CN109856015A - A kind of immediate processing method that cancer cell diagnoses automatically and its system - Google Patents
A kind of immediate processing method that cancer cell diagnoses automatically and its system Download PDFInfo
- Publication number
- CN109856015A CN109856015A CN201811418072.2A CN201811418072A CN109856015A CN 109856015 A CN109856015 A CN 109856015A CN 201811418072 A CN201811418072 A CN 201811418072A CN 109856015 A CN109856015 A CN 109856015A
- Authority
- CN
- China
- Prior art keywords
- clarity
- processing method
- cancer cell
- module
- immediate processing
- 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.)
- Granted
Links
- 206010028980 Neoplasm Diseases 0.000 title claims abstract description 27
- 201000011510 cancer Diseases 0.000 title claims abstract description 27
- 238000003672 processing method Methods 0.000 title claims abstract description 24
- 238000003745 diagnosis Methods 0.000 claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 230000000007 visual effect Effects 0.000 claims description 18
- 238000000605 extraction Methods 0.000 claims description 9
- 238000003709 image segmentation Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000013475 authorization Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 claims description 3
- 230000004886 head movement Effects 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims 1
- 201000010099 disease Diseases 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 2
- 210000004027 cell Anatomy 0.000 description 38
- 239000000523 sample Substances 0.000 description 22
- 230000000694 effects Effects 0.000 description 4
- 239000007788 liquid Substances 0.000 description 4
- 238000005119 centrifugation Methods 0.000 description 3
- 206010062717 Increased upper airway secretion Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000005357 flat glass Substances 0.000 description 2
- 208000026435 phlegm Diseases 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000002151 Pleural effusion Diseases 0.000 description 1
- 208000020584 Polyploidy Diseases 0.000 description 1
- 206010036790 Productive cough Diseases 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000004323 axial length Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012472 biological sample Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000003888 boundary cell Anatomy 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 230000009514 concussion Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000510 mucolytic effect Effects 0.000 description 1
- 238000010827 pathological analysis Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 208000024794 sputum Diseases 0.000 description 1
- 210000003802 sputum Anatomy 0.000 description 1
- 239000006228 supernatant Substances 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 210000002700 urine Anatomy 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
本发明提供一种癌细胞自动诊断的快速处理方法及其系统，自动化程度高，从细胞扫描到诊断确诊最终生成诊断报告，全部自动化完成；在智能诊断模块中生成与患者历史病症信息对比的大量图表信息，通过人工神经网络替代医师进行准确确诊；通过多个位置对比判定清晰度来选择拍照，速度可以达到五分钟800张图片；采用直接快速的USB加密计数方式，相比传统的IC卡加密方式，只需要远程授权而不是寄回方式，所有操作都可以通过网络完成，节约了时间，提升了效率。
The invention provides a fast processing method and system for automatic diagnosis of cancer cells, which has a high degree of automation, and generates a diagnosis report from cell scanning to diagnosis and diagnosis, and all of them are automatically completed; a large number of data are generated in an intelligent diagnosis module that are compared with the patient's historical disease information. The chart information can be accurately diagnosed by the artificial neural network instead of the doctor; the picture can be selected by comparing and determining the clarity of multiple positions, and the speed can reach 800 pictures in five minutes; the direct and fast USB encryption counting method is adopted, which is compared with the traditional IC card encryption. All operations can be completed through the network, saving time and improving efficiency.
Description
Technical field
The invention belongs to computer vision field more particularly to a kind of immediate processing method that cancer cell diagnoses automatically and its
System.
Background technique
At present when carrying out micro- scarnning mirror, scanning acquisition sample image, which may need to scan thousands of a visuals field, can just be obtained
Obtain significant result.But there are focusing accuracy inaccuracy, system are unstable for various comprehensive solutions currently on the market
And scanning speed is not able to satisfy the problem of large hospital demand.Meanwhile subsequent is also very slow, effect during automatic diagnosis
Rate is low.
In order to solve the problems, such as that whole efficiency is low, we herein basis on, using improve platform movement speed,
The quick focusing of camera lens and the quick processing image many aspects lifting system performance of algorithm, by system to each width visual field
Each can carry out image segmentation, feature extraction and cell classification with region, confirm diagnostic result finally by neural network,
Realize the acceleration to whole flow process is made a definite diagnosis from scanning to diagnosing.
Summary of the invention
In view of above-mentioned deficiencies of the prior art place, the purpose of the present invention is to provide a kind of cancer cell diagnose automatically it is fast
Fast processing method and its system, it is intended to it is low to solve the problems, such as that cellscan to cyto-diagnosis makes a definite diagnosis a whole set of flow path efficiency.
In order to achieve the above object, this invention takes following technical schemes:
A kind of immediate processing method that cancer cell diagnoses automatically, includes the following steps:
S1, the thickness for obtaining precise measurement full wafer sample, determine the variation range of the thickness；
S2, the adjusting step-length for determining each step of microscope；
S3, definition judgment is carried out to scanning area；
S4, it takes pictures to the highest position of clarity；
S5, pass through clarity decision boundaries；
The image data that S6, reading are taken pictures；
Image data is stored in corresponding archives if there are historical records in database by S7, reading patient history information
Otherwise library creates the file store of patient；
S8, image segmentation, feature extraction and screening are carried out to each of visual field region, obtains diagnostic result；
S9, confirmation diagnostic result
S10, output save diagnostic result and printed report list.
Further, the region of the sample is circle, and the visual field lap of scanning is equal to 13 microns.
Further, the definition judgment is that micro- lens head moves up 3 steps on Z axis, moves down 3 steps to focus,
Clarity comparison is carried out to 7 positions including home position.
Further, the clarity comparison obtains the highest position of clarity, and carries out to the highest position of clarity
It takes pictures.
Further, it is described by clarity decision boundaries be by testing setup threshold value, when be lower than the threshold value when determine
Without effective cell image in the visual field.
Further, scanning process is first to carry out upper semi-circle sector scanning, and after upper semi-circle sector scanning, camera lens is automatic
It is restored to the center location of original records, carries out symmetrical lower half circle sector scanning.
Further, the S7 should by whether there is in medical card sequence number or casebook sequence number detection database
The historical record of patient.
Further, the S9 is that its identification may make to output and input information through example repetition training neural network, from
And AD HOC is established, realize that computer neural network confirms diagnostic result.
Further, the immediate processing method use USB encrypted counter mode, it is only necessary to remote authorization rather than return
Mode realizes quick counter and authorization.
A kind of processing system for the immediate processing method that cancer cell diagnoses automatically, comprising:
Thickness measure module determines the variation range of the thickness for the thickness of precise measurement full wafer sample；
Top control module, for determining the adjusting step-length of each step of microscope and controlling micro- lens head movement；
Clarity detection module, for detecting and the clarity in contrast scans region；
Picture obtains module, for taking pictures to the highest position of clarity；
Boundary discrimination module, for differentiating the boundary of scanning；
Image data read module, for reading the image data taken pictures；
Patient history information's read module, will if there are historical records in database for reading patient history information
Image data is stored in corresponding file store, otherwise creates the file store of patient；
Intelligent diagnostics module is obtained for carrying out image segmentation, feature extraction and screening to each of visual field region
Diagnostic result；
Module is made a definite diagnosis, for confirming diagnostic result；
As a result output saves and print module, saves diagnostic result and printed report list for exporting.
Compared with prior art, beneficial effects of the present invention:
(1) high degree of automation is made a definite diagnosis from cellscan to diagnosis and ultimately generates diagnosis report, all automatically completes；
(2) a large amount of chart-informations with the comparison of patient history's illness information are generated in intelligent diagnostics module, by artificial
Neural network substitution doctor is accurately made a definite diagnosis；
(3) clarity is determined to select to take pictures by multiple position versus, speed can achieve five minutes 800 pictures；
(4) using directly quick USB encrypted counter mode, compared to traditional IC card cipher mode, it is only necessary to remotely award
It weighs rather than returns mode, all operations can be completed by network, save the time, improve efficiency.
Detailed description of the invention
Fig. 1 is a kind of flow diagram for the immediate processing method that cancer cell diagnoses automatically provided by the invention.
Fig. 2 is that a kind of scan vision of immediate processing method that cancer cell diagnoses automatically provided by the invention is overlapped signal
Figure.
Fig. 3 is a kind of processing system modules block diagram for the immediate processing method that cancer cell diagnoses automatically provided by the invention.
Specific embodiment
To make the purpose of the present invention, technical solution and effect clearer, clear and definite, right as follows in conjunction with drawings and embodiments
The present invention is further described.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not used to
Limit the present invention.
As shown in Figure 1-3, the immediate processing method that a kind of cancer cell provided by the invention diagnoses automatically, this method includes such as
Lower step:
S1, the thickness for obtaining precise measurement full wafer sample, determine the variation range of the thickness；
Specifically, taking pictures according to certain arrangement regulation to different positions, the z-axis position of initial position is defined
It sets, then as reference point in focal length judgement later.It is clear to naked eyes that focal length manually adjusted to different photos, then
The focal length variations in z-axis are observed, record its variation range, the focus adjustment the big, illustrates that thickness change is big herein, so that it may right
The thickness of sample is judged.
S2, the adjusting step-length for determining each step of microscope；
The step-length that focus adjustment is determined by the variation range of plate coating thickness realizes that multiple positions are caught by focusing
It catches, and all visuals field is covered.
S3, definition judgment is carried out to scanning area；
Specifically, carrying out definition judgment automatically, image transforms to HSV and Lab by algorithm process from rgb space respectively
Then color model calculates separately gradient both horizontally and vertically using Sobel operator using Tenengrad gradient method,
Same Scene descending stair angle value is higher, and image is more clear, and the index of measurement is the average ash by Sobel operator treated image
Angle value, value is bigger, and representative image is more clear.
S4, it takes pictures to the highest position of clarity；
The high position of clarity is judged by S3, industrial camera carries out automatic camera to the highest position of clarity, and
Picture is sent to background process center processing and is saved.
S5, pass through clarity decision boundaries.
The image data that S6, reading are taken pictures；
Image data is stored in corresponding archives if there are historical records in database by S7, reading patient history information
Otherwise library creates the file store of patient；
S8, image segmentation, feature extraction and screening are carried out to each of visual field region, obtains diagnostic result；
First determine whether suspicious region is cell.If suspicious region is cell, feature extraction is carried out to cell, and protect
Deposit this feature data；If not cell, then do not analyze.After being extracted to all cell characteristics, with classifier to cell
Classify, filters out cancer cell therein.All cancer cells are exported and are saved, 1. as diagnostic result.In conjunction with history disease
The data such as cancer cell number, cell average area, cell average gray value are checked that data compare with history respectively by feelings,
Corresponding variation tendency chart is generated, 2. as diagnostic result.By the partial feature value during system diagnostics, generate corresponding
Chart, as auxiliary diagnosis result, 3. (such as cell area corresponds to the histogram of cell quantity, other charts can be required according to doctor
It generates).
It should be noted that image segmentation: being divided using Otsu algorithm and through row black and white inverse；Edge detection is carried out again,
Corresponding ROI region outer profile is found using Canny and findContours.Feature extraction: gray scale, circularity, area, week are extracted
Long, main shaft length, secondary axial length, compactness, eccentricity etc. feature.Classifier uses python decision tree, calculates separately out each
The impact factor of feature obtains the calculation formula of cancer cell.
S9, confirmation diagnostic result
1. 2. 3. diagnostic result is forwarded to doctor diagnosed, diagnostic result is made a definite diagnosis by doctor.Knot will largely be confirmed
Fruit is as data training artificial neural network.Its identification may make to output and input information through example repetition training neural network,
To establish AD HOC, realize that computer pathological diagnosis, that is, neural network is made a definite diagnosis.
S10, output save diagnostic result and printed report list.
It is noted that required focus adjustment parameter is compiled pst file in advance, from the background by reading pst text
Part carrys out focusing and is adjusted, when needing replacing other parameters adjusting, it is only necessary to edit pst file and re-enter wanted parameter i.e.
It can.
Scanning principle is in scanning process, and objective table is automatically stepped in two dimensions of X, Y, and then industrial camera is by acquisition
Image is sent to automatic focusing module, obtains focal plane by the feeding of Z axis (object lens) vertical direction.In order to keep system hardware flat
Platform meets actual need of work, in the design of the platform, should follow all standing principle of cell, as avoid missing inspection cancer thin
Born of the same parents should follow cell all covering principles when controlling objective table X, Y-axis feeding.
In the present embodiment, the region of the sample is circle, as shown in Figure 2 about the visual field of scanning, the visual field 1 and the visual field
2 laps are equal to 13 microns.Because being directed to cervical exfoliated cell smear, when lap is less than 13 microns, image border
Nuclei picture be possible to be destroyed, normal process object cannot be included in, cause incomplete cell bank；And work as overlapping portion
Divide more than 13 microns, then may cause and duplicate hypercellularity in cell bank, increase calculation amount simultaneously, influences conclusive judgement essence
Degree.It needs on the basis of biomicroscope, by adding stepper motor and corresponding transmission mechanism to objective table, realizes simultaneously
The automatic scanning of smear.
In the present embodiment, the definition judgment is that micro- lens head moves up 3 steps on Z axis, moves down 3 steps to adjust coke
Away to 7 positions progress clarity comparison including home position.
In the present embodiment, the clarity comparison obtains the highest position of clarity, and to the highest position of clarity
It takes pictures.
In the present embodiment, it is described by clarity decision boundaries be by testing setup threshold value, when be lower than the threshold value when
Determine then to be determined as boundary without effective cell image in the visual field.
In the present embodiment, the scan method is first to carry out upper semi-circle sector scanning, after upper semi-circle sector scanning,
Camera lens automatically restores to the center location of original records, carries out symmetrical lower half circle sector scanning, symmetrical expression scanning is so that scanning
Path is more stable, scans more acurrate.
In the present embodiment, whether the S7 in medical card sequence number or casebook sequence number detection database by depositing
In the historical record of the patient, if it does, this final result checked is stored in corresponding file store；Otherwise patient is created
File store, and save idagnostic logout.
In the present embodiment, the S9 is that its identification may make to output and input letter through example repetition training neural network
Breath realizes that computer neural network confirms diagnostic result to establish AD HOC.
In the present embodiment, the immediate processing method use USB encrypted counter mode, it is only necessary to remote authorization rather than
Mode is returned, quick counter and authorization are realized.
It should be noted that the present invention uses parallel rejection tablet technology quick Fabrication smear, system is greatly improved from efficiency
Piece speed is quickly handled cell sample provided with parallel multichannel centrifuge, for gynaecology's sample, Pleural effusions sample and
Phlegm, urine humoral specimen, the following steps are included:
A, gynaecology's sample is put concussion 2~10 minutes on the oscillator together with bottle is saved by Pretreated, is drawn and is saved bottle
In indsole confluent monolayer cells make sample；It takes 40~50 milliliters to be centrifuged 10 minutes after mixing with 2000 revs/min, takes centrifugation bottom of the tube 1/3
Liquid is added preservation bottle and makees sample；Or sputum specimen add 5~10 milliliters of mucolytic liquid after put on the oscillator shake 2~10 points
Clock takes the liquid phlegm after decomposing that preservation bottle is added and makees sample；
B, it takes common centrifuge tube that 5 milliliters of adherency separating liquids are added, is slowly added to along centrifugation tube wall through step a Pretreated
Above-mentioned equivalent sample afterwards；
C, the sample mixture of step b is placed in a centrifuge and is centrifuged 5~10 minutes with 1200~2000 revs/min, according to
Centrifuged deposit object amount abandons supernatant in centrifuge tube, then mixes stand-by；
D, numbered sheet glass will be write to be put into the elongated slot of film-making corollary equipment natural settling device fixing seat, sheet glass
It is tightly attached to the elongated slot bottom edge of fixing seat, is centrifugated after fixed and is regarded as sample, constant temperature drying platform is dried again later, and is suppressed
The sample needed.Speed is faster, the bigger centrifugation systems of intensity realize cell on the basis of quickly more has
The separation of effect, to obtain the promotion of performance in subsequent display effect and two aspect of speed.
In the following way, the region of cell sample is circle to auto-focusing, passes through the judgement realization pair to sample boundary
Cell does not weigh leak-free scanning.The material and glass thickness of every one kind biological sample are different, first acquisition precise measurement full wafer sample
This thickness, determines the rough variation range of thickness.Then it calculates and determines each microscopical adjusting step-length of step.It is swept each time
Before retouching, it is clear that manually field of microscope is adjusted in center location, and then microscope automatically begins to scan.To often sweeping
Retouch region and all carry out definition judgment, camera lens setting moves up 3 steps, move down 3 steps and to 7 positions including home position into
Row judgement, compares and is called industrial camera to the maximum position of clarity and takes pictures.Pst has been made into for the adjusting of focal length
File carries out convenient modification editor, so as to realize target that speed and clarity are taken into account.It is same for the judgement on boundary
Carry out decision boundaries using clarity, by testing setup threshold value, determines in the visual field when being lower than the threshold value without effective cell
Image, so as to realize the judgement on boundary.The mode that scanning is scanned respectively using upper lower half circle area, upper semi-circle region terminates to sweep
After retouching, camera lens is automatically moved back to the center location of original records, carries out symmetrical lower half circle scan procedure.In scanning process
In, counting is synchronized for the polyploids such as diploid and cell quantity, is realized by later logical algorithm to overall flow
Control, reach and just stop scanning after object count.The scanning mode may be implemented to five minutes 800 pictures, high-efficient.
It should be noted that the movement of micro- lens head is to control by backstage master control stepper motor, stepper motor
It is mobile that camera lens is controlled again.
On the other hand the present invention also provides a kind of processing system of immediate processing method that cancer cell diagnoses automatically, the systems
Include:
Thickness measure module determines the variation range of the thickness for the thickness of precise measurement full wafer sample；
Top control module, for determining the adjusting step-length of each step of microscope and controlling micro- lens head movement；
Clarity detection module, for detecting and the clarity in contrast scans region；
Picture obtains module, for taking pictures to the highest position of clarity；
Boundary discrimination module, for differentiating the boundary of scanning；
Image data read module, for reading the image data taken pictures；
Patient history information's read module, will if there are historical records in database for reading patient history information
Image data is stored in corresponding file store, otherwise creates the file store of patient；
Intelligent diagnostics module is obtained for carrying out image segmentation, feature extraction and screening to each of visual field region
Diagnostic result；
Module is made a definite diagnosis, for confirming diagnostic result；
As a result output saves and print module, saves diagnostic result and printed report list for exporting；The top control module
It controls the module of all whole systems and is electrically connected with the module of the whole system.
It, can according to the technique and scheme of the present invention and its hair it is understood that for those of ordinary skills
Bright design is subject to equivalent substitution or change, and all these changes or replacement all should belong to the guarantor of appended claims of the invention
Protect range.
Claims (10)
1. a kind of immediate processing method that cancer cell diagnoses automatically, which comprises the steps of:
S1, the thickness for obtaining precise measurement full wafer sample, determine the variation range of the thickness；
S2, the adjusting step-length for determining each step of microscope；
S3, definition judgment is carried out to scanning area；
S4, it takes pictures to the highest position of clarity；
S5, pass through clarity decision boundaries；
The image data that S6, reading are taken pictures；
Image data is stored in corresponding file store if there are historical records in database by S7, reading patient history information,
Otherwise the file store of patient is created；
S8, image segmentation, feature extraction and screening are carried out to each of visual field region, obtains diagnostic result；
S9, confirmation diagnostic result；
S10, output save diagnostic result and printed report list.
2. a kind of immediate processing method that cancer cell diagnoses automatically as described in claim 1, which is characterized in that the sample
Region is circle, and the visual field lap of scanning is equal to 13 microns.
3. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 2, which is characterized in that the clarity
Judgement is that micro- lens head moves up 3 steps on Z axis, moves down 3 steps to focus, to 7 positions including home position
Carry out clarity comparison.
4. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 3, which is characterized in that the clarity
Comparison obtains the highest position of clarity, and takes pictures to the highest position of clarity.
5. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 4, which is characterized in that described by clear
Clear degree decision boundaries are determined in the visual field when being lower than the threshold value without effective cell image by testing setup threshold value.
6. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 5, which is characterized in that scanning process is
Upper semi-circle sector scanning is first carried out, after upper semi-circle sector scanning, camera lens automatically restores to the center location of original records, into
The symmetrical lower half circle sector scanning of row.
7. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 6, which is characterized in that the S7 passes through
It whether there is the historical record of the patient in medical card sequence number or casebook sequence number detection database.
8. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 7, which is characterized in that the S9 be through
Example repetition training neural network may make its identification to output and input information, to establish AD HOC, realize computer mind
Through network validation diagnostic result.
9. a kind of immediate processing method that cancer cell diagnoses automatically as claimed in claim 8, which is characterized in that the quick place
Reason method use USB encrypted counter mode, it is only necessary to remote authorization rather than return mode, realize quick counter and authorized party
Formula.
10. a kind of using a kind of described in any item processing for the immediate processing method that cancer cell diagnoses automatically of claim 1-9
System characterized by comprising
Thickness measure module determines the variation range of the thickness for the thickness of precise measurement full wafer sample；
Top control module, for determining the adjusting step-length of each step of microscope and controlling micro- lens head movement；
Clarity detection module, for detecting and the clarity in contrast scans region；
Picture obtains module, for taking pictures to the highest position of clarity；
Boundary discrimination module, for differentiating the boundary of scanning；
Image data read module, for reading the image data taken pictures；
Patient history information's read module, for reading patient history information, if there are historical records in database, by picture
Data are stored in corresponding file store, otherwise create the file store of patient；
Intelligent diagnostics module obtains diagnosis for carrying out image segmentation, feature extraction and screening to each of visual field region
As a result；
Module is made a definite diagnosis, for confirming diagnostic result；
As a result output saves and print module, saves diagnostic result and printed report list for exporting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811418072.2A CN109856015B (en) | 2018-11-26 | 2018-11-26 | A rapid processing method and system for automatic diagnosis of cancer cells |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811418072.2A CN109856015B (en) | 2018-11-26 | 2018-11-26 | A rapid processing method and system for automatic diagnosis of cancer cells |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109856015A true CN109856015A (en) | 2019-06-07 |
| CN109856015B CN109856015B (en) | 2021-08-17 |
Family
ID=66890307
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811418072.2A Expired - Fee Related CN109856015B (en) | 2018-11-26 | 2018-11-26 | A rapid processing method and system for automatic diagnosis of cancer cells |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109856015B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814537A (en) * | 2020-05-25 | 2020-10-23 | 苏州米特希赛尔人工智能有限公司 | Cervical cancer TCT slide microscope automatic scanning and AI diagnosis system and method |
| CN112992336A (en) * | 2021-02-05 | 2021-06-18 | 山西医科大学 | Intelligent pathological diagnosis system |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1462884A (en) * | 2003-06-24 | 2003-12-24 | 南京大学 | Method of recognizing image of lung cancer cells with high accuracy and low rate of false negative |
| JP2007079278A (en) * | 2005-09-15 | 2007-03-29 | Univ Of Tokyo | Material state measuring device |
| JP2008116526A (en) * | 2006-11-01 | 2008-05-22 | Matsushita Electric Ind Co Ltd | Microscope image processing apparatus and processing method |
| CN101615289A (en) * | 2009-08-05 | 2009-12-30 | 北京优纳科技有限公司 | The three-dimensional acquisition of biopsy tissues and fusion method of multilayer images |
| CN101788709A (en) * | 2010-03-10 | 2010-07-28 | 广西大学 | Digital confocal microscope optical section collecting device |
| CN102175625A (en) * | 2010-11-29 | 2011-09-07 | 樊潮 | Method for identifying cancer cells |
| CN103123321A (en) * | 2011-11-18 | 2013-05-29 | 索尼公司 | Image obtaining apparatus, image obtaining method, and image obtaining program |
| CN106104355A (en) * | 2014-12-22 | 2016-11-09 | 皇家飞利浦有限公司 | Method for simultaneously capturing image data of a sample at multiple depths |
| CN107077732A (en) * | 2014-08-27 | 2017-08-18 | 思迪赛特诊断有限公司 | Systems and methods for computing focus changes for a digital microscope |
| CN107257934A (en) * | 2015-03-10 | 2017-10-17 | 高通股份有限公司 | The hunting zone extension focused on automatically for depth assist type |
| CN107409205A (en) * | 2015-03-16 | 2017-11-28 | 深圳市大疆创新科技有限公司 | Device and method for focus adjustment and depth map determination |
| CN107561075A (en) * | 2017-07-26 | 2018-01-09 | 山东颐泽天泰医疗科技有限公司 | The fast scan imaging method of cell DNA ploidy analysis three-dimensional movement platform |
-
2018
- 2018-11-26 CN CN201811418072.2A patent/CN109856015B/en not_active Expired - Fee Related
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1462884A (en) * | 2003-06-24 | 2003-12-24 | 南京大学 | Method of recognizing image of lung cancer cells with high accuracy and low rate of false negative |
| JP2007079278A (en) * | 2005-09-15 | 2007-03-29 | Univ Of Tokyo | Material state measuring device |
| JP2008116526A (en) * | 2006-11-01 | 2008-05-22 | Matsushita Electric Ind Co Ltd | Microscope image processing apparatus and processing method |
| CN101615289A (en) * | 2009-08-05 | 2009-12-30 | 北京优纳科技有限公司 | The three-dimensional acquisition of biopsy tissues and fusion method of multilayer images |
| CN101788709A (en) * | 2010-03-10 | 2010-07-28 | 广西大学 | Digital confocal microscope optical section collecting device |
| CN102175625A (en) * | 2010-11-29 | 2011-09-07 | 樊潮 | Method for identifying cancer cells |
| CN103123321A (en) * | 2011-11-18 | 2013-05-29 | 索尼公司 | Image obtaining apparatus, image obtaining method, and image obtaining program |
| CN107077732A (en) * | 2014-08-27 | 2017-08-18 | 思迪赛特诊断有限公司 | Systems and methods for computing focus changes for a digital microscope |
| CN106104355A (en) * | 2014-12-22 | 2016-11-09 | 皇家飞利浦有限公司 | Method for simultaneously capturing image data of a sample at multiple depths |
| CN107257934A (en) * | 2015-03-10 | 2017-10-17 | 高通股份有限公司 | The hunting zone extension focused on automatically for depth assist type |
| CN107409205A (en) * | 2015-03-16 | 2017-11-28 | 深圳市大疆创新科技有限公司 | Device and method for focus adjustment and depth map determination |
| CN107561075A (en) * | 2017-07-26 | 2018-01-09 | 山东颐泽天泰医疗科技有限公司 | The fast scan imaging method of cell DNA ploidy analysis three-dimensional movement platform |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111814537A (en) * | 2020-05-25 | 2020-10-23 | 苏州米特希赛尔人工智能有限公司 | Cervical cancer TCT slide microscope automatic scanning and AI diagnosis system and method |
| CN111814537B (en) * | 2020-05-25 | 2025-03-11 | 苏州米特希赛尔人工智能有限公司 | Cervical cancer TCT slide microscope automatic scanning and AI diagnosis system and method |
| CN112992336A (en) * | 2021-02-05 | 2021-06-18 | 山西医科大学 | Intelligent pathological diagnosis system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109856015B (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6479676B2 (en) | System and method for classification of particles in a fluid sample | |
| JP3822242B2 (en) | Method and apparatus for evaluating slide and sample preparation quality | |
| EP4229460A2 (en) | Systems and methods for autofocus and automated cell count using artificial intelligence | |
| CN112352149A (en) | System and method for automatically analyzing air samples | |
| CN101339185B (en) | Automatic microscopic imager for detecting cast-off cells and detection method | |
| US12223704B2 (en) | Label-free cell classification and screening system based on hybrid transfer learning | |
| US12198300B2 (en) | Computational refocusing-assisted deep learning | |
| CN110108711A (en) | Visual inspection system for defects of side wall of circular ring | |
| EP3431957A1 (en) | Sample imaging apparatus | |
| CN113667584A (en) | Colony Contrast Collection | |
| CN102304472A (en) | Device and method for detecting sputum smear tubercle bacillus quickly | |
| WO2013094365A1 (en) | Observation system, program, and method for controlling observation system | |
| CN106661764B (en) | Automated imaging and analysis of hemagglutination inhibition assay (HAI) | |
| Wu et al. | Classification between digs and dust particles on optical surfaces with acquisition and analysis of polarization characteristics | |
| CN109612992A (en) | A rapid scanning method and system for cervical exfoliated cell smear | |
| CN117269193B (en) | Intelligent detection method for apparent mass of synthetic leather | |
| CN107103604B (en) | A kind of particulate coloration auto-clustering analysis system | |
| CN109856015A (en) | A kind of immediate processing method that cancer cell diagnoses automatically and its system | |
| CN117576103A (en) | Urine sediment microscopy analysis system integrating electronically controlled microscope and deep learning algorithm | |
| Evangeline et al. | Computer aided system for human blood cell identification, classification and counting | |
| CN118883591B (en) | Plastic product microscopic defect detection equipment based on super-resolution imaging | |
| CN116112793A (en) | A camera focusing method and system | |
| BR112021011795A2 (en) | SYSTEM AND METHOD TO MONITOR BACTERIAL GROWTH OF BACTERIAL COLONIES AND PREDICT COLON BIOMASS | |
| CN112924452A (en) | Blood examination auxiliary system | |
| Allen et al. | Automatic recognition of light microscope pollen images |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210817 |