CN106943192A - The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 - Google Patents
The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 Download PDFInfo
- Publication number
- CN106943192A CN106943192A CN201710151411.4A CN201710151411A CN106943192A CN 106943192 A CN106943192 A CN 106943192A CN 201710151411 A CN201710151411 A CN 201710151411A CN 106943192 A CN106943192 A CN 106943192A
- Authority
- CN
- China
- Prior art keywords
- expression index
- ggo
- forecast model
- preoperative
- lung carcinoma
- 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 20
- 206010058467 Lung neoplasm malignant Diseases 0.000 title claims abstract description 17
- 201000005296 lung carcinoma Diseases 0.000 title claims abstract description 14
- 210000004072 lung Anatomy 0.000 claims abstract description 23
- 230000001575 pathological effect Effects 0.000 claims abstract description 23
- 230000000153 supplemental effect Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000002790 cross-validation Methods 0.000 claims abstract description 7
- 238000012109 statistical procedure Methods 0.000 claims abstract description 3
- 238000012360 testing method Methods 0.000 claims description 14
- 230000035945 sensitivity Effects 0.000 claims description 7
- 238000012352 Spearman correlation analysis Methods 0.000 claims description 6
- 238000007689 inspection Methods 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 5
- 238000010827 pathological analysis Methods 0.000 claims description 5
- 230000002980 postoperative effect Effects 0.000 claims description 4
- 238000000611 regression analysis Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 abstract description 4
- 238000011160 research Methods 0.000 description 17
- 208000009956 adenocarcinoma Diseases 0.000 description 15
- 206010028980 Neoplasm Diseases 0.000 description 14
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 12
- 201000011510 cancer Diseases 0.000 description 12
- 239000005337 ground glass Substances 0.000 description 11
- 230000008595 infiltration Effects 0.000 description 11
- 238000001764 infiltration Methods 0.000 description 11
- 210000004907 gland Anatomy 0.000 description 9
- 238000005259 measurement Methods 0.000 description 8
- 208000010507 Adenocarcinoma of Lung Diseases 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 230000007170 pathology Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000007787 solid Substances 0.000 description 5
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 206010020718 hyperplasia Diseases 0.000 description 4
- 208000020816 lung neoplasm Diseases 0.000 description 4
- 230000000505 pernicious effect Effects 0.000 description 4
- 230000035755 proliferation Effects 0.000 description 4
- 230000002685 pulmonary effect Effects 0.000 description 4
- CTQNGGLPUBDAKN-UHFFFAOYSA-N O-Xylene Chemical compound CC1=CC=CC=C1C CTQNGGLPUBDAKN-UHFFFAOYSA-N 0.000 description 3
- 238000000540 analysis of variance Methods 0.000 description 3
- 230000003110 anti-inflammatory effect Effects 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 3
- 230000004663 cell proliferation Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004043 dyeing Methods 0.000 description 3
- 239000011521 glass Substances 0.000 description 3
- 238000011534 incubation Methods 0.000 description 3
- 201000005202 lung cancer Diseases 0.000 description 3
- 239000000243 solution Substances 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 description 2
- 201000007490 Adenocarcinoma in Situ Diseases 0.000 description 2
- 208000003200 Adenoma Diseases 0.000 description 2
- 206010001233 Adenoma benign Diseases 0.000 description 2
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 2
- MHAJPDPJQMAIIY-UHFFFAOYSA-N Hydrogen peroxide Chemical compound OO MHAJPDPJQMAIIY-UHFFFAOYSA-N 0.000 description 2
- 241001494479 Pecora Species 0.000 description 2
- 241000238370 Sepia Species 0.000 description 2
- 210000003123 bronchiole Anatomy 0.000 description 2
- 230000022131 cell cycle Effects 0.000 description 2
- 239000003153 chemical reaction reagent Substances 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 230000018044 dehydration Effects 0.000 description 2
- 238000006297 dehydration reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000010150 least significant difference test Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000001543 one-way ANOVA Methods 0.000 description 2
- 210000004224 pleura Anatomy 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000004393 prognosis Methods 0.000 description 2
- 230000002062 proliferating effect Effects 0.000 description 2
- 210000002966 serum Anatomy 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000001356 surgical procedure Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- WZUVPPKBWHMQCE-XJKSGUPXSA-N (+)-haematoxylin Chemical compound C12=CC(O)=C(O)C=C2C[C@]2(O)[C@H]1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-XJKSGUPXSA-N 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 206010006187 Breast cancer Diseases 0.000 description 1
- 208000026310 Breast neoplasm Diseases 0.000 description 1
- 102100025064 Cellular tumor antigen p53 Human genes 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 230000035519 G0 Phase Effects 0.000 description 1
- WZUVPPKBWHMQCE-UHFFFAOYSA-N Haematoxylin Natural products C12=CC(O)=C(O)C=C2CC2(O)C1C1=CC=C(O)C(O)=C1OC2 WZUVPPKBWHMQCE-UHFFFAOYSA-N 0.000 description 1
- 208000017604 Hodgkin disease Diseases 0.000 description 1
- 208000021519 Hodgkin lymphoma Diseases 0.000 description 1
- 208000010747 Hodgkins lymphoma Diseases 0.000 description 1
- 240000004343 Indigofera suffruticosa Species 0.000 description 1
- 102000009875 Ki-67 Antigen Human genes 0.000 description 1
- 108010020437 Ki-67 Antigen Proteins 0.000 description 1
- 206010027476 Metastases Diseases 0.000 description 1
- 102100022019 Pregnancy-specific beta-1-glycoprotein 2 Human genes 0.000 description 1
- 206010060862 Prostate cancer Diseases 0.000 description 1
- 208000000236 Prostatic Neoplasms Diseases 0.000 description 1
- 108700005075 Regulator Genes Proteins 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 235000011114 ammonium hydroxide Nutrition 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 239000000427 antigen Substances 0.000 description 1
- 108091007433 antigens Proteins 0.000 description 1
- 102000036639 antigens Human genes 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 210000000621 bronchi Anatomy 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 239000007979 citrate buffer Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000006059 cover glass Substances 0.000 description 1
- 238000013211 curve analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 238000010790 dilution Methods 0.000 description 1
- 239000012895 dilution Substances 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 239000012153 distilled water Substances 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 102000052116 epidermal growth factor receptor activity proteins Human genes 0.000 description 1
- 108700015053 epidermal growth factor receptor activity proteins Proteins 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 238000012151 immunohistochemical method Methods 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000009401 metastasis Effects 0.000 description 1
- 230000011278 mitosis Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- YOHYSYJDKVYCJI-UHFFFAOYSA-N n-[3-[[6-[3-(trifluoromethyl)anilino]pyrimidin-4-yl]amino]phenyl]cyclopropanecarboxamide Chemical compound FC(F)(F)C1=CC=CC(NC=2N=CN=C(NC=3C=C(NC(=O)C4CC4)C=CC=3)C=2)=C1 YOHYSYJDKVYCJI-UHFFFAOYSA-N 0.000 description 1
- 239000013642 negative control Substances 0.000 description 1
- -1 nitrite ions Chemical class 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 208000000649 small cell carcinoma Diseases 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 206010041823 squamous cell carcinoma Diseases 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 239000012224 working solution Substances 0.000 description 1
- 239000008096 xylene Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/52—Devices using data or image processing specially adapted for radiation diagnosis
- A61B6/5211—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data
- A61B6/5229—Devices using data or image processing specially adapted for radiation diagnosis involving processing of medical diagnostic data combining image data of a patient, e.g. combining a functional image with an anatomical image
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment
- A61B6/02—Arrangements for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computed tomography [CT]
- A61B6/032—Transmission computed tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Optics & Photonics (AREA)
- High Energy & Nuclear Physics (AREA)
- Biophysics (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Heart & Thoracic Surgery (AREA)
- Quality & Reliability (AREA)
- Pulmonology (AREA)
- Computer Graphics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a kind of method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67.Comprise the following steps：Step (1)：Case is screened, standard compliant patient is obtained；Step (2)：The described expression index of patient KI 67 of detection；Step (3)：CT image scans and three-dimensional reconstruction are carried out to described patient lungs, each CT supplemental characteristics and 3-D view is obtained；Step (4)：Statistical procedures analysis and cross validation are carried out to described CT supplemental characteristics and the expression index of KI 67, and set up KI 67 forecast model.Of the invention initiative is associated related CT parameters measured in the GGO Three-dimension Reconstruction Models with preferable objectivity and accuracy with the expression index of lung carcinoma cell ki 67 in Pathologic specimen, is set up by studying the quantization correlation of the two with the LI of three-dimensional reconstruction parameter prediction KI 67 multivariate regression models.
Description
Technical field
Three-dimensional measurement iconography parameter lung carcinoma cell KI-67 tables are based on the present invention relates to medical domain, more particularly to one kind
Up to the method for building up of the preoperative forecast model of index.
Background technology
With high-resolution ct (High resolution CT, HRCT) development and popularization, lung ground glass tubercle
The recall rate of (Ground-glass opacity, GGO) is significantly improved.Research shows focal GGO mostly adenocarcinomas of lung both at home and abroad
Early lesion.GGO is a non-specific focus, can be performance of a variety of diseases on CT, be found on HRCT
The focal shadow of lung, is generally described as clouding lung density by scholar and increases shadow, while inside can still show bronchus or blood vessel knot
Structure image.But generally acknowledge that it tends to lung's infantile tumour more both at home and abroad at present.Existing multinomial domestic and international research and clinical pathology money
Material prompting, most GGO histopathologies are early stage adenocarcinoma of lung.The histological type of early stage adenocarcinoma of lung presses evolution evolution, can divide
For atypical adenoma sample hyperplasia (Atypical adenomatous hyperplasia, AAH), in situ adenocarcinoma
(Adenocarcinoma in situ, AIS), it is micro- infiltration gland cancer (minimally invasive adenocarcinoma,
) and adenocarcinoma infiltrating (Invasive adenocarcinoma, IAC) MIA.Even follow-up observation, only by two-dimensional ct iconography
It is general levy as including traditional edge, size, whether pleura pulls, has impulse- free robustness etc. is difficult accurately to differentiate its histological type.
As a kind of quantizating index, CT iconography parameters are in studying GGO increasingly by the favor of scholars.In addition, three dimensional CT
Sensitivity and accuracy are had more to the evaluation of Small pulmonary nodule compared to conventional two-dimensional CT.
On the other hand, from the perspective of pathology, the increase of cell-proliferation activity is to create a bad precedent the beginning that lung cancer develops
Person.And cell nuclear proliferating antigen ki-67 often is used for detecting the proliferation activity of cell in sample by clinical pathologist, it is expressed in more
In the nucleus of the active cell of propagation, to regulate and control the cell cycle associated regulatory genes of division growth cell, its expression index
It is proportionate with cell-proliferation activity, many height are expressed in malignant cell, the generation development relationship with tumour is close, multinomial
It is used to explore the biological behaviour of malignant tumour propagation in research.It is thin expressed by researchers' prediction ki-67 both domestic and external
Born of the same parents' proliferation activity has good correlation with the prognosis of patients with lung cancer.It is documented that, Ki-67 albumen is originally defined as standard
Monoclonal antibody Ki-67, is obtained by Hodgkin lymphoma cell line L428 nucleus immune mouse.In fact Ki-67 eggs
All active periods (G1, S, G2, mitosis) of cell cycle are appeared in vain, but are not often expressed in akinete (G0 phases),
This becomes detection specific cell colony proliferation activity or the fabulous mark of growth fraction.High value-added rate is that tumour is most significant
Feature, therefore proliferation activity is used to estimation Huppert's disease, prostate cancer, the prognosis of breast cancer in multinomial research.
Although the CT features for having researched and analysed different pathological types GGO of a large amount of domestic and foreign scholars, seldom research GGO tri-
Relation in dimension reconstruction between iconography parameter and the pathological parameters such as cell-proliferation activity mark Ki-67LI of quantization.Cross
Performed an analysis toward diagnostic method and be only limitted to iconography level, be not directed to evaluate the Pathological levels situation as diagnosis goldstandard, make
Excessively subjectivity must be diagnosed and accuracy is not high.
So, if can be associated KI-67 indexes to related CT parameters, preoperative forecast model is obtained, is extremely to have
Practical value, but prior art, this part also still belongs to blank.
The content of the invention
In order to overcome the above-mentioned deficiencies of the prior art, Lung neoplasm CT three-dimensional reconstruction iconographies are based on the invention provides one kind
The preoperative forecast model of the lung carcinoma cell KI-67 expression index of parameter.
The method for building up of the preoperative forecast model for the lung carcinoma cell KI-67 expression index that the present invention is provided, it is characterised in that
Comprise the following steps：
Step (1)：Case is screened, standard compliant patient is obtained；
Step (2)：The described patient's KI-67 expression index of detection；
Step (3)：CT image scans and three-dimensional reconstruction are carried out to described patient lungs, each CT supplemental characteristics and three are obtained
Tie up image；
Step (4)：Described CT supplemental characteristics and KI-67 expression index are carried out statistical procedures analysis and intersected to test
Card, and set up KI-67 forecast model.
It is preferred that described patient is to meet following standard：
Preoperative row CT examination and GGO patient is diagnosed as first；
It is postoperative to have clear and definite pathological diagnosis result；
Diameter is less than 3cm pure GGO and Combination GGO.
It is preferred that the detection of KI-67 expression index uses SABC two step method.
It is preferred that described CT supplemental characteristics are average diameter, cumulative volume, maximum CT values, mean CT-number and CT Distribution values
Standard deviation.
It is preferred that the step (5) is further comprising the steps of：
Step (5.1)：Using Levene inspection CT supplemental characteristics and KI-67 expression index homogeneities of variance；
Step (5.2)：Examine and calculate between each group with Kruskal-Wallis for the CT supplemental characteristics of heterogeneity of variance
Whether supplemental characteristic has significant difference；
Step (5.3)：KI-67 expression index for homogeneity of variance then analyzes group difference with single factor test variance, and
Pair test two-by-two between group with LSD inspections to carry out kI-67；
Step (5.4)：Between being carried out two-by-two to CT supplemental characteristics and ki-67 expression index predicted value with Tamhane ' s T2
Pair test；
Step (5.5)：Each CT supplemental characteristics and ki-67 expression index pair are detected with Receiver operating curve's analysis
In the sensitivity and specificity of the GGO focuses for differentiating different pathological types；
Step (5.6)：KI- is set up using Spearman correlation analysis and multiple regression analysis and ten folding cross validations
The forecast model of 67 expression index.
Compared with prior art, beneficial effects of the present invention are as follows：
It is of the invention initiative will be measured related in the GGO Three-dimension Reconstruction Models of accuracy with preferable objectivity
CT parameters are associated with lung carcinoma cell ki-67 expression index (Labeling index, LI) in Pathologic specimen, pass through both research
Quantization correlation set up with three-dimensional reconstruction parameter prediction KI-67LI multivariate regression models so as to preoperative GGO pathology
The antidiastole of property provides more accurate quantifiable assessment, judges to provide a preferable median for doctor.Will than with
Toward merely more accurate come subjective judgement by Features.
Brief description of the drawings：
Figure 1A and Figure 1B be the embodiment of the present invention in KI-67 expression index SABC quantitative measurment figure.
Fig. 2A, Fig. 2 B and Fig. 2 C are the three-dimensional reconstruction processing and parameter measurement of lung ground glass tubercle in the embodiment of the present invention
Figure；
Fig. 3 is non-infiltration gland cancer (PIA), micro- adenocarcinoma infiltrating (MIA) and adenocarcinoma infiltrating (IAC) in the embodiment of the present invention
Between each parameter comparison figure；
Fig. 4 is expression lung ground glass tubercle (GGO) diameter, volume (TV), maximum CT values in the embodiment of the present invention
(MAX), the curve of Receiver operating curve (ROC) analysis of mean CT-number (AVG) and CT Distribution values standard deviation (STD)
Figure.
Fig. 5 is the diameter of lung ground glass tubercle (GGO) in the embodiment of the present invention, volume (TV), maximum CT values (MAX), put down
The scatter diagram of equal CT values (AVG) and CT Distribution values standard deviation (STD) the Spearman correlation analysis between ki-67Li.
Fig. 6 is that ki-67 expression index (LI) actual value in the embodiment of the present invention and predicted value are ground in different pathological types lung
Glass tubercle (GGO) includes the case line ratio between non-infiltration gland cancer (PIA), micro- infiltration gland cancer (MIA) and adenocarcinoma infiltrating (IAC)
Relatively scheme.
Fig. 7 is the KI-67 of different pathological types lung ground glass tubercle in embodiment of the present invention ROC curve figure.
Embodiment
The present invention is further described with reference to specific embodiment, to more fully understand the present invention.
First, method
1st, clinical data is gathered
Collect have clear and definite pathological examination in October, 2012 in October, 2014 after surgery excision to hospital and art
Before have complete HRCT and three-dimensional reconstruction 160 GGO patients clinical medical history, pathological replacement, operation record and CT image datas,
To the age of patient, sex, pathological, GGO shapes, edge, diameter (diameter), volume (total volume, TV),
Maximum CT values (the maximum CT attenuation value, MAX), mean CT-number (average CT
Attenuation, AVG) and GGO entirety CT Distribution values standard deviation (standard deviation of the
Distribution of CT attenuation within the whole GGO, STD) carry out sorting-out in statistics.All cases
Receive anti-inflammatory treatment after being detected first as GGO 2 weeks, CT is checked after follow-up in 3 months.GGO focuses are contrasted only after follow-up
The case that stable or diameter reduces can include research, and the case for foci disappearance after anti-inflammatory should give exclusion, mostly inflammatory
Focus.
Case is included into the standard of research：
1. it is preoperative to be diagnosed as in the court's row CT examination and first GGO patient；
2. it is postoperative to have clear and definite pathological diagnosis result；
3. diameter is less than 3cm pure GGO and Combination GGO.
Henschke et al. research reports GGO is than full reality Small pulmonary nodule (Full-solid nodules) grade malignancy
Higher, Feng Li et al. researchs are found in 137 full reality Small pulmonary nodules, and only 15 are pernicious focus, remaining 122
It is all benign focus, and polygonal, the smooth of the edge or the pernicious person of slightly smooth case are substantially fewer than benign person in full solid nodules
(polygonal：Pernicious benign 38%, the p=0.02 of 7%-；The smooth of the edge is slightly smooth：Pernicious benign 63%, the p=0.001 of 0%-)；
98% polygonal solid nodules (46/47) and the solid nodules (77/77) of 100% the smooth of the edge are benign lesion.Therefore
This research eliminates the case of full solid nodules.
The standard of Excluded cases：
1. the GGO or focus on CT images with diameter greater than 3cm are regression after full reality lesser tubercle person or follow-up anti-inflammatory treatment
Person；
2. the pathological examination person that is pulmonary metastasis, pathological examination are squamous carcinoma or small cell carcinoma person and though pathology is gland cancer,
By stages more than T1N0M0 person；
3. (some patientss are after local hospital CT is diagnosed to preoperative CT scan data person without postoperative pathological result or without the court
Go to the court)；
4. it is preoperative to receive lung's chemicotherapy and Biopsy person, iconography parameter measurement can be caused inaccurate；
5. there is the outer cancer medical history person of Lung Cancer in the past.
Final 160 GGO cases include research, wherein male 54, women 106, and average age is 56.59 ± 9.9
Year.All cases carry out three-dimensional reconstruction parameter measurements CT scan obtained to performing the operation the time-interval averaging of Pathologic specimen for 11 ±
4 days (1-23 days).All case pathological diagnosis results for including research include atypical adenoma sample hyperplasia (Atypical
Adenomatous hyperplasia, AAH) 26, it is in situ adenocarcinoma (Adenocarcinoma in situ, AIS) 11, micro-
Infiltrate gland cancer (Minimally invasive adenocarcinoma, MIA) 106 and adenocarcinoma infiltrating (Invasive
Adenocarcinoma, IAC) 17.Table 1 summarizes clinical data, imaging data and the pathology for including research case
Data.
Clinic, iconography and the pathologic data statistics (160) of the GGO cases of the different pathological types of table 1
Note：
Classified according to the international multidisciplinary adenocarcinoma of lung categorizing systems of newest U.S. IASLC/ATS/ERS；
All data are recorded with mean+SD (SD), and * represents p<0.05；
Sex, smoking history and GGO classifications are analyzed by Chi-square Test；
Average age, diameter, cumulative volume (TV), maximum CT values (MAX), mean CT-number (AVG), CT Distribution value standard deviations
(STD) and ki-67 expression index predicted value is by Kruskal-Wallis and Tambane ' sT2 examine analyzed；
Ki-67 expression index passes through one-way analysis of variance (one-way ANOVA) least significant difference test (LSD
Test) analyzed；
P represents the p value of all GGO cases the results of analysis of variance；
P1 represents the p value of significant difference between non-infiltration adenocarcinoma of lung (PIA) and micro- infiltration adenocarcinoma of lung (MIA) group；
P2 represents the p value of significant difference between micro- infiltration adenocarcinoma of lung (MIA) and infiltration adenocarcinoma of lung (IAC) group；
2nd, Immunohistochemical Method detection Ki-67 expression index
The SABC two step method that Ki-67 detection is adopted international standards is tested, and concrete operations are as follows：
1. the preparation of slide：The slide and cover glass of preparation flowing water after 24h in acid solution, taking-up is placed in first to rush
Wash, then rinsed 3-4 times with ddH20, be then immersed in 95% alcohol 2h, also need to make anti-flake processing after slide is dry, by what is cleaned
Slide is put into 30s in the 3- of Fresh aminopropyls-triethoxysilane (APES) working solution, uses pure acetone after taking-up again
Solution or ddH20 wash away uncombined APES, are fitted into standby in box after drying.
2. section：The sample of all surgery excisions is fixed with 10% neutral formalin, then after FFPE
Serial section, slice thickness is 4 μm, and every serial section three carries out conventional H E dyeing observation pathomorphisms, immuning tissue
Learn dyeing observation Ki-67, EGFR, P53, CEA expression；Roasting piece 6-8h under the conditions of 60 DEG C of electrically heated drying cabinet constant temperature can be used.
3. dewaxing：First with dimethylbenzene in dewaxing 3 times, each 15min at 60 DEG C；Gradient alcohol dehydration is used again, is followed successively by
Absolute alcohol 2 times, 95% alcohol 2 times, 80% alcohol 1 time, 70% alcohol 1 time, are 5min every time；Running water developing sheet is used again
DdH20 rinses 5min after quarter；0.01M PBS are rinsed 3 times, each 3min.
4. configuring 3% hydrogen peroxide blocks endogenous peroxydase, 10min is maintained at room temperature, then is rinsed 3 times with PBS,
Each 3-5min.
5. antigen retrieval：It is 6.0 citrate buffer solution that first the section handled by above-mentioned steps, which is placed on, and fills PH
In beaker, then beaker be put into high steam pot in, boil to pressure cooker jet and maintain 10min；Make after then taking out section
It naturally cools to room temperature, first with distilled water flushing 2 times, then is rinsed 3 times with PBS, each 3min.
6. closing：Excess surface moisture is cleaned, 2h is incubated at room temperature after the closing of 4% sheep blood serum is added dropwise, non-specific dye is reduced
Color.
7. primary antibody：Sheep blood serum is got rid of, ready first antibody is added dropwise, incubation at room temperature 1h is after 4 DEG C after each antibody dilution
It is lower to stay overnight；0.01M PBS are added dropwise and are used as negative control；0.01M PBS are rinsed 3 times, each 3min.
8. remove surface moisture, the reagent l in kit is added dropwise, 37 DEG C of incubation 20min, 0.01M PBS rinse 3 times, often
Secondary 3min；2,37 DEG C of incubation 30min of reagent in kit are added dropwise；0.01M PBS are rinsed 3 times, each 3min.
9. getting rid of PBS liquid, the section after above-mentioned processing is immersed to 5min in the DAB nitrite ions of Fresh, while
Micro- Microscopic observation colour developing degree, stained positive often shows as brown color or sepia, will then be cut after positive reaction colour developing substantially
Piece under flowing water in rinsing, and timely terminating reaction, general developing time is 5 minutes or so.
11. haematoxylin is redyed flowing water after 30s-2min and rinsed, then is broken up with l% hydrochloric acid-alcohol, ammoniacal liquor returns blue or running water
Indigo plant is returned, running water is rinsed.
12. gradient alcohol dehydration：It is dehydrated successively using 70% alcohol, 80% alcohol, 95% alcohol, absolute alcohol, every time
It is 5min；Xylene soak 2 times, each 8min.
13. using neutral gum fat mounting, then diagosis under microscope, coloration result is recorded.
The unified standard of the relevant strong and weak classification of Ki-67 expression is there is no at present.In Research Literature and Clinicopathologic Work generally
Ki-67 label indexs are represented using rough percentage, i.e., randomly choosing 10 under 40 × 10 times of mirrors, in every slide regards
Open country, the ratio for calculating the average shared visual field of 10 visual field positive cells estimates Ki-67LI roughly, and nuclei dyeing is brown color
Or the cell of sepia is then positive cell.As shown in figure 1, using image measurement software I mage Pro Plus in the present embodiment
6.0, which carry out the picture after being detected to ki-67 SABCs, carries out quantitative measurment.Figure 1A represents grey black in the karyon of proliferative cell
Grain is ki-67 positive expression；Figure 1B represents different according to gray value during quantitative detection, software automatic identification gray area
Gray value is simultaneously measured.
3rd, CT image scans and three-dimensional reconstruction post processing
It is commonly unenhanced to the leading routine of lung, then thin layer volume helical scanning is carried out to focus.Shield after advising the deep air-breathing of patient
Firmly, scanned by apertura thoracis superior to base of lung portion.
The condition of scanning：
120~140kV of voltage
200~400mA of electric current
Rebuild thickness 0.625mm
Matrix 512 × 512
Algorithm：Bone algorithm is axially rebuild, filtered back projection (filtered back projection, FBP) and double lungs are most
Low coverage method.
The CT of all cases is diagnosed and post-processed by two image doctor's read tablets for having 8 years and 12 years respectively, works as tubercle
More than one aspect can be diagnosed as GGO.HRCT images are stored in hospital DICM (digital imaging and
Communications in medicine) in computer system for inquiring about and study.
The related parameter of 5 GGO Three-dimension Reconstruction Models is have chosen in the present embodiment as variable：Average diameter, cumulative volume
(Total volume, TV), maximum CT values (MAX), mean CT-number (AVG) and CT Distribution values standard deviation (STD).
Three-dimensional reconstruction processing：Using ADW3.1 work stations (Advantage Workstation 4.3；GE
Healthcare), reconstruction software (Lung VCAR are utilized；GE Healthcare) three-dimensional reconstruction is carried out, main method is using appearance
(volume rendering, VR) is rebuild in product display.In VR image reconstructions, software after tubercle is clicked on not automatic according to CT value differences
Detect and delimit interest region (region of interest, ROI), i.e. GGO tubercles and surrounding adjacent structure, including in tubercle
The blood vessel and bronchiole in portion；The structure for being not belonging to tubercle to perinodal by cutting technique again is different according to each several part CT value differences
Surface trimming is carried out after discrimination；After three dimensional volumetric image is shown, contrast, brightness are suitably adjusted, image is reached optimum visual
Effect；Then can be used rotation technique from 720 ° of full angles tubercle three-dimensional configuration, internal blood vessel or bronchiole structure and
Situations such as with the relation of edge pleura；It is last automatic arranged side by side to the three-dimensional diameters of GGO, the accurate measurement of TV, MAX, AVG and STD progress
Go out.Fig. 2 shows the three-dimensional reconstruction processing and parameter measurement of lung ground glass tubercle (ground-glass opacity, GGO), Fig. 2A
Represent typical GGO (arrow) on high-resolution ct (HRCT)；Fig. 2 B represent the GGO models after the reconstruction that software is automatically generated with
And automatic measurement relevant parameter；Fig. 2 C represent the parameter list amplification in 2B, including three-dimensional diameter, volume (TV), maximum CT values
(MAX), mean CT-number (AVG) and CT Distribution values standard deviation (STD).
4th, statistical analysis
All data are recorded as mean+SD.Using Levene inspection variable homogeneities of variance, as a result remove
All variables are heterogeneity of variance beyond ki-67LI, as shown in table 2.Therefore use Kruskal- for the variable of heterogeneity of variance
Wallis examines to calculate whether variable between each group has significant difference, and the ki-67LI of homogeneity of variance then uses single factor test variance
(ANOVA) is analyzed to analyze group difference.In addition, Pair test two-by-two between group with LSD inspections to carry out ki-67LI, is used
Tamhane ' s T2 carry out Pair test between being carried out two-by-two to tubercle diameter, TV, MAX, AVG, STD and ki-67LI predicted value.With by
Examination person's performance curve (Receiver operating curve, ROC) is analyzed to detect each variable for differentiating different diseases
Manage the sensitivity and specificity of the GGO focuses of type.Simultaneously ten foldings intersection is tested for Spearman correlation analysis and multiple regression analysis
Demonstrate,prove to set up ki-67LI forecast model.Software used by statistical analysis is SPSS 22.0, and P ＜ 0.05 have statistics meaning for difference
Justice.
Table 2 is examined with Levene and carries out variable homogeneity test of variance result
Note：
Variable includes GGO tubercles diameter, cumulative volume, maximum CT values, mean CT-number, CT Distribution values standard deviation, Ki-67 expression
Index and Ki-67 expression index predicted values；
p(Sig.)<0.05 represents variable heterogeneity of variance, need to be examined with Tamhane ' s T2, p (Sig.)>0.05 expression
Homogeneity of variance, need to be examined (LSD) with least significant difference；
Two, results
1st, Features and Tissue pathological diagnosis
GGO three-dimensional reconstruction CT parameters are by the poster processing soft automatic measurement, and the parameter of each pathology compares as shown in figure 3, Fig. 3
The comparison of each parameter between expression non-infiltration gland cancer (PIA), micro- adenocarcinoma infiltrating (MIA) and adenocarcinoma infiltrating (IAC).Ki-67
Expression positive cell shows as the brown granular in the nucleus of excessive proliferated cell, and relevant statistics, which are shown in, is still shown in Table 1.
2nd, each parameter ROC curve discriminatory analysis of different pathological types
Tubercle diameter, TV, MAX, AVG, STD and ki-67LI are obtained for being reflected between PIA and MIA groups by ROC curve analysis
Other TG-AUC (AUC) divides 0.801,0.822,0.890,0.857,0.901 and 0.907 respectively, for MIA and IAC groups
Between the AUC that differentiates be respectively 0.812,0.793,0.749,0.731,0.684,0.901；Point on each independent variable curve is simultaneously
Choose maximum True Positive Rate (i.e. sensitivity) and minimum false positive rate (i.e. 1- specificity) just can obtain each variable between group
Discrimination threshold, be typically near the curve upper left corner that [37].Therefore gained diameter, TV, MAX, AVG, STD and ki-
67LI is respectively 10.55mm, 217mm for best discriminant technique threshold value between PIA and MIA groups3,-126.5HU,-615.5HU,135.5
With 4.38%, and it is respectively 21.8mm for best discriminant technique threshold value between MIA and IAC groups, 1708.5mm3,189HU,-464HU,
169.4 and 9.88%, as shown in figure 4, Fig. 4 represents lung ground glass tubercle (GGO) diameter, volume (TV), maximum CT values
(MAX), Receiver operating curve (ROC) analysis of mean CT-number (AVG) and CT Distribution values standard deviation (STD).According to song
Area (AUC) under line is it can be seen that ki-67LI has than other the every more preferable sensitivitys of three dimensional CT parameter and specificity.It is every
Parameter is for difference is more efficient between difference ratio MIA and IAC groups between discriminating PIA and MIA groups.
3rd, the correlation between three dimensional CT parameter and ki-67LI
Pass through Spearman correlation analysis, GGO diameters (p<0.001)、TV(p<0.001)、MAX(p<0.001),AVG
(p<0.001) with STD (p<0.001) there is conspicuousness related between ki-67Li, each auto-correlation coefficient is respectively 0.575,
0.559,0.605,0.585and 0.639, as shown in figure 5, Fig. 5 is the diameter of lung ground glass tubercle (GGO), volume (TV), most
Big CT values (MAX), mean CT-number (AVG) and CT Distribution values standard deviation (STD) Spearman correlation analysis between ki-67Li
Scatter diagram (r is coefficient correlation)；Each parameter is with ki-67Li into conspicuousness positive correlation；Fig. 5 (S) demonstrate GGO have it is heterogeneous
Property, be not in that STD parabolic declines when more than 50% with increasing for property composition really.
In addition, by multiple linear regression analysis come the phase between further quantitative search three dimensional CT parameter and ki-67Li
Guan Xing, and 160 GGO cases are divided into 10 groups by ten folding cross validations of progress (10-fold cross-validation),
It is test group (testing sets) to define 1 group successively, and 9 groups are training group (training sets) to carry out recurrence mould in addition
Type is built, and then substitutes into detection checking with test group.10 multiple regression equations on ki-67LI are finally obtained, and are calculated
The mean absolute error (Mean absolute error, MAE) of each equation, average relative error (Mean relative
Error, MRE) and root-mean-square error (Root mean square error, RMSE) evaluate the recurrence efficiency of respective equation.
N represents test group case load i.e. 10 in above-mentioned formula,Represent ki-67Li predicted value, y1Represent ki-67 LI's
Actual value.
3160 GGO case three dimensional CT parameters of table are handed over ten foldings of ki-67 expression index (LI) multiple linear regression model
Fork checking
Note：R represents multiple correlation coefficient, R2The coefficient of determination is represented, MAE represents mean absolute error, and MRE represents average phase
To error, RMSE represents root mean square error；
R and R2Represent the compatible degree of regression model；
MAE, MRE and RMSE represent the prediction precision of regression model, and three is more low, and then forecast of regression model is more accurate.
In final 10 regression equations, relatively show that the 5th prescription journey has of a relatively high prediction accurate by cross validation
True rate, regression equation is as follows：
Ki-67 LI=0.022*STD+0.001*TV+2.137 (4)
The 160 case three dimensional CT parameters for including research are all substituted into and obtain overall ki-67LI predicted values, PIA, MIA
Ki-67 LI predicted value averages with IAC be respectively 4.27 ± 0.76 (range, 2.67~6.05%), 6.50 ± 1.69
(range, 3.00~11.74%) and 8.81 ± 3.73 (range, 3.75~16.65%), and have conspicuousness poor between group two-by-two
Different (ANOVA P<0.001,LSD PIA vs.MIA P<0.001, MIA vs.IAC P=0.014, PIA vs.IAC P<
0.001) it grinds glass as shown in fig. 6, Fig. 6 Fig. 6 is ki-67 expression index (LI) actual value and predicted value in different pathological types lung
Glass tubercle (GGO) includes the box traction substation ratio between non-infiltration gland cancer (PIA), micro- infiltration gland cancer (MIA) and adenocarcinoma infiltrating (IAC)
Compared with.As a result ki-67 LI actual values are shown and have significant difference between predicted value group.Analyzed additionally by ROC curve, I
Compare the AUC of ki-67 LI predicted values and actual value, although the AUC (PIA/MIA of ki-67 LI predicted values：0.893；
MIA/IAC：0.841) AUC (PIA/MIA without actual value：0.907；MIA/IAC：0.901) it is high, but also than iconography parameter
For the degree of accuracy height differentiated between different pathological types GGO groups, it is as shown in fig. 7, Fig. 7 ROC curve com-parison and analysis ki-67 LI
Actual value and predicted value judge the sensitivity and specificity of different pathological types lung ground glass tubercle (GGO) for discriminating.
It is of the invention initiative will be measured related in the GGO Three-dimension Reconstruction Models of accuracy with preferable objectivity
CT parameters are associated with lung carcinoma cell ki-67 expression index (Labeling index, LI) in Pathologic specimen, pass through both research
Quantization correlation set up with three-dimensional reconstruction parameter prediction KI-67 LI multivariate regression models so as to preoperative GGO disease
The antidiastole of rationality matter provides more accurate quantifiable assessment, judges to provide a preferable median for doctor.Will compare
It is in the past simple more accurate come subjective judgement by Features.
The specific embodiment of the present invention is described in detail above, but it is intended only as example, and the present invention is not limited
It is formed on particular embodiments described above.To those skilled in the art, it is any to the equivalent modifications that carry out of the present invention and
Substitute also all among scope of the invention.Therefore, the impartial conversion made without departing from the spirit and scope of the invention and
Modification, all should be contained within the scope of the invention.
Claims (5)
1. a kind of method for building up of the preoperative forecast model of lung carcinoma cell KI-67 expression index, it is characterised in that including following step
Suddenly：
Step (1)：Case is screened, standard compliant patient is obtained；
Step (2)：The described patient's KI-67 expression index of detection；
Step (3)：CT image scans and three-dimensional reconstruction are carried out to described patient lungs, each CT supplemental characteristics and graphics is obtained
Picture；
Step (4)：Statistical procedures analysis and cross validation are carried out to described CT supplemental characteristics and KI-67 expression index, and
Set up KI-67 forecast model.
2. the method for building up of the preoperative forecast model of lung carcinoma cell KI-67 expression index according to claim 1, its feature
It is that described patient is to meet following standard：
(1) preoperative row CT examination and GGO patient is diagnosed as first；
(2) it is postoperative to have clear and definite pathological diagnosis result；
(3) diameter is less than 3cm pure GGO and Combination GGO.
3. the method for building up of the preoperative forecast model of lung carcinoma cell KI-67 expression index according to claim 1, its feature
It is that the detection of KI-67 expression index uses SABC two step method.
4. the method for building up of the preoperative forecast model of lung carcinoma cell KI-67 expression index according to claim 1, its feature
It is that described CT supplemental characteristics are average diameter, cumulative volume, maximum CT values, mean CT-number and CT Distribution value standard deviations.
5. the method for building up of the preoperative forecast model of lung carcinoma cell KI-67 expression index according to claim 1, its feature
It is that the step (5) is further comprising the steps of：
Step (5.1)：Using Levene inspection CT supplemental characteristics and KI-67 expression index homogeneities of variance；
Step (5.2)：For the CT supplemental characteristics of heterogeneity of variance parameter between each group is calculated with Kruskal-Wallis inspections
Whether data have significant difference；
Step (5.3)：KI-67 expression index for homogeneity of variance then analyzes group difference with single factor test variance, and uses
LSD examines between group to carry out kI-67 Pair test two-by-two；
Step (5.4)：Matched between being carried out with Tamhane ' s T2 to CT supplemental characteristics and ki-67 expression index predicted value two-by-two
Examine；
Step (5.5)：Detect each CT supplemental characteristics and ki-67 expression index for mirror with Receiver operating curve's analysis
The sensitivity and specificity of the GGO focuses of other different pathological types；
Step (5.6)：KI-67 tables are set up using Spearman correlation analysis and multiple regression analysis and ten folding cross validations
Up to the forecast model of index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710151411.4A CN106943192A (en) | 2017-03-14 | 2017-03-14 | The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710151411.4A CN106943192A (en) | 2017-03-14 | 2017-03-14 | The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106943192A true CN106943192A (en) | 2017-07-14 |
Family
ID=59467371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710151411.4A Pending CN106943192A (en) | 2017-03-14 | 2017-03-14 | The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106943192A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107545135A (en) * | 2017-08-15 | 2018-01-05 | 璞晞（广州）生物免疫技术有限公司 | The construction method of hepatitis B liver diseases T lymphocyte immunity state application assessment models |
| CN108376565A (en) * | 2018-02-13 | 2018-08-07 | 北京市神经外科研究所 | A kind of image group prediction technique of glioma Ki-67 expressions |
| WO2019037106A1 (en) * | 2017-08-24 | 2019-02-28 | 黄月华 | Method for constructing practical model for evaluating nk cell function in hepatitis b liver disease |
| CN111787878A (en) * | 2018-02-05 | 2020-10-16 | 堃博生物科技公司 | Image-guided lung tumor planning and ablation system |
| CN111933287A (en) * | 2020-06-24 | 2020-11-13 | 四川省肿瘤医院 | Integrating platelet characteristics in blood and platelet-rich plasma to establish a lung cancer model |
| CN112258390A (en) * | 2020-09-10 | 2021-01-22 | 华中师范大学 | A high-precision microscopic virtual learning resource generation method |
| WO2021155829A1 (en) * | 2020-02-05 | 2021-08-12 | 杭州依图医疗技术有限公司 | Medical imaging-based method and device for diagnostic information processing, and storage medium |
| WO2024060842A1 (en) * | 2022-09-19 | 2024-03-28 | 京东方科技集团股份有限公司 | Classification model acquiring method and apparatus, expression category determining method and apparatus, device, and medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717146A (en) * | 2016-03-29 | 2016-06-29 | 复旦大学附属中山医院 | Kit for predicating lung cancer risk for high-risk groups among China urban population on basis of CT (computed tomography) images and biomarker spectrums |
-
2017
- 2017-03-14 CN CN201710151411.4A patent/CN106943192A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105717146A (en) * | 2016-03-29 | 2016-06-29 | 复旦大学附属中山医院 | Kit for predicating lung cancer risk for high-risk groups among China urban population on basis of CT (computed tomography) images and biomarker spectrums |
Non-Patent Citations (1)
| Title |
|---|
| MINGZHENG PENG ET AL.: "Preoperative Prediction of Ki-67 Labeling Index By Three-dimensional CT Image Parameters for Differential Diagnosis Of Ground-Glass Opacity (GGO)", 《PLOS ONE》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019033444A1 (en) * | 2017-08-15 | 2019-02-21 | 黄月华 | Construction method for applicability evaluation model of immune state of t lymphocyte of hepatic diseases of hepatitis b |
| CN107545135B (en) * | 2017-08-15 | 2019-03-05 | 璞晞（广州）生物免疫技术有限公司 | The construction method of hepatitis B liver diseases T lymphocyte immune state application assessment models |
| CN107545135A (en) * | 2017-08-15 | 2018-01-05 | 璞晞（广州）生物免疫技术有限公司 | The construction method of hepatitis B liver diseases T lymphocyte immunity state application assessment models |
| WO2019037106A1 (en) * | 2017-08-24 | 2019-02-28 | 黄月华 | Method for constructing practical model for evaluating nk cell function in hepatitis b liver disease |
| CN111787878A (en) * | 2018-02-05 | 2020-10-16 | 堃博生物科技公司 | Image-guided lung tumor planning and ablation system |
| CN111787878B (en) * | 2018-02-05 | 2024-02-02 | 杭州堃博生物科技有限公司 | Image-guided lung tumor planning and ablation system |
| CN108376565B (en) * | 2018-02-13 | 2022-07-19 | 北京市神经外科研究所 | Imaging omics prediction method for expression level of brain glioma Ki-67 |
| CN108376565A (en) * | 2018-02-13 | 2018-08-07 | 北京市神经外科研究所 | A kind of image group prediction technique of glioma Ki-67 expressions |
| WO2021155829A1 (en) * | 2020-02-05 | 2021-08-12 | 杭州依图医疗技术有限公司 | Medical imaging-based method and device for diagnostic information processing, and storage medium |
| CN111933287A (en) * | 2020-06-24 | 2020-11-13 | 四川省肿瘤医院 | Integrating platelet characteristics in blood and platelet-rich plasma to establish a lung cancer model |
| US11164289B1 (en) | 2020-09-10 | 2021-11-02 | Central China Normal University | Method for generating high-precision and microscopic virtual learning resource |
| CN112258390A (en) * | 2020-09-10 | 2021-01-22 | 华中师范大学 | A high-precision microscopic virtual learning resource generation method |
| WO2024060842A1 (en) * | 2022-09-19 | 2024-03-28 | 京东方科技集团股份有限公司 | Classification model acquiring method and apparatus, expression category determining method and apparatus, device, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106943192A (en) | The method for building up of the preoperative forecast model of the expression index of lung carcinoma cell KI 67 | |
| Zhang et al. | Invasive ductal breast cancer: preoperative predict Ki-67 index based on radiomics of ADC maps | |
| Sasaki et al. | Artificial intelligence for breast cancer detection in mammography: experience of use of the ScreenPoint Medical Transpara system in 310 Japanese women | |
| Aker et al. | Magnetic resonance texture analysis in identifying complete pathological response to neoadjuvant treatment in locally advanced rectal cancer | |
| Mi et al. | Deep learning-based multi-class classification of breast digital pathology images | |
| Zhang et al. | CT-based radiomics to predict the pathological grade of bladder cancer | |
| Wang et al. | Semiquantitative computed tomography characteristics for lung adenocarcinoma and their association with lung cancer survival | |
| CN110391015B (en) | A radiomics-based method to quantify tumor immune status | |
| CN106248945B (en) | Method, system and the kit of the grouping of hepatocellular carcinoma radical excision prognosis situation are carried out to patients with hepatocellular carcinoma | |
| Gollub et al. | Limited accuracy of DCE-MRI in identification of pathological complete responders after chemoradiotherapy treatment for rectal cancer | |
| Zhang et al. | Automatic detection of invasive ductal carcinoma based on the fusion of multi-scale residual convolutional neural network and SVM | |
| CN117670794A (en) | TLS pathology detection method, device and medium based on deep learning | |
| Wang et al. | Tumor detection for whole slide image of liver based on patch-based convolutional neural network | |
| Matsumoto et al. | Utility of radiomics features of diffusion-weighted magnetic resonance imaging for differentiation of fat-poor angiomyolipoma from clear cell renal cell carcinoma: model development and external validation | |
| Zhao et al. | Preoperative evaluation of extramural venous invasion in rectal cancer using radiomics analysis of relaxation maps from synthetic MRI | |
| Zhang et al. | Developing a machine learning algorithm for identifying abnormal urothelial cells: a feasibility study | |
| Zhang et al. | Potential rapid intraoperative cancer diagnosis using dynamic full-field optical coherence tomography and deep learning: A prospective cohort study in breast cancer patients | |
| Li et al. | Contrast-enhanced CT-based radiomics for the differentiation of nodular goiter from papillary thyroid carcinoma in thyroid nodules | |
| Zhu et al. | Predicting Ki‐67 labeling index level in early‐stage lung adenocarcinomas manifesting as ground‐glass opacity nodules using intra‐nodular and peri‐nodular radiomic features | |
| Weikert et al. | Automated quantification of airway wall thickness on chest CT using retina U-Nets–Performance evaluation and application to a large cohort of chest CTs of COPD patients | |
| CN115937130A (en) | Image processing method for predicting ovarian cancer Ki-67 expression based on dual-energy CT | |
| Ma et al. | MRI radiomics for the preoperative evaluation of lymphovascular invasion in breast cancer: A meta-analysis | |
| Xu et al. | CT-based radiomics signature for preoperative prediction of coagulative necrosis in clear cell renal cell carcinoma | |
| CN113723441B (en) | Intelligent analysis system and method for lip gland pathology | |
| Fernandez et al. | Analytical validation of the PreciseDx digital prognostic breast cancer test in early-stage breast 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170714 |
|
| RJ01 | Rejection of invention patent application after publication |