CN108898583B - The detection method and device of micro- blutpunkte - Google Patents
The detection method and device of micro- blutpunkte Download PDFInfo
- Publication number
- CN108898583B CN108898583B CN201810601403.XA CN201810601403A CN108898583B CN 108898583 B CN108898583 B CN 108898583B CN 201810601403 A CN201810601403 A CN 201810601403A CN 108898583 B CN108898583 B CN 108898583B
- Authority
- CN
- China
- Prior art keywords
- blutpunkte
- micro
- image
- doubtful
- swi
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
This application provides a kind of detection methods of micro- blutpunkte, comprising: brain parenchym region is extracted from the SWI image and QSM image of the original scan image of brain；According to gray value feature of micro- blutpunkte on SWI image and QSM image, the SWI image to the brain parenchym region and QSM image carry out Threshold segmentation respectively, obtain doubtful micro- blutpunkte on the SWI image and QSM image；According to the Bleeding patterns of micro- blutpunkte, doubtful micro- blutpunkte is verified respectively, obtains target blutpunkte.In addition, present invention also provides a kind of detection devices of micro- blutpunkte.
Description
Technical field
This application involves medical data processing technology, in particular to the detection method and dress of a kind of micro- blutpunkte of brain
It sets.
Background technique
With the development of medical technology, the micro- bleeding of brain (Cerebral MicroBleeds, CMBs) was in quilt in 1994
The discovery such as Offenbacher, this is by chronic hypertension and amyloid protein blood vessel denaturation (Cerebral Amyloid
Angiopathy, CAA) etc. caused by reasons, it is a kind of with tiny blood vessels damage based on subclinical intraparenchymal injury.External big
In majority research, CMBs is considered as the particularity label of cerebrovascular disease relevant to blood pressure, helps to predict cranial vascular disease
The following morbidity tendency.Since the micro- bleeding of brain occurs have the features such as small in size, quantity is more, handmarking's method in brain parenchym
In the presence of time-consuming, it is not easy the problems such as distinguishing, so the detection of the automatic micro- blutpunkte of brain is just particularly important.
Currently, the method for the micro- bleeding in automatic detection of brain portion, is mainly handled by the magnetic resonance image to brain, example
Such as, using GRE (Gradient Recalled Echo, gtadient echo) sequence image or magnetic susceptibility-weighted imaging
(Susceptibility Weighted Imaging, SWI) image series, as the benchmark image of micro- blutpunkte detection, to know
Micro- blutpunkte in other and tag image.
But inventor has found in the course of the research, in the prior art, to the detection of micro- blutpunkte according only to simple sequence figure
As (i.e. GRE image or SWI image etc.), it is non-quantitation information image, lacks quantification information, therefore, compare and be difficult to
The calcification point of differentiation brain and micro- blutpunkte, be easy to cause erroneous judgement, so that the testing result of micro- blutpunkte is not accurate enough.
Summary of the invention
Based on this, this application provides a kind of detection methods of micro- blutpunkte, to the SWI image using brain parenchym region
Totally two kinds of sequence images carry out micro- blutpunkte detection with QSM image, because QSM image has quantification information, i.e., micro- blutpunkte
It in the feature of QSM image sequence is respectively bright spot and dim spot with calcification point, and QSM image has different images from SWI image
Feature allows for the differentiation that calcification point and micro- blutpunkte can be more accurate.
Present invention also provides a kind of detection device of micro- blutpunkte, to guarantee above method realization in practice and
Using.
In a first aspect, this application discloses a kind of detection methods of micro- blutpunkte, this method comprises:
Brain parenchym region is extracted from the SWI image and QSM image of the original scan image of brain；
According to gray value feature of micro- blutpunkte on SWI image and QSM image, respectively to the brain parenchym region
SWI image and QSM image carry out Threshold segmentation, obtain doubtful micro- blutpunkte on the SWI image and QSM image；
According to the Bleeding patterns of micro- blutpunkte, doubtful micro- blutpunkte is verified respectively, target is obtained and goes out
Blood point.
