CN109991205A - A kind of counting algorithm of circulating tumor cell and application - Google Patents
A kind of counting algorithm of circulating tumor cell and application Download PDFInfo
- Publication number
- CN109991205A CN109991205A CN201910368036.8A CN201910368036A CN109991205A CN 109991205 A CN109991205 A CN 109991205A CN 201910368036 A CN201910368036 A CN 201910368036A CN 109991205 A CN109991205 A CN 109991205A
- Authority
- CN
- China
- Prior art keywords
- cell
- circulating tumor
- tumor cell
- matching
- full
- 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
- 208000005443 Circulating Neoplastic Cells Diseases 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 42
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 21
- 201000011510 cancer Diseases 0.000 claims abstract description 17
- 210000004881 tumor cell Anatomy 0.000 claims abstract description 15
- 230000005859 cell recognition Effects 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 210000004027 cell Anatomy 0.000 claims description 66
- 238000001914 filtration Methods 0.000 claims description 17
- 238000004043 dyeing Methods 0.000 claims description 16
- 239000007850 fluorescent dye Substances 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 210000004369 blood Anatomy 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 4
- 238000011282 treatment Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 claims description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 9
- 238000012360 testing method Methods 0.000 abstract description 9
- 238000004458 analytical method Methods 0.000 abstract description 8
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 239000003814 drug Substances 0.000 abstract description 3
- 229940079593 drug Drugs 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000012744 immunostaining Methods 0.000 abstract description 3
- 238000011337 individualized treatment Methods 0.000 abstract description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000000338 in vitro Methods 0.000 abstract description 2
- 230000009467 reduction Effects 0.000 abstract description 2
- 230000035945 sensitivity Effects 0.000 abstract description 2
- 238000010166 immunofluorescence Methods 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 9
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 8
- 201000005202 lung cancer Diseases 0.000 description 8
- 208000020816 lung neoplasm Diseases 0.000 description 8
- 239000011324 bead Substances 0.000 description 7
- FWBHETKCLVMNFS-UHFFFAOYSA-N 4',6-Diamino-2-phenylindol Chemical compound C1=CC(C(=N)N)=CC=C1C1=CC2=CC=C(C(N)=N)C=C2N1 FWBHETKCLVMNFS-UHFFFAOYSA-N 0.000 description 6
- 208000009458 Carcinoma in Situ Diseases 0.000 description 5
- 201000004933 in situ carcinoma Diseases 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 101000738771 Homo sapiens Receptor-type tyrosine-protein phosphatase C Proteins 0.000 description 4
- 102100037422 Receptor-type tyrosine-protein phosphatase C Human genes 0.000 description 4
- 238000011534 incubation Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000012535 impurity Substances 0.000 description 3
- 238000000527 sonication Methods 0.000 description 3
- 238000010408 sweeping Methods 0.000 description 3
- 210000001364 upper extremity Anatomy 0.000 description 3
- 238000000018 DNA microarray Methods 0.000 description 2
- 241000283973 Oryctolagus cuniculus Species 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000000799 fluorescence microscopy Methods 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000427 antigen Substances 0.000 description 1
- 102000036639 antigens Human genes 0.000 description 1
- 108091007433 antigens Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 210000000601 blood cell Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 238000004113 cell culture Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000004324 lymphatic system Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000005374 membrane filtration Methods 0.000 description 1
- 239000002086 nanomaterial Substances 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 210000002966 serum Anatomy 0.000 description 1
- 230000009897 systematic effect Effects 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
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/645—Specially adapted constructive features of fluorimeters
- G01N21/6456—Spatial resolved fluorescence measurements; Imaging
- G01N21/6458—Fluorescence microscopy
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/62—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light
- G01N21/63—Systems in which the material investigated is excited whereby it emits light or causes a change in wavelength of the incident light optically excited
- G01N21/64—Fluorescence; Phosphorescence
- G01N21/6486—Measuring fluorescence of biological material, e.g. DNA, RNA, cells
-
- 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
- G01N2001/302—Stain compositions
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1006—Investigating individual particles for cytology
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/10—Investigating individual particles
- G01N2015/1024—Counting particles by non-optical means
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Biomedical Technology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Dispersion Chemistry (AREA)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention belongs to detect circulating tumor cell technical field, and in particular to a kind of method and its application for calculating circulating tumor cell.This method is enriched with all areas of the chip of the tumour cell of immunostaining by inverted fluorescence microscope scanning shoot, extract the image series of shooting fluorescence channel, image series are spliced into complete image again, complete full figure again through removal background, removal noise, cavity filling, be adhered cell recognition and carry out analytical calculation circulating tumor cell number.This method compensates for the blank of micro-fluidic circulating tumor cell detection chip subsequent detection, large and complete is presented to testing staff for acquisition testing information, reduction personnel's analysis time, improve detection accuracy, it offers an opinion for diagnosis, there is very big effect to the accurate tracking and monitoring, curative effect evaluation, drug sensitivity testing in vitro individualized treatment of cancer.
Description
Technical field
The invention belongs to detect circulating tumor cell technical field, and in particular to a kind of counting algorithm of circulating tumor cell
And its application.
Background technique
Cancer has become the disease for seriously threatening human life and health at this stage.Cancer cell is the pathogeny for generating cancer,
It is a kind of cell of variation, it is different from normal cell, has infinite multiplication, can convert and easily shift three big features, can be unlimited
It is proliferated and destroys normal cell tissue.Cancer cell is out of control outer in addition to dividing, can also locally invade arround normal tissue even warp
Body other parts are transferred to by body-internal-circulation system or lymphatic system.Malignant tumour is begun to when very early to blood
In discharge complete cancer cell, therefore the circulating tumor cell in cancer early detection blood has the diagnosing and treating of cancer
There is positive effect.
The existing circulating tumor cell detection method of existing market mainly has membrane filtration technique and immunomagnetic bead technique.Wherein
Immunomagnetic bead technique mainly utilizes magnetic bead and antibody to combine, then by the antibody for having magnetic bead and circulating tumor cell antigen binding
It is integrated, is attracted by magnet, the circulating tumor cell for being combined with magnetic bead is separated with normal cell.The disadvantages of this method is
Must first know circulating tumor cell type can configure antibody magnetic bead, and magnetic bead enter after circulating tumor cell can destroy it is thin
Cytoactive can not carry out the subsequent further screening procedure such as further cell culture.Membrane filter method, using the micro- logical of certain diameter
The normal cell of the biggish cancer cell of volume and small volume is separated by filtration by hole.The through-hole difficulty of processing of this method is larger, and
And limited by cell blocking through-hole, detection speed is slower, while hole wall is when stopping cancer cell, it is possible to can have to cell
Destruction influences cell activity.Also there is the circulating tumor cell of the collection using spiral centrifugal, have acquisition circulating tumor thin
Advantages such as cytoactive is good, but be difficult to controllable operating, filtering purity is low, and it is more to adulterate quantity of leucocyte in circulating tumor cell channel,
Very hang-up is brought to subsequent further examination.
And micro-fluidic circulating tumor cell detection chip is a kind of novel micro-nano structure device.Utilize different quality and body
Suffered inertia lift of the long-pending cell in spirality channel and resistance difference, so that moving radius is different, respectively along micro- logical
The inner wall or outer wall in road move, by the way that the separation of circulating tumor cell may be implemented in inner wall or opening of external wall, and by micro-
Through-hole array chip carries out secondary filter, further increases filtering purity, while being convenient for the collection of circulating tumor cell.The technology
The fast speed of circulating tumor cell is separated, accuracy is higher, and completely lossless to circulating tumor cell, while cost of manufacture
It is lower, the very wide utilization of following application prospect.
But there is no the subsequent further screening procedures for being directed to micro-fluidic circulating tumor cell detection chip at present, further
The method for calculating circulating tumor cell is screened, therefore, the invention proposes one kind to detect core for micro-fluidic circulating tumor cell
Piece separates the examination calculation method after circulating tumor cell, provides the means screened and calculated for cancer doctor and scientific research personnel.
Summary of the invention
In view of this, one of the objects of the present invention is to provide a kind of method for calculating circulating tumor cell, the method
For observing and analyzing the cell through immunofluorescence dyeing being collected into micro-fluidic circulating tumor cell detection chip, therefrom discriminate
Circulating tumor cell and output Chu not be counted.
To achieve the above object, the present invention uses following scheme:
A method of circulating tumor cell is calculated, the swollen of immunostaining is enriched with by inverted fluorescence microscope scanning shoot
The all areas of the chip of oncocyte extract the complete image of shooting fluorescence channel, then through removal background, removal noise, cavity
It fills, be adhered cell recognition and carry out analytical calculation circulating tumor cell number.
Specifically, the method for immunostaining is according to documented by " Measurement for Biochemistry principle and application " fourth edition profession book
Method is implemented.
Further, the circulating tumor cell is the circulating tumor collected using micro-fluidic circulating tumor cell detection chip
Cell.
Specifically, the micro-fluidic circulating tumor cell detection chip is as shown in Figure 1, the micro-fluidic circulating tumor cell
The cell sample that detection chip is collected can preferably keep activity and be metabolized convenient for subsequent cell closer to Tissue biopsy samples
Experiment.
Further, the inverted fluorescence microscope channel of the observation shooting is 4.
Specifically, 4 channels can be 1 white light channel, the corresponding fluorescence channel of 3 fluorescent dyes, can divide
Not are as follows: the channel DAPI, CD45, Anti-c-Kit.
Further, the algorithm that the serial picture is spliced into complete full figure realizes that program is calculated using template matching algorithm
Method finds the part that shooting is overlapped in serial picture, and serial picture is spliced into one completely according to the position coordinates being matched to
Blood cell sample full figure.
The function of images match is to find most to match (similar) portion with another width template image (T) in piece image (I)
Point.In order to determine matching area, slides (from left to right, from top to bottom) template image and original image is compared.For template
Image (T) is covered on each position on matching image (I), and matching degree magnitude is saved in result images matrix (R).In R
In each position include matching degree magnitude R (x, y)
Matching algorithm of the invention can be used 4 kinds of matching ways: difference of two squares matching, standard deviation matching, relevant matches,
Four kinds of standard relevant matches.The matching of default choice standard deviation.
The matched matching degree magnitude of the difference of two squares is expressed as:
The matched matching degree magnitude of standard deviation is expressed as:
Both the above by the difference of two squares come carry out it is matched in the way of, preferably matching R (x, y) be 0, matching value is bigger, matching
It is poorer.
The matching degree magnitude of the relevant matches is expressed as:
The matching degree magnitude of the standard relevant matches is expressed as:
Relevant matches and standard relevant matches are calculated using the multiplication operation between template and image, and biggish number indicates
Matching degree is higher, and 0 indicates the worst matching effect
Realize the specific algorithm step of splicing
Step 1: the realization of the splicing function is guaranteed using the image under scanning shoot inverted fluorescence microscope counterclockwise
The adjacent picture of shooting has overlapping region, and the picture in 4 channels is shot under each camera lens, guarantees the picture size position in all channels
It is identical.By the picture in the serial picture white light channel taken marked as Image1, Image2 ... ImageI ... ImageN, 3
Picture under fluorescence channel is respectively labeled as:
DAPI:Image1-1,Image2-1…ImageI-1…ImageN-1
CD45:Image1-1,Image2-1…ImageI-1…ImageN-1
Anti-c-Kit:Image1-1,Image2-1…ImageI-1…ImageN-1
Step 2: this step is template matching process, and matching algorithm can successively use 4 kinds, until successful match.Cause
Ensure that adjacent picture in step 1, there are overlapping regions, so 4 kinds of matching ways ensure that serial picture can be matched into
Function.Specifically, choosing the first picture Image1 is the first picture of row and matching picture, selection Image2 picture is current template figure
Piece, select current template picture from right to left 10% pixel region as template Template, match a picture
Image1 (a upper picture of Image2 is Image1, that is, matching picture Image1), obtains matching result R (x, y), greatly
In the expression successful match that threshold value is σ, matching picture becomes Image2, and template picture becomes Image3 (next of Image2
Picture);If matching result is less than threshold value σ, then it represents that unmatch, reselect current template picture from top to bottom 10% picture
Plain region obtains matching result R (x, y) as template Template, matching row head picture Image1, if successful match, row is first
Picture becomes current template picture Image2, and matching picture becomes Image2, and template picture becomes Image3, and (Image2's is next
Picture).
Step 3: in the coordinate P for the matching image that Record Matching Algorithm obtains to splicing list PList.According to matching algorithm
The coordinate that obtains, is spliced into new figure at matching picture, template picture.
Step 4: next picture of change current template picture is current template picture, repeats step 2, step 3, until
For last picture as current template picture and until generating last new figure, new figure final at this time is to be inverted fluorescence microscopy
The full figure of cell sample under mirror.
Step 5: according to the splicing list PList in step 3, successively splicing the serial picture of 3 fluorescence channels, obtain glimmering
Optical channel cell full figure.
Further, noise is removed using median filtering, then by the binary conversion treatment of full figure through-hole background removal.Binaryzation
Pattern later is that cell recognition filters out effective coverage.Full figure binaryzation is the necessary preamble step of subsequent Hole filling algorithms
Suddenly, in this figure cell compartment be it is white, background colour be it is black, white block be concentrate be absorbed in analyzed area.
Through many experiments it has been observed that the noise in biochip substantially belongs to impulsive noise, therefore this algorithm uses intermediate value
Filtering is to remove noise.Median filtering replaces isolated noise spot with the intermediate value being respectively worth in surrounding neighbors, disappears to reach
Retain the purpose of important image detail while except noise spot.
It removes useless through-hole background patterns, and purpose mainly eliminates the hole image in chip to cell recognition
Interference improves accuracy for subsequent algorithm process.The method of removal through-hole still uses matching algorithm to realize.It must carry out 2
Secondary matching, accurate matching, can match the through-hole for filtering out cell-free region for the first time, after completing accurate matching for the first time, into
The thick matching of row, can filter out the via regions of cell peripheral.
Specific steps, step 1: one cell full figure of duplication carries out median filtering to it and crosses noise filtering.
Step 2: using clean biochip through-hole as die plate pattern, cell full figure, will height as matching picture
The pixel region two-value for the chip picture being fitted on turns to 0 (black).
Step 3: region of this figure other than black portions is set to 255 (whites)
Further, the preliminary identification of circulating tumor cell is carried out using Hole filling algorithms.
Hole filling algorithms refer to a known seed point, are expanded outward from seed point up to full of entire hole.If lonely
The form size color of vertical hole all generally conforms to require, and can tentatively be confirmed as tumour cell;For the too small hole of size, can neglect
Slightly;For king-sized, can tentatively be confirmed as being adhered cell.
Step 1: choosing the binaryzation cell full figure by pretreatment, removal noise and removal background and carry out holes filling.
Step 2: setting the threshold value of holes filling as σ, be not filled with, otherwise fill if hole area is greater than threshold value.
Step 3: for the too small hole of area, can directly be set to background colour, make its disappearance.
Step 4: for the hole of several times size, it is believed that be adhered cell, be marked as BCell.
Further, cell is adhered further to identify using watershed algorithm.
The gray value of every bit pixel indicates the height above sea level of the point in the image of watershed, each local minimum and its
Influence area is known as reception basin, and the boundary of reception basin then forms watershed.Algorithm pierces through on each local minimum surface
One aperture, then slowly fills the water, and the domain of influence of each local minimum slowly extends to the outside, in two reception basin meets
Dam is constructed, that is, forms watershed.The place of height above sea level will not be overflow by water, to achieve the purpose that segmentation.
Binary picture boundary after holes filling is very clear.And the grayscale image in binary picture is obtained, it can be right
The black white image of binaryzation carries out range conversion, and range conversion, which refers to, is located proximate to nonzero element position most where neutral element
Short distance;Picture after range conversion is no longer binary map, but the black and white picture of height is indicated with grayscale, to this figure
Piece carries out the unrestrained operation of water.
Step 1: the picture after selection step 4 holes filling carries out range conversion, obtains DisImage
Step 2: the unrestrained operation of water is carried out to obtained DisImage.
Further, unrecognized for watershed algorithm to be adhered cell, using manual identification.
Specifically, the method for manual identification is specifically, at the interface UI of algorithm routine, user uses mouse as pen, for
It is adhered cell join domain to cross manually, the value of the pixel streaked is set as 0, after mouse up, then carries out a secondary ridge point
It cuts.
Further, cancer cell final amt is confirmed for fluorescence channel.
Specifically, the circulating tumor cell that white light channel is identified by above-mentioned series of algorithms, algorithm routine provide
Its specific location coordinate information detects whether exist in fluorescence channel full figure respectively again according to coordinate, and pixel is not 0 (black)
Then indicate there is corresponding fluorescent dye herein, then it represents that circulating tumor cell exists.
The second purpose of the present invention is to provide a kind of methods for calculating circulating tumor cell to calculate cancer early stage blood
It is applied in circulating tumor cell in liquid.
The method for calculating circulating tumor cell can provide information analysis function, and large and complete acquisition testing information is presented
To testing staff, reduce personnel's analysis time, improve detection accuracy, offer an opinion for diagnosis, to the accurate tracking and monitoring of cancer,
Curative effect evaluation, drug sensitivity testing in vitro individualized treatment have very big effect.
Preferably, the mating micro-fluidic circulating tumor cell detection chip of method for calculating circulating tumor cell makes
With can preferably provide more accurately information analysis function.
Specifically, the tumour is lung cancer (carcinoma in situ).
The third object of the present invention is to provide a kind of application, specially template matching algorithm and median filtering and binaryzation
The application in circulating tumor cell, the side for calculating circulating tumor cell are being calculated with Hole filling algorithms and watershed algorithm
Method includes removal background to image, removal noise, cavity filling and is adhered cell recognition.
Specifically, median filtering replaces isolated noise spot with the intermediate value being respectively worth in surrounding neighbors, disappear to reach
Retain the purpose of important image detail while except noise spot.Binaryzation is the necessary previous step of subsequent Hole filling algorithms,
Full figure is copied binaryzation full figure as reference by algorithm, cell compartment in this figure is all bleached, background colour whole blackening is white
Color block is to concentrate to be absorbed in analyzed area.
Specifically, Hole filling algorithms refer to a known seed point, expanded outward from seed point up to full of entire hole
Hole.Since tumour cell has already passed through immunofluorescence dyeing, by pretreatment, removal background and the chip full figure for removing noise
On, the location point of fluorescent staining is chosen, the seed point as holes filling;Chip full figure Jing Guo binaryzation is carried out hole to fill out
It fills.If the form size color of isolated hole all generally conforms to require, it can tentatively be confirmed as tumour cell;It is too small for size
Hole can be ignored;For king-sized, can tentatively be confirmed as being adhered cell.
Specifically, being adhered thin through Hole filling algorithms, treated that image is adhered the seed point in cell compartment discharges water
The place that surrounding's gradient of born of the same parents is high will not be overflow by water, and to achieve the purpose that segmentation, further identification is adhered cell.
Specifically, the pretreated algorithm is matched using the difference of two squares and/or standard deviation matches and/or relevant matches
And/or standard relevant matches.
Specifically, removing noise using median filtering, then full figure is subjected to binary conversion treatment.
Specifically, carrying out the preliminary identification for being adhered cell using Hole filling algorithms.
Specifically, being adhered cell using watershed algorithm further to identify.
Specifically, the tumour is lung cancer (carcinoma in situ).
The beneficial effects of the present invention are:
1) the large and complete acquisition testing information of the method for the present invention for calculating circulating tumor cell is presented to testing staff,
Reduction personnel's analysis time improves detection accuracy, offers an opinion for diagnosis, to accurate tracking and monitoring, curative effect evaluation, the body of cancer
Outer drug sensitive test individualized treatment has very big effect;
2) method for calculating circulating tumor cell can be collected for the micro-fluidic circulating tumor cell detection chip
Obtained circulating tumor cell further screens the number for calculating circulating tumor cell, compensates for the blank of the technical field.
Detailed description of the invention
Fig. 1 is micro-fluidic circulating tumor cell detection chip primary structure schematic diagram;1 is micro through hole chip in figure.
Fig. 2 is the collected cell series figure of micro-fluidic circulating tumor cell detection chip of inverted fluorescence microscope shooting
Piece
Fig. 3 is the full figure of the completion of serial picture splicing.
Fig. 4 is the white light channel splicing full figure after removing noise and removal background.
The channel DAPI full figure after Fig. 5 pretreatment, removal noise and removal background.
Fig. 6 is the cell recognition figure after binaryzation, holes filling, watershed algorithm.
The comparison diagram in 4 channels Fig. 7.
Specific embodiment
Illustrated embodiment is in order to which preferably the present invention will be described, but is not that the contents of the present invention are limited only to institute
For embodiment.So those skilled in the art according to foregoing invention content to embodiment carry out it is nonessential improvement and
Adjustment, still falls within protection scope of the present invention.
Implementation condition:
Equipment: inverted fluorescence microscope, glass slide, coverslip, wet box, 37 DEG C of incubator
Reagent: DAPI, aqua sterilisa, PBS, CD45 (rabbit-anti), Anti-C-Kit (mouse anti-), secondary antibody fluorescent dye (mouse,
Rabbit)
Immunofluorescence dyeing: being added dropwise lowlenthal serum for the blood circulation tumour cell being collected into, and room temperature closes 30min, uses
Blotting paper sops up confining liquid, and the CD45 (rabbit-anti) diluted is added, and is put into wet box, 4 DEG C of overnight incubations;Add the fluorescence two diluted
20-37 DEG C of incubation 1h in anti-(rabbit) wet box;Anti-C-Kit (mouse is anti-) the incubation at room temperature 2h diluted is added, is added after being incubated for well
Enter fluorescence secondary antibody (mouse) incubation at room temperature 30min;DAPI is added and contaminates mounting fluid-tight piece of the core containing anti-fluorescence quenching, is then falling
Set fluorescence microscopy acquisition image under the microscope.
The circulating tumor cell that embodiment 1 acquires micro-fluidic circulating tumor cell detection chip calculates
The present embodiment calculates the lung cancer carcinoma in situ tumour cell being collected into, and samples sources are early stage of lung cancer patient
Tumour cell.
(1) by collected cell, immunofluorescence dyeing, the method such as institute before " implementation condition " of immunofluorescence dyeing are carried out
It states;
(2) the micro through hole chip 1 of immunofluorescence dyeing is placed under inverted fluorescence microscope and is observed, according to sweeping counterclockwise
All observation pictures under shooting are retouched, in the case where not entering a new line, guarantee that the left edge of shooting picture has part and a upper picture
Right hand edge have coincidence;It is shot to line feed, then camera lens is moved into row head, and guarantee the picture upper limb and lastrow of this shooting
Picture lower edge have lap;
(3) it is successively read the white light channel for all pictures that inverted fluorescence microscope observes, arbitrarily interception present image
A pocket RC1 on the left side or lower section in Image1 chooses next picture Imag2, the fritter in comparison match Image1
Position of the region RC1 in Image2 (shown in Fig. 2);Algorithm uses four kinds of matching ways: difference of two squares matching, standard deviation
Match, relevant matches and standard relevant matches, after successful match, according to matching position splicing serial picture at complete full figure
(shown in Fig. 3) and successively splice remaining 3 dyeing channels according to the position that white light channel is spliced;
(4) full figure is carried out removing dryness sonication, is removed using median filtering;For the area for the micro through hole that area is less than
Domain also can be used as noise remove, and treated, and full figure is spliced as shown in figure 4, full figure such as Fig. 5 institute is spliced in the channel DAPI in white light channel
Show;
(5) by full figure carry out through-hole background removal: intercept this shooting serial picture core on piece without be stained with cell or
The single micro through hole of impurity makees the image in region as matching object BgImg, matches to full figure, the region that will match to is set to
Plain background, the then region for not being filled into circulating tumor cell in full figure are all removed, the purpose for the arrangement is that in order to remove
The interference that micro through hole is identified as cell analysis;
(6) a white light channel full figure is replicated, the full figure that background and noise are removed in 4,5 steps is subjected to binaryzation, collection
The rich celliferous region of middle processing;
(7) fluorescence stain is chosen in 4 channel full figures as seed point, and hole is carried out to the binaryzation full figure in step 6
Circulating tumor cell number is sifted out in hole filling, preliminary knowledge;Microperforate regions are less than for area, can be ignored;It is special for area
Big region can tentatively be identified as being adhered cell;
(8) it is adhered cell for what is just known in step 7, is divided using watershed algorithm, will be filled out in step 7 by hole
The binary picture filled carries out range conversion, obtains the black-white-gray image for having grayscale.So, it is adhered around cell
The high place of gradient (grayscale) will not be overflow by water, to achieve the purpose that segmentation;It is adhered cell for be extremely hard to identification, it can be with
Manual division is taken, treated, and cell recognition figure is as shown in Figure 6;
(9) the cell position information being collected into according to above-mentioned steps, the other 3 fluorescence dye being successively read under corresponding position
There is information in color region, 3 fluorescent staining regions just and can confirm that one's respective area is circulating tumor cell, and the comparison diagram in 4 channels is such as
Shown in Fig. 7.
It will be labeled by the region that 1~9 step is confirmed as circulating tumor cell, and provide count results, followed in this example
Ring tumour cell number is 10.
The circulating tumor cell that embodiment 2 acquires micro-fluidic circulating tumor cell detection chip calculates
The present embodiment calculates the lung cancer carcinoma in situ tumour cell being collected into, and samples sources are early stage of lung cancer patient
Tumour cell.
(1) by collected cell, immunofluorescence dyeing, the method such as institute before " implementation condition " of immunofluorescence dyeing are carried out
It states;
(2) the micro through hole chip 1 of immunofluorescence dyeing is placed under inverted fluorescence microscope and is observed, according to sweeping counterclockwise
All observation pictures under shooting are retouched, in the case where not entering a new line, guarantee that the left edge of shooting picture has part and a upper picture
Right hand edge have coincidence;It is shot to line feed, then camera lens is moved into row head, and guarantee the picture upper limb and lastrow of this shooting
Picture lower edge have lap;
(3) it is successively read the white light channel for all pictures that inverted fluorescence microscope observes, arbitrarily interception present image
A pocket RC1 on the left side or lower section in Image1 chooses next picture Imag2, the fritter in comparison match Image1
Position of the region RC1 in Image2;Algorithm uses two kinds of matching ways: difference of two squares matching and standard deviation matching, matching
After success, according to matching position splicing serial picture at complete full figure, and successively according to the position of white light channel splicing
Splice remaining 3 dyeing channels;
(4) full figure is carried out removing dryness sonication, is removed using median filtering;For the area for the micro through hole that area is less than
Domain also can be used as noise remove;
(5) by full figure carry out through-hole background removal: intercept this shooting serial picture core on piece without be stained with cell or
The single micro through hole of impurity makees the image in region as matching object BgImg, matches to full figure, the region that will match to is set to
Plain background, the then region for not being filled into circulating tumor cell in full figure are all removed, the purpose for the arrangement is that in order to remove
The interference that micro through hole is identified as cell analysis;
(6) a white light channel full figure is replicated, the full figure that background and noise are removed in 4,5 steps is subjected to binaryzation, collection
The rich celliferous region of middle processing;
(7) fluorescence stain is chosen in 4 channel full figures as seed point, and hole is carried out to the binaryzation full figure in step 6
Circulating tumor cell number is sifted out in hole filling, preliminary knowledge;Microperforate regions are less than for area, can be ignored;It is special for area
Big region can tentatively be identified as being adhered cell;
(8) it is adhered cell for what is just known in step 7, is divided using watershed algorithm, will be filled out in step 7 by hole
The binary picture filled carries out range conversion, obtains the black-white-gray image for having grayscale.So, it is adhered around cell
The high place of gradient (grayscale) will not be overflow by water, to achieve the purpose that segmentation;It is adhered cell for be extremely hard to identification, it can be with
Take manual division;
(9) the cell position information being collected into according to above-mentioned steps, the other 3 fluorescence dye being successively read under corresponding position
There is information in color region, 3 fluorescent staining regions just and can confirm that one's respective area is circulating tumor cell.
It will be labeled by the region that 1~9 step is confirmed as circulating tumor cell, and provide count results, followed in this example
Ring tumour cell number is 6.
The circulating tumor cell that embodiment 3 acquires micro-fluidic circulating tumor cell detection chip calculates
The present embodiment calculates the lung cancer carcinoma in situ tumour cell being collected into, and samples sources are early stage of lung cancer patient
Tumour cell.
(1) by collected cell, immunofluorescence dyeing, the method such as institute before " implementation condition " of immunofluorescence dyeing are carried out
It states;
(2) the micro through hole chip 1 of immunofluorescence dyeing is placed under inverted fluorescence microscope and is observed, according to sweeping counterclockwise
All observation pictures under shooting are retouched, in the case where not entering a new line, guarantee that the left edge of shooting picture has part and a upper picture
Right hand edge have coincidence;It is shot to line feed, then camera lens is moved into row head, and guarantee the picture upper limb and lastrow of this shooting
Picture lower edge have lap;
(3) it is successively read the white light channel for all pictures that inverted fluorescence microscope observes, arbitrarily interception present image
A pocket RC1 on the left side or lower section in Image1 chooses next picture Imag2, the fritter in comparison match Image1
Position of the region RC1 in Image2;Algorithm use two kinds of matching ways: the difference of two squares matching and standard relevant matches, matching at
After function, successively spelled according to matching position splicing serial picture at complete full figure, and according to the position that white light channel is spliced
Connect remaining 3 dyeing channels;
(4) full figure is carried out removing dryness sonication, is removed using median filtering;For the area for the micro through hole that area is less than
Domain also can be used as noise remove;
(5) by full figure carry out through-hole background removal: intercept this shooting serial picture core on piece without be stained with cell or
The single micro through hole of impurity makees the image in region as matching object BgImg, matches to full figure, the region that will match to is set to
Plain background, the then region for not being filled into circulating tumor cell in full figure are all removed, the purpose for the arrangement is that in order to remove
The interference that micro through hole is identified as cell analysis;
(6) a white light channel full figure is replicated, the full figure that background and noise are removed in 4,5 steps is subjected to binaryzation, collection
The rich celliferous region of middle processing;
(7) fluorescence stain is chosen in 4 channel full figures as seed point, and hole is carried out to the binaryzation full figure in step 6
Circulating tumor cell number is sifted out in hole filling, preliminary knowledge;Microperforate regions are less than for area, can be ignored;It is special for area
Big region can tentatively be identified as being adhered cell;
(8) it is adhered cell for what is just known in step 7, is divided using watershed algorithm, will be filled out in step 7 by hole
The binary picture filled carries out range conversion, obtains the black-white-gray image for having grayscale.So, it is adhered around cell
The high place of gradient (grayscale) will not be overflow by water, to achieve the purpose that segmentation;It is adhered cell for be extremely hard to identification, it can be with
Take manual division;
(9) the cell position information being collected into according to above-mentioned steps, the other 3 fluorescence dye being successively read under corresponding position
There is information in color region, 3 fluorescent staining regions just and can confirm that one's respective area is circulating tumor cell.
It will be labeled by the region that 1~9 step is confirmed as circulating tumor cell, and provide count results, followed in this example
Ring tumour cell number is 7.
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 referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered at this
In the scope of the claims of invention.
Claims (10)
1. a kind of method for calculating circulating tumor cell, which is characterized in that exempted from by the enrichment of inverted fluorescence microscope scanning shoot
The all areas of the chip of the tumour cell of epidemic disease dyeing, splicing shoot the image series of fluorescence channel at complete image, then through going
Except background, removal noise, cavity filling, it is adhered cell recognition and carrys out analytical calculation circulating tumor cell number.
2. the method according to claim 1, wherein the circulating tumor cell is to use micro-fluidic circulating tumor
The circulating tumor cell that cell detection chip is collected.
3. leading to the method according to claim 1, wherein the observation channel is 4 including 1 white light
Road, the corresponding fluorescence channel of 3 fluorescent dyes.
4. the method according to claim 1, wherein the algorithm that the serial picture is spliced into complete full figure uses
One or more of difference of two squares matching, standard deviation matching, relevant matches and standard relevant matches.In the feelings of image clearly
Under condition, four kinds of matching ways can successful match, user can select as needed matching way to obtain the full figure of optimum efficiency.If
Picture quality is bad, four kinds of matching ways is successively used, until successful match.
5. the method according to claim 1, wherein removing noise using median filtering, then full figure is carried out
Remove background, binary conversion treatment.
6. the method according to claim 1, wherein carrying out the preliminary knowledge for being adhered cell using Hole filling algorithms
Not.
7. the method according to claim 1, wherein being adhered cell using watershed algorithm further to identify.
8. being adhered cell the method according to the description of claim 7 is characterized in that unrecognized for watershed algorithm, adopt
Use manual identification.
9. the described in any item methods for calculating circulating tumor cell of claim 1-8 circulation in calculating cancer early stage blood is swollen
It is applied in oncocyte.
10. difference of two squares matching and/or standard deviation matching and/or relevant matches and/or standard relevant matches and median filtering
The application in circulating tumor cell is being calculated with binaryzation and Hole filling algorithms and watershed algorithm, which is characterized in that described
The method for calculating circulating tumor cell includes the splicing to image series, is spliced into after full figure, the removal background of full graphics image,
Cell recognition is filled and is adhered in removal noise, cavity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910368036.8A CN109991205A (en) | 2019-05-05 | 2019-05-05 | A kind of counting algorithm of circulating tumor cell and application |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910368036.8A CN109991205A (en) | 2019-05-05 | 2019-05-05 | A kind of counting algorithm of circulating tumor cell and application |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109991205A true CN109991205A (en) | 2019-07-09 |
Family
ID=67135867
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910368036.8A Pending CN109991205A (en) | 2019-05-05 | 2019-05-05 | A kind of counting algorithm of circulating tumor cell and application |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109991205A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111429440A (en) * | 2020-03-31 | 2020-07-17 | 上海杏脉信息科技有限公司 | Microscopic pathological image cell sufficiency detection method, system, equipment, device and medium |
CN111739010A (en) * | 2020-06-23 | 2020-10-02 | 珠海圣美生物诊断技术有限公司 | Method and device for detecting abnormal circulating cells |
CN111862004A (en) * | 2020-06-30 | 2020-10-30 | 江西微润芯璟科技有限公司 | Tumor cell phenotype identification and counting method based on cell fluorescence image |
CN113029919A (en) * | 2021-03-13 | 2021-06-25 | 长春长光辰英生物科学仪器有限公司 | Cell enrichment and fluorescence counting detection device and detection and counting method |
CN113256717A (en) * | 2021-05-08 | 2021-08-13 | 华南师范大学 | Cell smear auxiliary analysis method and system |
CN113902817A (en) * | 2021-11-23 | 2022-01-07 | 杭州智微信息科技有限公司 | Cell picture splicing method based on gray value |
CN114152557A (en) * | 2021-11-16 | 2022-03-08 | 深圳元视医学科技有限公司 | Image analysis based blood cell counting method and system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102732415A (en) * | 2012-04-24 | 2012-10-17 | 武汉介观生物科技有限责任公司 | High-efficiency rare-cell-capturing integrated chip, manufacturing method thereof, and application thereof |
CN104280329A (en) * | 2014-09-01 | 2015-01-14 | 上海柏慧康生物科技有限公司 | Micro-fluidic multicolor fluorescence cell counter |
CN105115878A (en) * | 2015-09-11 | 2015-12-02 | 上海交通大学 | Circulating tumor cell detection kit, preparing method thereof and application thereof |
CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
CN106596941A (en) * | 2016-12-21 | 2017-04-26 | 上海市质子重离子医院有限公司 | Detection method for detecting prostate cancer circulating tumor cells |
CN109187978A (en) * | 2018-08-10 | 2019-01-11 | 北京莱尔生物医药科技有限公司 | It is a kind of detect circulating tumor cell HER2, ER, PR immunofluorescent reagent box and its application |
-
2019
- 2019-05-05 CN CN201910368036.8A patent/CN109991205A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102732415A (en) * | 2012-04-24 | 2012-10-17 | 武汉介观生物科技有限责任公司 | High-efficiency rare-cell-capturing integrated chip, manufacturing method thereof, and application thereof |
CN104280329A (en) * | 2014-09-01 | 2015-01-14 | 上海柏慧康生物科技有限公司 | Micro-fluidic multicolor fluorescence cell counter |
CN105115878A (en) * | 2015-09-11 | 2015-12-02 | 上海交通大学 | Circulating tumor cell detection kit, preparing method thereof and application thereof |
CN106056118A (en) * | 2016-06-12 | 2016-10-26 | 合肥工业大学 | Recognition and counting method for cells |
CN106596941A (en) * | 2016-12-21 | 2017-04-26 | 上海市质子重离子医院有限公司 | Detection method for detecting prostate cancer circulating tumor cells |
CN109187978A (en) * | 2018-08-10 | 2019-01-11 | 北京莱尔生物医药科技有限公司 | It is a kind of detect circulating tumor cell HER2, ER, PR immunofluorescent reagent box and its application |
Non-Patent Citations (5)
Title |
---|
杨刚: "全景图像拼接算法的设计与实现", 《重庆工学院学报(自然可续版)》 * |
罗小辉: "循环肿瘤细胞快速自动识别研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
钱伶琳 等: "细胞捕获的微流控芯片及自动化细胞计数方法", 《微纳电子技术》 * |
陈卫兵: "几种图像相似性度量的匹配性能比较", 《计算机应用》 * |
齐美星 等: "基于金字塔图像结构与Hu高阶矩的螺丝目标匹配算法", 《组合机床与自动化加工技术》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111429440A (en) * | 2020-03-31 | 2020-07-17 | 上海杏脉信息科技有限公司 | Microscopic pathological image cell sufficiency detection method, system, equipment, device and medium |
CN111429440B (en) * | 2020-03-31 | 2023-04-28 | 上海杏脉信息科技有限公司 | Method, system, equipment, device and medium for detecting sufficiency of microscopic pathology image cells |
CN111739010B (en) * | 2020-06-23 | 2022-06-24 | 珠海圣美生物诊断技术有限公司 | Method and device for detecting abnormal circulating cells |
CN111739010A (en) * | 2020-06-23 | 2020-10-02 | 珠海圣美生物诊断技术有限公司 | Method and device for detecting abnormal circulating cells |
US11880974B2 (en) | 2020-06-23 | 2024-01-23 | Zhuhai Sanmed Biotech Ltd. | Method and device for detecting circulating abnormal cells |
CN111862004A (en) * | 2020-06-30 | 2020-10-30 | 江西微润芯璟科技有限公司 | Tumor cell phenotype identification and counting method based on cell fluorescence image |
CN111862004B (en) * | 2020-06-30 | 2023-08-29 | 江西中医药大学 | Tumor cell phenotype identification and counting method based on cell fluorescence image |
CN113029919A (en) * | 2021-03-13 | 2021-06-25 | 长春长光辰英生物科学仪器有限公司 | Cell enrichment and fluorescence counting detection device and detection and counting method |
CN113029919B (en) * | 2021-03-13 | 2024-04-02 | 长春长光辰英生物科学仪器有限公司 | Cell enrichment and fluorescence counting detection device and detection and counting method |
CN113256717B (en) * | 2021-05-08 | 2022-01-21 | 华南师范大学 | Cell smear auxiliary analysis method and system |
CN113256717A (en) * | 2021-05-08 | 2021-08-13 | 华南师范大学 | Cell smear auxiliary analysis method and system |
CN114152557A (en) * | 2021-11-16 | 2022-03-08 | 深圳元视医学科技有限公司 | Image analysis based blood cell counting method and system |
CN114152557B (en) * | 2021-11-16 | 2024-04-30 | 深圳元视医学科技有限公司 | Image analysis-based blood cell counting method and system |
CN113902817A (en) * | 2021-11-23 | 2022-01-07 | 杭州智微信息科技有限公司 | Cell picture splicing method based on gray value |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109991205A (en) | A kind of counting algorithm of circulating tumor cell and application | |
US10657643B2 (en) | Medical image analysis for identifying biomarker-positive tumor cells | |
CA2660113C (en) | System and methods for scoring images of a tissue micro array | |
US7282180B2 (en) | Devices and methods to image objects | |
JP2021506022A (en) | Deep learning systems and methods for solidarity cell and region classification in bioimaging | |
Wang et al. | Label-free detection of rare circulating tumor cells by image analysis and machine learning | |
JP2023100730A (en) | Systems for automated in situ hybridization analysis | |
US20150141278A1 (en) | Multiplexed assay method for lung cancer classification | |
JPH01165958A (en) | Method and apparatus for analyzing ploidy of immune | |
WO2003105675A2 (en) | Computerized image capture of structures of interest within a tissue sample | |
JP2000508095A (en) | Boundary mapping system and method | |
Ciurte et al. | Automatic detection of circulating tumor cells in darkfield microscopic images of unstained blood using boosting techniques | |
Nurzynska et al. | CAS: Cell annotation software–research on neuronal tissue has never been so transparent | |
JP2018501581A (en) | Blood vessel analysis in multiplexed images | |
Shakhawat et al. | Automatic grading of invasive breast cancer patients for the decision of therapeutic plan | |
Komura et al. | Restaining-based annotation for cancer histology segmentation to overcome annotation-related limitations among pathologists | |
Neuman et al. | Segmentation of stained lymphoma tissue section images | |
CN114387596A (en) | Automatic interpretation system for cytopathology smear | |
Brázdil et al. | Automated annotations of epithelial cells and stroma in hematoxylin–eosin‐stained whole‐slide images using cytokeratin re‐staining | |
Migliozzi et al. | Combining fluorescence-based image segmentation and automated microfluidics for ultrafast cell-by-cell assessment of biomarkers for HER2-type breast carcinoma | |
US7257243B2 (en) | Method for analyzing a biological sample | |
Hoon et al. | Using fluorescent markers to estimate synaptic connectivity in situ | |
Feng et al. | An advanced automated image analysis model for scoring of ER, PR, HER-2 and Ki-67 in breast carcinoma | |
Souchier et al. | Methods for cell proliferation analysis by fluorescent image cytometry | |
WO2007081969A2 (en) | Domain segmentation and analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190709 |