CN105741293B - The method for positioning organ on medical image - Google Patents
The method for positioning organ on medical image Download PDFInfo
- Publication number
- CN105741293B CN105741293B CN201610068472.XA CN201610068472A CN105741293B CN 105741293 B CN105741293 B CN 105741293B CN 201610068472 A CN201610068472 A CN 201610068472A CN 105741293 B CN105741293 B CN 105741293B
- Authority
- CN
- China
- Prior art keywords
- image
- organ
- sectioning image
- sectioning
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30008—Bone
- G06T2207/30012—Spine; Backbone
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30061—Lung
Abstract
A kind of method of organ on positioning medical image, comprising the following steps: step S1, input includes the medical image of several sectioning images；Step S2, the image of input is pre-processed, filters out non-body portion pixel；Step S3, connected domain number is calculated to every layer of sectioning image, by judging connected domain number and position, removes the part except the first organ, confirm that medical image includes the first organ；Characteristic value is calculated to every layer of sectioning image and obtains several characteristic values, several characteristic values and the number of plies of sectioning image form indicatrix, calculating characteristic value includes calculating every layer of sectioning image the ratio of the elemental area totality portion elemental area relatively of grey scale pixel value or CT value between the first range, and the sectioning image where organ is oriented according to ratio.So set, can be with quick positioner official location, and accuracy is high.
Description
Technical field
The present invention relates to the localization methods of organ-tissue in the processing of medical domain image more particularly to three-dimensional CT image.
Background technique
Organ-tissue identifies and positions method in existing three-dimensional CT image, for example, the method based on machine learning, the party
Method previous work is complicated, is related to a large amount of training images and collects and pre-process, needs to design complicated classifier, identify and position meter
It is higher to calculate complexity.In many image processing applications, for example segmentation, registration, automatic identification image locations, image are slightly aligned
Deng, need to carry out image locations or organ-tissue it is preliminary identify and judge, at this point, with greater need for a kind of for image itself
Quickly, easy implementation method.
Therefore, it is necessary to be improved to the localization method of organ-tissue in existing three-dimensional CT image, improve positioning
Speed.
Summary of the invention
The purpose of the present invention is to provide a kind of methods of organ on positioning medical image, for improving locating effect.
In order to realize aforementioned invention purpose, the present invention provides a kind of method of organ on positioning medical image, including following
Step:
Step S1, input includes the medical image of several sectioning images；
Step S2, the image of input is pre-processed, filters out non-body portion pixel；
Step S3, connected domain number in spongiosa region is calculated to every layer of sectioning image, by judging connected domain number and position,
The part except the first organ is removed, confirms that medical image includes the first organ；Characteristic value is calculated to every layer of sectioning image
And several characteristic values are obtained, the number of plies of several characteristic values and sectioning image forms indicatrix, and calculating characteristic value includes to every layer
Sectioning image calculates the elemental area total picture in totality portion specific region relatively of grey scale pixel value or CT value between the first range
The ratio of vegetarian noodles product, the sectioning image where organ is oriented according to ratio.
Preferably, the characteristic value that calculates further includes calculating every layer of sectioning image the ratio of width to height of spongiosa region, obtains one
Item is using the number of plies of sectioning image as the ratio of width to height indicatrix of axis of abscissas；Spongiosa region area is calculated to every layer of sectioning image,
Obtain the body portion area change feature curve using the number of plies of sectioning image as axis of abscissas.
Preferably, first organ includes lower limb, trunk and neck, and connected domain number and position packet are judged in step S3
It includes and judges that connected domain is three and two connected domains positioned at two sides, removing the part except the first organ includes that removal is located at
Two connected domains of two sides are the arm segment removed in image.
Preferably, in step S3 sectioning image connected domain number be two, then judge lower limb connected domain number be two
A sectioning image.
Preferably, first range is 350HU~3000HU, and step S3 includes the extreme point for finding indicatrix, if
The connected domain number of the corresponding sectioning image of extreme point is 2, then knee joint position is 2 to cut in extreme point corresponding connected domain number
Picture.
Preferably, the total pixel in the specific region is totality portion pixel, and first range is -910HU~-200HU, such as
The ratio of elemental area of the CT value between -910HU~-200HU totality portion elemental area relatively is greater than on fruit sectioning image
0.2, and totality portion elemental area is greater than π * 100cm2, it is determined that chest is located at the sectioning image.
Preferably, step S3 includes the maximum value for calculating specific curves, judges that lung top is located at curve along maximum value bottom right
The corresponding sectioning image of extreme point on edge drops.
Preferably, step S3 includes calculating between -910HU~-200HU of each sectioning image body center following region
The ratio of total pixel area totality portion elemental area relatively forms accounting curve, judges that the base of lung is located at accounting curve along ratio
The corresponding sectioning image of extreme point of the left failing edge of maximum value.
Preferably, step S3, which is included in CT image, is partitioned into two lungs, calculate between each two lung of sectioning image CT value-
Elemental area between 20HU~70HU, the heart centre elemental area of CT value between -20HU~70HU between two lungs
Sectioning image corresponding to maximum value.
Preferably, step S3 includes the company for calculating every layer of sectioning image region of the CT value between -910HU~-200HU
The number and area in logical domain, abdomen is located at connected domain number greater than 10, and connected domain average area is less than π * 4cm2Slice map
As upper, average area calculating is the connected domain by removing minimum area and maximum area, asks flat to the area of remaining connected domain
Mean value.
Preferably, calculate each sectioning image body center with left region calculate indicatrix, the first range be -20HU~
70HU, liver top are located at sectioning image corresponding to the maximum point of the indicatrix variable gradient.
Preferably, calculate each sectioning image body center with left region calculate indicatrix, the first range be -20HU~
70HU, liver centre are located at indicatrix sectioning image corresponding to the highest point in thorax abdomen sectioning image.
Preferably, the total pixel in the specific region is totality portion pixel, and first range is 350HU~3000HU, head
Positioned at the ratio of width to height less than 0.8, and totality portion elemental area is less than π * 100cm2, elemental area phase of the CT value between the first range
0.2 is greater than to the ratio of overall portion's elemental area, connected domain number is sectioning image corresponding to 1；Neck is less than positioned at the ratio of width to height
0.8, and totality portion elemental area is less than π * 100cm2, elemental area of the CT value between the first range totality portion pixel faces relatively
For long-pending ratio less than 0.15, connected domain number is sectioning image corresponding to 1.
Preferably, within the scope of the sectioning image containing head, elemental area of the CT value between the first range totality portion relatively
There are two extreme points for the ratio tool of elemental area；Elemental area with CT value between -20HU~70HU totality portion picture relatively again
The ratio of vegetarian noodles product distinguishes described two extreme points, and head middle layer is located at the corresponding sectioning image of the big extreme point of ratio, cranium
Bone bottom is located at the corresponding sectioning image of another extreme point.
Preferably, the characteristic value that calculates further includes calculating every layer of sectioning image the ratio of width to height of spongiosa region, obtains one
Item is using the number of plies of sectioning image as the ratio of width to height indicatrix of axis of abscissas；First range is -200HU~-20HU, described
The total pixel in specific region is totality portion pixel, calculates pixel faces of the HU value between -200HU~-20HU to every layer of sectioning image
The accounting of product totality portion elemental area relatively, if the accounting is greater than 0.45, and described the ratio of width to height is greater than 1.5, then corresponding
Sectioning image contains pelvis.
The present invention passes through step S3: step S3, connected domain number is calculated to every layer of sectioning image, by judging connected domain
Several and position removes the part except the first organ, confirms that medical image includes the first organ；To every layer of sectioning image meter
It calculates characteristic value and obtains several characteristic values, the number of plies of several characteristic values and sectioning image forms indicatrix, calculates characteristic value packet
It includes total with respect to specific region to the elemental area of every layer of sectioning image calculating grey scale pixel value or CT value between the first range
The ratio of elemental area, the sectioning image where organ is oriented according to ratio, quick and precisely orients the slice where organ
Image range provides important initial position message for next step image analysis.
Detailed description of the invention
Fig. 1 illustrates that the step process that the method for organ on medical image is positioned in the embodiment of the present invention.
Fig. 2 illustrates that the CT image inputted in the embodiment of the present invention.
Fig. 3 is illustrated that in the embodiment of the present invention only comprising the CT image of lower limb, trunk and neck.
Fig. 4 illustrates that the head middle layer that Coronal CT image is oriented along Z-direction in the embodiment of the present invention, skull
Bottom.
Fig. 5 illustrates that Coronal CT image is along the chest, abdomen, pelvis that Z-direction is oriented in the embodiment of the present invention
Organ.
Indicatrix in the embodiment of the present invention of Fig. 6 signal.
Specific embodiment
The present invention is described in further detail below in conjunction with the drawings and specific embodiments.It is wanted according to following explanation and right
Book is sought, advantages and features of the invention will become apparent from.It should be noted that attached drawing is all made of very simplified form and using non-
Accurately ratio, only for the purpose of facilitating and clarifying the purpose of the embodiments of the invention.
It please refers to shown in Fig. 1, the method that organ on medical image is positioned in the embodiment of the present invention is device on positioning CT image
The method of official, specifically includes the following steps:
Step S1: input includes several medical images along Z-direction arrangement sectioning image, and medical image can scheme for CT
Picture or magnetic resonance imaging image, CT image include volume data (volume data).Z-direction can be head-to-toe direction.
Step S2: pre-processing CT image, pretreatment the following steps are included:
Background process is removed to the CT image of input, for filtering out the non-physical feeling such as bed board, fixture
Pixel (non-body portion pixel).
Smothing filtering is carried out to image, is mainly used for removing noise.
Step S3: the organ and positioning organ for judging that CT image is included are identified and positioned to the organ on image
Group is woven in the position of image Z-direction, comprising the following steps:
Connected domain number in spongiosa region is calculated to every layer of sectioning image (slice), by judging connected domain number and position,
By taking Fig. 2 as an example, show that the sectioning image connected domain number is 3, remove the connected domain for being located at the correspondence arm regions of two sides, such as
As shown in figure 3, making CT image only includes the first organ: lower limb, thorax abdomen i.e. trunk and head to obtain several sectioning images
Neck.
Position incidence
It includes: the ratio of width to height for 1) calculating every layer of slice image spongiosa region that characteristic value, which calculates, obtain one with slice
The number of plies (slice number) is axis of abscissas, the ratio of width to height indicatrix that aspect ratio value is axis of ordinates；2) every layer is sliced
Image calculates spongiosa region area, show that spongiosa region area is the body portion face of axis of ordinates to be sliced the number of plies as axis of abscissas
Product variation characteristic curve；3) relatively total to total pixel area of the every layer of sectioning image calculating CT value between 350HU~3000HU
The accounting of body portion elemental area show that accounting is the accounting indicatrix of axis of ordinates to be sliced the number of plies as axis of abscissas.
Judging rules: if the ratio of width to height is less than certain value, such as 0.8, and totality portion elemental area is less than certain value,
Such as π * 10*10cm2, and the elemental area accounting between 350HU~3000HU is greater than certain value, such as 0.2, connected domain
Number is 1, then judges the sectioning image containing head.
If the ratio of width to height is less than 0.8, and totality portion elemental area (bulk area) is less than π * 10*10cm2, and 350HU~
For elemental area accounting between 3000HU less than 0.15, the sectioning image that connected domain number is 1 contains neck.
Position head centre and basis cranii
Within the scope of the sectioning image containing head, the elemental area accounting between 350HU~3000HU is calculated, can obtain two
A extreme point, an extreme point correspond to skull bottom, another extreme point corresponds to head middle layer, then between -20HU~70HU
Elemental area accounting, distinguish the two extreme points, head middle layer is located at the corresponding sectioning image of the big extreme point of accounting, then
Skull bottom is located at the corresponding sectioning image of another extreme point.
Position chest
It includes: 1) to calculate pixel total face of the HU value between -910HU~-200HU to every layer of sectioning image that characteristic value, which calculates,
The accounting of product totality portion elemental area relatively, obtains the accounting indicatrix to be sliced the number of plies as axis of abscissas.
Judging rules: if the elemental area accounting on sectioning image between -910HU~-200HU is greater than 0.2, and dignity
Product is greater than π * 10*10cm2, then contain chest.
Position lung top
The maximum value of the accounting indicatrix of the total pixel area between aforementioned -910HU~-200HU is calculated, curve is along most
The extreme point for being worth right failing edge greatly is lung top.
Position the base of lung
The total pixel area calculated between -910HU~-200HU of each sectioning image body center following region is relatively total
The accounting of body portion elemental area obtains the accounting curve to be sliced the number of plies as axis of abscissas, and curve is along the left failing edge of maximum value
Extreme point is the base of lung.
It positions among heart
Two lungs are partitioned into, are heart middle layer when calculating the elemental area maximum between m- 20HU~70HU of two lungs.
Position abdomen
It includes: the company for 1) calculating every layer of sectioning image region of the CT value between -910HU~-200HU that characteristic value, which calculates,
The number in logical domain and the center of area and each connected domain.
Judging rules: if connected domain number is greater than 10 on sectioning image, and average area is less than π * 2*2cm2(centre plane
Product calculation method: remove the connected domain of minimum area and maximum area, remaining connected domain area is averaged), then contain abdomen.
Position liver top
Characteristic value calculating includes: to calculate each slice body center with the total face of pixel between the -20HU in left region~70HU
The accounting of product totality portion elemental area relatively, obtains the accounting curve to be sliced the number of plies as axis of abscissas, curvilinear motion gradient is most
Big point is liver top.
It positions among liver
Characteristic value calculating includes: that 1) to calculate each slice body center total with the pixel between the -20HU in left region~70HU
The accounting of area totality portion elemental area relatively, show that the accounting curve to be sliced the number of plies as axis of abscissas, curve are cut in trunk
Highest point within the scope of picture is liver middle layer.
Position pelvis
It includes: 1) to calculate elemental area of the HU value between -200HU~-20HU to every layer of sectioning image that characteristic value, which calculates,
The accounting of totality portion elemental area relatively obtains the accounting indicatrix to be sliced the number of plies as axis of abscissas；2) every layer is sliced
Image calculates the ratio of width to height of spongiosa region, obtains the ratio of width to height indicatrix to be sliced the number of plies as reference axis.
Judging rules: if the ratio of width to height is greater than 1.5, and the elemental area accounting between -200HU~-20HU is greater than 0.45,
Then corresponding sectioning image contains pelvis.
Position femur and hip joint
It includes: to calculate elemental area of the CT value between 350HU~3000HU to every layer of sectioning image to account for that characteristic value, which calculates,
The indicatrix of overall portion's elemental area ratio.
Judging rules: the extreme point that curve is greater than 0.15 in pelvis slice range is found, if there are two be greater than 0.15
Extreme point is then femoral joint close to image the last layer, another extreme point then corresponds to hip joint, if there is one 0.15
Extreme point, then judge the extreme point position respectively with image foremost layer and the layer of last surface layer away from, with the layer of foremost layer away from
Greater than the layer with back layer away from being then hip joint, be otherwise femur.
Position lower limb
It includes: the number and area for calculating every layer of sectioning image spongiosa region connected domain that characteristic value, which calculates,.
Judging rules: connected domain number is 2 on sectioning image, then contains lower limb.
Position knee
It includes: to calculate elemental area phase of the CT value between 350HU~3000HU to every layer of sectioning image that characteristic value, which calculates,
To the accounting of overall portion's elemental area, the accounting indicatrix to be sliced the number of plies as axis of abscissas is obtained；
Judging rules: finding accounting indicatrix extreme point, and the connected domain number of sectioning image is 2 at extreme point, then
At knee joint.
The method of organ is based on CT image grayscale statistical information, grey scale change rule on positioning medical image provided by the invention
Rule and organ-tissue shape, the positional relationship etc. between organ-tissue, method is simple and easy.
The method of organ proposes indicatrix and enriches on positioning medical image provided by the invention, can quickly judge first
Position contained by CT image, can further sectioning image range corresponding to histoorgan in position contained by Quick positioning map picture, it is fixed
Position accuracy is high, and positioning result can be widely used in other image processing applications, such as segmentation, registration, improves at pictures subsequent
The efficiency and accuracy rate of reason.
On the positioning medical image of the above embodiment of the present invention the method for organ can in such as computer software, hardware or
It is implemented in the combined computer-readable medium of computer software and hardware.For hardware implementation, in the present invention
Described embodiment can be at one or more specific integrated circuits (ASIC), digital signal processor (DSP), digital signal
Manage device (DAPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller
The selection of device, microprocessor, other electronic devices for executing above-mentioned function or above-mentioned apparatus is combined to be implemented.In portion
In the case of point, this kind of embodiment can be implemented by controller.
For software implementation, embodiment described in the present invention can by such as program module (procedures) and
The independent software modules such as function module (functions) are implemented, wherein each module execute it is one or more this
The function and operation of described in the text.Software code can be implemented by the application software write in properly programmed language,
It can store in memory, be executed by controller or processor.
Although the present invention is described with reference to current specific embodiment, those of ordinary skill in the art
It should be appreciated that above embodiment is intended merely to illustrate the present invention, can also make in the case where no disengaging spirit of that invention
Various equivalent change or replacement out, therefore, as long as to the variation of above-described embodiment, change in spirit of the invention
Type will all be fallen in the range of following claims.
Claims (15)
1. a kind of method of organ on positioning medical image, comprising the following steps:
Step S1, input includes the medical image of several sectioning images；
Step S2, the image of input is pre-processed, filters out non-body portion pixel；
Step S3, connected domain number is calculated to every layer of sectioning image, by judging connected domain number and position, removes the first organ
Except part, confirm that medical image includes the first organ；Characteristic value is calculated to every layer of sectioning image and obtains several spies
The number of plies of value indicative, several characteristic values and sectioning image forms indicatrix, and calculating characteristic value includes calculating every layer of sectioning image
Ratio of the elemental area of grey scale pixel value or CT value between the first range with respect to the total elemental area in specific region, the spy
Determining the total pixel in region is totality portion pixel, and the sectioning image where the first organ is oriented according to ratio.
2. positioning the method for organ on medical image as described in claim 1, which is characterized in that the calculating characteristic value is also wrapped
The ratio of width to height for calculating every layer of sectioning image spongiosa region is included, is obtained one high using the number of plies of sectioning image as the width of axis of abscissas
Compare indicatrix；Spongiosa region area is calculated to every layer of sectioning image, is obtained using the number of plies of sectioning image as the body of axis of abscissas
Portion's area change feature curve.
3. positioning the method for organ on medical image as described in claim 1, which is characterized in that under first organ includes
Limb, trunk and neck judge connected domain number in step S3 and position include judging connected domain for three and positioned at two sides
Two connected domains, removing the part except the first organ includes that removal is located at two connected domains of two sides and removes hand in image
Arm section.
4. positioning the method for organ on medical image as described in claim 1, which is characterized in that sectioning image connects in step S3
Logical domain number is two, then judges the sectioning image that lower limb are two in connected domain number.
5. as claimed in claim 4 on positioning medical image organ method, which is characterized in that first range is
350HU~3000HU, step S3 include the extreme point for finding indicatrix, if the connected domain of the corresponding sectioning image of extreme point
Number is 2, then the sectioning image that knee joint position is 2 in the corresponding connected domain number of extreme point.
6. the method for positioning organ on medical image as described in claim 1, first range is -910HU~-200HU,
If the ratio of elemental area of the CT value between -910HU~-200HU totality portion elemental area relatively is greater than on sectioning image
0.2, and totality portion elemental area is greater than π * 100cm2, it is determined that chest is located at the sectioning image.
7. positioning the method for organ on medical image as claimed in claim 6, which is characterized in that step S3 includes calculating feature
The maximum value of curve judges the corresponding sectioning image of extreme point that lung top is located at curve along the right failing edge of maximum value.
8. positioning the method for organ on medical image as claimed in claim 6, which is characterized in that step S3 includes calculating each
The ratio of total pixel area totality portion elemental area relatively between -910HU~-200HU of sectioning image body center following region
Example forms accounting curve, judges the corresponding slice of extreme point that the base of lung is located at accounting curve along the left failing edge of ratio maximum value
Image.
9. positioning the method for organ on medical image as claimed in claim 6, which is characterized in that step S3 is included in CT image
In be partitioned into two lungs, elemental area of the CT value between -20HU~70HU between each two lung of sectioning image is calculated, among heart
The sectioning image corresponding to elemental area maximum value of the CT value between -20HU~70HU between two lungs.
10. positioning the method for organ on medical image as claimed in claim 6, which is characterized in that step S3 includes to every layer
Sectioning image calculates the number and area of the connected domain in region of the CT value between -910HU~-200HU, and abdomen is located at connected domain
Number is greater than 10, and connected domain average area is less than π * 4cm2Sectioning image on, average area calculating be by removing minimum
The connected domain of area and maximum area averages to the area of remaining connected domain.
11. positioning the method for organ on medical image as claimed in claim 10, which is characterized in that calculate each sectioning image
Body center calculates indicatrix with left region, and the first range is -20HU~70HU, and liver top is located at the indicatrix variable gradient
Sectioning image corresponding to maximum point.
12. positioning the method for organ on medical image as claimed in claim 10, which is characterized in that calculate each sectioning image
Body center calculates indicatrix with left region, and the first range is -20HU~70HU, is located at indicatrix among liver and cuts in thorax abdomen
Sectioning image corresponding to highest point in picture.
13. as claimed in claim 2 on positioning medical image organ method, which is characterized in that first range is
350HU~3000HU, head are located at the ratio of width to height less than 0.8, and totality portion elemental area is less than π * 100cm2, CT value is in the first range
Between elemental area totality portion elemental area relatively ratio be greater than 0.2, connected domain number be 1 corresponding to sectioning image；
Neck is located at the ratio of width to height less than 0.8, and totality portion elemental area is less than π * 100cm2, elemental area of the CT value between the first range
For the ratio of totality portion elemental area relatively less than 0.15, connected domain number is sectioning image corresponding to 1.
14. positioning the method for organ on medical image as claimed in claim 13, which is characterized in that in the sectioning image containing head
In range, there are two extreme points for the ratio tool of elemental area of the CT value between the first range totality portion elemental area relatively；Again
Described two extreme points are distinguished with the ratio of elemental area of the CT value between -20HU~70HU totality portion elemental area relatively,
Head middle layer is located at the corresponding sectioning image of the big extreme point of ratio, and skull bottom is located at the corresponding slice map of another extreme point
Picture.
15. positioning the method for organ on medical image as described in claim 1, which is characterized in that the calculating characteristic value is also
The ratio of width to height including calculating every layer of sectioning image spongiosa region, obtain one using the number of plies of sectioning image as the width of axis of abscissas
Higher bit levies curve；First range is -200HU~-20HU, to every layer of sectioning image calculate HU value -200HU~-
The accounting of elemental area totality portion elemental area relatively between 20HU, if the accounting is greater than 0.45, and described the ratio of width to height
Greater than 1.5, then corresponding sectioning image contains pelvis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610068472.XA CN105741293B (en) | 2016-01-30 | 2016-01-30 | The method for positioning organ on medical image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610068472.XA CN105741293B (en) | 2016-01-30 | 2016-01-30 | The method for positioning organ on medical image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105741293A CN105741293A (en) | 2016-07-06 |
| CN105741293B true CN105741293B (en) | 2019-03-05 |
Family
ID=56247292
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610068472.XA Active CN105741293B (en) | 2016-01-30 | 2016-01-30 | The method for positioning organ on medical image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105741293B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650734B (en) * | 2016-12-29 | 2020-11-24 | 上海联影医疗科技有限公司 | Positioning image subregion identification method, medical image display method and device |
| CN106815849A (en) * | 2017-01-18 | 2017-06-09 | 宁波江丰生物信息技术有限公司 | A kind of method for recognizing biopsy tissues |
| CN106898012A (en) * | 2017-01-19 | 2017-06-27 | 浙江大学 | CT images thoracic cavity profile automated detection method |
| CN107067420A (en) * | 2017-04-28 | 2017-08-18 | 上海联影医疗科技有限公司 | Image processing method, device and equipment |
| CN110555860B (en) * | 2018-06-04 | 2023-11-14 | 青岛海信医疗设备股份有限公司 | Method for labeling rib areas in medical image, electronic equipment and storage medium |
| CN111815590A (en) * | 2020-06-29 | 2020-10-23 | 苏州润心医疗器械有限公司 | Method and system for acquiring heart gravity center and spine gravity center based on CT sequence image |
| CN113469935B (en) * | 2021-04-15 | 2023-06-13 | 卡本(深圳)医疗器械有限公司 | Automatic detection and positioning method for posterior superior iliac spine based on CT image |
| CN114067361B (en) * | 2021-11-16 | 2022-08-23 | 西北民族大学 | SPECT imaging non-pathological hot area segmentation method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08136255A (en) * | 1994-11-08 | 1996-05-31 | Asia Kosoku Kk | Slice measuring method useful for solid modeling |
| CN1912927A (en) * | 2006-08-25 | 2007-02-14 | 西安理工大学 | Semi-automatic partition method of lung CT image focus |
| TWI277009B (en) * | 2005-04-29 | 2007-03-21 | Chunghwa Telecom Co Ltd | Picture positioning method and device of colored digital image |
| CN1943513A (en) * | 2006-11-08 | 2007-04-11 | 沈阳东软医疗系统有限公司 | Processing device method and system for CT image |
-
2016
- 2016-01-30 CN CN201610068472.XA patent/CN105741293B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08136255A (en) * | 1994-11-08 | 1996-05-31 | Asia Kosoku Kk | Slice measuring method useful for solid modeling |
| TWI277009B (en) * | 2005-04-29 | 2007-03-21 | Chunghwa Telecom Co Ltd | Picture positioning method and device of colored digital image |
| CN1912927A (en) * | 2006-08-25 | 2007-02-14 | 西安理工大学 | Semi-automatic partition method of lung CT image focus |
| CN1943513A (en) * | 2006-11-08 | 2007-04-11 | 沈阳东软医疗系统有限公司 | Processing device method and system for CT image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105741293A (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741293B (en) | The method for positioning organ on medical image | |
| Zoroofi et al. | Automated segmentation of acetabulum and femoral head from 3-D CT images | |
| US9943286B2 (en) | Ultrasonographic images processing | |
| US8094906B2 (en) | Bone segmentation | |
| CN109727235B (en) | Organ automatic delineation algorithm based on deep learning | |
| CN106163404B (en) | Lung segmentation and bone suppression technology for ray image | |
| US9214028B2 (en) | Method for segmenting a three-dimensional image data set, corresponding computer program and corresponding system | |
| US11710246B2 (en) | Skin 3D model for medical procedure | |
| CN105389815B (en) | Mammary gland image registration method and device | |
| US20190392552A1 (en) | Spine image registration method | |
| Mainprize et al. | Shape completion by U-Net: an approach to the AutoImplant MICCAI cranial implant design challenge | |
| CN110084766A (en) | A kind of image processing method, device and electronic equipment | |
| Yadollahi et al. | The use of combined illumination in segmentation of orthodontic bodies | |
| CN115137342A (en) | Image acquisition medical system and method based on deep learning | |
| Gooßen et al. | Model-based segmentation of pediatric and adult joints for orthopedic measurements in digital radiographs of the lower limbs | |
| O’Neill et al. | Segmentation of cam-type femurs from CT scans | |
| KR101494975B1 (en) | Nipple automatic detection system and the method in 3D automated breast ultrasound images | |
| CN112184664A (en) | Vertebra detection method and computer equipment | |
| Wu et al. | Fracture detection and quantitative measure of displacement in pelvic CT images | |
| Smith et al. | A hierarchical method based on active shape models and directed Hough transform for segmentation of noisy biomedical images; application in segmentation of pelvic X-ray images | |
| Lin et al. | Nipple detection in mammogram using a new convolutional neural network architecture | |
| Thakur et al. | Optimization of Direct Slicing Process Using DICOMS for Additive Manufacturing | |
| CN105608702B (en) | A kind of background suppression method and system of MRA brain image datas | |
| Dias et al. | Automatic sternum segmentation in thoracic MRI | |
| CN111598947B (en) | Method and system for automatically identifying patient position by identification features |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201807 No. 2258 Chengbei Road, Jiading Industrial Zone, Jiading District, Shanghai. Patentee after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 No. 2258 Chengbei Road, Jiading Industrial Zone, Jiading District, Shanghai. Patentee before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |