CN113380318A - Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system - Google Patents
Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system Download PDFInfo
- Publication number
- CN113380318A CN113380318A CN202110632492.6A CN202110632492A CN113380318A CN 113380318 A CN113380318 A CN 113380318A CN 202110632492 A CN202110632492 A CN 202110632492A CN 113380318 A CN113380318 A CN 113380318A
- Authority
- CN
- China
- Prior art keywords
- cell
- cells
- flow cytometry
- data
- population
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
-
- 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
- G01N33/569—Immunoassay; Biospecific binding assay; Materials therefor for microorganisms, e.g. protozoa, bacteria, viruses
- G01N33/56966—Animal cells
- G01N33/56972—White blood cells
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- 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
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention provides an artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method, which comprises the following steps: step S1, extracting flow cell data in a case; step S2, removing cell debris other than the effective cells from the flow cytometry data to obtain effective flow cytometry data; step S3, performing weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data obtained in the step S2 on the multidimensional Gaussian model; step S4, detecting the density of each cell group and judging the cell group type; step S5, according to the determined cell population category, performing cross-tube matching of the cell population to obtain the number, proportion and phenotype of various cells; and step S6, judging the abnormal cell type according to the number, the proportion and the phenotype of the various cells obtained in the step S5.
Description
Technical Field
The invention relates to the technical field of flow cytometry and software, in particular to an artificial intelligence assisted flow cytometry 40CD immunophenotype detection method and system.
Background
In the clinical screening of acute leukemia, flow cytometry is an important inspection means, and can rapidly and accurately perform multi-parameter quantitative analysis and sorting on internalization characteristics of single cells. At present, flow detection analysis mainly uses a manual gating analysis technology, which refers to selecting a specific cell population to be analyzed on a two-dimensional scatter diagram with a certain selected parameter according to the cell population distribution of the diagram. The doctor analyzes whether the case has cells with abnormal phenotype with acute leukemia, and diagnoses the case.
The traditional flow detection analysis method has the following disadvantages:
1. the need to spend a great deal of manpower classifying the flow data increases the labor cost of the hospital.
2. The professional quality of the analysts is high, the time for culturing is long, and particularly doctors with the report reviewing and sending capacity are not available or are few in number in general hospitals.
3. Manual gating may affect the cell classification result by subjective factors of the operator, resulting in erroneous final diagnosis results.
Disclosure of Invention
The object of the present invention is to solve at least one of the technical drawbacks mentioned.
Therefore, the invention aims to provide an artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method.
In order to achieve the above object, an embodiment of the present invention provides an artificial intelligence assisted flow cytometry 40CD immunophenotyping method, which comprises the following steps:
step S1, extracting flow cell data in a case;
step S2, removing cell debris other than the effective cells from the flow cytometry data to obtain effective flow cytometry data;
step S3, performing weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data obtained in the step S2 on the multidimensional Gaussian model;
step S4, detecting the density of each cell group and judging the cell group type;
step S5, according to the determined cell population category, performing cross-tube matching of the cell population to obtain the number, proportion and phenotype of various cells;
and step S6, judging the abnormal cell type according to the number, the proportion and the phenotype of the various cells obtained in the step S5.
Further, the file in FCS format or LM0 format is parsed to extract flow cytometric data in the case.
Further, in the step S2, two-dimensional nuclear density analysis is performed on all the cells on FSC-A/SSC-A, a cell group with high density is obtained as an effective cell group according to the analysis result, and then cell debris except the effective cells is artificially removed.
Further, in step S4, analyzing the density distribution of all the valid flow cytometry data on different fluorescent labels by using one-dimensional nuclear density estimation, and obtaining the negative-positive boundary of the cell on the fluorescent label; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
Further, in the step S5, after obtaining the specific population number of each kind of cell, finding the boundary of the kind of cell according to the distribution on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
The invention also provides an artificial intelligence assisted flow cytometry 40CD immunophenotype detection system, which comprises:
the cell data extraction module is used for extracting flow cell data in a case;
the cell debris removing module is used for removing cell debris except effective cells from the flow cytometry data to obtain effective flow cytometry data;
the clustering module is used for carrying out weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data on the multidimensional Gaussian model;
the density detection module is used for carrying out density detection on each cell population and judging the cell population type;
the cross-tube matching module is used for performing cross-tube matching on the cell populations according to the determined cell population types so as to obtain the number, proportion and phenotype of various cells;
and the cell abnormal type judging module is used for judging the cell abnormal type according to the obtained number, proportion and phenotype of various cells.
Further, the cell data extraction module parses a file in FCS format or LM0 format to extract flow cytometric data in cases.
Further, the cell debris removing module performs two-dimensional nuclear density analysis on all cells on FSC-A/SSC-A, obtains a cell population with high density as an effective cell population according to the analysis result, and then artificially removes cell debris except the effective cells.
Further, the density detection module analyzes the density distribution of all effective flow cytometry data on different fluorescent markers by utilizing one-dimensional nuclear density estimation to obtain the negative and positive boundaries of the cells on the fluorescent markers; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
Further, after the cross-tube matching module obtains the specific population number of various types of cells, finding the boundary of the cells according to the distribution of the cells on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
According to the artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system provided by the embodiment of the invention, the following technical problems can be solved:
(1) whether cells with abnormal phenotypes exist in the cases is analyzed through AI, and no false negative cases are ensured;
(2) for the judgment of negative and positive cases, AI can ensure the same accuracy rate as the artificial result or even higher than the artificial result, and for the positive cases, abnormal cell types are diagnosed;
(3) aiming at the CD marks with different data of each tube, the cell types mainly distinguished by each tube can be classified, and the proportion of the cell types is correspondingly counted;
(4) an AI prompt can be given for a case or other suspected case for which the AI cannot be normally analyzed.
The artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method provided by the embodiment of the invention has the following technical effects: firstly, parallel operation can be carried out on a plurality of data to be analyzed, the analysis time of each file is about 90s, and the time cost can be saved while the labor cost is saved; secondly, all data are analyzed objectively, and cell grouping is not influenced by artificial subjective factors; finally, noise interference can be effectively removed, so that abnormal conditions of cell groups can be automatically obtained and preliminary diagnosis can be performed.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method of artificial intelligence assisted flow cytometry 40CD immunophenotyping according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an artificial intelligence assisted flow cytometry 40CD immunophenotype detection method according to an embodiment of the present invention;
FIG. 3 is a block diagram of an artificial intelligence assisted flow cytometry 40CD immunophenotypic detection system according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
As shown in fig. 1, the artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method of the embodiment of the present invention includes the following steps:
in step S1, flow cytometric data of the case is extracted.
In this step, the file in FCS format or LM0 format is parsed to extract flow cytometric data in the case.
In step S2, cell debris other than the valid cells is removed from the flow cytometry data, and valid flow cytometry data is obtained.
Specifically, two-dimensional nuclear density analysis is carried out on all cells on FSC-A/SSC-A, a cell group with higher density is obtained as an effective cell group according to the analysis result, and then cell fragments except the effective cells are removed by combining with an artificial detection habit. The method realizes automatic analysis to obtain effective cell groups, and performs primary screening; and then, artificial fine detection is combined to perform secondary screening, so that effective flow cytometry data with more accurate results can be obtained.
Step S3, performing weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture Model (Gaussian-Mixed-Model), and establishing a multi-dimensional Gaussian Model. Then, the cell data is divided into different cell groups according to the probability distribution of the valid flow cytometry data obtained in step S2 on the multidimensional gaussian model.
By using the clustering algorithm of the Gaussian-Mixed-Model, the probability distribution of the effective loss cell data in step S2 can be obtained, so as to divide the effective flow cytometry data into a plurality of cell groups. This is to lay down the classification basis for the cell class identification of the subsequent step.
In step S4, density detection is performed for each cell population, and the cell population type is determined.
Specifically, the density distribution of all effective flow cytometry data on different fluorescent markers is analyzed by utilizing one-dimensional nuclear density estimation to obtain the positive and negative boundaries of the cells on the fluorescent markers; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
In this step, according to the result of the gaussian clustering analysis in step S3, density detection is performed on each cell group, and a fluorescence labeling threshold is obtained to determine the phenotype of the cell group, thereby obtaining the category of each cell group.
In the embodiment of the invention, the cell categories mainly distinguished in each tube can be classified according to the CD marks of each tube, and the proportion of the cell categories is correspondingly counted. By the mode, the cell group classification is realized, statistics aiming at cell data of each tube can be realized, the proportion of different cell data of each tube is analyzed by taking the test tube as a unit, and the multi-dimensional statistical analysis is realized.
Step S5, performing cross-tube matching of the cell population according to the determined cell population category to obtain the number, ratio and phenotype of each cell.
Specifically, after obtaining the specific population number of each kind of cells, finding the boundary of the kind of cells according to the distribution of the cells on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
And step S6, judging the abnormal cell type according to the number, the proportion and the phenotype of the various cells obtained in the step S5.
For example, in this step, it is determined whether there is an abnormality associated with acute leukemia and the type of the abnormality based on the number, ratio and representation of various cells, thereby performing a preliminary diagnosis.
In addition, an AI prompt can be given for cases that the AI cannot be normally analyzed or other suspected cases.
It should be noted that the method of the present invention is not limited to the abnormality determination of acute leukemia, but the above is only an exemplary function, and other types of abnormality detection can also be implemented as required, and the method has a wide application range and is suitable for popularization and use.
According to the artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method provided by the embodiment of the invention, the following technical problems can be solved:
(1) whether cells with abnormal phenotypes exist in the cases is analyzed through AI, and no false negative cases are ensured;
(2) for the judgment of negative and positive cases, AI can ensure the same accuracy rate as the artificial result or even higher than the artificial result, and for the positive cases, abnormal cell types are diagnosed;
(3) aiming at the CD marks with different data of each tube, the cell types mainly distinguished by each tube can be classified, and the proportion of the cell types is correspondingly counted;
(4) an AI prompt can be given for a case or other suspected case for which the AI cannot be normally analyzed.
As shown in fig. 3, the artificial intelligence assisted flow cytometry 40CD immunophenotyping detection system provided by the embodiment of the present invention comprises: the cell detection system comprises a cell data extraction module 1, a cell debris removal module 2, a clustering module 3, a density detection module 4, a cross-tube matching module 5 and a cell abnormity type judgment module 6.
Specifically, the cell data extraction module 1 is used for extracting flow cytometry data in a case.
In an embodiment of the present invention, the cell data extraction module 1 parses a file in FCS format or LM0 format to extract flow cytometric data in a case.
The cell debris removing module 2 is used for removing cell debris except for effective cells from the flow cytometry data to obtain effective flow cytometry data.
Specifically, the cell debris removal module 2 performs two-dimensional nuclear density analysis on all cells on FSC-A/SSC-A, obtains a cell population with high density as an effective cell population according to the analysis result, and then artificially removes cell debris except the effective cells. The method realizes automatic analysis to obtain effective cell groups, and performs primary screening; and then, artificial fine detection is combined to perform secondary screening, so that effective flow cytometry data with more accurate results can be obtained.
The clustering module 3 is used for performing weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; and dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data on the multidimensional Gaussian model.
The clustering and clustering module 3 obtains the probability distribution of the effective loss cell data by using the clustering and clustering algorithm of the Gaussian-Mixed-Model, so as to divide the effective flow cytometry data into a plurality of cell groups. This is to lay down the classification basis for the cell class identification of the subsequent step.
The density detection module 4 is used for performing density detection on each cell group and judging the cell group type.
Specifically, the density detection module 4 analyzes the density distribution of all effective flow cytometry data on different fluorescent markers by using one-dimensional nuclear density estimation to obtain the negative and positive boundaries of cells on the fluorescent markers; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
The density detection module 4 performs density detection on each cell group according to the Gaussian clustering analysis result, obtains a fluorescence labeling threshold value, judges the phenotype of the cell group, and further obtains the category of each cell group.
In the embodiment of the invention, the cell categories mainly distinguished in each tube can be classified according to the CD marks of each tube, and the proportion of the cell categories is correspondingly counted. By the mode, the cell group classification is realized, statistics aiming at cell data of each tube can be realized, the proportion of different cell data of each tube is analyzed by taking the test tube as a unit, and the multi-dimensional statistical analysis is realized.
The cross-tube matching module 5 is used for performing cross-tube matching of the cell population according to the determined cell population category so as to obtain the number, proportion and phenotype of various cells.
Specifically, after the cross-tube matching module 5 obtains the specific population number of various types of cells, the boundary of the cells is found according to the distribution of the cells on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
The cell abnormal type judging module 6 is used for judging the cell abnormal type according to the obtained number, proportion and phenotype of various cells.
For example, the number, ratio and representation of various cells are used to determine whether there is an abnormality or abnormality type associated with acute leukemia, so as to perform a preliminary diagnosis.
In addition, an AI prompt can be given for cases that the AI cannot be normally analyzed or other suspected cases.
It should be noted that the method of the present invention is not limited to the abnormality determination of acute leukemia, but the above is only an exemplary function, and other types of abnormality detection can also be implemented as required, and the method has a wide application range and is suitable for popularization and use.
The artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and the system thereof have the following technical effects: firstly, parallel operation can be carried out on a plurality of data to be analyzed, the analysis time of each file is about 90s, and the time cost can be saved while the labor cost is saved; secondly, all data are analyzed objectively, and cell grouping is not influenced by artificial subjective factors; finally, noise interference can be effectively removed, so that abnormal conditions of cell groups can be automatically obtained and preliminary diagnosis can be performed.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. An artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method is characterized by comprising the following steps:
step S1, extracting flow cell data in a case;
step S2, removing cell debris other than the effective cells from the flow cytometry data to obtain effective flow cytometry data;
step S3, performing weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data obtained in the step S2 on the multidimensional Gaussian model;
step S4, detecting the density of each cell group and judging the cell group type;
step S5, according to the determined cell population category, performing cross-tube matching of the cell population to obtain the number, proportion and phenotype of various cells;
and step S6, judging the abnormal cell type according to the number, the proportion and the phenotype of the various cells obtained in the step S5.
2. The artificial intelligence assisted flow cytometry 40CD immunophenotype detection method of claim 1, wherein files in FCS format or LM0 format are parsed to extract flow cytometric data in case.
3. The method for detecting 40CD immunophenotype according to claim 1, wherein in step S2, two-dimensional nuclear density analysis is performed on all cells on FSC-A/SSC-A, a dense cell group is obtained as an effective cell group according to the analysis result, and then cell debris except the effective cells is removed manually.
4. The artificial intelligence assisted flow cytometry 40CD immunophenotype detection method of claim 1, wherein in step S4, the density distribution of all valid flow cytometry data on different fluorescent markers is analyzed by using one-dimensional nuclear density estimation to obtain the negative and positive boundaries of cells on such fluorescent markers; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
5. The artificial intelligence assisted flow cytometry 40CD immunophenotype assay of claim 1, wherein in step S5, after obtaining the specific population of each type of cell, finding the boundary of each type of cell according to its distribution on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
6. An artificial intelligence assisted flow cytometry 40CD immunophenotypic test system, comprising:
the cell data extraction module is used for extracting flow cell data in a case;
the cell debris removing module is used for removing cell debris except effective cells from the flow cytometry data to obtain effective flow cytometry data;
the clustering module is used for carrying out weighted combination on the Gaussian distribution of the fluorescence intensity of each antibody through a clustering algorithm based on a Gaussian mixture model to establish a multidimensional Gaussian model; dividing the cell data into different cell groups according to the probability distribution of the effective flow cytometry data on the multidimensional Gaussian model;
the density detection module is used for carrying out density detection on each cell population and judging the cell population type;
the cross-tube matching module is used for performing cross-tube matching on the cell populations according to the determined cell population types so as to obtain the number, proportion and phenotype of various cells;
and the cell abnormal type judging module is used for judging the cell abnormal type according to the obtained number, proportion and phenotype of various cells.
7. The artificial intelligence assisted flow cytometry 40CD immunophenotype detection system of claim 6, wherein the cellular data extraction module parses a file in FCS format or LM0 format to extract flow cellular data in a case.
8. The system of claim 6, wherein the cell debris removal module performs two-dimensional nuclear density analysis on all cells on FSC-A/SSC-A, obtains a dense cell population as an effective cell population according to the analysis result, and then combines the cell debris removal with the effective cell removal.
9. The artificial intelligence assisted flow cytometry 40CD immunophenotype detection system of claim 6, wherein the density detection module analyzes the density distribution of all valid flow cytometry data over different fluorescent markers using one-dimensional nuclear density estimation to obtain negative and positive boundaries of cells over such fluorescent markers; the phenotype of each population of cells on the different antibodies was confirmed by means of an internal control, and the classification of each population of cells was confirmed.
10. The artificial intelligence assisted flow cytometry 40CD immunophenotype detection system of claim 6, wherein the cross-tube matching module, upon obtaining a specific population of each type of cell, finds the boundaries of each type of cell based on its distribution on SSC-A/CD 45; cross-tube matching is achieved by known boundaries of cells to detect the number, proportion, and phenotype of cells on fluorescent markers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632492.6A CN113380318B (en) | 2021-06-07 | 2021-06-07 | Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110632492.6A CN113380318B (en) | 2021-06-07 | 2021-06-07 | Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113380318A true CN113380318A (en) | 2021-09-10 |
| CN113380318B CN113380318B (en) | 2023-04-07 |
Family
ID=77576134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110632492.6A Active CN113380318B (en) | 2021-06-07 | 2021-06-07 | Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113380318B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114136868A (en) * | 2021-12-03 | 2022-03-04 | 浙江博真生物科技有限公司 | Flow cytometry full-automatic clustering method based on density and nonparametric clustering |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005085845A1 (en) * | 2004-03-03 | 2005-09-15 | Universidad De Salamanca | Method for the multidimensional detection of aberrant phenotypes in neoplastic cells to be used to monitor minimal disease levels using flow cytometry |
| CN102507417A (en) * | 2011-11-29 | 2012-06-20 | 长春迪瑞医疗科技股份有限公司 | Method for automatically classifying particles |
| CN105940301A (en) * | 2014-04-17 | 2016-09-14 | 深圳迈瑞生物医疗电子股份有限公司 | Flow cytometer and multidimensional data classification method and apparatus thereof |
| CN106548203A (en) * | 2016-10-21 | 2017-03-29 | 北京信息科技大学 | A kind of fast automatic point of group of multiparameter flow cytometry data and gating method |
| CN107389536A (en) * | 2017-07-31 | 2017-11-24 | 上海纳衍生物科技有限公司 | Fluidic cell particle classifying method of counting based on density distance center algorithm |
| CN110412287A (en) * | 2019-07-11 | 2019-11-05 | 上海宸安生物科技有限公司 | One kind being based on single celled immunocyte parting quantitative analysis method |
| CN110675914A (en) * | 2019-09-17 | 2020-01-10 | 佛山市第一人民医院（中山大学附属佛山医院） | Method for screening tumor specific T cells and TCR |
| CN111164103A (en) * | 2017-06-14 | 2020-05-15 | 西奈山伊坎医学院 | Methods for detecting and treating classes of hepatocellular carcinoma responsive to immunotherapy |
| CN112313497A (en) * | 2018-04-27 | 2021-02-02 | 纳诺斯迪科公司 | Methods of diagnosing disease using microflow cytometry |
| CN112666062A (en) * | 2020-11-20 | 2021-04-16 | 浙江省荣军医院 | Method for combined detection in humoral cell immune analysis by flow cytometry |
-
2021
- 2021-06-07 CN CN202110632492.6A patent/CN113380318B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005085845A1 (en) * | 2004-03-03 | 2005-09-15 | Universidad De Salamanca | Method for the multidimensional detection of aberrant phenotypes in neoplastic cells to be used to monitor minimal disease levels using flow cytometry |
| CN102507417A (en) * | 2011-11-29 | 2012-06-20 | 长春迪瑞医疗科技股份有限公司 | Method for automatically classifying particles |
| CN105940301A (en) * | 2014-04-17 | 2016-09-14 | 深圳迈瑞生物医疗电子股份有限公司 | Flow cytometer and multidimensional data classification method and apparatus thereof |
| CN106548203A (en) * | 2016-10-21 | 2017-03-29 | 北京信息科技大学 | A kind of fast automatic point of group of multiparameter flow cytometry data and gating method |
| CN111164103A (en) * | 2017-06-14 | 2020-05-15 | 西奈山伊坎医学院 | Methods for detecting and treating classes of hepatocellular carcinoma responsive to immunotherapy |
| CN107389536A (en) * | 2017-07-31 | 2017-11-24 | 上海纳衍生物科技有限公司 | Fluidic cell particle classifying method of counting based on density distance center algorithm |
| CN112313497A (en) * | 2018-04-27 | 2021-02-02 | 纳诺斯迪科公司 | Methods of diagnosing disease using microflow cytometry |
| CN110412287A (en) * | 2019-07-11 | 2019-11-05 | 上海宸安生物科技有限公司 | One kind being based on single celled immunocyte parting quantitative analysis method |
| CN110675914A (en) * | 2019-09-17 | 2020-01-10 | 佛山市第一人民医院（中山大学附属佛山医院） | Method for screening tumor specific T cells and TCR |
| CN112666062A (en) * | 2020-11-20 | 2021-04-16 | 浙江省荣军医院 | Method for combined detection in humoral cell immune analysis by flow cytometry |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114136868A (en) * | 2021-12-03 | 2022-03-04 | 浙江博真生物科技有限公司 | Flow cytometry full-automatic clustering method based on density and nonparametric clustering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113380318B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8682810B2 (en) | Method and system for analysis of flow cytometry data using support vector machines | |
| CN106248559B (en) | A kind of five sorting technique of leucocyte based on deep learning | |
| US20190228527A1 (en) | System and method of classification of biological particles | |
| CN111325103B (en) | Cell labeling system and method | |
| US6014904A (en) | Method for classifying multi-parameter data | |
| US20160169786A1 (en) | Automated flow cytometry analysis method and system | |
| US10337975B2 (en) | Method and system for characterizing particles using a flow cytometer | |
| Yang et al. | Rapid detection of rice disease using microscopy image identification based on the synergistic judgment of texture and shape features and decision tree–confusion matrix method | |
| CN108847022B (en) | Abnormal value detection method of microwave traffic data acquisition equipment | |
| CN110473167B (en) | Deep learning-based urinary sediment image recognition system and method | |
| CN103345654A (en) | Method for differential counting of white blood cells based on morphology | |
| CN103984939A (en) | Sample visible component classification method and system | |
| CN113380318B (en) | Artificial intelligence assisted flow cytometry 40CD immunophenotyping detection method and system | |
| CN112432902A (en) | Automatic detection system and method for judging cell number through peripheral blood cell morphology | |
| CN111832389A (en) | Counting and analyzing method of bone marrow cell morphology automatic detection system | |
| CN104751188B (en) | Picture processing method and system | |
| CN110060246A (en) | A kind of image processing method, equipment and storage medium | |
| CN111274949B (en) | Blood disease white blood cell scatter diagram similarity analysis method based on structural analysis | |
| EP3230887A1 (en) | Automated flow cytometry analysis method and system | |
| CN111833297B (en) | Disease association method of marrow cell morphology automatic detection system | |
| EP3244191A1 (en) | Method and system for characterizing particles using a flow cytometer | |
| Di Ruberto et al. | A region proposal approach for cells detection and counting from microscopic blood images | |
| CN109767430A (en) | The quality determining method and quality detecting system of valuable bills | |
| CN112557285B (en) | Automatic gating method and device for flow cytometry detection data | |
| CN117275574A (en) | Flow lymphocyte subpopulation analysis method, apparatus and storage medium thereof |
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 |