CN109381212A - A kind of image formation control method and system - Google Patents
A kind of image formation control method and system Download PDFInfo
- Publication number
- CN109381212A CN109381212A CN201811131376.0A CN201811131376A CN109381212A CN 109381212 A CN109381212 A CN 109381212A CN 201811131376 A CN201811131376 A CN 201811131376A CN 109381212 A CN109381212 A CN 109381212A
- Authority
- CN
- China
- Prior art keywords
- interest
- area
- sweep parameter
- locating plate
- scan
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000015572 biosynthetic process Effects 0.000 title claims abstract description 12
- 238000003384 imaging method Methods 0.000 claims abstract description 36
- 238000010801 machine learning Methods 0.000 claims description 31
- 210000000056 organ Anatomy 0.000 claims description 18
- 238000003909 pattern recognition Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 210000001519 tissue Anatomy 0.000 description 19
- 210000002216 heart Anatomy 0.000 description 17
- 230000008569 process Effects 0.000 description 7
- 238000002591 computed tomography Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 6
- 238000012417 linear regression Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 4
- 230000001537 neural effect Effects 0.000 description 4
- 210000003625 skull Anatomy 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 210000004556 brain Anatomy 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 210000003695 paranasal sinus Anatomy 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000004072 lung Anatomy 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000002600 positron emission tomography Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/54—Control of apparatus or devices for radiation diagnosis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/02—Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
- A61B6/03—Computerised tomographs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B6/00—Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
- A61B6/54—Control of apparatus or devices for radiation diagnosis
- A61B6/545—Control of apparatus or devices for radiation diagnosis involving automatic set-up of acquisition parameters
Abstract
The invention discloses a kind of image formation control method and systems, which comprises obtains at least one locating plate；Obtain the corresponding scan protocols of at least one described locating plate；Area-of-interest is determined according to the scan protocols and at least one described locating plate；Generate the sweep parameter of the area-of-interest；And the scan image of the area-of-interest is generated based on the interested sweep parameter control.Sweep parameter is automatically determined based on locating plate and then controls the imaging method for generating the scan image of area-of-interest, can reduce the time of adjustment sweep parameter and promotes accuracy rate of diagnosis, is a kind of simple and effective method.
Description
Technical field
It is the present invention relates to field of medical technology, in particular to a kind of sweep parameter is automatically determined according to locating plate to be imaged
The method and system of control.
Background technique
Computer tomography equipment (Computed Tomography, CT) is the common diagnostic imaging equipment of hospital.CT
Human body privileged site is scanned according to certain thickness level using X-ray beam, the density degree respectively organized due to human body
Difference causes the penetration level of X-ray different, can detecte the X-ray signal through human body by detector, and by the X
Ray signal is converted into digital signal and is handled by computer, generates CT image, medical staff can be according to the image to people
Body is detected.
Typical CT is operated, operator can obtain locating plate firstly the need of positioning scanning is carried out, by positioning scanning
(Topogram), then operator can select suitable sweep parameter according to locating plate and mark prescan portion on locating plate
Beginning scan position and end scan position, angle thickness of position etc., further according to the label on locating plate to the particular portion of human body
Position is scanned.
Specifically, as shown in Figure 1, CT system carries out the method for positioning scanning the following steps are included: patient (101) lies low
On examination couch, X-ray tube and patient keep opposing stationary, carry out CT scan during examination couch is at the uniform velocity mobile, obtain such as Fig. 1
Shown in locating plate (102)；Positioning picture is shown on locating plate, the starting position parameter of available examination couch in CT system
(L1), the end position parameter (L4) of examination couch, the end position ginseng of the starting position parameter (L1 ') and positioning picture that position picture
Number (L4 ')；Then the beginning scanning position parameter at prescan position can be above marked in positioning picture with mark line or planbox
(L2 ') and terminate scanning position parameter (L3 ').It is one-to-one with bed code position in the horizontal direction according to the above location parameter
Relationship can obtain beginning scanning position parameter (L2) and end scanning position parameter (L3) of the prescan position on examination couch.
In the prior art, above-mentioned position fixing process is usually to be manually operated to complete by doctor, and this mode will appear following
Problem: 1) accuracy rate for manually adjusting sweep parameter depends on the experience of operator, and operation is unskilled to will cause sweep parameter standard
True rate is relatively low, influences the accuracy of diagnostic result；2) operating time is longer, reduces working efficiency.Therefore, it is necessary to grind
Sweep parameter can be automatically selected based on locating plate to control the method and system of imaging by sending out one kind, help to reduce adjustment scanning
The time of parameter simultaneously promotes accuracy rate of diagnosis.
Summary of the invention
Sweep parameter cannot be automatically selected in medical imaging devices scanning process for the prior art, and then it is emerging to influence sense
The problem of interesting sector scanning image obtains, the purpose of the present invention is to provide one kind to automatically determine area-of-interest based on locating plate
Sweep parameter controls the method and system for generating the image of area-of-interest using the area-of-interest sweep parameter, can be with
It reduces the time of adjustment sweep parameter and promotes accuracy rate of diagnosis, be a kind of simple and effective method.
To achieve the above object of the invention, technical solution provided by the invention is as follows:
On the one hand, the present invention provides a kind of imaging methods, which comprises obtains at least one locating plate；It obtains
The corresponding scan protocols of described at least one locating plate, the scan protocols include scanned position；According to the scan protocols and
At least one described locating plate automatically determines area-of-interest；Generate the sweep parameter of the area-of-interest；And based on institute
State the scan image that interested sweep parameter control generates the area-of-interest.
In the present invention, at least one described locating plate includes P-A Cephalomatrics or lateral projection.
In the present invention, area-of-interest packet is automatically determined according to the scan protocols and at least one described locating plate
It includes: obtaining the relevant characteristics of image of at least one described locating plate；And it is based on described image feature, utilize the side of pattern-recognition
Method determines the area-of-interest.
In the present invention, the sweep parameter for generating area-of-interest includes: to join the area-of-interest and scanning
Data in number database are matched, and sweep parameter corresponding with the area-of-interest is obtained.
In the present invention, the sweep parameter database is joined including at least scanning corresponding with human organ and/or tissue
Number.
In the present invention, the sweep parameter for generating area-of-interest includes: that the area-of-interest is input to instruction
The machine learning model perfected generates the sweep parameter of the area-of-interest by the machine learning model；Wherein, described
Machine learning model is formed by history scanning area and the training of history sweep parameter.
In the present invention, the sweep parameter control based on the area-of-interest generates the scanning figure of area-of-interest
The method of picture includes: that the sweep parameter of the area-of-interest of the generation is automatically write the scan protocols, is swept according to described
Agreement is retouched to control the scan image for generating the area-of-interest.
On the one hand, the present invention provides a kind of imaging control apparatus, described device includes at least a processor and deposits
Storage media, the storage medium is for storing computer instruction, and the processor is for executing the computer instruction to realize
Presently disclosed imaging method.
On the one hand, the present invention provides a kind of computer readable storage medium, the storage medium stores computer instruction,
After computer reads the computer instruction in storage medium, presently disclosed imaging method may be implemented.
On the one hand, the embodiment of the invention provides a kind of imaging control system, the system comprises acquiring units, interested
Area determination unit, sweep parameter generation unit and imaging control unit.The acquiring unit is for obtaining at least one positioning
Piece and the corresponding scan protocols of at least one described locating plate, the scan protocols include scanned position；The region of interest
Domain determination unit is used to automatically determine area-of-interest according to the scan protocols and at least one described locating plate；The scanning
Parameter generating unit is used to generate the sweep parameter of the area-of-interest；And the imaging control unit is used for based on described
The sweep parameter control of area-of-interest generates the scan image of the area-of-interest.
In the present invention, at least one described locating plate includes P-A Cephalomatrics or lateral projection.
In the present invention, the relevant image of at least one available described locating plate of the area-of-interest determination unit
Feature；And it is based on described image feature, the area-of-interest is determined using the method for pattern-recognition.
In the present invention, the sweep parameter generation unit can will be in the area-of-interest and sweep parameter database
Data matched, obtain corresponding with area-of-interest sweep parameter.
In the present invention, the sweep parameter database is joined including at least scanning corresponding with human organ and/or tissue
Number.
In the present invention, the area-of-interest can be input to trained machine by the sweep parameter generation unit
Learning model generates the sweep parameter of the area-of-interest by the machine learning model；Wherein, the machine learning mould
Type is formed by history scanning area and the training of history sweep parameter.
In the present invention, the imaging control unit can write the sweep parameter of the area-of-interest of the generation automatically
Enter the scan protocols, and according to the scan protocols to control the scan image for generating the area-of-interest.
Compared with prior art, beneficial effects of the present invention performance is as follows:
1) for adjusting sweep parameter compared to traditional manual, automatically determining sweep parameter based on locating plate not only can be square
Just the operation of doctor, and the time during CT scan can be greatly simplified, to improve clinical inspection efficiency；
2) area-of-interest of the positioning as in can be accurately identified using the method for pattern-recognition；
3) sweep parameter for the sweep parameter database information Auto-matching area-of-interest established is utilized；
4) sweep parameter of area-of-interest is automatically determined using trained machine learning model.
Detailed description of the invention
Fig. 1 is the schematic diagram that CT system obtains patient's prescan range using locating plate；
Fig. 2 is the structural schematic diagram of the imaging control system of the invention in conjunction with CT system；
Fig. 3 be it is of the invention based on locating plate automatically determine sweep parameter carry out imaging control exemplary process diagram；With
Fig. 4 is an example of area-of-interest of the invention.
Fig. 1 label: 101 be the real human body on examination couch that lies low, and 102 be to be swept by CT system to the real human body
The locating plate retouched；
Fig. 2 label: 200 be typical CT system, comprising: 201 be X-ray tube, and 202 be collimator, and 203 be X-ray,
204 be detector, and 205 be high pressure generator, and 206 be collimator driver, and 207 be rotating driver, and 208 be position control
Device, 209 be examination couch；210 be imaging control system, comprising: 211 be acquiring unit, and 212 be area-of-interest determination unit,
213 be sweep parameter generation unit, and 214 be imaging control unit.
Specific embodiment
To make the above purposes, features and advantages of the invention more obvious and understandable, with reference to the accompanying drawings and examples
Specific embodiments of the present invention will be described in detail.
In order to completely understand the present invention, referring to FIG. 2, indicate the present invention in a preferred embodiment thereof in conjunction with CT system
The structural schematic diagram of the imaging control system used.The CT system 200 including but not limited to X-ray tube 201, collimator 202,
X-ray 203, detector 204, high pressure generator 205, collimator driver 206, rotating driver 207, positioner 208
With examination couch 209.The imaging control system 210 includes acquiring unit 211, area-of-interest determination unit 212, sweep parameter
Generation unit 213 and imaging control unit 214.
Positioning scanning is carried out to obtain the locating plate of patient by CT system 200, and doctor can be according to the locating plate of patient
The anatomic landmarks for determining patient, to determine exact position and the range of CT scan.In positioning scanning process, patient can be with
It is lain on examination couch according to the posture (such as lying low) that operator requires, X-ray tube 201 and patient should keep opposing stationary.When sweeping
After retouching starting, operation control computer (not shown in figure 1) issues scan instruction, is revolving rotary frame (not shown in figure 1)
Designated position as defined in operator is rotated under the action of transcoder controller 207.High pressure generator 205 reaches rapidly requirement later
Voltage simultaneously makes the voltage and current of X-ray tube 201 be maintained at preset level during scanning, so that X-ray tube generates X
Beam 203, the X-ray beam 203 is after the calibration of collimator 202, the patient being placed through on examination couch 209 and generating unit
Divide decaying.The collimator 202 can be used to calibrate the X-ray beam 203 launched from X-ray tube 201 to desired width, specifically
Ground controls the collimator 202 by control collimator driver 206.Detector 204 can receive it is described through overdamping it
Rear X-ray beam 203 is simultaneously converted into corresponding electric signal.Data-acquisition system in the operation control computer simultaneously
(not shown in figure 1) acquires the electric signal with uniform sampling rate, and the electric signal is converted to digital signal.Then
Image generation system (not shown in figure 1) handles the digital signal to obtain locating plate.
The X-ray tube 201, collimator 202 and detector 204 can be fixed on the rotary frame.For ability
For the those of ordinary skill in domain it is found that carrying out in positioning scanning process in CT system, X-ray tube 201 and detector 204 should keep solid
It is fixed, while examination couch 209 is axial (perpendicular to the direction x and the direction y, as shown in Figure 2) mobile with constant speed edge, thus the CT
System 200 can be scanned the privileged site of patient and obtain corresponding locating plate.
Acquiring unit 211 can be used for obtaining at least one locating plate of its shooting from the CT system 200.Some
In embodiment, the locating plate can be P-A Cephalomatrics and/or lateral projection.The P-A Cephalomatrics refer to when X-ray tube 201 is located at human body
At position directly above, the CT system is by positioning the locating plate for scanning the privileged site of patient and obtaining.The lateral projection is
Refer to when the privileged site that X-ray tube 201 is located at the position of human body left or right side, and the CT system passes through positioning scanning patient
The locating plate of acquisition.Optionally, for the ordinary skill in the art, the CT system executes the behaviour of shooting locating plate
It is to be performed according to the scan protocols in the CT system.The scan protocols include scanner section corresponding with locating plate
Position and locating plate sweep parameter.
It is understood that helping to feel emerging simultaneously using P-A Cephalomatrics and lateral projection as the input of imaging control system 210
The interesting realization of area determination unit 212 accurately identifies and positions area-of-interest.
In some embodiments, acquiring unit 211 can directly or indirectly obtain at least one locating plate.Example
Such as, after operator issues acquisition instruction by the acquiring unit 211, the CT system 200 responds the acquisition instruction, and
The corresponding component of CT system is automatically adjusted to predeterminated position and (X-ray tube 201 is such as adjusted to 12 o'clock position or 3 o'clock position
Set or 9 o'clock position) directly acquire the locating plate.In another example after the CT system has executed positioning scanning,
The locating plate of generation is stored in an individual storage medium (such as database (not shown)), the acquiring unit
211 can obtain locating plate from the storage medium.
In some embodiments, the corresponding scan protocols of the available locating plate of acquiring unit 211.The scanning association
View includes locating plate scanned position.For example, the scanned position can be the tissue or organ of human body, such as nasal sinus, heart, lung
Portion etc..In some embodiments, the scan protocols further comprise sweep parameter.The sweep parameter includes but is not limited to institute
State the corresponding scan type of scanned position (such as unenhanced, enhancing scanning), conditions of exposure, the visual field (FOV), scanning angle and scanning model
It encloses.In some embodiments, the scanning range (for example, including starting scan position and end scan position) of the locating plate
Including area-of-interest to be scanned.It is, including the region of interest area image to be scanned in the locating plate.
Area-of-interest determination unit 212 determines area-of-interest for handling the locating plate of the acquisition
(Region of Interest,ROI).In some embodiments, the area-of-interest can be certain of human body to be scanned
One organ or tissue.Since organ or tissue different in human body has different attenuation coefficients, different devices to X-ray
Official or tissue locating plate generated have different characteristics.The area-of-interest determination unit 212 can be known by mode
Other method utilizes the image feature information of the different organ or tissue, and corresponding is swept based on set in scan protocols
Position and sweep parameter information are retouched, and then identifies the area-of-interest.Optionally, described image characteristic information includes but not
It is limited to Gradient Features, gray scale or color characteristic, boundary characteristic, provincial characteristics, textural characteristics, the shape feature, topology spy of image
It seeks peace the one or more of them such as relational structure.The mode identification method includes image processing method, for example, image filtering,
Image segmentation etc..
Specifically, it may be implemented to reduce or eliminate picture noise to image feature information by being filtered to image
Interference, further divide using the method for image segmentation or identify the area-of-interest.Optionally, typical image point
Segmentation method includes method based on edge detection, threshold segmentation method, the dividing method based on cluster, the segmentation side based on region
Method, edge detection method based on wavelet transformation etc..
In some embodiments, the area-of-interest determination unit 212 can also be by calling for pattern-recognition
First machine learning model identifies the area-of-interest.First machine learning model is stored in the operational calculator
In storage medium in.For example, the machine learning model for pattern-recognition is special by the image for inputting the locating plate
Reference breath, exports and identifies corresponding area-of-interest.
In some embodiments, the area-of-interest can be on locating plate with rectangle frame or one or more mark line
(as shown in Figure 1) identifies.
In some embodiments, the area-of-interest can be the die body for testing CT performance (such as CT value) (as marked
Quasi- uniform water mould).The CT of standard Water ball as shown in Figure 4 positions picture, the rectangle frame (planbox) of arrow meaning band in figure
The as described area-of-interest can determine CT positioning as being handled by the determination unit 212 interested
The area-of-interest.
Sweep parameter generation unit 213 can be communicated with the determination unit 212 interested, emerging to obtain the sense
The characteristic information (for example, location information of heart) in interesting region generates corresponding sweep parameter in turn.The sweep parameter can be with
Including but not limited to scan type (such as unenhanced, enhancing scanning), conditions of exposure, the visual field (FOV), scanning angle and scanning range
Deng.
In some embodiments, sweep parameter generation unit 213 can give birth to automatically according to the area-of-interest of the generation
At scanning range.For example, corresponding using pattern-recognition and inquiry in locating plate by the area-of-interest determination unit 212
The methods of scan protocols identify area-of-interest (e.g., heart).The sweep parameter generation unit 213 obtains heart fixed
Then coordinate in bit slice automatically generates heart scanning range according to the coordinate information, for example, starting scan position and end
Scan position, and the scanning range of the generation is written in the scan protocols of the CT system 200 and is controlled for heart
Axial scan.
In some embodiments, sweep parameter generation unit 213 can by area-of-interest to the generation with sweep
It retouches the data in parameter database and match and then obtain the corresponding sweep parameter of the area-of-interest.The sweep parameter
Database includes at least sweep parameter corresponding with human organ and/or tissue.Optionally, the sweep parameter data-base recording
The history scan data of a large amount of different patients.It, can will be corresponding for example, when the CT system 200 scans a certain patient
Sweep parameter uploads to the sweep parameter database and is stored.In some embodiments, the sweep parameter database can
To record the sweep parameter data of a Jia Huoduojia medical institutions or scientific research institution.Optionally, the sweep parameter database is also
Have recorded default or preset tissue or organ scan's parameter.For example, default scan type is flat using cranium brain as sweep object
It sweeps, tube voltage is 120~140kV, tube current be 180~220mAs, scan vision (FOV) be 25cm, scanning range is to listen
Corner of the eyes line is that benchmark line is scanned up to calvarium (for example, the position of canthomeatal line correspondence proving bed is A, the position of calvarium correspondence proving bed
It is set to B).
For example, medical history and sign information that sweep parameter generation unit 213 can further analyze patient to be scanned are (such as
Whether have morbidity history, gender, height, weight etc.), and inquired by access scan parameter database (not shown) whether
In the presence of the history sweep parameter similar or identical with the patient, and if it exists, can be then arranged automatically according to history sweep parameter and be swept
Retouch parameter.If it does not exist, sweep parameter can be arranged according to the actual demand of patient in doctor.In another example sweep parameter generates list
Member 213 can call directly default or preset and people in the sweep parameter database according to the area-of-interest (such as heart)
Body organ and/or the corresponding sweep parameter of tissue, wherein preset sweep parameter corresponding with human organ and/or tissue according to
Each organ or tissue of human body is finely divided and corresponds.
In some embodiments, the sweep parameter generation unit 213, which can be called, is stored in the operation control calculating
The second machine learning model in storage medium in machine.Second machine learning model can be according to the area-of-interest
Automatically corresponding sweep parameter is exported.For example, the area-of-interest is the input value of the second machine learning model, sweep parameter
For the output valve of the second machine learning model.In some embodiments, the output valve may include one in sweep parameter
Or it is multiple.For example, output valve only includes scanning range.In another example output valve may include that scanning range, exposure parameter etc. are multiple
The combination of sweep parameter.
Second machine learning model can be formed by history scanning area and the training of history sweep parameter.Specifically
Ground can extract the characteristic value of the history scanning area to form the feature vector for training pattern, the history is swept
Mark information of the corresponding history sweep parameter in region as described eigenvector is retouched, by a large amount of feature vectors and its mark information
It is input in second machine learning model and is trained to obtain the parameter of the model (for example, using gradient descent method
Training obtains model parameter).By taking deep neural network as an example, the deep neural network may include input layer, hidden layer and
Output layer.Each layer can include multiple neuronal structures, and each neuronal structure is for handling in described eigenvector
Characteristic value, and result is output to next layer and is handled, predicted value is exported eventually by output layer, that is, prediction is scanned
Parameter.
Optionally, second machine learning model can include but is not limited to Xgboost (Extreme Gradient
Boosting, ultimate attainment trapezoidal iteration) model, decision-tree model, GBDT (Gradient Boosted Decision Tree/
Grdient Boosted Regression Tree) model, linear regression model (LRM), neural network model etc..
Imaging control unit 214 can automatically write the area-of-interest corresponding sweep parameter in scan protocols,
And then generate scan plan.In some embodiments, the scan protocols are sent CT system by the imaging control unit 214
In 200, the CT is set automatically to execute the scanning to area-of-interest according to the sweep parameter in scan protocols.It can pass through
The CT system 200 obtains scan data, and the image of the area-of-interest according to scan data reconstruction.
In some embodiments, the imaging control system 210 can be deployed in the control of the operation for controlling CT scan
On computer.Optionally, the operation control computer includes at least processor and/or computer readable storage medium.It is described
Computer-readable recording medium storage computer instruction, described instruction can be used for executing image formation control method of the invention.Institute
Described instruction can be run and execute corresponding image formation control method by stating operation control computer.The operation controls computer packet
Include but be not limited to desktop computer, portable computer, tablet computer, mobile terminal (such as smart phone, smartwatch, intelligence
The energy helmet, intelligent glasses etc.) etc..
Only as an example, above-mentioned imaging control system 210 is used in combination with CT system 200.For those skilled in the art
For, the imaging control system 210 can be used in combination with one or more imaging systems for being similar to CT system, for example,
Positron emission tomography imaging system (PET), MRI system (MRI), limit not to this.
Fig. 3 automatically determines the exemplary process diagram that sweep parameter carries out imaging control based on locating plate to be of the invention.
In step 301, at least one locating plate can be obtained by acquiring unit 211.
In some embodiments, the acquiring unit 211 can directly control CT system 200 by acquisition instruction and be determined
Bit scan reads locating plate.
In some embodiments, the locating plate can be individually obtained first with the CT system 200 and be stored to
One individual storage medium (such as database), the acquiring unit 211 reads the positioning from the storage medium later
Piece.
Specifically, the locating plate includes at least one P-A Cephalomatrics and/or lateral projection.It is understood that the system
210 both can be using single picture (P-A Cephalomatrics or lateral projection) that positions as input, can also be to position as (P-A Cephalomatrics and lateral projection) more
As input, to carry out the subsequent process for automatically determining sweep parameter control imaging.Wherein, and using single picture that positions as input phase
Than to position as being more conducive to accurately identify and position area-of-interest as input more.
In step 302, it can use acquiring unit 211 to obtain the corresponding scanning association of at least one described locating plate
View.The scan protocols include locating plate scanned position.For example, the scanned position can be the tissue or organ of human body.
In some embodiments, the scan protocols further comprise sweep parameter.The sweep parameter includes but unlimited
In the corresponding scan type of the scanned position (such as unenhanced, enhancing scanning), conditions of exposure, the visual field (FOV), scanning angle and sweep
Retouch range etc..In some embodiments, the scanning range of the locating plate is (for example, include starting scan position and terminating to scan
Position) it include area-of-interest to be scanned.It is, including the area-of-interest to be scanned in the locating plate
Image.
In some embodiments, the scanned position can be die body (such as standard for testing CT performance (such as CT value)
Uniform water mould, as shown in Figure 4).
In step 303, the area-of-interest determination unit 212 can be according to the scan protocols and described at least one
A locating plate automatically determines area-of-interest.
Due to organ or tissue different in human body to X-ray have different attenuation coefficients, it is generated about
The locating plate of different organ or tissues has different characteristics of image.For example, described image feature can include but is not limited to
Position Gradient Features, gray scale or color characteristic, boundary characteristic, provincial characteristics, textural characteristics, the shape feature, topology of picture
The one or more of them such as feature and relational structure.
Specifically, the characteristic information that the area-of-interest determination unit 212 can be had based on the locating plate, and lead to
The scanned position and sweep parameter information inquired in the scan protocols for obtaining locating plate are crossed, the method pair of pattern-recognition is utilized
The locating plate is handled, to obtain the area-of-interest.For example, it is assumed that area-of-interest to be scanned is heart,
The area-of-interest determination unit 212 can be according to the sweep parameter about heart recorded in scan protocols (as scanned
Range) and locating plate cardiac image feature information, to automatically identify heart, and be identified automatically in locating plate.
The mode identification method includes image processing method, for example, image filtering, image segmentation etc..Specifically, pass through
It is filtered the interference that may be implemented to reduce or eliminate picture noise to image feature information to image, further utilizes figure
As the area-of-interest is divided or identified to the method for segmentation.Optionally, typical image partition method includes being based on edge
The method of detection, threshold segmentation method, the dividing method based on cluster, the dividing method based on region, based on wavelet transformation
Edge detection method etc..
In some embodiments, the area-of-interest determination unit 212 can also be by calling for pattern-recognition
First machine learning model identifies the area-of-interest.First machine learning model is stored in the operational calculator
In storage medium in.For example, the machine learning model for pattern-recognition is special by the image for inputting the locating plate
Reference breath, exports and identifies corresponding area-of-interest.Optionally, first machine learning model includes but is not limited to
Xgboost (Extreme Gradient Boosting, ultimate attainment trapezoidal iteration) model, decision-tree model, GBDT (Gradient
Boosted Decision Tree/Grdient Boosted Regression Tree) model, linear regression model (LRM), nerve
Network model etc..Preferably, first machine learning model is deep neural network model.
In step 304, it can be automatically generated by sweep parameter generation unit 213 according to the area-of-interest described
The sweep parameter of area-of-interest.The sweep parameter can include but is not limited to scan type (unenhanced, enhancing scanning), exposure
Condition, the visual field (FOV), scanning angle and scanning range etc..
In some embodiments, the sweep parameter generation unit 213 obtains the interested area information and according to institute
Interested area information is stated to automatically generate the sweep parameter of the area-of-interest.The interested area information may include
Coordinate and/or classification (such as heart, nasal sinus, throat organ or tissue) of mark point or mark line (as shown in Figure 1) etc..Example
Such as, by taking heart as an example, coordinate of the heart in locating plate can be obtained by the sweep parameter generation unit 213, then root
Heart scanning range is automatically generated according to the coordinate information, for example, starting scan position and terminating scan position, further according to positioning
The coordinate one-to-one relationship of bed code position with examination couch in CT system in the axial direction, that is, can determine when scanning heart in piece
Required axial scan range.
In some embodiments, the sweep parameter generation unit 213 can be by the interested area information and scanning
Data in parameter database match and then generate the corresponding sweep parameter of the area-of-interest.The sweep parameter
Database includes at least sweep parameter corresponding with human organ and/or tissue.Optionally, the sweep parameter data-base recording
The history scan data of a large amount of different patients.It, can will be corresponding for example, when the CT system 200 scans a certain patient
Sweep parameter uploads to the sweep parameter database and is stored.In some embodiments, the sweep parameter database can
To record the sweep parameter data of a Jia Huoduojia medical institutions or scientific research institution.Optionally, the sweep parameter database is also
Have recorded default or preset tissue or organ scan's parameter.For example, default scan type is flat using cranium brain as sweep object
It sweeps, tube voltage is 120~140kV, tube current be 180~220mAs, scan vision (FOV) be 25cm, scanning range is to listen
Corner of the eyes line is that benchmark line is scanned up to calvarium (for example, the position of canthomeatal line correspondence proving bed is A, the position of calvarium correspondence proving bed
It is set to B).
For example, medical history and sign information that sweep parameter generation unit 213 can further analyze patient to be scanned are (such as
Whether morbidity history, gender, height, weight etc. are had), and be to inquire by access scan parameter database (not shown in figure 1)
It is no to there is the history sweep parameter similar or identical with the patient, and if it exists, can be then arranged automatically according to history sweep parameter
Sweep parameter.If it does not exist, sweep parameter can be arranged according to the actual demand of patient in doctor.In another example sweep parameter generates
Unit 213 can be called directly according to the area-of-interest (such as heart) in the sweep parameter database default or it is preset with
Human organ and/or the corresponding sweep parameter (such as preset sweep parameter about heart) of tissue.
In some embodiments, the scanning ginseng of the area-of-interest can be determined by the second machine learning model
Number.Second machine learning model can export automatically corresponding sweep parameter according to the area-of-interest.For example, described
Area-of-interest is the input value of the second machine learning model, and sweep parameter is the output valve of the second machine learning model.One
In a little embodiments, the output valve may include one or more of sweep parameter.For example, output valve only includes scanning model
It encloses.In another example output valve may include the combination of multiple sweep parameters such as scanning range, exposure parameter.
Second machine learning model can be formed by history scanning area and the training of history sweep parameter.Specifically
Ground, the characteristic value of the history scanning area and history sweep parameter can be extracted formed the feature for training pattern to
Amount, using the corresponding history sweep parameter of the history scanning area as the mark information of described eigenvector, by big measure feature
Vector and its mark information, which are input in second machine learning model, to be trained to obtain the parameter of the model (ratio
Such as, model parameter is obtained using gradient descent method training).By taking deep neural network as an example, the deep neural network be can wrap
Include input layer, hidden layer and output layer.Each layer can include multiple neuronal structures, and each neuronal structure is for handling
Characteristic value in described eigenvector, and result is output to next layer and is handled, predicted value is exported eventually by output layer,
That is, prediction obtains sweep parameter.
Optionally, second machine learning model can include but is not limited to Xgboost (Extreme Gradient
Boosting, ultimate attainment trapezoidal iteration) model, decision-tree model, GBDT (Gradient Boosted Decision Tree/
Grdient Boosted Regression Tree) model, linear regression model (LRM), neural network model etc..
In step 305, the sweep parameter control based on the area-of-interest generates the scanning of the area-of-interest
Image.
Specifically, the imaging control unit 214 can write the sweep parameter of the area-of-interest of the generation automatically
Enter into the scan protocols of CT system, the area-of-interest is then scanned according to scan protocols control.And then it is swept
Data are retouched, the image of the area-of-interest is generated according to the scan data reconstruction.
Presently disclosed automatically determines sweep parameter based on locating plate to generate the scan image of area-of-interest
Automated setting sweep parameter may be implemented in imaging method, can largely help doctor or operator to improve its work
Efficiency avoids the need for the sweep parameter for spending longer time to adjust area-of-interest.
The embodiments of the present invention also provide a kind of computer readable storage mediums.Optionally, in the present embodiment, described
Storage medium stores computer instruction, the method that described instruction is used to execute above-mentioned imaging control.The imaging method includes step
Rapid 301 arrive one or more of step 305 in step.When computer or processor execute described instruction, may be implemented
The method of above-mentioned imaging control.
It should be noted that " automatic " in the present invention means that can use computer or arithmetic element independently realizes or real
Corresponding steps are applied, do not need the interaction of user and computer substantially during realizing corresponding steps.But it is not precluded within reality
User is now needed to confirm that each step calculates as a result, selecting to stop according to calculated result or start newly during corresponding steps
Workflow or step.
The foregoing is merely preferred implementations of the invention, are not intended to restrict the invention, for the technology of this field
For personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of image formation control method, which is characterized in that the described method includes:
Obtain at least one locating plate；
The corresponding scan protocols of at least one described locating plate are obtained, the scan protocols include scanned position；
Area-of-interest is automatically determined according to the scan protocols and at least one described locating plate；
Generate the sweep parameter of the area-of-interest；And
Sweep parameter control based on the area-of-interest generates the scan image of the area-of-interest.
2. image formation control method according to claim 1, which is characterized in that at least one described locating plate includes P-A Cephalomatrics
Or lateral projection.
3. image formation control method according to claim 1, which is characterized in that according to the scan protocols and described at least one
A locating plate automatically determines area-of-interest
Obtain the relevant characteristics of image of at least one described locating plate；And
Based on described image feature, the area-of-interest is determined using the method for pattern-recognition.
4. image formation control method according to claim 1, which is characterized in that the sweep parameter for generating area-of-interest
Include:
The area-of-interest is matched with the data in sweep parameter database, is obtained corresponding with the area-of-interest
Sweep parameter.
5. image formation control method according to claim 4, which is characterized in that the sweep parameter database include at least with
Human organ and/or the corresponding sweep parameter of tissue.
6. image formation control method according to claim 1, which is characterized in that the sweep parameter for generating area-of-interest
Include:
The area-of-interest is input to trained machine learning model, the sense is generated by the machine learning model
The sweep parameter in interest region；Wherein, the machine learning model passes through history scanning area and history sweep parameter training
At.
7. image formation control method according to claim 1, which is characterized in that the scanning based on the area-of-interest
The method of scan image that state modulator generates area-of-interest includes:
The sweep parameter of the area-of-interest of the generation is automatically write into the scan protocols；And
According to the scan protocols to control the scan image for generating the area-of-interest.
8. a kind of imaging control apparatus, which is characterized in that including at least one processor and storage medium, wherein
The storage medium is for storing computer instruction；
At least one described processor is for executing the computer instruction to realize as described in any one of claim 1-7
Method.
9. a kind of computer readable storage medium, which is characterized in that the storage medium stores computer instruction, machine-readable when calculating
After taking the computer instruction in storage medium, computer runs the method as described in any one of claim 1-7.
10. a kind of imaging control system, which is characterized in that the system comprises acquiring unit, area-of-interest determination unit, sweep
Retouch parameter generating unit and imaging control unit, wherein
The acquiring unit is for obtaining at least one locating plate and the corresponding scan protocols of at least one described locating plate, institute
Stating scan protocols includes scanned position；
The area-of-interest determination unit is used to automatically determine sense according to the scan protocols and at least one described locating plate
Interest region；
The sweep parameter generation unit is used to generate the sweep parameter of the area-of-interest；And
The imaging control unit generates the area-of-interest for the sweep parameter control based on the area-of-interest
Scan image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811131376.0A CN109381212A (en) | 2018-09-27 | 2018-09-27 | A kind of image formation control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811131376.0A CN109381212A (en) | 2018-09-27 | 2018-09-27 | A kind of image formation control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109381212A true CN109381212A (en) | 2019-02-26 |
Family
ID=65418220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811131376.0A Pending CN109381212A (en) | 2018-09-27 | 2018-09-27 | A kind of image formation control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109381212A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109924993A (en) * | 2019-03-07 | 2019-06-25 | 上海联影医疗科技有限公司 | Image scanning agreement automatic planning, device, electronic equipment and storage medium |
| CN109938764A (en) * | 2019-02-28 | 2019-06-28 | 佛山原子医疗设备有限公司 | A kind of adaptive multiple location scan imaging method and its system based on deep learning |
| CN110084805A (en) * | 2019-04-30 | 2019-08-02 | 东软医疗系统股份有限公司 | FOV parameter setting method, device and image processing equipment |
| CN110123348A (en) * | 2019-04-15 | 2019-08-16 | 上海联影医疗科技有限公司 | Rebuild scan protocols formulating method, device and equipment |
| CN110960241A (en) * | 2019-12-09 | 2020-04-07 | 上海联影医疗科技有限公司 | Method and device for determining scanning parameters of medical image scanning and computer equipment |
| CN111028310A (en) * | 2019-12-31 | 2020-04-17 | 上海联影医疗科技有限公司 | Scanning parameter determination method, device, terminal and medium for breast tomography |
| CN111407298A (en) * | 2020-03-16 | 2020-07-14 | 京东方科技集团股份有限公司 | Scanning method and scanning device of CT imaging equipment |
| CN111968112A (en) * | 2020-09-02 | 2020-11-20 | 广州海兆印丰信息科技有限公司 | CT three-dimensional positioning image acquisition method and device and computer equipment |
| CN112089431A (en) * | 2020-09-15 | 2020-12-18 | 上海联影医疗科技股份有限公司 | Dose modulation optimization method, dose modulation optimization device, electronic equipment and medium |
| CN112348945A (en) * | 2020-11-02 | 2021-02-09 | 上海联影医疗科技股份有限公司 | Positioning image generation method, device, equipment and medium |
| CN112741643A (en) * | 2020-12-31 | 2021-05-04 | 苏州波影医疗技术有限公司 | CT system capable of automatically positioning and scanning and positioning and scanning method thereof |
| CN112820383A (en) * | 2019-11-15 | 2021-05-18 | 上海联影医疗科技股份有限公司 | Medical imaging method, system and storage medium |
| CN113876348A (en) * | 2021-11-17 | 2022-01-04 | 武汉联影生命科学仪器有限公司 | Scanning image generation method, system, device and processing equipment |
| WO2022017039A1 (en) * | 2020-07-24 | 2022-01-27 | International Business Machines Corporation | Internal and external proximate scanning |
| CN114237749A (en) * | 2021-12-18 | 2022-03-25 | 武汉联影生命科学仪器有限公司 | Parameter configuration method of scanning system, scanning system and electronic device |
| CN114692822A (en) * | 2020-12-31 | 2022-07-01 | 武汉联影生命科学仪器有限公司 | Scanning model training method, scanning device and storage medium |
| WO2022262871A1 (en) * | 2021-06-18 | 2022-12-22 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for medical imaging |
| US11654304B2 (en) | 2018-12-17 | 2023-05-23 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for determining a region of interest of a subject |
| US11672496B2 (en) | 2019-12-09 | 2023-06-13 | Shanghai United Imaging Healthcare Co., Ltd. | Imaging systems and methods |
| EP4344642A1 (en) * | 2022-09-30 | 2024-04-03 | Siemens Healthineers AG | Computer-implemented method for setting x-ray acquisition parameters |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327124A (en) * | 2010-06-24 | 2012-01-25 | 西门子公司 | Be chosen in method, equipment and the data medium of the magnitude of voltage that is provided with on the X-ray tube |
| CN103385728A (en) * | 2012-05-07 | 2013-11-13 | 上海西门子医疗器械有限公司 | X ray computed tomography method and X ray computed tomography system |
| CN103494613A (en) * | 2013-09-06 | 2014-01-08 | 沈阳东软医疗系统有限公司 | Plain film scanning method and device |
| CN104905766A (en) * | 2014-03-11 | 2015-09-16 | Ge医疗系统环球技术有限公司 | Medical scanning system and method for determining scanning parameters based on scout views |
| CN107789001A (en) * | 2017-10-31 | 2018-03-13 | 上海联影医疗科技有限公司 | A kind of pendulum position method and system for image scanning |
| CN107909622A (en) * | 2017-11-30 | 2018-04-13 | 上海联影医疗科技有限公司 | Model generating method, the scanning planing method of medical imaging and medical image system |
| CN107992817A (en) * | 2017-06-15 | 2018-05-04 | 上海联影医疗科技有限公司 | Automatic imaging method and system |
| CN108230261A (en) * | 2016-12-09 | 2018-06-29 | 通用电气公司 | Full-automatic image optimization based on automated organ identification |
-
2018
- 2018-09-27 CN CN201811131376.0A patent/CN109381212A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102327124A (en) * | 2010-06-24 | 2012-01-25 | 西门子公司 | Be chosen in method, equipment and the data medium of the magnitude of voltage that is provided with on the X-ray tube |
| CN103385728A (en) * | 2012-05-07 | 2013-11-13 | 上海西门子医疗器械有限公司 | X ray computed tomography method and X ray computed tomography system |
| CN103494613A (en) * | 2013-09-06 | 2014-01-08 | 沈阳东软医疗系统有限公司 | Plain film scanning method and device |
| CN104905766A (en) * | 2014-03-11 | 2015-09-16 | Ge医疗系统环球技术有限公司 | Medical scanning system and method for determining scanning parameters based on scout views |
| CN108230261A (en) * | 2016-12-09 | 2018-06-29 | 通用电气公司 | Full-automatic image optimization based on automated organ identification |
| CN107992817A (en) * | 2017-06-15 | 2018-05-04 | 上海联影医疗科技有限公司 | Automatic imaging method and system |
| CN107789001A (en) * | 2017-10-31 | 2018-03-13 | 上海联影医疗科技有限公司 | A kind of pendulum position method and system for image scanning |
| CN107909622A (en) * | 2017-11-30 | 2018-04-13 | 上海联影医疗科技有限公司 | Model generating method, the scanning planing method of medical imaging and medical image system |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11654304B2 (en) | 2018-12-17 | 2023-05-23 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for determining a region of interest of a subject |
| CN109938764A (en) * | 2019-02-28 | 2019-06-28 | 佛山原子医疗设备有限公司 | A kind of adaptive multiple location scan imaging method and its system based on deep learning |
| CN109938764B (en) * | 2019-02-28 | 2021-05-18 | 佛山原子医疗设备有限公司 | Self-adaptive multi-part scanning imaging method and system based on deep learning |
| CN109924993A (en) * | 2019-03-07 | 2019-06-25 | 上海联影医疗科技有限公司 | Image scanning agreement automatic planning, device, electronic equipment and storage medium |
| CN110123348A (en) * | 2019-04-15 | 2019-08-16 | 上海联影医疗科技有限公司 | Rebuild scan protocols formulating method, device and equipment |
| CN110084805A (en) * | 2019-04-30 | 2019-08-02 | 东软医疗系统股份有限公司 | FOV parameter setting method, device and image processing equipment |
| CN110084805B (en) * | 2019-04-30 | 2023-05-05 | 东软医疗系统股份有限公司 | FOV parameter setting method and device and image processing equipment |
| CN112820383B (en) * | 2019-11-15 | 2023-04-28 | 上海联影医疗科技股份有限公司 | Medical imaging method, system and storage medium |
| CN112820383A (en) * | 2019-11-15 | 2021-05-18 | 上海联影医疗科技股份有限公司 | Medical imaging method, system and storage medium |
| US11672496B2 (en) | 2019-12-09 | 2023-06-13 | Shanghai United Imaging Healthcare Co., Ltd. | Imaging systems and methods |
| CN110960241A (en) * | 2019-12-09 | 2020-04-07 | 上海联影医疗科技有限公司 | Method and device for determining scanning parameters of medical image scanning and computer equipment |
| CN111028310B (en) * | 2019-12-31 | 2023-10-03 | 上海联影医疗科技股份有限公司 | Method, device, terminal and medium for determining scanning parameters of breast tomography |
| CN111028310A (en) * | 2019-12-31 | 2020-04-17 | 上海联影医疗科技有限公司 | Scanning parameter determination method, device, terminal and medium for breast tomography |
| CN111407298B (en) * | 2020-03-16 | 2024-04-16 | 京东方科技集团股份有限公司 | Scanning method and scanning device of CT imaging equipment |
| CN111407298A (en) * | 2020-03-16 | 2020-07-14 | 京东方科技集团股份有限公司 | Scanning method and scanning device of CT imaging equipment |
| WO2022017039A1 (en) * | 2020-07-24 | 2022-01-27 | International Business Machines Corporation | Internal and external proximate scanning |
| US11464464B2 (en) | 2020-07-24 | 2022-10-11 | International Business Machines Corporation | Internal and external proximate scanning |
| CN111968112B (en) * | 2020-09-02 | 2023-12-26 | 广州海兆印丰信息科技有限公司 | CT three-dimensional positioning image acquisition method and device and computer equipment |
| CN111968112A (en) * | 2020-09-02 | 2020-11-20 | 广州海兆印丰信息科技有限公司 | CT three-dimensional positioning image acquisition method and device and computer equipment |
| CN112089431A (en) * | 2020-09-15 | 2020-12-18 | 上海联影医疗科技股份有限公司 | Dose modulation optimization method, dose modulation optimization device, electronic equipment and medium |
| CN112348945A (en) * | 2020-11-02 | 2021-02-09 | 上海联影医疗科技股份有限公司 | Positioning image generation method, device, equipment and medium |
| CN112348945B (en) * | 2020-11-02 | 2024-01-02 | 上海联影医疗科技股份有限公司 | Positioning image generation method, device, equipment and medium |
| CN114692822A (en) * | 2020-12-31 | 2022-07-01 | 武汉联影生命科学仪器有限公司 | Scanning model training method, scanning device and storage medium |
| CN112741643A (en) * | 2020-12-31 | 2021-05-04 | 苏州波影医疗技术有限公司 | CT system capable of automatically positioning and scanning and positioning and scanning method thereof |
| WO2022262871A1 (en) * | 2021-06-18 | 2022-12-22 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for medical imaging |
| CN113876348A (en) * | 2021-11-17 | 2022-01-04 | 武汉联影生命科学仪器有限公司 | Scanning image generation method, system, device and processing equipment |
| CN114237749A (en) * | 2021-12-18 | 2022-03-25 | 武汉联影生命科学仪器有限公司 | Parameter configuration method of scanning system, scanning system and electronic device |
| EP4344642A1 (en) * | 2022-09-30 | 2024-04-03 | Siemens Healthineers AG | Computer-implemented method for setting x-ray acquisition parameters |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109381212A (en) | A kind of image formation control method and system | |
| US10293182B2 (en) | Systems and methods for adaptive replanning based on multi-modality imaging | |
| US10699410B2 (en) | Automatic change detection in medical images | |
| JP6208535B2 (en) | Radiotherapy apparatus and system and method | |
| CN107206252B (en) | Motion management in a nuclear magnetic resonance guided linear accelerator | |
| US10149987B2 (en) | Method and system for generating synthetic electron density information for dose calculations based on MRI | |
| CN103889329B (en) | Motion compensation secondary for CT sectioning image transmits metal artifacts reduction | |
| JP2011194241A (en) | System and method for automatic computation of mr imaging scan parameter | |
| US20110007959A1 (en) | Ct surrogate by auto-segmentation of magnetic resonance images | |
| CN106725570A (en) | Imaging method and system | |
| CN106975163A (en) | The automated anatomy delineation planned for image guided therapy | |
| US20190313986A1 (en) | Systems and methods for automated detection of objects with medical imaging | |
| JP2023512139A (en) | Systems and methods for determining radiation parameters | |
| US9355454B2 (en) | Automatic estimation of anatomical extents | |
| CN115485019A (en) | Automatically planned radiation-based treatment | |
| JP6095112B2 (en) | Radiation therapy system | |
| CN115666717A (en) | Method and apparatus for deriving and using virtual volume structures to predict potential collisions in delivering therapeutic radiation | |
| US7668370B2 (en) | Segmenting a series of 2D or 3D images | |
| DE112019007533T5 (en) | CALCULATION OF A RESPIRATORY CURVE FOR MEDICAL APPLICATIONS | |
| EP2737455B1 (en) | Method for detecting the position of a transducer | |
| CN112089438B (en) | Four-dimensional reconstruction method and device based on two-dimensional ultrasonic image | |
| EP4176796A1 (en) | Multi-session breathing guidance | |
| WO2024067629A1 (en) | Methods, systems, and mediums for scanning | |
| Wang et al. | An unsupervised dual contrastive learning framework for scatter correction in cone-beam CT image | |
| DE112021006795T5 (en) | DETECTION OF FOREIGN BODY IN INTRAOPERATIVE IMAGES |
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 |
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. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190226 |
|
| RJ01 | Rejection of invention patent application after publication |