CN116399864A - Bacterial drug resistance detection method based on gram staining and machine vision - Google Patents
Bacterial drug resistance detection method based on gram staining and machine vision Download PDFInfo
- Publication number
- CN116399864A CN116399864A CN202310216133.1A CN202310216133A CN116399864A CN 116399864 A CN116399864 A CN 116399864A CN 202310216133 A CN202310216133 A CN 202310216133A CN 116399864 A CN116399864 A CN 116399864A
- Authority
- CN
- China
- Prior art keywords
- bacterial
- gram
- film sample
- solution
- sample
- 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
- 230000001580 bacterial effect Effects 0.000 title claims abstract description 56
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000003794 Gram staining Methods 0.000 title claims abstract description 21
- 206010059866 Drug resistance Diseases 0.000 title claims abstract description 16
- 239000000243 solution Substances 0.000 claims abstract description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 25
- 239000011521 glass Substances 0.000 claims abstract description 18
- 241000192125 Firmicutes Species 0.000 claims abstract description 17
- 238000011010 flushing procedure Methods 0.000 claims abstract description 16
- 239000000203 mixture Substances 0.000 claims abstract description 16
- 239000008223 sterile water Substances 0.000 claims abstract description 12
- 229940123982 Cell wall synthesis inhibitor Drugs 0.000 claims abstract description 10
- ZCYVEMRRCGMTRW-UHFFFAOYSA-N 7553-56-2 Chemical compound [I] ZCYVEMRRCGMTRW-UHFFFAOYSA-N 0.000 claims abstract description 9
- 239000013078 crystal Substances 0.000 claims abstract description 9
- 229910052740 iodine Inorganic materials 0.000 claims abstract description 9
- 239000011630 iodine Substances 0.000 claims abstract description 9
- OARRHUQTFTUEOS-UHFFFAOYSA-N safranin Chemical compound [Cl-].C=12C=C(N)C(C)=CC2=NC2=CC(C)=C(N)C=C2[N+]=1C1=CC=CC=C1 OARRHUQTFTUEOS-UHFFFAOYSA-N 0.000 claims abstract description 8
- 239000012192 staining solution Substances 0.000 claims abstract description 8
- IDGUHHHQCWSQLU-UHFFFAOYSA-N ethanol;hydrate Chemical compound O.CCO IDGUHHHQCWSQLU-UHFFFAOYSA-N 0.000 claims abstract description 7
- 238000001035 drying Methods 0.000 claims abstract description 6
- 238000011534 incubation Methods 0.000 claims abstract description 5
- 238000002156 mixing Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 22
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 14
- 239000008367 deionised water Substances 0.000 claims description 13
- 229910021641 deionized water Inorganic materials 0.000 claims description 13
- 238000004458 analytical method Methods 0.000 claims description 8
- 206010034133 Pathogen resistance Diseases 0.000 claims description 7
- 238000005406 washing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010521 absorption reaction Methods 0.000 claims description 3
- 238000004043 dyeing Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 241000894006 Bacteria Species 0.000 description 27
- 206010041925 Staphylococcal infections Diseases 0.000 description 20
- 208000015688 methicillin-resistant staphylococcus aureus infectious disease Diseases 0.000 description 20
- 229960003994 oxacillin sodium Drugs 0.000 description 10
- VDUVBBMAXXHEQP-ZTRPPZFVSA-M sodium;(2s,6r)-3,3-dimethyl-6-[(5-methyl-3-phenyl-1,2-oxazole-4-carbonyl)amino]-7-oxo-4-thia-1-azabicyclo[3.2.0]heptane-2-carboxylate Chemical compound [Na+].N([C@@H]1C(N2[C@H](C(C)(C)SC21)C([O-])=O)=O)C(=O)C1=C(C)ON=C1C1=CC=CC=C1 VDUVBBMAXXHEQP-ZTRPPZFVSA-M 0.000 description 10
- 238000010186 staining Methods 0.000 description 9
- RJQXTJLFIWVMTO-TYNCELHUSA-N Methicillin Chemical compound COC1=CC=CC(OC)=C1C(=O)N[C@@H]1C(=O)N2[C@@H](C(O)=O)C(C)(C)S[C@@H]21 RJQXTJLFIWVMTO-TYNCELHUSA-N 0.000 description 6
- 241000191967 Staphylococcus aureus Species 0.000 description 6
- 229940079593 drug Drugs 0.000 description 6
- 239000003814 drug Substances 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 6
- 229960003085 meticillin Drugs 0.000 description 6
- 210000002421 cell wall Anatomy 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000009635 antibiotic susceptibility testing Methods 0.000 description 3
- 239000003153 chemical reaction reagent Substances 0.000 description 3
- 238000001000 micrograph Methods 0.000 description 3
- 238000000513 principal component analysis Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 208000035143 Bacterial infection Diseases 0.000 description 2
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 2
- 239000003242 anti bacterial agent Substances 0.000 description 2
- 229940088710 antibiotic agent Drugs 0.000 description 2
- 239000007864 aqueous solution Substances 0.000 description 2
- 208000022362 bacterial infectious disease Diseases 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 229910052708 sodium Inorganic materials 0.000 description 2
- 239000011734 sodium Substances 0.000 description 2
- 230000004544 DNA amplification Effects 0.000 description 1
- MSFSPUZXLOGKHJ-UHFFFAOYSA-N Muraminsaeure Natural products OC(=O)C(C)OC1C(N)C(O)OC(CO)C1O MSFSPUZXLOGKHJ-UHFFFAOYSA-N 0.000 description 1
- 229930182555 Penicillin Natural products 0.000 description 1
- JGSARLDLIJGVTE-MBNYWOFBSA-N Penicillin G Chemical compound N([C@H]1[C@H]2SC([C@@H](N2C1=O)C(O)=O)(C)C)C(=O)CC1=CC=CC=C1 JGSARLDLIJGVTE-MBNYWOFBSA-N 0.000 description 1
- 108010013639 Peptidoglycan Proteins 0.000 description 1
- 108010059993 Vancomycin Proteins 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000002815 broth microdilution Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000005119 centrifugation Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007865 diluting Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003205 genotyping method Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007901 in situ hybridization Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000001840 matrix-assisted laser desorption--ionisation time-of-flight mass spectrometry Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000000386 microscopy Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 229960001019 oxacillin Drugs 0.000 description 1
- UWYHMGVUTGAWSP-JKIFEVAISA-N oxacillin Chemical compound N([C@@H]1C(N2[C@H](C(C)(C)S[C@@H]21)C(O)=O)=O)C(=O)C1=C(C)ON=C1C1=CC=CC=C1 UWYHMGVUTGAWSP-JKIFEVAISA-N 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 229940049954 penicillin Drugs 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 229960003165 vancomycin Drugs 0.000 description 1
- MYPYJXKWCTUITO-LYRMYLQWSA-N vancomycin Chemical compound O([C@@H]1[C@@H](O)[C@H](O)[C@@H](CO)O[C@H]1OC1=C2C=C3C=C1OC1=CC=C(C=C1Cl)[C@@H](O)[C@H](C(N[C@@H](CC(N)=O)C(=O)N[C@H]3C(=O)N[C@H]1C(=O)N[C@H](C(N[C@@H](C3=CC(O)=CC(O)=C3C=3C(O)=CC=C1C=3)C(O)=O)=O)[C@H](O)C1=CC=C(C(=C1)Cl)O2)=O)NC(=O)[C@@H](CC(C)C)NC)[C@H]1C[C@](C)(N)[C@H](O)[C@H](C)O1 MYPYJXKWCTUITO-LYRMYLQWSA-N 0.000 description 1
- MYPYJXKWCTUITO-UHFFFAOYSA-N vancomycin Natural products O1C(C(=C2)Cl)=CC=C2C(O)C(C(NC(C2=CC(O)=CC(O)=C2C=2C(O)=CC=C3C=2)C(O)=O)=O)NC(=O)C3NC(=O)C2NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(CC(C)C)NC)C(O)C(C=C3Cl)=CC=C3OC3=CC2=CC1=C3OC1OC(CO)C(O)C(O)C1OC1CC(C)(N)C(O)C(C)O1 MYPYJXKWCTUITO-UHFFFAOYSA-N 0.000 description 1
Images
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
- G01N21/84—Systems specially adapted for particular applications
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
- C12Q1/04—Determining presence or kind of microorganism; Use of selective media for testing antibiotics or bacteriocides; Compositions containing a chemical indicator therefor
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12Q—MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS; COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- C12Q1/00—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions
- C12Q1/02—Measuring or testing processes involving enzymes, nucleic acids or microorganisms; Compositions therefor; Processes of preparing such compositions involving viable microorganisms
- C12Q1/04—Determining presence or kind of microorganism; Use of selective media for testing antibiotics or bacteriocides; Compositions containing a chemical indicator therefor
- C12Q1/14—Streptococcus; Staphylococcus
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/30—Staining; Impregnating ; Fixation; Dehydration; Multistep processes for preparing samples of tissue, cell or nucleic acid material and the like for analysis
-
- C—CHEMISTRY; METALLURGY
- C12—BIOCHEMISTRY; BEER; SPIRITS; WINE; VINEGAR; MICROBIOLOGY; ENZYMOLOGY; MUTATION OR GENETIC ENGINEERING
- C12R—INDEXING SCHEME ASSOCIATED WITH SUBCLASSES C12C - C12Q, RELATING TO MICROORGANISMS
- C12R2001/00—Microorganisms ; Processes using microorganisms
- C12R2001/01—Bacteria or Actinomycetales ; using bacteria or Actinomycetales
- C12R2001/44—Staphylococcus
- C12R2001/445—Staphylococcus aureus
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A50/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE in human health protection, e.g. against extreme weather
- Y02A50/30—Against vector-borne diseases, e.g. mosquito-borne, fly-borne, tick-borne or waterborne diseases whose impact is exacerbated by climate change
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Organic Chemistry (AREA)
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Zoology (AREA)
- Biochemistry (AREA)
- Wood Science & Technology (AREA)
- Analytical Chemistry (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Biotechnology (AREA)
- Microbiology (AREA)
- Toxicology (AREA)
- Pathology (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a bacterial drug resistance detection method based on gram staining and machine vision, which comprises the following steps: step S1, a cell wall synthesis inhibitor acts on gram-positive bacteria, and after shaking, mixing and incubation treatment, centrifugal operation is carried out to obtain a mixture; step S2, adding a proper amount of sterile water into the mixture, transferring the mixture onto a glass slide for drying treatment, and then carrying out gram staining to obtain a first bacterial film sample; step S3, sequentially dripping a crystal violet solution, flushing, a gram iodine solution, flushing, an ethanol water solution, flushing, a safranin staining solution and flushing to the first bacterial film sample to obtain a final sample; and S4, observing the final sample to obtain a plurality of dyed pictures, extracting gray features of each dyed picture to obtain feature values, and analyzing each feature value to obtain a bacterial drug resistance detection result. The invention has the beneficial effect that the rapid detection of drug resistance of gram-positive bacteria can be realized.
Description
Technical Field
The invention relates to the technical field of bacterial drug resistance detection, in particular to a bacterial drug resistance detection method based on gram staining and machine vision.
Background
Infections caused by gram-positive bacteria are a terrible clinical threat, both morbidity and mortality are high, and mortality from drug-resistant bacterial infections is higher than from sensitive bacterial infections, and the current criteria for clinically detecting bacterial resistance are phenotypic methods of Antibiotic Susceptibility Testing (AST), such as paper spread testing and broth dilution testing, which require bacterial culture, typically taking 2-3 days, and genotyping methods based on DNA, gene amplification or sequencing, which may present false positives in addition to the cost of equipment and reagents far exceeding that of traditional AST, and in addition to other techniques approved by the U.S. Food and Drug Administration (FDA), such as MALDI-TOF, multiplex Automated Digital Microscopy (MADM) and accelerated Pheno systems based on fluorescence in situ hybridization, which, although mostly have high sensitivity, have complex sample pretreatment steps and require expensive and complex instrumentation.
Disclosure of Invention
The invention aims to solve the problems that: the bacterial drug resistance detection method based on gram staining and machine vision can effectively shorten the detection time of gram positive bacteria, reduce the cost of equipment and reagents, shorten the types of medicines and pretreatment steps, omit expensive and complex instruments, and simultaneously ensure the accuracy of detection results.
In order to solve the problems, the invention provides a bacterial drug resistance detection method based on gram staining and machine vision, which comprises the following steps:
step S1, a cell wall synthesis inhibitor acts on gram-positive bacteria, and after shaking, mixing and incubation treatment, centrifugal operation is carried out to obtain a mixture;
step S2, adding a proper amount of sterile water into the mixture, transferring the mixture onto a glass slide for drying treatment, and then carrying out gram staining to obtain a corresponding first bacterial film sample;
step S3, sequentially performing a crystal violet solution dropwise adding operation, a flushing operation, a gram iodine solution dropwise adding operation, a flushing operation, an ethanol water solution dropwise adding operation, a flushing operation, a safranin staining solution dropwise adding operation and a flushing operation on the first bacterial film sample to obtain a final sample;
and S4, carrying out microscopic observation on the final sample to obtain a plurality of dyed pictures, respectively carrying out gray feature extraction on each dyed picture by adopting a machine vision algorithm to obtain corresponding feature values, and then analyzing each feature value to obtain a corresponding bacterial drug resistance detection result.
Preferably, in the step S2, the mixture added with the sterile water is transferred onto the slide and subjected to a drying treatment at an ambient temperature of 40 ℃.
Preferably, the step S3 includes:
step S31, a proper amount of crystal violet solution is dripped into the first bacterial film sample and acts for 1 minute, and then deionized water is adopted to rinse the glass slide to obtain a second bacterial film sample;
step S32, a proper amount of gram iodine solution is dripped into the second bacterial film sample and acts for 1 minute, and then the deionized water is adopted to flush the glass slide to obtain a third bacterial film sample;
step S33, a proper amount of ethanol water solution is dripped into the third bacterial film sample for washing, and then the deionized water is adopted for washing the glass slide to obtain a fourth bacterial film sample;
and step S34, a proper amount of safranin staining solution is dripped into the fourth bacterial film sample and acts for 2 minutes, then the deionized water is adopted to flush the glass slide, and moisture absorption treatment is carried out to obtain the final sample.
Preferably, in the step S33, the third bacterial film sample is washed three times continuously by dropping the ethanol aqueous solution.
Preferably, the concentration of the aqueous ethanol solution is 95%.
Preferably, the step S4 includes:
s41, carrying out microscopic observation on the final sample to obtain a plurality of dyeing pictures;
step S42, respectively preprocessing each dyed picture and extracting gray features to obtain corresponding gray values, carrying out normalization processing on each dyed picture by a gray stretching method to obtain normalized images, then extracting the normalized images by a gray segmentation method to obtain bacterial areas, taking the normalized images containing the bacterial areas as final detection images and taking the gray values corresponding to the final detection images as the feature values;
and S43, visualizing the characteristic value by adopting an unsupervised analysis method, and analyzing the characteristic value by utilizing a pre-constructed supervision model to obtain a corresponding bacterial drug resistance detection result.
Preferably, in the step S1, the concentration of the cell wall synthesis inhibitor is 256. Mu.g/mL, and the concentration of the gram-positive bacteria is 10 7 CFU/mL。
Preferably, in the step S4, the final sample is observed by an optical microscope oil microscope at a magnification of 1000 times to obtain a plurality of stained pictures.
The invention has the following beneficial effects:
1) The preparation method only needs to prepare cell wall synthesis inhibitor, gram positive bacteria, sterile water, crystal violet solution, gram iodine solution, ethanol water solution, safranin staining solution and deionized water in advance, so that the types of medicines and pretreatment steps are greatly reduced, and the cost of reagents is reduced;
2) According to the invention, gray scale feature extraction is carried out on the dyed picture by utilizing a machine vision algorithm, and the feature value is directly analyzed to obtain a bacterial drug resistance detection result, so that the detection time of gram-positive bacteria can be effectively shortened, and meanwhile, the accuracy of the detection result is ensured;
3) The invention only needs to use the glass slide and the optical microscope for detection, can effectively reduce the cost of equipment and omits expensive and complex instruments.
Drawings
FIG. 1 is a flow chart of the steps of the present invention;
FIG. 2 is a flowchart showing the step S3 of the present invention;
FIG. 3 is a flowchart showing the step S4 of the present invention;
FIG. 4 is a microscopic image of the methicillin-resistant Staphylococcus aureus MRSA strain No.21B06749 of the present invention after gram staining;
FIG. 5 is a microscope image of the methicillin-resistant Staphylococcus aureus MRSA strain No.21R05333 of the present invention after gram staining;
FIG. 6 is a microscope image of methicillin-sensitive Staphylococcus aureus MSSA strain No.21B09710 after gram staining in accordance with the present invention;
FIG. 7 is a microscope image of methicillin-sensitive Staphylococcus aureus MSSA strain No.21W02902 after gram staining in accordance with the present invention;
fig. 8 (a) is a three-dimensional graph of the characteristic values of MRSA bacteria and MSSA bacteria of the present invention, and (b) is a violin graph of the characteristic values of MRSA bacteria and MSSA bacteria;
FIG. 9 (a) shows the PCA score of the dataset of the present invention, (b) shows the principal component analysis of MRSA bacteria and MSSA bacteria, and (c) shows the t-SNE analysis of MRSA bacteria and MSSA bacteria;
fig. 10 (a) shows the subject working characteristics obtained by analyzing MSSA strain and MRSA strain by LDA model, and (b) shows the subject working characteristics obtained by screening MSSA strain and MRSA strain by ANN model.
Detailed Description
In order that the above objects, features and advantages of the invention will be readily understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In a preferred embodiment of the present invention, based on the above-mentioned problems of the prior art, there is now provided a bacterial resistance detection method based on gram staining and machine vision, as shown in fig. 1, comprising the steps of:
step S1, a cell wall synthesis inhibitor acts on gram-positive bacteria, and after shaking, mixing and incubation treatment, centrifugal operation is carried out to obtain a mixture;
step S2, adding a proper amount of sterile water into the mixture, transferring the mixture onto a glass slide for drying treatment, and then carrying out gram staining to obtain a corresponding first bacterial film sample;
step S3, sequentially performing a crystal violet solution dropwise adding operation, a flushing operation, a gram iodine solution dropwise adding operation, a flushing operation, an ethanol water solution dropwise adding operation, a flushing operation, a safranin staining solution dropwise adding operation and a flushing operation on the first bacterial film sample to obtain a final sample;
and S4, carrying out microscopic observation on the final sample to obtain a plurality of dyed pictures, respectively carrying out gray feature extraction on each dyed picture by adopting a machine vision algorithm to obtain corresponding feature values, and then analyzing each feature value to obtain a corresponding bacterial drug resistance detection result.
In particular, in this example, considering that gram staining is an important microorganism classification tool, bacteria can be classified into gram-positive bacteria (purple) and gram-negative bacteria (pink) according to chemical and structural composition of cell walls, antibiotics of cell wall synthesis inhibitors such as penicillin, oxacillin, vancomycin and the like are added to bacteria and bacteria growth cultures, synthesis of cell wall peptidoglycan can be effectively inhibited, integrity of cell walls of gram-positive bacteria is damaged in the presence of antibiotics, and complex of crystal violet and iodine is not preserved in the decoloring process, so that it is gram-negative.
Preferably, a Machine Vision (MV) method belongs to a sub-field of artificial intelligence, and has achieved a great leap in recent years, and the machine vision method plays an important role in biomedical image analysis as well.
Preferably, the cell wall integrity of the gram-positive bacteria is destroyed and the color of the gram-negative bacteria appears under the action of the cell wall synthesis inhibitor, however, the gram-positive drug-resistant bacteria are relatively stable and still appear as the color of the gram-positive bacteria, and the change of the color can be detected by a machine vision method, so that the sensitive bacteria and the drug-resistant bacteria of the gram-positive bacteria can be directly classified by monitoring the change of the color of the staining.
Preferably, taking two strains of methicillin-resistant staphylococcus aureus MRSA and methicillin-sensitive staphylococcus aureus MSSA as examples, taking MRSA strain No.21B06749 for gram staining, and a microscopic image as shown in FIG. 4, wherein (a) represents staining results of three parallel experiments without treatment with oxacillin sodium, and (b), (c) and (d) represent staining results of three parallel experiments with oxacillin sodium, and the scale is 10 μm; gram staining was performed on MRSA strain No.21R05333, and a microscopic image is shown in FIG. 5, wherein (a) represents staining results of a treatment without using oxacillin sodium, and (b), (c) and (d) represent staining results of three parallel experiments with oxacillin sodium, with a scale of 10 μm; gram staining was performed on MSSA strain No.21B09710, and a microscopic image is shown in fig. 6, wherein (a) represents staining results of three parallel experiments without treatment with oxacillin sodium, and (b), (c) and (d) represent staining results of three parallel experiments with oxacillin sodium, with a scale of 10 μm; MSSA strain No.21W02902 was subjected to gram staining, and the microscopic image is shown in FIG. 7, wherein (a) represents the staining result of the treatment without using oxacillin sodium, and (b), (c) and (d) represent the staining result of three parallel experiments with oxacillin sodium, with a scale of 10. Mu.m.
In a preferred embodiment of the present invention, in step S2, the mixture with sterile water is transferred to a glass slide and dried at an ambient temperature of 40 ℃.
In a preferred embodiment of the present invention, as shown in fig. 2, step S3 includes:
step S31, a proper amount of crystal violet solution is dripped into the first bacterial film sample and acts for 1 minute, and then deionized water is adopted to rinse the glass slide to obtain a second bacterial film sample;
step S32, a proper amount of gram iodine solution is dripped into the second bacterial film sample and acts for 1 minute, and then deionized water is adopted to rinse the glass slide to obtain a third bacterial film sample;
step S33, a proper amount of ethanol aqueous solution is dripped into the third bacterial film sample for washing, and then deionized water is adopted for washing the glass slide to obtain a fourth bacterial film sample;
step S34, a proper amount of safranin staining solution is dripped into the fourth bacterial film sample and acts for 2 minutes, then deionized water is adopted to wash the glass slide, and moisture absorption treatment is carried out to obtain a final sample.
In a preferred embodiment of the present invention, in step S33, the third bacterial film sample is washed three times continuously by dripping an aqueous ethanol solution.
In a preferred embodiment of the invention, the concentration of the aqueous ethanol solution is 95%.
In a preferred embodiment of the present invention, as shown in fig. 3, step S4 includes:
step S41, carrying out microscopic observation on a final sample to obtain a plurality of dyeing pictures;
step S42, respectively preprocessing each dyed picture and extracting gray features to obtain corresponding gray values, carrying out normalization processing on each dyed picture by a gray stretching method to obtain normalized images, then extracting the normalized images by a gray segmentation method to obtain bacterial areas, taking the normalized images containing the bacterial areas as final detection images and taking the gray values corresponding to the final detection images as feature values;
and S43, visualizing the characteristic value by adopting an unsupervised analysis method, and analyzing the characteristic value by utilizing a pre-constructed supervision model to obtain a corresponding bacterial drug resistance detection result.
Specifically, in the present embodiment, the machine vision analysis of the dyed picture includes: in the process of preprocessing and gray feature extraction, all the dyed pictures are normalized through gray (0-255) stretching to eliminate calculation errors caused by different brightness of each dyed picture, a gray segmentation method is adopted to extract bacterial areas (ROI) in the dyed pictures, the ROI is reduced to obtain normalized images, the simplified color images are converted into red, green and blue channel images, average gray values (R_mean, G_mean and B_mean) of single channel images are calculated respectively and are used as feature values for further analysis, the model is constructed and optimized, feature data are visualized through unsupervised analysis (principal component analysis (PCA) and t-distribution random neighborhood embedding (t-SNE)), and then bacteria are classified through a Linear (LDA) and nonlinear classification model (ANN) construction model.
Preferably, taking MRSA bacteria and MSSA bacteria as examples, a three-dimensional graph of characteristic values of MRSA bacteria and MSSA bacteria is shown in fig. 8 (a), and a violin graph of characteristic values of MRSA bacteria and MSSA bacteria is shown in fig. 8 (b).
Preferably, the collected dye pictures are classified by two different constructed supervision models (LDA model and ANN model), model training, verification and optimization are performed by 3 times of cross verification, the dye pictures in the data set are randomly divided into three groups, two groups are used for training, the rest group is used for verification, and the circulation is performed three times until all data participate in training and testing, and in the cross verification process, a subject working characteristic curve (ROC), an Area Under Curve (AUC) and an accuracy index are calculated to optimize and verify the model, and parameters are adjusted for multiple times until the optimal performance of the model is achieved.
Preferably, the PCA scoring graph of the dataset is shown in FIG. 9 (a), the MRSA bacteria and MSSA bacteria principal component analysis graph is shown in FIG. 9 (b), and the MRSA bacteria and MSSA bacteria t-SNE analysis graph is shown in FIG. 9 (c).
Preferably, the subject working characteristics obtained by analyzing the MSSA strain and the MRSA strain by the LDA model are shown in (a) of fig. 10, and the subject working characteristics obtained by screening the MSS strain a and the MRSA strain by the ANN model are shown in (b) of fig. 10.
In a preferred embodiment of the present invention, in step S1, the concentration of the cell wall synthesis inhibitor is 256. Mu.g/mL, and the concentration of the gram-positive bacteria is 10 7 CFU/mL。
In the preferred embodiment of the present invention, in step S4, the final sample is observed by an optical microscope oil lens at 1000 times to obtain a plurality of stained pictures.
Embodiment one:
effect of oxacillin sodium with MSSA and MRSA:
the conditioned OD was obtained by using LB medium 600 Diluting bacterial liquid of MSSA and MRSA with value of 0.7-0.8 to 10 7 CFU·mL -1 Dissolving 1mg of oxacillin sodium in 1mL of sterile water to prepare 1000 mug.mL -1 The prepared benzoicillin sodium solution is diluted to 512 mug.mL step by using sterile water -1 500 mu L of benzoicillin sodium solution is taken and added with 500 mu L of 10 7 CFU·mL -1 After incubation in a thermostatic mixer at 37℃for 30min at 1250rpm, centrifugation at 10000pm for 2min, washing with 100. Mu.L of sterile water for 2 times, adding 20. Mu.L of sterile water to the pellet, mixing, transferring to a slide, drying at 40℃and performing the corresponding detection test.
Although the present disclosure is described above, the scope of protection of the present disclosure is not limited thereto. Various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the disclosure, and these changes and modifications will fall within the scope of the invention.
Claims (8)
1. A bacterial resistance detection method based on gram staining and machine vision, comprising the steps of:
step S1, a cell wall synthesis inhibitor acts on gram-positive bacteria, and after shaking, mixing and incubation treatment, centrifugal operation is carried out to obtain a mixture;
step S2, adding a proper amount of sterile water into the mixture, transferring the mixture onto a glass slide for drying treatment, and then carrying out gram staining to obtain a corresponding first bacterial film sample;
step S3, sequentially performing a crystal violet solution dropwise adding operation, a flushing operation, a gram iodine solution dropwise adding operation, a flushing operation, an ethanol water solution dropwise adding operation, a flushing operation, a safranin staining solution dropwise adding operation and a flushing operation on the first bacterial film sample to obtain a final sample;
and S4, carrying out microscopic observation on the final sample to obtain a plurality of dyed pictures, respectively carrying out gray feature extraction on each dyed picture by adopting a machine vision algorithm to obtain corresponding feature values, and then analyzing each feature value to obtain a corresponding bacterial drug resistance detection result.
2. The method according to claim 1, wherein in the step S2, the mixture added with the sterile water is transferred onto the slide and dried at an ambient temperature of 40 ℃.
3. The method for detecting bacterial resistance according to claim 1, wherein the step S3 comprises:
step S31, a proper amount of crystal violet solution is dripped into the first bacterial film sample and acts for 1 minute, and then deionized water is adopted to rinse the glass slide to obtain a second bacterial film sample;
step S32, a proper amount of gram iodine solution is dripped into the second bacterial film sample and acts for 1 minute, and then the deionized water is adopted to flush the glass slide to obtain a third bacterial film sample;
step S33, a proper amount of ethanol water solution is dripped into the third bacterial film sample for washing, and then the deionized water is adopted for washing the glass slide to obtain a fourth bacterial film sample;
and step S34, a proper amount of safranin staining solution is dripped into the fourth bacterial film sample and acts for 2 minutes, then the deionized water is adopted to flush the glass slide, and moisture absorption treatment is carried out to obtain the final sample.
4. The method according to claim 3, wherein in the step S33, the third bacterial film sample is washed three times continuously by dropping the aqueous ethanol solution.
5. The method for detecting bacterial resistance according to claim 3, wherein the concentration of the aqueous ethanol solution is 95%.
6. The method for detecting bacterial resistance according to claim 1, wherein the step S4 comprises:
s41, carrying out microscopic observation on the final sample to obtain a plurality of dyeing pictures;
step S42, respectively preprocessing each dyed picture and extracting gray features to obtain corresponding gray values, carrying out normalization processing on each dyed picture by a gray stretching method to obtain normalized images, then extracting the normalized images by a gray segmentation method to obtain bacterial areas, taking the normalized images containing the bacterial areas as final detection images and taking the gray values corresponding to the final detection images as the feature values;
and S43, visualizing the characteristic value by adopting an unsupervised analysis method, and analyzing the characteristic value by utilizing a pre-constructed supervision model to obtain a corresponding bacterial drug resistance detection result.
7. The method for detecting bacterial resistance according to claim 1, wherein in the step S1, the concentration of the cell wall synthesis inhibitor is 256. Mu.g/mL, and the concentration of the gram-positive bacteria is 10 7 CFU/mL。
8. The method according to claim 1, wherein in the step S4, the final sample is observed by an optical microscope at a magnification of 1000 times to obtain a plurality of the stained pictures.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310216133.1A CN116399864A (en) | 2023-03-08 | 2023-03-08 | Bacterial drug resistance detection method based on gram staining and machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310216133.1A CN116399864A (en) | 2023-03-08 | 2023-03-08 | Bacterial drug resistance detection method based on gram staining and machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116399864A true CN116399864A (en) | 2023-07-07 |
Family
ID=87011429
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310216133.1A Pending CN116399864A (en) | 2023-03-08 | 2023-03-08 | Bacterial drug resistance detection method based on gram staining and machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116399864A (en) |
-
2023
- 2023-03-08 CN CN202310216133.1A patent/CN116399864A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230145084A1 (en) | Artificial immunohistochemical image systems and methods | |
EP0635126B1 (en) | Detection of microorganisms and determination of their sensitivity to antibiotics | |
US20200357516A1 (en) | Systems and methods for automatically interpreting images of microbiological samples | |
Zahir et al. | High-throughput time-resolved morphology screening in bacteria reveals phenotypic responses to antibiotics | |
JP2023505265A (en) | Systems and methods for high-throughput drug screening | |
JP7534955B2 (en) | Method and system for identifying gram types of bacteria | |
KR20200100791A (en) | How to identify yeast or bacteria | |
Treebupachatsakul et al. | Microorganism image recognition based on deep learning application | |
Duan et al. | Rapid and Simple Approaches for Diagnosis of in Bloodstream Infections | |
He et al. | Rapid bacteria identification using structured illumination microscopy and machine learning | |
Paray et al. | Gram staining: a brief review | |
CN116399864A (en) | Bacterial drug resistance detection method based on gram staining and machine vision | |
Yu et al. | Simple and rapid discrimination of methicillin-resistant Staphylococcus aureus based on Gram staining and machine vision | |
JP7411583B2 (en) | A method for detecting bacteria according to their Gram signal in complex samples | |
Seo et al. | Morphological image analysis for foodborne bacteria classification | |
Wang et al. | Selective cultivation and rapid detection of Staphylococcus aureus by computer vision | |
Zmerli et al. | Rapid microbial viability assay using scanning electron microscopy: a proof-of-concept using Phosphotungstic acid staining | |
CN114921521A (en) | Food-borne intestinal pathogenic bacteria detection method based on deep convolutional neural network | |
Puchkov | Computer image analysis of microbial colonies | |
Corcuera et al. | Qualitative and quantitative agar invasion test based on bacterial colony/biofilm | |
Canciello et al. | An image processing‐based quantification of gram variability in Acinetobacter baumannii | |
Park et al. | Hyperspectral microscope imaging methods for multiplex detection of Campylobacter | |
Park et al. | New application of hyperspectral imaging for bacterial cell classification | |
Isil et al. | Virtual Gram staining of label-free bacteria using darkfield microscopy and deep learning | |
Köberle et al. | Next generation mycological diagnosis: Artificial intelligence‐based classifier of the presence of Malassezia yeasts in tape strip samples |
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 |