CN110415820A - Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data - Google Patents
Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data Download PDFInfo
- Publication number
- CN110415820A CN110415820A CN201910731727.XA CN201910731727A CN110415820A CN 110415820 A CN110415820 A CN 110415820A CN 201910731727 A CN201910731727 A CN 201910731727A CN 110415820 A CN110415820 A CN 110415820A
- Authority
- CN
- China
- Prior art keywords
- concentration
- lesion region
- small cell
- cell lung
- lung cancer
- 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
- 208000002154 non-small cell lung carcinoma Diseases 0.000 title claims abstract description 67
- 208000029729 tumor suppressor gene on chromosome 11 Diseases 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 55
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 62
- 201000011510 cancer Diseases 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 27
- 230000003902 lesion Effects 0.000 claims description 50
- 230000006870 function Effects 0.000 claims description 24
- 238000009826 distribution Methods 0.000 claims description 19
- 239000000427 antigen Substances 0.000 claims description 12
- 102000036639 antigens Human genes 0.000 claims description 12
- 108091007433 antigens Proteins 0.000 claims description 12
- 238000002591 computed tomography Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 239000000439 tumor marker Substances 0.000 claims description 9
- 238000002560 therapeutic procedure Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003745 diagnosis Methods 0.000 claims description 5
- 238000006467 substitution reaction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 10
- 239000003814 drug Substances 0.000 description 9
- 210000004027 cell Anatomy 0.000 description 8
- 229940079593 drug Drugs 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000007689 inspection Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 201000009030 Carcinoma Diseases 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 108010036226 antigen CYFRA21.1 Proteins 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 210000004072 lung Anatomy 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000002651 drug therapy Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000008194 pharmaceutical composition Substances 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 108010076876 Keratins Proteins 0.000 description 1
- 102000011782 Keratins Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000007596 consolidation process Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 210000001161 mammalian embryo Anatomy 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 210000002966 serum Anatomy 0.000 description 1
- 208000000649 small cell carcinoma Diseases 0.000 description 1
- 208000000587 small cell lung carcinoma Diseases 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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
- G06T2207/30061—Lung
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Public Health (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data, which comprises obtain the characteristic of cancer patient；The characteristic is pre-processed；The pretreated data are analyzed, analysis result is obtained；According to the analysis as a result, generating assessment result.This method can image to cancer patient and related data carry out processing analysis, to provide cancer assessment result.
Description
Technical field
The present invention relates to cancer assessments, particularly relate to a kind of non-small cell lung cancer appraisal procedure and dress based on big data
It sets.
Background technique
Non-small cell lung cancer (NSCLC) is a kind of high risk cancer, usually by PET-T be scanned detection, prediction, then to
Treatment method out.In actual hospital system, it is necessary to generate at least 640 images by PET-CT scanning for each patient.
Selecting all images manually may be inefficient for doctor, and doctor only can be using certain in these images
Some images are diagnosed, and so as to cause the wasting of resources of medical system, but man-made system can be handled with image and parameter,
To provide assessment result.
Summary of the invention
In view of this, it is an object of the invention to propose it is a kind of can be according to scan image and tumor markers concentration
Analysis handles the method and apparatus for obtaining cancer assessment result.
Based on above-mentioned purpose, the non-small cell lung cancer appraisal procedure based on big data that the present invention provides a kind of, comprising:
Obtain the characteristic of cancer patient；
The characteristic is pre-processed；
The pretreated data are analyzed, analysis result is obtained；
According to the analysis as a result, generating assessment result.
In some embodiments, the characteristic of the cancer patient includes lesion region PET scan image, tumour mark
Concentration, CT scan image and the non-small cell lung cancer cell antigen concentration of will object；The tumor markers have at least one.
In some embodiments, it is described to the pretreated data carry out analysis include:
Obtain the lesion region PET scan image；
It identifies the lesion region in the PET scan image, calculates the area of the lesion region；The lesion region has
At at least one；
Obtain the sum of the area of lesion region SNSCLC；
Calculate the area of the concentration lesion region in the lesion regionTo describedWith the SNSCLCIt asks
Ratio obtains concentrated area degree of correlation D (r)；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
It is in some embodiments, described that the pretreated data are analyzed further include:
Obtain the concentration of the tumor markers；
High correlation parameter R is obtained according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For age y tumor markers i it is flat
Equal concentration, αiFor weight,
Low correlation is obtained according to the PTE scan image, CT scan image and non-small cell lung cancer cell antigen concentration
Parameter RL(t)；
J is the project of the low correlation parameter, βjFor the factor to affect of each project, 0 < βj< 1；T is the assessment time；
Concentration degree of correlation D (t) is obtained according to the high correlation parameter and the low correlation parameter；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the factor to affect of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
In some embodiments, described to be analyzed according to described as a result, generation assessment result includes:
The weight of the high correlation parameter is distributed in assessment time t, obtains weighting function w (t)；
The joint probability distribution P of multiple therapy methods combination is obtained according to the concentration degree of correlation decision contentw；
According to the joint probability distribution PwExpected effects function is obtained with the w (t)
The weight of the high correlation parameter is distributed in assessment time t+N, obtains weighting function w (t+N)；
It will be described in the w (t+N) substitutionIt obtains
If w (t) > w (t+N) exists, andDiagnosis then is able to carry out in time t and selects the w
It (t) is optimal weight function.
The present invention also provides a kind of, and the non-small cell lung cancer based on big data assesses device, comprising:
Data acquisition module, for obtaining the characteristic of cancer patient；
Data preprocessing module, for being pre-processed to the characteristic；
Data analysis module obtains result for analyzing the pretreated data；
Assessment result generation module, for being analyzed according to described as a result, generating assessment result.
In some embodiments, the data analysis module includes:
Image collection module, for obtaining the lesion region PET scan image；
Area calculation module, for calculating the lesion region from the lesion region identified in the PET scan image
Area；Obtain the sum of the area of lesion region SNSCLC；
Areal analysis module, for calculating the area of the concentration lesion region in the lesion regionTo describedWith the SNSCLCRatio is sought, concentrated area degree of correlation D (r) is obtained；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
In some embodiments, the data analysis module further include:
Concentration obtains module, for obtaining the concentration of the tumor markers；
Parameter calculating module, for obtaining high correlation parameter R according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For crowd's tumor-marker that the age is y
The mean concentration of object i, αiFor weight,According to the PTE scan image, CT scan image and non-small cell
Lung carcinoma cell antigen concentration obtains low correlation parameter RL(t)；
J is the project of the low correlation parameter, βjFor the impact factor of each project, 0 < βj< 1；T is the assessment time；
Concentration degree of correlation D (t) is obtained according to the high correlation parameter and the low correlation parameter；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the influence coefficient of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
In some embodiments, the assessment result generation module further include:
Weight distribution module obtains weighting function w for distributing the weight of the high correlation parameter in assessment time t
(t)；The weight of the high correlation parameter is distributed in assessment time t+N, obtains weighting function w (t+N)；
Probability distribution computing module, for obtaining the connection of multiple therapy methods combination according to the concentration degree of correlation decision content
Close probability distribution Pw；
Assessment result obtains module, according to the joint probability distribution PwExpected effects function is obtained with the w (t)It will be described in the w (t+N) substitutionIt obtains
Weight parameter determining module, if w (t) > w (t+N) exists, andThen time t can be into
Row diagnoses and selects w (t) for optimal weight function.
The electronic equipment for the small cell carcinoma of lung appraisal procedure based on big data that the present invention also provides a kind of, including storage
Device, processor and storage are on a memory and the computer program that can run on a processor, which is characterized in that the processor
The non-small cell lung cancer appraisal procedure based on big data is realized when executing described program.
From the above it can be seen that a kind of non-small cell lung cancer appraisal procedure based on big data provided by the invention,
It include: the characteristic for obtaining cancer patient；The characteristic includes scan image, tumor markers concentration etc.；And then it is right
The characteristic is pre-processed, by the characteristic processing for calculate power it will be appreciated that language；To the pretreatment
Data afterwards are analyzed, and are analyzed as a result, the analysis result is specifically some parameters for assessment；According to described point
Analysis further divides the parameter for assessment more calculated in the analytic process as a result, generation assessment result
Analysis calculates, and generates the assessment result that doctor can refer to.The present invention also provides the non-small cell lung cancer assessments based on big data
Device and electronic equipment.Method, apparatus and electronic equipment of the invention can image to cancer patient and related data carry out
Processing analysis, to provide cancer assessment result.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of process signal of non-small cell lung cancer appraisal procedure based on big data provided in an embodiment of the present invention
Figure；
Fig. 2 is a kind of tumor markers maximum region scanning figure provided in an embodiment of the present invention；
Fig. 3 a is the process schematic that the embodiment of the present invention calculates the X-Y scheme of tumor markers；
Fig. 3 b is a kind of analysis datagram for calculating concentrated area area provided in an embodiment of the present invention；
Fig. 4 is the CYFRA-21-1 average data histogram of three patient in hospital over nearly 5 years；
Fig. 5 is the CEA average data histogram of three patient in hospital over nearly 5 years；
Fig. 6 is the CA-125 average data histogram of three patient in hospital over nearly 5 years；
Fig. 7 is the relation schematic diagram of high correlation parameter and carcinoma stage that big data is shown.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in more detail.
It should be noted that all statements for using " first " and " second " are for differentiation two in the embodiment of the present invention
The non-equal entity of a same names or non-equal parameter, it is seen that " first " " second " only for the convenience of statement, does not answer
It is interpreted as the restriction to the embodiment of the present invention, subsequent embodiment no longer illustrates this one by one.
