CN107301645A - A kind of data processing method and device - Google Patents
A kind of data processing method and device Download PDFInfo
- Publication number
- CN107301645A CN107301645A CN201710471722.9A CN201710471722A CN107301645A CN 107301645 A CN107301645 A CN 107301645A CN 201710471722 A CN201710471722 A CN 201710471722A CN 107301645 A CN107301645 A CN 107301645A
- Authority
- CN
- China
- Prior art keywords
- view data
- cerebral infarction
- dead zone
- weighted imaging
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Abstract
The embodiments of the invention provide a kind of data processing method and device.On the one hand, this method includes：Half-tone information in the diffusion-weighted imaging view data of the different b values of acquisition splits highlight regions to determine cerebral infarction dead zone automatically, according to the Perfusion weighted imaging view data of acquisition, perfusion parameters view data is obtained using assignment algorithm, ischemic area is determined using perfusion parameters view data and the internal anatomy obtained；Image registration is carried out to diffusion-weighted imaging view data and Perfusion weighted imaging view data, the mismatch information that registration result obtains cerebral infarction dead zone and ischemic area is then based on.In embodiments of the present invention, cerebral infarction dead zone and ischemic area can be determined by aforesaid operations, due to being analyzed without doctor diffusion-weighted imaging and Perfusion weighted imaging view data, and go out cerebral infarction dead zone and ischemic area without manually determined, therefore shorten the duration for confirming to be consumed when cerebral infarction dead zone and ischemic area.
Description
【Technical field】
The present invention relates to medical imaging technical field, more particularly to a kind of data processing method and device.
【Background technology】
Using MRI (Magnetic Resonance Imaging, magnetic resonance imaging) imaging technique, DWI can be obtained
(Diffusion weighted imaging, diffusion-weighted imaging) view data and PWI (Perfusion weighted
Imaging, Perfusion weighted imaging) view data, the offer of DWI view data and PWI view data to the judgement of acute cerebral infarction
Effective iconography information.In the prior art, after DWI view data and PWI view data is obtained, doctor is needed to DWI
View data and PWI view data carry out hand labeled respectively, and cerebral infarction dead zone and ischemic area are determined respectively.
In process of the present invention is realized, inventor has found that at least there are the following problems in the prior art：
Because aforesaid operations need after doctor analyzes DWI view data and PWI view data, to manually complete determination
Cerebral infarction dead zone and the operation of ischemic area, therefore, in the prior art it is determined that when cerebral infarction dead zone and ischemic area, consumption
Time is longer.
【The content of the invention】
In view of this, the embodiments of the invention provide a kind of data processing method and device, exist to solve prior art
When determining cerebral infarction dead zone and ischemic area, the problem of elapsed time is longer.
In a first aspect, the embodiments of the invention provide a kind of data processing method, methods described includes：
The diffusion-weighted imaging view data of different b values is obtained, the diffusion-weighted imaging view data has gray scale letter
Breath；
Split highlight regions automatically to determine cerebral infarction dead zone according to the half-tone information；
Perfusion weighted imaging view data is obtained, and obtains the targeted position of Perfusion weighted imaging view data
Internal anatomy；
According to the Perfusion weighted imaging view data, perfusion parameters view data is obtained using assignment algorithm, institute is utilized
State perfusion parameters view data and the internal anatomy determines ischemic area；
Image registration is carried out to the diffusion-weighted imaging view data and Perfusion weighted imaging view data and obtains registration
As a result；
The mismatch information of cerebral infarction dead zone and ischemic area is obtained based on the registration result.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
Half-tone information is stated to split highlight regions automatically to determine cerebral infarction dead zone, including：
According to the half-tone information, the grey level histogram of the diffusion-weighted imaging view data of the high b values is obtained；
According to the grey level histogram and the diffusion-weighted imaging view data of the different b values, in the high b values more
Dissipate and split highlight regions in weighted imaging view data automatically to determine cerebral infarction dead zone.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
The diffusion-weighted imaging view data of grey level histogram and the different b values is stated, in the diffusion-weighted imaging image of the high b values
Cerebral infarction dead zone is determined in data, including：
Gauss curve fitting is carried out to the grey level histogram, the Gaussian function of the grey level histogram is obtained；
According to the Gaussian function, doubtful cerebral infarction dead band is determined in the diffusion-weighted imaging view data of the high b values
Domain；
According to the diffusion-weighted imaging view data of the different b values, the artifact in the doubtful cerebral infarction dead zone is removed
Region, obtains the cerebral infarction dead zone.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
Gaussian function is stated, doubtful cerebral infarction dead zone is determined in the diffusion-weighted imaging view data of the high b values, including：
According to the Gaussian function, the average value and standard deviation of the Gaussian function are obtained；
According to the average value and the standard deviation, threshold value；
The gray value of each pixel in diffusion-weighted imaging view data based on the high b values, by each pixel
The gray value of point is compared with the threshold value, if the threshold value is less than or equal to the gray value of a pixel, it is determined that should
Pixel is target pixel points；
The region that each target pixel points are constituted is used as the doubtful cerebral infarction dead zone.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, according to described
The diffusion-weighted imaging view data of different b values, removes the artifact region in the doubtful cerebral infarction dead zone, obtains the cerebral infarction
Before dead zone, in addition to：
Using Morphology Algorithm, doubtful cerebral infarction dead zone is handled, with remove in the doubtful cerebral infarction dead zone by
Influence of noise is more than the region of designated value.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
Half-tone information is stated to split highlight regions automatically to determine cerebral infarction dead zone, including：
According to the half-tone information, using gray value clustering procedure, in the diffusion-weighted imaging view data of the high b values
It is automatic to split highlight regions to determine cerebral infarction dead zone.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
Perfusion weighted imaging view data is stated, perfusion parameters view data is obtained using assignment algorithm, utilizes the perfusion parameters image
Data and the internal anatomy determine ischemic area, including：
According to the Perfusion weighted imaging view data, using deconvolution algorithm or non-deconvolution algorithm, perfusion ginseng is obtained
Number；
According to the perfusion parameters and the internal anatomy, ischemic area is determined.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, the perfusion ginseng
Number includes：Mean transit time view data.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
Perfusion parameters and the internal anatomy are stated, ischemic area is determined, including：
Dividing processing is carried out to the internal anatomy；
According to dividing processing result, the brain parenchym region in the internal anatomy is determined；
Brain parenchym region registration in the internal anatomy is mapped to the mean transit time view data；
According to registering mapping result, the brain parenchym region in the mean transit time view data is determined；
The gray-scale watermark in the brain parenchym region in the mean transit time view data, is obtained described average
The grey level histogram in the brain parenchym region in passage time view data；
The grey level histogram in the brain parenchym region in the mean transit time view data, averagely passes through described
Ischemic area is determined in temporal image data.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described according to institute
The grey level histogram in the brain parenchym region in mean transit time view data is stated, in the mean transit time view data
Ischemic area is determined, including：
The grey level histogram in the brain parenchym region in the mean transit time view data, obtains described average logical
Cross the mean transit time average value of time view data midbrain parenchyma section；
According to the mean transit time average value, threshold value is obtained；
Based on each pixel gray value in the mean transit time view data midbrain parenchyma section, by each pixel
The gray value of point is compared with the threshold value, if the threshold value is less than the gray value of a pixel, determines that the pixel is
Target pixel points；
The region that each target pixel points are constituted is used as ischemic area.
Aspect as described above and any possible implementation, it is further provided a kind of implementation, it is described will be every
Before the gray value of individual pixel is compared with the threshold value, in addition to：
Brain parenchym region in the mean transit time view data is smoothed.
A technical scheme in above-mentioned technical proposal has the advantages that：
In embodiments of the present invention, after the diffusion-weighted imaging view data of different b values is obtained, according to diffusion-weighted into
As the half-tone information of view data, highlight regions are split automatically, to determine cerebral infarction dead zone, Perfusion weighted imaging image are being obtained
Data, and obtain after the internal anatomy at the targeted position of Perfusion weighted imaging view data, according to the Perfusion weighted imaging figure
As data, perfusion parameters view data is obtained using assignment algorithm, the perfusion parameters view data and the internal anatomy is utilized
Ischemic area is determined, then carrying out image registration to diffusion-weighted imaging view data and Perfusion weighted imaging view data obtains
Registration result, and obtain cerebral infarction dead zone and ischemic area mismatch information according to registration result, can be with by aforesaid operations
The analysis of diffusion-weighted imaging view data is automatically performed, cerebral infarction dead zone is determined, and be automatically performed Perfusion weighted imaging
The analysis of image data of view data, determines ischemic area, due to being weighted to without doctor to diffusion-weighted imaging and perfusion
As view data is analyzed, and without after doctor draws analysis result, then manually determined goes out cerebral infarction dead zone and ischemic
Region, therefore shorten the duration for confirming to be consumed when cerebral infarction dead zone and ischemic area.
Second aspect, the embodiments of the invention provide a kind of data processing equipment, described device includes processor and deposited
Reservoir；The memory is used for store instruction, when the instruction is by the computing device, causes described device to realize above-mentioned number
According to the method any one of processing method.
A technical scheme in above-mentioned technical proposal has the advantages that：
In embodiments of the present invention, after the diffusion-weighted imaging view data of different b values is obtained, according to diffusion-weighted into
As the half-tone information of view data, highlight regions are split automatically, to determine cerebral infarction dead zone, Perfusion weighted imaging image are being obtained
Data, and obtain after the internal anatomy at the targeted position of Perfusion weighted imaging view data, according to the Perfusion weighted imaging figure
As data, perfusion parameters view data is obtained using assignment algorithm, the perfusion parameters view data and the internal anatomy is utilized
Ischemic area is determined, then carrying out image registration to diffusion-weighted imaging view data and Perfusion weighted imaging view data obtains
Registration result, and obtain cerebral infarction dead zone and ischemic area mismatch information based on registration result, can be with by aforesaid operations
The analysis of diffusion-weighted imaging view data is automatically performed, cerebral infarction dead zone is determined, and be automatically performed Perfusion weighted imaging
The analysis of image data of view data, determines ischemic area, due to without doctor is to diffusion-weighted imaging and irrigates weighted graph
As data are analyzed, and without after doctor draws analysis result, then manually determined goes out cerebral infarction dead zone and ischemic area,
Therefore the duration for confirming to be consumed when cerebral infarction dead zone and ischemic area is shortened.
【Brief description of the drawings】
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be attached to what is used required in embodiment
Figure is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for this area
For those of ordinary skill, without having to pay creative labor, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of schematic flow sheet of data processing method provided in an embodiment of the present invention；
Fig. 2 is a kind of schematic diagram of DWI view data provided in an embodiment of the present invention；
Fig. 3 is a kind of schematic diagram in cerebral infarction dead zone provided in an embodiment of the present invention；
Fig. 4 is a kind of schematic diagram of PWI view data provided in an embodiment of the present invention；
Fig. 5 is a kind of schematic diagram of MTT view data provided in an embodiment of the present invention；
Fig. 6 is a kind of schematic diagram of ischemic area provided in an embodiment of the present invention；
Fig. 7 is a kind of schematic diagram of T2 internal anatomys provided in an embodiment of the present invention；
Fig. 8 is that the embodiment of the present invention provides a kind of structural representation of data processing equipment；
Fig. 9 is the structural representation that the embodiment of the present invention provides another data processing equipment.
【Embodiment】
In order to be better understood from technical scheme, the embodiment of the present invention is retouched in detail below in conjunction with the accompanying drawings
State.
It will be appreciated that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Base
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of creative work is not made it is all its
Its embodiment, belongs to the scope of protection of the invention.
The term used in embodiments of the present invention is the purpose only merely for description specific embodiment, and is not intended to be limiting
The present invention." one kind ", " described " and "the" of singulative used in the embodiment of the present invention and appended claims
It is also intended to including most forms, unless context clearly shows that other implications.
In the prior art, when judging acute cerebral infarction, MRI imaging techniques are generally used, can be with by MRI imaging techniques
DWI view data and PWI view data are obtained, DWI view data can embody the focal area of acute cerebral infarction, i.e. cerebral infarction dead band
Domain, PWI view data can embody ischemic area when occurring acute cerebral infarction, and in the prior art, obtain DWI images
, it is necessary to which doctor carries out manual analysis respectively to DWI view data and PWI view data after data and PWI view data, and need
Doctor marks cerebral infarction dead zone and ischemic area respectively manually, the cerebral infarction dead zone then marked using doctor and ischemic region
Domain is further diagnosed.When determining cerebral infarction dead zone and ischemic area by the above method, the time of consumption is longer.
In order to reduce in the prior art, the problem of time for being consumed when cerebral infarction dead zone and ischemic area is longer is determined, this
Inventive embodiments provide following solution,
Embodiment one
The embodiments of the invention provide a kind of data processing method, as shown in figure 1, this method comprises the following steps：
101st, the diffusion-weighted imaging view data of different b values is obtained, the diffusion-weighted imaging view data has ash
Spend information.
Specifically, the DWI images of the DWI view data, wherein b values of different b values by MRI imaging techniques, can be obtained
Data refer to the diffusion sensitising gradient field parameters applied in DWI technologies.
102nd, split highlight regions automatically to determine cerebral infarction dead zone according to the half-tone information.
Specifically, because half-tone information can reflect the corresponding gray level of brain different zones, due to cerebral infarction dead zone
Corresponding gray level gray level corresponding from normal brain region is different, therefore cerebral infarction dead band can be determined according to half-tone information
Domain, in order that the cerebral infarction dead zone determined has obvious mark, it is possible to height on the cerebral infarction dead zone determined
Bright mark is marked.
103rd, Perfusion weighted imaging view data is obtained, and obtains the targeted portion of Perfusion weighted imaging view data
The internal anatomy of position.
Specifically, PWI view data can quantify the hemodynamic data of brain tissue capillary, the internal anatomy of acquisition
Can be T1 (T1 is the imaging of tissue longitudinal relaxation contrast) or T2 (T2 is the imaging of tissue transverse relaxation contrast), and should
The same position of internal anatomy same patient corresponding with PWI view data.
104th, according to the Perfusion weighted imaging view data, perfusion parameters view data, profit are obtained using assignment algorithm
Ischemic area is determined with the perfusion parameters view data and the internal anatomy.
Specifically, the corresponding perfusion parameters view data of different tissues is different, for example, the tissue at ischemic is corresponding
Perfusion parameters mean transit time is higher than the corresponding perfusion parameters view data of normal structure, therefore, it can utilize perfusion parameters
View data and internal anatomy determine ischemic area.
105th, image registration is carried out to the diffusion-weighted imaging view data and Perfusion weighted imaging view data to obtain
Registration result.
Specifically, the cerebral infarction dead zone determined and ischemic area are the different images at the same position for same patient
On region, can be by after diffusion-weighted imaging view data and Perfusion weighted imaging graph data are carried out into image registration
Ischemic area and cerebral infarction dead zone are embodied into a view data.
106th, the mismatch information of cerebral infarction dead zone and ischemic area is obtained based on the registration result.
Specifically, after mismatch information is obtained, brain can be determined in view data according to mismatch information
Infarcted region and ischemic area.
Alternatively, when splitting highlight regions automatically according to the half-tone information to determine cerebral infarction dead zone, it can pass through
Following methods are determined：According to the half-tone information, the intensity histogram of the diffusion-weighted imaging view data of the high b values is obtained
Figure；According to the grey level histogram and the diffusion-weighted imaging view data of the different b values, add in the disperse of the high b values
Automatic segmentation highlight regions in image data are weighed, and remove highlighted artifact, to determine cerebral infarction dead zone.
Specifically, grey level histogram is the function of gray level, grey level histogram being capable of different gray scales in presentation image data
Level (the different gray value of different gray level correspondences), and the frequency that every kind of gray level occurs in pictorial data can be reflected
Rate, for example, the abscissa of grey level histogram can represent different gray levels, ordinate can represent the frequency that the gray level occurs
Rate, is the most basic feature in view data, therefore is schemed according to the DWI of the high b values of the acquisition of the DWI view data of high b values
As the grey level histogram of data can reflect gray levels different in the DWI view data of high b values, and high b values DWI figures
In picture data, the number of the corresponding pixel of different grey-scale, wherein, the inspection moved due to less b values to water diffusion
Survey insensitive, and the detection that high b values are moved to water diffusion is sensitive, also, according to cerebral infarction characteristic, it is necessary to detect hydrone
The water diffusion motion embodied in diffusion motion, therefore the DWI view data of high b values is more obvious.
Further, due to DWI view data can in response organization moisture subactivity the free degree, cerebral infarction dead zone table
It is now cytotoxic edema, hydrone disperse is limited, therefore the hydrone freedom of movement in cerebral infarction dead zone and normal brain activity group
Hydrone freedom of movement in knitting is different, each self-produced when carrying out MRI imagings due to the difference of hydrone freedom of movement
Raw signal is also just different, therefore cerebral infarction dead zone and normal cerebral tissue are also just different in the data characteristics of DWI view data, because
This cerebral infarction dead zone and the normal cerebral tissue corresponding gray level in the gray distribution features of DWI view data are also just different, because
This can determine cerebral infarction dead zone according to the grey level histogram.
Further, because DWI view data has anisotropic artifact region, Susceptibility effect region and basis cranii etc.
The artifact region at position, and data characteristics and cerebral infarction dead zone of the artifact region in DWI view data are in DWI view data
Data characteristics it is similar, therefore above-mentioned artifact region and cerebral infarction dead zone are corresponding in grey level histogram in grey level histogram
Gray level is identical, because the DWI view data of different b values is as characterized above, it is possible to according to the DWI images of different b values
Data determine artifact region, therefore in order to obtain the higher cerebral infarction dead zone of accuracy, it is necessary to according to grey level histogram and not
Obtained with the DWI view data of b values.
Alternatively, in the diffusion-weighted imaging view data according to the grey level histogram and the different b values, described
When determining cerebral infarction dead zone in the diffusion-weighted imaging view data of high b values, it can be determined by following methods：To the gray scale
Histogram carries out Gauss curve fitting, obtains the Gaussian function of the grey level histogram；According to the Gaussian function, in the high b values
Diffusion-weighted imaging view data in determine doubtful cerebral infarction dead zone；According to the diffusion-weighted imaging image of the different b values
Data, remove the artifact region in the doubtful cerebral infarction dead zone, obtain the cerebral infarction dead zone.
Specifically, the region determined according to the Gaussian function is to include the doubtful cerebral infarction of cerebral infarction dead zone and artifact region
Dead zone.In order to obtain accurate cerebral infarction dead zone, it is necessary to eliminate the artifact region in doubtful cerebral infarction dead zone, due to according to not
DWI view data with b values can obtain the artifact region of different artifact formation, therefore it is determined that doubtful cerebral infarction dead zone
Afterwards, it is possible to use the DWI view data of different b values, each artifact region is determined, and according to the artifact region, in doubtful brain
Removed it in infarcted region, and only retain cerebral infarction dead zone, for example, using the DWI view data of different b values, obtaining ADC
(Apparent diffusion coefficient, apparent diffusion coefficient) view data, cerebral infarction dead zone is in ADC view data
Grey level histogram in corresponding gray value be less than artifact region corresponding gray scale in the grey level histogram of ADC view data
Value, therefore can be removed the artifact region region in doubtful cerebral infarction dead zone according to obtained ADC view data, and then only
Retain cerebral infarction dead zone.
For example, as shown in Fig. 2 highlight regions are doubtful cerebral infarction dead zone, the doubtful cerebral infarction dead zone includes pseudo- shadow zone
Domain and cerebral infarction dead zone, then using the DWI view data of different b values, artifact region are removed, as shown in figure 3, obtaining doubtful
Cerebral infarction dead zone in cerebral infarction dead zone.
, can be to the DWI picture numbers of high b values it is determined that behind doubtful cerebral infarction dead zone in a feasible embodiment
It is marked on corresponding region, doubtful cerebral infarction dead zone is formed highlight regions, then after artifact region is determined,
The corresponding highlight regions in artifact region will be being removed in the highlight regions, so that remaining highlight regions are cerebral infarction dead zone.
Alternatively, according to the Gaussian function, determined in the diffusion-weighted imaging view data of the high b values doubtful
During cerebral infarction dead zone, it can be determined by following methods：According to the Gaussian function, obtain the Gaussian function average value and
Standard deviation；According to the average value and the standard deviation, threshold value；Diffusion-weighted imaging picture number based on the high b values
The gray value of each pixel in, the gray value of each pixel is compared with the threshold value, if the threshold value is small
In or equal to a pixel gray value, determine the pixel be target pixel points；The area that each target pixel points are constituted
Domain is used as the doubtful cerebral infarction dead zone.
Specifically, due to the corresponding pixel in cerebral infarction dead zone gray value can higher than the threshold value determined, and by
There is similar feature in artifact and cerebral infarction dead zone, therefore the gray value of the corresponding pixel of artifact can also be higher than high threshold,
Therefore the set of target pixel points can be determined by the above method, the set can form at least one region, and can
To regard the region as doubtful cerebral infarction dead zone.
In a feasible embodiment, it is possible to use equation below determines the threshold value：T=μ+3* σ, wherein, μ is should
Average value, σ is the standard deviation, and T is the threshold value.
Alternatively, in order that deagnostic structure is more accurate, after doubtful cerebral infarction dead zone is obtained, it is possible to use morphology is calculated
Method, is handled doubtful cerebral infarction dead zone, to remove the region affected by noise more than designated value in doubtful cerebral infarction dead zone.
Specifically, during the DWI view data of high b values is obtained, can be by noise jamming, by noise jamming
The feature of the feature view data corresponding with cerebral infarction dead zone of the corresponding view data in region is similar, that is, the doubtful brain determined
The region of noise jamming is further comprises in infarcted region, the region of noise jamming shows as scattered point in DWI view data, because
This is in order that the cerebral infarction region determined is more accurate, it is possible to use Morphology Algorithm removes the scattered point.
Alternatively, when splitting highlight regions automatically according to the half-tone information to determine cerebral infarction dead zone, it can also lead to
Following methods are crossed to determine：According to the half-tone information, using gray value clustering procedure, in the diffusion-weighted imaging figure of the high b values
As in data automatic segmentation highlight regions to determine cerebral infarction dead zone.
In embodiments of the present invention, due to the analysis of DWI view data can be automatically performed by aforesaid operations, with
And cerebral infarction dead zone is determined, therefore DWI view data is analyzed without doctor, and draw analysis result without doctor
Afterwards, then manually determined goes out cerebral infarction dead zone, so shortening the duration for confirming to be consumed during cerebral infarction dead zone, also, eliminate
Because diagnosis level is relatively low, and the situation of mistaken diagnosis is caused, and then cause diagnostic criteria to obtain unification.
Alternatively, according to the Perfusion weighted imaging view data, perfusion parameters picture number is obtained using assignment algorithm
According to when determining ischemic area using the perfusion parameters view data and the internal anatomy, being determined by following methods：Root
According to the Perfusion weighted imaging view data, using deconvolution algorithm or non-deconvolution algorithm, perfusion parameters are obtained；According to described
Perfusion parameters and the internal anatomy, determine ischemic area.
Specifically, the perfusion parameters of different tissues are different, the corresponding perfusion parameters of the tissue that such as ischemic goes out are averaged
Passage time is higher than the corresponding perfusion parameters of normal structure, therefore can determine ischemic area using perfusion parameters.
Alternatively, perfusion parameters include：Cerebral blood volume view data, cerebral blood flow (CBF) view data and mean transit time figure
As data.
Specifically, when perfusion parameters are mean transit time view data, because brain tissue includes brain parenchym region
With non-brain parenchym region, in brain parenchym region, brain tissue at ischemic is (Mean Transition Time, average logical in MTT
Spend the time) Low perfusion data (i.e. mean transit time is longer) are shown as in view data, and in non-brain parenchym region, such as brain
The non-brain regions such as room, scalp, eyes are influenceed by imaging artefacts etc., and Low perfusion ginseng is also shown as in MTT view data
Number, and above-mentioned non-brain tissue and brain tissue can be made a distinction by internal anatomy, you can so that any portion determined using internal anatomy
Subregion is brain parenchym region, and which subregion is non-brain parenchym region, can be determined accurately then in conjunction with MTT view data
Ischemic area, so as to eliminate influence of the non-brain parenchym region to brain parenchym region in MTT view data, determine that brain is real
At ischemic in matter region.
Alternatively, according to the perfusion parameters and the internal anatomy, when determining ischemic area, following methods can be passed through
It is determined that：Dividing processing is carried out to the internal anatomy；According to dividing processing result, the brain parenchym region in the internal anatomy is determined；
Brain parenchym region registration in the internal anatomy is mapped to the mean transit time view data；Tied according to registration mapping
Really, the brain parenchym region in the mean transit time view data is determined；According in the mean transit time view data
Brain parenchym region gray-scale watermark, the gray scale for obtaining brain parenchym region in the mean transit time view data is straight
Fang Tu；The grey level histogram in the brain parenchym region in the mean transit time view data, it is described averagely by when
Between determine ischemic area in view data.
Specifically, after dividing processing is carried out to internal anatomy, it may be determined that the brain parenchym region gone out in internal anatomy, then will
Brain parenchym region registration is mapped in MTT view data, due to the same portion that internal anatomy and MTT view data are same patient
Position, thus after registration mapping, it may be determined that the brain parenchym region gone out in MTT view data, simultaneously because at ischemic
It is Low perfusion that brain regions, which are cashed, therefore the gray-scale watermark in brain parenchym region that can be in MTT view data is obtained
The grey level histogram in the brain parenchym region in MTT view data is taken, due to the corresponding ash of different pixels point in the grey level histogram
It is different to spend level (pixel value), and due to the picture of the corresponding pixel in the grey level histogram of the brain regions at ischemic
Plain value is higher than the pixel value for brain regions corresponding pixel in the grey level histogram that non-ischemic goes out, therefore can basis
The grey level histogram, ischemic area is determined in MTT view data.
Alternatively, according to MTT view data and internal anatomy, when determining ischemic area in MTT view data, Ke Yitong
Cross following methods and determine ischemic area：The grey level histogram in the brain parenchym region in MTT view data, obtains MTT images
The MTT average values of data midbrain parenchyma section；According to institute's MTT average values, threshold value is obtained；Based on brain parenchym in MTT view data
Each pixel gray value in region, the gray value of each pixel and threshold value are compared, if threshold value is less than a pixel
The gray value of point, it is target pixel points to determine the pixel；The region that each target pixel points are constituted is used as ischemic area.
Specifically, due to the corresponding pixel in the grey level histogram of the brain regions at ischemic pixel value (
Gray level in grey level histogram, the different gray value of different gray level correspondences) exist higher than the brain regions at non-ischemic
The pixel value of corresponding pixel in the grey level histogram, thus obtain brain parenchym region MTT average values be less than ischemic at
Brain regions corresponding pixel in the grey level histogram gray value, and the brain regions gone out more than non-ischemic exist
The pixel value of corresponding pixel in the grey level histogram, therefore can be determined according to MTT average values in brain regions
The region that ischemic area, i.e. gray value are more than the MTT average values is ischemic area, in order to reduce amount of calculation, and determines to fall vacant
The more serious region of blood, can determine a threshold value, the threshold value can be 1.5 times of MTT average values according to the MTT average values,
And be compared the gray value of each pixel with the threshold value, when the gray value of a pixel is more than the threshold value, by the picture
Vegetarian refreshments is defined as target pixel points, by the gray value of each corresponding pixel of MTT view data midbrain parenchyma section with should
After threshold value is compared, it may be determined that go out multiple target pixel points, and multiple target pixel points can in MTT view data shape
Into at least one region, at least one region can be used as ischemic area.
For example, as shown in figure 4, a kind of PWI view data is provided for the embodiment of the present invention, as shown in figure 5, real for the present invention
A kind of MTT view data of example offer is provided, doubtful ischemic area can be determined according to the MTT view data, the doubtful ischemic
Region includes the corresponding regions such as the ischemic area and non-brain parenchym region midventricle, scalp, eyes in brain parenchym region, such as schemes
It is a kind of ischemic area provided in an embodiment of the present invention shown in 6, using internal anatomy, determines MTT view data brain parenchyms area
Domain, by the brain parenchym region and the registering mapping of doubtful ischemic area progress, by non-brain parenchym region midventricle, scalp, eyes etc.
Corresponding region is eliminated, and only retains the ischemic area in brain parenchym region.
Alternatively, in order that the brain parenchym region in obtained MTT view data spatially has preferable continuity,
Make the ischemic area of determination more accurate, MTT can be schemed before the gray value of each pixel and threshold value are compared
As the brain parenchym region in data is smoothed.
In embodiments of the present invention, due to the analysis of MTT view data can be automatically performed by aforesaid operations, and really
Ischemic area is made, due to being analyzed without doctor MTT view data, and without after doctor draws analysis result,
Manually determined goes out ischemic area again, therefore shortens the duration for confirming to be consumed during ischemic area, meanwhile, eliminate due to doctor
Diagnostic level is relatively low, and causes the situation of mistaken diagnosis, and then causes diagnostic criteria to obtain unification.
Alternatively, cerebral infarction dead zone is determined in the DWI view data of high b values using the above method and in MTT picture numbers
After middle determination ischemic area, carry out image registration in the imaging of diffusion-weighted imaging image and Perfusion weighted imaging view data and obtain
During to registration result, it can be obtained by following methods：DWI view data and MTT view data to high b values carry out image and matched somebody with somebody
It is accurate.
Specifically, the DWI view data and MTT view data of high b values are the differences at the same position for same patient
View data, the DWI view data of high b values and MTT view data are carried out after image registration, can be by ischemic area and cerebral infarction
Embody into a view data in dead zone.
Alternatively, when obtaining mismatch information based on registration result, it can be obtained by following methods：Based on image
The DWI view data and MTT view data of the high b values obtained after registration, obtain the mismatch of cerebral infarction dead zone and ischemic area
Property information.
Specifically, can DWI view data and MTT view data based on the high b values obtained after image registration, analysis brain
The mismatch of infarcted region and ischemic area, and according to the analysis result of mismatch, mismatch information is obtained, according to not
Matching information, can determine cerebral infarction dead zone and ischemic area etc. in view data, for example, as shown in fig. 7, Fig. 7 is
Carry out image registration to Fig. 3 and Fig. 6, what analysis chart 3 and Fig. 6 mismatch was obtained, during bottom figure is T2 internal anatomys, the figure
Highlight regions include cerebral infarction dead zone and ischemic area etc., wherein, cerebral infarction dead zone and ischemic area can use different colours
Highlight regions are identified.
In embodiments of the present invention, image registration is carried out in DWI view data and MTT view data to high b values, obtained
In when mismatching information, it is necessary to cerebral infarction dead zone and MTT view data in determining the DWI view data of high b values in advance
Ischemic area, due to it is determined that when cerebral infarction dead zone and ischemic area, point of DWI view data can be completed by aforesaid operations
Analysis and the analysis of MTT view data, and determine cerebral infarction dead zone and ischemic area, due to without doctor to DWI picture numbers
Analyzed, and drawn without doctor after analysis result according to MTT view data, then manually determined goes out cerebral infarction dead zone and lacked
Blood region, therefore the duration for confirming to be consumed when cerebral infarction dead zone and ischemic area is shortened, also, eliminate because doctor examines
Cut off the water supply flat relatively low, and cause the situation of mistaken diagnosis, and then cause diagnostic criteria to obtain unification.
Embodiment two
The embodiments of the invention provide a kind of data processing equipment, as shown in figure 8, the device includes：
First acquisition unit 801, the diffusion-weighted imaging view data for obtaining different b values, the diffusion-weighted into
As view data has half-tone information.
Cutting unit 802, for splitting highlight regions automatically according to the half-tone information to determine cerebral infarction dead zone.
Second acquisition unit 803, for obtaining Perfusion weighted imaging view data, and obtains the Perfusion weighted imaging
The internal anatomy at the targeted position of view data.
Determining unit 804, for according to the Perfusion weighted imaging view data, perfusion parameters to be obtained using assignment algorithm
View data, ischemic area is determined using the perfusion parameters view data and the internal anatomy.
Registration unit 805, for the diffusion-weighted imaging view data and the progress of Perfusion weighted imaging view data
Image registration obtains registration result.
3rd acquiring unit 806, for obtaining cerebral infarction dead zone and ischemic area mismatch based on the registration result
Information.
Because each unit in the present embodiment is able to carry out the method shown in embodiment one, what the present embodiment was not described in detail
Part, refers to the related description to embodiment one.
In embodiments of the present invention, after the diffusion-weighted imaging view data of different b values is obtained, according to diffusion-weighted into
As the half-tone information of view data, highlight regions are split automatically, to determine cerebral infarction dead zone, Perfusion weighted imaging image are being obtained
Data, and obtain after the internal anatomy at the targeted position of Perfusion weighted imaging view data, according to the Perfusion weighted imaging figure
As data, perfusion parameters view data is obtained using assignment algorithm, the perfusion parameters view data and the internal anatomy is utilized
Ischemic area is determined, then carrying out image registration to diffusion-weighted imaging view data and Perfusion weighted imaging view data obtains
Registration result, and obtain cerebral infarction dead zone and ischemic area mismatch information based on registration result, can be with by aforesaid operations
The analysis of diffusion-weighted imaging view data is automatically performed, cerebral infarction dead zone is determined, and be automatically performed Perfusion weighted imaging
The analysis of image data of view data, determines ischemic area, due to without doctor is to diffusion-weighted imaging and irrigates weighted graph
As data are analyzed, and without after doctor draws analysis result, then manually determined goes out cerebral infarction dead zone and ischemic area,
Therefore the duration for confirming to be consumed when cerebral infarction dead zone and ischemic area is shortened.
Embodiment three
The embodiment of the present invention additionally provides a kind of data processing equipment, as shown in figure 9, the device includes：Emitter 91, connects
Receipts machine 92, memory 93, and the processor 94 coupled with the memory 93, the emitter 91, receiver 92, memory
93 and processor 94 communicated by bus system；The memory 93 stores software program, and the processor 94 can be called
The program is to control emitter 91 and receiver 92.The processor 94 by run the software program for：
The diffusion-weighted imaging view data of different b values is obtained, the diffusion-weighted imaging view data has gray scale letter
Breath；Split highlight regions automatically to determine cerebral infarction dead zone according to the half-tone information；Perfusion weighted imaging view data is obtained,
And obtain the internal anatomy at the targeted position of Perfusion weighted imaging view data；According to the Perfusion weighted imaging picture number
According to obtaining perfusion parameters view data using assignment algorithm, utilize the perfusion parameters view data and the internal anatomy to determine
Ischemic area；Image registration is carried out to the diffusion-weighted imaging view data and Perfusion weighted imaging view data and obtains registration
As a result；Cerebral infarction dead zone and ischemic area mismatch information are obtained based on the registration result.
A technical scheme in above-mentioned technical proposal has the advantages that：
In embodiments of the present invention, after the diffusion-weighted imaging view data of different b values is obtained, according to diffusion-weighted into
As the half-tone information of view data, highlight regions are split automatically, to determine cerebral infarction dead zone, Perfusion weighted imaging image are being obtained
Data, and obtain after the internal anatomy at the targeted position of Perfusion weighted imaging view data, according to the Perfusion weighted imaging figure
As data, perfusion parameters view data is obtained using assignment algorithm, the perfusion parameters view data and the internal anatomy is utilized
Ischemic area is determined, then carrying out image registration to diffusion-weighted imaging view data and Perfusion weighted imaging view data obtains
Registration result, and obtain cerebral infarction dead zone and ischemic area mismatch information based on registration result, can be with by aforesaid operations
The analysis of diffusion-weighted imaging view data is automatically performed, cerebral infarction dead zone is determined, and be automatically performed Perfusion weighted imaging
The analysis of view data, determines ischemic area, due to entering without doctor to diffusion-weighted imaging and perfusion weighted image data
Row analysis, and need not be after doctor draws analysis result, then manually determined goes out cerebral infarction dead zone and ischemic area, therefore shorten
Confirm the duration consumed when cerebral infarction dead zone and ischemic area.
It is apparent to those skilled in the art that, for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, may be referred to the process in preceding method embodiment, will not be repeated here.
In several embodiments provided by the present invention, it should be understood that disclosed system, apparatus and method can be with
Realize by another way.For example, device embodiment described above is only schematical, for example, the unit
Divide, only a kind of division of logic function there can be other dividing mode when actually realizing, for example, multiple units or group
Part can combine or be desirably integrated into another system, or some features can be ignored, or not perform.It is another, it is shown
Or the coupling each other discussed or direct-coupling or communication connection can be by some interfaces, device or unit it is indirect
Coupling is communicated to connect, and can be electrical, machinery or other forms.
The unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
The above-mentioned integrated unit realized in the form of SFU software functional unit, can be stored in an embodied on computer readable and deposit
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are to cause a computer
Device (can be personal computer, server, or network equipment etc.) or processor (Processor) perform the present invention each
The part steps of embodiment methods described.And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD etc. it is various
Can be with the medium of store program codes.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
God is with principle, and any modification, equivalent substitution and improvements done etc. should be included within the scope of protection of the invention.
Claims (12)
1. a kind of data processing method, it is characterised in that methods described includes：
The diffusion-weighted imaging view data of different b values is obtained, the diffusion-weighted imaging view data has half-tone information；
Split highlight regions automatically to determine cerebral infarction dead zone according to the half-tone information；
Perfusion weighted imaging view data is obtained, and obtains the dissection at the targeted position of Perfusion weighted imaging view data
Figure；
According to the Perfusion weighted imaging view data, perfusion parameters view data is obtained using assignment algorithm, is filled using described
Note parametric image data and the internal anatomy determine ischemic area；
Image registration is carried out to the diffusion-weighted imaging view data and Perfusion weighted imaging view data and obtains registration result；
The mismatch information of cerebral infarction dead zone and ischemic area is obtained based on the registration result.
2. the method as described in claim 1, it is characterised in that it is described according to the half-tone information split automatically highlight regions with
Cerebral infarction dead zone is determined, including：
According to the half-tone information, the grey level histogram of the diffusion-weighted imaging view data of the high b values is obtained；
According to the grey level histogram and the diffusion-weighted imaging view data of the different b values, add in the disperse of the high b values
Automatic segmentation highlight regions in image data are weighed, and remove highlighted artifact, to determine cerebral infarction dead zone.
3. method as claimed in claim 2, it is characterised in that described according to the grey level histogram and the different b values
Diffusion-weighted imaging view data, determines cerebral infarction dead zone in the diffusion-weighted imaging view data of the high b values, including：
Gauss curve fitting is carried out to the grey level histogram, the Gaussian function of the grey level histogram is obtained；
According to the Gaussian function, doubtful cerebral infarction dead zone is determined in the diffusion-weighted imaging view data of the high b values；
According to the diffusion-weighted imaging view data of the different b values, the artifact region in the doubtful cerebral infarction dead zone is removed,
Obtain the cerebral infarction dead zone.
4. method as claimed in claim 3, it is characterised in that described according to the Gaussian function, in the disperse of the high b values
Doubtful cerebral infarction dead zone is determined in weighted imaging view data, including：
According to the Gaussian function, the average value and standard deviation of the Gaussian function are obtained；
According to the average value and the standard deviation, threshold value；
The gray value of each pixel in diffusion-weighted imaging view data based on the high b values, by each pixel
Gray value is compared with the threshold value, if the threshold value is less than or equal to the gray value of a pixel, determines the pixel
Point is target pixel points；
The region that each target pixel points are constituted is used as the doubtful cerebral infarction dead zone.
5. method as claimed in claim 3, it is characterised in that in the diffusion-weighted imaging picture number according to the different b values
According to, the artifact region in the doubtful cerebral infarction dead zone is removed, before obtaining the cerebral infarction dead zone, in addition to：
Using Morphology Algorithm, doubtful cerebral infarction dead zone is handled, to remove in the doubtful cerebral infarction dead zone by noise
Region of the influence more than designated value.
6. the method as described in claim 1, it is characterised in that it is described according to the half-tone information split automatically highlight regions with
Cerebral infarction dead zone is determined, including：
It is automatic in the diffusion-weighted imaging view data of the high b values using gray value clustering procedure according to the half-tone information
Split highlight regions to determine cerebral infarction dead zone.
7. the method as described in claim 1, it is characterised in that described according to the Perfusion weighted imaging view data, is utilized
Assignment algorithm obtains perfusion parameters view data, and ischemic region is determined using the perfusion parameters view data and the internal anatomy
Domain, including：
According to the Perfusion weighted imaging view data, using deconvolution algorithm or non-deconvolution algorithm, perfusion parameters are obtained；
According to the perfusion parameters and the internal anatomy, ischemic area is determined.
8. method as claimed in claim 7, it is characterised in that the perfusion parameters include：Mean transit time view data.
9. method as claimed in claim 8, it is characterised in that described according to the perfusion parameters and the internal anatomy, it is determined that
Ischemic area, including：
Dividing processing is carried out to the internal anatomy；
According to dividing processing result, the brain parenchym region in the internal anatomy is determined；
Brain parenchym region registration in the internal anatomy is mapped to the mean transit time view data；
According to registering mapping result, the brain parenchym region in the mean transit time view data is determined；
The gray-scale watermark in the brain parenchym region in the mean transit time view data, acquisition is described averagely to be passed through
The grey level histogram in the brain parenchym region in temporal image data；
The grey level histogram in the brain parenchym region in the mean transit time view data, in the mean transit time
Ischemic area is determined in view data.
10. method as claimed in claim 9, it is characterised in that described according in the mean transit time view data
The grey level histogram in brain parenchym region, ischemic area is determined in the mean transit time view data, including：
The grey level histogram in the brain parenchym region in the mean transit time view data, obtain it is described averagely by when
Between view data midbrain parenchyma section mean transit time average value；
According to the mean transit time average value, threshold value is obtained；
Based on each pixel gray value in the mean transit time view data midbrain parenchyma section, by each pixel
Gray value is compared with the threshold value, if the threshold value is less than the gray value of a pixel, and it is target to determine the pixel
Pixel；
The region that each target pixel points are constituted is used as ischemic area.
11. method as claimed in claim 10, it is characterised in that in the gray value by each pixel and the threshold value
Before being compared, in addition to：
Brain parenchym region in the mean transit time view data is smoothed.
12. a kind of data processing equipment, it is characterised in that described device includes processor and memory；The memory is used
In store instruction, when the instruction is by the computing device, described device is caused to be realized such as any one of claim 1-11 institutes
The method stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710471722.9A CN107301645A (en) | 2017-06-20 | 2017-06-20 | A kind of data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710471722.9A CN107301645A (en) | 2017-06-20 | 2017-06-20 | A kind of data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107301645A true CN107301645A (en) | 2017-10-27 |
Family
ID=60136371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710471722.9A Pending CN107301645A (en) | 2017-06-20 | 2017-06-20 | A kind of data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107301645A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833229A (en) * | 2017-11-02 | 2018-03-23 | 上海联影医疗科技有限公司 | Information processing method, apparatus and system |
| CN108665465A (en) * | 2018-05-14 | 2018-10-16 | 沈阳东软医疗系统有限公司 | Divide method, apparatus, storage medium and the equipment of cerebral ischemic penumbra |
| CN109410216A (en) * | 2018-09-14 | 2019-03-01 | 北京市商汤科技开发有限公司 | A kind of cerebral arterial thrombosis image region segmentation method and device |
| CN109461160A (en) * | 2018-10-12 | 2019-03-12 | 北京深睿博联科技有限责任公司 | The cerebral injury region segmentation method and device of the nuclear magnetic resonance image acquired in different scanning equipment |
| CN109658401A (en) * | 2018-12-14 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109671069A (en) * | 2018-12-14 | 2019-04-23 | 强联智创（北京）科技有限公司 | A kind of measurement method and system of the core Infarction volume based on head CT images |
| CN109903293A (en) * | 2019-01-24 | 2019-06-18 | 汕头大学 | A method of tissue segmentation is carried out using the ultrasonic mapping graph of blood perfusion parameter |
| CN110276762A (en) * | 2018-03-15 | 2019-09-24 | 北京大学 | A kind of full-automatic bearing calibration of respiratory movement of the diffusion-weighted Abdominal MRI imaging of more b values |
| CN110298832A (en) * | 2019-06-25 | 2019-10-01 | 沈阳东软智能医疗科技研究院有限公司 | Infarct method for detecting area, device, storage medium and equipment |
| CN110415228A (en) * | 2019-07-24 | 2019-11-05 | 上海联影医疗科技有限公司 | Nerve fibre method for tracing, magnetic resonance system and storage medium |
| CN111407277A (en) * | 2020-03-06 | 2020-07-14 | 中国科学院武汉物理与数学研究所 | Magnetic resonance perfusion-diffusion image registration method for acute ischemic stroke |
| CN113222893A (en) * | 2021-04-06 | 2021-08-06 | 数坤（北京）网络科技有限公司 | Abnormal area determination method and device |
| US11348247B2 (en) | 2017-11-02 | 2022-05-31 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for generating semantic information for scanning image |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101596109A (en) * | 2009-06-12 | 2009-12-09 | 深圳先进技术研究院 | Obtain method, system and the thrombolytic indication generation system and the method for brain characteristic parameter |
| CN103339653A (en) * | 2010-12-17 | 2013-10-02 | 奥胡斯大学 | Method for delineation of tissue lesions |
| CN104103083A (en) * | 2013-04-03 | 2014-10-15 | 株式会社东芝 | Image processing device, method and medical imaging device |
| KR20150030974A (en) * | 2013-09-13 | 2015-03-23 | 재단법인 아산사회복지재단 | Method for estimating onset time of infarct region based on brain image |
| EP2988270A1 (en) * | 2014-08-22 | 2016-02-24 | Siemens Aktiengesellschaft | Method for volume evaluation of penumbra mismatch in acute ischemic stroke and system therefor |
-
2017
- 2017-06-20 CN CN201710471722.9A patent/CN107301645A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101596109A (en) * | 2009-06-12 | 2009-12-09 | 深圳先进技术研究院 | Obtain method, system and the thrombolytic indication generation system and the method for brain characteristic parameter |
| CN103339653A (en) * | 2010-12-17 | 2013-10-02 | 奥胡斯大学 | Method for delineation of tissue lesions |
| CN104103083A (en) * | 2013-04-03 | 2014-10-15 | 株式会社东芝 | Image processing device, method and medical imaging device |
| KR20150030974A (en) * | 2013-09-13 | 2015-03-23 | 재단법인 아산사회복지재단 | Method for estimating onset time of infarct region based on brain image |
| EP2988270A1 (en) * | 2014-08-22 | 2016-02-24 | Siemens Aktiengesellschaft | Method for volume evaluation of penumbra mismatch in acute ischemic stroke and system therefor |
Non-Patent Citations (1)
| Title |
|---|
| 魏经国: "《影像诊断病理学》", 31 October 2007 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107833229A (en) * | 2017-11-02 | 2018-03-23 | 上海联影医疗科技有限公司 | Information processing method, apparatus and system |
| US11348247B2 (en) | 2017-11-02 | 2022-05-31 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for generating semantic information for scanning image |
| CN110276762A (en) * | 2018-03-15 | 2019-09-24 | 北京大学 | A kind of full-automatic bearing calibration of respiratory movement of the diffusion-weighted Abdominal MRI imaging of more b values |
| CN108665465A (en) * | 2018-05-14 | 2018-10-16 | 沈阳东软医疗系统有限公司 | Divide method, apparatus, storage medium and the equipment of cerebral ischemic penumbra |
| CN109410216A (en) * | 2018-09-14 | 2019-03-01 | 北京市商汤科技开发有限公司 | A kind of cerebral arterial thrombosis image region segmentation method and device |
| CN109410216B (en) * | 2018-09-14 | 2020-12-29 | 北京市商汤科技开发有限公司 | Ischemic stroke image region segmentation method and device |
| CN109461160B (en) * | 2018-10-12 | 2020-10-13 | 北京深睿博联科技有限责任公司 | Method and device for segmenting brain injury area in multi-equipment cerebral infarction MRI image |
| CN109461160A (en) * | 2018-10-12 | 2019-03-12 | 北京深睿博联科技有限责任公司 | The cerebral injury region segmentation method and device of the nuclear magnetic resonance image acquired in different scanning equipment |
| CN109658401A (en) * | 2018-12-14 | 2019-04-19 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109671069B (en) * | 2018-12-14 | 2021-02-19 | 强联智创（北京）科技有限公司 | Method and system for measuring core infarction volume based on skull CT image |
| CN109658401B (en) * | 2018-12-14 | 2022-04-29 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN109671069A (en) * | 2018-12-14 | 2019-04-23 | 强联智创（北京）科技有限公司 | A kind of measurement method and system of the core Infarction volume based on head CT images |
| CN109903293A (en) * | 2019-01-24 | 2019-06-18 | 汕头大学 | A method of tissue segmentation is carried out using the ultrasonic mapping graph of blood perfusion parameter |
| CN110298832A (en) * | 2019-06-25 | 2019-10-01 | 沈阳东软智能医疗科技研究院有限公司 | Infarct method for detecting area, device, storage medium and equipment |
| CN110298832B (en) * | 2019-06-25 | 2023-05-02 | 沈阳东软智能医疗科技研究院有限公司 | Infarct range area detection method, device, storage medium and equipment |
| CN110415228A (en) * | 2019-07-24 | 2019-11-05 | 上海联影医疗科技有限公司 | Nerve fibre method for tracing, magnetic resonance system and storage medium |
| CN111407277A (en) * | 2020-03-06 | 2020-07-14 | 中国科学院武汉物理与数学研究所 | Magnetic resonance perfusion-diffusion image registration method for acute ischemic stroke |
| CN111407277B (en) * | 2020-03-06 | 2022-04-26 | 中国科学院武汉物理与数学研究所 | Magnetic resonance perfusion-diffusion image registration method for acute ischemic stroke |
| CN113222893A (en) * | 2021-04-06 | 2021-08-06 | 数坤（北京）网络科技有限公司 | Abnormal area determination method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107301645A (en) | A kind of data processing method and device | |
| Archer et al. | A template and probabilistic atlas of the human sensorimotor tracts using diffusion MRI | |
| Hsu et al. | Quantitative myocardial infarction on delayed enhancement MRI. Part I: Animal validation of an automated feature analysis and combined thresholding infarct sizing algorithm | |
| Lahaye et al. | Functional connectivity: studying nonlinear, delayed interactions between BOLD signals | |
| Bastin et al. | Quantifying the effects of normal ageing on white matter structure using unsupervised tract shape modelling | |
| US7995825B2 (en) | Histogram segmentation of FLAIR images | |
| Deshpande et al. | Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature | |
| JP6506700B2 (en) | Method and system for cell level FISH dot counting | |
| US11302008B2 (en) | Systems and methods for automated detection and segmentation of vertebral centrum(s) in 3D images | |
| DE112015005479T5 (en) | Method and system for improved classification of inventory materials | |
| Liang et al. | Voxel-wise functional connectomics using arterial spin labeling functional magnetic resonance imaging: the role of denoising | |
| CN108272434A (en) | The method and device that eye fundus image is handled | |
| US8224048B2 (en) | Computer implemented method for correction of magnetic resonance images | |
| TWI788629B (en) | Image processing method, device and system, electronic apparatus, and computer readable storage medium | |
| JP2012527923A (en) | Method for displaying lesions with changes in the volume of the body, especially the amount of tumor growth | |
| CN110236544B (en) | Stroke perfusion imaging lesion area detection system and method based on correlation coefficient | |
| CN102419864A (en) | Method and device for extracting skeletons of brain CT (computerized tomography) image | |
| Geißler et al. | Comparing the microvascular specificity of the 3-and 7-T BOLD response using ICA and susceptibility-weighted imaging | |
| Gulban et al. | Mesoscopic in vivo human T2* dataset acquired using quantitative MRI at 7 Tesla | |
| Cho et al. | Cortical layer-specific differences in stimulus selectivity revealed with high-field fMRI and single-vessel resolution optical imaging of the primary visual cortex | |
| JP2015514520A (en) | Identification of blood vessel region | |
| Hennemuth et al. | Mixture-model-based segmentation of myocardial delayed enhancement MRI | |
| US20130144154A1 (en) | Method of visualization of tissue perfusion by means of assessing BOLD signal fluctuations, an apparatus therefor and the use thereof | |
| Provencher et al. | Structural impacts on the timing and amplitude of the negative BOLD response | |
| WO2018210233A1 (en) | Intravoxel incoherent motion mri 3-dimensional quantitative detection of tissue abnormality with improved data processing |
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 Jiading District Industrial Zone Jiading Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai city Jiading District Industrial Zone Jiading 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: 20171027 |
|
| RJ01 | Rejection of invention patent application after publication |