CN108345871A - A kind of cervical carcinoma slice recognition methods - Google Patents
A kind of cervical carcinoma slice recognition methods Download PDFInfo
- Publication number
- CN108345871A CN108345871A CN201810230790.0A CN201810230790A CN108345871A CN 108345871 A CN108345871 A CN 108345871A CN 201810230790 A CN201810230790 A CN 201810230790A CN 108345871 A CN108345871 A CN 108345871A
- Authority
- CN
- China
- Prior art keywords
- cervical carcinoma
- identified
- cervical
- recognition methods
- identification model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of cervical carcinomas to be sliced recognition methods, wherein a cervical carcinoma identification model is formed according to the pre-prepd training sample for being associated with cervical carcinoma slice training in advance, it is further comprising the steps of：Obtain a pathological section image to be identified；The pathological section image is identified by the cervical carcinoma identification model, and exports recognition result；The recognition result includes quantity and the location of the cervical cancer cell in the pathological section image；Advantageous effect：Rapidly the doubtful cervical cancer cell in cervical carcinoma image can be positioned, effectively reduce redundancy, reduce the workload in identification process；Digital cervical carcinoma image can also be counted instead of traditional artificial visual type, indirect labor diagnoses process, greatly promotes Artificial Diagnosis efficiency.
Description
Technical field
The present invention relates to disease identification fields more particularly to a kind of cervical carcinoma to be sliced recognition methods.
Background technology
Cervical carcinoma is to lead to the most common malignant tumour of second of female patient death, and the annual new cases in the whole world are about
52.9800 ten thousand, death toll about 27.5100 ten thousand, 85% is happened at the opposite developing country lacked of medical resource.In order to alleviate
Medical resource lacks, and research team both domestic and external is dedicated to that recognizer is researched and developed to carry out automatic identification to cervical carcinoma.
Cervical carcinoma recognizer can carry out automatic identification to cervical carcinoma digital picture.Relative to Artificial Diagnosis, which knows
The accuracy rate of other cervical carcinoma can reach 90% or more, and whole process need not manually be intervened.
In full-automatic uterine neck scanning process, cervical carcinoma recognizer is a most important ring, to reducing the death rate, is saved
Medical treatment cost have important realistic meaning, huge economic and social benefit can be created.
Existing diagnosis of cervical cancer flow has problems in that cervical cancer cell quantity is more, manually identifies and not only takes consumption
Power, while being difficult accurately to be recorded.In addition, when cervical cancer cell distribution is scattered, it is easy to appear fail to judge for manual identified.
Invention content
In view of the above-mentioned problems, the present invention provides a kind of cervical carcinomas to be sliced recognition methods, wherein according to pre-prepd pass
The training sample training in advance for being coupled to cervical carcinoma slice forms a cervical carcinoma identification model, further comprising the steps of：
Step S1, a pathological section image to be identified is obtained；
Step S2, the pathological section image is identified by the cervical carcinoma identification model, and exports identification knot
Fruit；
The recognition result includes quantity and the location of the cervical cancer cell in the pathological section image.
Wherein, in the step S2, the pathological section image is identified by the cervical carcinoma identification model
Method specifically includes：
Step S21 obtains a break area to be identified in the pathological section image to be identified, and is cut described
Panel region is sent into as identification image in the cervical carcinoma identification model；
Step S22 extracts the palace in the identification image using the characteristic extracting module in the cervical carcinoma identification model
Neck cancer identification feature；
Step S23 knows the cervical carcinoma extracted using the tagsort module in the cervical carcinoma identification model
Other feature carries out tagsort, and output category result；
Step S24, according to the described of the cervical carcinoma identification feature and each cervical carcinoma identification feature extracted
The break area is identified in classification results, to obtain and export the corresponding recognition result.
Wherein, in the step S21, by way of the manual frame choosing of user in the pathological section image to be identified
It chooses and obtains the break area.
Wherein, the cervical carcinoma identification model is realized using SSD network structures.
Wherein, the characteristic extracting module in the cervical carcinoma identification model is by the sequentially connected feature extraction layer of multilayer
It constitutes；
In every layer of feature extraction layer, output image is 0.5*0.5 times of input picture.
Wherein, the characteristic extracting module is made of 10 layers of feature extraction layer.
Wherein, the characteristic extracting module by 10 layers the different feature extraction layer of totally 6 classes constitute；
Feature extraction layer is made of the different pond layer of the different convolutional layer of 5 classes and 2 classes described in per class.
Wherein, the tagsort module includes the convolution kernel of 2 tagsort networks.
Advantageous effect：Rapidly the doubtful cervical cancer cell in cervical carcinoma image can be positioned, effectively reduce redundancy
Information reduces the workload in identification process；It can also unite to digital cervical carcinoma image instead of traditional artificial visual type
Meter, indirect labor diagnose process, greatly promote Artificial Diagnosis efficiency.
Description of the drawings
The flow of cervical carcinoma slice recognition methods in a kind of cervical carcinoma slice recognition methods specific embodiment of Fig. 1 present invention
Figure；
By the cervical carcinoma identification model to institute in a kind of cervical carcinoma slice recognition methods specific embodiment of Fig. 2 present invention
State the particular flow sheet that pathological section image is identified；
Characteristic extracting module and feature extraction layer in a kind of Fig. 3 present invention cervical carcinoma slice recognition methods specific embodiment
Schematic diagram；
Characteristic extracting module and tagsort module in a kind of cervical carcinoma slice recognition methods specific embodiment of Fig. 4 present invention
Operation principle schematic diagram.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of not making creative work it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The invention will be further described in the following with reference to the drawings and specific embodiments, but not as limiting to the invention.
As shown in Figure 1, providing a kind of cervical carcinoma slice recognition methods, wherein be associated with cervical carcinoma according to pre-prepd
The training in advance of the training sample of slice forms a cervical carcinoma identification model, further comprising the steps of：
Step S1, a pathological section image to be identified is obtained；
Step S2, the pathological section image is identified by the cervical carcinoma identification model, and exports identification knot
Fruit；
The recognition result includes quantity and the location of the cervical cancer cell in the pathological section image.
Above-mentioned technical proposal can rapidly position the doubtful cervical cancer cell in cervical carcinoma image, effectively reduce superfluous
Remaining information reduces the workload in identification process；Digital cervical carcinoma image can also be carried out instead of traditional artificial visual type
Statistics, indirect labor diagnose process, greatly promote Artificial Diagnosis efficiency.
In a preferred embodiment, as shown in Fig. 2, in the step S2, pass through the cervical carcinoma identification model pair
The method that the pathological section image is identified specifically includes：
Step S21 obtains a break area to be identified in the pathological section image to be identified, and is cut described
Panel region is sent into as identification image in the cervical carcinoma identification model；
Step S22 extracts the palace in the identification image using the characteristic extracting module in the cervical carcinoma identification model
Neck cancer identification feature；
Step S23 knows the cervical carcinoma extracted using the tagsort module in the cervical carcinoma identification model
Other feature carries out tagsort, and output category result；
Step S24, according to the described of the cervical carcinoma identification feature and each cervical carcinoma identification feature extracted
The break area is identified in classification results, to obtain and export the corresponding recognition result.
It whether there is cervical cancer cell in identified pathological section specifically, being determined by characteristic extracting module.If depositing
The position of cervical cancer cell and quantity in pathological section are then being determined by tagsort module again.
Specifically, the quantity of convolution kernel is 4 in the characteristic extracting module, for extracting the minimum boundary where cell
Frame (BoundingBox).
In above-mentioned technical proposal, characteristic extracting module is with tagsort module using convolution mode of the same race with different number
Convolution kernel carries out convolution to characteristic pattern.
In a preferred embodiment, in the step S21, in institute to be identified by way of the manual frame choosing of user
It states and the break area is chosen and obtained in pathological section image.
In above-mentioned technical proposal, the completion pathological section that break area can be more efficient is obtained using the mode that manual frame selects
Identification process.
In a preferred embodiment, the cervical carcinoma identification model is realized using SSD network structures.
In a preferred embodiment, the characteristic extracting module in the cervical carcinoma identification model by multilayer successively
The feature extraction layer of connection is constituted；
In every layer of feature extraction layer, output image is 0.5*0.5 times of input picture.
As shown in figure 3, the characteristic extracting module (that is, feature extraction network in figure) is by 10 layers of different institute of totally 6 classes
State feature extraction layer composition；
Feature extraction layer is made of the different pond layer of the different convolutional layer of 5 classes and 2 classes described in per class.
In above-mentioned technical proposal, the convolutional layer has different convolution kernels, step-length and surrounding zero padding.
Specifically, the type of convolutional layer includes following five kinds：
Convolutional layer Type C A:Core size is 3 × 3, and step sizes are 1 × 1, and surrounding zero padding size is 1 × 1；
Convolutional layer Type C B:Core size is 3 × 3, and step sizes are 1 × 1, and surrounding zero padding size is 6 × 6；
Convolutional layer Type C C:Core size is 1 × 1, and step sizes are 1 × 1, and surrounding zero padding size is 0 × 0；
Convolutional layer Type C D:Core size is 3 × 3, and step sizes are 2 × 2, and surrounding zero padding size is 1 × 1；
Convolutional layer Type C E:Core size is 4 × 4, and step sizes are 1 × 1, and surrounding zero padding size is 1 × 1.
The type of pond layer includes:
Pond channel type PA:Core size is 2 × 2, and step sizes are 2 × 2, and surrounding zero padding size is 0 × 0, pond mode
For maximum pond；
Pond channel type PB:Core size is 3 × 3, and step sizes are 1 × 1, and surrounding zero padding size is 1 × 1, pond mode
For maximum pond.
In above-mentioned technical proposal, maximum pond refer to using the maximum value in selected areas as the pool area after value.
Preferably cervical cancer cell can be distinguished using this pond mode from background in this example, improve the accurate of identification
Rate.
The type of feature extraction layer includes following six kinds:
Feature extraction channel type FA:It is made of the convolutional layer of 2 a types and the pond layer of 1 a type；
Feature extraction channel type FB:It is made of the convolutional layer of 3 a types and the pond layer of 1 a type；
Feature extraction channel type FC:It is made of the convolutional layer of 3 a types and the pond layer of 1 b type；
Feature extraction channel type FD:By the convolutional layer of 1 b type, the convolution of the convolutional layer and 1 d type of 2 c types
Layer composition；
Feature extraction channel type FE:By the convolutional layer of 1 c type, the convolutional layer composition of 1 d type；
Feature extraction channel type FF:By the convolutional layer of 1 c type, the convolutional layer composition of 1 e type.
Characteristic extracting module includes：
The L1 layers of feature extraction layer for FA types, the quantity of convolution kernel are：(64,64)；
The quantity of the L2 layers of feature extraction layer for FA types, convolution kernel is (128,128)；
The L3 layers of feature extraction layer for FB types, the quantity of convolution kernel are：(256,256,256)；
The L4 layers of feature extraction layer for FB types, the quantity of convolution kernel are：(512,512,512)；
The L5 layers of feature extraction layer for FC types, the quantity of convolution kernel are：(512,512,512)；
The L6 layers of feature extraction layer for FD types, the quantity of convolution kernel are：(1024,1024,256,512,128,
256)；
The L7 layers of feature extraction layer for FE types, convolution nuclear volume are：(128,256)；
The L8 layers of feature extraction layer for FE types, convolution nuclear volume are：(128,256)；
The L9 layers of feature extraction layer for FF types, convolution nuclear volume are：(128,256).
Further, as shown in figure 4, the cell extraction layer in characteristic extracting module and tagsort mould cell in the block point
The input feature vector figure of class layer takes L5, L6, L7, and L8, L9 layers of output feature, convolution kernel size is 3*3, and the step-length of convolution kernel is
1*1, surrounding zero padding are 1*1.
In above-mentioned technical proposal, due to cervical cancer cell in reality minimum dimension be 128*128, L1 layers to L4 layers
Size it is also smaller than the minimum dimension of cervical cancer cell, therefore the identification of image is directly proceeded by from L5 layers.
In a preferred embodiment, the tagsort module includes the convolution kernel of 2 tagsort networks.
In above-mentioned technical proposal, the quantity of convolution kernel is the quantity of cervical cancer cell type in tagsort module.Due to
Cervical cancer cell only has two classes：Positive cell, non-positive cell, so in this example cervical carcinoma cell classification module convolution check figure
Amount is 2.
The foregoing is merely preferred embodiments of the present invention, are not intended to limit embodiments of the present invention and protection model
It encloses, to those skilled in the art, should can appreciate that all with made by description of the invention and diagramatic content
Equivalent replacement and obviously change obtained scheme, should all be included within the scope of the present invention.
Claims (8)
1. a kind of cervical carcinoma is sliced recognition methods, which is characterized in that according to the pre-prepd training for being associated with cervical carcinoma slice
Sample training in advance forms a cervical carcinoma identification model, further comprising the steps of：
Step S1, a pathological section image to be identified is obtained；
Step S2, the pathological section image is identified by the cervical carcinoma identification model, and exports recognition result；
The recognition result includes quantity and the location of the cervical cancer cell in the pathological section image.
2. cervical carcinoma according to claim 1 is sliced recognition methods, which is characterized in that in the step S2, by described
The method that the pathological section image is identified in cervical carcinoma identification model specifically includes：
Step S21 obtains a break area to be identified in the pathological section image to be identified, and by the slice area
Domain is sent into as identification image in the cervical carcinoma identification model；
Step S22 extracts the cervical carcinoma in the identification image using the characteristic extracting module in the cervical carcinoma identification model
Identification feature；
Step S23 identifies the cervical carcinoma extracted using the tagsort module in the cervical carcinoma identification model special
Sign carries out tagsort, and output category result；
Step S24, the classification according to the cervical carcinoma identification feature and each cervical carcinoma identification feature extracted
As a result, the break area is identified, to obtain and export the corresponding recognition result.
3. cervical carcinoma according to claim 2 is sliced recognition methods, which is characterized in that in the step S21, pass through user
The mode of manual frame choosing is chosen in the pathological section image to be identified and obtains the break area.
4. cervical carcinoma according to claim 2 is sliced recognition methods, which is characterized in that the cervical carcinoma identification model uses
SSD network structures are realized.
5. cervical carcinoma according to claim 4 is sliced recognition methods, which is characterized in that in the cervical carcinoma identification model
The characteristic extracting module is made of the sequentially connected feature extraction layer of multilayer；
In every layer of feature extraction layer, output image is 0.5*0.5 times of input picture.
6. cervical carcinoma according to claim 5 is sliced recognition methods, which is characterized in that the characteristic extracting module is by 10 layers
The feature extraction layer is constituted.
7. cervical carcinoma according to claim 6 is sliced recognition methods, which is characterized in that the characteristic extracting module is by 10 layers
The different feature extraction layer of totally 6 classes is constituted；
Feature extraction layer is made of the different pond layer of the different convolutional layer of 5 classes and 2 classes described in per class.
8. cervical carcinoma according to claim 2 is sliced recognition methods, which is characterized in that the tagsort module includes
The convolution kernel of 2 tagsort networks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810230790.0A CN108345871A (en) | 2018-03-20 | 2018-03-20 | A kind of cervical carcinoma slice recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810230790.0A CN108345871A (en) | 2018-03-20 | 2018-03-20 | A kind of cervical carcinoma slice recognition methods |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108345871A true CN108345871A (en) | 2018-07-31 |
Family
ID=62957441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810230790.0A Pending CN108345871A (en) | 2018-03-20 | 2018-03-20 | A kind of cervical carcinoma slice recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108345871A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210519A (en) * | 2019-05-10 | 2019-09-06 | 上海联影智能医疗科技有限公司 | Classification method, computer equipment and storage medium |
| CN110490840A (en) * | 2019-07-11 | 2019-11-22 | 平安科技（深圳）有限公司 | A kind of cell detection method, device and the equipment of glomerulus pathology sectioning image |
| WO2020034192A1 (en) * | 2018-08-17 | 2020-02-20 | 孙永年 | Biopsy or pap smear image processing method, computer apparatus, and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130071876A1 (en) * | 2011-05-03 | 2013-03-21 | NO. 128 Hospital of Hangzhou | Method for Utilizing Soft X-Ray Microimaging for Cancer Cell Image Recognition |
| CN105931226A (en) * | 2016-04-14 | 2016-09-07 | 南京信息工程大学 | Automatic cell detection and segmentation method based on deep learning and using adaptive ellipse fitting |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106780466A (en) * | 2016-12-21 | 2017-05-31 | 广西师范大学 | A kind of cervical cell image-recognizing method based on convolutional neural networks |
| CN107665492A (en) * | 2017-06-29 | 2018-02-06 | 南京信息工程大学 | Colon and rectum panorama numeral pathological image tissue segmentation methods based on depth network |
-
2018
- 2018-03-20 CN CN201810230790.0A patent/CN108345871A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130071876A1 (en) * | 2011-05-03 | 2013-03-21 | NO. 128 Hospital of Hangzhou | Method for Utilizing Soft X-Ray Microimaging for Cancer Cell Image Recognition |
| CN105931226A (en) * | 2016-04-14 | 2016-09-07 | 南京信息工程大学 | Automatic cell detection and segmentation method based on deep learning and using adaptive ellipse fitting |
| CN105975793A (en) * | 2016-05-23 | 2016-09-28 | 麦克奥迪（厦门）医疗诊断系统有限公司 | Auxiliary cancer diagnosis method based on digital pathological images |
| CN106780466A (en) * | 2016-12-21 | 2017-05-31 | 广西师范大学 | A kind of cervical cell image-recognizing method based on convolutional neural networks |
| CN107665492A (en) * | 2017-06-29 | 2018-02-06 | 南京信息工程大学 | Colon and rectum panorama numeral pathological image tissue segmentation methods based on depth network |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020034192A1 (en) * | 2018-08-17 | 2020-02-20 | 孙永年 | Biopsy or pap smear image processing method, computer apparatus, and system |
| CN110210519A (en) * | 2019-05-10 | 2019-09-06 | 上海联影智能医疗科技有限公司 | Classification method, computer equipment and storage medium |
| CN110210519B (en) * | 2019-05-10 | 2021-06-22 | 上海联影智能医疗科技有限公司 | Classification method, computer device, and storage medium |
| CN110490840A (en) * | 2019-07-11 | 2019-11-22 | 平安科技（深圳）有限公司 | A kind of cell detection method, device and the equipment of glomerulus pathology sectioning image |
| WO2021003821A1 (en) * | 2019-07-11 | 2021-01-14 | 平安科技（深圳）有限公司 | Cell detection method and apparatus for a glomerular pathological section image, and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107220980B (en) | A kind of MRI image brain tumor automatic division method based on full convolutional network | |
| CN107247971B (en) | Intelligent analysis method and system for ultrasonic thyroid nodule risk index | |
| CN108345871A (en) | A kind of cervical carcinoma slice recognition methods | |
| CN106202955A (en) | Diagnosis associated packets method and system based on intellectual coded adaptation | |
| CN109063710A (en) | Based on the pyramidal 3D CNN nasopharyngeal carcinoma dividing method of Analysis On Multi-scale Features | |
| CN107066934A (en) | Tumor stomach cell image recognition decision maker, method and tumor stomach section identification decision equipment | |
| CN108229379A (en) | Image-recognizing method, device, computer equipment and storage medium | |
| CN110097559A (en) | Eye fundus image focal area mask method based on deep learning | |
| CN110232383A (en) | A kind of lesion image recognition methods and lesion image identifying system based on deep learning model | |
| CN107578060A (en) | A kind of deep neural network based on discriminant region is used for the method for vegetable image classification | |
| CN110298383A (en) | Pathological classification method and system based on multi-modal deep learning | |
| CN108986115A (en) | Medical image cutting method, device and intelligent terminal | |
| CN106339984B (en) | Distributed image ultra-resolution method based on K mean value driving convolutional neural networks | |
| CN110502987A (en) | A kind of plant pest recognition methods and system based on deep learning | |
| CN108564026A (en) | Network establishing method and system for Thyroid Neoplasms smear image classification | |
| CN109359569A (en) | Erythrocyte image sub-classification method based on CNN | |
| CN108961274A (en) | Automatic H/N tumors dividing method in a kind of MRI image | |
| CN109102498A (en) | A kind of method of cluster type nucleus segmentation in cervical smear image | |
| CN110516817A (en) | A kind of model training data load method and device | |
| CN109063713A (en) | A kind of timber discrimination method and system based on the study of construction feature picture depth | |
| CN109636791A (en) | A kind of Citrus Huanglongbing pathogen detection method based on deep learning, apparatus and system | |
| CN108319977A (en) | Cervical biopsy area recognizing method based on the multi-modal network of channel information and device | |
| CN105808665A (en) | Novel hand-drawn sketch based image retrieval method | |
| CN110415815A (en) | The hereditary disease assistant diagnosis system of deep learning and face biological information | |
| CN109215040A (en) | A kind of tumor of breast dividing method based on multiple dimensioned weighting study |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180731 |