The non-small cell lung cancer appraisal procedure based on big data that the embodiment of the invention provides a kind of, as shown in Figure 1, for this
A kind of flow diagram for non-small cell lung cancer appraisal procedure based on big data that inventive embodiments provide, the method packet
It includes:
S10 obtains the characteristic of cancer patient；The characteristic of the cancer patient includes lesion region PET scan
Image, the concentration of tumor markers, CT scan image and non-small cell lung cancer cell antigen concentration；The tumor markers have to
Few one kind.
In some embodiments, the characteristic further includes other about non-small cell lung in addition to described in S10
The related data of the inspection item of cancer.
The characteristic is pre-processed, and is handled using computer.By collecting multiple hospitals over the years
The related data of Patients with Non-small-cell Lung handles the related data, and carries out feature by machine learning model
The matching of data and result carries out the matching of carcinoma stage locating for the related data and patient using data over the years.It is described
The foundation of machine learning model is not repeating again.Data collection in the present embodiment, arranges and integration comes from Xiang Ya hospital, Hunan
Refined three hospital of refined two hospital and Hunan.The medical data of these hospitals passes through medical data central transmission and exchange.In medical data
The heart collects data from different departments, and if patient diagnoses, disease, operation, nursing care plan and medicament selection, progress data classification are cured
Raw, nurse and patient provide comprehensive information.
It is classified from three hospitals, 15 years NSCLC data.The NSCLC data case of various consolidations is as shown in table 1.Root
According to the data statistics of hospital NSCLC patient, we are extracted 12186 NSCLC patients and analyze.Meanwhile we are every
Patient selects 48145 lung images to carry out machine statistics.
The NSCLC data collection and type of 1 three hospitals of table
| Project | Quantity |
| Patient information | 2789675 |
| Outpatient services | 968545 people |
| The equipment of outpatient clinician | 28554590 |
| Number of hospitalized | 1676899 people |
| Checkup item | 1124561 |
| Electronic medical record | 5287413 |
| The equipment of clinician | 31427790 |
| Inspection record | 179712 |
| Medical laboratory's record | 9483216 |
| Routine inspection record | 24287612 |
| Operation note | 393218 |
| Drug record | 90631 |
In specific assessment models, intelligence is established in processing based on the calculated result of computer system parameter can be used
It can evaluation module.Doctor can judge disease state with reference to assessment result, improve diagnosis efficiency, reduce misdiagnosis rate.
In some embodiments, specific assessment models mainly consist of two parts, concentrated area degree of correlation D (r) and dense
It spends degree of correlation D (t).
Specific evaluation process is as follows:
S20 pre-processes the characteristic；The preprocessing process be by or the characteristic processing be
Computer it will be appreciated that computer binary language.
S30 analyzes the pretreated data, obtains analysis result；
Determine that the concentrated area of cancer cell has great significance for cancer assessment.For non-small cell lung cancer
(NSCLC), determine that concentrated area degree of correlation D (r) and concentration degree of correlation D (t) help that doctor is made to select suitable treatment method.
For non-diffused NSCLC, Direct Surgery excision is main treatment method, for the NSCLC spread, operation
It is main treatment method with drug therapy.The analysis of concentrated area degree of correlation D (r) and concentration degree of correlation D (t) are specific as follows.
In some embodiments, it is described to the pretreated data carry out analysis include:
S301-1 obtains the lesion region PET scan image；
S301-2 identifies the lesion region in the PET scan image, calculates the area of the lesion region；The disease
Becoming region has at least one；
During PET-CT scanning, by dye injection to patient's body, patient is scanned within 15-40 minutes, is developed
The concentrated area of the concentrated area reflection lesion of agent.During the scanning process, the range of tumor markers from small to large, reaches maximum
It gradually becomes smaller again later.The area of the maximum magnitude is the area of tumour concentrated area, and it is maximum to observe by the naked eye selection
Region.As shown in Fig. 2, being a kind of tumor markers maximum region scanning figure provided in an embodiment of the present invention.Pass through computer side
Boundary's identification, turns to X-Y scheme, the size and actual area of the X-Y scheme for the tumor markers maximum region image
It is identical, the X-Y scheme is calculated.As shown in Figure 3a, the X-Y scheme is calculated for the embodiment of the present invention
Process schematic.The two dimensional image is scanned up and down, distance d is selected equidistantly to scan, every time the corresponding transverse direction 2r mark of scanning
Note scans n times altogether, forms set V, wherein V={ ri|1≤i≤n}.Collect at this point, we can be stored by queue EnQ (V)
It closes.By to riIt averages to calculate the equivalent redius of the X-Y schemeWherein,
The X-Y scheme is equivalent to by a circle by this calculation.Select different distance d corresponding different
Scanning times, then calculate different equivalent redius.The cartographic represenation of area of the equivalent circular are as follows:
It enablesObtain maximum equivalent areaMachine point for ease of calculation
Analysis, can focus on regularization for the calculating of equivalent circular.The judgement of maximum magnitude can also calculate in the shortest possible time,
To maximize image intensity.
Fig. 3 b is a kind of analysis datagram for calculating concentrated area area provided in an embodiment of the present invention.It is shown in figure logical
Cross the calculating analysis for adjusting different cutting distances (d) to machine concentrated area.Per unit adds 0.05 centimetre of unit length.When
When d=0.1cm, concentrated area areaAs △ d=0.15cm to △ d=0.35cm, concentrated area face
ProductStability is in 12 and 13cm2Between；As △ d=0.4cm,Less than 12cm2, so that segmentation range △ d ∈
[0.15,0.35].Concentration range is maximum, and in 12.8cm2Locate the cluster value with maximum stable.Testing 79226 figures
As after, we determined that △ d=0.2cm is suitable for Training valuation system.Therefore, can be obtained during scanning patient optimization and
Clear image, the data basis as assessment.
S301-3 obtains the sum of the area of lesion region SNSCLC；
The area of all lesion regions is calculated using above-mentioned same method, and is summed, details are not described herein.
S301-4 calculates the area of the concentration lesion region in the lesion regionTo describedWith it is described
SNSCLCRatio is sought, concentrated area degree of correlation D (r) is obtained；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
In order to preferably analyze and calculate the concentration lesion region in image, we are using standard ratio calculation method to every
The clinical problem of a image and NSCLC are analyzed.Specifically, described in calculatingWith the SNSCLCRatio, described in acquisition
Concentrated area degree of correlation D (r),After the data for obtaining the concentrated area degree of correlation, we can be with
Scan each NSCLC clinical image.Clinical problem it is describedWith the SNSCLCRatio range may be used as being stored in number
According to one of the patient evaluation parameter in the system of library.
The relevant parameter of the D (t) includes: high correlation parameter and low correlation parameter.Specific analysis method is as follows:
S302-1 obtains the concentration of the tumor markers；
Blood serum tumor markers are mainly generated by the tumour cell of Healthy People, and detailed value is always in the normal range.But
In these malignant tumor patients especially patient with advanced cancer, the level of tumor markers is negatively correlated with life span.With
NSCLC high correlation parameter and the relevant primary tumor marker of decision data include cytokeratin (CYFRA21-1), cancer embryo
Antigen (CEA), the soluble fragments of cancer antigen (CA) -125, they have always been considered as being prognostic indicator, especially NSCLC's
Later stage.CYFRA21-1, CEA and (CA) -125 are set major parameter by us.
Table 2 reflects the normal range (NR) of three assessment parameters.Table 3 was shown according to the age between 35 to 78 years old
The parameter in each stage of NSCLC.We are by confirming that 48145 patient images carry out data over nearly 5 years at the center PET-CT
Statistics, all images are all from 1860 NSCLC patients.
Normal assessment parameter in 2 NSCLC of table
| Substance classes | Parameter |
| CYFRA-21-1(ug/mL) | 0-1.80 |
| CEA(ug/L) | 0-5.00 |
| CA-125(KU/L) | 0-35.00 |
Table 3 is carried out stage by stage by the assessment parameter in NSCLC (35-78 years old age)
Fig. 4 is the CYFRA-21-1 average data histogram of three patient in hospital over nearly 5 years.It may be seen that CYFRA-
The normal range (NR) of 21-1 is between 0 to 1.8.It is normal that NSCLC patient shows that the mean apparent of five sampling results is greater than, average super
Cross 35.CYFRA21-1 shows that the nearly 5 years NSCLC of patient are in abnormality.
Fig. 5 is the CEA average data histogram of three patient in hospital over nearly 5 years.It may be seen that the normal range (NR) of CEA
Between 0 to 5.0.It is normal that NSCLC patient shows that the mean apparent of 16 sampled results is greater than, average more than 80.CEA shows
NSCLC patient is in abnormality over nearly 5 years.
Fig. 6 is the CA-125 average data histogram of three patient in hospital over nearly 5 years.It may be seen that CA-125 is just
Normal range is between 0 to 35.0.5 sampled result mean apparents of NSCLC patient are all larger than normally, and average value is higher than CA-
125.CEA shows that NSCLC patient is in abnormality over nearly 5 years.
S302-2 obtains high correlation parameter R according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For age y tumor markers i it is flat
Equal concentration, αiFor weight,Altogether there are three types of tumor markers, n=3 respectively represents above-mentioned CYFRA21-1, CEA
(CA) -125.Therefore, the high correlation parameter also may indicate that are as follows:
Wherein 1,2,3 respectively indicate variety classes tumor markers.
S302-3 is obtained low according to the PTE scan image, CT scan image and non-small cell lung cancer cell antigen concentration
Relevance parameter RL(t)；
J is the project of the low correlation parameter, βjFor the factor to affect of each project, 0 < βj<1；T is the assessment time；
In the low correlation parameter, inspection item removes the concentrated area degree of correlation D of the above-mentioned PET scan image for including
It (r) further include the inspection item of some other conventional non-small cell lung cancers, such as non-small cell lung cancer antigen concentration, CT other than
The related data etc. of scanning.Item number j is up to 8, i.e. j≤8.
S302-4 obtains concentration degree of correlation D (t) according to the high correlation parameter and the low correlation parameter；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the factor to affect of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
According to the big data of collection, the high correlation parameter and carcinoma stage are closely coupled, as described in Figure 7, for big number
According to the high correlation parameter of display and the relation schematic diagram of carcinoma stage, facing for different phase high correlation parameter is shown in figure
Dividing value.We are given threshold ε, are shown according to big data, and in the present embodiment, ε=119 are cancer second stage and phase III
Critical value.It is divided into two kinds of situations according to the critical value:
Situation 1:RH (t) >=ε then assesses cancer development according to big data and is likely to be at phase III or fourth stage,
At this point, high correlation parameter accounts for the leading of assessment, low correlation parameter influences lower, α=1, β=0.At this point, D (t) can be direct
It indicates are as follows:
Situation 2:RH (t) < ε then assesses cancer development according to big data and is likely to be at first stage or second stage, this
When, high correlation parameter and low correlation parameter are affected to assessment result.At this point, D (t)=α × RH(t)+β×RL
(t)。
Therefore, the concentration dependence parameter is summarized as follows:
In the whole process, three assessment parameters with similar weighted factor, i.e. α i=dj=α k=1/ is arranged in we
3.Therefore, we can calculate the different parameters data assessment value of three patient in hospital.
Phase by calculating D (t) determines value, we may determine that patient is likely to be at a certain developing stage of NSCLC, when
Between the type of condition and decision-making technique facilitate assess status.From the above analysis, we can design a kind of algorithm to indicate
Whole process, the algorithm of algorithm and the concentration degree of correlation including the concentrated area degree of correlation.Specific algorithm content is as follows:
(1) algorithm of concentrated area degree of correlation D (r):
(2) algorithm of concentration degree of correlation D (t):
S40, according to the analysis as a result, generating assessment result.
In some embodiments, described to be analyzed according to described as a result, generation assessment result includes:
S402 obtains weighting function w (t) in the weight that assessment time t distributes the high correlation parameter；
S403 obtains the joint probability distribution P of multiple therapy methods combination according to the concentration degree of correlation decision contentw；
S404, according to the joint probability distribution PwExpected effects function is obtained with the w (t)
S405 obtains weighting function w (t+N) in the weight that assessment time t+N distributes the high correlation parameter；
S406, will be described in the w (t+N) substitutionIt obtains
If w (t) > w (t+N) exists, andDiagnosis then is able to carry out in time t and selects the w
It (t) is optimal weight function.
Before the joint probability distribution that setting multiple therapy methods combine, we first analyze the estimated assessment knot of drug k
Fruit, and the k is adjusted according to the estimated assessment result.
We use the parameter setting p (Tr (k)) of preceding k kind drug decision probability.P (Tr (k)) may be expressed as:
DNSL_par (t+1) is obtained after using drug k, and k is the major parameter of weight.We available
The Parameter Decision Making probability of one k method:
If p (Tr (k)) >=χ, after k, there is no effect due to NSCLC drug therapy or do not deteriorate,
The major parameter k of weight will not be reduced；
If 0≤ψ≤p (Tr (k))≤χ, after drug is using k, the parameter k of major weight declines；
If 0≤p (Tr (k))≤ψ, after k, the therapeutic effect of the major parameter as weight is apparent
, therefore do not need to take medicine or cut out drug k.
Wherein, χ and ψ is the threshold value being set according to actual conditions, this threshold value is equally calculated by big data and obtained, herein no longer
It repeats.
During treating NSCLC, a variety of pharmaceutical compositions are carried out to improve the Main Diagnosis parameter of NSCLC；Therefore, I
Can calculate the joint probability distributions of various treatment conditions:
We can assess different treatment method combinations by joint probability method, to improve NSCLC major parameter pair
The influence of patient.
We can calculate influence of the treatment method to assessment parameter.Utilize the information in data-gathering process, such as Tr
(1), (2) Tr ... Tr (k) drug collection, we can design D, i.e. training set.We are arranged in time t of optimal probability
Three kinds of assessment parameters.
W(t)≡P(DNSL_CYF(t)=α, DNSL_CEA(t)=β, DNSL_CA(t)=γ)
We set therapeutic choice after pharmaceutical composition probability
In each time t, patient is a medical scheme statistics, by calculating Pw (D) weight, in medical sequence of sets D
Three Evaluated effects in parameter.It is exactly:
T+1 next time, w (t+1) use probability for optimizing:
If t at any time, w (t) >=w (t+1) exists, and the processing combination in time t is imitated better than the t+1 time
It answers, then recommender system w (t) is used for this method.
If there is w (t) >=w (t+N), then after the N time for the treatment of method combination records, in treatment method combination
The current generation processing NSCLC effect of time t is optimal.
Meanwhile the excellent diagnostics time is selected by the assessment to D (t):
The embodiment of the invention also provides a kind of, and the non-small cell lung cancer based on big data assesses device, comprising:
Data acquisition module, for obtaining the characteristic of cancer patient；
Data preprocessing module, for being pre-processed to the characteristic；
Data analysis module obtains result for analyzing the pretreated data；
Assessment result generation module, for being analyzed according to described as a result, generating assessment result.
In some embodiments, the data analysis module includes:
Image collection module, for obtaining the lesion region PET scan image；
Area calculation module, for calculating the lesion region from the lesion region identified in the PET scan image
Area；Obtain the sum of the area of lesion region SNSCLC；
Areal analysis module, for calculating the area of the concentration lesion region in the lesion regionTo describedWith the SNSCLCRatio is sought, concentrated area degree of correlation D (r) is obtained；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
In some embodiments, the data analysis module further include:
Concentration obtains module, for obtaining the concentration of the tumor markers；
Parameter calculating module, for obtaining high correlation parameter R according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For crowd's tumor-marker that the age is y
The mean concentration of object i, αiFor weight,According to the PTE scan image, CT scan image and non-small cell
Lung carcinoma cell antigen concentration obtains low correlation parameter RL(t)；
J is the project of the low correlation parameter, βjFor the impact factor of each project, 0 < βj< 1；T is the assessment time；
Concentration degree of correlation D (t) is obtained according to the high correlation parameter and the low correlation parameter；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the influence coefficient of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
In some embodiments, the assessment result generation module further include:
Weight distribution module obtains weighting function w for distributing the weight of the high correlation parameter in assessment time t
(t)；The weight of the high correlation parameter is distributed in assessment time t+N, obtains weighting function w (t+N)；
Probability distribution computing module, for obtaining the connection of multiple therapy methods combination according to the concentration degree of correlation decision content
Close probability distribution Pw；
Assessment result obtains module, according to the joint probability distribution PwExpected effects function is obtained with the w (t)It will be described in the w (t+N) substitutionIt obtains
Weight parameter determining module, if w (t) > w (t+N) exists, andThen can time t into
Row diagnoses and selects w (t) for optimal weight function.
The electronic equipment for the non-small cell lung cancer assessment based on big data that the embodiment of the invention also provides a kind of, comprising:
Including memory, processor and store the computer program that can be run on a memory and on a processor.
The device of above-described embodiment for realizing method corresponding in previous embodiment there is corresponding method to implement
The beneficial effect of example, details are not described herein.
Assessment auxiliary system in small sample shows inaccuracy.Accuracy rate is only 55-60%.If without enough training
Data store in the database, then result will not assist the decision of doctor.In big data sample, training data can also increase
Add.When diagnostic data reaches 2000, accuracy has been increased to 70% or more.But this accuracy at a distance from doctor also very
Greatly.
Appraisal procedure and device are an auxiliary system, it cannot replace doctor and makes accuracy decision in NSCLC.
Even if we want system only judge ' have ' or ' or not.But we can reduce work using assessment system to assist a physician
Amount, while training data is continuously increased, accuracy is continuously improved.
Heretofore described appraisal procedure and device applies also for other classes in addition to being suitable for non-small cell lung cancer
The cancer of type, correspondingly, the equal adaptability such as the type and quantity of the related neoplasms marker and corresponding associated critical value
Variation.
It should be understood by those ordinary skilled in the art that: the discussion of any of the above embodiment is exemplary only, not
It is intended to imply that the scope of the present disclosure (including claim) is limited to these examples；Under thinking of the invention, above embodiments
Or can also be combined between the technical characteristic in different embodiments, step can be realized with random order, and be existed such as
Many other variations of the upper different aspect of the invention, for simplicity, they are not provided in details.
In addition, to simplify explanation and discussing, and in order not to obscure the invention, it can in provided attached drawing
It is connect with showing or can not show with the well known power ground of integrated circuit (IC) chip and other components.Furthermore, it is possible to
Device is shown in block diagram form, to avoid obscuring the invention, and this has also contemplated following facts, i.e., about this
The details of the embodiment of a little block diagram arrangements be height depend on will implementing platform of the invention (that is, these details should
It is completely within the scope of the understanding of those skilled in the art).Elaborating that detail (for example, circuit) is of the invention to describe
In the case where exemplary embodiment, it will be apparent to those skilled in the art that can be in these no details
In the case where or implement the present invention in the case that these details change.Therefore, these descriptions should be considered as explanation
Property rather than it is restrictive.
Although having been incorporated with specific embodiments of the present invention, invention has been described, according to retouching for front
It states, many replacements of these embodiments, modifications and variations will be apparent for those of ordinary skills.Example
Such as, discussed embodiment can be used in other memory architectures (for example, dynamic ram (DRAM)).
The embodiment of the present invention be intended to cover fall into all such replacements within the broad range of appended claims,
Modifications and variations.Therefore, all within the spirits and principles of the present invention, any omission, modification, equivalent replacement, the improvement made
Deng should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of non-small cell lung cancer appraisal procedure based on big data characterized by comprising
Obtain the characteristic of cancer patient；
The characteristic is pre-processed；
The pretreated data are analyzed, analysis result is obtained；
According to the analysis as a result, generating assessment result.
2. the non-small cell lung cancer appraisal procedure according to claim 1 based on big data, which is characterized in that the cancer
The characteristic of patient includes lesion region PET scan image, the concentration of tumor markers, CT scan image and non-small cell lung
Cancer cell antigen concentration；The tumor markers have at least one.
3. the non-small cell lung cancer appraisal procedure according to claim 1 based on big data, which is characterized in that described to institute
It states pretreated data and analyze and include:
Obtain the lesion region PET scan image；
It identifies the lesion region in the PET scan image, calculates the area of the lesion region；The lesion region has at least
At one；
Obtain the sum of the area of lesion region SNSCLC；
Calculate the area of the concentration lesion region in the lesion regionTo describedWith the SNSCLCRatio is sought,
Obtain concentrated area degree of correlation D (r)；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
4. the non-small cell lung cancer appraisal procedure according to claim 2 based on big data, which is characterized in that described to institute
Pretreated data are stated to be analyzed further include:
Obtain the concentration of the tumor markers；
High correlation parameter R is obtained according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For age y tumor markers i it is average dense
Degree, αiFor weight,
Low correlation parameter R is obtained according to the PTE scan image, CT scan image and non-small cell lung cancer cell antigen concentrationL
(t)；
J is the project of the low correlation parameter, βjFor the factor to affect of each project, 0 < βj<1；T is the assessment time；
Concentration degree of correlation D (t) is obtained according to the high correlation parameter and the low correlation parameter；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the factor to affect of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
5. the non-small cell lung cancer appraisal procedure according to claim 1 based on big data, which is characterized in that the basis
The analysis is as a result, generation assessment result includes:
The weight of the high correlation parameter is distributed in assessment time t, obtains weighting function w (t)；
The joint probability distribution P of multiple therapy methods combination is obtained according to the concentration degree of correlation decision contentw；
According to the joint probability distribution PwExpected effects function is obtained with the w (t)
The weight of the high correlation parameter is distributed in assessment time t+N, obtains weighting function w (t+N)；
It will be described in the w (t+N) substitutionIt obtains
If w (t) > w (t+N) exists, andThen time t be able to carry out diagnosis and select the w (t) for
Optimal weight function.
6. a kind of non-small cell lung cancer based on big data assesses device, comprising:
Data acquisition module, for obtaining the characteristic of cancer patient；
Data preprocessing module, for being pre-processed to the characteristic；
Data analysis module obtains result for analyzing the pretreated data；
Assessment result generation module, for being analyzed according to described as a result, generating assessment result.
7. the non-small cell lung cancer according to claim 6 based on big data assesses device, which is characterized in that the data
Analysis module includes:
Image collection module, for obtaining the lesion region PET scan image；
Area calculation module, for calculating the face of the lesion region from the lesion region identified in the PET scan image
Product；Obtain the sum of the area of lesion region SNSCLC；
Areal analysis module, for calculating the area of the concentration lesion region in the lesion regionTo described
With the SNSCLCRatio is sought, concentrated area degree of correlation D (r) is obtained；
For the equivalent redius for concentrating lesion region, i is equidistant scanning times.
8. the non-small cell lung cancer according to claim 7 based on big data assesses device, which is characterized in that the data
Analysis module further include:
Concentration obtains module, for obtaining the concentration of the tumor markers；
Parameter calculating module, for obtaining high correlation parameter R according to the tumor markers concentrationH(t)；
I is tumor-marker species, Ri(t) concentration for being i,For crowd's tumor markers i that the age is y
Mean concentration, αiFor weight,It is thin according to the PTE scan image, CT scan image and non-small cell lung cancer
Extracellular antigen concentration obtains low correlation parameter RL(t)；
J is the project of the low correlation parameter, βjFor the impact factor of each project, 0 < βj<1；T is the assessment time；According to institute
It states high correlation parameter and the low correlation parameter obtains concentration degree of correlation D (t)；
D (t)=α × RH(t)+β×RL(t)；
Wherein, α is the influence coefficient of the high correlation parameter, and β is the factor to affect of the low correlation coefficient.
9. the non-small cell lung cancer according to claim 8 based on big data assesses device, which is characterized in that the assessment
Result-generation module further include:
Weight distribution module obtains weighting function w (t) for distributing the weight of the high correlation parameter in assessment time t；
The weight of the high correlation parameter is distributed in assessment time t+N, obtains weighting function w (t+N)；
Probability distribution computing module, the joint for obtaining multiple therapy methods combination according to the concentration degree of correlation decision content are general
Rate is distributed Pw；
Assessment result obtains module, according to the joint probability distribution PwExpected effects function is obtained with the w (t)It will
Described in the w (t+N) substitutes intoIt obtains
Weight parameter determining module, if w (t) > w (t+N) exists, andIt can then be diagnosed in time t
And select w (t) for optimal weight function.
10. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the side as described in claim 1 to 5 any one when executing described program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910731727.XA CN110415820A (en) | 2019-08-08 | 2019-08-08 | Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910731727.XA CN110415820A (en) | 2019-08-08 | 2019-08-08 | Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110415820A true CN110415820A (en) | 2019-11-05 |
Family
ID=68366846
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910731727.XA Pending CN110415820A (en) | 2019-08-08 | 2019-08-08 | Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415820A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258511A (en) * | 2020-09-08 | 2021-01-22 | 广东省智能制造研究所 | Partial differential equation-based patient lung lesion prediction method and system |
| CN113838026A (en) * | 2021-09-22 | 2021-12-24 | 中南大学 | Non-small cell lung cancer detection method, non-small cell lung cancer detection device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070048750A1 (en) * | 2005-09-01 | 2007-03-01 | National Health Research Institute | Rapid efficacy assessment method for lung cancer therapy |
| CN105005714A (en) * | 2015-06-18 | 2015-10-28 | 中国科学院自动化研究所 | Non-small cell lung cancer prognosis method based on tumor phenotypic characteristics |
| CN109887600A (en) * | 2019-04-16 | 2019-06-14 | 上海理工大学 | A kind of analysis method of pair of non-small cell lung cancer prognosis Survival |
-
2019
- 2019-08-08 CN CN201910731727.XA patent/CN110415820A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070048750A1 (en) * | 2005-09-01 | 2007-03-01 | National Health Research Institute | Rapid efficacy assessment method for lung cancer therapy |
| CN105005714A (en) * | 2015-06-18 | 2015-10-28 | 中国科学院自动化研究所 | Non-small cell lung cancer prognosis method based on tumor phenotypic characteristics |
| CN109887600A (en) * | 2019-04-16 | 2019-06-14 | 上海理工大学 | A kind of analysis method of pair of non-small cell lung cancer prognosis Survival |
Non-Patent Citations (1)
| Title |
|---|
| JIAWU 等: "Decision based on big data research for non-small cell lung cancer in medical artificial system in developing country", 《COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112258511A (en) * | 2020-09-08 | 2021-01-22 | 广东省智能制造研究所 | Partial differential equation-based patient lung lesion prediction method and system |
| CN113838026A (en) * | 2021-09-22 | 2021-12-24 | 中南大学 | Non-small cell lung cancer detection method, non-small cell lung cancer detection device, computer equipment and storage medium |
| CN113838026B (en) * | 2021-09-22 | 2024-02-02 | 中南大学 | Non-small cell lung cancer detection method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5785184B2 (en) | Diagnostic techniques for continuous storage and integrated analysis of both medical and non-image medical data | |
| US7606405B2 (en) | Dynamic tumor diagnostic and treatment system | |
| JP2021002339A (en) | Method and system for machine learning classification based on structure or material segmentation in image | |
| US20130329973A1 (en) | Subvolume identification for prediction of treatment outcome | |
| CN109948667A (en) | Image classification method and device for the prediction of correct neck cancer far-end transfer | |
| CN110838114B (en) | Pulmonary nodule detection method, device and computer storage medium | |
| CN111340825A (en) | Method and system for generating mediastinal lymph node segmentation model | |
| CN110910342B (en) | Analysis of skeletal trauma by using deep learning | |
| CN110021022A (en) | A kind of thyroid gland nuclear medical image diagnostic method based on deep learning | |
| Fashandi et al. | An investigation of the effect of fat suppression and dimensionality on the accuracy of breast MRI segmentation using U‐nets | |
| CN114266729A (en) | Chest tumor radiotherapy-based radiation pneumonitis prediction method and system based on machine learning | |
| CN110415820A (en) | Non-small cell lung cancer appraisal procedure, device and electronic equipment based on big data | |
| Courot et al. | Automatic cervical lymphadenopathy segmentation from CT data using deep learning | |
| Gunasekaran | Leveraging object detection for the identification of lung cancer | |
| VK | An intelligent brain tumor segmentation using improved Deep Learning Model Based on Cascade Regression method | |
| US20240242338A1 (en) | Functional imaging features from computed tomography images | |
| Kumar et al. | Improved UNet deep learning model for automatic detection of lung cancer nodules | |
| Benbakreti et al. | Impact of the data augmentation on the detection of brain tumor from MRI images based on CNN and pretrained models | |
| CN103886580A (en) | Tumor image processing method | |
| de Azevedo Marques et al. | Content-based retrieval of medical images: landmarking, indexing, and relevance feedback | |
| CN115797308A (en) | DCE-MRI-based breast tumor segmentation method | |
| CN115331059A (en) | Spine three-column fracture classification and positioning system based on residual attention constraint mechanism | |
| Mohapatra et al. | Meta-Analysis of Transfer Learning for Segmentation of Brain Lesions | |
| JP7266349B1 (en) | In silico heart disease database utilization method, in silico heart disease database utilization program, and information processing device | |
| Ramakrishnan et al. | Development of Framework to Find Lung Canker Using GAN Technique |
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: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |