CN110208238A - It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue - Google Patents
It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue Download PDFInfo
- Publication number
- CN110208238A CN110208238A CN201910235612.1A CN201910235612A CN110208238A CN 110208238 A CN110208238 A CN 110208238A CN 201910235612 A CN201910235612 A CN 201910235612A CN 110208238 A CN110208238 A CN 110208238A
- Authority
- CN
- China
- Prior art keywords
- cell
- positioning method
- accurate positioning
- lung tissue
- image
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/65—Raman scattering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
- G06V20/698—Matching; Classification
Abstract
It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, the steps include: 1. to cultivate two kinds of cell lines；2. two kinds of cell lines after culture are placed on glass slide, with the Raman spectrum of Confocal laser-scanning microscopy instrument measurement cell；3. the Raman spectrum of the cell obtained after measurement is pre-processed；4. extracting feature to pretreated cell Raman spectrum, extraction is characterized in characteristic peak positions and the intensity rate of these characteristic peak positions；5. between correlation analysis the feature application multivariable of extraction；6. to step 4., 5. in extract feature, in conjunction with SVM classifier to spectroscopic data carry out Classification and Identification；7. choosing remaining sample to be tested, the accuracy, sensibility, specificity for having obtained cell further distinguish the sample of classification error using dye image or Raman image.The present invention can eliminate the phenomenon that lower rate is identified due to caused by the error during experiment or sample culturing.
Description
Technical field
The invention belongs to computer visions and area of pattern recognition, in particular to a kind of to be based on SVM models coupling image pair
The accurate positioning method of cancerous lung tissue.
Background technique
Identifying and positioning object is computer vision and the important research contents of area of pattern recognition, as object detection
Branch, the classification of cancer cell are a kind of object detections of special circumstances.Cell is a kind of special substance, is not only had universal
Property and have diversified particularity.Therefore, bio-identification, which detects, has wide scientific research value and application prospect, and
There is critically important research significance in terms of medicine.
Currently, fluorescent marker method due to its specificity, mainly for the identification of the type of cell.Fluorescent marker is based on antigen
With the specific binding of antibody, this method easily causes to damage and be easy to produce specific binding to the original physiologic activity of cell
The false positive results of albumen are unfavorable for further analyzing and studying.Further, since sample treatment is complicated, at high cost, efficiency
It is low, therefore there are many defects in clinical application.
Raman spectroscopy is a kind of molecule inelastic scattering fingerprint spectral technology, it is contactless technology, Ke Yi
Cancer cell is specifically identified on physical layer, it can not only keep integrality, cell activity, moreover it is possible to efficiently solve biology
The complexity and efficiency of sample pretreatment efficiency.Raman spectrum has very strong specificity, and it is raw to reflect living cells in aqueous solution
The variation of chemical conversion point, without any label and fixation.Therefore, Raman spectroscopy has been widely used in clinical diagnosis, toxicity
The fields such as detection and organizational project.Raman spectroscopy has quick, easy, reproducible, more important compared with other technologies
The characteristics of, it is a kind of undamaged qualitative and quantitative analysis method.It does not need sample preparation, and sample can be visited directly by optical fiber
Head is measured by glass or quartz and optical fiber measurement.
Confocal laser Raman spectrometer is a kind of effective spectroscopic analysis methods, for analyzing the Nomenclature Composition and Structure of Complexes of substance,
Its principle is that incident laser can cause molecule (or lattice) to generate vibration.(or acquisition) portion of energy is lost, makes to scatter light frequency
Scattering light analysis, i.e. Raman spectrum analysis are changed to, composition, structure and the relative amount of known molecular can be explored.Micro- drawing
The hot spot of exciting light can be focused on micron dimension by graceful technology, and then carry out Accurate Analysis to the microcell of sample, and laser is in sample
The definite position of upper generation effect, can be clearly displayed by CCD assessing instrument and a TV monitor.Copolymerization is burnt aobvious
Micro- Raman spectrum can choose any part in relation to analyzing interested any sample, entirely analyze and identify process, all non-
Chang Zhiguan is easy to be observed and controlled.
