CN110246150A - Metal detection method, apparatus, equipment and storage medium - Google Patents
Metal detection method, apparatus, equipment and storage medium Download PDFInfo
- Publication number
- CN110246150A CN110246150A CN201910515515.8A CN201910515515A CN110246150A CN 110246150 A CN110246150 A CN 110246150A CN 201910515515 A CN201910515515 A CN 201910515515A CN 110246150 A CN110246150 A CN 110246150A
- Authority
- CN
- China
- Prior art keywords
- metal
- region
- medical image
- edge region
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
-
- 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
Abstract
The embodiment of the invention discloses a kind of metal detection method, apparatus, equipment and storage mediums.This method comprises: obtaining the medical image of target object, and extract the object edge region of at least one area-of-interest in medical image;The target neighborhood of each pixel in medical image is obtained, and metal edge region is determined according to the gray value of pixel each in target neighborhood;The difference set in metal edge region and object edge region is obtained, seed point is extracted from difference set, and region growing is carried out based on seed point, to detect the metal in medical image.The technical solution of the embodiment of the present invention can detect with the presence or absence of metal in medical image, and then can receive additional dosage to avoid subject and picture quality can be improved.
Description
Technical field
The present embodiments relate to technical field of medical image processing more particularly to a kind of metal detection method, apparatus, set
Standby and storage medium.
Background technique
Image collection region in medical imaging equipment it is possible that for example various metal materials of more metal operation
Instrument, then, medical imaging equipment work when can the target object to metal and subject in image collection region carry out simultaneously
Image collection.Under normal conditions, the gray value of the metal in medical image got is lower than the gray value of target object, example
Such as, in C-arm, compared to target object, since attenuation degree of the metal to X-ray is higher, the medicine shadow got
The gray value of metal as in is lower.
However, above situation may bring problems, for example, medical imaging equipment is according to the medicine shadow got
The size of gray value adjustment dosage as in, since the gray value of metal is lower, in order to enable the overall gray value of medical image
Meet acquisition target, needs to increase more dosage, this makes subject that can receive many additional dosage.For another example working as
When medical imaging equipment carries out post-processing to the medical image got, since separation is not implemented in metal and target object, make
It obtains metal and occupies a part of tonal range that should work as displaying target object, lead to the contrast of the gray scale of target object not
Height, picture quality are poor.
Summary of the invention
The embodiment of the invention provides a kind of metal detection method, apparatus, equipment and storage mediums, to realize to medicine shadow
The effect that metal as in is detected.
In a first aspect, may include: the embodiment of the invention provides a kind of metal detection method
The medical image of target object is obtained, and extracts the object edge of at least one area-of-interest in medical image
Region;
The target neighborhood of each pixel in medical image is obtained, and true according to the gray value of pixel each in target neighborhood
Deposit category fringe region;
The difference set in metal edge region and object edge region is obtained, seed point is extracted from difference set, and be based on seed
Point carries out region growing, to detect the metal in medical image.
Optionally, carrying out region growing based on seed point to detect the metal in medical image may include:
Region growing is carried out based on seed point, obtains current region growth result, and, by area growth process
The access region that the pixel of access is constituted;
Update object edge region according to the difference set of object edge region and access region, and according to metal edge region and
The difference set of access region updates metal edge region;
Repeat to obtain the operation of the difference set in metal edge region and object edge region, until metal edge region or
It is that object edge region meets preset termination condition, using each current region growth result as the metal in medical image.
Optionally, region growing is carried out based on seed point, to detect the metal in medical image, it may include:
Region growing is carried out based on seed point, obtains current region growth result, and calculate in current region growth result
First gray average of each pixel;
The adaptive threshold in metal edge region is calculated, and calculates each picture for being less than adaptive threshold in metal edge region
Second gray average of vegetarian refreshments;
According to the numerical relation of the first gray average and the second gray average, determine whether current region growth result is doctor
Learn the metal in image.
Optionally, region growing is carried out based on seed point, may include:
Determine the pixel for meeting predeterminable area growth conditions in the default neighborhood of seed point, and according to meeting preset areas
The pixel of domain growth conditions updates seed point;
The operation of the pixel for meeting predeterminable area growth conditions in the default neighborhood of determining seed point is repeated, directly
It is sky to the pixel for meeting predeterminable area growth conditions.
Optionally, the pixel for meeting predeterminable area growth conditions in the default neighborhood of seed point is determined, it specifically can be with
Include:
It is similar with the structure of seed point according to neighborhood point using the pixel in the default neighborhood of seed point as neighborhood point
Degree, the intersection of neighborhood point and object edge region, and, the gray scale similarity of the mean value of neighborhood point and each seed point, from each
The pixel for meeting predeterminable area growth conditions is filtered out in a neighborhood point.
Optionally, metal edge region is determined according to the gray value of pixel each in target neighborhood, it may include: according to target
The gray variance value of each pixel, filters out metal edge region from target neighborhood in neighborhood.
Optionally, after the medical image for obtaining target object, this method, which may also include that, carries out normalizing to medical image
Change processing, and medical image is updated according to processing result.
Second aspect, the embodiment of the invention also provides a kind of metal detection device, the apparatus may include:
Object edge region extraction module for obtaining the medical image of target object, and extracts in medical image extremely
The object edge region of a few area-of-interest;
Metal edge area determination module, for obtaining the target neighborhood of each pixel in medical image, and according to mesh
The gray value of each pixel determines metal edge region in mark neighborhood;
Metal detection module is extracted from difference set for obtaining the difference set in metal edge region and object edge region
Seed point, and region growing is carried out based on seed point, to detect the metal in medical image.
The third aspect, the embodiment of the invention also provides a kind of equipment, which may include:
One or more processors;
Memory, for storing one or more programs;
When one or more programs are executed by one or more processors, so that one or more processors realize the present invention
Metal detection method provided by any embodiment.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, the computer program realize metal detection method provided by any embodiment of the invention when being executed by processor.
The technical solution of the embodiment of the present invention, firstly, extracting the mesh of at least one area-of-interest from medical image
Fringe region is marked, which may be metal boundary, it is also possible to target object boundary;Secondly, according to medicine shadow
The gray value of each pixel determines metal edge region in the target neighborhood of each pixel as in, thereby determines that out medical image
In whether there is metal;In turn, if there is metal edge region, the difference in metal edge region and object edge region is obtained
Collection, extracts seed point from difference set;Finally, region growing is carried out based on the seed point, to detect the metal in medical image.
Above-mentioned technical proposal can be detected with the presence or absence of metal in medical image, and then additional dosage can be received to avoid subject
And picture quality can be improved.
Detailed description of the invention
Fig. 1 is the flow chart of one of embodiment of the present invention one metal detection method;
Fig. 2 is the schematic diagram of one of embodiment of the present invention one metal detection method traditional Chinese medicine image;
Fig. 3 is the flow chart of one of embodiment of the present invention two metal detection method;
Fig. 4 is the structural block diagram of one of the embodiment of the present invention three metal detection device;
Fig. 5 is the structural schematic diagram of one of the embodiment of the present invention four equipment.
Specific embodiment
Invention is further described in detail with reference to the accompanying drawings and examples.It is understood that described herein
Specific embodiment be used only for explaining the present invention rather than limiting the invention.It also should be noted that for the ease of
It describes, only the parts related to the present invention are shown rather than entire infrastructure in attached drawing.
Embodiment one
Fig. 1 is a kind of flow chart of the metal detection method provided in the embodiment of the present invention one.The present embodiment is applicable to
The case where whether there is metal in medical image is detected, being particularly suitable for detecting in the medical image got based on C-arm is
No the case where there are metals.This method can be executed by metal detection device provided in an embodiment of the present invention, which can be with
It is realized by the mode of software and/or hardware, which can integrate in various equipment.
Referring to Fig. 1, the method for the embodiment of the present invention specifically comprises the following steps:
S110, the medical image for obtaining target object, and extract the mesh of at least one area-of-interest in medical image
Mark fringe region.
Wherein, medical image can be X ray image, CT scan image (CT images), B ultrasound image,
It is also possible to other medical images.Because the gray value of the sum of the grayscale values target object of metal is deposited in these medical images
In otherness, the otherness may be due to metal and target object to medical imaging when involved ray attenuation degree
It is different and caused by.As long as the having differences property of gray value of the sum of the grayscale values target object of the metal in medical image, based on this
The metal detection method of inventive embodiments can detect in medical image the case where with the presence or absence of metal.
Optionally, after getting the medical image of target object, which can be pre-processed.Than
It such as,, can be to medicine shadow since X-ray exponentially decays if the medical image is image such as CT images relevant to X-ray
As carrying out logarithmic transformation such as log transformation, so that the decaying of the contrast and X-ray of medical image is in a linear relationship, while may be used also
To increase the contrast of low tonal range.For another example, medical image can also be normalized, by different tonal ranges
Medical image processing to identical tonal range such as 0-1, the advantages of this arrangement are as follows, can be based at identical threshold value
Manage any medical image.After pre-processing medical image, need to update medical image according to processing result.
The object edge region of at least one area-of-interest in medical image is extracted, which may be
Metal boundary, it is also possible to target object boundary.Specifically, can based on boundary operator such as Roberts, Sobel,
Prewitt, Laplacian, Canny etc. extract the object edge region of at least one area-of-interest in medical image.It is logical
In normal situation, the rectangular area of M*N can be based on the object edge region that boundary operator extracts, wherein M and N is just
Integer.For example, the object edge region can be the rectangular area of 3*3.
S120, the target neighborhood for obtaining each pixel in medical image, and according to the ash of pixel each in target neighborhood
Angle value determines metal edge region.
Wherein, the having differences property of gray value of the sum of the grayscale values target object of the metal in medical image, for example, being penetrated in X
In line image, compared to target object, metal is higher to the attenuation degree of X-ray, then the gray value of metal is lower than target object
Gray value.Moreover, this otherness is but also there are apparent change of gradients metal boundary and target object boundary.Based on upper
Stating content may determine that with the presence or absence of metal in medical image, specifically, obtaining the target of each pixel in medical image
Neighborhood, the target neighborhood can be rectangular area.Optionally, object edge region may be considered thin rectangular area, and target
Neighborhood may be considered thick rectangular area.For example, if object edge region is the rectangular area of a 3*3, target neighborhood
It can be the rectangular area for being not less than 5*5.
It, can be according to pixel each in target neighborhood in getting medical image after the target neighborhood of each pixel
Gray value determines metal edge region.For example, can be according to the gray variance value of pixel each in target neighborhood, from target neighborhood
In filter out metal edge region.This is because in metal boundary and/or target object boundary there are apparent change of gradient,
This makes the gray variance value of each pixel in the target neighborhood of these boundaries larger.Therefore, can will meet default
The target neighborhood of gray variance threshold value is as metal edge region.It the metal edge region may be lower comprising a part of gray value
Region and the higher region of a part of gray value, the lower region of the gray value is likely to metal.
Thus obtained metal edge region can be one or more, when there are multiple metal edge regions, can incite somebody to action
Multiple metal edge region is integrated, and using the integrated results as metal edge region.Then metal edge area at this time
The inside in domain may be successional, it is also possible to discrete.
S130, the difference set for obtaining metal edge region and object edge region, extract seed point, and be based on from difference set
Seed point carries out region growing, to detect the metal in medical image.
Wherein, if there is metal edge region, the difference set in metal edge region and object edge region is obtained, the difference set
In pixel belong to metal edge region and do not belong to object edge region, then the pixel in these difference sets is likely located at
Metal boundary, it is also possible to be located at target object boundary.Therefore, seed point can be extracted from difference set, for example, with X-ray shadow
As for, since the gray value of metal in X ray image is lower than the gray value of target object, then if most by gray value in difference set
For small pixel as seed point, which must be the pixel of metallic region.Further, it is possible to be carried out based on the seed point
Region growing, to detect the metal in medical image.
Under normal conditions, for the target object of every subject, medical imaging equipment needs to acquire multiple medical images.
After collecting first medical image, metal in medical image can be detected based on above-mentioned steps.Then in medical image
Early period, acquisition phase, for example opened in acquisition second and when later medical image, can according in medical image in addition to metal
Region gray value adjustment dosage size, thus solve since the gray value of metal is lower, in order to enable medical image
Overall gray value meet acquisition target, need to increase more dosage, this makes subject that can receive many additional agent
The problem of amount.Moreover, in the later processing stage of medical image, for example open in processing second and when later medical image, it can
To adjust the gray value of whole picture medical image according to the gray value in the region in medical image in addition to metal, thus solves gold
Belong to and occupy a part of tonal range that should work as displaying target object, cause the contrast of the gray scale of target object not high, scheme
As second-rate problem.
The technical solution of the embodiment of the present invention, firstly, extracting the mesh of at least one area-of-interest from medical image
Fringe region is marked, which may be metal boundary, it is also possible to target object boundary;Secondly, according to medicine shadow
The gray value of each pixel determines metal edge region in the target neighborhood of each pixel as in, thereby determines that out medical image
In whether there is metal;In turn, if there is metal edge region, the difference in metal edge region and object edge region is obtained
Collection, extracts seed point from difference set;Finally, region growing is carried out based on the seed point, to detect the metal in medical image.
Above-mentioned technical proposal can be detected with the presence or absence of metal in medical image, and then additional dosage can be received to avoid subject
And picture quality can be improved.
A kind of optional technical solution carries out region growing based on seed point, to detect the metal in medical image, specifically
May include: based on seed point carry out region growing, obtain current region growth result, and, in area growth process by
The access region that the pixel accessed is constituted;Object edge area is updated according to the difference set of object edge region and access region
Domain, and metal edge region is updated according to the difference set of metal edge region and access region;It repeats to obtain metal edge area
The operation of the difference set in domain and object edge region, until metal edge region or object edge region meet preset end item
Part, using each current region growth result as the metal in medical image.
Wherein, if there are multiple metals in medical image, and multiple metal is then based on there are discrete situation
After seed point carries out region growing, the part metals in medical image can only be detected.Therefore, it is necessary to carry out to the medical image
Repeated detection, to ensure to detect each metal in medical image.Specifically, firstly, based on seed point carry out region growing,
Current region growth result is obtained, which is the part metals in medical image;Moreover, in region growing
In the process, the reason of may be constructed access region based on the pixel accessed, access region is individually extracted be,
During subsequent region growings, without accessing the pixel in these access regions again, detection efficiency is improved.Secondly, root
Object edge region is updated according to the difference set of object edge region and access region, and according to metal edge region and access region
Difference set updates metal edge region, obtains the object edge region for eliminating access region and metal edge region.Again, it repeats
It executes and obtains the operation of the difference set in metal edge region and object edge region, to realize the repeated detection of medical image, until
Metal edge region or object edge region meet preset termination condition, such as metal edge region or object edge area
Domain is sky, at this point, using each current region growth result as the metal in medical image.
A kind of optional technical solution carries out region growing based on seed point, to detect the metal in medical image, specifically
It may include: that region growing is carried out based on seed point, obtain current region growth result, and calculate in current region growth result
First gray average of each pixel;The adaptive threshold in metal edge region is calculated, and calculates and is less than in metal edge region
Second gray average of each pixel of adaptive threshold;According to the numerical relation of the first gray average and the second gray average,
Determine whether current region growth result is metal in medical image.
Wherein, when whether there is metal in judging medical image, it is understood that there may be following situation: according to every in medical image
The gray value of each pixel determines that there are a part of gray value is lower in metal edge region in the target neighborhood of a pixel
Region and the higher region of a part of gray value, but the lower region of the gray value may be target object, the gray value compared with
High region may be air, this is because air is minimum to the attenuation degree of X-ray.It is possible to miss target object in this way
It is considered metal, therefore, it is necessary to further be verified to obtained metal edge region, verifies whether it is real gold
Belong to.
Specifically, carrying out region growing when the gray value of metal is lower than the gray value of target object based on seed point, obtaining
To current region growth result, and the first gray average of each pixel in current region growth result is calculated, first gray scale
Mean value may be considered the gamma characteristic of each pixel for being determined as metal after verification.With some metal in medical image
Fringe region is operation object, calculates the adaptive threshold in the metal edge region, for example divide to obtain this certainly based on big law
Threshold value is adapted to, and then is calculated in the metal edge region less than the second gray average of each pixel of adaptive threshold, the step
The reason of rapid setting, is that, if including metal in the metal edge region, the second gray average should be the pixel of metal
The gamma characteristic of point, i.e. second gray average and the first gray average should be similar;Conversely, the second gray average should
It is the gamma characteristic of the pixel of target object, i.e. the otherness of second gray average and the first gray average is larger.Therefore,
Can determine whether current region growth result is medicine shadow according to the numerical relation of the first gray average and the second gray average
Metal as in, for example, if the difference of the second gray average and the first gray average is greater than preset threshold, then it is assumed that the metal
Not there is no metal in fringe region;Conversely, then there is metal.Above-mentioned steps setting is advantageous in that, can further be verified
To each metal edge region in whether really there is metal.
Illustratively, the correlation for each technical characteristic being related in above-mentioned steps in order to better understand, such as Fig. 2
Shown, medical image 10 includes target object 20 and metal 30, and target object is indicated with solid line;Object edge region may be mesh
Mark object bounds 401, it is also possible to metal boundary 402;Metal edge region 50 there are the lower region of a part of gray value and
A part of higher region of gray value, object edge region and metal edge region 50 are represented by dotted lines;Metal edge region 50
It can be a thick rectangular area, object edge region can be a thin rectangular area.
Embodiment two
Fig. 3 is a kind of flow chart of the metal detection method provided in the embodiment of the present invention two.The present embodiment is with above-mentioned each
It is optimized based on technical solution.In the present embodiment, optionally, region growing is carried out based on seed point, specifically can include:
It determines the pixel for meeting predeterminable area growth conditions in the default neighborhood of seed point, and grows item according to predeterminable area is met
The pixel of part updates seed point;Repeat the picture for meeting predeterminable area growth conditions in the default neighborhood of determining seed point
The operation of vegetarian refreshments, until meeting the pixel of predeterminable area growth conditions for sky.Wherein, identical or corresponding as the various embodiments described above
The explanation of term details are not described herein.
As shown in figure 3, the method for the present embodiment can specifically include following steps:
S210, the medical image for obtaining target object, and extract the mesh of at least one area-of-interest in medical image
Mark fringe region.
S220, the target neighborhood for obtaining each pixel in medical image, and according to the ash of pixel each in target neighborhood
Angle value determines metal edge region.
S230, the difference set for obtaining metal edge region and object edge region, extract seed point from difference set.
S240, the pixel for meeting predeterminable area growth conditions in the default neighborhood of seed point is determined, and according to satisfaction
The pixel of predeterminable area growth conditions updates seed point;It repeats in the default neighborhood of determining seed point and meets preset areas
The operation of the pixel of domain growth conditions, until meeting the pixel of predeterminable area growth conditions for sky, to detect medical image
In metal.
Wherein it is determined that meeting predeterminable area growth item in such as 4 neighborhoods or in 8 neighborhoods in the default neighborhood of seed point
These pixels for meeting predeterminable area growth conditions are continued region growing as new seed point by the pixel of part,
Until meeting the pixel of predeterminable area growth conditions for sky, i.e., when no longer there is new seed point, region growing terminates.Due to
In synchronization, there may be multiple seed points, that can carry out region growing based on these seed points simultaneously, improve detection effect
Rate.During region growing, it is believed that all pixels for being used as seed point belong to metal, thus detect to cure
Learn the metal in image.Optionally, the pixel that area growth process had accessed can also be marked, so as in subsequent sections
In growth course, without accessing these pixels accessed again, detection efficiency is improved.
Optionally, it determines the pixel for meeting predeterminable area growth conditions in the default neighborhood of seed point, can specifically wrap
It includes: using the pixel in the default neighborhood of seed point as neighborhood point, according to the structural similarity of neighborhood point and seed point, neighborhood
The intersection of point and object edge region, and, the gray scale similarity of the mean value of neighborhood point and each seed point, from each neighborhood point
In filter out the pixel for meeting predeterminable area growth conditions.
Illustratively, preset nonparametric image transformation such as Census can be carried out to medical image to convert to obtain neighborhood
The structural similarity of the structural similarity such as Hamming distance of the change point of point, change point and seed point should be less than the first threshold
Value, wherein seed point is non-transformed seed point;For another example can be according to the histogram calculation structure of neighborhood point and seed point
Similarity;For another example the intersection in neighborhood point and object edge region is sky, i.e., neighborhood point cannot be located on object edge region,
Because neighborhood point be located on object edge region be region growing termination condition;For another example the sum of the grayscale values of neighborhood point is each
The gray scale similarity of the mean value of seed point should be less than second threshold, i.e., the gray value of neighborhood point with it is determined that be metal picture
Otherness between the gray value of vegetarian refreshments should be smaller.If a pixel meets predeterminable area growth conditions, the pixel
At least one of above-mentioned condition should be met.On this basis, which can't be the pixel accessed, i.e., often
A pixel can only calculate once, so that region growing can terminate.
The technical solution of the embodiment of the present invention grows item by the predeterminable area that meets in the default neighborhood of determining seed point
The pixel of part, to extract new seed point in neighborhood;Based on new seed point, repeat within its preset neighborhood
The pixel for meeting predeterminable area growth conditions is found, until no longer there is new seed point, region growing terminates, and then will be every
A pixel for being used as seed point is determined as metal.Above-mentioned technical proposal determines metal based on region growing, has high efficiency
With high-precision feature.
Embodiment three
Fig. 4 is the structural block diagram for the metal detection device that the embodiment of the present invention three provides, and the device is for executing above-mentioned
Metal detection method provided by embodiment of anticipating.The metal detection method of the device and the various embodiments described above belongs to the same invention
Design, the detail content of not detailed description in the embodiment of metal detection device can be with reference to above-mentioned metal detection method
Embodiment.Referring to fig. 4, the device is specific can include: object edge region extraction module 310, metal edge area determination module
320 and metal detection module 330.
Wherein, object edge region extraction module 310 for obtaining the medical image of target object, and extracts medicine
The object edge region of at least one area-of-interest in image;
Metal edge area determination module 320, for obtaining the target neighborhood of each pixel in medical image, and according to
The gray value of each pixel determines metal edge region in target neighborhood;
Metal detection module 330 is extracted from difference set for obtaining the difference set in metal edge region and object edge region
Seed point out, and region growing is carried out based on seed point, to detect the metal in medical image.
Optionally, metal detection module 330 can specifically include:
Current region growth result obtains unit, for carrying out region growing based on seed point, obtains current region growth
As a result, and, the access region being made of in area growth process the pixel accessed;
Fringe region updating unit, for updating object edge area according to the difference set in object edge region and access region
Domain, and metal edge region is updated according to the difference set of metal edge region and access region;
First metal detection unit, the behaviour of the difference set for repeating to obtain metal edge region and object edge region
Make, until metal edge region or object edge region meet preset termination condition, by each current region growth result
As the metal in medical image.
Optionally, metal detection module 330 can specifically include:
First gray average computing unit, for obtaining current region growth result based on seed point progress region growing,
And calculate the first gray average of each pixel in current region growth result;
Second gray average computing unit, for calculating the adaptive threshold in metal edge region, and calculates metal edge
Less than the second gray average of each pixel of adaptive threshold in region;
Second metal detection unit, for the numerical relation according to the first gray average and the second gray average, determination is worked as
Whether forefoot area growth result is metal in medical image.
Optionally, metal detection module 330 can specifically include:
Seed point updating unit, the pixel for meeting predeterminable area growth conditions in default neighborhood for determining seed point
Point, and seed point is updated according to the pixel for meeting predeterminable area growth conditions;
Unit is repeated, meets predeterminable area growth conditions in the default neighborhood for repeating determining seed point
Pixel operation, until meeting the pixel of predeterminable area growth conditions for sky.
Optionally, seed point updating unit specifically can be used for:
It is similar with the structure of seed point according to neighborhood point using the pixel in the default neighborhood of seed point as neighborhood point
Degree, the intersection of neighborhood point and object edge region, and, the gray scale similarity of the mean value of neighborhood point and each seed point, from each
The pixel for meeting predeterminable area growth conditions is filtered out in a neighborhood point.
Optionally, metal edge area determination module 320, can be used for: according to the gray scale of pixel each in target neighborhood
Variance yields filters out metal edge region from target neighborhood.
Optionally, on the basis of above-mentioned apparatus, which can also include:
Normalized module updates medicine shadow for medical image to be normalized, and according to processing result
Picture.
The metal detection device that the embodiment of the present invention three provides, through object edge region extraction module from medical image
The object edge region of at least one area-of-interest is extracted, which may be metal boundary, it is also possible to
Target object boundary;Metal edge area determination module can be according to each picture in the target neighborhood of pixel each in medical image
The gray value of vegetarian refreshments determines metal edge region, thereby determines that out in medical image with the presence or absence of metal;If there is metal edges
Edge region, the difference set in metal detection module available metal edge region and object edge region, extracts kind from difference set
It is sub-, and then region growing is carried out based on the seed point, to detect the metal in medical image.Above-mentioned apparatus can detect medicine
It whether there is metal in image, and then additional dosage can be received to avoid subject and picture quality can be improved.
Metal inspection provided by any embodiment of the invention can be performed in metal detection device provided by the embodiment of the present invention
Survey method has the corresponding functional module of execution method and beneficial effect.
It is worth noting that, included each unit and module are only pressed in the embodiment of above-mentioned metal detection device
It is divided, but is not limited to the above division according to function logic, as long as corresponding functions can be realized;In addition,
The specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Example IV
Fig. 5 is a kind of structural schematic diagram for equipment that the embodiment of the present invention four provides, as shown in figure 5, the equipment includes depositing
Reservoir 410, processor 420, input unit 430 and output device 440.The quantity of processor 420 in equipment can be one
Or it is multiple, in Fig. 5 by taking a processor 420 as an example;Memory 410, processor 420, input unit 430 and output in equipment
Device 440 can be connected by bus or other means, in Fig. 5 for being connected by bus 450.
Memory 410 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of metal detection method in the embodiment of the present invention is (for example, metal detection fills
Object edge region extraction module 310, metal edge area determination module 320 and metal detection module 330 in setting).Processing
Software program, instruction and module of the device 420 by operation storage in store 410, thereby executing the various functions of equipment
Using and data processing, that is, realize above-mentioned metal detection method.
Memory 410 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to equipment.This
Outside, memory 410 may include high-speed random access memory, can also include nonvolatile memory, for example, at least one
Disk memory, flush memory device or other non-volatile solid state memory parts.In some instances, memory 410 can be into one
Step includes the memory remotely located relative to processor 420, these remote memories can pass through network connection to equipment.On
The example for stating network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Input unit 430 can be used for receiving the number or character information of input, and generate with the user setting of device with
And the related key signals input of function control.Output device 440 may include that display screen etc. shows equipment.
Embodiment five
The embodiment of the present invention five provides a kind of storage medium comprising computer executable instructions, and the computer is executable
Instruction is used to execute a kind of metal detection method when being executed by computer processor, this method comprises:
The medical image of target object is obtained, and extracts the object edge of at least one area-of-interest in medical image
Region;
The target neighborhood of each pixel in medical image is obtained, and true according to the gray value of pixel each in target neighborhood
Deposit category fringe region;
The difference set in metal edge region and object edge region is obtained, seed point is extracted from difference set, and be based on seed
Point carries out region growing, to detect the metal in medical image.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed metal detection provided by any embodiment of the invention
Relevant operation in method.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.According to such understanding, what technical solution of the present invention substantially in other words contributed to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of metal detection method characterized by comprising
The medical image of target object is obtained, and extracts the object edge of at least one area-of-interest in the medical image
Region;
The target neighborhood of each pixel in the medical image is obtained, and according to the gray scale of each pixel in the target neighborhood
It is worth and determines metal edge region;
The difference set in the metal edge region and the object edge region is obtained, seed point is extracted from the difference set, and
Region growing is carried out based on the seed point, to detect the metal in the medical image.
2. the method according to claim 1, wherein described carry out region growing based on the seed point, with inspection
Survey the metal in the medical image, comprising:
Region growing is carried out based on the seed point, obtains current region growth result, and, by area growth process
The access region that the pixel of access is constituted;
The object edge region is updated according to the difference set of the object edge region and the access region, and according to the gold
The difference set for belonging to fringe region and the access region updates the metal edge region;
It repeats to obtain the operation of the difference set in the metal edge region and the object edge region, until the metal edges
Edge region or the object edge region meet preset termination condition, using each current region growth result as institute
State the metal in medical image.
3. the method according to claim 1, wherein described carry out region growing based on the seed point, with inspection
Survey the metal in the medical image, comprising:
Region growing is carried out based on the seed point, obtains current region growth result, and calculate the current region grown junction
First gray average of each pixel in fruit;
The adaptive threshold in the metal edge region is calculated, and calculates and is less than the adaptive thresholding in the metal edge region
Second gray average of each pixel of value;
According to the numerical relation of first gray average and second gray average, the current region growth result is determined
It whether is metal in the medical image.
4. the method according to claim 1, wherein described carry out region growing based on the seed point, comprising:
It determines the pixel for meeting predeterminable area growth conditions in the default neighborhood of the seed point, and is met in advance according to described
If the pixel of region growing condition updates the seed point;
The operation of the pixel for meeting predeterminable area growth conditions in the default neighborhood for determining the seed point is repeated, directly
It is sky to the pixel for meeting predeterminable area growth conditions.
5. according to the method described in claim 4, it is characterized in that, satisfaction in the default neighborhood of the determination seed point
The pixel of predeterminable area growth conditions, comprising:
Using the pixel in the default neighborhood of the seed point as neighborhood point, according to the knot of the neighborhood point and the seed point
Structure similarity, the intersection of the neighborhood point and the object edge region, and, the neighborhood point and each seed point
The gray scale similarity of mean value filters out the pixel for meeting predeterminable area growth conditions from each neighborhood point.
6. the method according to claim 1, wherein the gray scale according to each pixel in the target neighborhood
It is worth and determines metal edge region, comprising:
According to the gray variance value of each pixel in the target neighborhood, metal edge area is filtered out from the target neighborhood
Domain.
7. the method according to claim 1, wherein being gone back after the medical image for obtaining target object
Include:
The medical image is normalized, and the medical image is updated according to processing result.
8. a kind of metal detection device characterized by comprising
Object edge region extraction module for obtaining the medical image of target object, and extracts in the medical image extremely
The object edge region of a few area-of-interest;
Metal edge area determination module, for obtaining the target neighborhood of each pixel in the medical image, and according to institute
The gray value for stating each pixel in target neighborhood determines metal edge region;
Metal detection module, for obtaining the difference set in the metal edge region and the object edge region, from the difference set
In extract seed point, and region growing is carried out based on the seed point, to detect the metal in the medical image.
9. a kind of equipment, which is characterized in that the equipment includes:
One or more processors;
Memory, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now metal detection method as described in any in claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The metal detection method as described in any in claim 1-7 is realized when being executed by processor.
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910515515.8A CN110246150A (en) | 2019-06-14 | 2019-06-14 | Metal detection method, apparatus, equipment and storage medium |
EP20814241.4A EP3958742A4 (en) | 2019-05-24 | 2020-05-24 | Systems and methods for processing x-ray images |
PCT/CN2020/091967 WO2020238817A1 (en) | 2019-05-24 | 2020-05-24 | Systems and methods for processing x-ray images |
US17/456,393 US20220092787A1 (en) | 2019-05-24 | 2021-11-24 | Systems and methods for processing x-ray images |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910515515.8A CN110246150A (en) | 2019-06-14 | 2019-06-14 | Metal detection method, apparatus, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110246150A true CN110246150A (en) | 2019-09-17 |
Family
ID=67887125
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910515515.8A Pending CN110246150A (en) | 2019-05-24 | 2019-06-14 | Metal detection method, apparatus, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110246150A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110766679A (en) * | 2019-10-25 | 2020-02-07 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
CN111537075A (en) * | 2020-04-14 | 2020-08-14 | 重庆中科云从科技有限公司 | Temperature extraction method, device, machine readable medium and equipment |
WO2020238817A1 (en) * | 2019-05-24 | 2020-12-03 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for processing x-ray images |
CN113034389A (en) * | 2021-03-17 | 2021-06-25 | 武汉联影智融医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101576997B (en) * | 2009-06-19 | 2011-07-20 | 西安电子科技大学 | Abdominal organ segmentation method based on secondary three-dimensional region growth |
CN103106675A (en) * | 2013-02-05 | 2013-05-15 | 南方医科大学 | X-ray computed tomography (CT) metal artifact processing method |
CN103440665A (en) * | 2013-09-13 | 2013-12-11 | 重庆大学 | Automatic segmentation method of knee joint cartilage image |
CN103793905A (en) * | 2012-11-02 | 2014-05-14 | 上海联影医疗科技有限公司 | Method and device for determining direction of coronal view of brain image |
US20150117740A1 (en) * | 2013-10-31 | 2015-04-30 | General Electric Company | Method and apparatus for metal artifact elimination in a medical image |
-
2019
- 2019-06-14 CN CN201910515515.8A patent/CN110246150A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101576997B (en) * | 2009-06-19 | 2011-07-20 | 西安电子科技大学 | Abdominal organ segmentation method based on secondary three-dimensional region growth |
CN103793905A (en) * | 2012-11-02 | 2014-05-14 | 上海联影医疗科技有限公司 | Method and device for determining direction of coronal view of brain image |
CN103106675A (en) * | 2013-02-05 | 2013-05-15 | 南方医科大学 | X-ray computed tomography (CT) metal artifact processing method |
CN103440665A (en) * | 2013-09-13 | 2013-12-11 | 重庆大学 | Automatic segmentation method of knee joint cartilage image |
US20150117740A1 (en) * | 2013-10-31 | 2015-04-30 | General Electric Company | Method and apparatus for metal artifact elimination in a medical image |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020238817A1 (en) * | 2019-05-24 | 2020-12-03 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for processing x-ray images |
CN110766679A (en) * | 2019-10-25 | 2020-02-07 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
CN110766679B (en) * | 2019-10-25 | 2022-09-06 | 普联技术有限公司 | Lens contamination detection method and device and terminal equipment |
CN111537075A (en) * | 2020-04-14 | 2020-08-14 | 重庆中科云从科技有限公司 | Temperature extraction method, device, machine readable medium and equipment |
CN113034389A (en) * | 2021-03-17 | 2021-06-25 | 武汉联影智融医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
CN113034389B (en) * | 2021-03-17 | 2023-07-25 | 武汉联影智融医疗科技有限公司 | Image processing method, device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11880972B2 (en) | Tissue nodule detection and tissue nodule detection model training method, apparatus, device, and system | |
CN110246150A (en) | Metal detection method, apparatus, equipment and storage medium | |
EP3449421B1 (en) | Classification and 3d modelling of 3d dento-maxillofacial structures using deep learning methods | |
WO2022089221A1 (en) | Medical image segmentation method and apparatus, and device, system and computer storage medium | |
CN108108739B (en) | Method and device for detecting image target area, X-ray system and storage medium | |
CN110706246A (en) | Blood vessel image segmentation method and device, electronic equipment and storage medium | |
US20030174890A1 (en) | Image processing device and ultrasonic diagnostic device | |
CN111768411B (en) | Coronary centerline extraction method, device, computer equipment and storage medium | |
US8086002B2 (en) | Algorithms for selecting mass density candidates from digital mammograms | |
CN110956632B (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
US8649578B2 (en) | Method and system for defining a breast window | |
EP1789920A1 (en) | Feature weighted medical object contouring using distance coordinates | |
CN110610498A (en) | Mammary gland molybdenum target image processing method, system, storage medium and equipment | |
CN111862044A (en) | Ultrasonic image processing method and device, computer equipment and storage medium | |
CN108389214B (en) | Ultrasonic image processing method and device, electronic equipment and storage medium | |
CN109461144B (en) | Method and device for identifying mammary gland image | |
CN110443254A (en) | The detection method of metallic region, device, equipment and storage medium in image | |
CN106600587A (en) | Lung CT image auxiliary detection processing device | |
US9538920B2 (en) | Standalone annotations of axial-view spine images | |
CN113658284A (en) | X-ray image synthesis from CT images for training nodule detection systems | |
CN111738975B (en) | Image identification method and image identification device | |
EP3658031B1 (en) | Motion compensated cardiac valve reconstruction | |
CN113924046A (en) | Computer-based method for classifying organ masses as cysts | |
CN110930346B (en) | Automatic detection method and storage device for eyeground image microangioma | |
US8260022B2 (en) | Automatic cardiac band detection of breast MRI |
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 | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |