CN105259095A - Negative-exclusion-method intelligent screening system for cervical cancer cellpathology - Google Patents
Negative-exclusion-method intelligent screening system for cervical cancer cellpathology Download PDFInfo
- Publication number
- CN105259095A CN105259095A CN201510659903.5A CN201510659903A CN105259095A CN 105259095 A CN105259095 A CN 105259095A CN 201510659903 A CN201510659903 A CN 201510659903A CN 105259095 A CN105259095 A CN 105259095A
- Authority
- CN
- China
- Prior art keywords
- sample
- cell
- cervical cancer
- screening system
- checked
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000012216 screening Methods 0.000 title claims abstract description 22
- 206010008342 Cervix carcinoma Diseases 0.000 title claims abstract description 15
- 208000006105 Uterine Cervical Neoplasms Diseases 0.000 title claims abstract description 15
- 201000010881 cervical cancer Diseases 0.000 title claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 6
- 230000007170 pathology Effects 0.000 claims description 16
- 239000000758 substrate Substances 0.000 claims description 7
- 230000004968 inflammatory condition Effects 0.000 claims description 6
- 230000002547 anomalous effect Effects 0.000 claims description 5
- 230000002950 deficient Effects 0.000 claims description 5
- 238000003745 diagnosis Methods 0.000 claims description 5
- 210000004907 gland Anatomy 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 238000010186 staining Methods 0.000 claims description 4
- 206010061218 Inflammation Diseases 0.000 claims description 3
- 206010028980 Neoplasm Diseases 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000004054 inflammatory process Effects 0.000 claims description 3
- 244000005700 microbiome Species 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 208000019065 cervical carcinoma Diseases 0.000 description 6
- 208000003464 asthenopia Diseases 0.000 description 3
- 230000007812 deficiency Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a negative-exclusion-method intelligent screening system for cervical cancer cellpathology. A computer is used for controlling a microscope camera. An automatic microscope platform is used for bearing and controlling the microscope camera and automatically adjusting the focal length according to real-time requirements, and moves left and right to ensure that a sample to be examined can be clearly and completely collected. The microscope camera is used for collecting a picture with the focal length adjusted well. The microscope camera and the automatic microscope platform are assembled together and then connected to the computer. A slide to be examined is placed on the automatic microscope platform, the automatic microscope platform is controlled by the computer to collect a sample image, the collected image is transmitted to the computer for negative-exclusion-method detection, and a prompt is given according to a judgment result. The negative-exclusion-method intelligent screening system has the advantage of effectively reducing workloads of doctors and specialists.
Description
Technical field
The invention belongs to cell pathology technical field of machine vision, relate to cervical cancer cell pathology and arrange cloudy method intelligence screening system.
Background technology
What current cervical carcinoma screening system sentence read result prompting mainly adopted is the point of directly pointing out doubtful danger in sample, it is abnormal cell that each point needs doctor expert to go diagnosis to be confirmed whether, do although it is so and reduce certain workload to doctor, but doctor still needs each sample to go confirmation one time, and workload is still very large.The domestic cervical carcinoma image intelligent screening system also not having independent research at present.What the method that this patent proposes adopted is only diagnose ' negative ' specimens, reliability is high, feminine gender detects ratio 50% ~ 60%, doctor expert only need diagnose all the other samples of 40% ~ 50%, and do like this in sample that doctor only needs never to carry out diagnosing and go to search diagnosis positive sample, workload can reduce a lot, work efficiency can have greatly improved, solve the problem of basic Hospital Pathological Department doctor deficiency, can be used as the blind check system in examination, for the networking of pathology hospital provides basis.
The existing techniques in realizing scheme the most similar to the present invention is a kind of cervical carcinoma screening system of the U.S. at present, but its negative recall rate only has about 20%, and compared with the method proposed with this patent, accurate rate and efficiency have larger gap.
Existing cervical carcinoma screening system provides multiple suspicious points to each sample allows expert go interpretation, expert needs to carry out interpretation to each sample and goes to confirm whether sample is positive sample, be expert so not need to go carefully to receive rope to sample and search pathology point, but still need to check each sample, workload is still very large.The negative recall rate of another kind of system only has 20%, does not also effectively reduce the workload of expert.
Summary of the invention
The object of the present invention is to provide cervical cancer cell pathology to arrange cloudy method intelligence screening system, solve existing
The cervical carcinoma screening system problem that causes expert's workload excessive, also solve the problem that basic hospital expert is few.
The technical solution adopted in the present invention is that cervical cancer cell pathology arrange cloudy method intelligence screening system, is made up of computing machine, microscope camera, micrometron platform and sample to be checked.
Computing machine is used for controlling microscope camera, and micrometron platform is used for Bearer Control microscope camera, according to real-time requirement automatic focus adjustable, moves left and right and ensures that sample to be checked can the carrying out of complete display gather.
Microscope camera is used for gathering and mixes up burnt picture.
Together with microscope camera is assembled into micrometron platform, then receive on computing machine, slide to be checked is put on micrometron platform, micrometron platform collect specimen image is controlled by computing machine, arrange cloudy method check processing by the image transmitting collected to computing machine carries out, differentiation result is pointed out.
Further, the cloudy method of described row detects:
(1) image acquisition is carried out to slide to be checked.
(2) carry out greyscale transformation to the picture collected, Iamge Segmentation process obtains intensity, distribution mean square deviation, color distance, histogram, number of cells, the cell area data of image.
(3) by intensity, distribution mean square deviation, histogram, color distance, number of cells, cell area data setting condition, specimen quality is monitored, mainly to specimen staining depth degree, cell dispersal degree, cell quantity, inflammatory conditions is monitored, and carries out digitized description to mirror hypograph content, carries out filtering to defective sample.
(4) inflammation, substrate, microorganism, clot Samples detection and tumour quality are differentiated.
(5) unicellular search, the search of group's cell and the search of gland cell are carried out to qualified sample image.
(6) system carries out anomalous discrimination to the cell searched.
(7) system will be ' negative ' specimens less than examining paracytic specimens in diagnosis.
The invention has the beneficial effects as follows and effectively reduce doctor expert's workload, effectively solve the problem of basic hospital expert deficiency.
Accompanying drawing explanation
Fig. 1 is that cervical cancer cell pathology of the present invention arrange cloudy method intelligence screening system structural representation.
Fig. 2 is that the cloudy method of row of the present invention detects concrete grammar.
In figure, 1. computing machine, 2. microscope camera, 3. micrometron platform, 4. sample to be checked.
Embodiment
Below in conjunction with embodiment, the present invention is described in detail.
Cervical cancer cell pathology of the present invention arrange cloudy method intelligence screening system as shown in Figure 1, are made up of computing machine 1, microscope camera 2, micrometron platform 3 and sample to be checked 4.
Computing machine 1 is used for controlling microscope camera 2, and micrometron platform 3 is used for Bearer Control microscope camera 2, according to real-time requirement automatic focus adjustable, moves left and right and ensures that sample to be checked can the carrying out of complete display gather.
Microscope camera 2 is used for gathering and mixes up burnt picture.
Together with microscope camera 2 is assembled into micrometron platform 3, then receive on computing machine 1, slide 4 to be checked is put on micrometron platform 3, micrometron platform 3 collect specimen image is controlled by computing machine 1, to the image transmitting collected to computing machine 1 carry out arrange cloudy method check processing, differentiation result is pointed out.
As shown in Figure 2, row of the present invention cloudy method detection concrete grammar is as follows:
(1) image acquisition is carried out to slide to be checked.
(2) carry out greyscale transformation to the picture collected, Iamge Segmentation process obtains intensity, distribution mean square deviation, color distance, histogram, number of cells, the cell area data of image.
(3) by intensity, distribution mean square deviation, histogram, color distance, number of cells, cell area data setting condition, specimen quality is monitored, mainly to specimen staining depth degree, cell dispersal degree, cell quantity, inflammatory conditions is monitored, and carries out digitized description to mirror hypograph content, carries out filtering to defective sample.
(4) inflammation, substrate, microorganism, clot Samples detection and tumour quality are differentiated.
(5) unicellular search, the search of group's cell and the search of gland cell are carried out to qualified sample image.
(6) system carries out anomalous discrimination to the cell searched.
(7) system will be ' negative ' specimens less than examining paracytic specimens in diagnosis.
For the problem existing for current two class cervical carcinoma intelligence screening systems, this patent proposes the cloudy method detection system of row, and this system is made up of computing machine, micrometron and microscope camera.Slide to be detected is placed on the objective table of micrometron, microscope automatic focusing, clear rear camera of focusing carries out collect and transmit to image, computing machine processes the image received, first carry out prompting to underproof sample to refuse inspection and need film-making again, again qualified sample is processed targetedly, by sample inflammatory conditions, substrate, secondary substrate sample, clot sample and infected by microbes sample tip out and adopt special mode process, then system is carried out unicellular to qualified sample, the receipts rope of group's cell and gland cell, the cell searched is carried out anomalous discrimination, final system carries out feminine gender prompting to all not finding paracytic sample through all anomalous discriminations, this sample is diagnosed to be ' negative ' specimens, these samples expert does not need to check, all the other samples need expert to check to determine sample situation.
The cloudy method of row of the proposition of this patent method, the negative reliability of prompting is high, false negative rate reaches below per mille, the ratio of detecting reaches 50% ~ 60%, therefore expert only needs to go to confirm sample situation from all the other samples of 40% ~ 50%, greatly reduce the workload of expert, owing to checking sample for a long time, easily shine into visual fatigue to people to cause false positive sample being mistaken for the positive or positive sample being missed, the proposition of this patent method makes expert need the specimen amount checked to greatly reduce, thus make expert have the more sufficient time to go to check sample, reduce visual fatigue to increase work efficiency.
This patent proposes the cloudy method of row, by directly diagnosing ' negative ' specimens, this part is diagnosed as negative sample does not need expert to go interpretation, expert only needs to carry out interpretation to all the other samples and diagnoses, expert's workload is reduced greatly, simultaneously because the minimizing of workload makes the visual fatigue of expert reduce, more accurate to the sample diagnosed out.
The above is only to better embodiment of the present invention, not any pro forma restriction is done to the present invention, every any simple modification done above embodiment according to technical spirit of the present invention, equivalent variations and modification, all belong in the scope of technical solution of the present invention.
Claims (7)
1. cervical cancer cell pathology arrange cloudy method intelligence screening system, it is characterized in that: be made up of computing machine (1), microscope camera (2), micrometron platform (3) and sample to be checked (4);
Computing machine (1) is used for controlling microscope camera (2), and micrometron platform (3) is used for Bearer Control microscope camera (2), according to real-time requirement automatic focus adjustable, moves left and right and ensures that sample to be checked can the carrying out of complete display gather;
Microscope camera (2) is used for gathering and mixes up burnt picture;
Together with microscope camera (2) is assembled into micrometron platform (3), then receive on computing machine (1), slide to be checked (4) is put on micrometron platform (3), micrometron platform (3) collect specimen image is controlled by computing machine (1), undertaken arranging cloudy method check processing by the image transmitting collected to computing machine (1), differentiation result is pointed out.
2. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 1, it is characterized in that: the cloudy method of described row detects following steps:
(1) image acquisition is carried out to slide to be checked;
(2) carry out greyscale transformation to the picture collected, Iamge Segmentation process obtains intensity, distribution mean square deviation, color distance, histogram, number of cells, the cell area data of image;
(3) by intensity, distribution mean square deviation, histogram, color distance, number of cells, cell area data setting condition, specimen quality is monitored, mainly to specimen staining depth degree, cell dispersal degree, cell quantity, inflammatory conditions is monitored, and carries out digitized description to mirror hypograph content, carries out filtering to defective sample;
(4) inflammation, substrate, microorganism, clot Samples detection and tumour quality are differentiated;
(5) unicellular search, the search of group's cell and the search of gland cell are carried out to qualified sample image;
(6) system carries out anomalous discrimination to the cell searched;
(7) system will be ' negative ' specimens less than examining paracytic specimens in diagnosis.
3. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 2, it is characterized in that: the cloudy method testing goal of described row is that system tips out being detected as negative sample automatically, the sample of not pointing out is doubtful positive sample, diagnoses further for expert.
4. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 2, it is characterized in that: system is assessed specimen quality to be checked automatically, defective sample is pointed out.
5. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 2, it is characterized in that: system carries out inflammatory conditions in prompting sample to sample situation to be checked automatically, substrate, attached substrate situation, infected by microbes situation, clot situation.
6. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 2, it is characterized in that: system is all searched for likely there is paracytic cell type in sample to be checked, comprising unicellular search, the search of group's cell, gland cell search.
7. arrange cloudy method intelligence screening system according to cervical cancer cell pathology described in claim 2, it is characterized in that: system is monitored specimen quality, comprise specimen staining depth degree, cell dispersal degree, cell quantity, inflammatory conditions is monitored, and carries out digitized description to mirror hypograph content, carries out filtering to defective sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510659903.5A CN105259095A (en) | 2015-10-14 | 2015-10-14 | Negative-exclusion-method intelligent screening system for cervical cancer cellpathology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510659903.5A CN105259095A (en) | 2015-10-14 | 2015-10-14 | Negative-exclusion-method intelligent screening system for cervical cancer cellpathology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105259095A true CN105259095A (en) | 2016-01-20 |
Family
ID=55098867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510659903.5A Pending CN105259095A (en) | 2015-10-14 | 2015-10-14 | Negative-exclusion-method intelligent screening system for cervical cancer cellpathology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105259095A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108745923A (en) * | 2018-04-16 | 2018-11-06 | 曾真 | A kind of slide sorting technique, device and slide test equipment, system |
| CN109073629A (en) * | 2016-02-23 | 2018-12-21 | 诺尔有限公司 | Blood dyes patch and makes the method and apparatus for using it to test blood |
| US11360005B2 (en) | 2016-02-23 | 2022-06-14 | Noul Co., Ltd. | Contact-type patch, staining method using the same, and manufacturing method thereof |
| US12181390B2 (en) | 2016-02-23 | 2024-12-31 | Noul Co., Ltd. | Substance labeling patch, method and apparatus for tissue diagnosis using the same |
| US12211257B2 (en) | 2019-11-28 | 2025-01-28 | Huawei Cloud Computing Technologies Co., Ltd. | Image processing method, apparatus, and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1989009969A1 (en) * | 1988-04-08 | 1989-10-19 | Neuromedical Systems, Inc. | Neural network based automated cytological specimen classification system and method |
| WO2005031319A1 (en) * | 2003-10-02 | 2005-04-07 | Petra Perner | Methods for automatically identifying microorganisms collected on a carrier |
| CN1806166A (en) * | 2003-06-12 | 2006-07-19 | 西泰克公司 | System for determining the stain quality of slides using scatter plot distributions |
| CN101149327A (en) * | 2007-11-06 | 2008-03-26 | 浙江大学 | Anticancer drug evaluation and screening method based on cell microscopic image information |
| CN101606060A (en) * | 2006-09-05 | 2009-12-16 | 维里德克斯有限责任公司 | Classification method of cell image |
-
2015
- 2015-10-14 CN CN201510659903.5A patent/CN105259095A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1989009969A1 (en) * | 1988-04-08 | 1989-10-19 | Neuromedical Systems, Inc. | Neural network based automated cytological specimen classification system and method |
| CN1806166A (en) * | 2003-06-12 | 2006-07-19 | 西泰克公司 | System for determining the stain quality of slides using scatter plot distributions |
| WO2005031319A1 (en) * | 2003-10-02 | 2005-04-07 | Petra Perner | Methods for automatically identifying microorganisms collected on a carrier |
| CN101606060A (en) * | 2006-09-05 | 2009-12-16 | 维里德克斯有限责任公司 | Classification method of cell image |
| CN101149327A (en) * | 2007-11-06 | 2008-03-26 | 浙江大学 | Anticancer drug evaluation and screening method based on cell microscopic image information |
Non-Patent Citations (4)
| Title |
|---|
| 傅华等: "《临床预防医学》", 31 January 2014, 上海：复旦大学出版社 * |
| 曹泽毅等: "《中华妇产科学》", 31 August 1998, 北京：人民卫生出版社 * |
| 李世红等: "《妇产科疾病诊疗学》", 30 June 2007, 长春：吉林人民出版社 * |
| 陈必良等: "《妇产科实验诊疗学》", 31 August 2003, 西安：第四军医大学出版社 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11366043B2 (en) | 2016-02-23 | 2022-06-21 | Noul Co., Ltd. | Contact-type patch, staining method using the same, and manufacturing method thereof |
| US11898947B2 (en) | 2016-02-23 | 2024-02-13 | Noul Co., Ltd. | Diagnostic method and device performing the same |
| CN109073629B (en) * | 2016-02-23 | 2021-03-02 | 诺尔有限公司 | Blood stain patch and method and device for testing blood using the same |
| US11041842B2 (en) | 2016-02-23 | 2021-06-22 | Noul Co., Ltd. | Culturing patch, culturing method, culture test method, culture test device, drug test method, and drug test device |
| US11208685B2 (en) | 2016-02-23 | 2021-12-28 | Noul Co., Ltd. | Diagnostic method and device performing the same |
| US11360005B2 (en) | 2016-02-23 | 2022-06-14 | Noul Co., Ltd. | Contact-type patch, staining method using the same, and manufacturing method thereof |
| US11740162B2 (en) | 2016-02-23 | 2023-08-29 | Noul Co., Ltd. | Contact-type patch, staining method using the same, and manufacturing method thereof |
| US12216033B2 (en) | 2016-02-23 | 2025-02-04 | Noul Co, Ltd. | Contact-type patch, staining method using the same, and manufacturing method thereof |
| CN109073629A (en) * | 2016-02-23 | 2018-12-21 | 诺尔有限公司 | Blood dyes patch and makes the method and apparatus for using it to test blood |
| US11808677B2 (en) | 2016-02-23 | 2023-11-07 | Noul Co., Ltd. | Polymerase chain reaction patch, method and device for diagnosis using the same |
| US11385144B2 (en) | 2016-02-23 | 2022-07-12 | Noul Co., Ltd. | Antibody-providing kit, antibody-containing patch, method and device for immunoassay using the same |
| US12181390B2 (en) | 2016-02-23 | 2024-12-31 | Noul Co., Ltd. | Substance labeling patch, method and apparatus for tissue diagnosis using the same |
| CN108745923A (en) * | 2018-04-16 | 2018-11-06 | 曾真 | A kind of slide sorting technique, device and slide test equipment, system |
| US12211257B2 (en) | 2019-11-28 | 2025-01-28 | Huawei Cloud Computing Technologies Co., Ltd. | Image processing method, apparatus, and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105259095A (en) | Negative-exclusion-method intelligent screening system for cervical cancer cellpathology | |
| CN101339185B (en) | Automatic microscopic imager for detecting cast-off cells and detection method | |
| Santos et al. | Evaluation of autofocus functions in molecular cytogenetic analysis | |
| EP2383569A1 (en) | Image analysis apparatus, image analysis method, image analysis program and recording medium | |
| US20220383629A1 (en) | Label-free cell classification and screening system based on hybrid transfer learning | |
| CN102662048B (en) | Method and device for analyzing urine | |
| JPH0484884A (en) | Method and system for diagnosing the activity of cultured organisms | |
| CN105821538A (en) | Spun yarn breakage detection method and system | |
| CN102359939A (en) | Method for detecting tubercle bacillus in sputamentum | |
| US20180040120A1 (en) | Methods for quantitative assessment of mononuclear cells in muscle tissue sections | |
| CN106835200B (en) | Aluminum electrolysis cell region control system | |
| CN108693342A (en) | Cervical carcinoma, the detection method of uterine cancer and system | |
| Fenech et al. | Preliminary studies on scoring micronuclei by computerised image analysis | |
| CN112432902A (en) | Automatic detection system and method for judging cell number through peripheral blood cell morphology | |
| CN111814537A (en) | Cervical cancer TCT slide microscope automatic scanning and AI diagnosis system and method | |
| CN102297833A (en) | Method for determination of content of various cells in human blood or bone marrow | |
| CN113222928B (en) | Urine cytology artificial intelligence urothelial cancer identification system | |
| CN112507821B (en) | Cell drug resistance detection method based on high content imaging, medium and electronic equipment | |
| CN106835201B (en) | Aluminium cell based on fuzzy clustering algorithm controls method | |
| Li et al. | A recognition method of urine cast based on deep learning | |
| CN109214433A (en) | A kind of method that convolutional neural networks distinguish liver cancer differentiation grade | |
| CN113049593A (en) | Method for realizing online biological monitoring by using intelligent imaging and recognition technology | |
| CN113808081A (en) | A system for detecting defects in small-sized fittings of transmission lines | |
| CN112481346A (en) | Automatic early warning system and method for detecting abnormal cells in peripheral blood cell morphology | |
| Friedrich et al. | Identification of prostate cancer cell nuclei for DNA-grading of malignancy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160120 |