Before measuring cell, we are first measured with a piece of silicon wafer, the whether askew shifting of optical path for detecting spectrometer, then
Again two kinds of cells are individually placed to measure cell on glass slide.Before doing spectrum experiment, a large amount of literature reading has been done,
Understand where two kinds of cells all will appear characteristic peak, what substance represent, this surveys the Raman spectrum of cell
Amount is actually very feasible.
It after raman spectroscopy measurement comes out, needs to pre-process spectroscopic data and subsequent feature extraction, utilize
These inputs as SVM classifier of feature extracted, for classification as a result, certain point for having classification error, according to these
The point of classification error reapplies and further discriminates between to the dye image or Raman image of two kinds of cells, reaches more accurate knot
Fruit.
Summary of the invention
It is an object of that present invention to provide a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, should
Method application Confocal laser-scanning microscopy instrument, the identification according to Raman spectrum combination SVM classifier to lung carcinoma cell and normal cell,
The result of classification is recycled further to distinguish using image to two kinds of cells, to eliminate due to experiment or sample culturing mistake
The phenomenon that lower rate is identified caused by error in journey.
To achieve the goals above, the scheme of the invention is:
It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is characterised in that: including walking as follows
It is rapid:
1. cultivating two kinds of cell lines；
2. two kinds of cell lines after culture are placed on glass slide, with the Raman light of Confocal laser-scanning microscopy instrument measurement cell
Spectrum；
3. the Raman spectrum of the cell obtained after measurement locates spectrum by 4.1 software of Project FOUR in advance
Reason, i.e. Baseline wander and smoothing processing；
4. feature extracted to pretreated cell Raman spectrum, extraction be characterized in characteristic peak positions and these
The intensity rate of characteristic peak positions；
5. eliminating the cross-sensitivity between feature to correlation analysis the feature application multivariable of extraction；
6. to step 4., 5. in extract feature, in conjunction with SVM classifier to spectroscopic data carry out Classification and Identification；
7. choosing remaining sample to be tested, the accuracy, sensibility, specificity of cell are obtained, for classification error
Sample, further distinguished using dye image or Raman image.
The two kinds of cell lines of the step 1. are lung adenocarcinoma cell line A549 and pleural mesothelial cell system Met-5A.
The condition of culture of the lung adenocarcinoma cell line A549 and pleural mesothelial cell system Met-5A are: lung adenocarcinoma cell system
A549 uses DMEM basal medium, and pleural mesothelial cell system Met-5A uses DMEM high glucose medium DMEM-H, in 30-50
DEG C, 5-10%CO2It is collected into sterile centrifugation tube after culture in incubator, is abandoned after buffer solution for cleaning and centrifugation cell
Whole supernatants are removed, the cell of collection are uniformly layered on glass slide, for observing.
The lung adenocarcinoma cell line A549 comes from General Hospital of Tianjin Medical Univ.'s lung cancer research center, pleural mesothelial cell system
Met-5A receives biological Co., Ltd from Su Zhoubei.
The DMEM basal medium includes 10% fetal calf serum, and 1% Pen .- Strep is dual anti-, the DMEM high sugar
Culture medium DMEM-H includes 10% fetal calf serum, and purchase is in Beijing So l arbi o Science and Technology Ltd..
4. the step extracts the intensity rate for being characterized in 9 characteristic peak positions and this 9 characteristic peak positions, and 9
The position of characteristic peak includes 1080cm-1、1128cm-1、1258cm-1、1301cm-1、1342cm-1、1449cm-1、1578cm-1、
1617cm-1、1659cm-1；8 intensity rates of this 9 characteristic peak positions are respectively 1.077,1.047,1.180,1.263,
1.214、1.468、1.036、1.414。
The SVM classifier uses LIBSVM.
The Confocal laser-scanning microscopy instrument is the WI Tec spectrometer of Germany's production.
The present invention has the advantage that and good effect:
1, the present invention passes through feature extraction (position of characteristic peak and the intensity with traditional Confocal laser-scanning microscopy instrument
Ratio) with SVM method to processed Raman spectrum carry out Classification and Identification, after identification further according to classification results by mistake sample
Two kinds of cell positions on point location to image are further accurately positioned, to effectively improve recognition accuracy.
2, the preprocessing process of the invention for Raman spectrum, since the characteristic peak of obtained Raman spectrum is that have biology to contain
Justice, and test obtained spectrum line and be apparent visible features peak, only a other Raman spectrum is that have cosmic ray
, cosmic ray is got rid of using 4.1 software of Project FOUR.
3, the present invention can effectively identify cancer cell and normal cell.As to traditional cancer cell recognition method improvement with
The combination of machine learning method, the data set as experiment sample are established with Confocal laser-scanning microscopy instrument, and operation is simple,
The SVM model size of building can be depending on corresponding data collection size, and the image procossing for research is also some computers
The basic operation of the image procossing of aspect.
4, there are cross-sensitivity for feature of present invention extraction part, therefore using correlation analysis between multivariable, right
Intersection between feature carries out experiment removal, in order to test to obtain higher accuracy below.
5, SVM classifier used in the present invention is LIBSVM, this is that Taiwan Univ. professor Lin Zhiren develops the one of design
A simple, easy to use and quickly and effectively SVM pattern-recognition and recurrence software package, the software is to related parameter regulation
It compares less, provides many default parameters, it is apparent to classifying quality.And provide cross-verification its no matter full-page proof
This or small sample have relatively good performance.
6, the present invention mutually arranges in pairs or groups 4.1 software of Project FOUR with focusing Raman spectrometer together, can be in a short time
It is largely pre-processed to the spectrum of Confocal laser-scanning microscopy instrument measurement cell.
Detailed description of the invention
Fig. 1-a is the optical imagery figure for the lung adenocarcinoma cell line A549 that the present invention measures；
Fig. 1-b is the optical imagery figure for the pleural mesothelial cell system Met-5A that the present invention measures；
Fig. 2 is the schematic diagram of Confocal laser-scanning microscopy instrument measurement cell Raman spectrum of the present invention；
Fig. 3 is the classification results schematic diagram of SVM classifier model of the present invention.
Specific embodiment
It is as shown in the figure: a kind of to be walked based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, including as follows
It is rapid:
1. cultivating two kinds of cells: lung adenocarcinoma cell line A549, pleural mesothelial cell system Met-5A, culture form is cell
Group.Condition of culture is that lung adenocarcinoma cell line A549 uses DMEM basal medium (comprising 10% fetal calf serum, 1% penicillin-chain
Mycin is dual anti-), pleural mesothelial cell system Met-5A using DMEM high glucose medium DMEM-H (include 10% fetal calf serum) 37
DEG C, 5%CO2Culture, is collected into 15ml sterile centrifugation tube, by phosphate buffer twice (PBS) after culture in incubator
After cleaning, centrifugation cell, 4500rpm is centrifuged 10mi n, after discarding whole supernatants, will collect cell, convenient for observation.
2. the cell mass after culture is placed on glass slide, with the spectrum of Confocal laser-scanning microscopy instrument measurement cell；
3. after obtaining Raman spectrum, being removed cosmic ray to some spectrum in conjunction with 4.1 software of Project FOUR
Processing and smoothing processing, Baseline wander.Here pretreatment is right after processing just for the spectrum for having cosmic ray individually
Raman spectrum will not have an impact.
4. carrying out feature extraction to pretreated Cellular spectroscopic.Extraction is characterized in 9 characteristic peak positions and this 9
8 intensity rates of characteristic peak positions.9 characteristic peak positions include 1080cm-1、1128cm-1、1258cm-1、1301cm-1、
1342cm-1、1449cm-1、1578cm-1、1617cm-1、1659cm-1.The intensity rate of this 9 characteristic peak positions, herein I with
The intensity value of 7th characteristic peak be normalized value, this 8 intensity rates be respectively (by taking first sample as an example) 1.077,
1.047、1.180、1.263、1.214、1.468、1.036、1.414。
5. eliminating the cross-sensitivity between feature to correlation analysis the feature application multivariable of extraction；
6. to step 4., 5. in extract feature, in conjunction with SVM classifier to spectroscopic data carry out Classification and Identification；Training
SVM classifier, this chooses a certain proportion of two kinds of cell samples and is trained to obtain.242, lung carcinoma cell sample, normally
Cell sample 231.
7. choosing remaining sample to be tested, the accuracy rate, sensibility, specificity of cell recognition are obtained.
H&E dyeing or other dyes can be carried out 8. carrying out Raman spectrum and testing the later cell being placed on glass slide
Color can also carry out Raman scattering imaging with spectrometer；Then two kinds of cells are further discriminated between according to image.
Above-mentioned SVM classifier is LIBSVM, this be one of the exploitations such as Taiwan Univ. professor Lin Zhiren design it is simple, be easy to
Use the software package with quickly and effectively SVM pattern-recognition and recurrence.Above-mentioned Confocal laser-scanning microscopy instrument is Germany's production
WITec spectrometer.
It should be noted that only explaining the present invention the foregoing is merely the embodiment of the present invention, it is not intended to limit this
Patent of invention range.To the technology of the present invention design is belonged to and only obvious change, equally the scope of the present invention it
It is interior.
Claims (8)
1. it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is characterised in that: including walking as follows
It is rapid:
1. cultivating two kinds of cell lines；
2. two kinds of cell lines after culture are placed on glass slide, with the Raman spectrum of Confocal laser-scanning microscopy instrument measurement cell；
3. the Raman spectrum of the cell obtained after measurement pre-processes spectrum by 4.1 software of Project FOUR,
That is Baseline wander and smoothing processing；
4. extracting feature to pretreated cell Raman spectrum, extraction is characterized in characteristic peak positions and these features
The intensity rate of peak position；
5. eliminating the cross-sensitivity between feature to correlation analysis the feature application multivariable of extraction；
6. to step 4., 5. in extract feature, in conjunction with SVM classifier to spectroscopic data carry out Classification and Identification；
7. choosing remaining sample to be tested, the accuracy, sensibility, specificity of cell are obtained, for the sample of classification error
This, is further distinguished using dye image or Raman image.
2. it is according to claim 1 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is special
Sign is: the two kinds of cell lines of the step 1. are lung adenocarcinoma cell line A549 and pleural mesothelial cell system Met-5A.
3. it is according to claim 1 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue,
It is characterized in that: stating step and 4. extract the intensity rate for being characterized in 9 characteristic peak positions and this 9 characteristic peak positions, 9 spies
The position for levying peak includes 1080cm-1、1128cm-1、1258cm-1、1301cm-1、1342cm-1、1449cm-1、1578cm-1、
1617cm-1、1659cm-1；8 intensity rates of this 9 characteristic peak positions are respectively 1.077,1.047,1.180,1.263,
1.214、1.468、1.036、1.414。
4. it is according to claim 1 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is special
Sign is: the SVM classifier uses LIBSVM.
5. it is according to claim 1 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is special
Sign is: the Confocal laser-scanning microscopy instrument is the WITec spectrometer of Germany's production.
6. it is according to claim 1 or 2 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue,
It is characterized by: the condition of culture of the lung adenocarcinoma cell line A549 and pleural mesothelial cell system Met-5A are: lung adenocarcinoma cell
It is A549 using DMEM basal medium, pleural mesothelial cell system Met-5A uses DMEM high glucose medium DMEM-H, in 30-50
DEG C, 5-10%CO2It is collected into sterile centrifugation tube after culture in incubator, is abandoned after buffer solution for cleaning and centrifugation cell
Whole supernatants are removed, the cell of collection are uniformly layered on glass slide, for observing.
7. it is according to claim 6 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is special
Sign is: the lung adenocarcinoma cell line A549 comes from General Hospital of Tianjin Medical Univ.'s lung cancer research center, pleural mesothelial cell system
Met-5A receives biological Co., Ltd from Su Zhoubei.
8. it is according to claim 6 it is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue, it is special
Sign is: the DMEM basal medium includes 10% fetal calf serum, and 1% Pen .- Strep is dual anti-, the DMEM high sugar training
Supporting base DMEM-H includes 10% fetal calf serum, and purchase is in Beijing Solarbio Science and Technology Ltd..
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235612.1A CN110208238A (en) | 2019-03-27 | 2019-03-27 | It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235612.1A CN110208238A (en) | 2019-03-27 | 2019-03-27 | It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110208238A true CN110208238A (en) | 2019-09-06 |
Family
ID=67785076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235612.1A Pending CN110208238A (en) | 2019-03-27 | 2019-03-27 | It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110208238A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111721751A (en) * | 2020-06-30 | 2020-09-29 | 四川大学华西医院 | Device for detecting colorectal malignant tumor |
| CN113324968A (en) * | 2021-04-01 | 2021-08-31 | 吉林大学 | Detection method for colorectal cancer mismatch repair protein expression based on Raman spectrum |
| CN113933285A (en) * | 2021-10-18 | 2022-01-14 | 安徽理工大学 | Establishment of non-labeling quantitative method for detecting lung tissue collagen |
| US11358984B2 (en) | 2018-08-27 | 2022-06-14 | Regeneran Pharmaceuticals, Inc. | Use of Raman spectroscopy in downstream purification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008016111A1 (en) * | 2006-08-04 | 2008-02-07 | Ajinomoto Co., Inc. | Method for evaluation of lung cancer, lung cancer evaluation apparatus, lung cancer evaluation method, lung cancer evaluation system, lung cancer evaluation program, and recording medium |
| WO2014127224A1 (en) * | 2013-02-14 | 2014-08-21 | The Research Foundation For The State University Of New York | Method for adaptive computer-aided detection of pulmonary nodules in thoracic computed tomography images using hierarchical vector quantization and apparatus for same |
| CN106874687A (en) * | 2017-03-03 | 2017-06-20 | 深圳大学 | Pathological section image intelligent sorting technique and device |
-
2019
- 2019-03-27 CN CN201910235612.1A patent/CN110208238A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008016111A1 (en) * | 2006-08-04 | 2008-02-07 | Ajinomoto Co., Inc. | Method for evaluation of lung cancer, lung cancer evaluation apparatus, lung cancer evaluation method, lung cancer evaluation system, lung cancer evaluation program, and recording medium |
| WO2014127224A1 (en) * | 2013-02-14 | 2014-08-21 | The Research Foundation For The State University Of New York | Method for adaptive computer-aided detection of pulmonary nodules in thoracic computed tomography images using hierarchical vector quantization and apparatus for same |
| CN106874687A (en) * | 2017-03-03 | 2017-06-20 | 深圳大学 | Pathological section image intelligent sorting technique and device |
Non-Patent Citations (5)
| Title |
|---|
| YUQING ZHANG 等: ""Identification and distinction of non-small-cell lung cancer cells by intracellular SERS nanoprobes"", 《RSC ADVANCES》 * |
| ZHIWEI HUANG 等: ""NEAR-INFRARED RAMAN SPECTROSCOPY FOR OPTICAL DIAGNOSIS OF LUNG CANCER"", 《INTERNATIONAL JOURNAL OF CANCER》 * |
| 王嫚: ""金纳米星SERS基底用于肺癌细胞分析检测的研究"", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
| 王磊: ""表面增强拉曼光谱在肺癌EGFR突变检测中的应用研究"", 《中国博士学位论文全文数据库 医药卫生科技辑》 * |
| 路交 等: ""拉曼光谱成像技术及其在生物医学中的应用"", 《中国激光》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11358984B2 (en) | 2018-08-27 | 2022-06-14 | Regeneran Pharmaceuticals, Inc. | Use of Raman spectroscopy in downstream purification |
| CN111721751A (en) * | 2020-06-30 | 2020-09-29 | 四川大学华西医院 | Device for detecting colorectal malignant tumor |
| CN113324968A (en) * | 2021-04-01 | 2021-08-31 | 吉林大学 | Detection method for colorectal cancer mismatch repair protein expression based on Raman spectrum |
| CN113933285A (en) * | 2021-10-18 | 2022-01-14 | 安徽理工大学 | Establishment of non-labeling quantitative method for detecting lung tissue collagen |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110208238A (en) | It is a kind of based on SVM models coupling image to the accurate positioning method of cancerous lung tissue | |
| Neugebauer et al. | Identification and differentiation of single cells from peripheral blood by Raman spectroscopic imaging | |
| Bocklitz et al. | Raman based molecular imaging and analytics: a magic bullet for biomedical applications!? | |
| Baker et al. | Investigating FTIR based histopathology for the diagnosis of prostate cancer | |
| JP6000345B2 (en) | Analysis method of biological samples by spectral imaging | |
| Agsalda-Garcia et al. | Raman-enhanced spectroscopy (RESpect) probe for childhood non-Hodgkin lymphoma | |
| Butler et al. | Shining a light on clinical spectroscopy: Translation of diagnostic IR, 2D-IR and Raman spectroscopy towards the clinic | |
| Krafft et al. | Classification of malignant gliomas by infrared spectroscopy and linear discriminant analysis | |
| KR20130056886A (en) | Method for analyzing biological specimens by spectral imaging | |
| JPS63501597A (en) | Analytical methods and devices for biological specimens | |
| GB2466442A (en) | A system to analyze a sample on a slide using Raman spectroscopy on an identified area of interest | |
| CN109297949B (en) | Tumor cell detection method and device by combining microscopic image with transmission Raman spectrum | |
| Liang et al. | Label-free distinction between p53+/+ and p53-/-colon cancer cells using a graphene based SERS platform | |
| CN111707656A (en) | Cerebrospinal fluid cell detection method and system based on Raman scattering spectrum | |
| Dubois et al. | Peer reviewed: IR spectroscopy in clinical and diagnostic applications | |
| CN108267416A (en) | A kind of circulating tumor cell screening system and method based on tera-hertz spectra | |
| Baker et al. | Fundamental developments in clinical infrared and Raman spectroscopy | |
| Bunaciu et al. | Biomedical investigations using Fourier transform-infrared microspectroscopy | |
| Cameron et al. | Clinical spectroscopy: lost in translation? | |
| Park et al. | Label-free, non-invasive, and repeatable cell viability bioassay using dynamic full-field optical coherence microscopy and supervised machine learning | |
| Yan et al. | Confocal Raman sensing based on a support vector machine for detecting lung adenocarcinoma cells | |
| CN103698353A (en) | Bird's nest identification method | |
| Babrah et al. | Fourier transform infrared spectroscopic studies of T-cell lymphoma, B-cell lymphoid and myeloid leukaemia cell lines | |
| Krauß et al. | Integrating spatial, morphological, and textural information for improved cell type differentiation using Raman microscopy | |
| Cañas et al. | Characterization and differentiation of cervical cancer cell lines using ATR-FTIR spectroscopy and multivariate data analysis |
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: 20190906 |
|
| RJ01 | Rejection of invention patent application after publication |