CN114093500A - Method for screening cervical cancer by fusing multiple detection results - Google Patents
Method for screening cervical cancer by fusing multiple detection results Download PDFInfo
- Publication number
- CN114093500A CN114093500A CN202111189520.8A CN202111189520A CN114093500A CN 114093500 A CN114093500 A CN 114093500A CN 202111189520 A CN202111189520 A CN 202111189520A CN 114093500 A CN114093500 A CN 114093500A
- Authority
- CN
- China
- Prior art keywords
- detection
- cervical cancer
- index
- value
- hpv
- 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
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/53—Immunoassay; Biospecific binding assay; Materials therefor
- G01N33/574—Immunoassay; Biospecific binding assay; Materials therefor for cancer
- G01N33/57407—Specifically defined cancers
- G01N33/57411—Specifically defined cancers of cervix
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/48—Biological material, e.g. blood, urine; Haemocytometers
- G01N33/50—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing
- G01N33/68—Chemical analysis of biological material, e.g. blood, urine; Testing involving biospecific ligand binding methods; Immunological testing involving proteins, peptides or amino acids
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Urology & Nephrology (AREA)
- Molecular Biology (AREA)
- Hematology (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Cell Biology (AREA)
- Analytical Chemistry (AREA)
- Biotechnology (AREA)
- General Physics & Mathematics (AREA)
- Biochemistry (AREA)
- Public Health (AREA)
- Microbiology (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Medicinal Chemistry (AREA)
- Food Science & Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Hospice & Palliative Care (AREA)
- Oncology (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a method for screening cervical cancer by fusing a plurality of detection results, which respectively detects normal cervical tissues and cancerous cervical tissues by integrating a DNA ploidy method, a TBS (TBS) method and an HPV (human papilloma virus) method to obtain corresponding detection indexes, and obtains a cervical precancerous early lesion stage diagnosis model for distinguishing the normal cervical tissues and the cancerous cervical tissues by carrying out regularization quantification on each detection index and then carrying out comprehensive analysis. According to the invention, by regularizing and quantifying a plurality of detection indexes, the weight of each index is obtained, and then comprehensive analysis and diagnosis are carried out, so that the sensitivity and specificity of detection are improved.
Description
Technical Field
The invention relates to the technical field of disease screening, in particular to a method for screening cervical cancer by fusing a plurality of detection results.
Background
The cervical cancer is one of high-incidence malignant tumors of gynecology, the incidence rate of the malignant tumors is second to breast cancer, according to the statistics of the world health organization, about 50 ten thousand women are diagnosed as the cervical cancer every year in the world, about 28.8 ten thousand patients die, and the life health of the women is seriously harmed. Therefore, the early diagnosis of cervical cancer and lesion is the key to improve the cure rate and survival rate of cervical cancer. At present, the technical means for cervical cancer screening comprise DNA ploid detection, conventional liquid-based cytology (TBS), HPV detection and the like, and each detection method has independent sensitivity and specificity and plays an important role in cervical cancer screening.
The principle of the DNA ploidy analysis method is to observe and quantitatively analyze the change condition of cell nuclei of non-lymphocyte cells such as squamous epithelial cells and glandular epithelial cells, and under the condition of canceration/precancerosis, the DNA of the cells abnormally proliferates, and the cell nuclei show the tendency of enlarging and deepening. The DNA ploidy analysis method mainly uses an optical method to measure the integral optical density of cell nucleus to quantify DNA value, including squamous epithelial cell, glandular cell, lymphocyte and the like. The nuclear DNA of the lymphocyte is insensitive to the lesion and usually keeps a certain constant, and as a comparison standard, the nuclear DNA of squamous epithelial cells, glandular cells and the like is compared with the standard to obtain DNA ploidy, and the higher part has larger possibility of the lesion.
The TBS method adopts a liquid-based thin-layer cell detection system to detect cervical cells and carry out cytological classification diagnosis, is the most advanced cytological examination technology for cervical cancer internationally at present, and obviously improves the satisfaction degree of a specimen and the detection rate of abnormal cervical cells compared with the traditional cervical smear examination by scraping a pap smear. TBS cervical cancer prevention cytology examination has high detection rate on cervical cancer cells, and can find partial precancerous lesions and microbial infections such as mold, trichomonas and the like. TBS detection is mainly carried out by observing cell morphology through a microscope, wherein nuclei are enlarged or abnormal, and lesions are more likely to exist.
HPV infection is one of the main causes of cervical cancer occurrence, and the correlation rate is as high as 99.7%. Two requirements for inducing cervical cancer by HPV infection are high risk HPV (hrHPV) infection and persistent HPV infection. The HPV is divided into low-risk type, medium-risk type and high-risk type, the high-risk type HPV comprises 16, 18, 31, 33, 39, 45, 52 subtypes and the like, wherein the HPV16 and HPV18 are the most common high-risk type subtypes and account for 75% of the pathogenesis of cervical cancer. HPV DNA detection requires sampling by gynecological examination, usually taking cervical exfoliated cells or cervical mucus, and performing HPV typing detection by Polymerase Chain Reaction (PCR). The patient may also experience discomfort and psychological adverse effects. HPV DNA examination is only a primary screening effect, and has no prognosis judgment effect. The HPV detection is to detect whether the HPV virus is infected by a nucleic acid molecular probe and a fluorescent quantitative analysis instrument.
CN201811425981.9 discloses a DNA quantitative analysis method based on cell microscope image, which uses the RAW file of information obtained directly from CCD or CMOS as the picture in DNA quantitative analysis to avoid the error caused by adding compensation calculation when calculating IOD value, so as to greatly improve the accuracy of DNA quantitative calculation, and make the result more stable when increasing or decreasing the incident light intensity.
CN202010355386.3 discloses a plasma exosome protein Mortalin as an HPV positive cervical cancer diagnostic marker and application thereof. Differential proteins of cervical cancer tumor group patients, precancerous lesion patients (CIN) and healthy human plasma exosomes are compared through proteomics, and mortalin expression conditions after HPV key molecules HPVE6/E7 are knocked out, so that the exosomes mortalin can be used as a molecular marker of cervical cancer, the plasma exosomes mortalin can be detected to preliminarily screen the cervical cancer, and the early diagnosis probability of the cervical cancer can be improved.
CN202110227238.8 provides an intelligent cervical cancer cell detection method based on liquid-based thin-layer slice cytology detection technology TBS, which comprises the steps of carrying out photomicrography on a cell smear inspected by the liquid-based thin-layer cytology detection technology TBS to obtain a digital image with stained cells; performing cell detection on the pathological image by adopting a full convolution network layer to obtain the position information of a single pathological cell; dividing single pathological cell images into four types by adopting a general network; and carrying out two-classification judgment on the single pathological cell images of the HISL and the LISL by adopting an expert network, thereby realizing five classifications of the cervical cancer cells.
In the prior art, a certain method is possibly sensitive to some types of lesions and is not sensitive to other types of lesions, and some low-level lesions or even individual high-level lesions are easy to miss diagnosis or misdiagnose more when only one of the methods is used; when a plurality of means are used for simultaneous detection, deviation of detection indexes often occurs, such as HPV positive display, DNA ploidy negative display and the like, diagnosis cannot be effectively and accurately carried out, such as missed diagnosis, the optimal treatment time is easily delayed, such as misdiagnosis, and unnecessary pain of a detected person is easily caused.
Based on the shortcomings of the prior art, there is a need for a method for screening cervical cancer by fusing multiple detection results.
Disclosure of Invention
In order to achieve the aim, the invention provides a method for screening cervical cancer by fusing a plurality of detection results, which carries out regularization quantification on a plurality of detection indexes, obtains the weight of each index and then carries out comprehensive analysis and diagnosis, thereby improving the sensitivity and specificity of detection.
The invention adopts the following technical scheme:
on one hand, the invention provides a method for screening cervical cancer by fusing a plurality of detection results, which respectively detects normal cervical tissues and cancerous cervical tissues by a comprehensive DNA ploidy method, a conventional cast-off cytology (TBS) method and an HPV method to obtain corresponding detection indexes, and obtains a cervical precancerous early stage lesion diagnosis model for distinguishing the normal cervical tissues and the cancerous cervical tissues by performing regularization quantification and then performing comprehensive analysis on each detection index.
Further, the regularization quantification process of the detection index of the DNA ploidy method is as follows: the specific quantization method can be various, for example, a sigmoid function is adopted:
x is (1/(1+ e ^ (c (d-v))) (formula one),
wherein c is a quality control factor parameter, optionally 1 to 10,
d is DNA ploidy detection value, such as 1.8, 2, 2.8, etc.,
v is a ploidy abnormality threshold, which can be set to 2, 2.5, etc. as the case may be,
x is the possibility, and the value range X is 0.0-1.0 or 0% -100%.
Further, the DNA ploidy detection index includes, but is not limited to, area of nucleus, average integrated optical density, smoothness, ploidy value of hyperploid, cell number, and the like.
Further, the regularization quantization process of the TBS detection index is as follows: for example, a bayesian optimization algorithm is used to obtain the weight of each type of morphological target (e.g., LSIL), the number of findings per field of view of each type of morphological target is weighted and summed to obtain a TBS index quantization value t, and the TBS index quantization value t is substituted into a sigmoid function X ═ (1/(1+ e ^ (c (t-v)))) (formula two) to be quantized into a probability (X ═ 0 to 1), where c is a quality control factor parameter, and is optionally set to 1 to 10; t is TBS index quantization value; v is a positive threshold; the possibility of quantization (X ═ 0.0 to 1.0 or 0% to 100%) can be optionally set.
Further, the type morphological target indexes in the TBS method detection include, but are not limited to, the number of ASCUS, the number of LSIL, the number of HSIL, the number of AGC-FN, and the like.
Further, the regularized quantization process of the HPV detection index is as follows: in some embodiments, a bayesian optimization algorithm is used to obtain the weight of each type of morphological target, the number of findings per field of view of each type of morphological target is weighted and summed to obtain an HPV index quantization value T, and the HPV index quantization value T is substituted into a sigmoid function X ═ (1/(1+ e ^ (c ^ (T-v))) (formula three) to be quantized into a probability (X ═ 0 to 1), where c is a quality control factor parameter, and is optionally 1 to 10; t is the HPV index quantification value; v is a positive threshold; optionally, the probability (X ═ 0.0 to 1.0 or 0% to 100%) is quantified on the sample particle size; in still other embodiments, sigmoid functions are employed: x is (1/(1+ e ^ (c (D-v))) (formula IV), wherein c is a quality control factor parameter and is 1-10 according to the situation; d is an HPV detection index, such as 1.8, 2, 2.8 and the like, and v is a detection index abnormality threshold, which can be set as 2, 2.5 and the like as appropriate.
Further, the HPV detection index includes, but is not limited to, protein E6, protein p53, protein E7, protein pRB, protein complex, and the like.
Furthermore, the method can change the dyeing method, the film making method, the detection parameters, the detection model and the like of the same sample aiming at the same detection method or different detection methods in the detection process, does not differ due to the change of a certain specific means, only needs to carry out regularization quantification and fusion calculation according to the detection indexes in the detection method process, and has wide coverage range.
Further, the comprehensive analysis is to perform fusion calculation on the probability result obtained by regularization quantization to obtain a comprehensive diagnosis quantization value.
Further, the method of fusion calculation includes, but is not limited to, arithmetic mean, weighted mean, harmonic mean, and the like.
The method provided by the invention combines the electrical, optical and genetic detection, the detection indexes among the detection methods are fused and complemented, the defects of various methods are overcome, the advantages of various methods are taken, the cervical cancer is rapidly screened, the accuracy of diagnosis results is improved, the detection can be finished at one time, manual discrimination is not needed, the detection period is shortened, and the survival rate of patients is effectively improved.
Has the advantages that:
the invention provides a method for screening cervical cancer by fusing a plurality of detection results, which is characterized in that after DNA (deoxyribonucleic acid) indexes, TBS (TBS) indexes and HPV (human papilloma virus) indexes are subjected to regularization and quantization, comprehensive diagnosis and quantization are carried out to obtain a comprehensive diagnosis result, the result indexes of a toilet are used for judging the possibility of cervical cancer, and the sensitivity and the specificity of the obtained comprehensive diagnosis result are superior to those of a single detection result.
The invention realizes the fusion of a plurality of detection indexes of a plurality of detection means or the same detection means by regularizing and quantizing discrete or continuous detection indexes in DNA ploid detection indexes, conventional cast-off cytology (TBS) detection indexes and HPV detection indexes, reduces the labor intensity of doctors, overcomes the conclusion difference caused by parameter difference among different detection means, and improves the accuracy for detecting the possibility of cervical cancer in a patient. The detection possibility for early diagnosis of cancer improves efficiency.
Detailed Description
The invention will be further illustrated with reference to the following specific examples. These examples are intended to illustrate the invention and are not intended to limit the scope of the invention.
Example 1
The core of the invention is to carry out regularization quantification on each detection index by using a computer algorithm, obtain the weight of each detection index from big data, and carry out comprehensive diagnosis by weighting and fusing each quantitative detection index. The embodiment provides a method for screening cervical cancer by fusing a plurality of detection results, which comprises the steps of respectively detecting a normal cervical tissue and a cancerous cervical tissue by a comprehensive DNA ploidy method, a conventional cast-off cytology (TBS) method and an HPV method to obtain corresponding detection indexes, and carrying out regularization quantification and comprehensive analysis on each detection index to obtain a cervical precancerous early lesion stage diagnosis model for distinguishing the normal cervical tissue and the cancerous cervical tissue; the method comprises the following specific steps:
1) the method comprises the following steps of obtaining corresponding detection indexes by detecting a sample (normal cervical tissue or cancerous cervical tissue), and carrying out regularization quantification on the continuous or discrete indexes, wherein the regularization quantification is as follows:
A) regularization quantification of DNA ploidy detection indexes: the DNA ploidy detection indexes include, but are not limited to, area of cell nucleus, average integrated optical density, smoothness, ploidy value of high ploidy, number of cells, etc., and are quantified as probability (X ═ 0.0-1.0 or 0-100%) in sample granularity, and there are many specific quantification methods, such as commonly used sigmoid function: x is (1/(1+ e ^ (c (d-v)))), wherein c is a quality control factor parameter and is optionally 1-10, d is a DNA ploidy detection value, such as 1.8, 2, 2.8 and the like, v is a ploidy abnormal threshold value and can be optionally set to be 2, 2.5 and the like, and X is the possibility;
B) regularization quantization of TBS detection index: TBS detection indexes include, but are not limited to, the number of asics, LSIL, the number of HSILs, AGC-FN, etc., and are quantized to a probability (X is 0.0 to 1.0 or 0% to 100%) at sample granularity, and there are many specific quantization methods, for example, a bayesian optimization algorithm is used to obtain a weight of each type of morphological target (e.g., LSIL), the number of findings per field of each type of morphological target is weighted and summed to obtain a TBS index quantization value t, and the value is substituted into a sigmoid function X (1/(1+ e ^ (c (t-v)))) to be quantized to a probability (X is 0 to 1), where c is a quality control factor parameter, and is optionally 1 to 10; t is TBS index quantization value; v is a positive threshold; can be set according to the situation;
C) regularization quantification of HPV detection indices: HPV detection indexes include but are not limited to protein E6, protein p53, protein E7, protein pRB, protein complex and the like; in some embodiments, a bayesian optimization algorithm is used to obtain the weight of each type of morphological target, the found number of each view of each type of morphological target is weighted and summed to obtain an HPV index quantization value T, and the HPV index quantization value T is substituted into a sigmoid function X (1/(1+ e (c ^ (T-v))) (formula three) to be quantized into the probability (X ═ 0 to 1), where c is a quality control factor parameter, and is optionally 1 to 10; t is the HPV index quantification value; v is a positive threshold; optionally, the probability (X ═ 0.0 to 1.0 or 0% to 100%) is quantified on the sample particle size; in still other embodiments, sigmoid functions are employed: x is (1/(1+ e ^ (c (D-v))) (formula IV), wherein c is a quality control factor parameter and is 1-10 according to the situation; d is an HPV detection index, such as 1.8, 2, 2.8 and the like, and v is a detection index abnormality threshold, which can be set as 2, 2.5 and the like as appropriate. A regularization quantization method for reference TBS and DNA detection indexes;
2) carrying out multiple independent detections on the same sample by using the same detection method or different detection methods by changing the detection parameters including but not limited to a dyeing method, a sheet making method, a detection model and the like, and carrying out regularization quantification on the detection result of each time through the step 1);
3) fusing the multiple independent detection quantification results (including multiple detection methods, different stains, different slices, different parameters, different models and the like of the same detection method) by using multiple methods including, but not limited to, arithmetic mean, weighted mean, harmonic mean and the like to obtain a comprehensive diagnosis quantification value;
4) and taking the comprehensive diagnosis quantitative value obtained in the steps as a diagnosis model of the cervical precancerous early stage lesion stage, and judging and analyzing the diagnosis model of the cervical precancerous early stage lesion stage to finally obtain a conclusion whether the sample is cancerated or not.
Example 2
The invention is used in the auxiliary diagnosis of the full-automatic cervical cell analyzer of Leiboshi, the analyzer has the functions of DNA quantitative analysis and TBS morphological analysis auxiliary diagnosis, and can respectively detect the ploidy value of DNA and the TBS morphology.
The method of the embodiment 1 of the invention is used for carrying out a detection test by cooperating with a certain provincial Hospital to detect 10044 cervical exfoliated cell fluid-based slice samples in total. The diagnosis result of expert radiograph interpretation is taken as a control standard, wherein the positive cases of LSIL and the positive cases account for 5.48 percent. The method of example 1 of the present invention provides a 5% increase in the positive detection rate over the results obtained with the assays alone (compared to the assays with DNA quantitation alone) and 3% increase over the results obtained with the assays alone (compared to the assays with TBS morphometric alone).
Although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method for screening cervical cancer by fusing a plurality of detection results is characterized in that normal cervical tissues and cancerous cervical tissues are respectively detected by a comprehensive DNA ploidy method, a TBS method and an HPV method to obtain corresponding detection indexes, and a cervical precancerous early lesion stage diagnosis model for distinguishing the normal cervical tissues and the cancerous cervical tissues is obtained by carrying out regularization quantification on each detection index and then carrying out comprehensive analysis.
2. The method for screening cervical cancer by fusing a plurality of detection results according to claim 1, wherein the regularized quantification process of the detection indexes of the DNA ploidy method is as follows: calculating by adopting a sigmoid function: x is (1/(1+ e ^ (c (d-v))) (formula one),
wherein c is a parameter of a quality control factor,
d is the detection value of the DNA ploidy,
v is the threshold value of the abnormal ploidy,
x is the possibility, and the value range X is 0.0-1.0 or 0% -100%.
3. The method for screening cervical cancer according to claim 2, wherein the DNA ploidy detection index comprises area of cell nucleus, average integrated optical density, smoothness, ploidy value of hyperploid or cell number.
4. The method for screening cervical cancer by fusing a plurality of detection results as claimed in claim 1, wherein the regularized quantization process of the TBS detection index is as follows: using a Bayesian optimization algorithm to calculate the weight of each type of form target, carrying out weighted summation on the found number of each visual field of each type of form target to obtain a TBS index quantization value t, and substituting the value into a sigmoid function X ═ 1/(1+ e ^ (c ^ (t-v))) (formula two) for quantization, wherein c is a quality control factor parameter; t is TBS index quantization value; v is a positive threshold; x is 0.0-1.0 or 0-100%.
5. The method of claim 4, wherein the indicator of the type morphological object comprises ASCUS number, LSIL, HSIL number, AGC, or AGC-FN number.
6. The method for screening cervical cancer by fusing a plurality of detection results according to claim 1, wherein the regularized quantification process of the HPV detection indexes is as follows: i) using a Bayesian optimization algorithm to calculate the weight of each type of morphological target, carrying out weighted summation on the found number of each visual field of each type of morphological target to obtain an HPV index quantization value T, and substituting the value into a sigmoid function X (1/(1+ e ^ (c) (T-v))) (formula III) for quantization, wherein c is a quality control factor parameter; t is the HPV index quantification value; v is a positive threshold; 0.0-1.0 or 0-100% of X; ii) using sigmoid function: x is (1/(1+ e ^ (c (D-v))) (formula IV), wherein c is a quality control factor parameter; d is HPV detection index, and v is detection index abnormal threshold.
7. The method for screening cervical cancer by fusing the detection results according to claim 6, wherein the HPV detection index comprises protein E6, protein p53, protein E7, protein pRB or protein complex.
8. The method for screening cervical cancer by fusing a plurality of detection results according to claim 1, wherein the staining method, the preparation method, the detection parameters and the detection model are changed for the same detection method or different detection methods of the same sample in the detection process, and the method is not different due to the change of a specific means, and only the regularization quantization and fusion calculation are performed according to the detection indexes in the detection process.
9. The method for screening cervical cancer by fusing a plurality of detection results according to claim 1, wherein the comprehensive analysis is to perform fusion calculation on the probability results obtained by regularization quantization to obtain a comprehensive diagnosis quantization value.
10. The method for screening cervical cancer according to claim 1, wherein the fusion calculation method comprises arithmetic mean, weighted mean or harmonic mean.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111189520.8A CN114093500B (en) | 2021-10-12 | 2021-10-12 | Diagnostic model establishing method fusing multiple detection results |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111189520.8A CN114093500B (en) | 2021-10-12 | 2021-10-12 | Diagnostic model establishing method fusing multiple detection results |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114093500A true CN114093500A (en) | 2022-02-25 |
| CN114093500B CN114093500B (en) | 2022-12-02 |
Family
ID=80296724
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111189520.8A Active CN114093500B (en) | 2021-10-12 | 2021-10-12 | Diagnostic model establishing method fusing multiple detection results |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114093500B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105177164A (en) * | 2015-10-21 | 2015-12-23 | 山东大学齐鲁医院 | Molecular marker for early screening cervical cancer and detecting primers |
| CN110684827A (en) * | 2019-11-15 | 2020-01-14 | 南京市妇幼保健院 | Cervical cancer staging method and detection kit based on cervical exfoliated cell gene detection |
| WO2020012367A2 (en) * | 2018-07-09 | 2020-01-16 | Hkg Epitherapeutics Limited | Dna methylation markers for noninvasive detection of cancer and uses thereof |
| CN111180071A (en) * | 2019-12-31 | 2020-05-19 | 四川大学 | Method and device for calculating relationship between high-risk HPV type and cervical cancer pre-lesion stage |
| CN111710427A (en) * | 2020-06-17 | 2020-09-25 | 广州市金域转化医学研究院有限公司 | Cervical precancerous early lesion stage diagnosis model and establishment method |
-
2021
- 2021-10-12 CN CN202111189520.8A patent/CN114093500B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105177164A (en) * | 2015-10-21 | 2015-12-23 | 山东大学齐鲁医院 | Molecular marker for early screening cervical cancer and detecting primers |
| WO2020012367A2 (en) * | 2018-07-09 | 2020-01-16 | Hkg Epitherapeutics Limited | Dna methylation markers for noninvasive detection of cancer and uses thereof |
| CN110684827A (en) * | 2019-11-15 | 2020-01-14 | 南京市妇幼保健院 | Cervical cancer staging method and detection kit based on cervical exfoliated cell gene detection |
| CN111180071A (en) * | 2019-12-31 | 2020-05-19 | 四川大学 | Method and device for calculating relationship between high-risk HPV type and cervical cancer pre-lesion stage |
| CN111710427A (en) * | 2020-06-17 | 2020-09-25 | 广州市金域转化医学研究院有限公司 | Cervical precancerous early lesion stage diagnosis model and establishment method |
Non-Patent Citations (3)
| Title |
|---|
| 李霞等: "宫颈DNA倍体分析联合宫颈细胞学检查在宫颈癌筛查中的应用价值", 《中华妇幼临床医学杂志(电子版)》 * |
| 邱志磊等: "前列腺癌人工神经网络诊断模型的应用研究", 《临床泌尿外科杂志》 * |
| 陈广莉等: "宫颈细胞DNA倍体分析与液基细胞学联合HPV检测宫颈癌前病变的临床应用价值", 《中国妇幼保健》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114093500B (en) | 2022-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Heselmeyer-Haddad et al. | Genomic amplification of the human telomerase gene (TERC) in pap smears predicts the development of cervical cancer | |
| EP2745111B1 (en) | System and method for the detection of precancer or cancer cells in a biological sample | |
| US7587078B2 (en) | Automated image analysis | |
| US9436992B2 (en) | Method of reconstituting cellular spectra useful for detecting cellular disorders | |
| CN111863118B (en) | TCT and DNA ploidy analysis method based on TCT flaking | |
| WO2012041333A1 (en) | Automated imaging, detection and grading of objects in cytological samples | |
| Saad et al. | Clinical significance of cytologic diagnosis of atypical squamous cells, cannot exclude high grade, in perimenopausal and postmenopausal women | |
| Papillo et al. | Effectiveness of the ThinPrep Imaging System: clinical experience in a low risk screening population | |
| US8983166B2 (en) | Method for automatically seeding previously-classified images among images of objects of interest from a specimen | |
| Duggan | Cytologic and histologic diagnosis and significance of controversial squamous lesions of the uterine cervix | |
| Schledermann et al. | Automated screening versus manual screening: A comparison of the ThinPrep® imaging system and manual screening in a time study | |
| CN104745670A (en) | Preparation method of cell chip and application of cell chip in tumour screening field | |
| CN114093500B (en) | Diagnostic model establishing method fusing multiple detection results | |
| US20040235180A1 (en) | Method for analyzing a biological sample | |
| Thrall | A practical approach to squamous abnormalities on cervical cytology: overview of interpretive criteria and guidance for altering thresholds in response to quality assurance findings | |
| CN107578411A (en) | Method based on computer image analysis test cervical squamous cells parameter | |
| Böcking et al. | Diagnostic cytometry | |
| Cochrane Gynaecological, Neuro-oncology and Orphan Cancer Group et al. | Low cost versus other screening tests to detect cervical cancer or precancer in developing countries | |
| Zhou | Application of different methods for cervical cancer detection | |
| Kruse et al. | The relationship between syntactic structure analysis features, histological grade and high‐risk HPV DNA in cervical intraepithelial neoplasia | |
| Nagayama et al. | Oral cytology in Japan: Its useful approach and criteria for early detection of carcinoma and precursor lesions | |
| Thiripurasundari et al. | Pap screening for cervical carcinoma–evolving trends | |
| Smith et al. | Automated quantitative fluorescent image analysis of cervical cytology | |
| Wang et al. | Automated segmentation and analysis of fluorescent in situ hybridization (FISH) signals in interphase nuclei of pap-smear specimens | |
| Li et al. | Study on the Application of P16/KI67 Protein in Screening of Cervical Cancer |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230327 Address after: 519000 5-540, Floor 5, Yunxi Valley Digital Industrial Park, No. 168, Youyou Road, Xiangzhou District, Zhuhai City, Guangdong Province (Block B, Meixi Commercial Plaza) (centralized office area) Patentee after: Zhuhai Laibosai Medical Robot Co.,Ltd. Address before: 410000 room 437, No. 1318, Kaiyuan East Road, Xingsha industrial base, Changsha Economic and Technological Development Zone, Hunan Province Patentee before: Hunan solai Intelligent Technology Co.,Ltd. Patentee before: HUNAN LABSCI MEDICAL ROBOT Co.,Ltd. |
|
| TR01 | Transfer of patent right |