecting that the washing separation means has completed a washing separation operation;
the substrate supplementing mechanism is used for adding a substrate of the enzyme reaction to the surface of the solid phase carrier after the adding treatment mechanism finishes the adding treatment for a second set time length so as to obtain a colored product, wherein the colored product is a product of the substrate catalyzed by the enzyme;
the AI analysis equipment is used for establishing an AI analysis model based on a BP neural network, taking the RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging area as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in a tested sample output by the model;
the number of each pixel point input into the model is a preset pixel number, and the preset pixel number is positively correlated with the set volume;
the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product;
wherein when the interleukin antigen is bound on the surface of the solid support, the sample to be tested contains the interleukin antibody, and the enzyme-labeled interleukin antigen is added to the antigen-antibody complex formed on the surface of the solid support.
According to a second aspect of the present invention, there is provided an AI analysis method for interleukin concentration detection, the method comprising:
a carrier pushing mechanism is used for pushing a single solid carrier to the position right below a dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody;
a drip actuator is arranged at the drip station and is used for executing drip treatment of a set volume of sample to be detected containing the interleukin antibody or antigen after each single solid phase carrier is pushed to the position right below the drip station so as to drip the set volume of sample to be detected containing the interleukin antibody or antigen onto the surface of the solid phase carrier;
a washing and separating mechanism is used for executing washing and separating operation to separate antigen-antibody complex formed on the surface of the solid phase carrier from other substances in the liquid on the surface of the solid phase carrier obtained by the drip treatment in a washing mode after the drip execution mechanism completes the drip treatment of the tested specimen for a first set time length;
using an addition processing mechanism for adding an enzyme-labeled interleukin antigen or antibody to the antigen-antibody complex formed on the surface of the solid carrier and binding to the surface of the solid carrier by a reaction after detecting that the washing separation mechanism completes a washing separation operation;
a substrate supplementing mechanism is used for adding a substrate of the enzyme reaction to the surface of the solid phase carrier after the adding treatment mechanism finishes the adding treatment for a second set time length so as to obtain a colored product, wherein the colored product is a product of the substrate catalyzed by the enzyme;
using an AI analysis device for establishing an AI analysis model based on a BP neural network, taking RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging region as input data of the model, and running the model to obtain the concentration of interleukin antibodies or antigens in a detected specimen output by the model;
the number of each pixel point input into the model is a preset pixel number, and the preset pixel number is positively correlated with the set volume;
the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product;
wherein when the interleukin antigen is bound on the surface of the solid support, the sample to be tested contains the interleukin antibody, and the enzyme-labeled interleukin antigen is added to the antigen-antibody complex formed on the surface of the solid support.
Therefore, the invention has at least the following four remarkable technical advances:
(1) Introducing an AI analysis device for establishing an AI analysis model based on a BP neural network to perform intelligent analysis of the interleukin concentration, specifically, taking the RGB color channel values of each pixel point of a currently detected corresponding set volume, a first set time length, a second set time length and a colored product imaging region as input data of the model, and running the model to obtain the concentration of the interleukin antibody or antigen in a detected specimen output by the model;
(2) Performing targeted design and customized training on an AI analysis model, wherein the number of each pixel point input into the model is a preset pixel number, the preset pixel number is positively correlated with a set volume of a sample to be tested containing an interleukin antibody or antigen, the AI analysis model is a BP neural network after training for a set number of times, and the set number of times is positively correlated with the set volume;
(3) When each pixel point of a colored product imaging area input into a model is acquired, when the total number of the pixel points in the colored product imaging area is more than the preset pixel number, each pixel point of the preset pixel number of the central position of the colored product imaging area is taken to input the model, and when the total number of the pixel points in the colored product imaging area is less than the preset pixel number, interpolation processing is performed on the colored product imaging area to obtain an interpolated colored product imaging area with the total number of occupied pixel points equal to the set pixel number, and each pixel point of the interpolated colored product imaging area is input into the model;
(4) The automatic interleukin concentration detection structure comprises a carrier pushing mechanism, a liquid dripping executing mechanism, a washing separating mechanism, an adding processing mechanism and a substrate supplementing mechanism, and the speed and the efficiency of interleukin concentration detection at each time are improved.
Drawings
Embodiments of the present invention will be described below with reference to the accompanying drawings, in which:
FIG. 1 is a technical flow diagram of an AI analysis system and method for interleukin concentration detection in accordance with the invention.
Fig. 2 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 1 of the present invention.
Fig. 3 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 2 of the present invention.
Fig. 4 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 3 of the present invention.
Fig. 5 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 4 of the present invention.
Fig. 6 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 5 of the present invention.
Detailed Description
As shown in fig. 1, a technical flow diagram of an AI analysis system and method for interleukin concentration detection according to the present invention is presented.
As shown in fig. 1, the specific technical process of the present invention is as follows:
firstly, establishing an automatic interleukin concentration detection structure comprising a carrier pushing mechanism, a drip execution mechanism, a washing separation mechanism, an addition treatment mechanism and a substrate supplementing mechanism, replacing a manual detection mode, and improving the speed and efficiency of the whole detection mechanism;
secondly, an AI analysis model based on the BP neural network is established, wherein the AI analysis model is the BP neural network which is trained for a plurality of times, and the reliability and the stability of the AI analysis model are ensured by executing a specific structural design and a customized training mechanism;
illustratively, as shown in fig. 1, the BP neural network-based AI analysis model includes an input layer, a hidden layer, and an output layer, the hidden layer being disposed between the input layer and the output layer;
and in the AI analysis model based on BP neural network, various x may represent input signals of the model, various y may represent intermediate output signals of the model, and the concentration of interleukin antibody or antigen is the final output signal of the model;
thirdly, performing intelligent analysis of the interleukin concentration in the current detection by adopting the AI analysis model, specifically, taking the currently detected multiple process parameters and RGB color channel values of each pixel point of a colored product imaging area as input data of the model, and operating the model to obtain the interleukin antibody or antigen concentration in a detected specimen output by the model, thereby obtaining the actual immunocompetence or invasion degree of the human body or animal;
as shown in fig. 1, RGB color channel values of each pixel point of the colored product imaging area are input into the AI analysis model as visual features of the colored product, and simultaneously, a plurality of currently detected process parameters including a detected sample volume, a first set time length and a second set time length are also input into the AI analysis model, so as to realize intelligent detection of the concentration of the interleukin antibody or antigen corresponding to the color depth of the colored product, and the reliability and stability of the analysis result of the AI analysis model are ensured by a targeted structure and a customized training mechanism of the AI analysis model;
the method comprises the steps of obtaining each pixel point of a colored product imaging area, inputting RGB color channel values of each pixel point of the colored product imaging area into a model directly when each pixel point of the colored product imaging area is equal to the preset pixel number according to specific image acquisition conditions, interpolating the colored product imaging area so that each pixel point of the interpolated colored product imaging area is equal to the preset pixel number when each pixel point of the colored product imaging area is less than the preset pixel number, and inputting a plurality of pixel points of the preset pixel number of the central part of the colored product imaging area into the model as the RGB color channel values of each pixel point of the colored product imaging area when each pixel point of the colored product imaging area is greater than the preset pixel number.
The key points of the invention are as follows: the detection structure of the full-automatic interleukin concentration, the AI analysis model based on the BP neural network and the dynamic acquisition of each pixel point of the colored product imaging area are adopted, so that the speed and the accuracy of the interleukin concentration detection are improved.
The AI analysis system and method for interleukin concentration detection of the present invention will be specifically described below by way of examples.
Example 1
Fig. 2 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 1 of the present invention.
As shown in fig. 2, the AI analysis system for interleukin concentration detection includes the following components:
the carrier pushing mechanism is used for pushing a single solid carrier to the position right below the liquid dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody;
specifically, the antigen and antibody differ as follows:
1. the principle is different: the antigen is a substance capable of inducing an immune response of an organism and generating antibodies, and the antigen can be bacteria, viruses, microorganisms, biological agents, dead cells and the like;
2. the effects are different: the antibody is produced by plasma cells differentiated from B lymphocytes under the stimulation of the antigen, can be combined with the corresponding antigen, and is an immunoglobulin; the antigen is an invader, is a foreign substance, can cause certain damage to the organism in general, the antibody is a defender, is a substance generated by the organism, can effectively remove pathogens such as microorganisms, parasites and the like invaded into the organism, synthesizes toxins released by the pathogens, or removes certain self-antigens in the organism, and generally has a protective effect on the organism;
that is, antibodies may reflect the immunological competence of a human or animal, and antigens may reflect the degree of invasion of a human or animal;
the dropping execution mechanism is arranged at the dropping station and is used for executing the dropping treatment of a set volume of the sample to be detected containing the interleukin antibody or the antigen after each single solid-phase carrier is pushed to the position right below the dropping station so as to drop the set volume of the sample to be detected containing the interleukin antibody or the antigen into the surface of the solid-phase carrier;
the washing and separating mechanism is used for executing washing and separating operation to separate antigen-antibody complex formed on the surface of the solid phase carrier from other substances in the liquid on the surface of the solid phase carrier obtained by the drip treatment by adopting a washing mode after the drip execution mechanism finishes the drip treatment of the tested specimen for a first set time length;
an addition processing means for adding an enzyme-labeled interleukin antigen or antibody to the antigen-antibody complex formed on the surface of the solid carrier and binding to the surface of the solid carrier by a reaction after detecting that the washing separation means has completed a washing separation operation;
the substrate supplementing mechanism is used for adding a substrate of the enzyme reaction to the surface of the solid phase carrier after the adding treatment mechanism finishes the adding treatment for a second set time length so as to obtain a colored product, wherein the colored product is a product of the substrate catalyzed by the enzyme;
illustratively, the substrates of the enzymatic reaction may be different types of developers, and the developers are in a liquid state;
the AI analysis equipment is used for establishing an AI analysis model based on a BP neural network, taking the RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging area as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in a tested sample output by the model;
by way of example, a numerical simulation mode may be employed to complete the test operation of establishing and running an AI analysis model based on a BP neural network;
for example, a MATLAB toolbox may be employed to complete the test operations for the establishment and operation of the BP neural network-based AI analysis model;
the number of each pixel point input into the model is a preset pixel number, and the preset pixel number is positively correlated with the set volume;
illustratively, the positively associating the preset number of pixels with the set volume comprises: the value of the set volume is 1.0 milliliter, the value of the preset pixel number is 200, the value of the set volume is 1.5 milliliters, the value of the preset pixel number is 300, the value of the set volume is 2.0 milliliters, and the value of the preset pixel number is 400;
the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product;
wherein when the interleukin antigen is combined on the surface of the solid carrier, the sample to be tested contains the interleukin antibody, and the enzyme-labeled interleukin antigen is added to the antigen-antibody complex formed on the surface of the solid carrier;
wherein inputting the number of each pixel point in the model as the preset number of pixels includes: when the total number of the pixel points in the colored product imaging area is more than the preset pixel number, taking each pixel point with the preset pixel number at the central position of the colored product imaging area and inputting the pixel points into the model;
wherein inputting the number of each pixel point in the model as the preset number of pixels further comprises: when the total number of pixel points in the colored product imaging area is less than the preset pixel number, performing interpolation processing on the colored product imaging area to obtain an interpolated colored product imaging area with the total number of occupied pixel points equal to the set pixel number, and inputting each pixel point of the interpolated colored product imaging area into the model;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and the image area includes: performing nodding processing on the environment where the colored product is positioned by adopting nodding imaging equipment arranged at the liquid dropping station to obtain a real-time nodding image;
illustratively, performing a nodding process on an environment in which the colored product is located with a nodding imaging device disposed at the drip station to obtain a real-time nodding image includes: the nodding imaging device comprises an image sensor, wherein the image sensor is a CCD sensor or a CMOS sensor;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and further comprises: performing detection processing based on preset brightness imaging characteristics of colored products on a real-time nodding image to obtain an image area where the colored products are located in the real-time nodding image;
illustratively, the preset brightness imaging characteristic of the colored product is a preset brightness upper limit threshold value and a preset brightness lower limit threshold value, a pixel point of the brightness value between the preset brightness upper limit threshold value and the preset brightness lower limit threshold value in the real-time nodding image is taken as one pixel point forming an image area where the colored product is located, and a pixel point of the brightness value outside the preset brightness upper limit threshold value and the preset brightness lower limit threshold value in the real-time nodding image is taken as one pixel point forming an image area outside the image area where the colored product is located.
Example 2
Fig. 3 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 2 of the present invention.
As shown in fig. 3, unlike the system in fig. 2, the AI analysis system for interleukin concentration detection in fig. 3 further includes:
the instant display device is connected with the AI analysis device and is used for receiving and displaying the concentration of the interleukin antibody or antigen in the tested sample output by the model;
the instant display device is, for example, a liquid crystal display or an LED display array composed of a plurality of LED units laid out in a planar matrix structure.
Example 3
Fig. 4 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 3 of the present invention.
As shown in fig. 4, unlike the system in fig. 2, the AI analysis system for interleukin concentration detection in fig. 4 further includes:
the synchronous driving device is respectively connected with the carrier pushing mechanism and the drip execution mechanism and is used for executing the pushing of the single solid carrier of the carrier pushing mechanism and the synchronous control of drip treatment of the drip execution mechanism;
illustratively, performing the simultaneous control of the pushing of a single portion of the solid phase carrier by the carrier pushing mechanism and the drip treatment by the drip actuator includes: triggering the drip treatment of the drip execution mechanism by adopting the rising edge of the square wave;
wherein, the synchronous control of the pushing of the single solid phase carrier of the carrier pushing mechanism and the drip treatment of the drip actuating mechanism comprises: and triggering the drip execution mechanism to execute drip treatment once when the carrier pushing mechanism completes pushing of a single solid carrier every time.
Example 4
Fig. 5 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 4 of the present invention.
As shown in fig. 5, unlike the system in fig. 2, the AI analysis system for interleukin concentration detection in fig. 5 further includes:
the time service device is respectively connected with the washing separation mechanism and the substrate supplementing mechanism and is used for providing timing service of a first set time length for the washing separation mechanism;
the time service device is also used for providing timing service of a second set time length for the substrate feeding mechanism;
illustratively, the value of the second set time length is greater than or equal to the value of the first set time length.
Example 5
Fig. 6 is a schematic structural diagram of an AI analysis system for interleukin concentration detection according to embodiment 5 of the present invention.
As shown in fig. 6, unlike the system in fig. 2, the AI analysis system for interleukin concentration detection in fig. 6 further includes:
the data storage device is connected with the AI analysis device and used for storing model parameters of an AI analysis model based on the BP neural network;
the data storage device may be one of an MMC memory card, a FLASH memory chip, or an SD memory card, for example.
Next, further description will be given of various embodiments of the present invention.
In any of the above embodiments, optionally, in the AI analysis system for interleukin concentration detection:
when the interleukin antibody is bound to the surface of the solid support, the sample to be tested contains the interleukin antigen, and the enzyme-labeled interleukin antibody is added to the antigen-antibody complex formed on the surface of the solid support.
In any of the above embodiments, optionally, in the AI analysis system for interleukin concentration detection:
taking the RGB color channel values of each pixel point of the set volume, the first set time length, the second set time length and the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the examined specimen output by the model comprises: the RGB color channel value of each pixel point of the colored product imaging region is R color channel value, G color channel value and B color channel value of each pixel point of the colored product imaging region in RGB color space;
illustratively, each of the R color channel value, the G color channel value, and the B color channel value has a value between 0-255.
In any of the above embodiments, optionally, in the AI analysis system for interleukin concentration detection:
wherein taking the set volume, the first set time length, the second set time length and the RGB color channel value of each pixel point of the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the examined specimen output by the model comprises: adopting RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging area to respectively carry out binarization processing and then inputting the binary processing into the model;
wherein taking the set volume, the first set time length, the second set time length and the RGB color channel values of each pixel point of the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the specimen output by the model further comprises: the concentration of the interleukin antibody or antigen in the specimen output by the model is binarized representation data.
Example 6
Embodiment 6 of the present invention provides a step of an AI analysis method for interleukin concentration detection, comprising the steps of:
a carrier pushing mechanism is used for pushing a single solid carrier to the position right below a dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody;
specifically, the antigen and antibody differ as follows:
1. the principle is different: the antigen is a substance capable of inducing an immune response of an organism and generating antibodies, and the antigen can be bacteria, viruses, microorganisms, biological agents, dead cells and the like;
2. the effects are different: the antibody is produced by plasma cells differentiated from B lymphocytes under the stimulation of the antigen, can be combined with the corresponding antigen, and is an immunoglobulin; the antigen is an invader, is a foreign substance, can cause certain damage to the organism in general, the antibody is a defender, is a substance generated by the organism, can effectively remove pathogens such as microorganisms, parasites and the like invaded into the organism, synthesizes toxins released by the pathogens, or removes certain self-antigens in the organism, and generally has a protective effect on the organism;
that is, antibodies may reflect the immunological competence of a human or animal, and antigens may reflect the degree of invasion of a human or animal;
a drip actuator is arranged at the drip station and is used for executing drip treatment of a set volume of sample to be detected containing the interleukin antibody or antigen after each single solid phase carrier is pushed to the position right below the drip station so as to drip the set volume of sample to be detected containing the interleukin antibody or antigen onto the surface of the solid phase carrier;
a washing and separating mechanism is used for executing washing and separating operation to separate antigen-antibody complex formed on the surface of the solid phase carrier from other substances in the liquid on the surface of the solid phase carrier obtained by the drip treatment in a washing mode after the drip execution mechanism completes the drip treatment of the tested specimen for a first set time length;
using an addition processing mechanism for adding an enzyme-labeled interleukin antigen or antibody to the antigen-antibody complex formed on the surface of the solid carrier and binding to the surface of the solid carrier by a reaction after detecting that the washing separation mechanism completes a washing separation operation;
a substrate supplementing mechanism is used for adding a substrate of the enzyme reaction to the surface of the solid phase carrier after the adding treatment mechanism finishes the adding treatment for a second set time length so as to obtain a colored product, wherein the colored product is a product of the substrate catalyzed by the enzyme;
illustratively, the substrates of the enzymatic reaction may be different types of developers, and the developers are in a liquid state;
using an AI analysis device for establishing an AI analysis model based on a BP neural network, taking RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging region as input data of the model, and running the model to obtain the concentration of interleukin antibodies or antigens in a detected specimen output by the model;
by way of example, a numerical simulation mode may be employed to complete the test operation of establishing and running an AI analysis model based on a BP neural network;
for example, a MATLAB toolbox may be employed to complete the test operations for the establishment and operation of the BP neural network-based AI analysis model;
the number of each pixel point input into the model is a preset pixel number, and the preset pixel number is positively correlated with the set volume;
illustratively, the positively associating the preset number of pixels with the set volume comprises: the value of the set volume is 1.0 milliliter, the value of the preset pixel number is 200, the value of the set volume is 1.5 milliliters, the value of the preset pixel number is 300, the value of the set volume is 2.0 milliliters, and the value of the preset pixel number is 400;
the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product;
wherein when the interleukin antigen is combined on the surface of the solid carrier, the sample to be tested contains the interleukin antibody, and the enzyme-labeled interleukin antigen is added to the antigen-antibody complex formed on the surface of the solid carrier;
wherein inputting the number of each pixel point in the model as the preset number of pixels includes: when the total number of the pixel points in the colored product imaging area is more than the preset pixel number, taking each pixel point with the preset pixel number at the central position of the colored product imaging area and inputting the pixel points into the model;
wherein inputting the number of each pixel point in the model as the preset number of pixels further comprises: when the total number of pixel points in the colored product imaging area is less than the preset pixel number, performing interpolation processing on the colored product imaging area to obtain an interpolated colored product imaging area with the total number of occupied pixel points equal to the set pixel number, and inputting each pixel point of the interpolated colored product imaging area into the model;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and the image area includes: performing nodding processing on the environment where the colored product is positioned by adopting nodding imaging equipment arranged at the liquid dropping station to obtain a real-time nodding image;
illustratively, performing a nodding process on an environment in which the colored product is located with a nodding imaging device disposed at the drip station to obtain a real-time nodding image includes: the nodding imaging device comprises an image sensor, wherein the image sensor is a CCD sensor or a CMOS sensor;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and further comprises: performing detection processing based on preset brightness imaging characteristics of colored products on a real-time nodding image to obtain an image area where the colored products are located in the real-time nodding image;
illustratively, the preset brightness imaging characteristic of the colored product is a preset brightness upper limit threshold value and a preset brightness lower limit threshold value, a pixel point of the brightness value between the preset brightness upper limit threshold value and the preset brightness lower limit threshold value in the real-time nodding image is taken as one pixel point forming an image area where the colored product is located, and a pixel point of the brightness value outside the preset brightness upper limit threshold value and the preset brightness lower limit threshold value in the real-time nodding image is taken as one pixel point forming an image area outside the image area where the colored product is located.
In addition, in the AI analysis system and method for interleukin concentration detection shown in accordance with the present invention:
the AI analysis model is a BP neural network after training for a set number of times, and the set number of times is positively correlated with the set volume;
the AI analysis model is a BP neural network after training for a set number of times, and the forward correlation between the preset pixel number and the set volume includes: and taking the concentration of the interleukin antibody or antigen in the tested sample with the measured concentration in a certain previous detection as output data of the network, and taking the RGB color channel values of each pixel point of the set volume, the first set time length, the second set time length and the colored product imaging region corresponding to the certain previous detection as input data of the network to complete single training of the BP neural network.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Claims (7)
1. An AI analysis system for interleukin concentration detection, the system comprising:
the carrier pushing mechanism is used for pushing a single solid carrier to the position right below the liquid dropping station, and the surface of the solid carrier is combined with interleukin antigen or antibody;
the dropping execution mechanism is arranged at the dropping station and is used for executing the dropping treatment of a set volume of the sample to be detected containing the interleukin antibody or the antigen after each single solid-phase carrier is pushed to the position right below the dropping station so as to drop the set volume of the sample to be detected containing the interleukin antibody or the antigen into the surface of the solid-phase carrier;
the washing and separating mechanism is used for executing washing and separating operation to separate antigen-antibody complex formed on the surface of the solid phase carrier from other substances in the liquid on the surface of the solid phase carrier obtained by the drip treatment by adopting a washing mode after the drip execution mechanism finishes the drip treatment of the tested specimen for a first set time length;
an addition processing means for adding an enzyme-labeled interleukin antigen or antibody to the antigen-antibody complex formed on the surface of the solid carrier and binding to the surface of the solid carrier by a reaction after detecting that the washing separation means has completed a washing separation operation;
the substrate supplementing mechanism is used for adding a substrate of the enzyme reaction to the surface of the solid phase carrier after the adding treatment mechanism finishes the adding treatment for a second set time length so as to obtain a colored product, wherein the colored product is a product of the substrate catalyzed by the enzyme;
the AI analysis equipment is used for establishing an AI analysis model based on a BP neural network, taking the RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging area as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in a tested sample output by the model;
the number of each pixel point input into the model is a preset pixel number, and the preset pixel number is positively correlated with the set volume;
the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product;
wherein when the interleukin antigen is combined on the surface of the solid carrier, the sample to be tested contains the interleukin antibody, and the enzyme-labeled interleukin antigen is added to the antigen-antibody complex formed on the surface of the solid carrier;
the inputting of the number of each pixel point in the model as the preset number of pixels includes: when the total number of the pixel points in the colored product imaging area is more than the preset pixel number, taking each pixel point with the preset pixel number at the central position of the colored product imaging area and inputting the pixel points into the model;
wherein inputting the number of each pixel point in the model as the preset number of pixels further comprises: when the total number of pixel points in the colored product imaging area is less than the preset pixel number, performing interpolation processing on the colored product imaging area to obtain an interpolated colored product imaging area with the total number of occupied pixel points equal to the set pixel number, and inputting each pixel point of the interpolated colored product imaging area into the model;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and the image area includes: performing nodding processing on the environment where the colored product is positioned by adopting nodding imaging equipment arranged at the liquid dropping station to obtain a real-time nodding image;
wherein the colored product imaging area is an image area where the colored product is located in an image obtained by performing nodding on the colored product, and further comprises: performing detection processing based on preset brightness imaging characteristics of colored products on a real-time nodding image to obtain an image area where the colored products are located in the real-time nodding image;
when the interleukin antibody is bound to the surface of the solid support, the sample to be tested contains the interleukin antigen, and the enzyme-labeled interleukin antibody is added to the antigen-antibody complex formed on the surface of the solid support.
2. The AI analysis system for interleukin concentration detection according to claim 1, wherein said system further comprises:
and the instant display device is connected with the AI analysis device and is used for receiving and displaying the concentration of the interleukin antibody or antigen in the tested sample output by the model.
3. The AI analysis system for interleukin concentration detection according to claim 1, wherein said system further comprises:
the synchronous driving device is respectively connected with the carrier pushing mechanism and the drip execution mechanism and is used for executing the pushing of the single solid carrier of the carrier pushing mechanism and the synchronous control of drip treatment of the drip execution mechanism;
wherein, the synchronous control of the pushing of the single solid phase carrier of the carrier pushing mechanism and the drip treatment of the drip actuating mechanism comprises: and triggering the drip execution mechanism to execute drip treatment once when the carrier pushing mechanism completes pushing of a single solid carrier every time.
4. The AI analysis system for interleukin concentration detection according to claim 1, wherein said system further comprises:
the time service device is respectively connected with the washing separation mechanism and the substrate supplementing mechanism and is used for providing timing service of a first set time length for the washing separation mechanism;
the time service device is further used for providing timing service for the substrate replenishing mechanism for a second set time length.
5. The AI analysis system for interleukin concentration detection according to claim 1, wherein said system further comprises:
and the data storage device is connected with the AI analysis device and is used for storing model parameters of an AI analysis model based on the BP neural network.
6. The AI analysis system for interleukin concentration detection according to any one of claims 1 to 5, wherein:
taking the RGB color channel values of each pixel point of the set volume, the first set time length, the second set time length and the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the examined specimen output by the model comprises: the RGB color channel value of each pixel of the color product imaging region is an R color channel value, a G color channel value, and a B color channel value of each pixel of the color product imaging region in the RGB color space.
7. The AI analysis system for interleukin concentration detection according to any one of claims 1 to 5, wherein:
wherein taking the set volume, the first set time length, the second set time length and the RGB color channel value of each pixel point of the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the examined specimen output by the model comprises: adopting RGB color channel values of each pixel point of a set volume, a first set time length, a second set time length and a colored product imaging area to respectively carry out binarization processing and then inputting the binary processing into the model;
wherein taking the set volume, the first set time length, the second set time length and the RGB color channel values of each pixel point of the colored product imaging region as input data of the model, and operating the model to obtain the concentration of the interleukin antibody or antigen in the specimen output by the model further comprises: the concentration of the interleukin antibody or antigen in the specimen output by the model is binarized representation data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310472438.9A CN116203253B (en) | 2023-04-27 | 2023-04-27 | AI analysis system and method for detecting interleukin concentration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310472438.9A CN116203253B (en) | 2023-04-27 | 2023-04-27 | AI analysis system and method for detecting interleukin concentration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116203253A CN116203253A (en) | 2023-06-02 |
| CN116203253B true CN116203253B (en) | 2023-07-11 |
Family
ID=86507977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310472438.9A Active CN116203253B (en) | 2023-04-27 | 2023-04-27 | AI analysis system and method for detecting interleukin concentration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116203253B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018039816A1 (en) * | 2016-08-30 | 2018-03-08 | 刘长亮 | Neural network electrical activity detection system and screening method for neuropsychiatric drugs based on system |
| CN109036571A (en) * | 2014-12-08 | 2018-12-18 | 20/20基因***股份有限公司 | The method and machine learning system of a possibility that for predicting with cancer or risk |
| CN111260677A (en) * | 2020-02-20 | 2020-06-09 | 腾讯科技（深圳）有限公司 | Cell analysis method, device, equipment and storage medium based on microscopic image |
| CN111402957A (en) * | 2020-03-10 | 2020-07-10 | 成都益安博生物技术有限公司 | Immune characteristic recognition method based on neural network |
| CN113178228A (en) * | 2021-05-25 | 2021-07-27 | 郑州中普医疗器械有限公司 | Cell analysis method based on nuclear DNA analysis, computer device, and storage medium |
| CN113989284A (en) * | 2021-12-29 | 2022-01-28 | 广州思德医疗科技有限公司 | Helicobacter pylori assists detecting system and detection device |
| CN114152557A (en) * | 2021-11-16 | 2022-03-08 | 深圳元视医学科技有限公司 | Image analysis based blood cell counting method and system |
| CN114250285A (en) * | 2020-09-21 | 2022-03-29 | 上海市公共卫生临床中心 | Respiratory tract virus infection (danger) severe early warning based on interleukin 37 |
| WO2023017290A1 (en) * | 2021-08-10 | 2023-02-16 | University Of Helsinki | Image-based antibody test |
| CN115954102A (en) * | 2023-03-14 | 2023-04-11 | 中山大学附属第一医院 | Artificial joint prosthesis peripheral infection diagnosis model and diagnosis system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7225172B2 (en) * | 1999-07-01 | 2007-05-29 | Yeda Research And Development Co. Ltd. | Method and apparatus for multivariable analysis of biological measurements |
-
2023
- 2023-04-27 CN CN202310472438.9A patent/CN116203253B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109036571A (en) * | 2014-12-08 | 2018-12-18 | 20/20基因***股份有限公司 | The method and machine learning system of a possibility that for predicting with cancer or risk |
| WO2018039816A1 (en) * | 2016-08-30 | 2018-03-08 | 刘长亮 | Neural network electrical activity detection system and screening method for neuropsychiatric drugs based on system |
| CN111260677A (en) * | 2020-02-20 | 2020-06-09 | 腾讯科技（深圳）有限公司 | Cell analysis method, device, equipment and storage medium based on microscopic image |
| CN111402957A (en) * | 2020-03-10 | 2020-07-10 | 成都益安博生物技术有限公司 | Immune characteristic recognition method based on neural network |
| CN114250285A (en) * | 2020-09-21 | 2022-03-29 | 上海市公共卫生临床中心 | Respiratory tract virus infection (danger) severe early warning based on interleukin 37 |
| CN113178228A (en) * | 2021-05-25 | 2021-07-27 | 郑州中普医疗器械有限公司 | Cell analysis method based on nuclear DNA analysis, computer device, and storage medium |
| WO2023017290A1 (en) * | 2021-08-10 | 2023-02-16 | University Of Helsinki | Image-based antibody test |
| CN114152557A (en) * | 2021-11-16 | 2022-03-08 | 深圳元视医学科技有限公司 | Image analysis based blood cell counting method and system |
| CN113989284A (en) * | 2021-12-29 | 2022-01-28 | 广州思德医疗科技有限公司 | Helicobacter pylori assists detecting system and detection device |
| CN115954102A (en) * | 2023-03-14 | 2023-04-11 | 中山大学附属第一医院 | Artificial joint prosthesis peripheral infection diagnosis model and diagnosis system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116203253A (en) | 2023-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5675638B2 (en) | Methods for diagnosing allergic reactions | |
| Nouri et al. | Designing a direct ELISA kit for the detection of Staphylococcus aureus enterotoxin A in raw milk samples | |
| US6410252B1 (en) | Methods for measuring T cell cytokines | |
| EP4148118A1 (en) | System, device and method for high-throughput multi-plexed detection | |
| EP0866968B1 (en) | A process for in vitro analysis of toxic and allergenic substances | |
| CN116203253B (en) | AI analysis system and method for detecting interleukin concentration | |
| CN111521812A (en) | Neuromyelitis optica pedigree disease biomarker group and application thereof, protein chip and kit | |
| CN112331344B (en) | Immune state evaluation method and application | |
| Karulin et al. | Artificial intelligence-based counting algorithm enables accurate and detailed analysis of the broad spectrum of spot morphologies observed in antigen-specific B cell EliSpot and FluoroSpot assays | |
| EP1718970B1 (en) | Method and device for the determination of several analytes with simultaneous internal verification in a graphical combination | |
| US20180095075A1 (en) | Analyte detection and methods therefor | |
| RU2009144277A (en) | METHODS AND COMPOSITIONS FOR DIAGNOSTIC OF OSTEOARTHRITIS IN AN ANIMAL FAMILY | |
| Puchades et al. | ELISA tools for food PDO authentication | |
| GB2591009A (en) | Composite target-tumor serum nucleic acid ligand detection method and kit | |
| Eyer | One by one–insights into complex immune responses through functional single-cell analysis | |
| CN109781987A (en) | Terminal effector T cell subgroup is preparing the application in aided assessment aplastic amenia feelings degree kit | |
| Rubina et al. | Multiplex assay of allergen-specific and total immunoglobulins of E and G classes in the biochip format. | |
| US20030049626A1 (en) | Antibody-based analysis of matrix protein arrays | |
| CN213275622U (en) | Kit for simultaneously detecting 20 kinds of food specific IgG | |
| CA2364148C (en) | Detection and quantification of one or more target analytes in a sample using spatially localized analyte reproduction | |
| JP6170367B2 (en) | Multiwell analysis method | |
| CN107151697A (en) | Method and kit for predicting the response that Chronic Hepatitis B is treated to IFN α | |
| Fleisher | Immunological tests–from the microscope to whole genome analysis | |
| Rosenberg et al. | Tay-Sachs carrier detection by mechanized serum hexosaminidase assay | |
| Tian et al. | Screening strategy of aptamer and its application in food contaminants determination |
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 |