Optionally, the Bleeding patterns include: the size of blutpunkte, the Bleeding patterns according to micro- blutpunkte,
Doubtful micro- blutpunkte is verified respectively, obtains target blutpunkte, comprising:
Calculate the actual volume of each doubtful micro- blutpunkte, and judge the actual volume whether less than the first volume threshold,
Or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than second volume threshold；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then delete using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Optionally, the Bleeding patterns include: the body of blutpunkte, the Bleeding patterns according to micro- blutpunkte,
Doubtful micro- blutpunkte is verified respectively, obtains target blutpunkte, comprising:
Whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then the actual volume is corresponding doubtful
It is deleted as non-blutpunkte micro- blutpunkte.
Optionally, further includes:
Intensity profile statistics is carried out to the remaining blutpunkte for having deleted non-micro- blutpunkte, and using described in normal distribution fitting
Intensity profile statistics, and, the non-blutpunkte in the remaining blutpunkte is deleted according to the result of the fitting.
Optionally, the Bleeding patterns according to micro- blutpunkte respectively verify doubtful micro- blutpunkte,
Obtain target blutpunkte, further includes:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
Second aspect, this application discloses a kind of detection device of micro- blutpunkte, which includes:
Extraction unit, for extracting brain parenchym region in the SWI image and QSM image of the original scan image from brain；
Threshold segmentation unit, it is right respectively for the gray value feature according to micro- blutpunkte on SWI image and QSM image
The SWI image and QSM image in the brain parenchym region carry out Threshold segmentation, obtain doubting on the SWI image and QSM image
Like micro- blutpunkte；
Authentication unit respectively tests doubtful micro- blutpunkte for the Bleeding patterns according to micro- blutpunkte
Card, obtains target blutpunkte.
Optionally, the Bleeding patterns include: the size of blutpunkte；
The authentication unit, is specifically used for:
Computation subunit for calculating the actual volume of each doubtful micro- blutpunkte, and judges whether the actual volume is small
In the first volume threshold, or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than second body
Product threshold value；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then delete using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Optionally, the Bleeding patterns include: the body of blutpunkte；
The authentication unit, is specifically used for:
Whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then the actual volume is corresponding doubtful
It is deleted as non-blutpunkte micro- blutpunkte.
Optionally, further includes:
Statistic unit, for carrying out intensity profile statistics to the remaining blutpunkte for having deleted non-micro- blutpunkte；
Fitting unit, for being fitted the intensity profile statistics using normal distribution；
Unit is deleted, for deleting the non-blutpunkte in the remaining blutpunkte according to the result of the fitting.
Optionally, the authentication unit, is also used to:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
The third aspect, this application discloses a kind of detection device of micro- blutpunkte, the equipment includes processor and deposits
Reservoir:
Said program code is transferred to the processor for storing program code by the memory；
The processor is used for according to any implementation of instruction execution aforementioned first aspect in said program code
The detection method of micro- blutpunkte.
Fourth aspect, this application discloses a kind of storage medium, the storage medium is for storing program code, the journey
Sequence code is used to execute the detection method of micro- blutpunkte described in any implementation of aforementioned first aspect.
Compared with prior art, the application includes following advantages:
In the embodiment of the present application, SWI image and QSM image of micro- blutpunkte detection based on brain parenchym region totally two is carried out
Kind of sequence image, it is contemplated that feature of micro- blutpunkte in two kinds of sequence images of SWI image and QSM image, come carry out it is micro- go out
Blood point detection, since the basic sequence image that QSM image is detected as micro- bleeding has quantification information, i.e., micro- blutpunkte and calcium
Changing point in the feature of QSM image sequence is respectively bright spot and dim spot, and QSM image has different characteristics of image from SWI image,
Allow for the differentiation that calcification point and micro- blutpunkte can be more accurate realizes to the micro- blutpunkte of brain compared with prior art
It more precisely detects.
Certainly, any product for implementing the application does not necessarily require achieving all the advantages described above at the same time.
Detailed description of the invention
In order to more clearly explain the technical solutions in the embodiments of the present application, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the drawings in the following description are only some examples of the present application, for
For those of ordinary skill in the art, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is a flow chart of the detection method embodiment of micro- blutpunkte of the application；
Fig. 2 is another flow chart of the detection method embodiment of micro- blutpunkte of the application；
Fig. 3 is the structural block diagram of the detection device embodiment of micro- blutpunkte of the application；
Fig. 4 is the configuration diagram of the detection device embodiment of micro- blutpunkte of the application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
With reference to Fig. 1, a kind of flow chart of the detection method embodiment of micro- blutpunkte of the application is shown, the present embodiment can be with
The following steps are included:
Step 101: brain parenchym region is extracted from the SWI image and QSM image of the original scan image of brain.
In the present embodiment, after obtaining the magnetic resonance image of brain, the phase diagram to magnetic resonance image can be passed through
It is combined together with map of magnitudes, to obtain the SWI image of brain, brain parenchym region is carried out by the SWI image to brain
It extracts, so that skull and brain parenchym region be separated, obtains the SWI image in individual brain parenchym region.Wherein, SWI schemes
It is obtained as that can be combined by phase diagram and map of magnitudes, and QSM image is to carry out a series of processing to phase diagram to obtain, at this
Reason may include two steps, and the first step is filtering, and to reduce noise, second step is inverse filtering (Inverse Filter), from
And it converts and obtains the QSM image in brain parenchym region.Certainly using other way to obtain QSM image can also be with.In addition, SWI image
It may each be a width with QSM image, can also be with multiple image sequence, the application is it is not limited here.
Specifically, this step can carry out brain parenchym region using adaptive profile (Deformable Model) method
Segmentation.
Step 102: according to gray value feature of micro- blutpunkte on SWI image and QSM image, respectively to the brain parenchym
The SWI image and QSM image in region carry out Threshold segmentation, obtain doubtful micro- bleeding on the SWI image and QSM image
Point.
In practical applications, gray scale of the micro- blutpunkte of brain on SWI image is darker than the gray scale of brain tissue part, and
On QSM (Quantitative Susceptibility Mapping, quantitative susceptibility imaging) image, gray scale is then than normal
The gray scale of brain tissue part wants bright.Therefore, the gray value feature based on micro- blutpunkte on SWI image and QSM image is right respectively
The SWI image and QSM image in brain parenchym region carry out Threshold segmentation, on the contrary it will not be possible to and it is the brain regions exclusion of micro- blutpunkte,
And by zone marker method, doubtful micro- blutpunkte is obtained.
Specifically, this step can be closed by the intensity profile analyzed between micro- blutpunkte and normal brain regions
System, and be split using the method for the extreme value distribution threshold value: it is high to see normal brain tissue intensity profile approximation as mixing
This model (Gaussian Mixture Model, GMM), and for micro- blutpunkte on QSM image, gray scale is mainly distributed on
On the right side of GMM, and for micro- blutpunkte on SWI image, gray scale is mainly distributed on the left of GMM, therefore, in practical applications may be used
Micro- blutpunkte is fitted to the extreme value distribution, then using the intersection point of the extreme value distribution and GMM as threshold value, thus to micro- blutpunkte and just
Normal brain regions are split.
After carrying out Threshold segmentation, the 0-1 template in QSM image and SWI image can be respectively obtained, that is, certain pixels
The value of point is 1, and the value of certain pixels is 0.Because between micro- blutpunkte being picture that is isolated, being 1 to all values
Vegetarian refreshments carries out zone marker, obtains multiple isolated connected regions, and using this multiple connected region as doubtful micro- blutpunkte.
Step 103: according to the Bleeding patterns of micro- blutpunkte, doubtful micro- blutpunkte being verified respectively, is obtained
To target blutpunkte.
Then, the definition based on the Bleeding patterns clinically to micro- blutpunkte, doubtful micro- bleeding that step 102 is partitioned into
Point is verified, for example, the size of micro- blutpunkte or the definition of body etc., doubtful micro- in SWI image and QSM image respectively
The image-region for meeting Bleeding patterns is picked out in blutpunkte as target blutpunkte.In practical applications, it can be directed to respectively
SWI image and QSM image carry out the processing of step 103, and the processing of the two is independent of each other.
Specifically, the size of micro- blutpunkte can be first passed through to verify to doubtful non-blutpunkte, then step 103 can be with
Include:
Step A1: the actual volume of each doubtful micro- blutpunkte in SWI image and QSM image is calculated.
In this step, the size of the actual volume of each doubtful micro- blutpunkte of mark is first calculated.Because of micro- bleeding
The diameter of point is generally between 2-10mm, so illustrating not to be micro- blutpunkte if the size of actual volume exceeds the range.
Step A2: judge the actual volume being calculated whether less than the first volume threshold, or, if be greater than the second body
Product threshold value；If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then enter step A3.
Wherein, first volume threshold be less than second volume threshold, in practical applications, according to it is the smallest it is micro- go out
The diameter of blood point is about 2mm, and the diameter of maximum micro- blutpunkte is about 10mm, then can set the first volume threshold to(sphere volume size when i.e. diameter is 2mm), the second volume threshold is set as(i.e. diameter is 10mm
When sphere volume size), in this step, then actual volume betweenWithBetween it is doubtful
Micro- blutpunkte, which then has biggish, to be actual micro- blutpunkte, and actual volume is less thanOr it is greater thanDoubtful micro- blutpunkte be then unlikely to be micro- blutpunkte.
Step A3: it is deleted using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Therefore, in this step, actual volume is less thanOr it is greater thanIt is doubtful it is micro- go out
Blood point is deleted as non-micro- blutpunkte.
Specifically, can also be verified by the body of micro- blutpunkte to doubtful non-blutpunkte, then step 103 can be with
Include:
Step B1: whether the body for judging each doubtful micro- blutpunkte in SWI image and QSM image is class ball-type, if not,
Then enter step B2.
In this step, Shape analysis is carried out to each doubtful micro- bleeding, if it is class ball-type, then has and biggish may be
Micro- blutpunkte in practice, and if not class ball-type, then enter step B2.Specifically, principal component analysis can be used
The method of (Principle Component Analysis, PCA) analyzes the spherical feature of each doubtful micro- blutpunkte, such as
The doubtful micro- blutpunkte of fruit is no more than whole 1% in the principal component ratio gap of three orthogonal planes, then it is assumed that is that this is doubtful micro-
The body of blutpunkte be it is spherical, if it exceeds whole 1%, then it is assumed that the body of doubtful micro- blutpunkte be not it is spherical,
Enter step B2.
Step B2: it is deleted using doubtful micro- blutpunkte as non-blutpunkte.
It in this step, is not that doubtful micro- blutpunkte of class ball-type is deleted as non-blutpunkte using body.
It is understood that in practical applications, it, can be with size and shape in order to promote the accuracy in detection of target blutpunkte
Body is all judged, because size and the deterministic process of body are independent of each other, first judge size or first judge that body is equal
The embodiment of the present application can be achieved.
As it can be seen that in the embodiment of the present application, carrying out micro- blutpunkte detection and being schemed based on the SWI image and QSM in brain parenchym region
As totally two kinds of sequence images, it is contemplated that feature of micro- blutpunkte in two kinds of sequence images of SWI image and QSM image, into
The micro- blutpunkte detection of row, since the basic sequence image that QSM image is detected as micro- bleeding has quantification information, i.e., micro- bleeding
Point and calcification point are respectively bright spot and dim spot in the feature of QSM image sequence, and QSM image has different figures from SWI image
As feature, allow for the differentiation that calcification point and micro- blutpunkte can be more accurate realizes micro- to brain compared with prior art
Bleeding more precisely detects.
With reference to Fig. 2, a kind of flow chart of the detection method embodiment of micro- blutpunkte of the application is shown, the present embodiment can be with
The following steps are included:
Step 201: brain parenchym region is extracted from the SWI image of the original scan image of brain.
Step 202: according to gray value feature of micro- blutpunkte on SWI image and QSM image, respectively to the brain parenchym
The SWI image and QSM image in region carry out Threshold segmentation, obtain doubtful micro- bleeding on the SWI image and QSM image
Point.
In the present embodiment, step 201~step 202 is identical as the embodiment of previous embodiment, no longer superfluous herein
It states.
Step 203: calculating the actual volume of each doubtful micro- blutpunkte, and judge the actual volume whether less than the first body
Product threshold value, or, if it is greater than the second volume threshold；If the actual volume is less than first volume threshold, alternatively, institute
Actual volume is stated greater than the second volume threshold, then enters step 203.
Step 204: being deleted using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Wherein, first volume threshold is less than second volume threshold.After obtaining doubtful blutpunkte, in step
In 203~step 204, size judgement first is carried out to each doubtful blutpunkte in SWI image and QSM image, calculates each doubt
It is less than like the volume of blutpunkte, and by actual volumeOr it is greater thanDoubtful micro- blutpunkte, make
It is deleted for non-micro- blutpunkte.
Step 205: whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then entering step 206.
In this step, to the shape for having deleted the remaining each doubtful micro- blutpunkte in non-micro- blutpunkte in step 204
Body is judged, if not class ball-type, is then entered step 206 and is deleted, if it is class ball-type, then retain this it is doubtful it is micro- go out
Blood point.
Step 206: doubtful micro- blutpunkte of non-globoid is deleted as non-blutpunkte.
Step 207: intensity profile statistics being carried out to the remaining blutpunkte for having deleted non-micro- blutpunkte, and uses normal distribution
It is fitted the intensity profile statistics, and, the non-blutpunkte in the remaining blutpunkte is deleted according to the result of the fitting.
In step 207, then intensity profile statistics is carried out to the doubtful blutpunkte retained by step 206, because
Normal distribution should be totally presented in micro- blutpunkte of practical application deutocerebral region, therefore, can be gone to be fitted the gray scale with normal distribution
Distribution statistics, and doubtful micro- blutpunkte by gray scale outside the range of { normal distribution mean value ± (3* normal distribution standard is poor) },
It is deleted as non-blutpunkte.Wherein, numerical value 3 is the pre-set empirical value of those skilled in the art, can be based on difference
The image of manufacturer carries out the adjustment of adaptability, such as is adjusted to 2 or 4 etc..The size of specific value does not influence the reality of the application
It is existing.
Step 208: doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, be determined as the target
Blutpunkte.
In the present embodiment, it in order to further ensure the accuracy of micro- blutpunkte detection, can also will exist simultaneously in institute
The doubtful micro- blutpunkte for stating SWI image and QSM image, is determined as the target blutpunkte.If some doubtful micro- blutpunkte is deposited
It is but to be not present in QSM image in SWI image, also deletes the doubtful blutpunkte, similarly, if some is doubtful
Micro- blutpunkte, which is present in QSM image, to be but not present in SWI image, also deletes the doubtful blutpunkte, then will
The remaining doubtful micro- blutpunkte arrived is as target blutpunkte.For example, in a kind of specific example of determining target blutpunkte, it can
The position of each blutpunkte in the position and QSM of each blutpunkte in SWI image to be compared one by one.Pass through comparison
As a result, determining in the position blutpunkte identical with the position in QSM image in SWI image, as target blutpunkte.
In the present embodiment, SWI image and QSM image of micro- blutpunkte detection based on brain parenchym region totally two kinds of sequences are carried out
Column image, it is contemplated that feature of micro- blutpunkte in two kinds of sequence images of SWI image and QSM image, to carry out micro- blutpunkte
Detection, since the basic sequence image that QSM image is detected as micro- bleeding has quantification information, i.e., micro- blutpunkte and calcification point
It is respectively bright spot and dim spot in the feature of QSM image sequence, and QSM image has different characteristics of image from SWI image, just makes
Calcification point and micro- blutpunkte can be more accurate differentiation realize compared with prior art to subject to the micro- bleeding more of brain
Really detect.
For the aforementioned method embodiment, for simple description, therefore, it is stated as a series of action combinations, still
Those skilled in the art should understand that the application is not limited by the described action sequence, because according to the application, it is certain
Step can be performed in other orders or simultaneously.Secondly, those skilled in the art should also know that, it is described in the specification
Embodiment belong to preferred embodiment, necessary to related actions and modules not necessarily the application.
It is corresponding with method provided by a kind of detection method embodiment of micro- blutpunkte of above-mentioned the application, referring to Fig. 3, originally
Application additionally provides a kind of detection device embodiment of micro- blutpunkte, in the present embodiment, the apparatus may include:
Extraction unit, for extracting brain parenchym region in the SWI image and QSM image of the original scan image from brain；
Threshold segmentation unit, it is right respectively for the gray value feature according to micro- blutpunkte on SWI image and QSM image
The SWI image and QSM image in the brain parenchym region carry out Threshold segmentation, obtain doubting on the SWI image and QSM image
Like micro- blutpunkte；
Authentication unit respectively tests doubtful micro- blutpunkte for the Bleeding patterns according to micro- blutpunkte
Card, obtains target blutpunkte.
Optionally, the Bleeding patterns include: the size of blutpunkte；
The authentication unit, is specifically used for:
Computation subunit for calculating the actual volume of each doubtful micro- blutpunkte, and judges whether the actual volume is small
In the first volume threshold, or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than second body
Product threshold value；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then delete using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Optionally, the Bleeding patterns include: the body of blutpunkte；
The authentication unit, is specifically used for:
Whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then the actual volume is corresponding doubtful
It is deleted as non-blutpunkte micro- blutpunkte.
Optionally, further includes:
Statistic unit, for carrying out intensity profile statistics to the remaining blutpunkte for having deleted non-micro- blutpunkte；
Fitting unit, for being fitted the intensity profile statistics using normal distribution；
Unit is deleted, for deleting the non-blutpunkte in the remaining blutpunkte according to the result of the fitting.
Optionally, the authentication unit, is also used to:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
In addition, present invention also provides a kind of detection devices of micro- blutpunkte.The application is shown refering to Fig. 4, Fig. 4 to provide
A kind of micro- blutpunkte detection device embodiment configuration diagram, the equipment 400 include processor 401 and memory
402:
Said program code is transferred to the processor 401 for storing program code by the memory 402；
The processor 401 is used for according to operating below the instruction execution in said program code:
Brain parenchym region is extracted from the SWI image and QSM image of the original scan image of brain；
According to gray value feature of micro- blutpunkte on SWI image and QSM image, respectively to the brain parenchym region
SWI image and QSM image carry out Threshold segmentation, obtain doubtful micro- blutpunkte on the SWI image and QSM image；
According to the Bleeding patterns of micro- blutpunkte, doubtful micro- blutpunkte is verified respectively, target is obtained and goes out
Blood point.
Optionally, the Bleeding patterns include: the size of blutpunkte；
The processor 401 is also used to operate according to below the instruction execution in said program code:
Calculate the actual volume of each doubtful micro- blutpunkte, and judge the actual volume whether less than the first volume threshold,
Or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than second volume threshold；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then delete using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Optionally, the Bleeding patterns include: the body of blutpunkte；
The processor 401 is also used to operate according to below the instruction execution in said program code:
Whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then the actual volume is corresponding doubtful
It is deleted as non-blutpunkte micro- blutpunkte.
Optionally, the processor 401 is also used to operate according to below the instruction execution in said program code:
Intensity profile statistics is carried out to the remaining blutpunkte for having deleted non-micro- blutpunkte, and using described in normal distribution fitting
Intensity profile statistics, and, the non-blutpunkte in the remaining blutpunkte is deleted according to the result of the fitting.
Optionally, the processor 401 is also used to operate according to below the instruction execution in said program code:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
In addition, the storage medium is for storing program code, described program present invention also provides a kind of storage medium
Code such as gives an order for executing:
Brain parenchym region is extracted from the SWI image and QSM image of the original scan image of brain；
According to gray value feature of micro- blutpunkte on SWI image and QSM image, respectively to the brain parenchym region
SWI image and QSM image carry out Threshold segmentation, obtain doubtful micro- blutpunkte on the SWI image and QSM image；
According to the Bleeding patterns of micro- blutpunkte, doubtful micro- blutpunkte is verified respectively, target is obtained and goes out
Blood point.
Optionally, the Bleeding patterns include: the size of blutpunkte；
Said program code is also used to execute and such as give an order:
Calculate the actual volume of each doubtful micro- blutpunkte, and judge the actual volume whether less than the first volume threshold,
Or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than second volume threshold；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold
Value, then delete using the corresponding doubtful micro- blutpunkte of the actual volume as non-blutpunkte.
Optionally, the Bleeding patterns include: the body of blutpunkte；
Said program code is also used to execute and such as give an order:
Whether the body for judging each doubtful micro- blutpunkte is class ball-type, if it is not, then the actual volume is corresponding doubtful
It is deleted as non-blutpunkte micro- blutpunkte.
Optionally, said program code is also used to execute and such as give an order:
Intensity profile statistics is carried out to the remaining blutpunkte for having deleted non-micro- blutpunkte, and using described in normal distribution fitting
Intensity profile statistics, and, the non-blutpunkte in the remaining blutpunkte is deleted according to the result of the fitting.
Optionally, said program code is also used to execute and such as give an order:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
It should be noted that all the embodiments in this specification are described in a progressive manner, each embodiment weight
Point explanation is the difference from other embodiments, and the same or similar parts between the embodiments can be referred to each other.
For device class embodiment, since it is basically similar to the method embodiment, so being described relatively simple, related place ginseng
See the part explanation of embodiment of the method.
Finally, it is to be noted that, the terms "include", "comprise" or its any other variant be intended to it is non-exclusive
Property include so that include a series of elements process, method, article or equipment not only include those elements, but also
Further include other elements that are not explicitly listed, or further include for this process, method, article or equipment it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described
There is also other identical elements in the process, method, article or equipment of element.
The detection method and device of micro- blutpunkte provided herein are described in detail above, it is used herein
The principle and implementation of this application are described for specific case, and the above embodiments are only used to help understand
The present processes and its core concept；At the same time, for those skilled in the art is having according to the thought of the application
There will be changes in body embodiment and application range, in conclusion the content of the present specification should not be construed as to the application
Limitation.
Claims (6)
1. a kind of detection device of micro- blutpunkte, which is characterized in that the device includes:
Extraction unit, for extracting brain parenchym region in the SWI image and QSM image of the original scan image from brain；
Threshold segmentation unit, for the gray value feature according to micro- blutpunkte on SWI image and QSM image, respectively to described
The SWI image and QSM image in brain parenchym region carry out Threshold segmentation, obtain doubtful micro- on the SWI image and QSM image
Blutpunkte；Gray value feature of the micro- blutpunkte on SWI image includes: that the gray value of micro- blutpunkte is less than normal brain activity
The gray value of tissue part；Gray value feature of the micro- blutpunkte on QSM image includes: the gray value of micro- blutpunkte
Greater than the gray value of normal cerebral tissue part, and the gray value of micro- blutpunkte is greater than the gray value of calcification point；
Authentication unit is respectively verified doubtful micro- blutpunkte, is deleted for the Bleeding patterns according to micro- blutpunkte
Except non-micro- blutpunkte therein, target blutpunkte is obtained；The Bleeding patterns include in the size and body of blutpunkte at least
It is a kind of；
Further include:
Statistic unit, for carrying out intensity profile statistics to the remaining blutpunkte for having deleted non-micro- blutpunkte；
Fitting unit, for being fitted the intensity profile statistics using normal distribution；
Unit is deleted, for deleting non-micro- blutpunkte in the remaining blutpunkte according to the result of the fitting.
2. the apparatus according to claim 1, which is characterized in that the Bleeding patterns include: the size of blutpunkte；
The authentication unit, is specifically used for:
Whether computation subunit for calculating the actual volume of each doubtful micro- blutpunkte, and judges the actual volume less than
One volume threshold, or, if it is greater than the second volume threshold；Wherein, first volume threshold is less than the second volume threshold
Value；
If the actual volume is less than first volume threshold, alternatively, the actual volume is greater than the second volume threshold, then
It is deleted using the corresponding doubtful micro- blutpunkte of the actual volume as non-micro- blutpunkte；
First volume threshold isSecond volume threshold is
3. the apparatus according to claim 1, which is characterized in that the Bleeding patterns include: the body of blutpunkte；
The authentication unit, is specifically used for:
Principal component analysis PCA method is used to judge the body of each doubtful micro- blutpunkte whether for class ball-type, if it is not, then will be described
It is deleted as non-micro- blutpunkte doubtful micro- blutpunkte.
4. device according to claim 2 or 3, which is characterized in that the authentication unit is also used to:
Doubtful micro- blutpunkte in the SWI image and QSM image will be existed simultaneously, is determined as the target blutpunkte.
5. a kind of detection device of micro- blutpunkte, the equipment includes processor and memory:
Said program code is transferred to the processor for storing program code by the memory；
The processor is used for the detection device of the described in any item micro- blutpunktes of Claims 1-4.
6. a kind of storage medium, the storage medium is used for Claims 1-4 for storing program code, said program code
The detection device of described in any item micro- blutpunktes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810601403.XA CN108898583B (en) | 2018-06-12 | 2018-06-12 | The detection method and device of micro- blutpunkte |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810601403.XA CN108898583B (en) | 2018-06-12 | 2018-06-12 | The detection method and device of micro- blutpunkte |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108898583A CN108898583A (en) | 2018-11-27 |
| CN108898583B true CN108898583B (en) | 2019-08-13 |
Family
ID=64344805
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810601403.XA Active CN108898583B (en) | 2018-06-12 | 2018-06-12 | The detection method and device of micro- blutpunkte |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108898583B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111179222B (en) * | 2019-12-09 | 2023-08-22 | 平安科技（深圳）有限公司 | Intelligent cerebral hemorrhage point detection method and device and computer readable storage medium |
| CN111445520B (en) * | 2020-05-26 | 2021-09-24 | 河南省人民医院 | Thalamus abdominal intermediate nucleus positioning method and positioning device based on magnetic resonance quantitative magnetic sensitive image |
| CN113421231B (en) * | 2021-06-08 | 2023-02-28 | 杭州海康威视数字技术股份有限公司 | Bleeding point detection method, device and system |
| CN113344922A (en) * | 2021-08-04 | 2021-09-03 | 南京钺曦医疗科技有限公司 | Method for automatically segmenting cerebral microhemorrhage points |
| CN117158919B (en) * | 2023-10-25 | 2024-03-15 | 深圳大学 | Bleeding point detection device and computer-readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1652721A (en) * | 2002-05-10 | 2005-08-10 | 马克·E·哈克 | Magnetic resonance imaging |
| CN102077108A (en) * | 2008-04-28 | 2011-05-25 | 康奈尔大学 | Tool for accurate quantification in molecular mri |
| CN104414636A (en) * | 2013-08-23 | 2015-03-18 | 北京大学 | Magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system |
-
2018
- 2018-06-12 CN CN201810601403.XA patent/CN108898583B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1652721A (en) * | 2002-05-10 | 2005-08-10 | 马克·E·哈克 | Magnetic resonance imaging |
| CN102077108A (en) * | 2008-04-28 | 2011-05-25 | 康奈尔大学 | Tool for accurate quantification in molecular mri |
| CN104414636A (en) * | 2013-08-23 | 2015-03-18 | 北京大学 | Magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108898583A (en) | 2018-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108898583B (en) | The detection method and device of micro- blutpunkte | |
| US9445744B2 (en) | Methods, systems, and devices for spine centrum extraction and intervertebral disk dividing | |
| CN108985155A (en) | Mouth model training method, mouth recognition methods, device, equipment and medium | |
| CN109997200A (en) | Stroke diagnosis and method for prediction of prognosis and system | |
| CN108932479A (en) | A kind of human body anomaly detection method | |
| CN108122221B (en) | Segmentation method and device for cerebral ischemia area in diffusion weighted imaging image | |
| Zhang et al. | Structured learning for 3-D perivascular space segmentation using vascular features | |
| CN110415234A (en) | Brain tumor dividing method based on multi-parameter magnetic resonance imaging | |
| Law et al. | Segmentation of intracranial vessels and aneurysms in phase contrast magnetic resonance angiography using multirange filters and local variances | |
| Zhong et al. | Automated white matter hyperintensity detection in multiple sclerosis using 3D T2 FLAIR | |
| CN109858476A (en) | The extending method and electronic equipment of label | |
| CN109461163A (en) | A kind of edge detection extraction algorithm for magnetic resonance standard water mould | |
| CN111709421A (en) | Bird identification method and device, computer equipment and storage medium | |
| CN111914665A (en) | Face shielding detection method, device, equipment and storage medium | |
| CN110264454A (en) | Cervical cancer tissues pathological image diagnostic method based on more hidden layer condition random fields | |
| KR101284388B1 (en) | Method and apparatus for analyzing magnetic resonance imaging, and recording medium for executing the method | |
| CN115953393A (en) | Intracranial aneurysm detection system, equipment and storage medium based on multitask learning | |
| CN109558773A (en) | Information identifying method, device and electronic equipment | |
| CN101847260B (en) | Image processing apparatus, and image processing method | |
| Dhumane et al. | Automated glaucoma detection using cup to disc ratio | |
| CN105225234A (en) | Based on the lung tumor identification method of support vector machine MRI Iamge Segmentation | |
| CN105184799A (en) | Modified non-supervision brain tumour MRI (Magnetic Resonance Imaging) image segmentation method | |
| CN103049913A (en) | Method and device for dividing brain magnetic resonance angiography data | |
| CN112308842B (en) | Positioning core automatic extraction method based on printed matter image | |
| WO2004051568A1 (en) | Brain connectivity mapping |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yang Qi Inventor after: Bian Yueyan Inventor before: Bian Yueyan |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 110179 No. 177-1 Innovation Road, Hunnan District, Shenyang City, Liaoning Province Applicant after: DongSoft Medical System Co., Ltd. Address before: 110179 No. 177-1 Innovation Road, Hunnan District, Shenyang City, Liaoning Province Applicant before: Dongruan Medical Systems Co., Ltd., Shenyang |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |