CN109978790A - A kind of calcification artifact eliminating method, equipment and computer storage medium - Google Patents
A kind of calcification artifact eliminating method, equipment and computer storage medium Download PDFInfo
- Publication number
- CN109978790A CN109978790A CN201910234292.8A CN201910234292A CN109978790A CN 109978790 A CN109978790 A CN 109978790A CN 201910234292 A CN201910234292 A CN 201910234292A CN 109978790 A CN109978790 A CN 109978790A
- Authority
- CN
- China
- Prior art keywords
- image
- calcification
- original
- fringe region
- artifact
- 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
- 230000002308 calcification Effects 0.000 title claims abstract description 358
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 210000004204 blood vessel Anatomy 0.000 claims description 17
- 238000005259 measurement Methods 0.000 claims description 11
- 238000000638 solvent extraction Methods 0.000 claims description 8
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 6
- 229910052791 calcium Inorganic materials 0.000 claims description 6
- 239000011575 calcium Substances 0.000 claims description 6
- 238000010191 image analysis Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- 230000008030 elimination Effects 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a kind of calcification artifact eliminating method, equipment and computer storage mediums, comprising: obtains and handles primitive vessel image data, obtain original calcification image data；Clustering processing is carried out to the original calcification image data, obtains calcification centre area image and fringe region image；Area ratio analysis is carried out to both the fringe region image and the calcification centre area image, obtains area ratio analysis result；Result, which is analyzed, according to obtained area ratio determines that artifact corrects calcification image.The present invention is by carrying out first calcified regions image zooming-out to original image, after obtaining original calcification image data, clustering processing is carried out to this original calcification image data again, the calcification pixel and Image artifacts being further separated out in original calcification image data, and by after multiple Image Adjusting, the influence for preferably eliminating artifact has obtained more accurate artifact amendment calcification image, has been conducive to the accuracy for improving calcification calculated result.
Description
Technical field
The present invention relates to blood-vessel image technical field more particularly to a kind of calcification artifact eliminating methods, equipment and computer
Storage medium.
Background technique
In modern medical techniques field, narrow result computing technique is capable of the patient's condition knot of quickly output patient to coronary artery automatically
Fruit, it is very helpful for clinician, when automatic narrow calculating, an important problem be how to obtain it is accurately narrow
How narrow degree obtains accurate angiosteosis degree.
Since the calcification part of blood vessel can be by non-being always on of X-ray excitation when enhancing scanning, which can be peripheral vessels
Tissue also according to it is very bright, therefore bring calcification artifact, influence very much the judgement of calcification degree.General clinician can be by by meat
The judging result of eye carries out the method for reduction processing etc. to calculate practical calcification degree, but this method error is larger, is not suitable for
It is judged automatically in computer.Therefore, the impact effect for how preferably eliminating calcification artifact obtains more accurate calcification and calculates
As a result become urgent problem to be solved.
Summary of the invention
The embodiment of the present invention creatively provides a kind of calcification to effectively overcome drawbacks described above present in the prior art
Artifact eliminating method, equipment and computer storage medium.
One aspect of the present invention provides a kind of calcification artifact eliminating method, comprising: primitive vessel image data is obtained and handles,
Obtain original calcification image data；Clustering processing is carried out to the original calcification image data, obtains calcification centre area image
With fringe region image；Area ratio analysis is carried out to both the fringe region image and the calcification centre area image, is obtained
Result is analyzed to area ratio；Result, which is analyzed, according to obtained area ratio determines that artifact corrects calcification image.
In an embodiment, the processing primitive vessel image data, obtaining original calcification image data includes: pair
The primitive vessel image data carries out initial partitioning, obtains original calcified regions；To the original calcified regions and corresponding institute
It states primitive vessel image data and does dot product, obtain original calcification image data, wherein the primitive vessel image data is at least wrapped
Include one of following: image or blood vessel short axle CT image is straightened in blood vessel.
It is described that clustering processing is carried out to the original calcification image data in an embodiment, obtain calcification centre
Area image and fringe region image include: by the gray value of pixel and the pixel in the original calcification image data
The gray value of point and the difference of adjacent threshold gray value are weighted, and obtain between class distance measurement；According between class distance measurement pair
The original calcification image data carries out two mean cluster processing, obtains calcification centre area image and fringe region image.
It is described to determine that artifact corrects calcification image packet according to obtained area ratio analysis result in an embodiment
It includes:, will if the area ratio of the area of the fringe region image and the calcification centre area image is no more than given threshold
The calcification centre area image is determined as artifact amendment calcification image；If the area of the fringe region image and the calcification
The area ratio of central area image is more than given threshold, then according to the fringe region image and the calcification centre area image
Average gray difference value determine artifact correct calcification image.
In an embodiment, being averaged according to the fringe region image and the calcification centre area image
Gray scale difference value determines that artifact amendment calcification image includes: to judge the calcification centre area image and the fringe region image
Whether average gray difference value is more than setting difference；If the average ash of the calcification centre area image and the fringe region image
Spending difference is more than setting difference, then the calcification centre area image is determined as artifact amendment calcification image；If the calcification
The average gray difference value of central area image and the fringe region image is less than setting difference, then by the calcification centre area
The merging image of area image and the fringe region image is determined as artifact amendment calcification image.
Another aspect of the present invention provides a kind of calcification artifact elimination equipment, comprising: original image processing module, for obtaining
And primitive vessel image data is handled, obtain original calcification image data；Image clustering module, for the original calcification figure
As data progress clustering processing, calcification centre area image and fringe region image are obtained；Areal analysis module, for described
Both fringe region image and the calcification centre area image carry out area ratio analysis, obtain area ratio analysis result；Amendment
Determining module determines that artifact corrects calcification image for analyzing result according to obtained area ratio.
In an embodiment, the original image processing module includes: original image cutting unit, for described
Primitive vessel image data carries out initial partitioning, obtains original calcified regions；Image dot product unit, for the original calcification
Dot product is done with the corresponding primitive vessel image data in region, obtains original calcification image data, wherein the primitive vessel figure
As data are including at least one of following: image or blood vessel short axle CT image is straightened in blood vessel.
In an embodiment, described image cluster module includes: between class distance measure determining unit, and being used for will be described
The difference of the gray value of the gray value of pixel and the pixel and adjacent threshold gray value is added in original calcification image data
Power obtains between class distance measurement；Clustering processing unit, for being measured according to the between class distance to the original calcification picture number
According to two mean cluster processing are carried out, calcification centre area image and fringe region image are obtained.
In an embodiment, the amendment determining module includes: the first amending unit, if being used for the fringe region
The area ratio of the area of image and the calcification centre area image is no more than given threshold, then by the calcification centre administrative division map
As being determined as artifact amendment calcification image；Second amending unit, if area and the calcification for the fringe region image
The area ratio of central area image is more than given threshold, then according to the fringe region image and the calcification centre area image
Average gray difference value determine artifact correct calcification image.
In an embodiment, second amending unit includes: revise subelemen, for judging the calcification centre
Whether the average gray difference value of area image and the fringe region image is more than setting difference；If the calcification centre administrative division map
The average gray difference value of picture and the fringe region image is more than setting difference, then is determined as the calcification centre area image
Artifact corrects calcification image；If the average gray difference value of the calcification centre area image and the fringe region image is less than
Difference is set, then the merging image of the calcification centre area image and the fringe region image is determined as artifact amendment calcium
Change image.
Another aspect of the present invention provides a kind of computer readable storage medium, and the storage medium includes one group of computer can
It executes instruction, when executed for executing calcification artifact eliminating method described in any of the above embodiments.
The present invention is to overcome to eliminate calcification artifact effects in conventional method by being reduced, and causes to calculate practical calcification degree
When the larger problem of error, provide a kind of calcification artifact eliminating method.Firstly, primitive vessel image data is obtained and handles,
Original calcification image data is obtained, has just tentatively extracted the rough region image data of calcification image in this way.Then to extraction
Original calcification image data out carries out clustering processing, obtains calcification centre region and includes the fringe region figure of Image artifacts
Picture tentatively distinguishes calcification pixel in original calcification image data with Image artifacts point.Again to edge area image and calcium
Change both central area images and carry out area ratio analytical calculation, obtains area ratio analysis as a result, can judge fringe region figure
Whether the Image artifacts quantity ratio situation in calcification pixel quantity and calcification centre area image as in is reasonable.Last basis
Obtained area ratio analysis according to calcification pixel quantity and Image artifacts quantity ratio situation as a result, determine that artifact is corrected
Calcification image.The embodiment of the present invention obtains original calcification image by carrying out first calcified regions image zooming-out to original image
After data, then clustering processing, the calcium being further separated out in original calcification image data are carried out to this original calcification image data
Change pixel and Image artifacts, and by the influence of artifact preferably being eliminated, having been obtained more accurate after multiple Image Adjusting
Artifact corrects calcification image, is conducive to the accuracy for improving calcification calculated result.
Detailed description of the invention
The following detailed description is read with reference to the accompanying drawings, above-mentioned and other mesh of exemplary embodiment of the invention
, feature and advantage will become prone to understand.In the accompanying drawings, if showing by way of example rather than limitation of the invention
Dry embodiment, in which:
In the accompanying drawings, identical or corresponding label indicates identical or corresponding part.
Fig. 1 is a kind of implementation process schematic diagram of calcification artifact eliminating method of the embodiment of the present invention；
Fig. 2 is a kind of idiographic flow schematic diagram of calcification artifact eliminating method of the embodiment of the present invention；
Fig. 3 is the composed structure schematic diagram that a kind of calcification artifact of the embodiment of the present invention eliminates equipment.
Specific embodiment
To keep the purpose of the present invention, feature, advantage more obvious and understandable, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is only a part of the embodiment of the present invention, and not all embodiments.Based on the embodiments of the present invention, those skilled in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Fig. 1 is a kind of implementation process schematic diagram of calcification artifact eliminating method of the embodiment of the present invention；Fig. 2 is that the present invention is implemented
A kind of idiographic flow schematic diagram of calcification artifact eliminating method of example；Please refer to Fig. 1 and Fig. 2.
The embodiment of the present invention provides a kind of calcification artifact eliminating method, comprising:
Step 101, primitive vessel image data is obtained and handled, original calcification image data is obtained；
Step 102, clustering processing is carried out to original calcification image data, obtains calcification centre area image and fringe region
Image；
Step 103, area ratio analysis is carried out to both edge area image and calcification centre area image, obtains area ratio
Analyze result；
Step 104, result is analyzed according to obtained area ratio and determines that artifact corrects calcification image.
The present invention is to overcome to eliminate calcification artifact effects in conventional method by being reduced, and causes to calculate practical calcification degree
When the larger problem of error, provide a kind of calcification artifact eliminating method.Referring to FIG. 1, firstly, being obtained simultaneously by step 101
Primitive vessel image data is handled, original calcification image data is obtained, has just tentatively extracted the rough area of calcification image in this way
Area image data.Then clustering processing is carried out to the original calcification image data extracted by step 102, obtains calcification centre
Region and the fringe region image for including Image artifacts, tentatively by calcification pixel in original calcification image data and pseudo- image
Vegetarian refreshments distinguishes.Area ratio analysis meter is carried out to both edge area image and calcification centre area image by step 103 again
It calculates, obtains area ratio analysis as a result, can judge the calcification pixel quantity and calcification centre administrative division map in fringe region image
Whether the Image artifacts quantity ratio situation as in is reasonable.Analyzed finally by step 104 according to obtained area ratio as a result,
Determine that artifact corrects calcification image according to calcification pixel quantity and Image artifacts quantity ratio situation.The embodiment of the present invention is logical
It crosses and first calcified regions image zooming-out is carried out to original image, after obtaining original calcification image data, then to this original calcification figure
As data progress clustering processing, the calcification pixel being further separated out in original calcification image data and Image artifacts, and pass through
After multiple Image Adjusting, the influence of artifact is preferably eliminated, more accurate artifact amendment calcification image has been obtained, has been conducive to
Improve the accuracy of calcification calculated result.
In an embodiment, primitive vessel image data is handled, obtaining original calcification image data includes: to original
Blood-vessel image data carry out initial partitioning, obtain original calcified regions；To original calcified regions and corresponding primitive vessel picture number
According to dot product is done, original calcification image data is obtained, wherein primitive vessel image data includes at least one of following: figure is straightened in blood vessel
Picture or blood vessel short axle CT image.
The embodiment of the present invention is obtained by carrying out initial partitioning to primitive vessel image data with part calcification puppet shadow zone
Then original calcified regions are done dot product with corresponding primitive vessel image data by the original calcified regions in domain, obtaining can be in original
Beginning calcified regions show the original calcification image data of calcification artifacts data.Be conducive in this way to calcification artifact portion
The original calcification image data divided carries out advanced treating, and the calcification for obtaining more accurately eliminating calcification artifact effects effect calculates
As a result.
In an embodiment, clustering processing is carried out to original calcification image data, obtains calcification centre area image
It include: by the gray value of the gray value of pixel and pixel in original calcification image data and adjacent threshold with fringe region image
The difference of gray value is weighted, and obtains between class distance measurement；Original calcification image data is carried out according between class distance measurement
The processing of two mean clusters, obtains calcification centre area image and fringe region image.
Such as Fig. 2, the embodiment of the present invention passes through with the gray value of pixel in original calcification image data and pixel
The weighting of the difference of gray value and adjacent threshold gray value, the between class distance as K mean value (K-means) is measured, then according between class
Distance metric carries out two mean cluster processing to original calcification image data, so that calcification pixel and Image artifacts are carried out area
Point, and then obtain calcification centre area image and include the fringe region image of Image artifacts, has realized that eliminate calcification pseudo-
Shadow influences, and improves the effect of calcification calculated result accuracy.The present invention can be just by calcification and artifact by two mean clusters
Pixel separation is opened, and two kinds of cluster results are obtained, but it is also possible to be not limited to through two means clustering methods to original calcification figure
It, can be such as to set suitable cluster number K to K-means as data are clustered, K is more than or equal to 2, then to obtained K
Class result such as is adaptively adjusted, is merged at the operation, finally obtain mainly include calcification pixel calcification centre area image
It mainly include both of the fringe region image of Image artifacts as a result, calcification pixel and Image artifacts can be distinguished
It opens, is conducive to improve the precision to practical calcification calculated result.
In an embodiment, result is analyzed according to obtained area ratio and determines that artifact amendment calcification image includes:
If the area ratio of the area of fringe region image and calcification centre area image is no more than given threshold, by calcification centre region
Image is determined as artifact amendment calcification image；If the area of fringe region image and the area ratio of calcification centre area image are more than
Given threshold then determines that artifact corrects calcification figure according to the average gray difference value of fringe region image and calcification centre area image
Picture.
Such as Fig. 2, in the embodiment of the present invention, after obtaining calcification centre area image and fringe region image, to calcification centre
Whether the area ratio of area image and fringe region image is more than that given threshold is analyzed and determined, if the face of fringe region image
The long-pending area ratio with calcification centre area image is no more than given threshold, then illustrates that Image artifacts are being set with calcification pixel quantity ratio
Determine in threshold value, then, the main fringe region image comprising Image artifacts is given up, calcification centre area image is determined as puppet
Shadow amendment calcification image can eliminate artifact effects, improve the accuracy rate that calcification calculates.If the area and calcium of fringe region image
The area ratio for changing central area image is more than given threshold, then illustrates Image artifacts and calcification pixel quantity ratio not in given threshold
It is interior, directly the main fringe region image comprising Image artifacts can not be given up accordingly, then then according to fringe region and calcification
The average gray difference value of central area mentions to determine that artifact corrects calcification image to accurately eliminate to artifact effects
The accuracy of high calcification calculated result.
In an embodiment, determined according to the average gray difference value of fringe region image and calcification centre area image
Artifact amendment calcification image include: judge calcification centre area image and fringe region image average gray difference value whether be more than
Set difference；If the average gray difference value of calcification centre area image and fringe region image is more than setting difference, by calcification
Central area image is determined as artifact amendment calcification image；If the average gray of calcification centre area image and fringe region image
Difference is less than setting difference, then the merging image of calcification centre area image and fringe region image is determined as artifact amendment
Calcification image.
In the embodiment of the present invention, judge whether the average gray difference value of calcification centre area image and fringe region image sets
Determine difference, the Image artifacts quantity in the calcification pixel quantity and fringe region image in calcification centre area image can be reflected
Whether setting ratio is reached.Such as Fig. 2, if the average gray difference value of calcification centre area image and fringe region image is more than setting
Difference then illustrates that the calcification pixel quantity and the Image artifacts quantity in fringe region image in calcification centre area image reach
Setting ratio, thus can give up accordingly it is main include Image artifacts fringe region image, by calcification centre area image
It is determined as artifact amendment calcification image, improves the calculated result accuracy of practical calcification.If calcification centre area image and edge
The average gray difference value of area image is less than setting difference, then illustrate calcification pixel quantity in calcification centre area image with
Image artifacts quantity in fringe region image is not up to setting ratio, may include more calcification picture in fringe region image
Element, then, the merging image of calcification centre area image and fringe region image is determined as artifact amendment calcification image, ability
Accurate practical calcification image is obtained, the calculated result accuracy for improving practical calcification is conducive to.
Fig. 3 is the composed structure schematic diagram that a kind of calcification artifact of the embodiment of the present invention eliminates equipment.Please refer to Fig. 3.
Another aspect of the present invention provides a kind of calcification artifact elimination equipment, comprising:
Original image processing module 201 obtains original calcification picture number for obtaining and handling primitive vessel image data
According to；
Image clustering module 202 obtains calcification centre administrative division map for carrying out clustering processing to original calcification image data
Picture and fringe region image；
Areal analysis module 203, for carrying out area score to both edge area image and calcification centre area image
Analysis obtains area ratio analysis result；
Determining module 204 is corrected, determines that artifact corrects calcification image for analyzing result according to obtained area ratio.
The present invention is to overcome to eliminate calcification artifact effects in conventional method by being reduced, and causes to calculate practical calcification degree
When the larger problem of error, provide a kind of calcification artifact and eliminate equipment.Firstly, being obtained by original image processing module 201
And primitive vessel image data is handled, original calcification image data is obtained, has just tentatively extracted the rough of calcification image in this way
Region image data.Then clustering processing is carried out to the original calcification image data extracted by image clustering module 202, obtained
To calcification centre region and include Image artifacts fringe region image, tentatively by calcification pixel in original calcification image data
Point is distinguished with Image artifacts point.Again by areal analysis module 203 to edge area image and calcification centre area image two
Person carries out area ratio analytical calculation, obtains area ratio analysis as a result, can judge the calcification pixel number in fringe region image
Whether the Image artifacts quantity ratio situation in amount and calcification centre area image is reasonable.Finally by amendment determining module 204
It is analyzed according to obtained area ratio as a result, determining artifact according to calcification pixel quantity and Image artifacts quantity ratio situation
Correct calcification image.The embodiment of the present invention obtains original calcification by carrying out first calcified regions image zooming-out to original image
After image data, then clustering processing is carried out to this original calcification image data, is further separated out in original calcification image data
Calcification pixel and Image artifacts, and by preferably eliminating the influence of artifact, having obtained more smart after multiple Image Adjusting
Quasi- artifact corrects calcification image, is conducive to the accuracy for improving calcification calculated result.
In an embodiment, original image processing module 201 includes: original image cutting unit, for original
Blood-vessel image data carry out initial partitioning, obtain original calcified regions；Image dot product unit, for original calcified regions with it is right
It answers primitive vessel image data to do dot product, obtains original calcification image data, wherein primitive vessel image data includes at least such as
One of lower: image or blood vessel short axle CT image is straightened in blood vessel.
The embodiment of the present invention carries out initial partitioning to primitive vessel image data by original image cutting unit, obtains band
Have the original calcified regions of part calcification artifact region, then by image dot product unit by original calcified regions with it is corresponding original
Blood-vessel image data do dot product, obtain to show the original calcification images of calcification artifacts data in original calcified regions
Data.Be conducive to carry out advanced treating to the original calcification image data with calcification artifact sections in this way, it is more accurate to obtain
Elimination calcification artifact effects effect calcification calculated result.
In an embodiment, image clustering module 202 includes: between class distance measure determining unit, and being used for will be original
The gray value of the gray value of pixel and pixel and the difference of adjacent threshold gray value are weighted in calcification image data, are obtained
Between class distance measurement；Clustering processing unit, it is poly- for carrying out two mean values to original calcification image data according between class distance measurement
Class processing, obtains calcification centre area image and fringe region image.
The embodiment of the present invention passes through between class distance measure determining unit for the gray scale of pixel in original calcification image data
The weighting of the difference of the gray value and adjacent threshold gray value of value and pixel, the between class distance degree as K mean value (K-means)
Then amount is measured according between class distance by clustering processing unit and carries out two mean cluster processing to original calcification image data,
To distinguishing calcification pixel with Image artifacts, and then calcification centre area image is obtained and includes Image artifacts
Fringe region image realizes and eliminates calcification artifact effects, improves the effect of calcification calculated result accuracy.The embodiment of the present invention
In clustering processing unit calcification and Image artifacts can be separated just by two mean clusters, obtain two kinds of clusters knot
Fruit, but it is also possible to be not limited to cluster original calcification image data by two means clustering methods, it can be such as to K-
Then means setting suitable cluster number K, K are adaptively adjusted obtained K class result more than or equal to 2, are merged
Deng operation, finally obtain mainly include the calcification centre area image of calcification pixel and mainly include Image artifacts edge
Both of area image are conducive to improve and calculate practical calcification as a result, can distinguish calcification pixel with Image artifacts
As a result precision.
In an embodiment, amendment determining module 204 includes: the first amending unit, if being used for fringe region image
Area and calcification centre area image area ratio be no more than given threshold, then calcification centre area image is determined as artifact
Correct calcification image；Second amending unit, if for the area of fringe region image and the area ratio of calcification centre area image
More than given threshold, then determine that artifact corrects calcium according to the average gray difference value of fringe region image and calcification centre area image
Change image.
In the embodiment of the present invention, after obtaining calcification centre area image and fringe region image, by calcification centre area
Whether the area ratio of area image and fringe region image is more than that given threshold is analyzed and determined, if the area of fringe region image
It is no more than given threshold with the area ratio of calcification centre area image, then illustrates that Image artifacts are being set with calcification pixel quantity ratio
In threshold value, then, the main fringe region image comprising Image artifacts is given up by the first amending unit, by calcification centre area
Area image, which is determined as artifact amendment calcification image, can eliminate artifact effects, improve the accuracy rate that calcification calculates.If fringe region
The area of image and the area ratio of calcification centre area image are more than given threshold, then illustrate Image artifacts and calcification pixel quantity
Than that directly the main fringe region image comprising Image artifacts can not be given up accordingly, then then passing through not in given threshold
Second amending unit determines that artifact corrects calcification image according to fringe region and the average gray difference value in calcification centre region, from
And accurately artifact effects are eliminated, improve the accuracy of calcification calculated result.
In an embodiment, the second amending unit includes: revise subelemen, for judging calcification centre area image
Whether the average gray difference value with fringe region image is more than setting difference；If calcification centre area image and fringe region image
Average gray difference value be more than setting difference, then by calcification centre area image be determined as artifact amendment calcification image；If calcification
The average gray difference value of central area image and fringe region image is less than setting difference, then by calcification centre area image and
The merging image of fringe region image is determined as artifact amendment calcification image.
In the embodiment of the present invention, being averaged for calcification centre area image and fringe region image is judged by revise subelemen
Whether gray scale difference value sets difference, can reflect in the calcification pixel quantity and fringe region image in calcification centre area image
Image artifacts quantity whether reach setting ratio.If the average gray difference value of calcification centre area image and fringe region image
More than setting difference, then illustrate the Image artifacts in the calcification pixel quantity and fringe region image in calcification centre area image
Quantity has reached setting ratio, therefore can give up the main fringe region image comprising Image artifacts accordingly, by calcification centre
Area image is determined as artifact amendment calcification image, improves the calculated result accuracy of practical calcification.If calcification centre administrative division map
The average gray difference value of picture and fringe region image is less than setting difference, then illustrates the calcification picture in calcification centre area image
Image artifacts quantity in prime number amount and fringe region image is not up to setting ratio, may include in fringe region image compared with
More calcification pixels, then, the merging image of calcification centre area image and fringe region image is determined as artifact amendment calcification
Image can just obtain accurate practical calcification image, be conducive to the calculated result accuracy for improving practical calcification.
Another aspect of the present invention provides a kind of computer readable storage medium, and storage medium includes that one group of computer is executable
Instruction, when executed for executing the calcification artifact eliminating method of any of the above-described.
The present invention is to overcome to eliminate calcification artifact effects in conventional method by being reduced, and causes to calculate practical calcification degree
When the larger problem of error, provide a kind of computer readable storage medium, storage medium, which includes that one group of computer is executable, to be referred to
It enables, when executed for executing following calcification artifact eliminating method: firstly, by obtaining and handling primitive vessel image
Data obtain original calcification image data, have just tentatively extracted the rough region image data of calcification image in this way.Then right
The original calcification image data that extracts carries out clustering processing, obtains calcification centre region and includes the marginal zone of Image artifacts
Area image tentatively distinguishes calcification pixel in original calcification image data with Image artifacts point.Again by fringe region
Both image and calcification centre area image carry out area ratio analytical calculation, obtain area ratio analysis as a result, can judge side
Whether the Image artifacts quantity ratio situation in the calcification pixel quantity and calcification centre area image in edge area image is reasonable.
It is finally analyzed according to obtained area ratio as a result, being determined according to calcification pixel quantity and Image artifacts quantity ratio situation
Artifact corrects calcification image.The embodiment of the present invention is obtained original by carrying out first calcified regions image zooming-out to original image
After calcification image data, then clustering processing is carried out to this original calcification image data, is further separated out original calcification picture number
Calcification pixel and Image artifacts in, and by preferably eliminating the influence of artifact, having obtained more after multiple Image Adjusting
Add accurately artifact amendment calcification image, is conducive to the accuracy for improving calcification calculated result.
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all cover
Within protection scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (11)
1. a kind of calcification artifact eliminating method characterized by comprising
Primitive vessel image data is obtained and handled, original calcification image data is obtained；
Clustering processing is carried out to the original calcification image data, obtains calcification centre area image and fringe region image；
Area ratio analysis is carried out to both the fringe region image and the calcification centre area image, obtains area ratio analysis
As a result；
Result, which is analyzed, according to obtained area ratio determines that artifact corrects calcification image.
2. the method according to claim 1, wherein the processing primitive vessel image data, obtains original calcium
Changing image data includes:
Initial partitioning is carried out to the primitive vessel image data, obtains original calcified regions；
Dot product is done with the corresponding primitive vessel image data to the original calcified regions, obtains original calcification image data,
Wherein the primitive vessel image data includes at least one of following: image or blood vessel short axle CT image is straightened in blood vessel.
3. the method according to claim 1, wherein described carry out at cluster the original calcification image data
Reason, obtains calcification centre area image and fringe region image includes:
By the gray value of the gray value of pixel and the pixel in the original calcification image data and adjacent threshold gray value
Difference is weighted, and obtains between class distance measurement；
Two mean cluster processing are carried out to the original calcification image data according between class distance measurement, obtain calcification centre
Area image and fringe region image.
4. the method according to claim 1, wherein described analyze the determining puppet of result according to obtained area ratio
Shadow corrects calcification image
It, will if the area ratio of the area of the fringe region image and the calcification centre area image is no more than given threshold
The calcification centre area image is determined as artifact amendment calcification image；
If the area ratio of the area of the fringe region image and the calcification centre area image is more than given threshold, basis
The average gray difference value of the fringe region image and the calcification centre area image determines that artifact corrects calcification image.
5. according to the method described in claim 4, it is characterized in that, described according in the fringe region image and the calcification
The average gray difference value of heart district area image determines that artifact amendment calcification image includes:
Whether the average gray difference value for judging the calcification centre area image and the fringe region image is more than setting difference；
If the average gray difference value of the calcification centre area image and the fringe region image is more than setting difference, by institute
It states calcification centre area image and is determined as artifact amendment calcification image；
It, will if the average gray difference value of the calcification centre area image and the fringe region image is less than setting difference
The merging image of the calcification centre area image and the fringe region image is determined as artifact amendment calcification image.
6. a kind of calcification artifact eliminates equipment characterized by comprising
Original image processing module obtains original calcification image data for obtaining and handling primitive vessel image data；
Image clustering module obtains calcification centre area image for carrying out clustering processing to the original calcification image data
With fringe region image；
Areal analysis module, for carrying out area score to both the fringe region image and the calcification centre area image
Analysis obtains area ratio analysis result；
Determining module is corrected, determines that artifact corrects calcification image for analyzing result according to obtained area ratio.
7. equipment according to claim 6, which is characterized in that the original image processing module includes:
Original image cutting unit obtains original calcified regions for carrying out initial partitioning to the primitive vessel image data；
Image dot product unit is obtained for doing dot product with the corresponding primitive vessel image data to the original calcified regions
Original calcification image data, wherein the primitive vessel image data is including at least one of following: image or blood vessel is straightened in blood vessel
Short axle CT image.
8. equipment according to claim 6, which is characterized in that described image cluster module includes:
Between class distance measure determining unit, for by the gray value and the picture of pixel in the original calcification image data
The gray value of vegetarian refreshments and the difference of adjacent threshold gray value are weighted, and obtain between class distance measurement；
Clustering processing unit, for carrying out two mean clusters to the original calcification image data according between class distance measurement
Processing, obtains calcification centre area image and fringe region image.
9. equipment according to claim 6, which is characterized in that the amendment determining module includes:
First amending unit, if for the fringe region image area and the calcification centre area image area ratio not
More than given threshold, then the calcification centre area image is determined as artifact amendment calcification image；
Second amending unit, if super for the area of the fringe region image and the area ratio of the calcification centre area image
Given threshold is crossed, then artifact is determined according to the average gray difference value of the fringe region image and the calcification centre area image
Correct calcification image.
10. equipment according to claim 9, which is characterized in that second amending unit includes:
Revise subelemen, for judging that the average gray difference value of the calcification centre area image and the fringe region image is
No is more than setting difference；If the average gray difference value of the calcification centre area image and the fringe region image is more than setting
The calcification centre area image is then determined as artifact amendment calcification image by difference；If the calcification centre area image and
The average gray difference value of the fringe region image is less than setting difference, then by the calcification centre area image and the side
The merging image of edge area image is determined as artifact amendment calcification image.
11. a kind of computer readable storage medium, which is characterized in that the storage medium, which includes that one group of computer is executable, to be referred to
It enables, requires the described in any item calcification artifact eliminating methods of 1-5 for perform claim when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910234292.8A CN109978790A (en) | 2019-03-26 | 2019-03-26 | A kind of calcification artifact eliminating method, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910234292.8A CN109978790A (en) | 2019-03-26 | 2019-03-26 | A kind of calcification artifact eliminating method, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109978790A true CN109978790A (en) | 2019-07-05 |
Family
ID=67080680
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910234292.8A Pending CN109978790A (en) | 2019-03-26 | 2019-03-26 | A kind of calcification artifact eliminating method, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978790A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269733A (en) * | 2021-05-14 | 2021-08-17 | 成都真实维度科技有限公司 | Artifact detection method for radiation particles in tomography image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101238987A (en) * | 2007-09-06 | 2008-08-13 | 深圳先进技术研究院 | Processing method of CT cerebral hemorrhage image |
| CN103093457A (en) * | 2012-12-28 | 2013-05-08 | 中国科学院深圳先进技术研究院 | Detecting system and detecting method for ultrasonic blood vessel boundaries |
| CN103106675A (en) * | 2013-02-05 | 2013-05-15 | 南方医科大学 | X-ray computed tomography (CT) metal artifact processing method |
| CN104599239A (en) * | 2013-10-31 | 2015-05-06 | 通用电气公司 | Medical image metal artifact eliminating method and device |
-
2019
- 2019-03-26 CN CN201910234292.8A patent/CN109978790A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101238987A (en) * | 2007-09-06 | 2008-08-13 | 深圳先进技术研究院 | Processing method of CT cerebral hemorrhage image |
| CN103093457A (en) * | 2012-12-28 | 2013-05-08 | 中国科学院深圳先进技术研究院 | Detecting system and detecting method for ultrasonic blood vessel boundaries |
| CN103106675A (en) * | 2013-02-05 | 2013-05-15 | 南方医科大学 | X-ray computed tomography (CT) metal artifact processing method |
| CN104599239A (en) * | 2013-10-31 | 2015-05-06 | 通用电气公司 | Medical image metal artifact eliminating method and device |
Non-Patent Citations (1)
| Title |
|---|
| 李裕: "基于CCA和CCTA图像的冠状动脉狭窄度量化方法研究", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269733A (en) * | 2021-05-14 | 2021-08-17 | 成都真实维度科技有限公司 | Artifact detection method for radiation particles in tomography image |
| CN113269733B (en) * | 2021-05-14 | 2024-04-16 | 成都真实维度科技有限公司 | Artifact detection method for radioactive particles in tomographic image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Odstrcilik et al. | Retinal vessel segmentation by improved matched filtering: evaluation on a new high‐resolution fundus image database | |
| Naqi et al. | Lung nodule detection using polygon approximation and hybrid features from CT images | |
| Delibasis et al. | Automatic model-based tracing algorithm for vessel segmentation and diameter estimation | |
| JP4950071B2 (en) | Method for automatic extraction of pulmonary artery tree from 3D medical images | |
| JP6005663B2 (en) | Automatic measurement of arteriovenous ratio in blood vessel images | |
| CN111340789A (en) | Method, device, equipment and storage medium for identifying and quantifying eye fundus retinal blood vessels | |
| CA2732647C (en) | Image processing apparatus, image processing method, and image processing program | |
| Hassan et al. | Joint segmentation and quantification of chorioretinal biomarkers in optical coherence tomography scans: A deep learning approach | |
| CN107292312B (en) | Tumor CT image processing method | |
| Barbosa et al. | Fast and fully automatic 3-d echocardiographic segmentation using b-spline explicit active surfaces: Feasibility study and validation in a clinical setting | |
| US11357400B2 (en) | Image processing method for glaucoma detection and computer program products thereof | |
| CN110415234A (en) | Brain tumor dividing method based on multi-parameter magnetic resonance imaging | |
| US20110218427A1 (en) | Diagnosis assisting apparatus, coronary artery analyzing method and recording medium having a coronary artery analyzing program stored therein | |
| Nisha et al. | A computer-aided diagnosis system for plus disease in retinopathy of prematurity with structure adaptive segmentation and vessel based features | |
| US10521906B2 (en) | Method and image processor for evaluating a contrast agent-enhanced magnetic resonance slice image of a heart | |
| CN108272434A (en) | The method and device that eye fundus image is handled | |
| Maitra et al. | Automated digital mammogram segmentation for detection of abnormal masses using binary homogeneity enhancement algorithm | |
| US10664985B2 (en) | Determining a complexity value of a stenosis or a section of a vessel | |
| CN105389810A (en) | Identification system and method of intravascular plaque | |
| CN106446805B (en) | A kind of eyeground shine in optic cup dividing method and system | |
| Gao et al. | Accurate lung segmentation for X-ray CT images | |
| Bento et al. | Automatic identification of atherosclerosis subjects in a heterogeneous MR brain imaging data set | |
| CN117547306B (en) | Left ventricular ejection fraction measurement method, system and device based on M-type ultrasound | |
| Onkaew et al. | Automatic extraction of retinal vessels based on gradient orientation analysis | |
| CN106934815A (en) | Movable contour model image partition method based on Mixed Zone |
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: 20190705 |