CN105701778A - Method of removing metal artifact from CT image - Google Patents
Method of removing metal artifact from CT image Download PDFInfo
- Publication number
- CN105701778A CN105701778A CN201610013374.6A CN201610013374A CN105701778A CN 105701778 A CN105701778 A CN 105701778A CN 201610013374 A CN201610013374 A CN 201610013374A CN 105701778 A CN105701778 A CN 105701778A
- Authority
- CN
- China
- Prior art keywords
- image
- projection
- projection domain
- picture
- described original
- 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
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 114
- 239000002184 metal Substances 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000001914 filtration Methods 0.000 claims abstract description 13
- 238000012937 correction Methods 0.000 claims description 50
- 210000004872 soft tissue Anatomy 0.000 claims description 34
- 238000001883 metal evaporation Methods 0.000 claims description 26
- 230000011218 segmentation Effects 0.000 claims description 26
- 210000001519 tissue Anatomy 0.000 claims description 24
- 238000003702 image correction Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 abstract description 2
- 238000007781 pre-processing Methods 0.000 abstract 1
- 239000007943 implant Substances 0.000 description 13
- 238000003709 image segmentation Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000008030 elimination Effects 0.000 description 7
- 238000003379 elimination reaction Methods 0.000 description 7
- 238000005481 NMR spectroscopy Methods 0.000 description 6
- 150000002739 metals Chemical class 0.000 description 6
- 238000012805 post-processing Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- 229910001069 Ti alloy Inorganic materials 0.000 description 2
- RTAQQCXQSZGOHL-UHFFFAOYSA-N Titanium Chemical compound [Ti] RTAQQCXQSZGOHL-UHFFFAOYSA-N 0.000 description 2
- 238000002558 medical inspection Methods 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 239000010936 titanium Substances 0.000 description 2
- 229910052719 titanium Inorganic materials 0.000 description 2
- 229910000640 Fe alloy Inorganic materials 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 229910045601 alloy Inorganic materials 0.000 description 1
- 239000000956 alloy Substances 0.000 description 1
- 210000003445 biliary tract Anatomy 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 210000003238 esophagus Anatomy 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229910052758 niobium Inorganic materials 0.000 description 1
- 239000010955 niobium Substances 0.000 description 1
- GUCVJGMIXFAOAE-UHFFFAOYSA-N niobium atom Chemical compound [Nb] GUCVJGMIXFAOAE-UHFFFAOYSA-N 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000005311 nuclear magnetism Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 210000002307 prostate Anatomy 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 210000003625 skull Anatomy 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- GOLXNESZZPUPJE-UHFFFAOYSA-N spiromesifen Chemical compound CC1=CC(C)=CC(C)=C1C(C(O1)=O)=C(OC(=O)CC(C)(C)C)C11CCCC1 GOLXNESZZPUPJE-UHFFFAOYSA-N 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000007631 vascular surgery Methods 0.000 description 1
Classifications
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a method of removing metal artifact from a CT image. The method comprises the steps of firstly carrying out the pre-processing via the image adaptive filtering to obtain an original reconstruction image from which the noise and a part of streak artifact are removed; then segmenting the original reconstruction image via a clustering method to obtain the areas of different tissues, establishing a model image, at the same time, carrying out the orthographic projection on a segmented metal area to obtain the position of the metal area in a projection domain; and then carrying out the orthographic projection on the model image to obtain the projection data of the model image, and then using the projection domain data of the model image to substitute for the projection domain data of the original reconstruction image according to the previously obtained position of the metal area in the projection domain; finally carrying out the filtering back projection on the repaired projection domain data to obtain a final corrected image. The method of the present invention reduces a real image accurately, enables the metal artifact to be removed effectively, and helps doctors to judge the states of illnesses accurately.
Description
Technical field
The present invention relates to the enhancing of CT image or recovery, be specifically related to a kind of method removing metal artifacts from CT image。
Background technology
Medically human body is repaired the history having more than 400 years by applied metal implant, time very early, doctor just repairs skull with proof gold plate and has a denture made, thereafter silver is employed successively, ferrum, ferrous alloys etc. fix fracture joint, employed again cobalt-base alloys modern age as body implant, rustless steel is also widely used subsequently, development along with rare metals industry, processing titanium and casting titanium, the rare metals such as niobium by clinical practice in human body, nowadays titanium alloy is due to its intensity height, good corrosion resistance, thermostability high and be reserved as the first-selection of body implant, it is widely used。
MRI is a kind of biological magnetic spin imaging technique, and it is the feature utilizing nuclear spin campaign, in externally-applied magnetic field, produces signal through radio-frequency pulse laser, detects with detector and input computer, shows image after computer disposal is changed on screen。
It is orthopaedics that nuclear magnetic resonance (MRI) checks, the especially effective tool of spinal surgery medical diagnosis on disease。
But when the human body that there is metal implant carries out having following two drawback when nuclear-magnetism checks:
1) due to the magnetic field very powerful at nuclear magnetic resonance, NMR machine and the existence of nuclear magnetic resonance check indoor, therefore, equipped with cardiac pacemaker person, and after vascular surgery, leave metal clip, metal rack person, or other coronary artery, esophagus, prostate, biliary tract carry out metal rack operator, definitely forbid to make nuclear magnetic resonance check, otherwise, owing to metal move by the attraction of strong magnetic field, it would be possible to generation serious consequence is so that life danger。
2) for the patient with metal implant, during inspection, in MRI image metal implant district, may occur in which a large amount of artifact, so that affecting diagnostic imaging performance。Adopting ferrum, rustless steel etc. as orthopaedics implant material, artifact is fairly obvious, the severe jamming quality of image。
Therefore the patient containing metal in some hospital formulary body does not do nuclear magnetic resonance check without exception, and especially internal metal implant is stainless but not the situation of titanium alloy。Just because of MRI in clinical practice drawback as above, CT has just had obvious advantage as another kind of medical inspection means。
CT has better application when there being metal implant in the patient than MRI as conventional medical inspection means, but owing to the reconstruct image of its scanning still can be had a certain impact by the existence of metal implant。The existence that typical situation is exactly metal object makes the image after rebuilding produce substantial amounts of black and bright radial-like streak artifact at metallic perimeter, can have a strong impact on doctor's judgement to checking result when metal implant is relatively larger。
The main following points of metal artifacts Producing reason: when the metal that density implanted in human body is bigger, due to the attenuation quotient that its attenuation quotient is far longer than in human body its hetero-organization, will weaken in a large number when ray is through metal, produce beam hardening phenomenon and cause that the first derivative of data for projection presents weak flatness at a certain section, produce the jump of data for projection, after processing after filtering, this weak flatness can be further magnified, and forms light and dark strip artifact thus final in rebuilding image。Simultaneously because X ray hardening problem, producing non-linear partial volume effect, and scattering phenomenon can be made to aggravate, these all can cause the distortion of reconstruct image, especially forms substantial amounts of interference at metallic perimeter。
In order to recover the reconstruct image polluted by metal artifacts, substantial amounts of metal artifacts elimination algorithm is suggested。Method currently mainly is segmented into following three classes: 1. carry out the elimination of metal artifacts with iterative reconstruction algorithm, 2. carries out the elimination of metal artifacts in projection domain。3. the elimination of metal artifacts is carried out at image area。
Iterative reconstruction algorithm is theoretically and extraordinary goes metal artifacts method, and this algorithm can effectively be removed metal artifacts and suppress noise, and can well present the structure of metal object, but its operand is very big, and speed is very slow, it is difficult to practical。Projection domain is removed metal artifacts and is a kind of method of pre-treatment and has certain advantage, because image area goes the post-processing approach of metal artifacts to need through backprojection algorithm such as FBP, this can strengthen the metal artifacts impact on truthful data, and the reconstruct image comprising metal artifacts is polluted in a large number due to it, carry out on this basis processing and will necessarily bring bigger error。But current main flow algorithm major part is also based on the post-processing algorithm of reconstruct image, reason mainly has following two aspects: 1. the post-processing approach based on reconstruct image does not need original raw data, the reconstruct image having only to DICOM format can complete the elimination of metal artifacts, and data acquisition is relatively easy。2. there are a lot of technological difficulties based on the pre-treating method of projection domain, first data for projection amount is very big, secondly projection domain is difficult to have accurate method metal part to be split from other people body portion, therefore but the data for projection that Exact recovery is contaminated with metals it is difficult to, so while carry out metal artifacts elimination from projection domain have its advantage its application the post-processing algorithm not as image area。
The image area post-processing approach of metal artifacts is broadly divided into following three classes: 1. the filtration combined weighted correction method 3. model correction method of interpolation correction method 2.。Interpolation correction method is most known method, its main thought is to go out, by the data for projection interpolation of metallic perimeter, the data for projection being contaminated with metals, obtain reconstruct image followed by filtered back projection, the reconstruct image that is finally added to by the metal parts of images being partitioned into again obtains final correction chart picture。The method is simple and practical, metal artifacts can there be is certain elimination effect, but due to it simply recovers the data for projection being contaminated with metals simply by interpolation method, do not consider the details of metal part, even and if select high-order interpolation function also to be difficult to the flatness ensureing data for projection at metal edge, finally need to be added to the metal parts of images being partitioned in final reconstruct image additionally, due to its algorithm, making can not have at the edge of metallic region well excessively, therefore interpolation correction method is unsatisfactory to the treatment effect of metal artifacts。Filtration combined weighted method be by multiple known go metal artifacts method (such as nmar etc.) correction after image carry out high pass and low-pass filtering treatment, then it is weighted merging, thus obtaining final correction chart picture, this algorithm can obtain certain effect, but comparing the basis relying on its utilization and remove artifact algorithm, actual effect is unsatisfactory。Model correction method is bearing calibration popular in recent years, its basic thought is better to reduce true picture by setting up model image, the data for projection of model image is substituted the part being contaminated with metals in Raw projection data, finally gives the reconstruct image not having metallic pollution。The method computation complexity is low, and retains the details of metal while the reasonable removal metal artifacts of energy, particularly in metal edge excessively naturally。The difficult point of the method is how to set up accurate model image to reduce real image, and this is also the fundamental difference place of different model correcting algorithm。
Model correction method has than the better accuracy of interpolation correction method and filtration combined weighted method and practicality, so the present invention is also based on model correction method and metal artifacts is removed。Model correction method is how to set up model image accurately at all, and this is the difficult point place distinguishing place this type of correction method especially of different model correction method。
More accurate model bearing calibration is proposed in order to enable effectively to remove the metal artifacts present invention, the method is set up in process at model image, the minutia of different tissues and the characteristic of metal object are taken into full account, not only fully apply the advantage of model correction method, more carry out improving and perfect to it according to actual clinical data, thus obtaining better metal artifacts removal effect。
Summary of the invention
It is an object of the invention to provide a kind of method removing metal artifacts from CT image, first pass through image adaptive filter and carry out pretreatment, obtain the original reconstructed image eliminating noise and part strip artifact；Original reconstructed image is split by the method then passing through cluster, obtains the region of different tissues, and sets up model image, by orthographic projection, the metallic region being partitioned into is obtained its position in projection domain simultaneously；Next by orthographic projection, model image being obtained its data for projection, the projection domain data of the metallic region that basis had previously obtained afterwards position model image in projection domain substitute the projection domain data of original reconstructed image；Finally the projection domain data after reparation are obtained final correction chart picture by filtered back projection。
It is an object of the invention to be realized by following technical proposals: a kind of method removing metal artifacts from CT image, the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
C, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The segmentation of D, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
E, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
F, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
The purpose of the present invention can also be realized by following technical proposals: a kind of method removing metal artifacts from CT image, and the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
C, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
D, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The segmentation of E, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
F, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
Further, described self-adaptive routing is median filtering method。
Further, described cluster segmentation algorithm is K-means cluster segmentation algorithm。
Further, described tissue regions also includes normal tissue。
The present invention compared with prior art has the advantage that
1, current model correction method is generally simply constructed model image, is left out the feature of metal implant and the position in human body, and simply simple threshold application method splits different tissue regions, the excessively simple inaccuracy of the model image of foundation。The present invention has taken into full account the metal implant issuable impact of different parts at human body, and for the clustering algorithm of different body part application self-adaptings, thus establishing more accurate model image, finally gives more accurate correction chart picture。
2, image is very effective on the whole eliminates bright band and the blanking bar that metal artifacts causes in the reconstruct that the present invention finally gives, and around metal, also no longer there is obvious hole, reduce true picture accurately, illustrate that metal artifacts can be effectively removed in the model image correction method improved, contribute to the doctor's accurate judgement to the state of an illness。
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail。
Accompanying drawing explanation
Fig. 1 is the flow chart of present pre-ferred embodiments；
Fig. 2 is CT image；
Fig. 3 is original reconstructed image；
Fig. 4 is original dendrogram picture；
Fig. 5 is weight map picture；
Fig. 6 revises dendrogram picture；
Fig. 7 is model image；
Tu8Shi metal shadowing area image；
Fig. 9 is the correction reconstruct image removing metal artifacts。
Detailed description of the invention
Referring to Fig. 1, a kind of method removing metal artifacts from CT image, the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；Present invention application medium filtering eliminates partial noise, however, it would be possible to use more complicated filtering method better eliminates noise。
Fig. 2 is CT original image, and CT original image is exactly that only form is likely to some difference (dicom etc.) not past eliminating the CT reconstruct image that metal artifacts 1 processes, may be substantially identical to the image of traditional sense。Fig. 3 is image after adaptive-filtering (owing to original image noise is only small so image and original image difference inconspicuous after pretreatment)。
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
Referring to Fig. 4, the image segmentation stage: sweep object substantially can be divided into metal (A) 2 according to the structure of human body, skeleton (B) 3, soft tissue (C) 4, the different tissue regions such as air (D) 5, along with the classification of the different segmentations at scanning position can also change, when such as scanning comprises the head of metal tooth, sweep object can be divided into metal (A), skeleton (B), four classes such as soft tissue (C) and air (D)；But when scanning the positions such as abdominal part, sweep object then can be divided into metal (A), skeleton (B), soft tissue (C1), five classes such as normal tissue (C2) and air (D), so can obtain finer segmentation, thus setting up finer model image。Different classification sums is primarily to can be finer accurate in the segmentation stage, but finally sweep object is divided into four classes----metal, skeleton, soft tissue and air (soft tissue and normal tissue are merged into a class) by us。Partitioning algorithm does not limit in principle, it is only necessary to obtain accurate segmentation result just passable, and the present invention selects K-means cluster segmentation algorithm。
Fig. 4 can be seen that, sweep object has been divided into four classes, colors corresponding different respectively。(noting the air section of metallic perimeter, actually should not exist)
I (i, j) for original segmentation image, I'(i, j) for the segmentation image after merging, when classification adds up to four,
I (i, j) and I'(i, j) identical, when classification adds up to five, I'(i, j) calculated by above formula and obtain。
C, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The common impact of metal artifacts is all near metallic region, more serious closer to metallic region artifact, so effectively judging that current pixel is extremely important by metal effect, this makes us can focus more on process, and those are affected big region by metal artifacts, this makes the more targeted of process on the one hand, can also reduce the error owing to correction brings on the other hand as far as possible。The present invention calculates weight by calculating the distance of different images position and the metallic region pixel of diverse location in composition picture of attaching most importance to, thus judging its size affected by metal artifacts。The standard of distance selects Euclidean distance (being not limited to Euclidean distance in principle), obtains the calculating apart from rear weight and is inversely proportional to distance, and namely after normalization, inside metallic region, weight is 1, more little further away from metallic region weight, until 0。
Fig. 5 can be seen that the position weight that brightness is more big is more high, namely from metallic region more close to。
Wherein, (i, j) for weight map picture, (i, is j) current location and metallic region institute Euclidean distance minima a little to D to W, and maxDistance is set in advance apart from maximum。
The segmentation of D, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
Referring to Fig. 6, the image segmentation correction stage: be all be implanted to inside of human body due to metal, so should be generally soft tissue 4 around metal 2, and metal artifacts can produce blanking bar at metallic perimeter, these blanking bars are probably assigned in air section 5 in the image segmentation stage by wrong, and this and general knowledge are not inconsistent, so we should assign it in soft tissue area 4 again。According to the weight map picture obtained before, it is possible to the image knowing which position easily is at metallic perimeter, so those very big for weight regions belonging to air can be modified to soft tissue area by us, thus obtaining more accurate image segmentation result。
Wherein Ic(i, j) for revised dendrogram picture, threshold is for being set in advance in the threshold value in [0,1] scope。
Concrete, it is exactly after original reconstructed image is split, image can be divided into four part (air, soft tissue, skeleton and metal), for being divided into the part of air section, if also (weighted value is in 0～1 scope very greatly for the weighted value of correspondence position in weight map picture, such as more than 0.9), then just this partial air region is divided into soft tissue area again, namely original dendrogram picture is modified。
Fig. 6 can be seen that revised segmentation image eliminates the hole near metallic region, obtains and splits image more accurately。
E, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
Model image establishment stage: after image segmentation, sweep object is divided into different parts, usually, the CT value of metal artifacts is closer to soft tissue area, so can be divided in the middle of soft tissue area, in order to reduce more real scanogram, when setting up model image, we carry out assignment for regional image again。Owing to metal artifacts major part is divided to soft tissue area, so being averaged by the image of soft tissue area, and it is reassigned to all of pixel。The numerical value in other regions is constant。Have benefited from We conducted the correction of image segmentation, obtain more accurate image segmentation result, it is possible to set up more accurate model image。
Wherein IM(i, j) for model image, CTavgCAverage for soft tissue area's CT value。
Fig. 7 can be seen that metal artifacts has been included in soft tissue area by the model image of foundation。
F, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
The stage is determined in position, metal shadowing territory: carrying out the image segmentation stage, we can obtain independent metallic region image, its projection domain data can be obtained further by orthographic projection, by judging which data is not zero, metallic region particular location (channel position under each visual angle) in projection domain data may finally be obtained。
Fig. 8 can be seen that the scope of metallic region in projection domain。
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
The projection domain correction stage based on model image: after obtaining model image, respectively original image and model image are carried out orthographic projection, obtain the projection domain data of correspondence, according to the metallic region determined before position in projection domain, Raw projection data is replaced, thus obtaining revised data for projection with the data for projection of model image。Replace in original image data for projection process at model image data for projection, so that more smooth thus the new artifact that do not induce one at metal edge, it is possible to use mean filter processes metal boundary data for projection。
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
After obtaining the data for projection revised, obtain final correction reconstruct image according to filter back-projection algorithm。
Wherein, PCK () is the corrected projection data of certain visual angle lower channel, POK () is the Raw projection data of corresponding visual angle lower channel, PMK () is the model projection data of corresponding visual angle lower channel, m, n represents the metal range boundary in respective channel data。
Fig. 9 can be seen that final correction chart picture is very effective on the whole and eliminates bright band and the blanking bar that metal artifacts causes, and around metal, also no longer there is obvious hole, reduce true picture accurately, illustrate that metal artifacts can be effectively removed in the model image correction method improved, contribute to the doctor's accurate judgement for the state of an illness。
In another embodiment, the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
C, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
D, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The segmentation of E, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
F, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
The content of the present embodiment is only the present invention preferably detailed description of the invention; but protection scope of the present invention is not limited thereto; any those familiar with the art is in the technical scope of present disclosure; the change that can readily occur in or replacement, all should be encompassed within protection scope of the present invention。Therefore, protection scope of the present invention should be as the criterion with the protection domain of claims。
Claims (8)
1. the method removing metal artifacts from CT image, it is characterised in that: the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
C, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The segmentation of D, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
E, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
F, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
2. the method removing metal artifacts from CT image according to claim 1, it is characterised in that: described self-adaptive routing is median filtering method。
3. the method removing metal artifacts from CT image according to claim 1, it is characterised in that: described cluster segmentation algorithm is K-means cluster segmentation algorithm。
4. the method removing metal artifacts from CT image according to claim 1, it is characterised in that: described tissue regions also includes normal tissue。
5. the method removing metal artifacts from CT image, it is characterised in that: the step of described removal metal artifacts includes:
A, Image semantic classification: use self-adaptive routing to remove the noise in CT image and part strip artifact, obtain original reconstructed image；
B, image are split: use cluster segmentation algorithm to split described original reconstructed image, obtain comprising the original dendrogram picture in different tissues region；Described tissue regions includes metallic region, bony areas, soft tissue area, air section；
C, determine the projection domain position of metallic region: the metallic region in described original dendrogram picture is carried out orthographic projection, obtain metal shadowing's area image, record the location of pixels being not zero in described metal shadowing area image, obtain described metallic region projection domain position in described metal shadowing area image；
D, set up weight map picture: calculate in described original dendrogram picture the distance between metallic region in diverse location and described original dendrogram picture, calculate the weighted value of this position pixel according to this distance, obtain weight map picture；Described weight map picture is made up of the weighted value of diverse location pixel；
The segmentation of E, image is revised: according to described weight map picture, air section big for the weighted value of pixel in described original dendrogram picture is modified to soft tissue area, obtains revising dendrogram picture；
F, set up model image: ask for the meansigma methods with all pixels of the soft tissue area corresponding region of described correction dendrogram picture in described original reconstructed image, and by this meansigma methods, all pixels of this corresponding region in described original reconstructed image are carried out assignment, obtain model image；
G, projection domain image based on model image correction original reconstructed image: respectively described original reconstructed image and described model image are carried out orthographic projection, obtain the projection domain image of described original reconstructed image and the projection domain image of described model image；According to described metallic region projection domain position in described metal shadowing area image, with in the projection domain image of described model image to should the projection domain data of projection domain position replace in the projection domain image of described original reconstructed image to should the projection domain data of projection domain position, obtain the correction projection domain image of described original reconstructed image；
H, the correction that the correction projection domain image of described original reconstructed image obtains removing metal artifacts by filtered back projection reconstruct image。
6. the method removing metal artifacts from CT image according to claim 5, it is characterised in that: described self-adaptive routing is median filtering method。
7. the method removing metal artifacts from CT image according to claim 5, it is characterised in that: described cluster segmentation algorithm is K-means cluster segmentation algorithm。
8. the method removing metal artifacts from CT image according to claim 5, it is characterised in that: described tissue regions also includes normal tissue。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610013374.6A CN105701778B (en) | 2016-01-11 | 2016-01-11 | A kind of method that metal artifacts are removed in the image from CT |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610013374.6A CN105701778B (en) | 2016-01-11 | 2016-01-11 | A kind of method that metal artifacts are removed in the image from CT |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105701778A true CN105701778A (en) | 2016-06-22 |
| CN105701778B CN105701778B (en) | 2018-04-20 |
Family
ID=56227036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610013374.6A Active CN105701778B (en) | 2016-01-11 | 2016-01-11 | A kind of method that metal artifacts are removed in the image from CT |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701778B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447631A (en) * | 2016-09-19 | 2017-02-22 | 深圳市贝斯达医疗股份有限公司 | Image processing method and device |
| CN106485287A (en) * | 2016-10-25 | 2017-03-08 | 帝麦克斯(苏州)医疗科技有限公司 | The acquisition methods of scanning area, the acquisition methods of digital slices and device |
| CN107316277A (en) * | 2017-04-24 | 2017-11-03 | 苏州动影信息科技有限公司 | Motion artifacts modification method in a kind of medical science pyramidal CT image |
| CN107978003A (en) * | 2017-10-30 | 2018-05-01 | 沈阳东软医疗系统有限公司 | A kind of processing method and processing device of CT image metal artifacts |
| CN108961176A (en) * | 2018-06-14 | 2018-12-07 | 中国科学院半导体研究所 | Range gating three-dimensional imaging is adaptive bilateral with reference to restorative procedure |
| CN109472754A (en) * | 2018-11-06 | 2019-03-15 | 电子科技大学 | CT image metal artifact removing method based on image repair |
| CN109859140A (en) * | 2019-02-15 | 2019-06-07 | 数坤（北京）网络科技有限公司 | A kind of restorative procedure and equipment for medical image |
| CN110097517A (en) * | 2019-04-28 | 2019-08-06 | 东软医疗系统股份有限公司 | Remove the method and device of image artifacts |
| CN111402150A (en) * | 2020-03-09 | 2020-07-10 | 北京灵医灵科技有限公司 | CT image metal artifact removing method and device |
| CN111815521A (en) * | 2020-05-27 | 2020-10-23 | 南京国科医工科技发展有限公司 | Cone beam CT metal artifact correction algorithm based on prior image |
| CN111803107A (en) * | 2020-08-06 | 2020-10-23 | 上海联影医疗科技有限公司 | Metal detection method, device, equipment and storage medium |
| CN113256542A (en) * | 2021-06-22 | 2021-08-13 | 明峰医疗系统股份有限公司 | Noise suppression method, system and medium for CT scanner |
| CN113520441A (en) * | 2021-08-03 | 2021-10-22 | 浙江大学 | Tissue imaging method and system for eliminating CT high-impedance artifact interference |
| CN113902824A (en) * | 2021-10-12 | 2022-01-07 | 哈尔滨工业大学 | Guide wire artifact removing method for intravascular optical coherence tomography |
| CN114983452A (en) * | 2022-05-11 | 2022-09-02 | 赛诺威盛科技(北京)股份有限公司 | CT spiral reconstruction image artifact removing method and device |
| CN116309923A (en) * | 2023-05-24 | 2023-06-23 | 吉林大学 | CT metal artifact eliminating method and system based on graph neural network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060285737A1 (en) * | 2005-06-17 | 2006-12-21 | Hamill James J | Image-based artifact reduction in PET/CT imaging |
| CN102376097A (en) * | 2010-08-25 | 2012-03-14 | 东软飞利浦医疗设备系统有限责任公司 | Computed tomography (CT) iteration reconstruction method for asymmetrical detector |
| CN102567958A (en) * | 2010-12-31 | 2012-07-11 | 东软飞利浦医疗设备系统有限责任公司 | Image postprocessing method for removing metal artifact from computed tomography (CT) image |
| CN103020928A (en) * | 2012-11-21 | 2013-04-03 | 深圳先进技术研究院 | Metal artifact correcting method of cone-beam CT (computed tomography) system |
| CN104504655A (en) * | 2014-12-04 | 2015-04-08 | 沈阳东软医疗系统有限公司 | CT (computer tomography) metal artifact processing method and device |
-
2016
- 2016-01-11 CN CN201610013374.6A patent/CN105701778B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060285737A1 (en) * | 2005-06-17 | 2006-12-21 | Hamill James J | Image-based artifact reduction in PET/CT imaging |
| CN102376097A (en) * | 2010-08-25 | 2012-03-14 | 东软飞利浦医疗设备系统有限责任公司 | Computed tomography (CT) iteration reconstruction method for asymmetrical detector |
| CN102567958A (en) * | 2010-12-31 | 2012-07-11 | 东软飞利浦医疗设备系统有限责任公司 | Image postprocessing method for removing metal artifact from computed tomography (CT) image |
| CN103020928A (en) * | 2012-11-21 | 2013-04-03 | 深圳先进技术研究院 | Metal artifact correcting method of cone-beam CT (computed tomography) system |
| CN104504655A (en) * | 2014-12-04 | 2015-04-08 | 沈阳东软医疗系统有限公司 | CT (computer tomography) metal artifact processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 洪虹: "CT中金属伪影的校正研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106447631B (en) * | 2016-09-19 | 2019-04-02 | 深圳市贝斯达医疗股份有限公司 | The processing method and processing device of image |
| CN106447631A (en) * | 2016-09-19 | 2017-02-22 | 深圳市贝斯达医疗股份有限公司 | Image processing method and device |
| CN106485287A (en) * | 2016-10-25 | 2017-03-08 | 帝麦克斯(苏州)医疗科技有限公司 | The acquisition methods of scanning area, the acquisition methods of digital slices and device |
| CN107316277B (en) * | 2017-04-24 | 2020-12-18 | 苏州动影信息科技有限公司 | Method for correcting motion artifact in medical cone beam CT image |
| CN107316277A (en) * | 2017-04-24 | 2017-11-03 | 苏州动影信息科技有限公司 | Motion artifacts modification method in a kind of medical science pyramidal CT image |
| CN107978003B (en) * | 2017-10-30 | 2021-03-30 | 东软医疗系统股份有限公司 | CT image metal artifact processing method and device |
| CN107978003A (en) * | 2017-10-30 | 2018-05-01 | 沈阳东软医疗系统有限公司 | A kind of processing method and processing device of CT image metal artifacts |
| CN108961176A (en) * | 2018-06-14 | 2018-12-07 | 中国科学院半导体研究所 | Range gating three-dimensional imaging is adaptive bilateral with reference to restorative procedure |
| CN108961176B (en) * | 2018-06-14 | 2021-08-03 | 中国科学院半导体研究所 | Self-adaptive bilateral reference restoration method for range-gated three-dimensional imaging |
| CN109472754A (en) * | 2018-11-06 | 2019-03-15 | 电子科技大学 | CT image metal artifact removing method based on image repair |
| CN109859140A (en) * | 2019-02-15 | 2019-06-07 | 数坤（北京）网络科技有限公司 | A kind of restorative procedure and equipment for medical image |
| CN110097517A (en) * | 2019-04-28 | 2019-08-06 | 东软医疗系统股份有限公司 | Remove the method and device of image artifacts |
| CN110097517B (en) * | 2019-04-28 | 2022-12-27 | 东软医疗系统股份有限公司 | Method and device for removing image artifacts |
| CN111402150A (en) * | 2020-03-09 | 2020-07-10 | 北京灵医灵科技有限公司 | CT image metal artifact removing method and device |
| CN111402150B (en) * | 2020-03-09 | 2023-07-28 | 北京灵医灵科技有限公司 | CT image metal artifact removal method and device |
| CN111815521A (en) * | 2020-05-27 | 2020-10-23 | 南京国科医工科技发展有限公司 | Cone beam CT metal artifact correction algorithm based on prior image |
| CN111815521B (en) * | 2020-05-27 | 2024-02-13 | 南京国科精准医学科技有限公司 | Cone beam CT metal artifact correction algorithm based on priori image |
| CN111803107A (en) * | 2020-08-06 | 2020-10-23 | 上海联影医疗科技有限公司 | Metal detection method, device, equipment and storage medium |
| CN111803107B (en) * | 2020-08-06 | 2023-09-12 | 上海联影医疗科技股份有限公司 | Metal detection method, device, equipment and storage medium |
| CN113256542A (en) * | 2021-06-22 | 2021-08-13 | 明峰医疗系统股份有限公司 | Noise suppression method, system and medium for CT scanner |
| CN113520441A (en) * | 2021-08-03 | 2021-10-22 | 浙江大学 | Tissue imaging method and system for eliminating CT high-impedance artifact interference |
| CN113902824A (en) * | 2021-10-12 | 2022-01-07 | 哈尔滨工业大学 | Guide wire artifact removing method for intravascular optical coherence tomography |
| CN113902824B (en) * | 2021-10-12 | 2022-10-28 | 哈尔滨工业大学 | Guide wire artifact removing method for intravascular optical coherence tomography |
| CN114983452A (en) * | 2022-05-11 | 2022-09-02 | 赛诺威盛科技(北京)股份有限公司 | CT spiral reconstruction image artifact removing method and device |
| CN116309923A (en) * | 2023-05-24 | 2023-06-23 | 吉林大学 | CT metal artifact eliminating method and system based on graph neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105701778B (en) | 2018-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701778A (en) | Method of removing metal artifact from CT image | |
| Kiraly et al. | Three-dimensional human airway segmentation methods for clinical virtual bronchoscopy | |
| Lell et al. | New techniques in CT angiography | |
| CN104036484B (en) | Image segmenting device, image partition method and medical image equipment | |
| US7330573B2 (en) | Visualization of medical images | |
| CN104899876B (en) | A kind of eye fundus image blood vessel segmentation method based on adaptive Gauss difference | |
| US20050244036A1 (en) | Method and apparatus for evaluating regional changes in three-dimensional tomographic images | |
| CN102024251B (en) | System and method for multi-image based virtual non-contrast image enhancement for dual source CT | |
| DE102012108185A1 (en) | System and method for visualization of blood vessel stenosis and navigation | |
| CN105640583A (en) | Angiography method | |
| CN112017131B (en) | CT image metal artifact removing method and device and computer readable storage medium | |
| Bullitt et al. | 3d graph description of the intracerebral vasculature from segmented mra and tests of accuracy by comparison with x-ray angiograms | |
| WO2022105623A1 (en) | Intracranial vascular focus recognition method based on transfer learning | |
| CN112950737A (en) | Fundus fluorescence radiography image generation method based on deep learning | |
| CN112950595A (en) | Human body part segmentation method and system based on SPECT imaging | |
| CN112562058B (en) | Method for quickly establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
| CN113222974B (en) | Automatic evaluation method and device for side branch circulation | |
| CN114170151A (en) | Intracranial vascular lesion identification method based on transfer learning | |
| Park et al. | MRI-based computed tomography metal artifact correction method for improving proton range calculation accuracy | |
| CN113361689A (en) | Training method of super-resolution reconstruction network model and scanning image processing method | |
| JP6705528B2 (en) | Medical image display processing method, medical image display processing apparatus and program | |
| Kohan et al. | The impact of orthopedic metal artifact reduction software on interreader variability when delineating areas of interest in the head and neck | |
| JP3488515B2 (en) | Diagnosis support system and diagnosis support method | |
| CN111862312B (en) | Brain blood vessel display device and method | |
| CN114170337A (en) | Method for establishing intracranial vascular enhancement three-dimensional model based on transfer learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method of removing metal artifact from CT image Effective date of registration: 20180813 Granted publication date: 20180420 Pledgee: Beijing Zhongguancun bank Limited by Share Ltd Pledgor: Sainuo via science and Technology (Beijing) Co. Ltd. Registration number: 2018110000019 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20200323 Granted publication date: 20180420 Pledgee: Beijing Zhongguancun bank Limited by Share Ltd Pledgor: SAINUO WEISHENG TECHNOLOGY (BEIJING) Co.,Ltd. Registration number: 2018110000019 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Method of removing metal artifact from CT image Effective date of registration: 20200323 Granted publication date: 20180420 Pledgee: Beijing Zhongguancun bank Limited by Share Ltd Pledgor: SAINUO WEISHENG TECHNOLOGY (BEIJING) Co.,Ltd. Registration number: Y2020990000200 |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 100176 1st floor, building 8, 11 Kangding street, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee after: Sinovision Technology (Beijing) Co.,Ltd. Address before: 100176 floor 1, Yuehong building, No.13, Yongchang North Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee before: SAINUO WEISHENG TECHNOLOGY (BEIJING) Co.,Ltd. |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20220406 Granted publication date: 20180420 Pledgee: Beijing Zhongguancun bank Limited by Share Ltd. Pledgor: SAINUO WEISHENG TECHNOLOGY (BEIJING) Co.,Ltd. Registration number: Y2020990000200 |