CN111896456A - Single cell analysis method based on micro-fluidic and hyperspectral imaging - Google Patents
Single cell analysis method based on micro-fluidic and hyperspectral imaging Download PDFInfo
- Publication number
- CN111896456A CN111896456A CN202010566413.1A CN202010566413A CN111896456A CN 111896456 A CN111896456 A CN 111896456A CN 202010566413 A CN202010566413 A CN 202010566413A CN 111896456 A CN111896456 A CN 111896456A
- Authority
- CN
- China
- Prior art keywords
- cell
- hyperspectral
- method based
- analysis method
- single cell
- 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.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 29
- 238000000701 chemical imaging Methods 0.000 title claims abstract description 15
- 210000004027 cell Anatomy 0.000 claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 51
- 238000005516 engineering process Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 claims description 14
- 239000000463 material Substances 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000011176 pooling Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 5
- 239000000243 solution Substances 0.000 claims description 4
- 210000004102 animal cell Anatomy 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims description 3
- 239000002953 phosphate buffered saline Substances 0.000 claims description 3
- XUIMIQQOPSSXEZ-UHFFFAOYSA-N Silicon Chemical compound [Si] XUIMIQQOPSSXEZ-UHFFFAOYSA-N 0.000 claims description 2
- 238000013459 approach Methods 0.000 claims description 2
- 238000003491 array Methods 0.000 claims description 2
- 239000006143 cell culture medium Substances 0.000 claims description 2
- 230000007423 decrease Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 claims description 2
- 239000011521 glass Substances 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 claims description 2
- 230000000813 microbial effect Effects 0.000 claims description 2
- 229920000620 organic polymer Polymers 0.000 claims description 2
- 239000002504 physiological saline solution Substances 0.000 claims description 2
- 239000010453 quartz Substances 0.000 claims description 2
- 229910052710 silicon Inorganic materials 0.000 claims description 2
- 239000010703 silicon Substances 0.000 claims description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 2
- 238000005406 washing Methods 0.000 claims description 2
- LOKCTEFSRHRXRJ-UHFFFAOYSA-I dipotassium trisodium dihydrogen phosphate hydrogen phosphate dichloride Chemical compound P(=O)(O)(O)[O-].[K+].P(=O)(O)([O-])[O-].[Na+].[Na+].[Cl-].[K+].[Cl-].[Na+] LOKCTEFSRHRXRJ-UHFFFAOYSA-I 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 210000003850 cellular structure Anatomy 0.000 abstract description 3
- 238000004445 quantitative analysis Methods 0.000 abstract description 2
- 239000000523 sample Substances 0.000 description 11
- 238000001514 detection method Methods 0.000 description 9
- 230000001413 cellular effect Effects 0.000 description 4
- 238000002372 labelling Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 239000003814 drug Substances 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 239000012530 fluid Substances 0.000 description 3
- 108090000623 proteins and genes Proteins 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000003248 secreting effect Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 108091028043 Nucleic acid sequence Proteins 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 201000007270 liver cancer Diseases 0.000 description 2
- 208000014018 liver neoplasm Diseases 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 241001584785 Anavitrinella pampinaria Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005842 biochemical reaction Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000009089 cytolysis Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000013412 genome amplification Methods 0.000 description 1
- 210000005260 human cell Anatomy 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004949 mass spectrometry Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000007481 next generation sequencing Methods 0.000 description 1
- 238000007899 nucleic acid hybridization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 230000028327 secretion Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000405 serological effect Effects 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01L—CHEMICAL OR PHYSICAL LABORATORY APPARATUS FOR GENERAL USE
- B01L3/00—Containers or dishes for laboratory use, e.g. laboratory glassware; Droppers
- B01L3/50—Containers for the purpose of retaining a material to be analysed, e.g. test tubes
- B01L3/502—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures
- B01L3/5027—Containers for the purpose of retaining a material to be analysed, e.g. test tubes with fluid transport, e.g. in multi-compartment structures by integrated microfluidic structures, i.e. dimensions of channels and chambers are such that surface tension forces are important, e.g. lab-on-a-chip
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Dispersion Chemistry (AREA)
- Hematology (AREA)
- Clinical Laboratory Science (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Apparatus Associated With Microorganisms And Enzymes (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a single cell analysis method based on micro-fluidic and hyperspectral imaging, which is characterized in that a single cell array is manufactured by a micro-fluidic technology; and (4) performing learning training on the preprocessed data, verifying by using a test set, and analyzing the hyperspectral data by using the obtained optimal model. The invention combines the micro-fluidic technology and the hyperspectral imaging technology to complete the steps of separating cells, acquiring hyperspectral images and processing image data by an artificial intelligence method, finally realizes the quantitative analysis of the single cell components without marking and non-contact, and solves the problem that some existing methods can not identify cells rapidly without damage.
Description
Technical Field
The invention relates to the field of cell analysis and identification, in particular to a single cell detection technology combining a hyperspectral image with deep learning.
Background
At present, the cell identification technology is widely applied to various fields such as biology, medicine, industry and the like, and the high-throughput and rapid cell analysis identification technology is very important. The traditional cell analysis and identification method identifies cells based on morphological characteristics of cells or communities, physiological and biochemical reaction characteristics, serological reaction characteristics and the like, and the method is not only time-consuming and labor-consuming, but also related to subjective judgment of operators. The molecular biological detection method can also be used for cell analysis and identification, and comprises PCR technology, nucleic acid hybridization, gene probe technology, gene chip and the like. The method improves the sensitivity of cell detection and identification, reduces the time required by the detection process, but still has difficulty in realizing the rapid analysis and identification of single cells. Single cell sequencing is a technical means for DNA and RNA sequence determination of single cells of organisms, and comprises the main steps of single cell separation, whole genome amplification, next generation sequencing and data analysis, but the single cell sequencing method needs to invade and damage cells and cannot realize in-situ operation of the cells. Mass spectrometry is a common method for analyzing cellular proteins, but this method requires lysis of the cells and a large number of cells for the experiment, which averages and ignores the heterogeneity between cells. In addition to the above methods, cellular components can be detected by labeling methods and non-labeling methods. Labeling methods, which label cells with materials that specifically recognize components and detect the presence and quantity of materials for component analysis, alter cells, reduce reliability, and are only semi-quantitative. The non-labeling method identifies cellular components by detecting their electro-optical and structural properties, however, this method has limited applicability to detecting known cellular components. Therefore, we need to research a label-free non-contact single cell component accurate analysis method.
The acquisition of medical data highly depends on advanced instruments and equipment, the current medical field instruments cannot meet the requirements of unmarked and non-contact diversified atlas scientific research, and the hyperspectral medical research worldwide is in the beginning stage. The high-performance medical high-spectrum analyzer integrates the characteristics of the spectrum and the image to obtain the chemical structure information and the physical appearance information of a target object, so that the advantages of high spectral resolution, multiple wave bands and spectrum combination are utilized. Finally, the positioning, qualitative and quantitative description of the detection target is realized, and further, the accurate diagnosis of the serious disease is realized. The method is combined with the micro-fluidic technology, the hyperspectral microimaging technology and the single cell analysis and identification of an artificial intelligence algorithm, and can be widely applied to early accurate diagnosis and accurate classification (detection of diseased cells and tissues) of major diseases; precise application of the drug (precise detection of antibody secretion); accurate assessment of efficacy (detection of changes in composition of recipient cells); and accurately predicting the prognosis.
Disclosure of Invention
In order to solve the problems, the invention designs a method combining deep learning and hyperspectral imaging to realize single cell analysis and identification, and has the characteristics of high throughput, no damage and high speed.
The micro-fluidic can accurately control and control micro-scale fluid, the used pipeline is only dozens of microns to hundreds of microns, the detection can be completed only by using very few samples and data, and the micro-fluidic has the characteristics of high flux, integration and light weight and plays an important role in the fields of biology, medicine and the like. Different from common gray level images and color images, the hyperspectral images have a plurality of wave bands, different substances have different spectral curves, classification and the like of the different substances can be completed, and therefore spectral information can reflect information such as component structures of the substances. The hyperspectral microimaging system is applied to single cell analysis, a hyperspectral image of a cell can be obtained, due to the fact that the hyperspectral image is huge in data quantity, the hyperspectral image is difficult to process along with the increase of a sample, a deep learning method is selected to learn the data, and therefore automatic analysis of the sample is achieved.
The method separates single cells by a microfluidic technology, obtains a hyperspectral image of the cells, extracts and classifies features by combining a deep learning method, realizes single cell analysis, is an innovative method, and can realize nondestructive, noninvasive and rapid analysis and identification of the single cells.
In order to realize the aim of the invention, the steps for realizing single cell analysis by combining hyperspectrum and deep learning are as follows:
s1, obtaining cell sap to be analyzed, and manufacturing a single cell array by a microfluidic technology;
s2, acquiring a hyperspectral image of the single cell array and preprocessing the hyperspectral image;
and S3, performing learning training on the preprocessed data, verifying the preprocessed data by using a test set, and analyzing the hyperspectral data by using the obtained optimal model.
The specific process of step S1 is as follows:
obtaining living cell fluid to be detected, and washing cells in the cell fluid by using a solution (the specific solution type is determined by downstream experiment requirements) such as physiological saline, PBS or cell culture medium, wherein the concentration of the solution is determined according to actual conditions.
The washed cells were loaded to generate single-cell droplets.
And setting chip moving step pitch, and arranging the single cell liquid drops on the cell chip to obtain the single cell array.
The material of the chip in the step S1 is any one of a silicon wafer material, a quartz material, a glass material, and an organic polymer.
The specific process of step S2 is:
acquiring a hyperspectral image by using a hyperspectral microimaging system: the method comprises the following steps of building and connecting a microscope, a hyperspectral camera and a computer, placing the single cell array manufactured in the step S1 on a microscope objective table, adjusting a coarse focusing screw and a fine focusing screw of the microscope to make displayed images clearer, setting parameters such as exposure time and the like, and then starting to collect the images, wherein the hyperspectral image collection process is push-broom collection without any change in the collection process.
Preprocessing a hyperspectral image: the hyperspectral image preprocessing method has various preprocessing modes, including filtering, dimensionality reduction, wave band selection and the like. The filtering methods include mean filtering, gaussian filtering, etc., and the dimensionality reduction methods include methods such as PCA (principal component analysis), ICA (independent component analysis), LDA (linear discriminant analysis), etc. In the actual application process, the most suitable pretreatment method is tried according to the actual situation, and one or more of the pretreatment methods may be included. Taking mean filtering and LFDA linear discriminant analysis as examples:
and (3) mean filtering: and replacing the value of each pixel point in the original image by the average value, selecting a filtering template which comprises the current processing pixel point and the surrounding pixel points, and replacing the value of the current processing pixel point by the average value of all the pixels in the template. The mathematical formula of the method is as follows,
s (m, n) is the intra-filter-template pixel value (i ═ 0,1 … H-1, j ═ 0,1 … W-1), H is the height of the filter template, W is the width of the filter template, and R (i, j) is the filter template region.
LFDA linear discriminant analysis: as an optimization algorithm of the LDA, the advantages of the LDA and Local Preserving Projection (LPP) are fused, and not only can a subspace with good inter-class separability be obtained, but also a local structure in the class can be kept. Traditional LDA methods consider all samples in a class to have the same contribution weight, and LFDA treats samples of a class or pattern as independent individuals and gives them a weight to the data-related attributes.
The specific process of step S3 is:
the model used for deep learning comprises an input layer, a hidden layer and an output layer. The hidden layer comprises a convolution layer, a pooling layer and a full-connection layer, the pooling method is maximum pooling or average pooling, the convolution layer is 2-50 layers, the pooling layer is 2-50 layers, and the full-connection layer is at least 1. The model verification method is K-time cross verification, and the evaluation index is overall classification accuracy (OA).
The method comprises the steps of obtaining sample data, scrambling the sample by using a random sequence, dividing the sample data into a training set, a testing set and a verification set, and respectively realizing the functions of training model parameters, testing model errors and verifying model hyper-parameters.
The sample database is constructed as follows: the method comprises the steps of obtaining different cell sap, respectively preparing the obtained cell sap into cell arrays, obtaining hyperspectral images by using a hyperspectral microimaging system, respectively preprocessing the images, distinguishing all samples according to categories, and storing the samples into a database.
The wavelength range of the high-resolution spectrometer is 400-1000 nm.
The sample database may be plant cells, animal cells, microbial cells, etc., mainly human or animal cells.
In step S3, the model training is ended based on the convergence of the Loss function, and the Loss function gradually decreases and approaches a certain value, which is approximately stable.
Conventional machine learning methods and deep learning methods include Support Vector Machines (SVM), Extreme Learning Machines (ELM), Alexnet, Resnet20, VGG19, and the like. In the experiments of various machine learning algorithms, the consistency of the training samples and the test samples is maintained. Meanwhile, various preprocessing steps can be combined with the learning algorithm to finally determine the most suitable preprocessing step. The Overall Accuracy (OA), Average Accuracy (AA) and Kappa coefficient can be used to compare the effectiveness of different algorithms.
In the processing process, many parameter adjusting steps are included, for example, the most suitable dimension of the dimension reduction algorithm, the parameters of the filtering process, the parameters in the process of the machine learning algorithm, such as the learning rate, and the like.
The invention has the beneficial effects that: the invention combines the micro-fluidic technology and the hyperspectral imaging technology to complete the steps of separating cells, acquiring hyperspectral images and processing image data by an artificial intelligence method, finally realizes the quantitative analysis of the single cell components without marking and non-contact, and solves the problem that some existing methods can not identify cells rapidly without damage.
Drawings
Fig. 1 is a general flow diagram of single cell analysis based on microfluidics and hyperspectral imaging.
Detailed Description
To further illustrate the processes and features of the present invention, the specific implementation steps are explained.
Example 1
Cell sap of liver cancer tumor cells and normal cells are respectively obtained, a single cell array is prepared by a microfluidic technology and is arranged on a chip. The hyperspectral microimaging system can respectively acquire hyperspectral images of each liver cancer cell and each normal cell, the hyperspectral images are imported into ENVI software, regions of interest are marked, and a group route image is exported, so that the cell regions are extracted, and backgrounds, possibly-occurring impurities and the like are ignored. And the marked pixel points are used as sample data in a point or block form for deep learning. The image is preprocessed before artificial intelligence learning, and the methods of filtering, dimensionality reduction, denoising and the like can be included. All sample data are divided into a training set, a test set and a verification set according to a certain proportion. The learning process tries a number of methods, the final model being used optimally.
Example 2
In this example, three types of cells (incapable of secreting antibody type, secreting antibody type 1, and secreting antibody type 2) were identified by classification. Cell sap of three kinds of cells is respectively obtained, a micro-cell array is manufactured by a micro-fluidic technology, a hyperspectral image is obtained, target pixel points are marked to obtain a Grountruth image, the hyperspectral image is preprocessed, learning is carried out based on a machine learning method, and accurate classification of the three kinds of cells is achieved. After the optimal model is obtained, the method can be used for classification of larger sample amount, thereby solving the problem that the current classification and identification method consumes a large amount of manpower and material resources.
Claims (8)
1. A single cell analysis method based on micro-fluidic and hyperspectral imaging is characterized in that: the method comprises the following implementation steps:
s1, obtaining cell sap to be analyzed, and manufacturing a single cell array by a microfluidic technology;
s2, acquiring a hyperspectral image of the single cell array and preprocessing the hyperspectral image;
and S3, performing learning training on the preprocessed data, verifying the preprocessed data by using a test set, and analyzing the hyperspectral data by using the obtained model.
2. The single-cell analysis method based on microfluidics and hyperspectral imaging according to claim 1, wherein the step S1 specifically comprises:
obtaining living cell sap to be detected, and washing cells in the cell sap by using physiological saline, PBS (phosphate buffered saline) or cell culture medium solution;
loading the washed cells to generate single-cell liquid drops;
and setting chip moving step pitch, and arranging the single cell liquid drops on the cell chip to obtain the single cell array.
3. A single-cell analysis method based on microfluidics and hyperspectral imaging according to claim 1 or 2, wherein the material of the chip in step S1 is any one of a silicon wafer material, a quartz material, a glass material or an organic polymer.
4. A single-cell analysis method based on microfluidics and hyperspectral imaging according to any one of claims 1 to 3, wherein the step S2 specifically comprises:
acquiring a hyperspectral image by using a hyperspectral microimaging system: building and connecting a microscope, a hyperspectral camera and a computer, placing the single cell array manufactured in the step S1 on a microscope objective table, adjusting a coarse focusing screw and a fine focusing screw of the microscope to enable displayed images to be clear, setting exposure time parameters, and then starting to acquire the images, wherein the hyperspectral image acquisition process is push-broom acquisition;
preprocessing a hyperspectral image: the hyperspectral image preprocessing comprises filtering, dimensionality reduction and wave band selection.
5. A single-cell analysis method based on microfluidics and hyperspectral imaging according to any one of claims 1 to 4, wherein the step S3 specifically comprises:
the model used for deep learning comprises an input layer, a hidden layer and an output layer; the hidden layer comprises a convolution layer, a pooling layer and a full-connection layer, wherein the pooling method is maximum pooling or average pooling, the convolution layer is 2-50 layers, the pooling layer is 2-50 layers, and the full-connection layer is at least 1; the model verification method is K-time cross verification, and the evaluation index is the overall classification precision;
the method comprises the steps of obtaining sample data, scrambling the sample data by using a random sequence, dividing the sample data into a training set, a testing set and a verification set, and respectively realizing the functions of training model parameters, testing model errors and verifying model hyper-parameters.
6. A single-cell analysis method based on microfluidics and hyperspectral imaging according to any one of claims 1 to 5, wherein in step S3:
the sample database is constructed as follows: obtaining different cell sap, respectively preparing the obtained cell sap into cell arrays, obtaining hyperspectral images by using a hyperspectral microimaging system, respectively preprocessing the images, distinguishing all samples according to categories, and storing the samples into a database.
7. A single-cell analysis method based on microfluidics and hyperspectral imaging according to any one of claims 1 to 6, wherein in step S3:
the kind of the sample database is plant cell, animal cell or microbial cell.
8. A single-cell analysis method based on microfluidics and hyperspectral imaging according to any one of claims 1 to 7, wherein in step S3: the model training is finished based on the convergence of the Loss function, and the Loss function gradually decreases and approaches a certain value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566413.1A CN111896456A (en) | 2020-06-19 | 2020-06-19 | Single cell analysis method based on micro-fluidic and hyperspectral imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010566413.1A CN111896456A (en) | 2020-06-19 | 2020-06-19 | Single cell analysis method based on micro-fluidic and hyperspectral imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111896456A true CN111896456A (en) | 2020-11-06 |
Family
ID=73207403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010566413.1A Pending CN111896456A (en) | 2020-06-19 | 2020-06-19 | Single cell analysis method based on micro-fluidic and hyperspectral imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111896456A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560597A (en) * | 2020-12-02 | 2021-03-26 | 吉林大学 | Microscopic hyperspectral COVID-19 detection and identification method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260730A (en) * | 2015-11-24 | 2016-01-20 | 严媚 | Machine learning-based contact-type imaging microfluid cell counter and image processing method thereof |
| CN106226247A (en) * | 2016-07-15 | 2016-12-14 | 暨南大学 | A kind of cell detection method based on EO-1 hyperion micro-imaging technique |
| CN108732103A (en) * | 2018-06-01 | 2018-11-02 | 大连晓辉医药科技有限公司 | A kind of cell detection and sorter based on optofluidic imaging spectral |
| CN109001180A (en) * | 2018-08-10 | 2018-12-14 | 青岛启明生物科技有限公司 | A kind of Raman spectrum combination artificial intelligence high throughput single cell analysis identification method |
-
2020
- 2020-06-19 CN CN202010566413.1A patent/CN111896456A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105260730A (en) * | 2015-11-24 | 2016-01-20 | 严媚 | Machine learning-based contact-type imaging microfluid cell counter and image processing method thereof |
| CN106226247A (en) * | 2016-07-15 | 2016-12-14 | 暨南大学 | A kind of cell detection method based on EO-1 hyperion micro-imaging technique |
| CN108732103A (en) * | 2018-06-01 | 2018-11-02 | 大连晓辉医药科技有限公司 | A kind of cell detection and sorter based on optofluidic imaging spectral |
| CN109001180A (en) * | 2018-08-10 | 2018-12-14 | 青岛启明生物科技有限公司 | A kind of Raman spectrum combination artificial intelligence high throughput single cell analysis identification method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112560597A (en) * | 2020-12-02 | 2021-03-26 | 吉林大学 | Microscopic hyperspectral COVID-19 detection and identification method |
| CN112560597B (en) * | 2020-12-02 | 2022-07-22 | 吉林大学 | Microscopic hyperspectral based COVID-19 detection and identification method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230127698A1 (en) | Automated stereology for determining tissue characteristics | |
| US11836950B2 (en) | Quality metrics for automatic evaluation of dual ISH images | |
| US11066689B2 (en) | Analysis and screening of cell secretion profiles | |
| JP7201681B2 (en) | Systems and methods for single-channel whole-cell segmentation | |
| US20230145084A1 (en) | Artificial immunohistochemical image systems and methods | |
| DE60226043T2 (en) | METHOD FOR QUANTITATIVE VIDEO MICROSCOPY AND DEVICE AND PROGRAM FOR IMPLEMENTING THE PROCESS | |
| CN108280320B (en) | Rapid and accurate high-flux drug screening system based on deep learning | |
| US20230186659A1 (en) | Machine learning models for cell localization and classification learned using repel coding | |
| CN115088022A (en) | Federal learning system for training machine learning algorithms and maintaining patient privacy | |
| Haney | High content screening: science, techniques and applications | |
| Krauß et al. | Colocalization of fluorescence and Raman microscopic images for the identification of subcellular compartments: a validation study | |
| CN112037853B (en) | Method for screening cell strain capable of expressing expected product | |
| CN111666895B (en) | Neural stem cell differentiation direction prediction system and method based on deep learning | |
| Mondol et al. | Application of high-throughput screening Raman spectroscopy (HTS-RS) for label-free identification and molecular characterization of Pollen | |
| CN114782372B (en) | DNA fluorescence in situ hybridization BCR/ABL fusion state detection method and detection system | |
| JP4985480B2 (en) | Method for classifying cancer cells, apparatus for classifying cancer cells, and program for classifying cancer cells | |
| CN111896456A (en) | Single cell analysis method based on micro-fluidic and hyperspectral imaging | |
| Niederlein et al. | Image analysis in high content screening | |
| CN114299492A (en) | Method and device for detecting medicinal components of Chinese patent medicine based on YOLOX model | |
| Chu et al. | High resolution U-Net for quantitatively analyzing early spatial patterning of human induced pluripotent stem cells on micropatterns | |
| Voros et al. | Correlative Fluorescence and Raman Microscopy to Define Mitotic Stages at the Single-Cell Level: Opportunities and Limitations in the AI Era | |
| CN112669288A (en) | Cell target expression prediction method, system and device based on digital pathological image | |
| US20230326221A1 (en) | Systems for identifying cells and uses thereof | |
| CN108764367A (en) | A kind of characteristic image extraction element and extracting method based on relationship regularization | |
| Gholap et al. | Content-based tissue image mining |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201106 |
|
| RJ01 | Rejection of invention patent application after publication |