CN110298832A - Infarct method for detecting area, device, storage medium and equipment - Google Patents
Infarct method for detecting area, device, storage medium and equipment Download PDFInfo
- Publication number
- CN110298832A CN110298832A CN201910553962.2A CN201910553962A CN110298832A CN 110298832 A CN110298832 A CN 110298832A CN 201910553962 A CN201910553962 A CN 201910553962A CN 110298832 A CN110298832 A CN 110298832A
- Authority
- CN
- China
- Prior art keywords
- infarct
- region
- weighted
- diffusion
- candidate
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30096—Tumor; Lesion
Abstract
This application discloses a kind of infarct method for detecting area, device, storage medium and equipment, which includes: the brain parenchym tissue part obtained in magnetic resonance image；According to the surface diffusion coefficient threshold value of setting, infarct candidate region is obtained from the brain parenchym tissue part；It obtains in the brain parenchym tissue part, the infarct that the ratio of Diffusion-Weighted MR Imaging signal and surface diffusion coefficient is higher than setting value confirms region；It determines in the infarct candidate region, the candidate connected region with infarct confirmation regional connectivity；According to the Diffusion-Weighted MR Imaging signal value in the candidate connected region, target infarct region is determined.The application is able to carry out acute and Super acute infarct detection, and calculating speed is fast and can distinguish the tumour for being similarly high DWI value and low ADC value and infarct region.
Description
Technical field
This specification is related to technical field of medical equipment more particularly to a kind of infarct method for detecting area, device, storage
Medium and equipment.
Background technique
In magnetic resonance imaging, Diffusion-Weighted MR Imaging (diffusion-weighted imaging, DWI) and diffusion into the surface
Coefficient (apparent diffusion coefficients, ADC) imaging is the imaging for being able to reflect water diffusion particularity
Method.In Acute Cerebral Infarction, due to obstruction of artery, blood diffusion motion weakens, and obvious high RST is presented in DWI, and ADC figure is in
Now obvious low signal；And with disease, DWI high signal intensity is gradually reduced, and ADC schemes obvious low signal intensity and gradually returns
It rises.As it can be seen that DWI and ADC has very high application value in diagnosis acute cerebral infarction.
In the related technology, usually high DWI is recycled to be modified erroneous judgement by ADC threshold test infarct.But due to
The characteristics of human brain, DWI and ADC and non-uniform Distribution, this method detected using hard -threshold, it is difficult to guarantee testing result
Accuracy；Also, this detection method cannot exclude certain non-ischemics but the lesion with high DWI and low ADC, such as swollen
Tumor.
Summary of the invention
To overcome the problems in correlation technique, present description provides a kind of infarct method for detecting area, device,
Storage medium and equipment.
Specifically, the application is achieved by the following technical solution:
In a first aspect, providing a kind of infarct method for detecting area, which comprises
Obtain the brain parenchym tissue part in magnetic resonance image；
According to the surface diffusion coefficient threshold value of setting, infarct candidate region is obtained from the brain parenchym tissue part；
It obtains in the brain parenchym tissue part, the ratio of Diffusion-Weighted MR Imaging signal and surface diffusion coefficient is higher than setting
The infarct of value confirms region；
It determines in the infarct candidate region, the candidate connected region with infarct confirmation regional connectivity；
According to the Diffusion-Weighted MR Imaging signal value in the candidate connected region, target infarct region is determined.
Optionally, the brain parenchym tissue part in magnetic resonance image is obtained, comprising:
It obtains in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging signal；
By in the magnetic resonance image, Diffusion-Weighted MR Imaging signal is higher than the area of the first threshold of the weighted imaging signal
Domain is determined as brain parenchym tissue part.
Optionally it is determined that the candidate connected region in the infarct candidate region, with infarct confirmation regional connectivity
Domain, comprising:
Binary conversion treatment is carried out to the infarct candidate region, obtains the connected domain in infarct candidate region；
Binary conversion treatment is carried out to infarct confirmation region, obtains the connected domain in infarct confirmation region；
In the connected domain for determining the infarct candidate region, there is intersection with the connected domain in infarct confirmation region
Candidate connected region.
Optionally, according to the Diffusion-Weighted MR Imaging signal value in the candidate connected region, target infarct region is determined,
Include:
Determine the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part；
Determine the Diffusion-Weighted MR Imaging signal of the candidate connected region average value and the candidate connected region
The average value of the Diffusion-Weighted MR Imaging signal of neighborhood tissue；
By the Diffusion-Weighted MR Imaging that in the candidate connected region, the average value of Diffusion-Weighted MR Imaging signal is organized with field
Average signal value or global threshold meet the region of setting ratio relationship, be determined as target infarct region.
Optionally it is determined that in the brain parenchym tissue part Diffusion-Weighted MR Imaging signal global threshold, comprising:
It obtains in the magnetic resonance image, divides the second threshold of the Diffusion-Weighted MR Imaging signal of the brain parenchym tissue part
Value, the second threshold are obtained by carrying out maximum between-cluster variance processing to the magnetic resonance image；
It is handled by carrying out maximum between-cluster variance twice to the brain parenchym tissue part, obtains Diffusion-Weighted MR Imaging respectively
The Low threshold and high threshold of signal；
According to the second threshold, numerical relation with the Low threshold and the high threshold determines the global threshold.
Second aspect, provides a kind of infarct regional detection device, and described device includes:
First obtains unit, for obtaining the brain parenchym tissue part in magnetic resonance image；
Second obtaining unit is obtained from the brain parenchym tissue part for the surface diffusion coefficient threshold value according to setting
Obtain infarct candidate region；
Third obtaining unit, for obtaining in the brain parenchym tissue part, Diffusion-Weighted MR Imaging signal and diffusion into the surface
The infarct that the ratio of coefficient is higher than setting value confirms region；
First determination unit, for determining in the infarct candidate region, with infarct confirmation regional connectivity
Candidate connected region；
Second determination unit, for determining target according to the Diffusion-Weighted MR Imaging signal value in the candidate connected region
Infarct region.
Optionally, first obtains unit is specifically used for:
It obtains in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging signal；
By in the magnetic resonance image, Diffusion-Weighted MR Imaging signal is higher than the area of the first threshold of the weighted imaging signal
Domain is determined as brain parenchym tissue part.
Optionally, the first determination unit is specifically used for:
Binary conversion treatment is carried out to the infarct candidate region, obtains the connected domain in infarct candidate region；
Binary conversion treatment is carried out to infarct confirmation region, obtains the connected domain in infarct confirmation region；
In the connected domain for determining the infarct candidate region, there is intersection with the connected domain in infarct confirmation region
Candidate connected region.
Optionally, the second determination unit is specifically used for:
Determine the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part；
Determine the average value of the Diffusion-Weighted MR Imaging signal of the candidate connected domain and the neighborhood of the candidate connected domain
The average value of the Diffusion-Weighted MR Imaging signal of tissue；
By the Diffusion-Weighted MR Imaging that in the candidate connected region, the average value of Diffusion-Weighted MR Imaging signal is organized with field
Average signal value or global threshold meet the connected region of setting ratio relationship, be determined as target infarct region.
Optionally, the second determination unit is for determining the complete of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part
When office's threshold value, it is specifically used for:
It obtains in the magnetic resonance image, divides the second threshold of the Diffusion-Weighted MR Imaging signal of the brain parenchym tissue part
Value, the second threshold are obtained by carrying out maximum between-cluster variance processing to the magnetic resonance image；
It is handled by carrying out maximum between-cluster variance twice to the brain parenchym tissue part, obtains Diffusion-Weighted MR Imaging respectively
The Low threshold and high threshold of signal；
According to the second threshold, numerical relation with the Low threshold and the high threshold determines the global threshold.
The third aspect provides a kind of image detecting apparatus, comprising: internal bus, and deposited by what internal bus connected
Reservoir, processor and external interface；Wherein,
The external interface, for obtaining magnetic resonance image；
The memory, for storing the corresponding machine readable instructions of infarct region detection logic；
The processor for reading the machine readable instructions on the memory, and executes stalk as described above
Dead stove method for detecting area.
Fourth method provides a kind of computer readable storage medium, is stored thereon with program, and described program is held by processor
Row infarct method for detecting area as described above.
In this specification embodiment, it is candidate that infarct is carried out by the combination of the ratio using DWI and ADC and ADC threshold value
The screening in region, and infarct region is further determined that according to DWI value, it is able to carry out acute and Super acute infarct inspection
It surveys, calculating speed is fast and can distinguish the tumour for being similarly high DWI value and low ADC value and infarct region.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
This specification can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the reality for meeting this specification
Example is applied, and is used to explain the principle of this specification together with specification.
Fig. 1 is a kind of flow chart of infarct method for detecting area shown in one exemplary embodiment of the application；
Fig. 2 is the brain parenchym organization chart picture shown in one exemplary embodiment of the application；
Fig. 3 is the binaryzation infarct candidate region image shown in one exemplary embodiment of the application；
Fig. 4 is that the binaryzation infarct shown in one exemplary embodiment of the application determines area image；
Fig. 5 is the infarct candidate region figure that regional connectivity is determined with infarct shown in one exemplary embodiment of the application
Picture；
Fig. 6 is a kind of flow chart of determining target infarct region method shown in one exemplary embodiment of the application；
Fig. 7 is a kind of schematic diagram of infarct regional detection device shown in one exemplary embodiment of the application；
Fig. 8 is a kind of structural schematic diagram of image detecting apparatus shown in one exemplary embodiment of the application.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent device and method of some aspects be described in detail in attached claims, this specification.
In order to solve in the related technology, infarct detection is carried out in conjunction with DWI value by ADC threshold value, it is difficult to which it is accurate to guarantee
Rate, and the problem of cannot exclude non-ischemic but there is the lesion of high DWI and low ADC, the application proposes a kind of infarct region
Detection method, device, image processing equipment and computer readable storage medium.
It is a kind of flow chart of infarct method for detecting area shown in one exemplary embodiment of the application referring to Fig. 1, it should
Method may comprise steps of:
In a step 101, the brain parenchym tissue part in magnetic resonance image is obtained.
Since infarct is in brain parenchym tissue, therefore, it is necessary to by wiping out background in magnetic resonance image, by brain parenchym tissue
Extracting section comes out.
In one example, the brain parenchym tissue part that can be prepared by the following in magnetic resonance image:
Firstly, obtaining in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging DWI signal；
Next, Diffusion-Weighted MR Imaging signal is higher than the first of the weighted imaging signal by the magnetic resonance image
The region of threshold value is determined as brain parenchym tissue part.
It will be appreciated by those skilled in the art that the method for obtaining brain parenchym tissue part is not limited to the above, it can also be with
Brain parenchym tissue part is extracted using other methods.
It for the first threshold of DWI signal, can be obtained by maximum variance between clusters, other methods can also be passed through
It obtains.
Brain parenchym tissue part obtained image is for example shown in Fig. 2.
In a step 102, according to the surface diffusion coefficient threshold value of setting, infarct is obtained from the brain parenchym tissue part
Stove candidate region.
In this step, the ADC threshold value of setting is obtained first.The ADC threshold value, as " ADC described in the relevant technologies
Hard -threshold ", for screening in brain parenchym tissue part, it is possible to the region of infarct.For example, ADC threshold value can be set to 620~
The arbitrary value in 635 sections.It will be appreciated by those skilled in the art that range above setting is merely illustrative, the present embodiment does not limit this
The specific range of ADC threshold value.
According to ADC threshold value obtained, by brain parenchym tissue part, detected ADC value is less than the area of the threshold value
Domain is determined as infarct candidate region.
The infarct candidate region can indicate with binary image, as shown in Figure 3.Wherein, pixel value is the 1 doubtful stalk of expression
Dead stove tissue, pixel value are the 0 non-infarct of expression.All doubtful infarct tissues are formed by region, and as infarct is candidate
Region.
In step 103, it obtains in the brain parenchym tissue part, Diffusion-Weighted MR Imaging signal and surface diffusion coefficient
The infarct that ratio is higher than setting value confirms region.
In this step, the DWI signal value and ADC value of each pixel in brain parenchym tissue part are obtained first, and are counted
Calculate the ratio p of DWI signal value and ADC value.
Next, obtaining the setting value for screening ratios region, the range of the setting value for example be can be set to
0.25~0.3, which can be the arbitrary value within the scope of this.It will be appreciated by those skilled in the art that range above is arranged
Merely illustrative, the present embodiment does not limit the specific range of the setting value.
Finally, ratio p to be higher than to the region of above-mentioned setting value, it is determined as infarct confirmation region.That is, in the infarct
Confirm in region, the DWI signal of all pixels and the ratio of ADC, is higher than above-mentioned setting value.The infarct can also be confirmed into area
Domain, referred to as ratios region.
The infarct determines that region can be indicated with binary image, as shown in Figure 4.Wherein, pixel value is 1 expression ratio p
Indicate that ratio p is less than or equal to the tissue of setting value higher than the tissue of setting value, 0.All ratio p are higher than the tissue shape of setting value
Region is confirmed at ratios region namely infarct.
At step 104, it determines in the infarct candidate region, candidate the connecting with infarct confirmation regional connectivity
Logical region.
Regional connectivity is confirmed with the infarct, namely has intersection with infarct confirmation region.Since infarct is true
Recognize the higher region ratio p that region is DWI and ADC, that is to say, that in this step, determine in infarct candidate region,
The higher candidate connected region of the ratio p of DWI and ADC.
Since in infarct candidate region, doubtful infarct tissue may be discontinuous distribution, it is thus possible to exist more
Sub-regions；Infarct confirms that region is also that may also deposit in this way, since ratios tissue may be discontinuous distribution
In multiple subregions.In this step, it filters out in multiple subregions of infarct candidate region, confirms region with infarct
(ratios region) has the subregion of intersection, using these subregions as candidate connected region.
Candidate connected region determined by retaining, to carry out subsequent processing；For the tissue in other regions, due to it
The ratio p of DWI and ADC is lower, eliminates a possibility that it is infarction tissue.
In one example, the candidate connected region of table and infarct confirmation regional connectivity is determined by the following method:
Binary conversion treatment is carried out to the infarct candidate region, obtains the connected domain in infarct candidate region, and right
Connected domain obtained carries out label, shown in Figure 3.
Binary conversion treatment is carried out to infarct confirmation region, obtains the connected domain in infarct confirmation region, referring to
Shown in Fig. 4.
In the connected domain for determining the infarct candidate region, there is intersection with the connected domain in infarct confirmation region
Candidate connected region.As shown in figure 5, showing the connected domain for having intersection with infarct confirmation region, that is, indicate that it is true with infarct
Recognize regional connectivity, which is determined as candidate connected region.
Wherein, connected domain can be regarded as in infarct marquis region or infarct confirmation region, and the two of continuous subregion
Value shows result.
In step 105, according to the Diffusion-Weighted MR Imaging signal value in the candidate connected region, target infarct is determined
Region.
For the infarct candidate region (candidate connected region) remained at step 104, according in the region
Diffusion-Weighted MR Imaging signal value, determine final target infarct region.
It is a kind of process of determining target infarct region method shown in one exemplary embodiment of the application referring to Fig. 6
Figure, this method may comprise steps of:
In step 601, the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part is determined.
In this step, the global threshold T of DWI signalglobal, refer to the gray average M of normal brain parenchymglobal.Due to
Before no determining lesion, the region of normal brain parenchym can not be determined, so proposing a kind of estimation DWI signal in disclosure
Global threshold TglobalMethod:
Firstly, obtaining in the magnetic resonance image, the Diffusion-Weighted MR Imaging signal of the brain parenchym tissue part is divided
Second threshold Tair, second threshold TairIt is obtained by carrying out maximum between-cluster variance processing to the magnetic resonance image.
It should be noted that the case where previously described first threshold is obtained using maximum variance between clusters
Under, which can be equal with first threshold.
Next, handling by carrying out maximum between-cluster variance twice to the brain parenchym tissue part, DWI letter is obtained respectively
Number Low threshold TlowWith high threshold Thigh。
Finally, according to second threshold TairWith Low threshold TlowWith high threshold ThighNumerical relation, determine global threshold
Tglobal。
For example, can determine global threshold T according to following values relationshipglobal: it is in described in 2 times of second thresholds
In the case where between Low threshold and the high threshold, determine that the global threshold is 2 times of second threshold；It otherwise, will be described complete
Office's threshold value is determined as second threshold closer one of 2 times of distance among the Low threshold and the high threshold.
That is, if Tlow<2Tair<Thigh, then by 2*TairAs Tglobal；
Otherwise, then T is takenlowWith ThighAmong, distance 2*TairCloser one, as Tglobal。
In step 602, determine the Diffusion-Weighted MR Imaging signal of the candidate connected region average value and the time
Select the average value of the Diffusion-Weighted MR Imaging signal of the neighborhood tissue of connected region.
In this step, the average value for determining the candidate connected region DWI signal, refers to and determines candidate connected region
In, the average value of the DWI signal of each connected domain (subregion) namely the gray average M of each connected domaincore；It determines
The average value of the DWI signal of the neighborhood tissue of candidate's connected region, refers to the field for determining each connected domain (subregion)
The gray average M of the neighborhood tissue of the average value namely each connected domain of the DWI signal of tissuelocal。
In step 603, by the candidate connected region, the average value of Diffusion-Weighted MR Imaging signal and field tissue
The average signal value or global threshold of Diffusion-Weighted MR Imaging meet the region of setting ratio relationship, are determined as target infarct area
Domain.
According to the gray average of each connected domain, the proportionate relationship for the gray average organized with field, or according to every
The gray average of one connected domain, the proportionate relationship with the gray average of normal brain parenchym can determine target infarct region.
In this step, not only according in candidate connected region, the height of DWI signal value determines infarct region,
Also according to the relationship with neighborhood tissue DWI signal, or according to the relationship with global threshold, to determine infarct.
For example, can be by the candidate connected region, Mcore≧0.9×MglobaL or Mcore≧1.2×Mlocal's
Connected domain is determined as target infarct region；Other parts then filter out, and determination is finally only remained in magnetic resonance image
For the region of infarct.
It will be appreciated by those skilled in the art that the numerical value in the above proportionate relationship is merely illustrative, the disclosure not restriction proportion
Specific value in relationship.
In the present embodiment, infarct candidate region is carried out by the combination of the ratio using DWI and ADC and ADC threshold value
Screening, and infarct region is further determined that according to DWI value, is able to carry out acute and Super acute infarct detection, meter
It calculates speed fastly and the tumour for being similarly high DWI value and low ADC value and infarct region can be distinguished.
Each step in process shown in above-mentioned Fig. 1 and Fig. 6, execution sequence are not limited to the sequence in flow chart.This
Outside, the description of each step can be implemented as software, hardware or its form combined, for example, those skilled in the art can be with
The form of software code is implemented these as, can be the executable finger of computer that can be realized the corresponding logic function of the step
It enables.When it is realized in the form of software, the executable instruction be can store in memory, and by the processing in system
Device executes.
Corresponding with the embodiment of aforementioned infarct method for detecting area, present invention also provides infarct region detection dresses
It sets, the embodiment of image detecting apparatus and computer readable storage medium.
It is one embodiment block diagram of the application infarct regional detection device referring to Fig. 7, the apparatus may include: the
One obtaining unit 710, the second obtaining unit 720, third obtaining unit 730, the first determination unit 740 and the second determination unit
750。
Wherein, first obtains unit 710, for for obtaining the brain parenchym tissue part in magnetic resonance image；
Second obtaining unit 720, for the surface diffusion coefficient threshold value according to setting, from the brain parenchym tissue part
Obtain infarct candidate region；
Third obtaining unit 730, for obtaining in the brain parenchym tissue part, Diffusion-Weighted MR Imaging signal and surface are expanded
The ratio for dissipating coefficient is higher than the infarct confirmation region of setting value；
First determination unit 740 confirms regional connectivity with the infarct for determining in the infarct candidate region
Candidate connected region；
Second determination unit 750, for determining mesh according to the Diffusion-Weighted MR Imaging signal value in the candidate connected region
Mark infarct region.
In an optional embodiment, first obtains unit 710 is specifically used for:
It obtains in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging signal；
By in the magnetic resonance image, Diffusion-Weighted MR Imaging signal is higher than the area of the first threshold of the weighted imaging signal
Domain is determined as brain parenchym tissue part.
In an optional embodiment, the first determination unit 740 is specifically used for:
Binary conversion treatment is carried out to the infarct candidate region, obtains the connected domain in infarct candidate region；
Binary conversion treatment is carried out to infarct confirmation region, obtains the connected domain in infarct confirmation region；
In the connected domain for determining the infarct candidate region, there is intersection with the connected domain in infarct confirmation region
Candidate connected region.
In an optional embodiment, the second determination unit 750 is specifically used for:
Determine the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part；
Determine the average value of the Diffusion-Weighted MR Imaging signal of the candidate connected domain and the neighborhood of the candidate connected domain
The average value of the Diffusion-Weighted MR Imaging signal of tissue；
By the Diffusion-Weighted MR Imaging that in the candidate connected region, the average value of Diffusion-Weighted MR Imaging signal is organized with field
Average signal value or global threshold meet the connected region of setting ratio relationship, be determined as target infarct region.
In an optional embodiment, the second determination unit 750 is for determining in the brain parenchym tissue part
When the global threshold of Diffusion-Weighted MR Imaging signal, it is specifically used for:
It obtains in the magnetic resonance image, divides the second threshold of the Diffusion-Weighted MR Imaging signal of the brain parenchym tissue part
Value, the second threshold are obtained by carrying out maximum between-cluster variance processing to the magnetic resonance image；
It is handled by carrying out maximum between-cluster variance twice to the brain parenchym tissue part, obtains Diffusion-Weighted MR Imaging respectively
The Low threshold and high threshold of signal；
According to the second threshold, numerical relation with the Low threshold and the high threshold determines the global threshold.
It is one embodiment schematic diagram of the application image detecting apparatus, which may include: by interior referring to Fig. 8
Memory 820, processor 830 and the external interface 840 that portion's bus 810 connects.
Wherein, the external interface 840, for obtaining magnetic resonance image；
Memory 820, for storing the corresponding machine readable instructions of infarct region detection logic；
Processor 830 for reading the machine readable instructions on memory 820, and executes infarct as described above
Stove method for detecting area.
The application also proposes a kind of computer readable storage medium, is stored thereon with program, which is executed by processor
Infarct method for detecting area as described above.
In the embodiment of the present application, computer readable storage medium can be diversified forms, for example, in different examples
In, the machine readable storage medium may is that RAM (Radom Access Memory, random access memory), volatile deposit
Reservoir, nonvolatile memory, flash memory, memory driver (such as hard disk drive), solid state hard disk, any kind of storage dish
(such as CD, dvd) perhaps similar storage medium or their combination.Special, described computer-readable medium
Can also be paper or other be suitably capable of the medium of print routine.Using these media, these programs can be passed through
The mode of electricity gets (for example, optical scanner), can be compiled, be explained and processing in an appropriate manner, then can be by
It stores in computer media.
The foregoing is merely the preferred embodiments of the application, not to limit the application, all essences in the application
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the application protection.
Claims (10)
1. a kind of infarct method for detecting area characterized by comprising
Obtain the brain parenchym tissue part in magnetic resonance image；
According to the surface diffusion coefficient threshold value of setting, infarct candidate region is obtained from the brain parenchym tissue part；
It obtains in the brain parenchym tissue part, the ratio of Diffusion-Weighted MR Imaging signal and surface diffusion coefficient is higher than setting value
Infarct confirms region；
It determines in the infarct candidate region, the candidate connected region with infarct confirmation regional connectivity；
According to the Diffusion-Weighted MR Imaging signal value in the candidate connected region, target infarct region is determined.
2. being wrapped the method according to claim 1, wherein obtaining the brain parenchym tissue part in magnetic resonance image
It includes:
It obtains in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging signal；
By in the magnetic resonance image, the region that Diffusion-Weighted MR Imaging signal is higher than the first threshold of the weighted imaging signal is true
It is set to brain parenchym tissue part.
3. the method according to claim 1, wherein determining in the infarct candidate region, with the infarct
The candidate connected region of stove confirmation regional connectivity, comprising:
Binary conversion treatment is carried out to the infarct candidate region, obtains the connected domain in infarct candidate region；
Binary conversion treatment is carried out to infarct confirmation region, obtains the connected domain in infarct confirmation region；
In the connected domain for determining the infarct candidate region, there is the candidate of intersection with the connected domain in infarct confirmation region
Connected region.
4. the method according to claim 1, wherein according to the Diffusion-Weighted MR Imaging in the candidate connected region
Signal value determines target infarct region, comprising:
Determine the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part；
Determine the average value of the Diffusion-Weighted MR Imaging signal of the candidate connected region and the neighborhood of the candidate connected region
The average value of the Diffusion-Weighted MR Imaging signal of tissue；
By in the candidate connected region, the Diffusion-Weighted MR Imaging of the average value of Diffusion-Weighted MR Imaging signal and field tissue is put down
Equal signal value or global threshold meet the region of setting ratio relationship, are determined as target infarct region.
5. according to the method described in claim 4, it is characterized in that, determining Diffusion-Weighted MR Imaging in the brain parenchym tissue part
The global threshold of signal, comprising:
It obtains in the magnetic resonance image, divides the second threshold of the Diffusion-Weighted MR Imaging signal of the brain parenchym tissue part,
The second threshold is obtained by carrying out maximum between-cluster variance processing to the magnetic resonance image；
It is handled by carrying out maximum between-cluster variance twice to the brain parenchym tissue part, obtains Diffusion-Weighted MR Imaging signal respectively
Low threshold and high threshold；
According to the second threshold, numerical relation with the Low threshold and the high threshold determines the global threshold.
6. a kind of infarct regional detection device characterized by comprising
First obtains unit, for obtaining the brain parenchym tissue part in magnetic resonance image；
Second obtaining unit is obstructed from the brain parenchym tissue part for the surface diffusion coefficient threshold value according to setting
Dead stove candidate region；
Third obtaining unit, for obtaining in the brain parenchym tissue part, Diffusion-Weighted MR Imaging signal and surface diffusion coefficient
Ratio be higher than setting value infarct confirm region；
First determination unit, the candidate for determining in the infarct candidate region, with infarct confirmation regional connectivity
Connected region；
Second determination unit, for determining target infarct according to the Diffusion-Weighted MR Imaging signal value in the candidate connected region
Stove region.
7. device according to claim 6, which is characterized in that the first obtains unit is specifically used for:
It obtains in magnetic resonance image, the first threshold of Diffusion-Weighted MR Imaging signal；
By in the magnetic resonance image, the region that Diffusion-Weighted MR Imaging signal is higher than the first threshold of the weighted imaging signal is true
It is set to brain parenchym tissue part.
8. device according to claim 7, which is characterized in that second determination unit is specifically used for:
Determine the global threshold of Diffusion-Weighted MR Imaging signal in the brain parenchym tissue part；
Determine the average value of the Diffusion-Weighted MR Imaging signal of the candidate connected domain and the neighborhood tissue of the candidate connected domain
Diffusion-Weighted MR Imaging signal average value；
By in the candidate connected region, the Diffusion-Weighted MR Imaging of the average value of Diffusion-Weighted MR Imaging signal and field tissue is put down
Equal signal value or global threshold meet the connected region of setting ratio relationship, are determined as target infarct region.
9. a kind of image detecting apparatus characterized by comprising internal bus, and by internal bus connect memory,
Processor and external interface；Wherein,
The external interface, for obtaining magnetic resonance image；
The memory, for storing the corresponding machine readable instructions of infarct region detection logic；
The processor for reading the machine readable instructions on the memory, and is executed as appointed in claim 1-5
Method described in one.
10. a kind of computer readable storage medium, is stored thereon with program, which is characterized in that described program is executed by processor
Method of any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553962.2A CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910553962.2A CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110298832A true CN110298832A (en) | 2019-10-01 |
| CN110298832B CN110298832B (en) | 2023-05-02 |
Family
ID=68028791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910553962.2A Active CN110298832B (en) | 2019-06-25 | 2019-06-25 | Infarct range area detection method, device, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298832B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127428A (en) * | 2019-12-24 | 2020-05-08 | 强联智创（北京）科技有限公司 | Method and system for extracting target region based on brain image data |
| CN115205294A (en) * | 2022-09-16 | 2022-10-18 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
| CN115578554A (en) * | 2021-06-21 | 2023-01-06 | 数坤(北京)网络科技股份有限公司 | Blood vessel focus identification method, device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104510469A (en) * | 2013-09-26 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristic based on magnetic resonance diffusion-weighted image |
| CN104510470A (en) * | 2013-09-29 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristics based on diffusion-weighted magnetic resonance imaging |
| CN107301645A (en) * | 2017-06-20 | 2017-10-27 | 上海联影医疗科技有限公司 | A kind of data processing method and device |
| CN107427255A (en) * | 2015-03-12 | 2017-12-01 | 财团法人峨山社会福祉财团 | The method that the generation time point of infarct area is estimated based on brain image |
| CN108122221A (en) * | 2016-11-29 | 2018-06-05 | 中国科学院深圳先进技术研究院 | The dividing method and device of diffusion-weighted imaging image midbrain ischemic area |
-
2019
- 2019-06-25 CN CN201910553962.2A patent/CN110298832B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104510469A (en) * | 2013-09-26 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristic based on magnetic resonance diffusion-weighted image |
| CN104510470A (en) * | 2013-09-29 | 2015-04-15 | 深圳先进技术研究院 | Method and device for determining cerebral ischemia characteristics based on diffusion-weighted magnetic resonance imaging |
| CN107427255A (en) * | 2015-03-12 | 2017-12-01 | 财团法人峨山社会福祉财团 | The method that the generation time point of infarct area is estimated based on brain image |
| CN108122221A (en) * | 2016-11-29 | 2018-06-05 | 中国科学院深圳先进技术研究院 | The dividing method and device of diffusion-weighted imaging image midbrain ischemic area |
| CN107301645A (en) * | 2017-06-20 | 2017-10-27 | 上海联影医疗科技有限公司 | A kind of data processing method and device |
Non-Patent Citations (2)
| Title |
|---|
| ARCHANA PURUSHOTHAM ET AL: "Apparent diffusion coefficient threshold for delineation of ischemic core", 《INTERNATIONAL JOURNAL OF STROKE》 * |
| 徐天同: "DWI与ADC在早期脑梗死中的诊断价值", 《现代中西医结合杂志》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111127428A (en) * | 2019-12-24 | 2020-05-08 | 强联智创（北京）科技有限公司 | Method and system for extracting target region based on brain image data |
| CN115578554A (en) * | 2021-06-21 | 2023-01-06 | 数坤(北京)网络科技股份有限公司 | Blood vessel focus identification method, device, electronic equipment and readable storage medium |
| CN115578554B (en) * | 2021-06-21 | 2024-02-02 | 数坤(上海)医疗科技有限公司 | Vascular focus identification method, device, electronic equipment and readable storage medium |
| CN115205294A (en) * | 2022-09-16 | 2022-10-18 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
| CN115205294B (en) * | 2022-09-16 | 2022-11-22 | 杭州脉流科技有限公司 | Ischemic stroke infarction assessment device and method based on multi-model fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110298832B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6703082B2 (en) | Medical image processing apparatus for segmenting structures in medical image, method for segmenting medical image, and storage medium storing computer program for segmenting medical image | |
| Wink et al. | 3D MRA coronary axis determination using a minimum cost path approach | |
| Reid et al. | A cross-modal, cross-species comparison of connectivity measures in the primate brain | |
| JP5200101B2 (en) | Detection of hemorrhagic stroke in CT image data | |
| CN110298832A (en) | Infarct method for detecting area, device, storage medium and equipment | |
| Deshpande et al. | Automatic segmentation, feature extraction and comparison of healthy and stroke cerebral vasculature | |
| Ter Telgte et al. | The contribution of acute infarcts to cerebral small vessel disease progression | |
| JP2004535874A (en) | Magnetic resonance angiography and apparatus therefor | |
| US11055565B2 (en) | Systems and methods for the identification of perivascular spaces in magnetic resonance imaging (MRI) | |
| KR20230059799A (en) | A Connected Machine Learning Model Using Collaborative Training for Lesion Detection | |
| Chesebro et al. | Automated detection of cerebral microbleeds on T2*-weighted MRI | |
| US20210303933A1 (en) | Validity evaluation device for cancer region detection | |
| Ziegler et al. | Visualizing and quantifying flow stasis in abdominal aortic aneurysms in men using 4D flow MRI | |
| Bouraoui et al. | Fully automatic 3D segmentation of coronary arteries based on mathematical morphology | |
| Goel et al. | Fully automated tool to identify the aorta and compute flow using phase‐contrast MRI: validation and application in a large population based study | |
| KR20190067477A (en) | A measuring method and apparatus of alzheimer's disease clinical stage using amyloid pet | |
| US7711164B2 (en) | System and method for automatic segmentation of vessels in breast MR sequences | |
| Srivastava et al. | Feature-based statistical analysis of structural MR data for automatic detection of focal cortical dysplastic lesions | |
| KR20200114228A (en) | Method and system for predicting isocitrate dehydrogenase (idh) mutation using recurrent neural network | |
| CN110301900B (en) | Quantitative analysis method and system for dynamic perfusion image processing | |
| US8260022B2 (en) | Automatic cardiac band detection of breast MRI | |
| Bernal et al. | Selective motion artefact reduction via Radiomics and k-space reconstruction for improving perivascular space quantification in brain magnetic resonance imaging | |
| US20200013171A1 (en) | Method for quantification of uncertainty of contours in manual & auto segmenting algorithms | |
| Ravi et al. | Accelerated MRI using intelligent protocolling and subject-specific denoising applied to Alzheimer's disease imaging | |
| US20210365722A1 (en) | Information processing device, information processing method, and storage medium |
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 |