CN113702140B - Method for automatically calculating tissue section staining time and optimizing flow - Google Patents
Method for automatically calculating tissue section staining time and optimizing flow Download PDFInfo
- Publication number
- CN113702140B CN113702140B CN202110936153.7A CN202110936153A CN113702140B CN 113702140 B CN113702140 B CN 113702140B CN 202110936153 A CN202110936153 A CN 202110936153A CN 113702140 B CN113702140 B CN 113702140B
- Authority
- CN
- China
- Prior art keywords
- dyeing
- hard tissue
- staining
- time
- tissue slice
- 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.)
- Active
Links
- 238000010186 staining Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004043 dyeing Methods 0.000 claims abstract description 107
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 8
- 238000010200 validation analysis Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 239000007788 liquid Substances 0.000 claims 3
- 239000012192 staining solution Substances 0.000 description 6
- WZUVPPKBWHMQCE-UHFFFAOYSA-N Haematoxylin Chemical compound C12=CC(O)=C(O)C=C2CC2(O)C1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-UHFFFAOYSA-N 0.000 description 4
- 239000000975 dye Substances 0.000 description 3
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- 206010024769 Local reaction Diseases 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000016 photochemical curing Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000018044 dehydration Effects 0.000 description 1
- 238000006297 dehydration reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003292 glue Substances 0.000 description 1
- 238000012333 histopathological diagnosis Methods 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
Classifications
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a method for automatically calculating tissue slice staining time and optimizing flow, which comprises the steps of obtaining a hard tissue slice sample; inputting sample quantitative data, and calculating dyeing time t by using a dyeing estimation model 1; putting the sample into a dyeing machine for dyeing; taking out the sample after t time and putting the sample into a scanner; the automatic analysis module of the scanner calculates and analyzes the dyeing condition of the sample to obtain a result of whether counterstaining is needed; calculating the counterstain time and counterstain by using the dyeing estimation model 2 according to the counterstain result; and the scanner automatic analysis module analyzes the dyeing condition of the sample which does not need counterstaining to obtain dyeing evaluation. The invention effectively improves the stability and accuracy of dyeing time estimation, reduces the probability of occurrence of counterstain and overstain, improves the sheet forming rate of single hard tissue sections, improves the dyeing efficiency and quality, reduces the dependence on high-level technicians and saves the cost by optimizing the dyeing flow and applying the advanced algorithm principle.
Description
Technical Field
The invention belongs to the technical field of pathological section manufacturing, and particularly relates to a method for automatically calculating tissue section dyeing time and optimizing a flow.
Background
The hard tissue cutting and grinding technology is an important technical means for evaluating biological safety of the implantation local reaction test of the medical instrument. The local tissue containing the implant is subjected to the steps of tissue fixation, ethanol gradient dehydration, photo-curing resin glue infiltration, photo-curing embedding, tabletting, slicing, lapping, dyeing and the like to prepare the tissue lapping with the thickness of 20-50 mu m. The cycle span of making a standard hard tissue abrasive disc is very long, the whole operation steps are irreversible, and each hard tissue specimen block can be cut into a plurality of slices at most, and each slice is very precious, so that each operation is in place, careful and careful, accurate time control is realized, and errors are avoided. Furthermore, operators are required to constantly learn and practice, thereby accumulating a rich production experience. The dyeing operation is particularly critical, and only a hard tissue abrasive disc with high dyeing quality is manufactured, so that histopathological diagnosis can be effectively carried out, and accurate biosafety evaluation is carried out on an implantable local reaction test.
In conventional staining procedures, sections are stained with a variety of dyes. As shown in FIG. 1, the dyeing of each dye is essentially carried out according to the following procedure:
1) Obtaining a hard tissue slice sample;
2) Empirically estimating staining time n1 according to the thickness, type, size of the hard tissue section;
3) Placing the tissue slice into a dyeing machine for dyeing;
4) Taking out the slice after n1 min, and observing under a microscope;
5) Judging whether counterstaining is needed according to the observation result under the microscope, if so, entering the step 6), and if not, entering the step 7);
6) Estimating counterstain time n2 empirically according to the dyeing time, current dyeing condition, slice thickness, etc., and returning to step 3);
7) The completion of dyeing or the excessive dyeing is not required to be described by counterstaining, and whether the dyeing is completed or the excessive dyeing is confirmed according to the observation result under a mirror.
However, the existing staining procedures for such sections have the following problems:
1. in estimating the dyeing time n1, too many factors need to be considered, and the method completely depends on personal experience of technicians, so that it is often difficult to give an objective and accurate time estimation, so that most of slices need to be subjected to counterstain operation or the quality of the slices is too low due to excessive dyeing, and especially the process is highly dependent on experience of the technicians, so that the cost of enterprise personnel is increased, and quality control is difficult to guarantee due to influence of subjective factors.
2. When microscopic observation is carried out, a microscope is required to observe the dyeing conditions of multiple parts and different thicknesses of the slice, so that the operation is complicated and time-consuming, and only subjective qualitative analysis can be given to the dyeing conditions.
3. When the counterstain time n2 is estimated, the counterstain time needs to be estimated by comprehensively considering the microscopic observation result and the slice thickness. Because microscopic observation is tedious and time-consuming, the judgment is often to give an estimation result only according to the dyeing conditions of the last few parts, so that the process has poor stability of the estimation result and the dyeing condition estimation is difficult to quantify.
4. All three key steps of the whole dyeing process are highly dependent on experience of technicians, so that final flaking quality is low, flaking results are unstable, flaking rate of hard tissue specimens is low, and company operation cost is increased.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for automatically calculating the staining time of a tissue section and optimizing the flow, which improves the stability and the accuracy of the estimation of the staining time, reduces the probability of occurrence of counterstain and overstain, improves the flaking rate of a single hard tissue specimen, improves the staining efficiency and the quality, reduces the dependence on high-level technicians and reduces the company cost through the flow optimization and advanced algorithm principle.
In order to solve the technical problems and achieve the technical effects, the invention is realized by the following technical scheme:
a method for automatically calculating tissue section staining time and optimizing flow comprises the following steps:
step 1) obtaining a hard tissue slice sample to be stained;
step 2) inputting quantitative data of the hard tissue slice including thickness, type and size, and calculating dyeing time t by using a pre-trained dyeing estimation model 1;
step 3) placing the hard tissue slice into a dyeing machine for dyeing;
step 4) after the dyeing time t, taking out the dyed hard tissue slice, and putting the hard tissue slice into a scanner;
step 5), a scanner automatic analysis module in the scanner performs calculation analysis on the staining condition of the hard tissue slice to obtain an analysis result of whether the hard tissue slice needs counterstaining or not, if yes, the step 6) is entered, and if no, the step 7) is entered;
step 6) calculating the hard tissue section counterstain time T by using the staining estimation model 2 according to the counterstain result obtained by the scanner automatic analysis module, and then returning to the step 3);
step 7) the scanner in the scanner automatically analyzes the model, and directly gives the staining evaluation result of the hard tissue slice as the completion of staining or over staining.
Further, the training method of the staining evaluation model 1 is as follows:
1) Collecting historical data and experimental data, and obtaining related data of the hard tissue slice;
2) Processing the obtained related data of the hard tissue slice, taking the dyeing time in the data as output, taking the data except the dyeing time as input, and dividing the data into a verification set and a training set according to the proportion;
3) Training a model using a support vector machine regression model and the training set;
4) Validating a model using the validation set;
5) Finally, the dyeing estimation model 1 is obtained.
Further, the relevant data of the hard tissue section comprises the type, thickness and size of the hard tissue section, the room temperature for staining, the concentration of the staining solution, the using times of the staining solution, the using time of the staining solution, the optimal staining time and the like.
Further, the ratio of the validation set to the training set is 2:8.
further, the information of the hard tissue slice to be dyed including thickness, type and size is input into the dyeing estimation model 1, and the dyeing estimation model 1 automatically outputs the time required for dyeing the hard tissue slice.
Further, the scanner automatic analysis module quantitatively evaluates the staining condition of the hard tissue section by using the saturation.
Further, the method for calculating and analyzing the staining condition of the hard tissue slice by the automatic scanner analyzing module comprises the following steps:
s1) placing the dyed hard tissue slice into a scanner;
s2) a scanner shoots a preview image of the hard tissue slice, uniformly samples the whole tissue range of the hard tissue slice, and generates a plurality of pre-detection points;
s3) the scanner shoots an image of each pre-checking point along the Z axis direction at intervals of n micrometers, and the total of X images are obtained; i.e., X = sample thickness/n, where n is a positive number and X is a natural number;
s4) converting the shot X images into an HSV color space, and acquiring S average values of all the images by using an S saturation channel as a judgment basis of dyeing shades;
s5) the scanner automatic analysis module obtains the minimum value S in X S values min And S is combined with min Comparing with a preset counterstain threshold S1, so as to judge whether the hard tissue slice needs counterstaining or not;
if S min S1, giving out an analysis result requiring counterstaining, and entering a step S7);
if S min And (2) not needing counterstaining, giving an analysis result, and entering a step S6);
s6) for analysis results without counterstaining, the scanner automatic analysis module further obtains an intermediate value S in the X S values med And S is combined with med Comparing with a preset overstaining threshold S2, so as to judge whether the hard tissue slice which does not need counterstaining is overstained or not;
if S med S2, giving an evaluation result of the optimal dyeing;
if S med And (2) not less than S2, giving an evaluation result of excessive dyeing;
s7) the scanner automatic analysis module calculates the current dyeing depth Y now Recording the current dyeing time T now 。
Further, the method for constructing the staining evaluation model 2 comprises the following steps:
1) Collecting and acquiring discrete data set A of staining depth and corresponding staining time of hard tissue section
(Y 1 1 ，T 1 1 )、(Y 2 1 ，T 2 1 )…(Y n 1 ，T n 1 )，
(Y 1 2 ，T 1 2 )、(Y 2 2 ，T 2 2 )…(Y n 2 ，T n 2 )，
…
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
Wherein, the superscript 1,2, …, m represents a hard tissue slice with a certain number, and the subscripts 1,2, …, n represent the first observation in the staining process of the hard tissue slice; such as (Y) n m ，T n m ) Represents the depth of staining and the corresponding staining time in the nth observation of the hard tissue section m;
2) Designing a search algorithm, and searching slice data of the hard tissue slice m with the most similar staining process;
when the current staining depth and the current staining time (Y now ，T now ) And automatically searching a group of thicknesses Y in the data set A when the thickness Y of the hard tissue slice is larger than or equal to Y n And let the formula (Y) n m /Y now -1) 2 *(T n m /T now -1) 2 Staining data of the hard tissue section m with the smallest value,
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
3) Designing a searching algorithm, and searching the most similar data points in the staining data of the hard tissue section m;
staining data in hard tissue section m (Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m ) Middle search and current dyeing thickness Y now The most recent data point (Y x1 m ，T x1 m ) And the data point nearest to the slice thickness Y (Y x2 m ，T x2 m )；
4) Automatically calculating the counterstain time T;
T＝T now *(T x2 m /T x1 m -1)*(Y/Y now -1)/(Y x2 m /Y x1 m -1)；
5) Finally, a dyeing estimation model 2 is obtained.
Further, the current observation data (Y now ，T now ) And slice thickness Y, input the said dyeing estimate model 2, the said dyeing estimate model 2 gives the counterstain time automatically.
The beneficial effects of the invention are as follows:
1. the invention effectively improves the stability and accuracy of the estimation of the staining time of the hard tissue section by optimizing the staining process and applying the advanced algorithm principle, reduces the probability of occurrence of counterstain and excessive staining, improves the number and the rate of the single hard tissue specimens, improves the staining efficiency and the staining quality, reduces the dependence on high-level technicians, and saves the cost of companies.
2. The first dyeing estimation mode of the invention is superior to the traditional method, and the proportion of counterstain and overstain is greatly reduced, thereby improving the working efficiency and increasing the sheet rate of single hard slice.
3. The invention uses the full-automatic saturation quantitative method to replace the original complicated microscopic observation process, and can more comprehensively record the current dyeing condition.
4. The secondary dyeing estimation mode of the invention can more accurately estimate the dyeing time required by counterstaining by means of the pre-trained dyeing estimation model and the obtained quantitative data of the hard tissue slice, and can basically avoid the occurrence of secondary counterstaining of the hard tissue slice.
The foregoing description is only an overview of the present invention, and is intended to provide a more thorough understanding of the present invention, and is to be accorded the full scope of the present invention. Specific embodiments of the present invention are given in detail by the following examples.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:
FIG. 1 is a flow chart of a prior art staining of hard tissue sections;
FIG. 2 is a flow chart of staining of hard tissue sections according to the present invention.
Detailed Description
The present invention will be described in detail with reference to examples. The description herein is to be taken in a providing further understanding of the invention and is made a part of this application and the exemplary embodiments of the invention and their description are for the purpose of illustrating the invention and are not to be construed as limiting the invention.
Referring to fig. 2, a method for automatically calculating tissue section staining time and optimizing flow comprises the following steps:
step 1) obtaining a hard tissue slice sample to be stained;
step 2) inputting quantitative data of the hard tissue slice including thickness, type and size, and calculating dyeing time t by using a pre-trained dyeing estimation model 1;
step 3) placing the hard tissue slice into a dyeing machine for dyeing;
step 4) after the dyeing time t, taking out the dyed hard tissue slice, and putting the hard tissue slice into a scanner;
step 5), a scanner automatic analysis module in the scanner performs calculation analysis on the staining condition of the hard tissue slice to obtain an analysis result of whether the hard tissue slice needs counterstaining or not, if yes, the step 6) is entered, and if no, the step 7) is entered;
step 6) calculating the hard tissue section counterstain time T by using the staining estimation model 2 according to the counterstain result obtained by the scanner automatic analysis module, and then returning to the step 3);
and 7) directly giving the staining evaluation result of the hard tissue slice to be the completion of staining or excessive staining by the scanner automatic analysis module in the scanner.
Further, the training method of the staining evaluation model 1 is as follows:
1) Collecting historical data and experimental data, and obtaining related data of the hard tissue slice;
2) Processing the obtained related data of the hard tissue slice, taking the dyeing time in the data as output, taking the data except the dyeing time as input, and dividing the data into a verification set and a training set according to the proportion;
3) Training a model using a support vector machine regression model and the training set;
4) Validating a model using the validation set;
5) Finally, the dyeing estimation model 1 is obtained.
Further, the relevant data of the hard tissue section comprises the type, thickness and size of the hard tissue section, the room temperature for staining, the concentration of the staining solution, the using times of the staining solution, the using time of the staining solution, the optimal staining time and the like.
Further, the ratio of the validation set to the training set is 2:8.
further, the information of the hard tissue slice to be dyed including thickness, type and size is input into the dyeing estimation model 1, and the dyeing estimation model 1 automatically outputs the time required for dyeing the hard tissue slice.
Further, the scanner automatic analysis module quantitatively evaluates the staining condition of the hard tissue section by using the saturation.
Further, the method for calculating and analyzing the staining condition of the hard tissue slice by the automatic scanner analyzing module comprises the following steps:
s1) placing the dyed hard tissue slice into a scanner;
s2) a scanner shoots a preview image of the hard tissue slice, uniformly samples the whole tissue range of the hard tissue slice, and generates a plurality of pre-detection points;
s3) the scanner shoots an image of each pre-checking point along the Z axis direction at intervals of n micrometers, and the total of X images are obtained; i.e., X = sample thickness/n, where n is a positive number and X is a natural number;
s4) converting the shot X images into an HSV color space, and acquiring S average values of all the images by using an S saturation channel as a judgment basis of dyeing shades;
s5) the scanner automatic analysis module obtains the minimum value S in X S values min And S is combined with min Comparing with a preset counterstain threshold S1, so as to judge whether the hard tissue slice needs counterstaining or not;
if S min S1, giving out an analysis result requiring counterstaining, and entering a step S7);
if S min And (2) not needing counterstaining, giving an analysis result, and entering a step S6);
s6) for analysis results without counterstaining, the scanner automatic analysis module further obtains an intermediate value S in the X S values med And S is combined with med Comparing with a preset overstaining threshold S2, so as to judge whether the hard tissue slice which does not need counterstaining is overstained or not;
if S med S2, giving an evaluation result of the optimal dyeing;
if S med And (2) not less than S2, giving an evaluation result of excessive dyeing;
s7) the scanner automatic analysis module calculates the current dyeing depth Y now Recording the current dyeing time T now 。
Further, the method for constructing the staining evaluation model 2 comprises the following steps:
1) Collecting and acquiring discrete data set A of staining depth and corresponding staining time of hard tissue section
(Y 1 1 ，T 1 1 )、(Y 2 1 ，T 2 1 )…(Y n 1 ，T n 1 )，
(Y 1 2 ，T 1 2 )、(Y 2 2 ，T 2 2 )…(Y n 2 ，T n 2 )，
…
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
Wherein, the superscript 1,2, …, m represents a hard tissue slice with a certain number, and the subscripts 1,2, …, n represent the first observation in the staining process of the hard tissue slice; such as (Y) n m ，T n m ) Represents the depth of staining and the corresponding staining time in the nth observation of the hard tissue section m;
2) Designing a search algorithm, and searching slice data of the hard tissue slice m with the most similar staining process;
when the current staining depth and the current staining time (Y now ，T now ) And automatically searching a group of thicknesses Y in the data set A when the thickness Y of the hard tissue slice is larger than or equal to Y n And let the formula (Y) n m /Y now -1) 2 *(T n m /T now -1) 2 Staining data of the hard tissue section m with the smallest value,
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
3) Designing a searching algorithm, and searching the most similar data points in the staining data of the hard tissue section m;
staining data in hard tissue section m (Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m ) Middle search and current dyeing thickness Y now The most recent data point (Y x1 m ，T x1 m ) And the data point nearest to the slice thickness Y (Y x2 m ，T x2 m )；
4) Automatically calculating the counterstain time T;
T＝T now *(T x2 m /T x1 m -1)*(Y/Y now -1)/(Y x2 m /Y x1 m -1)；
5) Finally, a dyeing estimation model 2 is obtained.
Further, the current observation data (Y now ，T now ) And slice thickness Y, input the said dyeing estimate model 2, the said dyeing estimate model 2 gives the counterstain time automatically.
The following is one specific example of hematoxylin staining of dental hard tissue sections according to the present invention:
1) Obtaining a hard tissue slice of a tooth;
2) Inputting relevant information such as the thickness of a hard tissue section of the tooth is 30 micrometers, the size is 5mm, the concentration of the hematoxylin of the dye is 0.002g/ml, the use times are 1, the use time is 0 days and the like into a dyeing estimation model 1, and automatically obtaining the dyeing time for 22 minutes by the dyeing estimation model 1;
3) Placing the hard tissue slices of the teeth into a dyeing machine for dyeing;
4) Taking out the hard tissue slices of the teeth after 22 minutes, and putting the hard tissue slices into a scanner;
5) The automatic analysis module of the scanner in the scanner calculates and analyzes the staining condition of the hard tissue slice of the tooth to obtain a result that counterstain is needed;
6) Inputting current observation data and slice thickness of the hard tissue slice of the tooth into a dyeing estimation model 2, wherein the dyeing estimation model 2 automatically gives a counterstain time of 4 minutes;
7) Putting the hard tissue slice into a dyeing machine for counterstaining;
8) Taking out the hard tissue slices of the teeth after 4 minutes, and putting the hard tissue slices into a scanner again;
9) And (3) the automatic scanner analysis module in the scanner performs calculation analysis again on the staining condition of the hard tissue section of the tooth to obtain a result that counterstain is not needed and the staining is completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The method for automatically calculating the staining time of the tissue section and optimizing the flow is characterized by comprising the following steps of:
step 1) obtaining a hard tissue slice sample to be stained;
step 2) inputting quantitative data of the hard tissue slice including thickness, type and size, and calculating dyeing time t by using a pre-trained dyeing estimation model 1;
step 3) placing the hard tissue slice into a dyeing machine for dyeing;
step 4) after the dyeing time t, taking out the dyed hard tissue slice, and putting the hard tissue slice into a scanner;
step 5), a scanner automatic analysis module in the scanner performs calculation analysis on the staining condition of the hard tissue slice to obtain an analysis result of whether the hard tissue slice needs counterstaining or not, if yes, the step 6) is entered, and if no, the step 7) is entered;
the scanner automatic analysis module quantitatively evaluates the staining condition of the hard tissue slice by using the saturation; the method for calculating and analyzing the staining condition of the hard tissue slice by the scanner automatic analysis module comprises the following steps:
s1) placing the dyed hard tissue slice into a scanner;
s2) a scanner shoots a preview image of the hard tissue slice, uniformly samples the whole tissue range of the hard tissue slice, and generates a plurality of pre-detection points;
s3) the scanner shoots an image of each pre-checking point along the Z axis direction at intervals of n micrometers, and the total of X images are obtained; i.e., X = sample thickness/n, where n is a positive number and X is a natural number;
s4) converting the shot X images into an HSV color space, and acquiring S average values of all the images by using an S saturation channel as a judgment basis of dyeing shades;
s5) the scanner automatic analysis module obtains the minimum value S in X S values min And S is combined with min Comparing with a preset counterstain threshold S1, so as to judge whether the hard tissue slice needs counterstaining or not;
if S min < S1, give the analysis result of the counterstain, andstep S7) is entered;
if S min And (2) not needing counterstaining, giving an analysis result, and entering a step S6);
s6) for analysis results without counterstaining, the scanner automatic analysis module further obtains an intermediate value S in the X S values med And S is combined with med Comparing with a preset overstaining threshold S2, so as to judge whether the hard tissue slice which does not need counterstaining is overstained or not;
if S med S2, giving an evaluation result of the optimal dyeing;
if S med And (2) not less than S2, giving an evaluation result of excessive dyeing;
s7) the scanner automatic analysis module calculates the current dyeing depth Y now Recording the current dyeing time T now ；
Step 6) calculating the hard tissue section counterstain time T by using the staining estimation model 2 according to the counterstain result obtained by the scanner automatic analysis module, and then returning to the step 3);
and 7) directly giving the staining evaluation result of the hard tissue slice to be the completion of staining or excessive staining by the scanner automatic analysis module in the scanner.
2. The method for automatic calculation and optimization of tissue section staining time according to claim 1, wherein the training method of the staining evaluation model 1 is as follows:
1) Collecting historical data and experimental data, and obtaining related data of the hard tissue slice;
2) Processing the obtained related data of the hard tissue slice, taking the dyeing time in the data as output, taking the data except the dyeing time as input, and dividing the data into a verification set and a training set according to the proportion;
3) Training a model using a support vector machine regression model and the training set;
4) Validating a model using the validation set;
5) Finally, the dyeing estimation model 1 is obtained.
3. The method for automatic calculation and flow optimization of tissue slice staining time according to claim 2, wherein: the related data of the hard tissue slice comprises the type, thickness and size of the hard tissue slice, the dyeing room temperature, the concentration of the dyeing liquid, the using times of the dyeing liquid, the using time of the dyeing liquid, the optimal dyeing time and the like.
4. The method for automatic calculation and flow optimization of tissue slice staining time according to claim 2, wherein: the ratio of the validation set to the training set is 2:8.
5. the method for automatic calculation and flow optimization of tissue slice staining time according to claim 2, wherein: information of the hard tissue slice to be stained including thickness, type and size is input into the staining evaluation model 1, and the staining evaluation model 1 automatically outputs the time required for staining the hard tissue slice.
6. The method for automatically calculating the staining time and optimizing the flow of the tissue section according to claim 1, wherein the method for constructing the staining evaluation model 2 is as follows:
1) Collecting and acquiring discrete data set A of staining depth and corresponding staining time of hard tissue section
(Y 1 1 ，T 1 1 )、(Y 2 1 ，T 2 1 )…(Y n 1 ，T n 1 )，
(Y 1 2 ，T 1 2 )、(Y 2 2 ，T 2 2 )…(Y n 2 ，T n 2 )，
…
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
Wherein, the superscript 1,2, …, m represents a certainThe numbers of hard tissue sections, subscripts 1,2, …, n each represent a first observation during staining of the hard tissue section; such as (Y) n m ，T n m ) Represents the depth of staining and the corresponding staining time in the nth observation of the hard tissue section m;
2) Designing a search algorithm, and searching slice data of the hard tissue slice m with the most similar staining process;
when the current staining depth and the current staining time (Y now ，T now ) And automatically searching a group of thicknesses Y in the data set A when the thickness Y of the hard tissue slice is larger than or equal to Y n And let the formula (Y) n m /Y now -1) 2 *(T n m /T now -1) 2 Staining data of the hard tissue section m with the smallest value,
(Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m )；
3) Designing a searching algorithm, and searching the most similar data points in the staining data of the hard tissue section m;
staining data in hard tissue section m (Y 1 m ，T 1 m )、(Y 2 m ，T 2 m )…(Y n m ，T n m ) Middle search and current dyeing thickness Y now The most recent data point (Y x1 m ，T x1 m ) And the data point nearest to the slice thickness Y (Y x2 m ，T x2 m )；
4) Automatically calculating the counterstain time T;
T＝T now *(T x2 m /T x1 m -1)*(Y/Y now -1)/(Y x2 m /Y x1 m -1)；
5) Finally, a dyeing estimation model 2 is obtained.
7. The tissue of claim 6The method for automatically calculating the slice dyeing time and optimizing the flow is characterized by comprising the following steps of: the current observation data (Y now ，T now ) And slice thickness Y, input the said dyeing estimate model 2, the said dyeing estimate model 2 gives the counterstain time automatically.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936153.7A CN113702140B (en) | 2021-08-16 | 2021-08-16 | Method for automatically calculating tissue section staining time and optimizing flow |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110936153.7A CN113702140B (en) | 2021-08-16 | 2021-08-16 | Method for automatically calculating tissue section staining time and optimizing flow |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113702140A CN113702140A (en) | 2021-11-26 |
| CN113702140B true CN113702140B (en) | 2024-02-23 |
Family
ID=78653168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110936153.7A Active CN113702140B (en) | 2021-08-16 | 2021-08-16 | Method for automatically calculating tissue section staining time and optimizing flow |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113702140B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115033557A (en) * | 2022-08-11 | 2022-09-09 | 富联裕展科技(深圳)有限公司 | Dyeing model establishing method and device, dyeing method and equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142304A (en) * | 2013-05-06 | 2014-11-12 | 立信染整机械(深圳)有限公司 | Detection and control method of water washing programs of dyeing machine |
| CN106645153A (en) * | 2016-12-23 | 2017-05-10 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Fast staining and detecting method for cell pathological sections |
| CN108198250A (en) * | 2018-01-23 | 2018-06-22 | 网易（杭州）网络有限公司 | Virtual objects model colouring method and device, storage medium, electronic equipment |
| CN111982638A (en) * | 2020-08-20 | 2020-11-24 | 上海诒福科技有限公司 | Biological tissue staining method, biological tissue staining apparatus, computer device, and storage medium |
| CN112215801A (en) * | 2020-09-14 | 2021-01-12 | 北京航空航天大学 | Pathological image classification method and system based on deep learning and machine learning |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU762085B2 (en) * | 1999-04-13 | 2003-06-19 | Chromavision Medical Systems, Inc. | Histological reconstruction and automated image analysis |
| US10706535B2 (en) * | 2017-09-08 | 2020-07-07 | International Business Machines Corporation | Tissue staining quality determination |
| US11593656B2 (en) * | 2017-12-31 | 2023-02-28 | Astrazeneca Computational Pathology Gmbh | Using a first stain to train a model to predict the region stained by a second stain |
| WO2020039520A1 (en) * | 2018-08-22 | 2020-02-27 | オリンパス株式会社 | Image processing device, image system, operation method of image processing device, and operation program of image processing device |
-
2021
- 2021-08-16 CN CN202110936153.7A patent/CN113702140B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104142304A (en) * | 2013-05-06 | 2014-11-12 | 立信染整机械(深圳)有限公司 | Detection and control method of water washing programs of dyeing machine |
| CN106645153A (en) * | 2016-12-23 | 2017-05-10 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Fast staining and detecting method for cell pathological sections |
| CN108198250A (en) * | 2018-01-23 | 2018-06-22 | 网易（杭州）网络有限公司 | Virtual objects model colouring method and device, storage medium, electronic equipment |
| CN111982638A (en) * | 2020-08-20 | 2020-11-24 | 上海诒福科技有限公司 | Biological tissue staining method, biological tissue staining apparatus, computer device, and storage medium |
| CN112215801A (en) * | 2020-09-14 | 2021-01-12 | 北京航空航天大学 | Pathological image classification method and system based on deep learning and machine learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113702140A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2153401B1 (en) | System and method for quality assurance in pathology | |
| CN111260638B (en) | Automatic detection and counting method and system for cerebrospinal fluid cells and pathogens based on convolutional neural network | |
| CN112529234A (en) | Surface water quality prediction method based on deep learning | |
| CN113702140B (en) | Method for automatically calculating tissue section staining time and optimizing flow | |
| US20210124904A1 (en) | Smart Microscope System for Radiation Biodosimetry | |
| WO2012109571A1 (en) | Systems and methods for object identification | |
| US20230419483A1 (en) | Threshold determination method | |
| Mölder et al. | Semiautomated analysis of embryoscope images: Using localized variance of image intensity to detect embryo developmental stages | |
| CN107567631B (en) | Tissue sample analysis techniques | |
| EP3818468A1 (en) | Method and apparatus for training a neural network classifier to classify an image depicting one or more objects of a biological sample | |
| CN109615613A (en) | Method, device, computer equipment and storage medium for evaluating staining quality of pathological sections | |
| Goegebeur et al. | Goodness-of-fit testing for Weibull-type behavior | |
| CN102628377A (en) | Method for processing measured data of speed regulating system parameters of steam turbine unit | |
| CN110618130A (en) | Bacterium morphology identification system | |
| CN117136303A (en) | Information processing system, biological sample processing device, and program | |
| JP6246978B2 (en) | Method for detecting and quantifying fibrosis | |
| CN106802346A (en) | A kind of pathology aided analysis method based on immunohistochemistry technique | |
| CN105488521B (en) | A kind of dilatation screening sample method based on kernel function | |
| CN115063403A (en) | Method, Apparatus and Equipment for Recognition of Tertiary Lymphatic Structure | |
| CN108827887B (en) | Phytolacca acinosa genome size estimation method and genome size measurement system | |
| CN113222061A (en) | MRI image classification method based on two-way small sample learning | |
| CN102869988B (en) | Grafted evaluation method | |
| WO2020037255A1 (en) | Automatic identification and analysis of a tissue sample | |
| CN112750493A (en) | DNA ploid quantitative analysis method and system based on Papanicolaou staining mode | |
| CN116631617B (en) | Prostate Gleason scoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |