CN109740600A - Localization method, device, computer equipment and the storage medium of highlighted focal area - Google Patents
Localization method, device, computer equipment and the storage medium of highlighted focal area Download PDFInfo
- Publication number
- CN109740600A CN109740600A CN201910008074.2A CN201910008074A CN109740600A CN 109740600 A CN109740600 A CN 109740600A CN 201910008074 A CN201910008074 A CN 201910008074A CN 109740600 A CN109740600 A CN 109740600A
- Authority
- CN
- China
- Prior art keywords
- image
- highlighted
- focal area
- mammary gland
- threshold value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
This application involves localization method, device, computer equipment and the storage mediums of a kind of highlighted focal area, a kind of localization method of highlighted focal area, applied in mammary gland three-dimensional tomographic image, comprising: obtain space interested in the mammary gland three-dimensional tomographic image；Shape constraining is carried out to the space interested to obtain constraint image；Determine the threshold value of region growing；Region growing is carried out to the constraint image based on the threshold value, to obtain highlighted focal area.After the localization method of above-mentioned highlighted focal area chooses space interested in mammary gland three-dimensional tomographic image, shape constraining is carried out so that body of gland around highlighted focal area is isolated to space interested, and determine suitable region growing threshold value, to realize the segmentation to highlighted focal area, many inappropriate threshold values have been weeded out in position fixing process.This localization method accelerates the speed of processing, and improves the precision of segmentation.
Description
Technical field
The present invention relates to medical instruments fields, localization method, device, calculating more particularly to a kind of highlighted focal area
Machine equipment and storage medium.
Background technique
When being detected to breast tissue, it is often necessary to be carried out to highlight regions such as lump, lesions in galactophore image
Positioning.The localization method of these highlight regions is handled generally be directed to two-dimentional molybdenum target image in traditional galactophore image,
By simple Region growing segmentation highlight regions, but focal area is easy other highlighted bodies of gland of adhesion, causes positioning inadequate
Accurately.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide localization method, device, the meter of a kind of highlighted focal area
Machine equipment and storage medium are calculated, highlighted focal area can be positioned according to mammary gland three-dimensional tomographic image, and position fixing process is more
Quick and precisely.
A kind of localization method of highlighted focal area is applied in mammary gland three-dimensional tomographic image, comprising:
Space interested is obtained in the mammary gland three-dimensional tomographic image；
Shape constraining is carried out to the space interested to obtain constraint image；
Determine the threshold value of region growing；
Region growing is carried out to the constraint image based on the threshold value, to obtain highlighted focal area.
The localization method of above-mentioned highlighted focal area, after space interested is chosen in mammary gland three-dimensional tomographic image, to sense
Space of interest carries out shape constraining so that body of gland around highlighted focal area is isolated, and determines suitable region growing threshold value, thus
It realizes the segmentation to highlighted focal area, has weeded out many inappropriate threshold values in position fixing process.This localization method accelerates
The speed of processing, and improve the precision of segmentation.
In one of the embodiments, the method also includes:
The radial gradient index of focal area, choosing are highlighted in each layer mammary gland three-dimensional tomographic image based on mammary gland 3-D image
The determination of the mammary gland 3-D image is taken to highlight focal area.
Before in one of the embodiments, described to the progress shape constraining in space interested, the method is also
Include:
The space interested is sampled.
It is described in one of the embodiments, that shape constraining is carried out to the space interested to obtain constraint image packet
It includes:
It is handled by interested space of the Gauss template to the mammary gland three-dimensional tomographic image to obtain the first constraint
Image.
In one of the embodiments, the method also includes:
The first constraint image is weighted with the space interested and is superimposed to obtain the second constraint image.
The threshold value of the determining region growing includes: in one of the embodiments,
Threshold Analysis is carried out to obtain masked areas to the first constraint image；
Threshold Analysis is carried out to obtain threshold value model to region corresponding with the masked areas in the second constraint image
It encloses；
The threshold value of region growing is determined in the threshold range based on radial gradient index.
The Threshold Analysis is Otsu threshold analysis in one of the embodiments,.
A kind of positioning device of highlighted focal area is applied in mammary gland three-dimensional tomographic image, comprising:
Module is obtained, for obtaining space interested in the mammary gland three-dimensional tomographic image；
Constraints module, for carrying out shape constraining to the space interested to obtain constraint image；
Threshold module, for determining the threshold value of region growing；
Pop-in upgrades, for carrying out region growing to the constraint image based on the threshold value, to obtain highlighted focal zone
Domain.
The positioning device of above-mentioned highlighted focal area, after space interested is chosen in mammary gland three-dimensional tomographic image, to sense
Space of interest carries out shape constraining so that body of gland around highlighted focal area is isolated, and determines suitable region growing threshold value, thus
It realizes the segmentation to highlighted focal area, has weeded out many inappropriate threshold values in position fixing process.This localization method accelerates
The speed of processing, and improve the precision of segmentation.
A kind of computer equipment can be run on a memory and on a processor including memory, processor and storage
The step of computer program, the processor realizes the above method when executing described program.
A kind of computer readable storage medium, is stored thereon with computer program, realization when which is executed by processor
The step of above method.
Detailed description of the invention
Fig. 1 is the flow diagram that the localization method of focal area is highlighted in one embodiment；
Fig. 2 is the flow diagram of step S140 in the localization method for highlight in one embodiment focal area；
Fig. 3 is the flow diagram of step S160 in the localization method for highlight in one embodiment focal area；
Fig. 4 is the flow diagram that the localization method of focal area is highlighted in another embodiment；
Fig. 5 is the schematic diagram that the positioning result of focal area is highlighted in one embodiment；
Fig. 6 is the schematic diagram of three faultage images of mammary gland two dimension blending image and mammary gland in one embodiment；
Fig. 7 is the structural schematic diagram that the positioning device of focal area is highlighted in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, and
It is not used in restriction the application.
Fig. 1 is the flow diagram that the localization method of focal area is highlighted in one embodiment, as shown in Figure 1, a kind of high
The localization method of bright focal area is applied in mammary gland three-dimensional tomographic image, comprising:
Step S120: space interested is obtained in mammary gland three-dimensional tomographic image.
Specifically, above-mentioned highlighted region generally can be mammary gland three-dimensional tomographic image (Digital Breast
Tomsynthesis, abbreviation DBT) in focal area, focal area can specifically include lump region, asymmetric region and
Structural distortion region etc., these regions are shown generically as highlight regions in mammary gland three-dimensional tomographic image.To above-mentioned highlighted disease
When stove region is detected and positioned, fixed mammary gland is exposed every certain angle first, to obtain several mammary gland
Three-dimensional tomographic image obtains space interested (Volume of Interest, abbreviation VOI) in mammary gland three-dimensional tomographic image.
The acquisition modes in space interested can realize that interactive mode may include drawing a circle, marking diameter or beat according to interactive mode
The modes such as point.Doctor or operator can generally be presented the highlighted focal area such as lump in several mammary gland three-dimensional tomographic images
Compare more or obvious one layers to interact, or can also directly be interacted in mammary gland two dimension blending image, is selected
The maximum cross-section of highlighted focal area is taken, to obtain more accurate space interested.The acquisition in space interested can also be with
It is obtained automatically by models such as machine learning or deep learnings, can also be obtained manually in conjunction with interaction and model obtains progress automatically
It obtains.Subsequent data volume to be treated can be reduced by choosing space interested, promote the speed and accuracy of positioning.
Step S140: shape constraining is carried out to space interested to obtain constraint image.
Specifically, after obtaining space interested, since there may be other to highlight body of gland etc. around highlighted focal area
Tissue, links together with highlighted focal area, can impact to the segmentation of highlighted focal area, it is therefore desirable to interested
Space carries out shape constraining, the interference such as the highlighted body of gland in space interested around highlighted focal area are isolated.Highlighted lesion
The shape constraining in region can be in such a way that shape template be to spatial manipulation interested, and the type of shape template can be according to reality
Border demand determines, specifically can be Gauss template etc., obtains a constraint image after carrying out shape constraining to space interested, after
Continuous cutting procedure can carry out on the constraint image, tie so as to avoid body of gland is highlighted around highlighted focal area to segmentation
The interference of fruit improves the accuracy of highlighted focal area positioning.
Step S160: the threshold value of region growing is determined.
Specifically, it after constraint image is obtained in space interested, needs to carry out region growing (region to constraint image
Growing), so that the adjacent pixel for having like attribute such as intensity, gray level, texture color etc. with each seed point be carried out
Merge to obtain highlighted focal area.For highlighting the region growing of focal area, seed point is the center in space interested
Point, and the threshold value of region growing can first pass through the range that Threshold Analysis threshold value is carried out to constraint image, then in the threshold
It is worth in range and chooses segmentation result preferable threshold value, choosing for threshold value can the segmentation result according to obtained by carrying out region growing
Radial gradient index (Radial Gradient Index, abbreviation RGI) judges, radial gradient index can be used for describing to
The geometrical relationship of deckle circle and border inner pixel, so as to be used to judge the quality of segmentation result, general area growth
The radial gradient index of obtained segmentation result afterwards is higher, it is better to illustrate segmentation result, therefore can choose in threshold range
It can obtain threshold value of the value as subsequent region growings of highest radial gradient index.
Step S180: region growing is carried out to constraint image based on threshold value, to obtain highlighted focal area.
Specifically, after determining the threshold value of region growing, using the central point in space interested as seed point, based on what is obtained
Threshold value carries out region growing to constraint figure, post processing of image can also be carried out to the segmentation result of region growing, after image
Reason can specifically include such as smooth, so that obtaining picture quality preferably highlights focal area image, and this is highlighted sick
Stove area image is shown to doctor or operator.
The localization method of above-mentioned highlighted focal area, after space interested is chosen in mammary gland three-dimensional tomographic image, to sense
Space of interest carries out shape constraining so that body of gland around highlighted focal area is isolated, and determines suitable region growing threshold value, thus
It realizes the segmentation to highlighted focal area, has weeded out many inappropriate threshold values in position fixing process.This localization method accelerates
The speed of processing, and improve the precision of segmentation.
Fig. 2 is the flow diagram of step S140 in the localization method for highlight in one embodiment focal area, at one
In embodiment, as shown in Fig. 2, above-mentioned steps S140 can specifically include:
Step S142: it is handled by interested space of the Gauss template to mammary gland three-dimensional tomographic image to obtain first
Constrain image.
Specifically, the connection of body of gland is highlighted in order to which highlighted focal area and surrounding is truncated, three-dimensional Gaussian template can be passed through
Space interested is handled, to obtain the first constraint image.Such as in one embodiment, the image in space interested is
Space f interested (x, y, z) is multiplied by the Gaussian template N (x, y, z) an of elliposoidal, to obtain shape about by f (x, y, z)
The first constraint image after beam is h (x, y, z)=f (x, y, z) * N (x, y, z), and above-mentioned Gaussian template can beWherein, x0,y0,z0For the central point in space interested, from
And will be divided with the highlighted body of gland of highlighted focal area adhesion by three-dimensional Gaussian template, the processing such as subsequent region growing can be with
It is carried out based on the first constraint image, segmentation result is interfered to avoid its hetero-organization around highlighted focal area.
In one embodiment, above-mentioned steps S140 specifically can also include:
Step S144: the first constraint image is weighted with space interested and is superimposed to obtain the second constraint image.
Specifically, segmentation result is influenced excessive by Gaussian template in order to prevent, influences the accuracy of segmentation result, can be with
First constraint image is weighted with the image in space interested and is superimposed, to reduce the power that Gauss template influences segmentation result
Weight.Above-mentioned first constraint image h (x, y, z) and spatial image f (x, y, z) interested are weighted superposition, obtain second about
Beam images fNew(x, y, z)=λ * f (x, y, z)+(1- λ) * h (x, y, z), for the first constraint image and spatial image interested
Weight can be determined according to segmentation precision demand and the actual conditions of Gauss template, the second constraint image fNew(x, y, z) is by height
The influence of this template is smaller, and image h (x, y, z) is constrained compared to first closer to focal area highlighted in space interested
Original image, therefore the dividing processing of subsequent region growing can be in second constraint image fNewIt is carried out on (x, y, z).
Fig. 3 is the flow diagram of step S160 in the localization method for highlight in above-described embodiment focal area, at one
In embodiment, as shown in figure 3, above-mentioned steps S160 can specifically include:
Step S162: Threshold Analysis is carried out to obtain masked areas to the first constraint image.
Step S164: Threshold Analysis is carried out to obtain threshold value model to region corresponding with masked areas in the second constraint image
It encloses.
Step S166: the threshold value of region growing is determined in threshold range based on radial gradient index.
It specifically, in the above-described embodiments, can be first to the first constraint image h for the selection of region growing threshold value
(x, y, z) carries out Threshold Analysis and obtains a masked areas, which can determine the approximate range of highlighted focal area.
Then to the second constraint image fNewRegion corresponding with the masked areas carries out Threshold Analysis in (x, y, z), to obtain one
The threshold range of a region growing.The threshold range can be a small threshold value TminThe threshold value T big to onemaxBetween.
It, can be with Statistics-Based Method, at regular intervals using more in the threshold range after obtaining the range of threshold value
Then a threshold value is analyzed by radial gradient index and selects optimal threshold value in multiple threshold value.Specific screening mode can
Think one threshold value of every selection, is based on the threshold value, just with the central point (x in space interested0,y0,z0) it is seed point, to second
Constrain image fNew(x, y, z) carries out region growing, obtains a segmentation result, calculates the radial gradient index of the segmentation result.
To make each threshold value correspond to the radial gradient index value of a segmentation result, wherein the highest gradient of numerical value refers to for selection
Threshold value of the corresponding threshold value of number as region growing.
Further, in an alternative embodiment, above-mentioned Threshold Analysis be Otsu threshold (maximum variance between clusters,
Abbreviation otsu) analysis.Otsu threshold analysis carries out the highly effective algorithm of binaryzation for a kind of pair of image, by the gamma characteristic base of image
Divide the image into background and highlighted focal area in threshold value, then calculate the inter-class variance between background and highlighted focal area with
It indicates two-part difference, and threshold range is obtained by continuous iteration.Otsu threshold is first carried out in this method to analyze to obtain threshold
It is worth range, then selects optimal threshold by way of statistics, many inappropriate threshold values can be fast and accurately excluded, to mention
The precision of subsequent obtained segmentation result is risen.
Fig. 4 is the flow diagram that the localization method of focal area is highlighted in another embodiment, as shown in figure 4, wherein
Step S220, S240, S260 and S280 can be identical as the corresponding steps difference in above embodiments.The embodiment highlights
The localization method of focal area can also include:
Step S230: space interested is sampled.
Specifically, before carrying out shape constraining to space interested, first space interested can also be carried out at image sampling
Reason carries out the processing such as shape constraining and region growing again after sampling, can basis for the specific sampling precision in space interested
Actual positioning accuracy and speed requirement determine.Compared to directly being handled using original image, space interested is carried out
Sampling can reduce data volume to be processed, realize speed up processing, so that the positioning of highlighted focal area is quicker.
Step S290: the radial ladder of focal area is highlighted in each layer mammary gland three-dimensional tomographic image based on mammary gland 3-D image
Index is spent, the determination for choosing mammary gland 3-D image highlights focal area.
Specifically, pass through the highlighted focal area of three-dimensional tomographic image in mammary gland 3-D image, the available three-dimensional figure
Determination as in highlights focal area.It is maximum that user or operator highlight focal area cross-sectional area in mammary gland 3-D image
One layer of three-dimensional tomographic image in choose space interested after, the highlighted focal area of remaining each layer is divided and comes out, can be with
Determination in mammary gland 3-D image is highlighted to the center that focal area is highlighted in focal area or every layer of mammary gland three-dimensional tomographic image
It is shown to doctor or operator, such as Fig. 5 is the schematic diagram that the positioning result of focal area is highlighted in one embodiment, at this
In embodiment, as shown, it is disconnected to show respectively the 1st layer, the 10th layer, the 20th layer and the 31st layer this four layers of mammary gland three-dimensionals in figure
The highlighted focal area of tomographic image.
Further, the highlighted focal area in mammary gland 3-D image can also be carried out by mammary gland two dimension blending image
Navigation.Fig. 6 is the schematic diagram of mammary gland two dimension blending image and mammary gland three-dimensional tomographic image in one embodiment, as shown in fig. 6, newborn
Size of the gland two dimension blending image in X-Y horizontal direction is consistent with the size of 3-D image.It can be merged first in two dimension
It is interacted on image, such as diameter is drawn to highlighted focal area maximum cross-section or is drawn a circle, to obtain an area-of-interest
(Region of Interest, abbreviation ROI), while corresponding space interested is also intercepted in 3-D image, and two dimension is melted
The central point for closing area-of-interest in image is mapped in the space interested of 3-D image, can be using the method enumerated to sense
The selection that the central point in interest region is mapped to Z-direction in 3-D image is analyzed.
The central point of above-mentioned mammary gland two dimension blending image area-of-interest may map to any one of mammary gland 3-D image
In layer, so the value that can take of Z value is [1,2,3 ... SliceNum], wherein SliceNum is total layer of mammary gland 3-D image
Number.For speed up processing, Z-direction can be sampled, Z is rounded according to preset interval, one Z of every mapping
Value, so that it may calculate the segmentation result for highlighting focal area in this layer, and calculate corresponding radial gradient index.It is final to choose number
The determination for being worth segmentation result corresponding to highest radial gradient index as mammary gland 3-D image highlights focal area, thus real
Navigation of the existing mammary gland two dimension blending image to mammary gland 3-D image.
Fig. 7 is the structural schematic diagram that the positioning device of focal area is highlighted in one embodiment, as shown in fig. 7, at one
In embodiment, the positioning device 500 of highlighted focal area includes: to obtain module 520, for obtaining in mammary gland three-dimensional tomographic image
Take space interested；Constraints module 540, for carrying out shape constraining to space interested to obtain constraint image；Threshold module
560, for determining the threshold value of region growing；Pop-in upgrades 580, for carrying out region growing to constraint image based on threshold value, with
Obtain highlighted focal area.
Specifically, it obtains module 520 and obtains space interested in mammary gland three-dimensional tomographic image, space interested specifically may be used
Realization is interacted in three-dimensional tomographic image by obtaining module 520 by doctor or operator, after determining space interested,
It obtains module 520 and space interested is sent to constraints module 540；Constraints module 540 carries out shape to received space interested
Shape constraint, segmentation module 540 can be handled space interested by three-dimensional Gaussian template, highlighted focal area is isolated
The highlighted body of gland of surrounding adhesion, to obtain constraint image and send to threshold module 560, threshold module 560 to it is received about
Beam images carry out Threshold Analysis, and determine the optimal threshold value of segmentation result based on radial gradient index, which is sent to life
Long module 580；Pop-in upgrades 580 using the center in space interested as seed point, based on the received threshold value of institute to constraint figure into
Row region growing, and post processing of image is carried out to the segmentation result of region growing, so that highlighted focal area image is obtained, it is above-mentioned
Highlighted focal area may include lump region, asymmetric region and structural distortion region etc., and this is highlighted focal area
Image is shown to doctor or operator.
Further, in an alternative embodiment, the positioning device 500 for highlighting focal area can also include: two
Tie up module (not indicating in figure) and determining module (not indicating in figure), wherein two-dimentional module can be merged according to mammary gland two dimension
Image determines the space interested in each layer mammary gland three-dimensional tomographic image of mammary gland 3-D image, and determining module can be based on each layer
The radial gradient index that focal area is highlighted in mammary gland three-dimensional tomographic image, the determination for choosing mammary gland 3-D image highlight focal zone
Domain.After two-dimentional module interacts selection area-of-interest in mammary gland two dimension blending image, determining module can be partitioned into cream
Highlighted focal area in gland 3-D image is simultaneously shown, to realize the navigation of mammary gland two dimensional image to 3-D image.
The positioning device 500 of above-mentioned highlighted focal area is right after choosing space interested in mammary gland three-dimensional tomographic image
Space interested carries out shape constraining so that body of gland around highlighted focal area is isolated, and determines suitable region growing threshold value, from
And realize the segmentation to highlighted focal area, many inappropriate threshold values have been weeded out in position fixing process.This localization method is accelerated
The speed of processing, and improve the precision of segmentation.
In one embodiment, a kind of medical supply is provided, including memory, processor and storage are on a memory and can
With the computer program run on a processor, following steps can be executed when processor executes the program: disconnected in mammary gland three-dimensional
Space interested is obtained in tomographic image；Shape constraining is carried out to space interested to obtain constraint image；Determine region growing
Threshold value；Region growing is carried out to constraint image based on threshold value, to obtain highlighted focal area.
In one embodiment, a kind of computer readable storage medium is provided, is deposited on the computer readable storage medium
Computer program is contained, processor can be made to execute following steps when which is executed by processor: in mammary gland three
Space interested is obtained in dimension faultage image；Shape constraining is carried out to space interested to obtain constraint image；Determine that region is raw
Long threshold value；Region growing is carried out to constraint image based on threshold value, to obtain highlighted focal area.
It is above-mentioned that the computer-readable restriction for depositing storage medium and computer equipment may refer to above for method
Specific restriction, details are not described herein.
It should be noted that those of ordinary skill in the art will appreciate that realizing all or part of stream in the above method
Journey is relevant hardware can be instructed to complete by computer program, which can be stored in one and computer-readable deposit
In storage media；Above-mentioned program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, above-mentioned storage is situated between
Matter can be magnetic disk, CD, read-only memory (Read-Only Memory, abbreviation ROM) or random access memory
(Random Access Memory, abbreviation RAM) etc..
Each technical characteristic of embodiment described above can be combined arbitrarily, for simplicity of description, not to above-mentioned reality
It applies all possible combination of each technical characteristic in example to be all described, as long as however, the combination of these technical characteristics is not deposited
In contradiction, all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of localization method of highlighted focal area is applied in mammary gland three-dimensional tomographic image characterized by comprising
Space interested is obtained in the mammary gland three-dimensional tomographic image；
Shape constraining is carried out to the space interested to obtain constraint image；
Determine the threshold value of region growing；
Region growing is carried out to the constraint image based on the threshold value, to obtain highlighted focal area.
2. the method according to claim 1, wherein the method also includes:
The radial gradient index that focal area is highlighted in each layer mammary gland three-dimensional tomographic image based on mammary gland 3-D image, chooses institute
The determination for stating mammary gland 3-D image highlights focal area.
3. the method according to claim 1, wherein it is described to the space interested carry out shape constraining it
Before, the method also includes:
The space interested is sampled.
4. the method according to claim 1, wherein described carry out shape constraining to the space interested to obtain
Include: to constraint image
It is handled by interested space of the Gauss template to the mammary gland three-dimensional tomographic image to obtain the first constraint image.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
The first constraint image is weighted with the space interested and is superimposed to obtain the second constraint image.
6. according to the method described in claim 5, it is characterized in that, the threshold value of the determining region growing includes:
Threshold Analysis is carried out to obtain masked areas to the first constraint image；
Threshold Analysis is carried out to obtain threshold range to region corresponding with the masked areas in the second constraint image；
The threshold value of region growing is determined in the threshold range based on radial gradient index.
7. according to the method described in claim 6, it is characterized in that, the Threshold Analysis is Otsu threshold analysis.
8. a kind of positioning device of highlighted focal area is applied in mammary gland three-dimensional tomographic image characterized by comprising
Module is obtained, for obtaining space interested in the mammary gland three-dimensional tomographic image；
Constraints module, for carrying out shape constraining to the space interested to obtain constraint image；
Threshold module, for determining the threshold value of region growing；
Pop-in upgrades, for carrying out region growing to the constraint image based on the threshold value, to obtain highlighted focal area.
9. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes side described in any one of claim 1 to 7 when executing described program
The step of method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The step of any one of claim 1 to 7 the method is realized when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008074.2A CN109740600B (en) | 2019-01-04 | 2019-01-04 | Method and device for positioning highlight focus area, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910008074.2A CN109740600B (en) | 2019-01-04 | 2019-01-04 | Method and device for positioning highlight focus area, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109740600A true CN109740600A (en) | 2019-05-10 |
| CN109740600B CN109740600B (en) | 2020-11-27 |
Family
ID=66361560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910008074.2A Active CN109740600B (en) | 2019-01-04 | 2019-01-04 | Method and device for positioning highlight focus area, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109740600B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211141A (en) * | 2019-06-14 | 2019-09-06 | 山东大学 | A kind of lung airway tree dividing method carrying out the closure of tracheal wall notch under globoid range constraint |
| CN111260642A (en) * | 2020-02-12 | 2020-06-09 | 上海联影医疗科技有限公司 | Image positioning method, device, equipment and storage medium |
| CN111311553A (en) * | 2020-01-21 | 2020-06-19 | 长沙理工大学 | Mammary tumor identification method and device based on region of interest and storage medium |
| CN113222038A (en) * | 2021-05-24 | 2021-08-06 | 北京安德医智科技有限公司 | Breast lesion classification and positioning method and device based on nuclear magnetic image |
| CN114298927A (en) * | 2021-12-16 | 2022-04-08 | 北京朗视仪器股份有限公司 | CBCT image denoising method and device, storage medium and electronic equipment |
| WO2022101768A1 (en) * | 2020-11-16 | 2022-05-19 | International Business Machines Corporation | Medical object detection and identification |
| CN114820591A (en) * | 2022-06-06 | 2022-07-29 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334895A (en) * | 2008-08-07 | 2008-12-31 | 清华大学 | Image division method aiming at dynamically intensified mammary gland magnetic resonance image sequence |
| CN104143035A (en) * | 2013-05-10 | 2014-11-12 | 上海联影医疗科技有限公司 | Method for partitioning breast lesion |
| CN104268873A (en) * | 2014-09-25 | 2015-01-07 | 南京信息工程大学 | Breast tumor partition method based on nuclear magnetic resonance images |
| WO2015127464A1 (en) * | 2014-02-24 | 2015-08-27 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Methods and systems for performing segmentation and registration of images using neutrosophic similarity scores |
| CN106097378A (en) * | 2016-07-24 | 2016-11-09 | 江西理工大学 | A kind of level set retinal vascular images dividing method merging shape prior |
| CN106778005A (en) * | 2016-12-27 | 2017-05-31 | 中南民族大学 | Prostate cancer computer aided detection method and system based on multi-parameter MRI |
| CN107481252A (en) * | 2017-08-24 | 2017-12-15 | 上海术理智能科技有限公司 | Dividing method, device, medium and the electronic equipment of medical image |
| CN109215032A (en) * | 2017-06-30 | 2019-01-15 | 上海联影医疗科技有限公司 | The method and system of image segmentation |
-
2019
- 2019-01-04 CN CN201910008074.2A patent/CN109740600B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334895A (en) * | 2008-08-07 | 2008-12-31 | 清华大学 | Image division method aiming at dynamically intensified mammary gland magnetic resonance image sequence |
| CN104143035A (en) * | 2013-05-10 | 2014-11-12 | 上海联影医疗科技有限公司 | Method for partitioning breast lesion |
| WO2015127464A1 (en) * | 2014-02-24 | 2015-08-27 | H. Lee Moffitt Cancer Center And Research Institute, Inc. | Methods and systems for performing segmentation and registration of images using neutrosophic similarity scores |
| CN104268873A (en) * | 2014-09-25 | 2015-01-07 | 南京信息工程大学 | Breast tumor partition method based on nuclear magnetic resonance images |
| CN106097378A (en) * | 2016-07-24 | 2016-11-09 | 江西理工大学 | A kind of level set retinal vascular images dividing method merging shape prior |
| CN106778005A (en) * | 2016-12-27 | 2017-05-31 | 中南民族大学 | Prostate cancer computer aided detection method and system based on multi-parameter MRI |
| CN109215032A (en) * | 2017-06-30 | 2019-01-15 | 上海联影医疗科技有限公司 | The method and system of image segmentation |
| CN107481252A (en) * | 2017-08-24 | 2017-12-15 | 上海术理智能科技有限公司 | Dividing method, device, medium and the electronic equipment of medical image |
Non-Patent Citations (1)
| Title |
|---|
| 欧阳成等: "乳腺X线图像肿块分割", 《北京生物医学工程》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110211141A (en) * | 2019-06-14 | 2019-09-06 | 山东大学 | A kind of lung airway tree dividing method carrying out the closure of tracheal wall notch under globoid range constraint |
| CN110211141B (en) * | 2019-06-14 | 2022-06-28 | 山东大学 | Lung airway tree segmentation method for trachea wall gap plugging under constraint of spheroid region |
| CN111311553A (en) * | 2020-01-21 | 2020-06-19 | 长沙理工大学 | Mammary tumor identification method and device based on region of interest and storage medium |
| CN111260642A (en) * | 2020-02-12 | 2020-06-09 | 上海联影医疗科技有限公司 | Image positioning method, device, equipment and storage medium |
| WO2022101768A1 (en) * | 2020-11-16 | 2022-05-19 | International Business Machines Corporation | Medical object detection and identification |
| US11580337B2 (en) | 2020-11-16 | 2023-02-14 | International Business Machines Corporation | Medical object detection and identification |
| CN113222038A (en) * | 2021-05-24 | 2021-08-06 | 北京安德医智科技有限公司 | Breast lesion classification and positioning method and device based on nuclear magnetic image |
| CN113222038B (en) * | 2021-05-24 | 2021-10-22 | 北京安德医智科技有限公司 | Breast lesion classification and positioning method and device based on nuclear magnetic image |
| CN114298927A (en) * | 2021-12-16 | 2022-04-08 | 北京朗视仪器股份有限公司 | CBCT image denoising method and device, storage medium and electronic equipment |
| CN114298927B (en) * | 2021-12-16 | 2022-10-04 | 北京朗视仪器股份有限公司 | CBCT image denoising method and device, storage medium and electronic equipment |
| CN114820591A (en) * | 2022-06-06 | 2022-07-29 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
| CN114820591B (en) * | 2022-06-06 | 2023-02-21 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109740600B (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109740600A (en) | Localization method, device, computer equipment and the storage medium of highlighted focal area | |
| US7860290B2 (en) | Three-dimensional (3D) modeling of coronary arteries | |
| US7339585B2 (en) | Method and apparatus for visualization of biological structures with use of 3D position information from segmentation results | |
| Praßni et al. | Shape-based transfer functions for volume visualization | |
| EP1995690B1 (en) | Generating an anatomical model using a rule-based segmentation and classification process | |
| EP2120208A1 (en) | Method and system for lesion segmentation | |
| CN107103605B (en) | Breast tissue segmentation method | |
| US8290247B2 (en) | Method and system for segmentation of tubular structures in 3D images | |
| US20090326363A1 (en) | Fused image modalities guidance | |
| CN107230206A (en) | A kind of 3D Lung neoplasm dividing methods of the super voxel sequence lung images based on multi-modal data | |
| Ming et al. | Rapid reconstruction of 3D neuronal morphology from light microscopy images with augmented rayburst sampling | |
| EP2827301B1 (en) | Image generation device, method, and program | |
| US9773325B2 (en) | Medical imaging data processing apparatus and method | |
| JP2021529622A (en) | Method and computer program for segmentation of light interference tomography images of the retina | |
| CN109801271A (en) | Localization method, device, computer equipment and the storage medium of calcification clusters | |
| JP5202841B2 (en) | Medical imaging system and method of segmenting an object of interest | |
| CN103903255B (en) | A kind of ultrasonic image division method and system | |
| CN114677436A (en) | Automatic cerebrovascular positioning method in brain CTA image based on model registration | |
| KR101251822B1 (en) | System and method for analysising perfusion in dynamic contrast-enhanced lung computed tomography images | |
| JP2006521150A5 (en) | ||
| EP1794717B1 (en) | Conformal segmentation of organs in medical images | |
| Karimov et al. | Guided volume editing based on histogram dissimilarity | |
| Levinski et al. | Interactive surface-guided segmentation of brain MRI data | |
| CN115018825A (en) | Coronary artery dominant type classification method, classification device and storage medium | |
| Zhuo et al. | Local adaptive segmentation algorithm for 3-D medical image based on robust feature statistics |
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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |