CN102567734A - Specific value based retina thin blood vessel segmentation method - Google Patents
Specific value based retina thin blood vessel segmentation method Download PDFInfo
- Publication number
- CN102567734A CN102567734A CN2012100004431A CN201210000443A CN102567734A CN 102567734 A CN102567734 A CN 102567734A CN 2012100004431 A CN2012100004431 A CN 2012100004431A CN 201210000443 A CN201210000443 A CN 201210000443A CN 102567734 A CN102567734 A CN 102567734A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- pixel
- result
- minute
- minute blood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses a specific value based retina thin blood vessel segmentation method, and mainly solves the problem that the present retina thin blood vessel segmentation method has poor effects in segmenting thin blood vessels. The method is realized through the following steps: (1) selecting a green component image of a retina image, calculating the directions and specific values for all pixel points in the image; (2) detecting the thin blood vessels for the result obtained through once segmentation, and calculating ratio features of the detected thin blood vessel pixel points, such as the mean value and the variance, so as to obtain weight values of all pixel points; (3) taking one segmentation result as a sample point, searching in the neighborhood of the sample point the pixel points with the weight values less than a specific threshold value, and adding the pixel values into the sample; and (4), repeating the step (3) until no confirming pixel point can be found in the neighborhood of the sample, so as to obtain a second segmentation result. According to the invention, the integrity of the segmentation is greatly improved after treatment, so that the method can be used for restoring thin blood vessels which are not segmented.
Description
Technical field
The invention belongs to technical field of image processing, relate to a kind of retina minute blood vessel dividing method, can be used for the retina minute blood vessel is cut apart based on ratio.
Background technology
Retinal vessel is cut apart an application as Flame Image Process, in clinical, is bringing into play more and more important effect.Retinal vessel is the unique blood vessel that uses the atraumatic means to observe directly at live body of human body; Many pink mans and metabolic disease all can make optical fundus blood vessel receive infringement in various degree; Organ generation pathologies relevant with blood vessel such as the heart, brain, kidney particularly, the change of optical fundus blood vessel can reflect the degree of pathology to a certain extent.Clinically, the retinal blood managed network is all significant to diagnosis, the treatment of diseases such as hypertension, diabetes, artery sclerosis, ephritis, the postevaluation of healing.In addition, retinal vessel is as the important biomolecule characteristic of human body, and its Stability Analysis of Structures is disguised strong, differentiates that in identity contour level has important application prospects aspect time safe and secret.Because the hardware condition restriction, retinal images shows following deficiency more significantly: uneven illumination is even; Blood vessel and background contrasts are not strong; Picture noise point is many.These problems will cause adopting image processing method commonly used to be difficult to be partitioned into gratifying effect.Simultaneously; Blood vessel changes from coarse to fine; Meanwhile the gray scale of background and contrast constantly weaken, and be very faint in blood vessel tip place's gray scale and contrast, and existing partitioning algorithm major part all is to adopt single threshold method; Cutting apart the major part as a result that obtains so all is the trunk of blood vessel, so all do not split for little blood vessel and the lower blood vessel of contrast.
Chinese journal of computers Vol.34; No.3; Mar.2011:574-582; A kind of " retina based on non-downsampling Contourlet conversion is cut apart " method is disclosed; Being the advantage that has good multiple dimensioned, multi-direction and translation invariance according to non-downsampling Contourlet conversion NSCT, having proposed a kind of retinal image segmentation method based on NSCT. this method at first through analyzing the coefficient response of NSCT transfer pair blood vessel, proposes the line feature extraction algorithm based on NSCT. and utilize gauss hybrid models GMM to carry out modeling to the proper vector of being extracted subsequently; And adopt the EM algorithm to estimate its parameter. adopt Bayes rule that blood vessel and non-blood vessel pixel are classified at last, to reach the purpose of image segmentation.
This method has all obtained result preferably on DRIVE and STARE retina database; Segmentation effect method than before promotes to some extent; But the segmentation effect at the more weak tiny retinal vessel place of contrast is still undesirable; This has just influenced the integrality of segmentation result greatly, brings difficulty for the automatic analysis and the diagnosis of retinal images.
Summary of the invention
The objective of the invention is to deficiency to above-mentioned prior art; Retina minute blood vessel dividing method based on ratio feature has been proposed; Further minute blood vessel is carried out secondary splitting on the segmentation result basis that obtains at said method; Make that the minute blood vessel segmentation result is more accurate, further improve segmentation effect.
Realize the technical scheme of the object of the invention, comprise the steps:
(1) to the original color retinal images of input, gets its green sub spirogram I
g, in size is 9 * 9 frame, calculate I respectively
gThe average m of the middle green component of pixel on 8 directions
iAnd variances sigma
i, according to this average m
iAnd variances sigma
iCalculate the direction r of current pixel point:
Wherein, m
sBe m
iMinimum value, s is m
sPairing direction, σ
tBe σ
iMinimum value, t is σ
tPairing direction, minimum value is got in the min representative, and standard deviation, Th are got in the std representative
1Be the threshold value that is provided with, value is 10;
(2), calculate the ratio feature c of current pixel point according to following formula according to the pixel direction r that obtains:
C wherein
1Be the green component average on the direction r of current pixel point place, c
2, c
3Be respectively the green component average of its place direction areas at both sides;
(3) retinal vessel of input after having carried out cutting apart for the first time figure v as a result, detect this retinal vessel as a result figure v belong to the pixel set of minute blood vessel, and calculate the average μ of its ratio feature
TAnd variances sigma
T
(4) calculate original color retinal images green sub spirogram I
gIn pixel belong to the weight w of minute blood vessel:
w=|c-μ
T|
In the formula, c is I
gThe ratio feature of middle pixel, Gaussian distribution of its approximate obedience, μ
TAverage for the ratio feature of minute blood vessel collection of pixels;
(5) belong to the weight w of minute blood vessel according to the pixel that calculates, with the retinal vessel after cutting apart for the first time as a result the blood vessel among the figure v find out in sample 3 * 3 neighborhoods all weight w that belong to minute blood vessel less than given threshold value Th as sample
2Pixel, and these pixels are labeled as sample, accomplish the renewal of sample, Th
2Value is σ
T, σ
TVariance for the ratio feature of minute blood vessel collection of pixels;
(6) weight w that belongs to minute blood vessel of repeating step (5) pixel in 3 * 3 neighborhoods of all samples is all greater than given threshold value Th
2, obtain new segmentation result v '.
The present invention has following advantage compared with prior art:
1. the present invention is through calculating pixel point direction r, for the ratio feature c of calculating pixel point provides foundation;
2. the present invention is owing to adopt ratio feature c as a kind of characteristic of describing retinal vessel, and the average μ of the ratio feature through calculating the minute blood vessel set
TAnd variances sigma
T, for the weight w that obtains pixel provides foundation;
3. the present invention passes through the weight w of calculating pixel point, and judges as foundation whether pixel is the point on the minute blood vessel with the weights that obtain, thereby accomplishes cutting apart of minute blood vessel, improves the segmentation effect of minute blood vessel.
Description of drawings
Fig. 1 is a process flow diagram of the present invention;
Fig. 2 is the 8 direction template synoptic diagram that the present invention uses;
Fig. 3 is the test retinal images that the present invention uses;
Fig. 4 is the segmentation result figure of the existing NSCT method of usefulness to Fig. 3;
Fig. 5 carries out secondary splitting figure as a result with the inventive method to figure.
Embodiment
With reference to Fig. 1, the present invention is based on the retina minute blood vessel dividing method of ratio, comprise the steps:
1a) input colored retinal images as shown in Figure 3, and get the dimension of second in its red, green, blue three-dimensional component component, as green sub spirogram I
g
1b) utilize 8 direction templates as shown in Figure 2, in a size is 9 * 9 frame, calculate green sub spirogram I respectively
gThe average m of the middle green component of pixel on 8 directions
iAnd variances sigma
i, these 8 directions are to be obtained through uniformly-spaced rotating counterclockwise by horizontal direction, each direction is used same numeral;
1c) utilize the direction r of following formula calculating pixel point:
Wherein, m
sBe m
iMinimum value, s is m
sPairing direction, σ
tBe σ
iMinimum value, t is σ
tPairing direction, minimum value is got in the min representative, and standard deviation, Th are got in the std representative
1Be the threshold value that is provided with, value is 10.
2a) the average c of the green component of calculating pixel point on direction r
1:
c
1=m
r
Wherein, m
rRemarked pixel point direction r goes up the average of green component;
2b) according to the average c of the green component on the direction r of the pixel that obtains
1, the ratio feature c of calculating pixel point:
Wherein, c
2, c
3Be respectively the green component average of pixel place direction areas at both sides.
3a) retinal vessel of as shown in Figure 4 the carrying out of input after cutting apart for the first time as a result figure v detect this retinal vessel minute blood vessel collection of pixels T among the figure v as a result, method is following:
The width h of definition blood vessel pixel is the continuous blood vessel pixel number on the normal direction of blood vessel pixel place direction;
The length l of definition blood vessel pixel is the continuous blood vessel pixel number on the direction of blood vessel pixel place;
If pixel satisfies simultaneously: the condition of h≤3 and l>=10, then this pixel is judged as the pixel on the minute blood vessel, will detect all qualified pixels and form a set, and should gather as minute blood vessel collection of pixels T;
3b) to detected minute blood vessel pixel set T, calculate the ratio feature average μ of all pixels in this set respectively
TAnd variances sigma
T
w=|c-μ
T|
Wherein, c is I
gThe ratio feature of middle pixel, Gaussian distribution of its approximate obedience, μ
TAverage for the minute blood vessel ratio feature.
Step 5 belongs to the weight w of minute blood vessel according to the pixel that calculates, with the retinal vessel after cutting apart for the first time as a result the blood vessel among the figure v find out in sample 3 * 3 neighborhoods all weight w that belong to minute blood vessel less than given threshold value Th as sample
2Pixel, and these pixels are labeled as sample, accomplish the renewal of sample, Th
2Value is σ
T, σ
TVariance for the ratio feature of minute blood vessel collection of pixels.
The weight w that step 6, repeating step (5) pixel in 3 * 3 neighborhoods of all samples belongs to minute blood vessel is all greater than given threshold value Th
2, obtain new segmentation result v ', i.e. the secondary splitting result.
Effect of the present invention can further confirm through following experiment:
One. experiment condition and content
Experiment condition: testing employed input picture is two width of cloth retinal images on the picked at random Drive database.The DRIVE database is retinal image data storehouse, a disclosed eyeground.It is made up of 40 full-color retinal images, and it is the symptom image that 5 width of cloth are wherein arranged, and has provided the manual segmentation result of expert of correspondence image.All eyeground retinal images are taken under 45 degree visible ranges by Cannon CR_5 type camera.Every width of cloth size of images is 768 * 584 pixels, and the viewing area is a circle that diameter is 540 pixels.All images is the full-color figure of tif form, does not pass through processed compressed, therefore helps subsequent treatment more.In addition, cut apart for the ease of exercising supervision, preceding 20 images in 40 width of cloth images as test set, are wherein contained 2 width of cloth symptom images, back 20 images are classified as training set, wherein contain 3 width of cloth symptom images, and have comprised 3 ophthalmologist, oculist's hand labeled figure.The training set signature is manually cut apart by an expert, and test set is then cut apart by two different observers, obtains set A and set B.In the set A, it is the blood vessel pixel that the observer has write down 577649 pixels, and 3960494 pixels are put pixel as a setting, and 12.7% pixel is divided into puncta vasculosa; Among the corresponding set B, 556532 pixels are marked as blood vessel, and 3981611 pixels are labeled as background, and 12.3% pixel is labeled as puncta vasculosa.Therefore, the result cut apart of two set is identical basically.In the supervision partitioning algorithm was estimated, set A was considered to correct segmentation result, and set B can be used as an observer and participates in accuracy relatively.
Experiment content: under above-mentioned experiment condition; Fig. 4 is carried out secondary splitting; Wherein Fig. 4 (a) is the figure as a result after utilizing the NSCT method once to cut apart to the original retinal images shown in Fig. 3 (a); Fig. 4 (b) is the figure as a result after utilizing the NSCT method once to cut apart to the original retinal images shown in 3 (b), the result after the secondary splitting such as Fig. 5.Wherein, Fig. 5 (a) carries out the result after the secondary splitting to Fig. 4 (a), and Fig. 5 (b) carries out the result after the secondary splitting to Fig. 4 (b).
Two. experimental result
Through the contrast of the result before and after the secondary splitting, can find out that it is better that minute blood vessel recovers, and improves a lot before the comparison process through after the present invention's processing.
With the evaluation index of integrity degree TF as segmentation effect, its computing method are to all images among Fig. 4, Fig. 5:
TF=TP/AP
TP is a number of cutting apart correct blood vessel pixel in the formula, and AP is cut apart the number of masterplate medium vessels pixel for expert's manual work.To pass through the percentage of head rice of the present invention before and after handling lists in table 1.
Result's contrast before and after table 1 is handled
Visible from table 1, have higher integrity degree through the segmentation result comparison NSCT method after the inventive method processing.The present invention's effect on minute blood vessel recovers is better, and the integrity degree of cutting apart after the processing improves a lot.
Claims (2)
1. the retina minute blood vessel dividing method based on ratio comprises the steps:
(1) to the original color retinal images of input, gets its green sub spirogram I
g, in size is 9 * 9 frame, calculate I respectively
gThe average m of the middle green component of pixel on 8 directions
iAnd variances sigma
i, according to this average m
iAnd variances sigma
iCalculate the direction r of current pixel point:
Wherein, m
sBe m
iMinimum value, s is m
sPairing direction, σ
tBe σ
iMinimum value, t is σ
tPairing direction, minimum value is got in the min representative, and standard deviation, Th are got in the std representative
1Be the threshold value that is provided with, value is 10;
(2), calculate the ratio feature c of current pixel point according to following formula according to the pixel direction r that obtains:
C wherein
1Be the green component average on the direction r of current pixel point place, c
2, c
3Be respectively the green component average of its place direction areas at both sides;
(3) retinal vessel of input after having carried out cutting apart for the first time figure v as a result, detect this retinal vessel as a result figure v belong to the pixel set of minute blood vessel, and calculate the average μ of its ratio feature
TAnd variances sigma
T
(4) calculate original color retinal images green sub spirogram I
gMiddle pixel belongs to the weight w of minute blood vessel:
w=|c-μ
T|
In the formula, c is I
gThe ratio feature of middle pixel, Gaussian distribution of its approximate obedience, μ
TAverage for the ratio feature of minute blood vessel collection of pixels;
(5) belong to the weight w of minute blood vessel according to the pixel that calculates, with the retinal vessel after cutting apart for the first time as a result the blood vessel among the figure v find out in sample 3 * 3 neighborhoods all weight w that belong to minute blood vessel less than given threshold value Th as sample
2Pixel, and these pixels are labeled as sample, accomplish the renewal of sample, Th
2Value is σ
T, σ
TVariance for the ratio feature of minute blood vessel collection of pixels;
(6) repeating step (5) pixel in 3 * 3 neighborhoods of all samples belong to minute blood vessel weight w all greater than given threshold value Th
2, obtain new segmentation result v '.
2. the retina minute blood vessel dividing method based on ratio according to claim 1, it is characterized in that this retinal vessel of the described detection of step (3) as a result figure v belong to the pixel set of minute blood vessel, be to obtain as follows:
The width h of definition blood vessel pixel is the continuous blood vessel pixel number on the normal direction of blood vessel pixel place direction;
The length l of definition blood vessel pixel is the continuous blood vessel pixel number on the direction of blood vessel pixel place;
If pixel satisfies simultaneously: the condition of h≤3 and l>=10 then is judged as the pixel on the minute blood vessel with this pixel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201210000443 CN102567734B (en) | 2012-01-02 | 2012-01-02 | Specific value based retina thin blood vessel segmentation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 201210000443 CN102567734B (en) | 2012-01-02 | 2012-01-02 | Specific value based retina thin blood vessel segmentation method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102567734A true CN102567734A (en) | 2012-07-11 |
CN102567734B CN102567734B (en) | 2013-06-12 |
Family
ID=46413107
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 201210000443 Expired - Fee Related CN102567734B (en) | 2012-01-02 | 2012-01-02 | Specific value based retina thin blood vessel segmentation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102567734B (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104182956A (en) * | 2013-05-21 | 2014-12-03 | 上海联影医疗科技有限公司 | Blood vessel extraction method |
CN104573717A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Manifold learning algorithm with monitoring |
CN104573714A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Self-adaptation parameter-free feature extraction method |
CN104809480A (en) * | 2015-05-21 | 2015-07-29 | 中南大学 | Retinal vessel segmentation method of fundus image based on classification and regression tree and AdaBoost |
CN107203741A (en) * | 2017-05-03 | 2017-09-26 | 上海联影医疗科技有限公司 | Vessel extraction method, device and its system |
CN109886973A (en) * | 2019-01-25 | 2019-06-14 | 杭州晟视科技有限公司 | A kind of vessel extraction method, apparatus and computer readable storage medium |
CN111789572A (en) * | 2019-04-04 | 2020-10-20 | 奥普托斯股份有限公司 | Determining hypertension levels from retinal vasculature images |
CN112309542A (en) * | 2020-07-27 | 2021-02-02 | 王艳 | Heart bypass mode selection system |
US11344273B2 (en) | 2016-06-30 | 2022-05-31 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for extracting blood vessel |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101520888A (en) * | 2008-02-27 | 2009-09-02 | 中国科学院自动化研究所 | Method for enhancing blood vessels in retinal images based on the directional field |
CN101667289A (en) * | 2008-11-19 | 2010-03-10 | 西安电子科技大学 | Retinal image segmentation method based on NSCT feature extraction and supervised classification |
US20100290005A1 (en) * | 2009-05-14 | 2010-11-18 | Topcon Medical Systems, Inc. | Circular Profile Mapping and Display of Retinal Parameters |
WO2010138645A2 (en) * | 2009-05-29 | 2010-12-02 | University Of Pittsburgh - Of The Commonwealth System Of Higher Education | Blood vessel segmentation with three-dimensional spectral domain optical coherence tomography |
-
2012
- 2012-01-02 CN CN 201210000443 patent/CN102567734B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101520888A (en) * | 2008-02-27 | 2009-09-02 | 中国科学院自动化研究所 | Method for enhancing blood vessels in retinal images based on the directional field |
CN101667289A (en) * | 2008-11-19 | 2010-03-10 | 西安电子科技大学 | Retinal image segmentation method based on NSCT feature extraction and supervised classification |
US20100290005A1 (en) * | 2009-05-14 | 2010-11-18 | Topcon Medical Systems, Inc. | Circular Profile Mapping and Display of Retinal Parameters |
WO2010138645A2 (en) * | 2009-05-29 | 2010-12-02 | University Of Pittsburgh - Of The Commonwealth System Of Higher Education | Blood vessel segmentation with three-dimensional spectral domain optical coherence tomography |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104182956B (en) * | 2013-05-21 | 2018-08-03 | 上海联影医疗科技有限公司 | A kind of vessel extraction method |
CN104182956A (en) * | 2013-05-21 | 2014-12-03 | 上海联影医疗科技有限公司 | Blood vessel extraction method |
CN104573717B (en) * | 2014-12-31 | 2018-03-09 | 南京理工大学 | There is the manifold learning arithmetic of supervision |
CN104573717A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Manifold learning algorithm with monitoring |
CN104573714A (en) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | Self-adaptation parameter-free feature extraction method |
CN104809480B (en) * | 2015-05-21 | 2018-06-19 | 中南大学 | A kind of eye fundus image Segmentation Method of Retinal Blood Vessels based on post-class processing and AdaBoost |
CN104809480A (en) * | 2015-05-21 | 2015-07-29 | 中南大学 | Retinal vessel segmentation method of fundus image based on classification and regression tree and AdaBoost |
US11344273B2 (en) | 2016-06-30 | 2022-05-31 | Shanghai United Imaging Healthcare Co., Ltd. | Methods and systems for extracting blood vessel |
CN107203741A (en) * | 2017-05-03 | 2017-09-26 | 上海联影医疗科技有限公司 | Vessel extraction method, device and its system |
CN109886973A (en) * | 2019-01-25 | 2019-06-14 | 杭州晟视科技有限公司 | A kind of vessel extraction method, apparatus and computer readable storage medium |
CN111789572A (en) * | 2019-04-04 | 2020-10-20 | 奥普托斯股份有限公司 | Determining hypertension levels from retinal vasculature images |
CN112309542A (en) * | 2020-07-27 | 2021-02-02 | 王艳 | Heart bypass mode selection system |
CN112309542B (en) * | 2020-07-27 | 2021-06-15 | 李星阳 | Heart bypass mode selection system |
Also Published As
Publication number | Publication date |
---|---|
CN102567734B (en) | 2013-06-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102567734B (en) | Specific value based retina thin blood vessel segmentation method | |
CN105513077B (en) | A kind of system for diabetic retinopathy screening | |
Wang et al. | Human visual system-based fundus image quality assessment of portable fundus camera photographs | |
Sivaswamy et al. | Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation | |
CN104809480B (en) | A kind of eye fundus image Segmentation Method of Retinal Blood Vessels based on post-class processing and AdaBoost | |
EP2888718B1 (en) | Methods and systems for automatic location of optic structures in an image of an eye, and for automatic retina cup-to-disc ratio computation | |
CN109858540B (en) | Medical image recognition system and method based on multi-mode fusion | |
CN107330449A (en) | A kind of BDR sign detection method and device | |
CN107408211A (en) | Method for distinguishing is known again for object | |
CN108765392B (en) | Digestive tract endoscope lesion detection and identification method based on sliding window | |
JP2019192215A (en) | 3d quantitative analysis of retinal layers with deep learning | |
CN112101424B (en) | Method, device and equipment for generating retinopathy identification model | |
CN109961848A (en) | Macula lutea image classification method and equipment | |
CN110533113A (en) | Branch's point detecting method of tree in a kind of digital picture | |
CN111797900B (en) | Artery and vein classification method and device for OCT-A image | |
CN114694236A (en) | Eyeball motion segmentation positioning method based on cyclic residual convolution neural network | |
Guo et al. | Emfn: Enhanced multi-feature fusion network for hard exudate detection in fundus images | |
Maqsood et al. | Detection of macula and recognition of aged-related macular degeneration in retinal fundus images | |
CN109241963A (en) | Blutpunkte intelligent identification Method in capsule gastroscope image based on Adaboost machine learning | |
CN106446805B (en) | A kind of eyeground shine in optic cup dividing method and system | |
Shaik et al. | Glaucoma identification based on segmentation and fusion techniques | |
CN111028230A (en) | Fundus image optic disc and macula lutea positioning detection algorithm based on YOLO-V3 | |
Kaur et al. | Automated detection and segmentation of exudates for the screening of background retinopathy | |
Yadav et al. | Automatic Cataract Severity Detection and Grading Using Deep Learning | |
CN110378333B (en) | SD-OCT image macular fovea center positioning method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130612 Termination date: 20190102 |
|
CF01 | Termination of patent right due to non-payment of annual fee |