CN109580527A - A kind of infrared spectrum analysis identifying abo blood group based on histotomy - Google Patents
A kind of infrared spectrum analysis identifying abo blood group based on histotomy Download PDFInfo
- Publication number
- CN109580527A CN109580527A CN201910078389.4A CN201910078389A CN109580527A CN 109580527 A CN109580527 A CN 109580527A CN 201910078389 A CN201910078389 A CN 201910078389A CN 109580527 A CN109580527 A CN 109580527A
- Authority
- CN
- China
- Prior art keywords
- blood group
- histotomy
- slice
- identifying
- model
- 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
- 210000004369 blood Anatomy 0.000 title claims abstract description 152
- 239000008280 blood Substances 0.000 title claims abstract description 150
- 238000004458 analytical method Methods 0.000 title claims abstract description 26
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000001228 spectrum Methods 0.000 claims abstract description 42
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 18
- 238000004566 IR spectroscopy Methods 0.000 claims abstract description 15
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000003909 pattern recognition Methods 0.000 claims abstract description 7
- 230000003595 spectral effect Effects 0.000 claims description 30
- 238000005259 measurement Methods 0.000 claims description 22
- 210000004072 lung Anatomy 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000003705 background correction Methods 0.000 claims description 5
- 238000004433 infrared transmission spectrum Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000013459 approach Methods 0.000 claims 1
- 238000012790 confirmation Methods 0.000 abstract description 6
- 238000000502 dialysis Methods 0.000 abstract description 3
- 238000010827 pathological analysis Methods 0.000 abstract description 2
- 210000001519 tissue Anatomy 0.000 description 20
- 210000003743 erythrocyte Anatomy 0.000 description 10
- 239000000427 antigen Substances 0.000 description 7
- 102000036639 antigens Human genes 0.000 description 7
- 108091007433 antigens Proteins 0.000 description 7
- 238000001514 detection method Methods 0.000 description 6
- 230000003118 histopathologic effect Effects 0.000 description 6
- 230000004520 agglutination Effects 0.000 description 5
- 125000003147 glycosyl group Chemical group 0.000 description 5
- 210000002966 serum Anatomy 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 239000000910 agglutinin Substances 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 101000874347 Streptococcus agalactiae IgA FC receptor Proteins 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 101710186708 Agglutinin Proteins 0.000 description 2
- 101710146024 Horcolin Proteins 0.000 description 2
- 101710189395 Lectin Proteins 0.000 description 2
- 101710179758 Mannose-specific lectin Proteins 0.000 description 2
- 101710150763 Mannose-specific lectin 1 Proteins 0.000 description 2
- 101710150745 Mannose-specific lectin 2 Proteins 0.000 description 2
- 206010028980 Neoplasm Diseases 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 2
- 208000009956 adenocarcinoma Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 102000004169 proteins and genes Human genes 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- HVCOBJNICQPDBP-UHFFFAOYSA-N 3-[3-[3,5-dihydroxy-6-methyl-4-(3,4,5-trihydroxy-6-methyloxan-2-yl)oxyoxan-2-yl]oxydecanoyloxy]decanoic acid;hydrate Chemical compound O.OC1C(OC(CC(=O)OC(CCCCCCC)CC(O)=O)CCCCCCC)OC(C)C(O)C1OC1C(O)C(O)C(O)C(C)O1 HVCOBJNICQPDBP-UHFFFAOYSA-N 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 208000035240 Disease Resistance Diseases 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 238000005033 Fourier transform infrared spectroscopy Methods 0.000 description 1
- 229930186217 Glycolipid Natural products 0.000 description 1
- 206010018910 Haemolysis Diseases 0.000 description 1
- 208000035186 Hemolytic Autoimmune Anemia Diseases 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 239000004793 Polystyrene Substances 0.000 description 1
- 208000007500 Pulmonary Sclerosing Hemangioma Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000000890 antigenic effect Effects 0.000 description 1
- 201000000448 autoimmune hemolytic anemia Diseases 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000012850 discrimination method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000035931 haemagglutination Effects 0.000 description 1
- 230000002949 hemolytic effect Effects 0.000 description 1
- 210000000987 immune system Anatomy 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 208000020141 lung sclerosing hemangioma Diseases 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 229920002223 polystyrene Polymers 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000000376 reactant Substances 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000007811 spectroscopic assay Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
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
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of infrared spectrum analysis for identifying abo blood group based on histotomy, first collect the histotomy from different blood group human bodies, measure its infrared spectroscopy, gained spectrum carries out spectroscopic data processing using chemometrics method, and the model for identifying abo blood group is established using pattern recognition analysis method；It takes the tissue of unknown blood group to be sliced again, acquire spectrum by same procedure and carries out spectroscopic data processing, finally predicted using model built.The method of the present invention can based on histotomy it is accurate, it is durable, objective, simply and quickly identify abo blood group, histotomy suitable for different parts, and it can be with the identical slice that is unstained of the common lossless use of pathological diagnosis, the bracket for blood grouping result that gained blood group identification result can obtain for other methods provides confirmation, it is especially of great significance in forensic medical examination, blood group confirmation can be carried out to the remaining dialysis corpse in the scene of the accident or tissue quick and precisely to assist individual identification.
Description
Technical field
The present invention relates to the prediction techniques of human body blood group, identify ABO blood based on histotomy more specifically to one kind
The infrared spectrum analysis of type.
Background technique
Blood group (blood groups) is a kind of hereditary capacity showed in the form of blood antigen.Human Blood Type ABO
System is according to Staphylococal Protein A on red blood cell and B antigen with or without being divided into A type, Type B, AB type and O-shaped totally four kinds of phenotypes.A type blood
Only have on red blood cell Staphylococal Protein A (A agglutinogen, serum in have anti-B agglutinin), only B antigen (B agglutination on the red blood cell of Type B blood
Original has anti-A agglutinin in serum), there are A and B two kinds of antigens (A agglutinogen and B agglutinogen, blood on the red blood cell of AB type blood
There is no two kinds of anti-A, anti-B agglutinins in clear), on the red blood cell of O-shaped blood without two kinds of antigens of A and B (there is no two kinds of agglutinogens of A, B,
There are two kinds of anti-A, anti-B agglutinins in its serum).It (is not sugared egg that the structure of antigen, which is glycolipid, in ABO blood group system, on red blood cell
It is white), sugar chain structure is essentially identical, and only the glycosyl of sugar-chain end is different.The glycosyl of A type blood is N- acetyl galactose, Type B blood
Glycosyl is galactolipin, and two kinds of glycosyls of AB type blood have, and then two kinds of glycosyls all do not have O blood group.
Bracket for blood grouping has extensive and important meaning.For example, when 1) clinically transfusing blood (immunohematology), if for
The blood group of blood person and the blood group of receptor mismatch, and can cause the serious hemolytic reaction of patient or even threat to life rapidly.2) close
Nian Lai has found that the antigen being present on red blood cell exists in other haemocytes and general histocyte.All cell surface blood
The specificity of type antigen can be used as the mark that body immune system identifies itself and foreign matter.Therefore, clinically histoorgan moves
When plant, bracket for blood grouping (trnasplantion immunity) is the key that one of transplanting success or failure.3) in criminal investigation, (medical jurisprudence-is gradually by more
Accurate genetics method replaces) in, blood group is one of the important evidence of confirmation individual.In addition, bracket for blood grouping (is exempted from science of heredity
Epidemic disease science of heredity, paternity test-are gradually replaced by more accurate genetics method), anthropology, ethnology (abo blood group antigen
With racial difference), neonatal hemolytic disease, autoimmune hemolytic anemia, disease resistance (or neurological susceptibility) etc.
There is very high application value.
Currently, bracket for blood grouping uses blood sample mostly.But in some major traffic accidents, airplane crash, explosion and act of violence
It kills in case, blood sample is difficult to obtain, and is badly in need of carrying out blood group confirmation based on the remaining dialysis corpse in scene or tissue to assist
Individual identification.As it can be seen that being of great significance in forensic medical examination based on tissue detection blood group.In addition, histopathologic slide
If the result of abo blood group detection is identical as the blood abo blood group testing result of pathological tissue supplier, can effectively help really
The information for recognizing pathological tissue supplier is errorless, obscures caused mistaken diagnosis to avoid due to sample.Although existing document (Yang Jian disease
Manage histotomy abo blood group and detect [J] China Journal of Forensic Sciences .1997,12 (4): 229-230.) it reports based on human body group
Knit and carry out blood group identification, but its identify principle be using A the or B antigen on red blood cell in conjunction with corresponding antibody after occur
Macroscopic agglutination phenomenon, that is, hemagglutination test (HA test) is identified, and the agglutination phenomenon may be by reaction temperature, red blood cell
Or there is nonspecific agglutination i.e. false positive reaction in the influences such as serum type, it is also possible to by shadows such as reactant ratio, reaction time
Pilot causes the unobvious i.e. false negative reaction of agglutination phenomenon.In addition, the method sensitivity is low, it is larger to be interfered by extraneous factor (such as temperature)
I.e. poor durability, cumbersome, detection time is long.Therefore, establish it is a kind of it is accurate, durable, objective, easy based on tissue,
Quick abo blood group discrimination method is a urgent problem to be solved.
Summary of the invention
It is an object of the invention to overcome the shortcomings of the prior art, provide it is a kind of it is accurate, durable based on histotomy,
Infrared spectrum analysis that is objective, simply and quickly identifying abo blood group.
Through studying, technical scheme is as follows:
A kind of infrared spectrum analysis identifying abo blood group based on histotomy, comprising the following steps:
(1) histotomy from different blood group human bodies is collected, the every corresponding blood group of slice is recorded；
(2) infrared spectroscopy of every slice obtained by measuring process (1)；
(3) to spectrum obtained by step (2), spectroscopic data processing is carried out using chemometrics method, using pattern-recognition
Analysis method establishes the prediction model of abo blood group；
(4) it takes the tissue of unknown blood group to be sliced, infrared spectroscopy is measured according to step (2) the method, according to step
(3) the method carries out spectroscopic data processing, and then applying step (3) model built predicts the blood group of the histotomy.
Since the method for the present invention is based on the antigenic structure on the characteristic information of blood group in tissue i.e. red blood cell come to blood group
Identified, do not influenced in the process of the present invention by tissue site, i.e., the method for the present invention be suitable for different parts tissue cut
Piece, preferably blood transport the histotomies such as histotomy, such as liver, spleen, lung abundant.Meanwhile the method for the present invention is not also by organization department
Whether position occurs the influence of lesion, i.e. the method for the present invention is not only suitable for normal tissue sections and is suitable for histopathologic slide, example again
Such as tumor tissue section.Because there is interference to the blood group characteristic information in spectrum in the own absorption of coloring agent, the present invention
Described in histotomy be to be unstained slice.
Preferably, a kind of infrared spectrum analysis identifying abo blood group based on histotomy, comprising the following steps:
(1) histotomy from different blood group human bodies is collected, the every corresponding blood group of slice is recorded；
(2) spectral measurement parameter: resolution ratio 8cm is set-1, scanning times not less than 64 times, scanning range 4000~
1900cm-1, the infrared transmission spectra of every slice obtained by measuring process (1), before each scan slice simultaneously with identical parameters scanning
Background correction；
(3) it to spectrum obtained by step (2), is pre-processed without or through Chemical Measurement, selection modeling spectral region, using master
Componential analysis, that is, PCA dimensionality reduction is chosen one or more principal components as Modelling feature according to model performance index and right judging rate and is become
Amount, the prediction model of abo blood group is established using linearly or nonlinearly pattern recognition analysis method；
(4) it takes the tissue of unknown blood group to be sliced, infrared spectroscopy is measured according to step (2) the method, according to step
(3) the method carries out spectroscopic data processing, and then applying step (3) model built predicts the blood group of the histotomy.
Spectral measurement parameter in above-mentioned steps (2) have passed through preferably.It only uses and is suitable for histotomy detection ABO blood
The infrared spectrometry parameter of type could obtain the strong infrared spectroscopy of characterization performance, thus to establish the excellent ABO of estimated performance
Blood group identifies model and provides the data of high quality.
High resolution ratio can obtain more data, but simultaneously also along with the increase of noise.It is optimal in order to determine
Resolution ratio, scanning constant number of the present invention are 32 times, are respectively 2cm with resolution ratio-1、4cm-1、8cm-1、16cm-1、32cm-1It is right
Same slice is measured in parallel 6 times, and the smoothness of synthesis variance size and variance spectrum show that resolution ratio is 8cm-1And 16cm-1
Shi Guangpu is best, but due to 16cm-1Resolution ratio it is lower, slice information data are less, and therefore, the resolution ratio of spectral measurement is preferred
For 8cm-1。
Increasing scanning times can make spectrum more acurrate, but the acquisition time of spectrum can be increase accordingly.It is optimal in order to determine
Scanning times, fixed resolution of the present invention are 8cm-1, it is respectively 16,32,64,128 times parallel to same slice with scanning times
Measurement 6 times, as a result, it has been found that, spectral variance is larger when scanning times are 16 times and 32 times, and scanning times are 64 times and 128 Shi Fang
Difference spectra no significant difference, and scanning times are more, spent time is longer, and therefore, the scanning times of spectral measurement are preferably not
Lower than 64 times.
Since blank slide is lower than 1900cm generally in infrared spectroscopy-1Region will appear very strong absorption even
Hypersorption is unfavorable for spectrum analysis and Accurate Prediction, while in order to shorten the spectral measurement time, and the present invention carries out scanning range
Screening, from 4000~400cm of infrared range of spectrum-1Test serum characteristic information 4000~1900cm of region is inside selected-1Make
For the scanning range of spectral measurement.
Specifically, a kind of infrared spectrum analysis for identifying abo blood group based on histotomy, comprising the following steps:
(1) lung tissue's slice from different blood group human bodies is collected, and records the every corresponding blood group of slice；
(2) spectral measurement parameter: resolution ratio 8cm is set-1, scanning times not less than 64 times, scanning range 4000~
1900cm-1, the infrared transmission spectra of every slice obtained by measuring process (1), before each scan slice simultaneously with identical parameters scanning
Background correction；
(3) not preprocessed or be smoothly SGS pretreatment, selection through Savitzky-Golay to spectrum obtained by step (2)
The wave number upper limit value for modeling spectral region is 3833 ± 167cm-1That is 4000~3666cm-1, lower limit value 2100cm-1, use
PCA dimensionality reduction chooses preceding 10 principal components as Modelling feature variable, using linear or non-according to the sequence of contribution rate from high to low
Linear model identifying and analyzing method establishes the prediction model of abo blood group；
(4) the human lung's histotomy for taking unknown blood group measures infrared spectroscopy according to step (2) the method, according to
Step (3) the method carries out spectroscopic data processing, and then applying step (3) model built predicts the blood group of the histotomy.
Pretreated spectra scheme, modeling spectral region and Modelling feature variable in above-mentioned steps (3) are suitable for lung
The preferred embodiment of histotomy identification abo blood group.The optimization of modeling spectral region and Modelling feature variable helps to extract tissue
The characteristic information of middle abo blood group is to improve the specificity of prediction model.The present invention provides reflected based on lung pathologies histotomy
The specific embodiment of other abo blood group.It can be seen that from the embodiment and foundation identification abo blood group be sliced based on lung tissue
When model, using different Pretreated spectra schemes, modeling spectral region and Modelling feature variable, the performance of model built exists
Notable difference.
Preferably, in above-mentioned steps (3) to spectrum obtained by step (2) without pretreatment.Method is simpler, detection time
It is shorter.
Preferably, linear model identifying and analyzing method is discriminant analysis, that is, DA, nonlinear pattern recognition in above-mentioned steps (3)
Analysis method is opposite propagation artificial neural network, that is, CP-ANN.From specific embodiments of the present invention as can be seen that based on preferred
Pretreated spectra scheme, modeling spectral region and Modelling feature variable established identification abo blood group linear DA model and
Accurate identify can be achieved in non-linear CP-ANN model.That is, built DA model and CP-ANN model all have it is excellent
Estimated performance has been confirmed selected Pretreated spectra scheme, modeling spectral region and Modelling feature of the invention each other and has been become
Amount collective effect makes the characteristic information of sample be effectively extracted and utilize.
It preferably, is to measure a Zhang Guang in 3 different locations of every histotomy in the step of above method (2)
Spectrum, every spectrum is used to model, as sensitive as possible, quasi- to maximally utilise the characteristic information of blood group in histotomy
Really identified.
It preferably, is to take the histotomy of different blood groups random in the step of above method (2) when the spectrum of measurement slice
Measurement.It is can avoid by the way of different classes of sample random measurement because possible by the way of the measurement of the same category sampfe order
Caused systematic error generates interference to the predicting reliability of model built.
The present invention is the infrared spectroscopy based on histotomy, in conjunction with chemometric techniques, identifies abo blood group, have with
Lower advantage:
1) the method for the present invention is not influenced by whether tissue site and tissue site occur lesion, is suitable for different parts
Histotomy, including normal tissue sections and histopathologic slide；
2) the method for the present invention is easy to operate, detection is quick, durability is good (being influenced by extraneous factor smaller), and testing result is quasi-
Really, objective；
3) the method for the present invention can be common lossless using the identical histotomy that is unstained with pathological diagnosis, without additional
Histotomy is prepared, the bracket for blood grouping result that gained blood group identification result can obtain for other methods provides confirmation；
4) the method for the present invention has a very important significance in forensic medical examination, such as can be to some major motor vehicle things
Therefore the remaining dialysis corpse such as airplane crash, explosion and homicide scene or tissue carry out blood group confirmation quick and precisely to assist individual
Identification.
Detailed description of the invention
Fig. 1 is the distribution map for predicting the optimal DA model of histotomy blood group: A, B, AB, O respectively represent A type, Type B, AB
Type and O-shaped calibration set slice, a, b, ab, o respectively represent A type, Type B, AB type and O-shaped verifying collection slice.
Fig. 2 is the distribution map for predicting the optimal CP-ANN model of histotomy blood group: white area represents A type, light grey
Regional Representative's Type B, grey area represent O-shaped, and dark gray areas represents AB type；A, B, AB, O respectively represent A type, Type B, AB type
It is sliced with O-shaped calibration set, a, b, ab, o respectively represent A type, Type B, AB type and O-shaped verifying collection slice.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawing to of the invention preferred
Embodiment is described in detail.
Infrared spectrometer used in preferred embodiment is Nicolet iS50 FT-IR spectrometer (Thermo Fisher
Scientific)。
A kind of infrared spectroscopy DA method for identifying abo blood group based on histotomy of embodiment 1
1. the collection of sample
Lung of the collection from different patients is unstained, and (hardenability alveolar cell tumor tissue is cut for histopathologic slide totally 59
Piece 29 and lung in situ adenocarcinoma histotomy 30), including 34 A blood groups, 5 B blood groups, 8 AB blood groups and 12 O blood
Type records the every corresponding blood group information of slice.
2. the measurement of spectrum
After infrared spectrometer is preheated 2 hours and passes through verification, its symbol is confirmed using the polystyrene film being equipped at random
Spectroscopic assay requirement is closed, spectral measurement parameter: resolution ratio 8cm is set-1, scanning times 64 times, 4000~1900cm of scanning range-1, the infrared transmission spectra of every slice is measured, with identical parameters scanning and background correction, every slice before each scan slice
A Zhang Guangpu is respectively measured in 3 different locations respectively, every spectrum is used to model, the histotomy random measurement of 4 kinds of blood groups.
3. the extraction and modeling of spectral signature variable
(1) selection of Pretreated spectra scheme
In order to make model built have excellent estimated performance, to include it is untreated i.e. NP, multiplicative scatter correction, that is, MSC,
Standard contact transformation, that is, SNV, first derivative, that is, FD, second dervative, that is, SD, SGS, Norris are smoothly that the multiple spectrum of NDS is located in advance
Reason technology is screened and has been combined, and is shown in Table 1.The result shows that gained spectrum is not preprocessed or when pre-processing through SGS, is built
The estimated performance of DA model is optimal, such as the model 1 and 6 in table 1.
(2) selection of spectral region is modeled
Using aforementioned preferred Pretreated spectra scheme, absorbed according to the infrared signature of blood group in histotomy, in software
On the basis of automatic screening, the wave number upper limit value that artificial optimization models spectral region is 3833 ± 167cm-1I.e. 4000~
3666cm-1, lower limit value 2100cm-1, the calibration set right judging rate of model and verifying collection right judging rate are up to 100.0% at this time, institute
It can be used to model with the spectral region in optimization range, such as the model 1,13,14 and 15 in table 1；And when modeling spectrum
When range is not in optimization range, the calibration set right judging rate or/and verifying collection right judging rate of model are not up to 100.0%, in table 1
Model 16.
(3) selection of the dimensionality reduction of spectroscopic data and principal component
PCA dimensionality reduction is carried out to the spectroscopic data in selected modeling spectral region, when being modeled using different principal components, mould
The performance of type is there are notable difference, such as the model 1,11 and 12 in table 1, before finally choosing according to the sequence of contribution rate from high to low
10 principal components establish the DA model of prediction histotomy blood group as Modelling feature variable.
(4) foundation and verifying of model
Take 9 A blood groups, 2 B blood groups, 2 respectively from 34 A blood groups, 5 B blood groups, 8 AB blood groups and 12 O blood groups
As verifying collection slice, remaining is calibration set slice for piece AB blood group and 3 O blood group histotomies.Collected using calibration set and verifying
The principal component scores of spectroscopic data establish the DA model for identifying histotomy blood group with verifying.Seen from table 1, model 1,6,13,
14 and 15 calibration set right judging rate is that 100.0%, verifying collection right judging rate is 100.0%, and it is excellent to illustrate that these models have
Identification performance, can accurately identify the blood group of histotomy.The distribution map of optimal DA model (1 model 1 of table) is as shown in Figure 1.
The main modeling parameters and estimated performance of 1 blood group DA model of table
4. the prediction of unknown sample
The lung of 1 unknown blood group is taken to be unstained histopathologic slide (hardenability Pneumocytoma histotomy), according to
Method same as before acquires spectrum and carries out spectroscopic data processing, is then predicted using built DA model.DA model it is pre-
Survey as the result is shown: the blood group of the histotomy is A type, and the blood blood group identification result of patient corresponding with the histotomy is consistent.
Illustrate institute's construction method of the present invention can the blood group to histotomy accurately identified.
A kind of infrared spectroscopy CP-ANN method for identifying abo blood group based on histotomy of embodiment 2
1. the collection of sample
With embodiment 1.
2. the measurement of spectrum
With embodiment 1.
3. the extraction and modeling of spectral signature variable
(1) selection of the pretreating scheme of spectrum
In order to make model built that there is excellent estimated performance, to a variety of including NP, MSC, SNV, FD, SD, SGS, NDS
Pretreated spectra technology is screened and has been combined, and is shown in Table 2.The result shows that when gained spectrum is pre-processed through NP, built CP-ANN
The estimated performance of model is optimal, such as the model 1 in table 2.
(2) selection of spectral region is modeled
It is identical as DA model as used sample spectra when verifying CP-ANN model due to establishing, and two kinds of models
Prediction characteristic is similarly blood group, i.e., characterizes the effective information of same target feature in same spectra in same area, only model
Algorithm is different, so CP-ANN model is identical as modeling spectral region used in DA model, it is 3833~2100cm-1。
(3) selection of the dimensionality reduction of spectroscopic data and principal component
PCA dimensionality reduction is carried out to the spectroscopic data in selected modeling spectral region, when being modeled using different principal components, mould
The performance of type is there are notable difference, such as the model 1,11 and 12 in table 2, before finally choosing according to the sequence of contribution rate from high to low
10 principal components establish the CP-ANN model of prediction histotomy blood group as Modelling feature variable.
(4) foundation and verifying of model
Take 9 A blood groups, 2 B blood groups, 2 respectively from 34 A blood groups, 5 B blood groups, 8 AB blood groups and 12 O blood groups
As verifying collection slice, remaining is calibration set slice for piece AB blood group and 3 O blood group histotomies.Collected using calibration set and verifying
The principal component scores of spectroscopic data establish the CP-ANN model for identifying histotomy blood group with verifying.As can be seen from Table 2, model 1
Calibration set right judging rate is 100.0%, cross validation right judging rate is 98.0%, verifying collection right judging rate is 100.0%, illustrates the model
With excellent identification performance, it can accurately identify the blood group of histotomy.The distribution of optimal CP-ANN model (2 model 1 of table)
Figure is as shown in Figure 2.
The main modeling parameters and estimated performance of 2 blood group CP-ANN model of table
4. the prediction of unknown sample
The lung of 1 unknown blood group is taken to be unstained histopathologic slide (lung in situ adenocarcinoma histotomy), according to aforementioned phase
Spectrum is acquired with method and carries out spectroscopic data processing, is then predicted using built CP-ANN model.CP-ANN model
Prediction result is shown: the blood group of the histotomy is A type, the blood blood group identification result one of patient corresponding with the histotomy
It causes.Illustrate institute's construction method of the present invention can the blood group to histotomy accurately identified.
By above-mentioned experimental result it is found that linear DA model and non-linear CP-ANN model that embodiment 1 and embodiment 2 are established
It can sensitive, accurately predict the blood group of histotomy, it was demonstrated that the highly sensitive spectrum packet of histotomy that the method for the present invention obtains
The characteristic information of blood group is contained.When Pretreated spectra Scheme Choice is NP, Pretreated spectra scheme that two kinds of models use is built
Mould spectral region and Modelling feature variable are all the same, and two kinds of models all have excellent estimated performance, have confirmed this hair each other
Bright method accurately extracts and is utilized the effective information of target signature from infrared spectroscopy, ensure that the spy of analysis method of the present invention
Anisotropic, sensitivity and accuracy.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although passing through ginseng
According to the preferred embodiment of the present invention, invention has been described, however, those skilled in the art should understand that, can be in shape
Various changes are made in formula and to it in details, without departing from protection of the invention defined by the appended claims
Range.
Claims (7)
1. a kind of infrared spectrum analysis for identifying abo blood group based on histotomy, which comprises the following steps:
(1) histotomy from different blood group human bodies is collected, the every corresponding blood group of slice is recorded；
(2) infrared spectroscopy of every slice obtained by measuring process (1)；
(3) to spectrum obtained by step (2), spectroscopic data processing is carried out using chemometrics method, using pattern recognition analysis
Method establishes the prediction model of abo blood group；
(4) it takes the tissue of unknown blood group to be sliced, infrared spectroscopy is measured according to step (2) the method, according to step (3) institute
It states method and carries out spectroscopic data processing, then applying step (3) model built predicts the blood group of the histotomy.
2. a kind of infrared spectrum analysis for identifying abo blood group based on histotomy according to claim 1, feature
It is, comprising the following steps:
(1) histotomy from different blood group human bodies is collected, the every corresponding blood group of slice is recorded；
(2) spectral measurement parameter: resolution ratio 8cm is set-1, scanning times be not less than 64 times, 4000~1900cm of scanning range-1,
The infrared transmission spectra of every slice obtained by measuring process (1), with identical parameters scanning and background correction before each scan slice；
(3) it to spectrum obtained by step (2), is pre-processed without or through Chemical Measurement, selection modeling spectral region, using principal component
Analytic approach, that is, PCA dimensionality reduction chooses one or more principal components as Modelling feature variable according to model performance index and right judging rate,
The prediction model of abo blood group is established using linearly or nonlinearly pattern recognition analysis method；
(4) it takes the tissue of unknown blood group to be sliced, infrared spectroscopy is measured according to step (2) the method, according to step (3) institute
It states method and carries out spectroscopic data processing, then applying step (3) model built predicts the blood group of the histotomy.
3. a kind of infrared spectrum analysis for identifying abo blood group based on histotomy according to claim 2, feature
It is, comprising the following steps:
(1) lung tissue's slice from different blood group human bodies is collected, the every corresponding blood group of slice is recorded；
(2) spectral measurement parameter: resolution ratio 8cm is set-1, scanning times be not less than 64 times, 4000~1900cm of scanning range-1,
The infrared transmission spectra of every slice obtained by measuring process (1), with identical parameters scanning and background correction before each scan slice；
(3) not preprocessed or be smoothly SGS pretreatment, selection modeling through Savitzky-Golay to spectrum obtained by step (2)
The wave number upper limit value of spectral region is 3833 ± 167cm-1That is 4000~3666cm-1, lower limit value 2100cm-1, dropped using PCA
Dimension chooses preceding 10 principal components as Modelling feature variable, using linearly or nonlinearly according to the sequence of contribution rate from high to low
Pattern recognition analysis method establishes the prediction model of abo blood group；
(4) the human lung's histotomy for taking unknown blood group measures infrared spectroscopy according to step (2) the method, according to step
(3) the method carries out spectroscopic data processing, and then applying step (3) model built predicts the blood group of the histotomy.
4. a kind of infrared spectrum analysis for identifying abo blood group based on histotomy according to claim 3, feature
It is: to spectrum obtained by step (2) without pretreatment in step (3).
5. according to a kind of described in any item infrared spectrum analysis sides for identifying abo blood group based on histotomy of claim 2 to 4
Method, it is characterised in that: linear model identifying and analyzing method described in step (3) is discriminant analysis, that is, DA, the nonlinear model
Identifying and analyzing method is opposite propagation artificial neural network, that is, CP-ANN.
6. a kind of infrared spectrum analysis side for identifying abo blood group based on histotomy according to any one of claims 1 to 3
Method, it is characterised in that: be that 3 different locations being sliced at every measure a Zhang Guangpu in step (2), every spectrum is used to
Modeling.
7. a kind of infrared spectrum analysis side for identifying abo blood group based on histotomy according to any one of claims 1 to 3
Method, it is characterised in that: be the histotomy random measurement for taking different blood groups in step (2) when the spectrum of measurement slice.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910078389.4A CN109580527A (en) | 2019-01-18 | 2019-01-18 | A kind of infrared spectrum analysis identifying abo blood group based on histotomy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910078389.4A CN109580527A (en) | 2019-01-18 | 2019-01-18 | A kind of infrared spectrum analysis identifying abo blood group based on histotomy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109580527A true CN109580527A (en) | 2019-04-05 |
Family
ID=65918201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910078389.4A Pending CN109580527A (en) | 2019-01-18 | 2019-01-18 | A kind of infrared spectrum analysis identifying abo blood group based on histotomy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109580527A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110726695A (en) * | 2019-11-19 | 2020-01-24 | 湖北医药学院 | Method for identifying gastrodin near infrared spectrum specificity of different parts of brain tissue of mouse |
| CN110763652A (en) * | 2019-04-12 | 2020-02-07 | 重庆医科大学 | Near infrared spectrum method for detecting BRAF V600E mutation |
| CN112309498A (en) * | 2020-12-31 | 2021-02-02 | 武汉纽福斯生物科技有限公司 | Gene detection method and device based on deep learning and fluorescence spectrum |
| CN112466773A (en) * | 2021-02-01 | 2021-03-09 | 中电化合物半导体有限公司 | Method and device for detecting epitaxial thickness of semiconductor |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732121A (en) * | 2018-08-01 | 2018-11-02 | 重庆医科大学 | A method of benign and malignant tumour is differentiated based on infrared spectrum |
-
2019
- 2019-01-18 CN CN201910078389.4A patent/CN109580527A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108732121A (en) * | 2018-08-01 | 2018-11-02 | 重庆医科大学 | A method of benign and malignant tumour is differentiated based on infrared spectrum |
Non-Patent Citations (2)
| Title |
|---|
| PAGPARPAT VARRATHYAROM等: "Evaluated the Potential of Near Infrared Spectroscopy to Detect ABO Blood Grouping in Hair", 《J PUNJAB ACAD FORENSIC MED TOXICOL》 * |
| 杨剑: "病理组织切片ABO血型检测", 《中国法医学杂志》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110763652A (en) * | 2019-04-12 | 2020-02-07 | 重庆医科大学 | Near infrared spectrum method for detecting BRAF V600E mutation |
| CN110726695A (en) * | 2019-11-19 | 2020-01-24 | 湖北医药学院 | Method for identifying gastrodin near infrared spectrum specificity of different parts of brain tissue of mouse |
| CN112309498A (en) * | 2020-12-31 | 2021-02-02 | 武汉纽福斯生物科技有限公司 | Gene detection method and device based on deep learning and fluorescence spectrum |
| CN112309498B (en) * | 2020-12-31 | 2021-04-09 | 武汉纽福斯生物科技有限公司 | Gene detection method and device based on deep learning and fluorescence spectrum |
| CN112466773A (en) * | 2021-02-01 | 2021-03-09 | 中电化合物半导体有限公司 | Method and device for detecting epitaxial thickness of semiconductor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109580527A (en) | A kind of infrared spectrum analysis identifying abo blood group based on histotomy | |
| JP6333326B2 (en) | Analysis method of biological samples by spectral imaging | |
| US7038774B2 (en) | Method of characterizing spectrometer instruments and providing calibration models to compensate for instrument variation | |
| Been et al. | Profiling of counterfeit medicines by vibrational spectroscopy | |
| Chen et al. | Exploration research on the fusion of multimodal spectrum technology to improve performance of rapid diagnosis scheme for thyroid dysfunction | |
| Krafft et al. | Classification of malignant gliomas by infrared spectroscopy and linear discriminant analysis | |
| EP2480874B1 (en) | Serum infrared spectroscopy for non invasive assessment of hepatic fibrosis in patients with chronic liver disease | |
| Hall et al. | Near-infrared spectroscopic determination of serum total proteins, albumin, globulins, and urea | |
| Wu et al. | Classification of apple varieties using near infrared reflectance spectroscopy and fuzzy discriminant c‐means clustering model | |
| KR20130056886A (en) | Method for analyzing biological specimens by spectral imaging | |
| US20110028808A1 (en) | Method and apparatus for examination of cancer, systemic lupus erythematosus (sle), or antiphospholipid antibody syndrome using near-infrared light | |
| CN103674854A (en) | Apple grading method based on synergic interval partial least square discriminant analysis | |
| Ralbovsky et al. | Analysis of individual red blood cells for Celiac disease diagnosis | |
| CN108732121A (en) | A method of benign and malignant tumour is differentiated based on infrared spectrum | |
| CN113533236A (en) | Fruit spectrum feature extraction method, model training method and detection method | |
| CN109791158A (en) | The method that more attributes for complex sample monitor | |
| US20030087456A1 (en) | Within-sample variance classification of samples | |
| CN109520950A (en) | The insensitive chemical component spectral method of detection of a kind of pair of spectral shift | |
| CN109580526A (en) | A kind of infrared spectrum analysis identifying human body gender based on histotomy | |
| CN108931548A (en) | A method of tea-leaf producing area difference is identified by purifying displacement study H NMR spectroscopy | |
| CN108072628A (en) | A kind of near infrared spectroscopy for differentiating Medical Packing Materials material | |
| CN110108661B (en) | Tea near infrared spectrum classification method based on fuzzy maximum entropy clustering | |
| Zeb et al. | Towards the selection of the best machine learning techniques and methods for urinalysis | |
| CN107024449A (en) | The other near-infrared spectral analytical method of mammalian is differentiated based on urine | |
| CN106353280A (en) | Quick near infrared spectrum identification method of venlafaxine crystal |
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: 20190405 |
|
| RJ01 | Rejection of invention patent application after publication |