CN106558045A - A kind of segmentation of lung parenchyma method, device, magic magiscan - Google Patents
A kind of segmentation of lung parenchyma method, device, magic magiscan Download PDFInfo
- Publication number
- CN106558045A CN106558045A CN201610912654.0A CN201610912654A CN106558045A CN 106558045 A CN106558045 A CN 106558045A CN 201610912654 A CN201610912654 A CN 201610912654A CN 106558045 A CN106558045 A CN 106558045A
- Authority
- CN
- China
- Prior art keywords
- segmentation
- medical image
- connected domain
- image
- skin line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10104—Positron emission tomography [PET]
-
- 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
The invention discloses a kind of segmentation of lung parenchyma method, including：The first medical image of person under inspection target area is obtained, the first medical image includes several slice images, each slice image includes multiple pixels；The sagittal plane of the first medical image is linearly strengthened, and the first medical image is added with the gray value through linear enhanced first image respective pixel, generated the second medical image；Determine the sagittal plane skin line of the second medical image, and the cross section skin line of the second medical image is determined on the second medical image that sagittal plane skin line determines；The connected domain that sagittal plane skin line and cross section skin line are surrounded is obtained, and the segmentation result of lung tissue is obtained in connected domain.Segmentation of lung parenchyma method of the present invention can accurately obtain the borderline region of lung tissue.Meanwhile, the present invention also proposes a kind of segmentation of lung parenchyma device and the magic magiscan using the segmentation of lung parenchyma device.
Description
Technical field
The present invention relates to the dividing method of lung tissue in technical field of medical image processing, more particularly to medical image, dress
Put and magic magiscan.
Background technology
Prostate specific antigen instrument (Emission Computed Tomography, ECT) mainly includes monochromatic light
Sub- emission computed tomography (SPECT) and PET-Positron emission computed tomography scanning (PET), wherein PET is used as current
High-level NMT, it has also become tumour, the heart, the indispensable important method of cerebral disease diagnosis.Magnetic resonance imaging
(Magnetic Resonance Imaging, MRI) can provide the anatomic form and physiological function information at imaging position, in reaction
It is preferably right that there is unrivaled superiority, particularly soft tissue MR images to present for anatomic form and physiological function information approach
It is than effect and radiationless.The combination that PET and MR are checked has the advantages that sensitivity is good, the degree of accuracy is high.PET/MR it is multi-modal into
As in system, needing to carry out PET image correction for attenuation, but due to MR image pixel values only with tissue in proton density and
The lax degree of tissue is relevant, and the mass attentuation coefficient related to electron density is unrelated, and such as bone and air have respectively
Highest and minimum positive electron attenuation coefficient, are but all low signal on MR images, so the correction for attenuation ratio based on MR images
It is more difficult.
The attenuation correction method for being currently based on MR is broadly divided into region segmentation method：Attenuation characteristic different tissues and device
Official is divided into different regions, such as air, lung, fat, muscle and bone etc., the zones of different split then reentried
The attenuation coefficient of respective organization under 511keV, carries out correction for attenuation.In prior art, had based on the precision of the method for region segmentation
Treat further to improve, and the segmentation of different tissues and organ in many bed MRIs cannot be realized.In consideration of it, be necessary it is right
Existing medical image cutting method is improved.
The content of the invention
The technical problem to be solved is the medical image for proposing a kind of high precision and being capable of achieving many bed scannings
Dividing method.
The present invention solve the technical scheme that adopted of above-mentioned technical problem for：A kind of segmentation of lung parenchyma method, including it is as follows
Step：
The first medical image of person under inspection target area is obtained, first medical image includes several slice images,
Described each slice image includes multiple pixels；
The sagittal plane of first medical image is linearly strengthened, and to first medical image and through linear
The gray value of enhanced first image respective pixel is added, and generates the second medical image；
Determine the sagittal plane skin line of second medical image, and the second medical science determined in the sagittal plane skin line
The cross section skin line of second medical image is determined on image；
The connected domain that the sagittal plane skin line and cross section skin line are surrounded is obtained, and lung is obtained in the connected domain
The segmentation result of tissue.
Alternatively, first medical image is CT images or MR images.
Alternatively, the sagittal plane skin line of second medical image is obtained by following process：
Binary conversion treatment is carried out using given threshold to sagittal each pixel of second medical image；
The quantity of the included connected domain of sagittal each lamella of statistics second medical image Jing after binary conversion treatment；
Judge that the quantity of the included connected domain of each lamella, whether less than the first given threshold, if condition meets, retains
The connected domain；Otherwise, comprising connected domain in only one or more maximum connected domains of Retention area；
The sagittal plane skin line of second medical image is determined according to the connected domain of the reservation.
Alternatively, also including the point that pixel value on acquisition slice image border is 1, and according to the point that the pixel value is 1
By the connected domain closure for retaining.
Alternatively, the cross section skin line of second medical image is determined by following process：
Obtain the second medical image that the sagittal plane skin line determines；
Each lamella in the second medical image cross section determined to the sagittal plane skin line carries out two-dimentional corrosion treatmentCorrosion Science,
Connected domain of the Retention area more than the first setting area threshold；
Two-dimensional swelling process carried out to the connected domain of the area of the reservation more than the first setting area threshold, and according to two
Connected domain after dimension expansion process determines the cross section skin line of second medical image.
Alternatively, the segmentation result of the lung tissue is obtained by following process：
The boundary pixel point of high gray value connected domain is obtained in the cross section of the connected domain；
Cross section segmentation figure picture and coronal-plane segmentation figure picture are obtained in the connected domain that the boundary pixel point is surrounded, it is described
Cross section segmentation figure picture or the coronal-plane segmentation figure picture are low gray value region；
Center line is obtained according to the coronal-plane segmentation figure picture；
Lung group is determined in the position of the cross section segmentation figure picture and the coronal-plane segmentation figure picture according to the center line
Knit corresponding connected domain.
Alternatively, the center line passes through following Procedure Acquisition：
The coronal-plane segmentation figure is calculated as the connected domain area of each lamella, the maximum lamella of connected domain area is determined；
The initial row and termination row of connected domain are determined in the maximum lamella of the connected domain area；
Center line is determined according to the initial row and termination row of the connected domain.
Alternatively, it is true in the position of the cross section segmentation figure picture and the coronal-plane segmentation figure picture according to the center line
Determine concretely comprising the following steps for the corresponding connected domain of lung tissue：
Retain the connected domain is expert at by center line on the coronal-plane segmentation figure picture；
The connected domain is expert at by the center line is filled on the cross section segmentation figure picture, obtains lung tissue pair
The connected domain answered.
According to a further aspect in the invention, it is also proposed that a kind of segmentation of lung parenchyma device, including image segmentation module, the image
Segmentation module includes：
First medical image acquisition unit, for receiving the first medical image of person under inspection target area, first doctor
Learning image includes several slice images, and described each slice image includes multiple pixels；
Second medical image signal generating unit is for linearly being strengthened to the sagittal plane of first medical image and right
First medical image is added with the gray value through linear enhanced first medical image respective pixel, generates the second medical science
Image；
Skin line determining unit, for determining the sagittal plane skin line of second medical image, and in the sagittal plane
The cross section skin line of second medical image is determined on the second medical image that skin line determines；
Cutting unit, for obtaining the connected domain that the sagittal plane skin line and cross section skin line are surrounded, and described
The segmentation result of lung tissue is obtained in connected domain.
According to another aspect of the invention, it is also proposed that a kind of magic magiscan, the magic magiscan
Including segmentation of lung parenchyma device, also include：
MR scan modules, for scanning person under inspection target area, and obtain the corresponding first medical science figure in the target area
Picture；
PET scan module, for scanning the target area, and gathers the corresponding PET data in target Europe region；
Module is rebuild, for obtaining the segmentation of lung parenchyma result that the segmentation of lung parenchyma device is obtained, and is the segmentation
Lung tissue each pixel distribute respective attenuation coefficient, generate decay pattern, and the PET according to the decay pattern iterative approximation
Data produce PET image.
Compared with prior art, it is an advantage of the current invention that：Cut in differences such as sagittal plane, cross sections with reference to MRI
The gray scale of face image, positional information, obtain the connected domain that sagittal plane skin line and cross section skin line are surrounded, realize medical image
Effective differentiation of the image tissue such as the similar background area of gray value and lung, bone, it is to avoid background area is tied by lung segmentation
The impact of fruit；Split in the connected domain cross section that sagittal plane skin line and cross section skin line are surrounded and obtain high gray value area
Domain, obtains the connected domain that lung tissue may be included, and connected domain is sieved according to the architectural feature selected center line of lung tissue
Choosing, effectively excludes impact of the bone to lung tissue；Many bed scannings need not be applicable to using complicated priori matching template.
Description of the drawings
Magic magiscan structured flowcharts of the Fig. 1 for one embodiment of the invention；
MR scan module structured flowcharts of the Fig. 2 for one embodiment of the invention；
PET scan modular structure block diagrams of the Fig. 3 for one embodiment of the invention；
Segmentation of lung parenchyma apparatus structure block diagrams of the Fig. 4 for one embodiment of the invention；
Segmentation of lung parenchyma method flow diagrams of the Fig. 5 for one embodiment of the invention；
Fig. 6 a are the cross-sectional view strength of the first medical image that one embodiment of the invention is obtained；
Fig. 6 b are the coronal-plane view of the first medical image that one embodiment of the invention is obtained；
Fig. 6 c are the sagittal plane view of the first medical image that one embodiment of the invention is obtained；
Fig. 7 obtains flow chart for the sagittal plane skin line of the second medical image of one embodiment of the invention；
Fig. 8 is that one embodiment of the invention obtains lung group in the connected domain that sagittal plane skin line and cross section skin line are surrounded
The segmentation result flow chart knitted；
Fig. 9 a are the cross section skin line result schematic diagram that one embodiment of the invention is obtained；
Fig. 9 b are the segmentation of lung parenchyma result schematic diagram that one embodiment of the invention is obtained.
Specific embodiment
In order to be illustrated more clearly that the technical scheme of embodiments herein, below will be to making needed for embodiment description
Accompanying drawing is briefly described.It should be evident that drawings in the following description are only some examples of the application or enforcement
Example, for one of ordinary skill in the art, on the premise of not paying creative work, can be with according to these accompanying drawings
The application is applied to into other similar scenes.Unless obviously or separately explained from language environment, identical label generation in figure
The identical structure of table or operation.
As shown in the application and claims, unless context clearly points out exceptional situation, " one ", " one ", " one
The word such as kind " and/or " being somebody's turn to do " not refers in particular to odd number, may also comprise plural number.It is, in general, that term " including " only points out bag with "comprising"
Include the step of clearly identifying and element, and these steps and element do not constitute one it is exclusive enumerate, method or equipment
It is likely to comprising the step of other or element.
Although the application is made that various drawing to some of the data handling system according to embodiments herein module
With, however, any amount of disparate modules can by using and operate in a client being connected with the system by network
And/or on server.The module is merely illustrative, and the different aspect of the system and method can be using different moulds
Block.
Flow chart used herein is used for illustrating according to performed by the data handling system of embodiments herein
Operating procedure.It should be appreciated that being displayed in the operating procedure of above or below not necessarily in order accurately carrying out.Phase
Instead, according to inverted order or while various steps can be processed.It is also possible to during other operating procedures are added to these,
Or a certain step or number step operation are removed from these processes.
In medical image or data handling procedure, " image segmentation ", " image zooming-out ", " image classification " mutually can turn
Change, express and the image for meeting certain condition is chosen from extensive area.In certain embodiments, magic magiscan can
With including one or more form.The form is included but is not limited to, digital subtraction angiography (DSA), magnetic resonance imaging
(MRI), magnetic resonance angiography (MRA), computed tomography (CT), computed tomography angiography (CTA), ultrasound
Ripple scans (US), positron emission tomography (PET), single photon emission computerized tomography,SPECT (SPECT), SPECT-
MR, CT-PET, CE-SPECT, DSA-MR, PET-MR, PET-US, SPECT-US, TMS-MR, US-CT, US-MR, X-ray-CT,
X-ray-PET, X-ray-US, video-CT, the combination of video-US and/or similar one or more.In certain embodiments,
The target area of image scanning can the combination of one or more of organ, body, object, damage location, tumour etc. be located
Region.In certain embodiments, the target area of image scanning can be thoracic cavity, belly, organ, four limbs, bone, blood vessel etc.
Plant or various regions for combining place.In certain embodiments, the target area of scanning can be one or more positions
The region that tissue is located.In certain embodiments, image can be two dimensional image and/or 3-D view.In two dimensional image, most
Trickle resolvable elements can be pixel (pixel).In 3-D view, most trickle resolvable elements can be voxel
(voxel).In 3-D view, image can be by a series of two dimension slicing or two-dimensional slice image construction.
It should be noted that below for the description of magic magiscan, only for convenience of description, can not be this Shen
Within the scope of please being limited in illustrated embodiment.It is appreciated that for a person skilled in the art, in the original for understanding the system
After reason, in the case of without departing substantially from this principle, modules are combined, or constitute subsystem and other modules
Connection, the various amendments and change to implementing said method and in systematic difference field form and details.
Some embodiments of the invention, propose a kind of segmentation of lung parenchyma device, including image segmentation module, the image
Segmentation module includes：First medical image acquisition unit, for receiving the first medical image of person under inspection target area, this first
Medical image includes several slice images, and each slice image includes multiple pixels；Second medical image signal generating unit, is used for
The sagittal plane of the first medical image is linearly strengthened, and to first medical image and through linear enhanced first medical science
The gray value of image respective pixel is added, and generates the second medical image；Skin line determining unit, for determining the second medical image
Sagittal plane skin line, and sagittal plane skin line determine the second medical image on determine the cross-section of second medical image
Surface skin line；Cutting unit, for obtaining the connected domain that the sagittal plane skin line and cross section skin line are surrounded, and described
The segmentation result of lung tissue is obtained in connected domain.In one embodiment, the first medical image acquisition unit can be with storage
The memory of function, the memory can be floppy disk, CD, CD-ROM (compact-disc-read-only storage), magneto-optic disk, ROM (only
Read memory), RAM (random access memory), EPROM (Erasable Programmable Read Only Memory EPROM), (electric erasable can for EEPROM
Program read-only memory), magnetic or optical card, flash memory or be suitable to store machine-executable instruction other kinds of medium/machine
Computer-readable recording medium.
In certain embodiments, the segmentation of lung parenchyma device can be with central processing unit (Central
Processing Unit, CPU), specialized application integrated circuit (Application Specific Integrated
Circuit, ASIC), dedicated instruction processor (Application Specific Instruction Set Processor,
ASIP), concurrent physical processor (Physics Processing Unit, PPU), digital signal processor (Digital
Processing Processor, DSP), field programmable gate array (Field-Programmable Gate Array,
FPGA), PLD (Programmable Logic Device, PLD), processor, microprocessor, controller, micro-
The processor of the combination of one or more in controller etc., for performing aforesaid operations.
In further embodiments, segmentation of lung parenchyma device can include the first medical image generation module, first medical science
Image generating module can be the MR scanners being connected with image segmentation module, and the first medical image generation module can be to being examined
Person target area is scanned, and generates the anatomic image of person under inspection target area.Exemplarily, first medical image produces single
Unit can be magnetic resonance scanner (equipment), magnetic resonance angiography scanner, computed tomography scanner, computer break
Layer vessel scanning angiography scans instrument etc. can produce the imaging device of person under inspection target area anatomical information.
Some embodiments of the invention, propose a kind of Medical Image Processing system using aforementioned segmentation of lung parenchyma device
System, to process multi-modality medical image.In one embodiment, the magic magiscan may include that segmentation of lung parenchyma is filled
Put, the segmentation of lung parenchyma device includes image segmentation module, and image segmentation module is capable of achieving the automatic segmentation of lung tissue.
In another embodiment, the magic magiscan may include image segmentation module and other scan modules.
In some embodiments of the invention, such as Fig. 1 is the magic magiscan structural frames of some embodiments of the invention
Figure, the magic magiscan include MR scan modules 100, PET scan module 200, the lung containing image segmentation module 300
Tissue segmentation device 30, reconstruction module 400, control module 500, display module 600.Wherein, the storage in MR scan modules 100
Unit 103 is connected with the first medical image acquisition unit 301 of image segmentation module 300；The segmentation list of image segmentation module 300
The memory 204 of unit 304, PET scan module 200 is connected with reconstruction module 400 respectively；It is single that control module 500 can connect segmentation
Unit 304, reconstruction module 400 or display module 600.
MR scan module 100 structured flowcharts of the Fig. 2 for one embodiment of the invention, exemplarily, the MR scan modules 100 can
Being MR scanners, including MR signals are produced and collecting unit 101, MR signal processing units 102, memory cell 103 and MR control
Unit processed 104, and can connect each other, the connection can be wireless network connection or finite element network connection.
MR signals are produced and collecting unit 101 may include magnet and radio-frequency coil, and magnet comprising the master for producing main field
The gradient component of magnet and generation gradient.Main magnet can be permanent magnet or superconducting magnet；Gradient component is mainly comprising gradient electricity
Stream amplifier (AMP), gradient coil；Gradient component can also include three autonomous channels Gx, Gy, Gz, and each gradient amplifier swashs
A corresponding gradient coil in heat gradient coil group, produces for generating the gradient fields of additional space encoded signal, with to magnetic
Resonance signal carries out space orientation；Radio-frequency coil can be divided into radio-frequency sending coil and RF receiving coil, and radio-frequency sending coil is used
In to person under inspection or human-body emitting RF pulse signal, RF receiving coil is used to receive the magnetic resonance signal from human body collection.
Alternatively, the species of radio-frequency coil can be bird basket coil, solenoid-shaped coil, saddle-type coil, Helmholtz coil, battle array
Alignment circle, circuit coil etc..
MR control units 104 can control MR signals and produce and collecting unit 101, MR signal processing units 102 and storage list
Unit 103.Specifically, MR control units 104 are connected with comprising pulse-series generator, gradient waveform generator, emitter and connect
Receipts machine etc., after the instruction that user is sent from console is received, control MR signals are produced and collecting unit 101 performs respective scanned
Sequence；MR signal processing units 102 can receive the magnetic resonance signal that MR signals are produced and collecting unit 101 is gathered, and MR controls
The control MR of unit 104 signal processing units 102 carry out the operation such as Fourier transformation to magnetic resonance signal, generate the magnetic at imaging position
Resonance image；Memory cell 103 can store the MRI in the case where MR control units 104 are controlled.
Memory cell 103 can make the memory with store function, and the memory includes, but not limited to floppy disk, light
Disk, CD-ROM (compact-disc-read-only storage), magneto-optic disk, ROM (read-only storage), RAM (random access memory), EPROM
(Erasable Programmable Read Only Memory EPROM), EEPROM (Electrically Erasable Read Only Memory), magnetic or optical card, flash memory or
It is suitable to store the other kinds of medium/machine readable media of machine-executable instruction.
Exemplarily, the first medical image can be MR images, and in one embodiment of the invention, MR scan modules 100 produce the
The detailed process of one medical image includes：Main magnet produces B0 main fields, and the atomic nucleus in person under inspection's body is under main field effect
Precession frequency is produced, the precession frequency is proportional with main field strength；MR control units 104 are stored and sent needs what is performed to sweep
Retouch the instruction of sequence (scan sequence), pulse-series generator instructed to gradient waveform generator according to scanning sequence and
Emitter is controlled, and gradient pulse signal of the gradient waveform generator output with scheduled timing and waveform, the signal are passed through
Gx, Gy and Gz gradient current amplifier, then by gradient component in three autonomous channels Gx, Gy, Gz, each gradient amplifier
A corresponding gradient coil in gradient coils set is excited, is produced for generating the gradient fields of additional space encoded signal, with right
Magnetic resonance signal carries out space orientation；Pulse-series generator also performs scanning sequence, and output includes the RF pulse-to-pulse of radio-frequency transmissions
The data such as the timing of punching, intensity, shape and the timing of radio frequency reception and the length of data acquisition window are to emitter, while sending out
Penetrate machine by respective radio-frequency pulse send to comprising radio-frequency sending coil MR signals produce and collecting unit 101 produce B1 fields,
The signal that the atomic nucleus being excited under B1 field actions in patient body sends is produced and is adopted by the MR signals comprising RF receiving coil
Collection unit 101 is perceived；Then, MR signal processing units 102 are transferred to by sending/receiving switch, through amplifying, demodulating,
The digitized processings such as filtration, AD conversion can form raw k-space data, and the raw k-space data are fourier transformed can rebuild
For the first medical image (MR images), and it is stored in memory cell 103.
If Fig. 3 is 200 structured flowchart of PET scan module of some embodiments of the invention.The PET scan module can be adopted
The PET scanner of collection person under inspection target area PET data, it may include detector cells 201, PET signal processing unit 202, symbol
Total counting unit 203, memory cell 204 and PET control units 205.PET control units 205 can control other multiple unit works
Make execution probe command, detector cells 201 include the multiple detector rings being arranged in frame, and the detector rings have arrangement
Multiple detectors on central shaft circumference, person under inspection can be at scan vision (the Field Of surrounded by multiple detectors
View, FOV) interior imaging.
Memory cell 204 can be the memory with store function, the memory include, but are not limited to floppy disk, CD,
CD-ROM (compact-disc-read-only storage), magneto-optic disk, ROM (read-only storage), RAM (random access memory), EPROM (can
Erasable programmable read-only memory (EPROM)), EEPROM (Electrically Erasable Read Only Memory), magnetic or optical card, flash memory or be suitable to
Other kinds of medium/the machine readable media of storage machine-executable instruction.
Exemplarily, the process of above-mentioned pet scanner acquisition PET data is：Before PET scan, note into person under inspection's body
Enter the medicament (tracer) of radio isotope mark；What detector detection was released from inside subject penetrates into pair annihilation gamma
Line, generates pulse type electric signal corresponding with the light quantity into pair annihilation gamma ray for detecting；The pulse type electric signal is supplied
To PET signal processing unit 202, the PET signal processing unit 202 generates single event data (Single according to electric signal
Event Data), this case that PET signal processing unit 202 exceedes threshold value by the intensity for detecting electric signal in practice, so as to
Electro-detection annihilation gamma ray；Single event data are supplied to coincidence counting unit 203, the coincidence counting unit 203 pairs with it is multiple
The relevant single event data of single event are implemented counting simultaneously and are processed, and specifically, coincidence counting unit 203 is from repetition supply
Repeatedly determine in single event data and be contained in the event data relevant with two single events in time range set in advance, when
Between scope be set to such as 6ns～18ns or so, the paired single event is presumed to origin in from same into pair annihilation point
The paired annihilation gamma ray for producing, wherein paired single event is briefly referred to as meeting event, link detects that this falls into oblivion in pairs
The line for not having gamma-ray paired detector is referred to as line of response (Line Of Response, LOR), corresponding with line of response is met
The data that meet be PET data；Memory cell 204 can store PET data in the case where PET control units 205 are controlled.Need explanation
, as PET scan equipment and measurement process have error, the PET data also needs to carry out detector sensitivity correction, same to position
Plain time decay correction, coincidence correction, coincidence correction, scatter correction, correction for attenuation or geometric correction and other corrections.
The medicament of the above-mentioned radio isotope mark being related to can be reversible tracer or irreversible tracer, and PET sweeps
The process retouched can be using single tracer scanning or many tracer dynamic scans.PET scan is double spikes in one embodiment
Agent dynamic scan, the first tracer I comprising initial time injection1With T0Second tracer I of moment injection2, and first show
Track agent I1For reversible tracer, the second tracer is irreversible tracer, and dynamic scan is specially：PET scan from the beginning of t=0,
And the first tracer I is injected into person under inspection's body in t=01；In t=T0When inject the second tracer I2, elapsed time T1Scanning
Terminate, the whole scanning process duration is T0+T1.In scanning process, the head for injecting tracer is carried out using detector
Real-time detection obtains the radiated signal that sends of person under inspection's head, process this meet detection and acquisition system is processed, formed original
Meet data, frequency acquisition is to gather once at the per unit moment, obtains T0+T1Group coincidence counting, wherein：In T0In time period
The T for collecting0Group coincidence counting the first tracer I of correspondence1, in T1The T collected in time period1Group coincidence counting is simultaneously
The first tracer I of correspondence1With the second tracer I2。
If Fig. 4 is 30 structured flowchart of segmentation of lung parenchyma device of one embodiment of the invention.The segmentation of lung parenchyma device 30 is wrapped
Image segmentation module 300 is included, the image segmentation module 300 includes the first medical image acquisition unit 301, the life of the second medical image
Into unit 302, skin line determining unit 303, cutting unit 304.Exemplarily：First medical image acquisition unit 301, can be even
Memory cell 103 is connect, for obtaining the first medical image of person under inspection's scanned position, first medical image includes several pieces
Tomographic image, and each slice image includes multiple pixels.In one embodiment, the first medical image is a MR images.
Second medical image signal generating unit 302, is connected with the first medical image acquisition unit 301, for the first medical science
The sagittal plane of image is linearly strengthened, and to the first medical image and through linear enhanced first medical image respective pixel
Gray value be added, generate the second medical image, further, linearly strengthened it in the sagittal plane to the first medical image
Before, also gamma correction process can be carried out to the first medical image.In one embodiment, the second medical image can be a MR
Image is added the 2nd MR images for obtaining with the gray value through linear enhanced MR image respective pixels.
Skin line determining unit 303, is connected with the second medical image signal generating unit 302, for determining the second medical image
Sagittal plane skin line, and the cross-section musculus cutaneus of the second medical image is determined on the second medical image that sagittal plane skin line determines
Skin line；
Cutting unit 304, is connected with skin line determining unit 303, for obtaining sagittal plane skin line and cross-section surface skin
The connected domain that line is surrounded, and the segmentation result of lung tissue is obtained in connected domain.Further, can also be tied according to the segmentation of lung tissue
Fruit distributes corresponding attenuation coefficient for each pixel.It should be noted that in another embodiment, segmentation of lung parenchyma device 30 may be used also
It is including skeletal tissue's cutting unit, musculature cutting unit, adipose tissue cutting unit etc., many for imaging region is divided into
Sub-regions, and same tissue is only included per sub-regions, are implemented as respectively organizing as position, the Accurate Segmentation of organ.
In certain embodiments, image segmentation device 30 is capable of achieving the segmentation of multiple organ or tissues such as lung tissue, wherein
The dividing method of lung tissue includes as shown in Figure 5：
Step 510. obtains the first medical image of person under inspection's scanned position, and the first medical image may include several lamellas
Image, and each slice image of the first medical image includes multiple pixels or voxel.Alternatively, the first medical image can be
Three-dimensional magnetic resonance (MR) sequence image, computerized tomography (CT) image or positron emission tomography (PET) image etc., and
First medical image includes sagittal plane (sagittal plane), coronal-plane (coronal plane) and cross section
(transverse plane).If Fig. 6 is the first medical science that the first medical image acquisition of one embodiment of the invention unit 301 is obtained
Image, can be MR images, wherein, Fig. 6 a are cross-sectional view strength；Fig. 6 b are coronal-plane view；Fig. 6 c are sagittal plane view.Three kinds
In view, different gray values represent different scanned positions respectively, lung areas, background area and including bodies such as nasal cavity, oral cavities
The pixel of cavity region has low gray value；The pixel in the regions such as muscle, soft tissue has high gray value.Therefore, only according to ash
Angle value cannot be by lung areas from medical image segmentation.
The sagittal plane (gray value) of the first medical image of step 520. pair is linearly strengthened, and to the first medical image and
It is added through the gray value of the first image respective pixel of grey level enhancement, generates the second medical image.The arrow of the first medical image
Shape face carries out grey level enhancement and can be represented by with formula：
G (x, y)=T [f (x, y)] (formula 1)
Wherein, (x, y) represents the position of the first medical image (sagittal plane) pixel, and x represents the abscissa of pixel, y tables
Show the ordinate of pixel；F (x, y) represents gray value of the front coordinate of the first medical image conversion for the pixel of (x, y)；G (x, y) table
Show that the first medical image conversion recoil is designated as the gray value of the pixel of (x, y)；T represents certain mapping relations；First medical image
Before conversion, the actual range of gray scale is represented by [f1,f2], the scope required after the conversion of the first medical image is represented by [g1,
g2].It is capable of achieving gray scales are stretched or compressed using equation below, so as to reach the effect for strengthening contrast.
In another embodiment, the sagittal plane of the first medical image is carried out linearly strengthening and can be adopted based on gradient of image and gray scale
Linear enhancement method, make the profile and background difference of display foreground become big.Document Weickert is referred to,
J.1996.Anisotropic Diffusion in Image Processing.Ph.D.Thesis,Dept.of
Mathematics, University of Kaiserslautern, Germany, pp.42-43,80-82,107, to realize
The enhancing of target area and region intersection (skin line edge) in one medical image, alternatively adopted two Gaussian smoothing systems
Number may be set to any number between 0.3-0.6.In another embodiment, can be to the imaging organic region in the first medical image
Different greyscale transformations are respectively adopted with background area, and stretch to being imaged the tonal range occupied by organ, to background
It is compressed.In this specific embodiment, following steps can be performed in the second medical image signal generating unit 302：Traversal first
Medical image all pixels, obtain maximum gradation value f of all pixelsmaxWith minimum gradation value fmin；Gray threshold is selected respectively
First medical image is split, and imaging organic region, background area and boundary is obtained in imaging organic region and background area
Domain transitional region between the two；Gray level to being imaged organic region adopts the gray level of stretching conversion, transitional region to keep
It is constant, and compressed transform is adopted to the gray level of background area.In this particular embodiment, gray threshold may be selected double gray scale thresholds
Value fth1And fth2, and fmin<fth1<fth2<fmax.When the gray value f of any pixel in the first medical image meets fmin<f<
fth1, then the pixel classify as background area；When the gray value f of any pixel in the first medical image meets fth1<f<fth2,
Then the pixel classifies as transitional region；When the gray value f of any pixel in the first medical image meets fth2<f<fmax, then should
Pixel classifies as imaging organic region.Scope [g that is corresponding, can requiring after the conversion of the first medical image1,g2] interior setting two
Individual gray threshold gth1And gth2, and g1<gth1<gth2<g2.For imaging organic region, background area and transitional region can be adopted respectively
With following greyscale transformation mode：
By aforesaid operations, the edge of enhanced skin line is obtained.Further, by the first enhanced medical image
It is added with the gray value at each pixel of original first medical image correspondence, you can obtain the second medical image.It should be noted that
To the first medical image enhancement before processing, gamma correction can be carried out to the first medical image also.More specifically, gamma correction mistake
Correction coefficient in journey is may be selected between 1.05-1.45.
Step 530. determines the sagittal plane skin line of the second medical image, and the second medical science determined in sagittal plane skin line
The cross section skin line of the second medical image is determined on image.Exemplarily, the sagittal plane skin line of the second medical image can lead to
Cross skin line determining unit 303 to obtain, and step as shown in Figure 7 is performed in the unit：
Sagittal each pixel of the second medical image of step 710. pair carries out binary conversion treatment using given threshold；
Step 720. counts the quantity of the included connected domain of sagittal each lamella of the second medical image；
Whether step 730. judges the quantity of the included connected domain of each lamella less than the first given threshold, if condition is full
Foot, then retain the connected domain, and execution step 750；Otherwise, execution step 740；In certain embodiments, first setting
Threshold value may be provided at any integer value between 1-5.Only Retention area is maximum in the included connected domain of each lamella for step 740.
One or more connected domains, and execution step 750；Alternatively, first given threshold is set as 2 in one embodiment,
At most retain two connected domains in each lamella by aforesaid operations, two connected domains are area maximum in all connected domains
The first connected domain and only secondary first connected domain of area the second connected domain.
Step 750. determines the sagittal plane skin line of the second medical image according to the connected domain for retaining.
In an embodiment of the invention, in each pixel sagittal to the second medical image using setting pixel threshold
Before carrying out binary conversion treatment, the three-dimensional cross-sectional image data of the second medical image can be converted into three sagittal plane picture numbers
According to, and set the optional 30-60 of the scope of pixel threshold.
Exemplarily, the sagittal plane skin line of the second medical image is obtained by following process：Obtain slice image border
Upper pixel value is 1 point, and is closed the connected domain for retaining according to the point that pixel value is 1；Reservation connected domain to closing is carried out
Filling, will gray value be that 0 position is entered as 1 in connected domain, and the boundary pixel set of connected domain after filling is the second doctor
Learn the sagittal plane skin line of image.In this particular embodiment, the closing course of the connected domain of reservation is：For by step
730 connected domains for retaining, if there is common factor the coboundary or lower boundary of connected domain and image on each lamella tomographic image, close
Lower boundary or coboundary.Illustrate as a example by following closing of the frontier, border is located at the Nth row of slice image instantly, on search N-1 rows
First pixel value is 1 position (N-1, A) and position (N-1, B) that last pixel value is 1, then by Nth row from A row
Pixel value to B row is assigned to 1, forms the connected domain of a closure, and A, B represent the columns that pixel is located respectively.
On the basis of the second medical image of acquisition is sagittal, the cross section of the second medical image can be determined based on this
Skin line.Exemplarily, first, the second medical image that the sagittal plane skin line determines is obtained, second medical image is
Three-dimensional sagittal plane view data；Then, each lamella in the second medical image cross section for determining to sagittal plane skin line is carried out
Two-dimentional corrosion treatmentCorrosion Science, connected domain of the Retention area more than the first setting area threshold；The area of the reservation is set more than first
The connected domain for determining area threshold carries out two-dimensional swelling process, and determines second doctor according to the connected domain after two-dimensional swelling process
Learn the cross section skin line of image.In above process, the first setting area threshold is may be provided between 100-200.At one
In embodiment, the first setting area threshold may be set to 150.The second medical image cross section that sagittal plane skin line is determined
Each slice image carries out the circle that two-dimentional etching operation available parameter radius is 3-6；Two-dimensional swelling processes available parameter
Circle of the radius for 2-4.
Step 540. obtains the connected domain that sagittal plane skin line and cross section skin line are surrounded, and in connected domain obtains lung
The segmentation result of tissue.Exemplarily, as shown in Figure 8 in segmentation of lung parenchyma unit 304 can perform following Procedure Acquisition lung group
The segmentation result knitted：
Step 810. obtains high gray scale in connected domain (being surrounded by sagittal plane skin line and cross section skin line) cross section
The boundary pixel point of value connected domain, i.e., split high gray value connected domain in connected domain cross section, obtains high gray value connected domain side
In boundary, pixel value is 1 point, and pixel value is that the collection of 1 point composition is combined into boundary pixel point., exemplarily, can first according to arrow
The three-dimensional cross section greyscale image data that shape surface skin line and cross section skin line determine enters row threshold division, and (gray threshold is optional
Select 30-60), binary image is obtained, even image intensity value is 1 more than the pixel of gray threshold, other pixels are 0.Then
The characteristics of being imaged according to lung tissue screens connected domain, in this specific embodiment, can count connected domain in each slice image
Number, if the number of connected domain is less equal than the second given threshold, retains all connected domains；If connected domain number is more
In the second given threshold, then retain the connected domain that quantity is equal to the second given threshold；For the connected domain for retaining further is filled out
Fill process, and calculate the area of connected domain after filling, remove company of the connected domain area less than the second setting area threshold after filling
Logical domain, finally gives high gray value region (connected domain).In certain embodiments, the second given threshold is may be configured as between 3-5
Any number.Alternatively, the second given threshold may be set to 3, and the connected domain for retaining is I1、I2And I3.In one embodiment
In, make the connected domain for retaining be I1Area be S1, make the connected domain for retaining be I2Area be S2The connected domain that order retains is I3
Area be S3, maximum connected domain I of area in connected domain to be removed4, and lead I4Area be S4, then S should be met1≥S4；S2
≥S4；S3≥S4.In another embodiment, the second setting area threshold may be provided at any number between 200-250.
Step 820. obtains cross section segmentation figure picture and coronal-plane segmentation figure picture in the connected domain that boundary pixel point is surrounded,
Cross section segmentation figure picture or coronal-plane segmentation figure picture are low gray value region.In one embodiment, all pixels value is 1 picture
Vegetarian refreshments can be by the connected domain closure for retaining.There is low gray value region in the closed communicating domain of above-mentioned reservation.Can be to high gray scale
The three-dimensional cross section greyscale image data that value determines enters row threshold division (gray threshold may be set to 30-60), obtains binaryzation
Image；The number of connected domain in each slice image is counted, if the number of connected domain is less than 2, retains all connected domains；
If connected domain number more than two, 2 maximum connected domains of Retention area, the connected domain obtained through aforesaid operations are
Cross section segmentation figure picture.Further, for cross section segmentation figure picture determines 3-D view region, on its corresponding coronal-plane
The number of connected domain in each slice image is counted, if the number of connected domain is less than 2, retains all connected domains；If
Connected domain number more than two, then 2 maximum connected domains of Retention area, as coronal through the connected domain of aforesaid operations acquisition
Face segmentation figure picture.
Step 830. obtains center line according to coronal-plane segmentation figure picture.In one embodiment, the acquisition process of center line
May include：Coronal-plane segmentation figure is calculated as the connected domain area of each lamella, the maximum lamella of connected domain area is determined；In connection
The initial row and termination row of connected domain are determined in the maximum lamella of domain area；In being determined according to the initial row and termination row of connected domain
Heart line.In an embodiment of the present invention, for coronal-plane segmentation figure picture can travel through the gross area of connected domain in each slice image,
Relatively on each lamella, the area of connected domain can obtain the maximum lamella S of connected domain area.The connected domain area is maximum
The bianry image of lamella S can be projected along Y-axis, find the initial row L of connected domain1With termination row L2, initial row L1That is lung tissue
The initial row in region, termination row L2The as termination row in lung tissue region, L1And L2Mean value be center line be located line number
L3。
Step 840. determines lung tissue pair in the position of cross section segmentation figure picture and coronal-plane segmentation figure picture according to center line
The connected domain answered.Exemplarily, the step of connected domain corresponding according to center line acquisition lung tissue it is：In coronal-plane segmentation figure picture
It is upper to retain the connected domain is expert at by center line；The connected domain being expert to center line in cross section is filled, and obtains tissue right
The connected domain answered.In a specific embodiment of the invention, can retain through center line L in coronal-plane segmentation figure picture3It is be expert at (such as：
[L3- 2, L3+ 3] it is) or be expert at (such as through image lower boundary：[N-3, N]) connected domain；To coronal-plane segmentation figure picture, conversion
To on corresponding cross section, it is filled to retaining connected domain, obtains segmentation of lung parenchyma result.The lung obtained by said process
Tissue segmentation result can avoid impact of the background area to lung segmentation result, improve the accuracy of automatic segmentation, be suitable for
Scan in many beds, improve sweep speed.
In PET/MR multi-mode imaging systems, it usually needs the information based on MR images carries out PET correction for attenuations：By MR
Image segmentation is divided into several regions, and wherein each region includes multiple voxels for belonging to same tissue or organ respectively,
Several regions can correspond to the voxel of the Different Organs such as skin, lung tissue, soft tissue and bone or tissue respectively；According to priori
Information is that different attenuation coefficients are distributed in several regions of segmentation.
The dividing method of lung tissue of the present invention can accurately and efficiently realize the automatic segmentation of lung tissue in medical image.Such as
Fig. 9 a are the cross section skin line result schematic diagram that one embodiment of the invention is obtained, by the skin line (outside of lung areas
Outline line) background area and image tissue region of medical image, and image tissue intra-zone can be distinguished comprising different gray scales
Value region, and the air section of bone tissue and lung tissue shows as high gray value simultaneously.Fig. 9 b are obtained for one embodiment of the invention
Segmentation of lung parenchyma result schematic diagram, above-mentioned skin line surround connected domain on the basis of, can accurately confirm the region A of lung tissue
And B, realize accurately identifying for air section that lung tissue includes and bone tissue；Gray scale with reference to lung tissue in coronal image
Distribution and positional information, it is to avoid using complicated priori matching template, are applicable to many bed scannings.
In other embodiments of the invention, above-mentioned Medical Image Processing module can be used for the correction for attenuation of PET imagings.Show
Example property ground, rebuilds the segmentation of lung parenchyma result that module 400 can be obtained according to image segmentation module 300, corrects PET data.Rebuild
Module 400 can iterative approximation PET data, and according to after iterative approximation PET data produce PET image, wherein, in PET data
The PET data is corrected using decay pattern during iterative approximation, and in the iterative reconstruction process of PET data, iteration updates
State decay pattern.
Control module 500 can be centralized, such as data center；It can also be distributed, such as one distribution
Formula system.Control module 500 can be local, or long-range.In certain embodiments, control module 500 can be with
Including central processing unit (Central Processing Unit, CPU), specialized application integrated circuit (Application
Specific Integrated Circuit, ASIC), dedicated instruction processor (Application Specific
Instruction Set Processor, ASIP), concurrent physical processor (Physics Processing Unit, PPU), numeral
Signal processor (Digital Processing Processor, DSP), field programmable gate array (Field-
Programmable Gate Array, FPGA), PLD (Programmable Logic Device, PLD),
The combination of one or more in processor, microprocessor, controller, microcontroller etc..
Display module 600 may also display the height of person under inspection, body weight, age, imaging position, MR scan modules 100, PET
The working condition of scan module 200, the MRI at imaging position or PET image etc..The type of display module 600 can be
In cathode-ray tube (CRT) display, liquid crystal display (LCD), OLED (OLED), plasma display etc.
The combination of one or more.
It should be noted that each module of the magic magiscan of the present invention or unit can connect each other, the company
Connecing can be wireless network connection or finite element network connection.Wherein, cable network can be included using metallic cable, mixing electricity
The mode of one or more combination such as cable, one or more interfaces.Wireless network can be included using bluetooth, regional area networks
(LAN), one or more group of wide local area network (WAN), near source field communication (Near Field Communication, NFC) etc.
The mode of conjunction.
Above for the description of magic magiscan, only for convenience of description, the application can not be limited in and is lifted
Within scope of embodiments.It is appreciated that for a person skilled in the art, after the principle for understanding the system, Ke Neng
In the case of without departing substantially from this principle, modules are combined, or constitute subsystem and be connected with other modules, it is right
Implement said method and various amendments and change in systematic difference field form and details.
In one embodiment, the process of magic magiscan process multi-modality medical image is：Scanned using MR
Module 100 scans person under inspection's organic region, obtains the MR images of correspondence organic region, and is stored in memory cell 103；Using
PET scan module 200 scans person under inspection's organic region, obtains the PET data of correspondence organic region, and is stored in memory 204；
Image segmentation module 300 obtains MR images from memory cell 103, obtains sagittal plane skin line and cross-section surface skin from MR images
Line, and the corresponding connected domain of lung tissue is determined according to skin line, and, determined according to the architectural feature of lung tissue in connected domain
The segmentation result of lung tissue；Rebuild module 400 to be connected with segmentation of lung parenchyma unit 304, memory 204, can be according to lung tissue point
The segmentation result for cutting the acquisition of unit 304 is that each pixel (or voxel) distributes respective attenuation coefficient, generates the first decay pattern；According to
One decay pattern rebuilds PET data, obtains the first PET image；First decay pattern is updated according to the first PET image, and produces second
Decay pattern；The first PET image is rebuild based on the second decay pattern, obtain the second PET image；Repeat said process and know product
The final target decay pattern (decay pattern estimation) of life and final goal PET image (PET image estimation).
Further, display module 600 can show the multi-modality images of PET image and MR image co-registrations, and image melts
Close and can adopt light stream field method, the method for registering of distinguished point based, the method for registering based on appearance profile or be based on gray value etc.
Method for registering.
It should be noted that through the above description of the embodiments, those skilled in the art can be understood that
Part or all of to the present invention can be realized by software and with reference to required general hardware platform.Based on such understanding,
Can be embodied in the form of software product the part that technical scheme is substantially contributed to prior art in other words
Out, the computer software product may include one or more machine readable medias for being stored thereon with machine-executable instruction,
These instructions can be caused when by one or more machines execution such as computer, computer network or other electronic systems should
One or more machine embodiments in accordance with the present invention are performing operation.
Although the present invention is disclosed as above with preferred embodiment, so which is not limited to the present invention, any this area skill
Art personnel, without departing from the spirit and scope of the present invention, when a little modification and perfect, therefore the protection model of the present invention can be made
Enclose when by being defined that claims are defined.
Claims (10)
1. a kind of segmentation of lung parenchyma method, comprises the steps：
The first medical image of person under inspection target area is obtained, first medical image includes several slice images, described
Each slice image includes multiple pixels；
The sagittal plane of first medical image is linearly strengthened, and to first medical image and through linear enhancing
The first image respective pixel gray value be added, generate the second medical image；
Determine the sagittal plane skin line of second medical image, and the second medical image determined in the sagittal plane skin line
The upper cross section skin line for determining second medical image；
The connected domain that the sagittal plane skin line and cross section skin line are surrounded is obtained, and lung tissue is obtained in the connected domain
Segmentation result.
2. segmentation of lung parenchyma method according to claim 1, it is characterised in that first medical image be CT images or
MR images.
3. segmentation of lung parenchyma method according to claim 1, it is characterised in that the sagittal musculus cutaneus of second medical image
Skin line is obtained by following process：
Binary conversion treatment is carried out using given threshold to sagittal each pixel of second medical image；
The quantity of the included connected domain of sagittal each lamella of statistics second medical image Jing after binary conversion treatment；
Judge that the quantity of the included connected domain of each lamella, whether less than the first given threshold, if condition meets, retains described
Connected domain；Otherwise, comprising connected domain in only one or more maximum connected domains of Retention area；
The sagittal plane skin line of second medical image is determined according to the connected domain of the reservation.
4. segmentation of lung parenchyma method according to claim 3, it is characterised in that also including obtaining picture on slice image border
Element value is 1 point, and is closed the connected domain for retaining according to the point that the pixel value is 1.
5. segmentation of lung parenchyma method according to claim 1, it is characterised in that the cross-section musculus cutaneus of second medical image
Skin line is determined by following process：
Obtain the second medical image that the sagittal plane skin line determines；
Each lamella in the second medical image cross section determined to the sagittal plane skin line carries out two-dimentional corrosion treatmentCorrosion Science, retains
Connected domain of the area more than the first setting area threshold；
Two-dimensional swelling process is carried out more than the connected domain of the first setting area threshold to the area of the reservation, and it is swollen according to two dimension
Connected domain after swollen process determines the cross section skin line of second medical image.
6. segmentation of lung parenchyma method according to claim 1, it is characterised in that the segmentation result of the lung tissue is by such as
Lower process is obtained：
The boundary pixel point of high gray value connected domain is obtained in the cross section of the connected domain；
Cross section segmentation figure picture and coronal-plane segmentation figure picture are obtained in the connected domain that the boundary pixel point is surrounded, it is described cross-section
Face segmentation figure picture or the coronal-plane segmentation figure picture are low gray value region；
Center line is obtained according to the coronal-plane segmentation figure picture；
Lung tissue pair is determined in the position of the cross section segmentation figure picture and the coronal-plane segmentation figure picture according to the center line
The connected domain answered.
7. segmentation of lung parenchyma method according to claim 6, it is characterised in that the center line is obtained by following process
Take：
The coronal-plane segmentation figure is calculated as the connected domain area of each lamella, the maximum lamella of connected domain area is determined；
The initial row and termination row of connected domain are determined in the maximum lamella of the connected domain area；
Center line is determined according to the initial row and termination row of the connected domain.
8. segmentation of lung parenchyma method according to claim 6, it is characterised in that according to the center line in the cross section
The position of segmentation figure picture and the coronal-plane segmentation figure picture determines concretely comprising the following steps for the corresponding connected domain of lung tissue：
Retain the connected domain is expert at by center line on the coronal-plane segmentation figure picture；
The connected domain is expert at by the center line is filled on the cross section segmentation figure picture, obtains lung tissue corresponding
Connected domain.
9. a kind of segmentation of lung parenchyma device, including image segmentation module, the image segmentation module include：
First medical image acquisition unit, for receiving the first medical image of person under inspection target area, the first medical science figure
As including several slice images, described each slice image includes multiple pixels；
Second medical image signal generating unit, for linearly being strengthened to the sagittal plane of first medical image, and to described
First medical image is added with the gray value through linear enhanced first medical image respective pixel, generates the second medical science figure
Picture；
Skin line determining unit, for determining the sagittal plane skin line of second medical image, and in the sagittal surface skin
The cross section skin line of second medical image is determined on the second medical image that line determines；
Cutting unit, for obtaining the connected domain that the sagittal plane skin line and cross section skin line are surrounded, and in the connection
The segmentation result of lung tissue is obtained in domain.
10. a kind of magic magiscan, it is characterised in that the magic magiscan is included such as claim 9 institute
The segmentation of lung parenchyma device stated, also includes：
MR scan modules, for scanning person under inspection target area, and obtain corresponding first medical image in the target area；
PET scan module, for scanning the target area, and gathers the corresponding PET data in target Europe region；
Module is rebuild, for obtaining the segmentation of lung parenchyma result that the segmentation of lung parenchyma device is obtained, and for the lung of the segmentation
Organize each pixel to distribute respective attenuation coefficient, generate decay pattern, and the PET data according to the decay pattern iterative approximation
Produce PET image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610912654.0A CN106558045B (en) | 2016-10-20 | 2016-10-20 | A kind of segmentation of lung parenchyma method, apparatus, magic magiscan |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610912654.0A CN106558045B (en) | 2016-10-20 | 2016-10-20 | A kind of segmentation of lung parenchyma method, apparatus, magic magiscan |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106558045A true CN106558045A (en) | 2017-04-05 |
| CN106558045B CN106558045B (en) | 2019-07-19 |
Family
ID=58443306
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610912654.0A Active CN106558045B (en) | 2016-10-20 | 2016-10-20 | A kind of segmentation of lung parenchyma method, apparatus, magic magiscan |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106558045B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107260137A (en) * | 2017-07-31 | 2017-10-20 | 济南显微智能科技有限公司 | It is a kind of to detect ICG and double Tracing detection device and methods of methylenum careuleum simultaneously |
| CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
| CN109512449A (en) * | 2018-09-26 | 2019-03-26 | 沈阳东软医疗系统有限公司 | Physiological parameter output method and device |
| CN110363744A (en) * | 2019-06-10 | 2019-10-22 | 深圳市智影医疗科技有限公司 | A kind of lung's age detection method and apparatus |
| CN110555860A (en) * | 2018-06-04 | 2019-12-10 | 青岛海信医疗设备股份有限公司 | Method, electronic device and storage medium for marking rib region in medical image |
| CN110689550A (en) * | 2019-10-12 | 2020-01-14 | 嘉应学院 | Efficient and automatic screening system and method for lumbar vertebra sagittal plane CT (computed tomography) images |
| CN111128317A (en) * | 2019-11-20 | 2020-05-08 | 中国辐射防护研究院 | Ionizing radiation tissue equivalent material formula design method and system |
| CN111312369A (en) * | 2018-12-11 | 2020-06-19 | 脉得谱株式会社 | Medical image reconstruction method and device |
| CN111918610A (en) * | 2018-05-16 | 2020-11-10 | 松下电器产业株式会社 | Gradation conversion method for chest X-ray image, gradation conversion program, gradation conversion device, server device, and conversion method |
| CN112884792A (en) * | 2021-02-02 | 2021-06-01 | 青岛海信医疗设备股份有限公司 | Lung image segmentation method and device, electronic equipment and storage medium |
| CN114943856A (en) * | 2021-04-12 | 2022-08-26 | 四川省肿瘤医院 | Pulmonary nodule region identification method, labeling method and identification system |
| CN115937163A (en) * | 2022-12-19 | 2023-04-07 | 西北民族大学 | Target region extraction method and system for SPECT lung perfusion imaging |
| US11657508B2 (en) | 2019-01-07 | 2023-05-23 | Exini Diagnostics Ab | Systems and methods for platform agnostic whole body image segmentation |
| CN116205920A (en) * | 2023-05-05 | 2023-06-02 | 天津医科大学总医院 | Method and system for generating key region detection model based on lung scanning data |
| US11894141B2 (en) | 2016-10-27 | 2024-02-06 | Progenics Pharmaceuticals, Inc. | Network for medical image analysis, decision support system, and related graphical user interface (GUI) applications |
| US11900597B2 (en) | 2019-09-27 | 2024-02-13 | Progenics Pharmaceuticals, Inc. | Systems and methods for artificial intelligence-based image analysis for cancer assessment |
| TWI835768B (en) | 2018-01-08 | 2024-03-21 | 美商普吉尼製藥公司 | Systems and methods for rapid neural network-based image segmentation and radiopharmaceutical uptake determination |
| US11937962B2 (en) | 2019-04-24 | 2024-03-26 | Progenics Pharmaceuticals, Inc. | Systems and methods for automated and interactive analysis of bone scan images for detection of metastases |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040206913A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for characterization of tissue samples |
| CN101273919A (en) * | 2007-03-30 | 2008-10-01 | 通用电气公司 | Sequential image acquisition with updating method and system |
| CN101379413A (en) * | 2006-02-03 | 2009-03-04 | 皇家飞利浦电子股份有限公司 | Accounting for foreign objects when creating CT-based attenuation maps |
| CN102274038A (en) * | 2010-06-10 | 2011-12-14 | 株式会社岛津制作所 | Radiological image area extracting apparatus, radiological image area extraction program, and radiographic apparatus |
| CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
| CN104992445A (en) * | 2015-07-20 | 2015-10-21 | 河北大学 | Automatic division method for pulmonary parenchyma of CT image |
| US20160005193A1 (en) * | 2014-07-02 | 2016-01-07 | Covidien Lp | System and method for segmentation of lung |
-
2016
- 2016-10-20 CN CN201610912654.0A patent/CN106558045B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040206913A1 (en) * | 2003-04-18 | 2004-10-21 | Medispectra, Inc. | Methods and apparatus for characterization of tissue samples |
| CN101379413A (en) * | 2006-02-03 | 2009-03-04 | 皇家飞利浦电子股份有限公司 | Accounting for foreign objects when creating CT-based attenuation maps |
| CN101273919A (en) * | 2007-03-30 | 2008-10-01 | 通用电气公司 | Sequential image acquisition with updating method and system |
| CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
| CN102274038A (en) * | 2010-06-10 | 2011-12-14 | 株式会社岛津制作所 | Radiological image area extracting apparatus, radiological image area extraction program, and radiographic apparatus |
| US20160005193A1 (en) * | 2014-07-02 | 2016-01-07 | Covidien Lp | System and method for segmentation of lung |
| CN104992445A (en) * | 2015-07-20 | 2015-10-21 | 河北大学 | Automatic division method for pulmonary parenchyma of CT image |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11894141B2 (en) | 2016-10-27 | 2024-02-06 | Progenics Pharmaceuticals, Inc. | Network for medical image analysis, decision support system, and related graphical user interface (GUI) applications |
| CN107260137A (en) * | 2017-07-31 | 2017-10-20 | 济南显微智能科技有限公司 | It is a kind of to detect ICG and double Tracing detection device and methods of methylenum careuleum simultaneously |
| CN107563998B (en) * | 2017-08-30 | 2020-02-11 | 上海联影医疗科技有限公司 | Method for processing heart image in medical image |
| CN107563998A (en) * | 2017-08-30 | 2018-01-09 | 上海联影医疗科技有限公司 | Medical image cardiac image processing method |
| TWI835768B (en) | 2018-01-08 | 2024-03-21 | 美商普吉尼製藥公司 | Systems and methods for rapid neural network-based image segmentation and radiopharmaceutical uptake determination |
| CN111918610A (en) * | 2018-05-16 | 2020-11-10 | 松下电器产业株式会社 | Gradation conversion method for chest X-ray image, gradation conversion program, gradation conversion device, server device, and conversion method |
| 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 |
| CN110555860A (en) * | 2018-06-04 | 2019-12-10 | 青岛海信医疗设备股份有限公司 | Method, electronic device and storage medium for marking rib region in medical image |
| CN109512449A (en) * | 2018-09-26 | 2019-03-26 | 沈阳东软医疗系统有限公司 | Physiological parameter output method and device |
| CN111312369A (en) * | 2018-12-11 | 2020-06-19 | 脉得谱株式会社 | Medical image reconstruction method and device |
| US11941817B2 (en) | 2019-01-07 | 2024-03-26 | Exini Diagnostics Ab | Systems and methods for platform agnostic whole body image segmentation |
| US11657508B2 (en) | 2019-01-07 | 2023-05-23 | Exini Diagnostics Ab | Systems and methods for platform agnostic whole body image segmentation |
| US11937962B2 (en) | 2019-04-24 | 2024-03-26 | Progenics Pharmaceuticals, Inc. | Systems and methods for automated and interactive analysis of bone scan images for detection of metastases |
| CN110363744A (en) * | 2019-06-10 | 2019-10-22 | 深圳市智影医疗科技有限公司 | A kind of lung's age detection method and apparatus |
| US11900597B2 (en) | 2019-09-27 | 2024-02-13 | Progenics Pharmaceuticals, Inc. | Systems and methods for artificial intelligence-based image analysis for cancer assessment |
| CN110689550B (en) * | 2019-10-12 | 2022-06-21 | 嘉应学院 | High-efficiency automatic screening system and method for CT (computed tomography) images of sagittal plane of lumbar vertebra |
| CN110689550A (en) * | 2019-10-12 | 2020-01-14 | 嘉应学院 | Efficient and automatic screening system and method for lumbar vertebra sagittal plane CT (computed tomography) images |
| CN111128317A (en) * | 2019-11-20 | 2020-05-08 | 中国辐射防护研究院 | Ionizing radiation tissue equivalent material formula design method and system |
| CN112884792A (en) * | 2021-02-02 | 2021-06-01 | 青岛海信医疗设备股份有限公司 | Lung image segmentation method and device, electronic equipment and storage medium |
| CN114943856A (en) * | 2021-04-12 | 2022-08-26 | 四川省肿瘤医院 | Pulmonary nodule region identification method, labeling method and identification system |
| CN114943856B (en) * | 2021-04-12 | 2024-04-26 | 四川省肿瘤医院 | Lung nodule region identification method, labeling method and identification system |
| CN115937163B (en) * | 2022-12-19 | 2023-07-28 | 西北民族大学 | Method and system for extracting target region of SPECT (single photon emission computed tomography) lung perfusion imaging |
| CN115937163A (en) * | 2022-12-19 | 2023-04-07 | 西北民族大学 | Target region extraction method and system for SPECT lung perfusion imaging |
| CN116205920B (en) * | 2023-05-05 | 2023-07-18 | 天津医科大学总医院 | Method and system for generating key region detection model based on lung scanning data |
| CN116205920A (en) * | 2023-05-05 | 2023-06-02 | 天津医科大学总医院 | Method and system for generating key region detection model based on lung scanning data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106558045B (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106558045B (en) | A kind of segmentation of lung parenchyma method, apparatus, magic magiscan | |
| CN106600609B (en) | Spine segmentation method and system in medical image | |
| CN107644421B (en) | Medical image segmentation method and system | |
| CN109961834B (en) | Image diagnosis report generation method and device | |
| US9204817B2 (en) | Attenuation correction in positron emission tomography using magnetic resonance imaging | |
| CN102525466B (en) | Image processing apparatus and MR imaging apparatus | |
| CN105263407B (en) | Use the detection to bone tissue of magnetic resonance imaging | |
| US8588486B2 (en) | Apparatus and method for isolating a region in an image | |
| US8787648B2 (en) | CT surrogate by auto-segmentation of magnetic resonance images | |
| US8218848B2 (en) | System and method for the generation of attenuation correction maps from MR images | |
| CN100550004C (en) | A kind of method that the three-dimensional medical image that comprises region of interest is cut apart | |
| Kartmann et al. | Integrated PET/MR imaging: automatic attenuation correction of flexible RF coils | |
| CN103445801B (en) | For performing the method and system of correction for attenuation | |
| CN107599412A (en) | A kind of three-dimensional modeling method based on institutional framework, system and threedimensional model | |
| CN103562960B (en) | For generating the assigned unit between the image-region of image and element class | |
| US8867814B2 (en) | Methods and systems for generating a positron emission tomography attenuation correction map | |
| US20180356484A1 (en) | Removal of image artifacts in sense-mri | |
| WO2021169695A1 (en) | Ct image generation method for attenuation correction of pet images | |
| Krokos et al. | A review of PET attenuation correction methods for PET-MR | |
| Ai et al. | Feasibility of using respiration‐averaged MR images for attenuation correction of cardiac PET/MR imaging | |
| Rybak et al. | Measurement of the upper respiratory tract aerated space volume using the results of computed tomography | |
| Papp et al. | Deep learning for improving ZTE MRI images in free breathing | |
| US20240046535A1 (en) | System and method for pet-ct image artifact evaluation and correction | |
| CN103654829A (en) | Method for generating a pet image data record and facility therefor | |
| Manber et al. | Practical PET respiratory motion correction in clinical simultaneous PET/MR |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 201807 Shanghai city Jiading District Industrial Zone Jiading Road No. 2258 Patentee after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai city Jiading District Industrial Zone Jiading Road No. 2258 Patentee before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder |