CN111292315A - Rapid registration algorithm for pathological section tissue area - Google Patents
Rapid registration algorithm for pathological section tissue area Download PDFInfo
- Publication number
- CN111292315A CN111292315A CN202010151108.6A CN202010151108A CN111292315A CN 111292315 A CN111292315 A CN 111292315A CN 202010151108 A CN202010151108 A CN 202010151108A CN 111292315 A CN111292315 A CN 111292315A
- Authority
- CN
- China
- Prior art keywords
- tissue region
- region map
- mutual information
- map
- algorithm
- 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
Images
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
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a pathological section tissue area rapid registration algorithm, which comprises the following steps: s100, acquiring a thumbnail a1 from the digital slice A1, and acquiring a thumbnail a2 from the digital slice A2; s200, segmenting a tissue region map b1 from a thumbnail a1, and segmenting a tissue region map b2 from a thumbnail a 2; s300, taking the tissue region map b1 as a template, taking mutual information measurement of the tissue region map b1 and the tissue region map b2 as an objective function, and searching an optimal transformation matrix from three dimensions of a rotation angle, scale transformation and turning over to enable the mutual information measurement of the tissue region map b1 and the transformed tissue region map b2 to be maximum, so that a coarse registration result c1 is obtained; s400, the tissue region map b1 is used as a template, the coarse registration result c1 is used as an initialization image, and similarity measurement in the tissue region map b1 and the coarse registration result c1 is optimized, so that the optimal solution can be converged quickly, and a fine registration result is obtained. The invention has better generalization capability of the registration process and higher registration efficiency.
Description
Technical Field
The invention relates to the technical field of image matching, in particular to a rapid registration algorithm for a pathological section tissue region.
Background
Clinically, a plurality of sections are taken from the same tissue by histological immunohistochemical staining of a pathology department, different staining agents are used for staining, and doctors perform registration in the brain and sea when reading the sections. This method is difficult to register effectively in the brain when the sections are too lightly stained, and the physician needs repeated comparisons to overlap the regions in the brain.
The currently available solution is to perform registration directly on the images taken on the digital scan slices, but rotation, flip, displacement and slight deformation conditions are usually present for different slices. The direct registration method is time consuming and cannot guarantee correct registration.
Disclosure of Invention
The invention aims to provide a rapid registration algorithm for a pathological section tissue region, which has better generalization capability of a registration process and higher registration efficiency.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
the invention discloses a pathological section tissue area rapid registration algorithm, which comprises the following steps:
s100, acquiring a thumbnail a1 from the digital slice A1, and acquiring a thumbnail a2 from the digital slice A2;
s200, segmenting a tissue region map b1 from a thumbnail a1, and segmenting a tissue region map b2 from a thumbnail a 2;
s300, taking the tissue region map b1 as a template, taking mutual information measurement of the tissue region map b1 and the tissue region map b2 as an objective function, and searching an optimal transformation matrix from three dimensions of a rotation angle, scale transformation and turning over to enable the mutual information measurement of the tissue region map b1 and the transformed tissue region map b2 to be maximum, so that a coarse registration result c1 is obtained;
s400, the tissue region map b1 is used as a template, the coarse registration result c1 is used as an initialization image, and similarity measurement in the tissue region map b1 and the coarse registration result c1 is optimized, so that the optimal solution can be converged quickly, and a fine registration result is obtained.
Preferably, in step S200, the segmentation algorithm includes a threshold segmentation algorithm, a region growing segmentation algorithm, and a segmentation algorithm based on deep learning.
Preferably, in step S300, the method for determining the optimal transformation matrix includes the following steps:
S3111and rotating the tissue region map b2 by the angle p to obtain a tissue region map b 2'1Comparison of tissue region map b 2'1And the tissue region map b1 to obtain a mutual information measure k1；
S3112And a tissue region map b 2'1Rotating the angle p to obtain a tissue region map b 2'2Comparison of tissue region map b 2'2And the tissue region map b1 to obtain a mutual information measure k2；
……
S311iAnd a tissue region map b 2'i-1Rotating the angle p to obtain a tissue region map b 2'iComparison of tissue region map b 2'iAnd the tissue region map b1 to obtain a mutual information measure ki；
……
S311nAnd a tissue region map b 2'n-1Rotating the angle p to obtain a tissue region map b 2'nComparison of tissue region map b 2'nAnd the tissue region map b1 to obtain a mutual information measure kn；
S312, measuring k from mutual information1Mutual information metric knIn the selected maximum mutual information measure kmaxDetermining the corresponding most suitable rotation angle, obtaining a tissue region map b2_1,
wherein 1 < i < n, n p 360 °.
Preferably, in step S300, the method for determining the optimal transformation matrix further includes the following steps:
S3211and converting the tissue region map b2_1 into magnification q to obtain a tissue region map b2_ 1'1Comparison of tissue region map b2_ 1'1And the tissue region map b1 are obtainedMutual information metric x1；
……
S321hAnd a tissue region map b2_ 1'h-1The magnification q was converted to obtain a tissue region map b2_ 1'hComparison of tissue region map b2_ 1'hAnd the tissue region map b1 to obtain a mutual information measure xh；
……
S321mAnd a tissue region map b2_ 1'm-1The magnification q was converted to obtain a tissue region map b2_ 1'mComparison of tissue region map b2_ 1'mAnd the tissue region map b1 to obtain a mutual information measure xm；
S322, measuring x from mutual information1Mutual information metric xmIn the selected maximum mutual information metric xmaxThen, the corresponding optimum conversion magnification is determined, and the tissue region map b2_2 is obtained.
Preferably, in step S300, the method for determining the optimal transformation matrix further includes the following steps:
s331, turning over the tissue region map b2_2 to obtain a tissue region map b2_2 ', comparing the tissue region map b2_ 2' with the tissue region map b1 to obtain a mutual information metric y, and comparing the mutual information metric y with a maximum mutual information metric xmaxAnd a corresponding coarse registration result c1 is obtained.
Preferably, the angle p for each rotation is 1 °.
Preferably, the magnification q per conversion is 0.05 times,
step S3211～S321mIn the tissue region map b2_1, the entire conversion magnification is from 0.8 times to 1.2 times.
Preferably, in step S300, the step of,
mutual information metric calculates the similarity of X and Y images by measuring the distance between the joint distribution p (X, Y) and the completely independent p (X) p (Y) correlation distribution, the calculation formula being:
preferably, in step S400, the similarity measure in the optimized tissue region map b1 and the coarse registration result c1 is an intensity-based image matching method.
Preferably, in step S400, the algorithm for optimizing the similarity measure in the tissue region map b1 and the coarse registration result c1 includes a gradient descent algorithm.
The invention has the beneficial effects that:
1. the invention solves the problem that the regions such as positive contrast and the like which are irrelevant to registration have influence on the result of the registration algorithm;
2. the invention solves the problems of long time consumption and difficult optimization of direct registration;
3. the invention has better generalization capability of the registration process and higher registration efficiency.
Drawings
FIG. 1 is a schematic illustration of a thumbnail a 1;
FIG. 2 is a schematic illustration of thumbnail a 2;
FIG. 3 is a schematic view of tissue region map b 1;
FIG. 4 is a schematic view of tissue region map b 2;
FIG. 5 is a flowchart illustrating the step S300;
fig. 6 is a schematic diagram of the coarse registration result c 1;
fig. 7 is an overlay display effect of the tissue region map b1 and the coarse registration result c 1;
fig. 8 is an overlapping display effect of the tissue region map b1 and the fine registration result in step S400.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings.
As shown in fig. 1 to 8, the present invention comprises the following steps:
s100, thumbnail acquisition:
acquiring a thumbnail a1 and a thumbnail a2 from a digital slice WSI to be registered;
s200, effective area segmentation:
dividing the effective regions in the thumbnail by using a division algorithm, wherein the division algorithm comprises traditional division algorithms such as threshold division and region growing and a division algorithm based on deep learning, the division algorithm is not limited to the traditional division algorithm, the division algorithm is used for dividing a tissue region map b1 from the thumbnail a1, and the division algorithm is used for dividing a tissue region map b2 from the thumbnail a 2;
s300, coarse image registration:
and (3) taking the tissue region map b1 as a template, taking the mutual information measurement of the tissue region map b1 and the tissue region map b2 as an objective function, and searching an optimal transformation matrix from three dimensions of rotation angle, scale transformation and whether turning over, so that the mutual information measurement of the tissue region map b1 and the transformed tissue region map b2 is maximum, and a coarse registration result is obtained.
When the method for searching the optimal transformation matrix is adopted, the mutual information quantity between the tissue region graph b2 and the tissue region graph b1 after the tissue region graph b2 is transformed by a rotation angle of 0-359 degrees is calculated, and the angle when the mutual information quantity is the maximum is taken as the rotation angle;
setting the current rotation angle as an initial quantity, calculating the mutual information quantity of each scale transformation between 0.8 and 1.2 by taking 0.05 times as the granularity, and taking the multiplying power when the maximum mutual information quantity is taken as the scale transformation quantity;
and finally comparing the mutual information quantity before and after mirror image turning, taking the maximum state as the optimal state, and calculating a transformation matrix by using the current rotation angle, the scale variation and whether turning is performed or not.
Wherein the mutual information metric calculates the similarity of the X and Y images by measuring the distance between the joint distribution p (X, Y) and the completely independent p (X) p (Y) correlation distribution by the formula:
s400, fine image registration:
by taking the tissue region map b1 as a template, taking the coarse registration result c1 as an initialization image, optimizing similarity measures in the tissue region map b1 and the coarse registration result c1 by using an optimization algorithm such as a gradient descent algorithm and the like, the optimal solution can be converged quickly to obtain a fine registration result,
the method adopted in the step is a classic intensity-based image matching method, details in the process are not in the patent protection range, and the method is only used as a loop in the whole process of the scheme.
The present invention is capable of other embodiments, and various changes and modifications may be made by one skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. A pathological section tissue region fast registration algorithm is characterized by comprising the following steps:
s100, acquiring a thumbnail a1 from the digital slice A1, and acquiring a thumbnail a2 from the digital slice A2;
s200, segmenting a tissue region map b1 from a thumbnail a1, and segmenting a tissue region map b2 from a thumbnail a 2;
s300, taking the tissue region map b1 as a template, taking mutual information measurement of the tissue region map b1 and the tissue region map b2 as an objective function, and searching an optimal transformation matrix from three dimensions of a rotation angle, scale transformation and turning over to enable the mutual information measurement of the tissue region map b1 and the transformed tissue region map b2 to be maximum, so that a coarse registration result c1 is obtained;
s400, the tissue region map b1 is used as a template, the coarse registration result c1 is used as an initialization image, and similarity measurement in the tissue region map b1 and the coarse registration result c1 is optimized, so that the optimal solution can be converged quickly, and a fine registration result is obtained.
2. The registration algorithm of claim 1, wherein: in step S200, the segmentation algorithm includes a threshold segmentation algorithm, a region growing segmentation algorithm, and a segmentation algorithm based on deep learning.
3. The registration algorithm of claim 1, wherein: in step S300, the method for determining the optimal transformation matrix includes the following steps:
S3111and rotating the tissue region map b2 by the angle p to obtain a tissue region map b 2'1Is toTissue comparison region map b 2'1And the tissue region map b1 to obtain a mutual information measure k1；
S3112And a tissue region map b 2'1Rotating the angle p to obtain a tissue region map b 2'2Comparison of tissue region map b 2'2And the tissue region map b1 to obtain a mutual information measure k2；
……
S311iAnd a tissue region map b 2'i-1Rotating the angle p to obtain a tissue region map b 2'iComparison of tissue region map b 2'iAnd the tissue region map b1 to obtain a mutual information measure ki；
……
S311nAnd a tissue region map b 2'n-1Rotating the angle p to obtain a tissue region map b 2'nComparison of tissue region map b 2'nAnd the tissue region map b1 to obtain a mutual information measure kn；
S312, measuring k from mutual information1Mutual information metric knIn the selected maximum mutual information measure kmaxDetermining the corresponding most suitable rotation angle, obtaining a tissue region map b2_1,
wherein 1 < i < n, n p 360 °.
4. The registration algorithm of claim 3, wherein: in step S300, the method for determining the optimal transformation matrix further includes the following steps:
S3211and converting the tissue region map b2_1 into magnification q to obtain a tissue region map b2_ 1'1Comparison of tissue region map b2_ 1'1And the tissue region map b1 to obtain a mutual information measure x1；
……
S321hAnd a tissue region map b2_ 1'h-1The magnification q was converted to obtain a tissue region map b2_ 1'hComparison of tissue region map b2_ 1'hAnd the tissue region map b1 to obtain a mutual information measure xh；
……
S321mTissue regionDomain map b2_ 1'm-1The magnification q was converted to obtain a tissue region map b2_ 1'mComparison of tissue region map b2_ 1'mAnd the tissue region map b1 to obtain a mutual information measure xm；
S322, measuring x from mutual information1Mutual information metric xmIn the selected maximum mutual information metric xmaxThen, the corresponding optimum conversion magnification is determined, and the tissue region map b2_2 is obtained.
5. The registration algorithm of claim 1, wherein: in step S300, the method for determining the optimal transformation matrix further includes the following steps:
s331, turning over the tissue region map b2_2 to obtain a tissue region map b2_2 ', comparing the tissue region map b2_ 2' with the tissue region map b1 to obtain a mutual information metric y, and comparing the mutual information metric y with a maximum mutual information metric xmaxAnd a corresponding coarse registration result c1 is obtained.
6. The registration algorithm of claim 3, wherein: the angle p of each rotation is 1 °.
7. The registration algorithm of claim 4, wherein: the multiplying power q of each transformation is 0.05 times,
step S3211～S321mIn the tissue region map b2_1, the entire conversion magnification is from 0.8 times to 1.2 times.
8. The registration algorithm according to any of claims 3-7, wherein: in the step S300, the process is performed,
mutual information metric calculates the similarity of X and Y images by measuring the distance between the joint distribution p (X, Y) and the completely independent p (X) p (Y) correlation distribution, the calculation formula being:
9. the registration algorithm of claim 1, wherein: in step S400, the similarity measure in the optimized tissue region map b1 and the coarse registration result c1 is an intensity-based image matching method.
10. The registration algorithm of claim 9, wherein: in step S400, the algorithm for optimizing the similarity measure in the tissue region map b1 and the coarse registration result c1 includes a gradient descent algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010151108.6A CN111292315A (en) | 2020-03-05 | 2020-03-05 | Rapid registration algorithm for pathological section tissue area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010151108.6A CN111292315A (en) | 2020-03-05 | 2020-03-05 | Rapid registration algorithm for pathological section tissue area |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111292315A true CN111292315A (en) | 2020-06-16 |
Family
ID=71030181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010151108.6A Pending CN111292315A (en) | 2020-03-05 | 2020-03-05 | Rapid registration algorithm for pathological section tissue area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111292315A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111751371A (en) * | 2020-06-24 | 2020-10-09 | 武汉中纪生物科技有限公司 | Immunohistochemical digital slide reading system and method |
| CN111768393A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111768394A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN112381838A (en) * | 2020-11-14 | 2021-02-19 | 四川大学华西医院 | Automatic image cutting method for digital pathological section image |
| CN115482181A (en) * | 2021-05-31 | 2022-12-16 | 数坤(北京)网络科技股份有限公司 | Image information extraction method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509114A (en) * | 2011-11-22 | 2012-06-20 | 李京娜 | Image registration method based on improved structural similarity |
| CN104050666A (en) * | 2014-06-10 | 2014-09-17 | 电子科技大学 | Brain MR image registration method based on division |
| CN106096616A (en) * | 2016-06-08 | 2016-11-09 | 四川大学华西医院 | A kind of nuclear magnetic resonance image feature extraction based on degree of depth study and sorting technique |
| CN106204415A (en) * | 2015-05-04 | 2016-12-07 | 南京邮电大学 | A kind of novel method for registering images |
| CN110473196A (en) * | 2019-08-14 | 2019-11-19 | 中南大学 | A kind of abdominal CT images target organ method for registering based on deep learning |
-
2020
- 2020-03-05 CN CN202010151108.6A patent/CN111292315A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102509114A (en) * | 2011-11-22 | 2012-06-20 | 李京娜 | Image registration method based on improved structural similarity |
| CN104050666A (en) * | 2014-06-10 | 2014-09-17 | 电子科技大学 | Brain MR image registration method based on division |
| CN106204415A (en) * | 2015-05-04 | 2016-12-07 | 南京邮电大学 | A kind of novel method for registering images |
| CN106096616A (en) * | 2016-06-08 | 2016-11-09 | 四川大学华西医院 | A kind of nuclear magnetic resonance image feature extraction based on degree of depth study and sorting technique |
| CN110473196A (en) * | 2019-08-14 | 2019-11-19 | 中南大学 | A kind of abdominal CT images target organ method for registering based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| HASHIMOTO N等: "《Multiple Tissue Blocks: Towards High-Resolution Whole-Organ 3D Histological Images》", 《PATHOBIOLOGY》 * |
| 汪婷: "《生物医学图像归一化及配准方法研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈杰 等: "《纤维支气管镜肺泡灌洗对支气管扩张合并感染患者治疗效果的影响》", 《医疗装备》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111751371A (en) * | 2020-06-24 | 2020-10-09 | 武汉中纪生物科技有限公司 | Immunohistochemical digital slide reading system and method |
| CN111751371B (en) * | 2020-06-24 | 2021-01-08 | 武汉中纪生物科技有限公司 | Immunohistochemical digital slide reading system and method |
| CN111768393A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111768394A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN112381838A (en) * | 2020-11-14 | 2021-02-19 | 四川大学华西医院 | Automatic image cutting method for digital pathological section image |
| CN112381838B (en) * | 2020-11-14 | 2022-04-19 | 四川大学华西医院 | Automatic image cutting method for digital pathological section image |
| CN115482181A (en) * | 2021-05-31 | 2022-12-16 | 数坤(北京)网络科技股份有限公司 | Image information extraction method and device, electronic equipment and readable storage medium |
| CN115482181B (en) * | 2021-05-31 | 2024-05-24 | 数坤(北京)网络科技股份有限公司 | Image information extraction method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111292315A (en) | Rapid registration algorithm for pathological section tissue area | |
| CN111798462B (en) | Automatic delineation method of nasopharyngeal carcinoma radiotherapy target area based on CT image | |
| CN110321920B (en) | Image classification method and device, computer readable storage medium and computer equipment | |
| CN110599528B (en) | Unsupervised three-dimensional medical image registration method and system based on neural network | |
| WO2021233021A1 (en) | Method for training image region segmentation model, and segmentation method and apparatus | |
| US7245766B2 (en) | Method and apparatus for determining a region in an image based on a user input | |
| CN109754396B (en) | Image registration method and device, computer equipment and storage medium | |
| WO2019000455A1 (en) | Method and system for segmenting image | |
| WO2020211530A1 (en) | Model training method and apparatus for detection on fundus image, method and apparatus for detection on fundus image, computer device, and medium | |
| CN113379764B (en) | Pathological image segmentation method based on domain antagonism self-supervision learning | |
| CN112215844A (en) | MRI (magnetic resonance imaging) multi-mode image segmentation method and system based on ACU-Net | |
| CN113177592B (en) | Image segmentation method and device, computer equipment and storage medium | |
| CN115423754A (en) | Image classification method, device, equipment and storage medium | |
| CN111709929A (en) | Lung canceration region segmentation and classification detection system | |
| Zhao et al. | Al-net: Attention learning network based on multi-task learning for cervical nucleus segmentation | |
| CN112614093A (en) | Breast pathology image classification method based on multi-scale space attention network | |
| CN115294086A (en) | Medical image segmentation method, segmentation model training method, medium, and electronic device | |
| CN110223331B (en) | Brain MR medical image registration method | |
| Ramella | Saliency-based segmentation of dermoscopic images using colour information | |
| CN112950684B (en) | Target feature extraction method, device, equipment and medium based on surface registration | |
| CN110288617B (en) | Automatic human body slice image segmentation method based on shared matting and ROI gradual change | |
| Wang et al. | Image registration based on maximization of gradient code mutual information | |
| CN111932575A (en) | Image segmentation method and system based on fuzzy C-means and probability label fusion | |
| WO2020140380A1 (en) | Method and device for quickly dividing optical coherence tomography image | |
| CN116468923A (en) | Image strengthening method and device based on weighted resampling clustering instability |
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: 20200616 |