CN109671067A - A kind of measurement method and system of the core Infarction volume based on head CT images - Google Patents
A kind of measurement method and system of the core Infarction volume based on head CT images Download PDFInfo
- Publication number
- CN109671067A CN109671067A CN201811531722.4A CN201811531722A CN109671067A CN 109671067 A CN109671067 A CN 109671067A CN 201811531722 A CN201811531722 A CN 201811531722A CN 109671067 A CN109671067 A CN 109671067A
- Authority
- CN
- China
- Prior art keywords
- infarct
- target area
- judging result
- head
- infarction volume
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30016—Brain
Abstract
This specification embodiment discloses the measurement method and system of a kind of core Infarction volume based on head CT images, belongs to field of medical imaging.This specification embodiment solves the problems, such as that subjectivity differs greatly in the prior art, core Infarction volume measurement result poor accuracy by the measurement method of the core Infarction volume based on head CT images.The measurement method of the core Infarction volume includes: to extract target area from multiframe head CT image data to be processed；The each target area for being included to target area carries out infarct judgement respectively, exports infarct judging result；Infarct judging result based on target area, measurement core Infarction volume.This specification embodiment provide measurement method and system, can quick, accurate measurement core Infarction volume, exclude or reduce subjective factor interference provide objective basis as computer-aid method for medical researches such as cerebral apoplexies.
Description
Technical field
This specification is related to medical image and field of computer technology more particularly to a kind of core based on head CT images
The measurement method and system of Infarction volume.
Background technique
Core infarct be acute ischemic cerebral apoplexy (acute ischemic stroke, AIS) evaluation important indicator it
One.Wherein, core infarct is the brain tissue that irreversible damage occurs, and is referred to compared with normal cerebral tissue, under cerebral blood flow (CBF)
Drop is more than 30% region, is shown as low density area in NCCT (non-contrast CT, unenhanced computed tomography).
The size of infarct core and the clinical prognosis of patient are closely related.A possibility that infarct core is smaller, patient prognosis bona is bigger.
Meanwhile assessment infarct core also can be predicted endovascular treatment and the risk of complication occurs, therefore, accurate evaluation infarct core helps
In the apoplexy patient for filtering out suitable endovascular treatment.Core Infarction volume is to assess one of the index of core infarct, is suffered from AIS
The relevant prediction index of person's good prognosis.
In currently available technology, the measurement of core Infarction volume mainly includes hand dipping and two kinds of computer aided measurement
Method.Wherein, hand dipping core Infarction volume key is manually to delineate infarct lesion, and this method is very cumbersome, accuracy,
There is larger limitation in terms of repeatability and objectivity.Computer aided measurement core Infarction volume mostly uses image segmentation
Method measures, but this method can lose some information during processing, influence measurement result.
Therefore, a kind of measurement method of core Infarction volume is needed at present, it being capable of quick, accurate measurement core stalk
Dead volume excludes or reduces the interference of subjective factor, and as computer-aid method, it is objective to provide for medical researches such as cerebral apoplexies
Foundation.
Summary of the invention
This specification embodiment provides the measurement method and system of a kind of core Infarction volume based on head CT images, uses
In solving following technical problem: can quick, accurate measurement core Infarction volume, exclude or reduce the dry of subjective factor
It disturbs, as computer-aid method, provides objective basis for medical researches such as cerebral apoplexies.
This specification embodiment provides a kind of measurement method of core Infarction volume based on head CT images, including following
Step:
From multiframe head CT image data to be processed, target area is extracted, wherein the target area is the head
The region of measurement core Infarction volume is used in cranium CT images data；
The each target area for being included to the target area carries out infarct judgement respectively, exports the target area
Infarct judging result；
Infarct judging result based on the target area, measurement core Infarction volume.
Preferably, from multiframe head CT image data to be processed, target area is extracted, is specifically included:
By head CT image data to be processed, input is extracted in model, to each of head CT images data picture
Vegetarian refreshments carries out digital label classification, exports and with each pixel in the head CT image data corresponding has digital label
Three-dimensional matrice, wherein the digital label and the target area correspond.
Preferably, each target area for being included to the target area carries out infarct judgement, exports the target area
The infarct judging result in domain, specifically includes:
Based on each pixel for being included in the target area, infarct judgement is carried out, the target area is exported
Infarct judging result.
Further, each target area for being included to the target area carries out infarct judgement, exports the target
The infarct judging result in region further comprises:
According to the infarct judging result of the target area, judge whether target area in the brain of left and right has infarct；
If target area has infarct in the brain of left and right, further infarct occurs for which specific side of judgement, described in correction
The infarct judging result of target area, the new infarct judging result as target area.
It is preferably based on the infarct judging result of the target area, measurement core Infarction volume specifically includes:
Infarct judging result based on the target area determines in each target area that infarct occurs and cerebral infarction occurs
Pixel number；
According to the pixel spacing of CT images, the thickness of CT images to be sent out in each target area that cerebral infarction occurs
The pixel number of raw cerebral infarction, determines the core Infarction volume that each target area of cerebral infarction occurs, each target
Measurement result of the summation of the core Infarction volume in region as core Infarction volume.
A kind of measuring system for core Infarction volume based on head CT images that this specification embodiment provides, comprising:
Region extraction module extracts target area, wherein the mesh from multiframe head CT image data to be processed
Marking region is the region that measurement core Infarction volume is used in the head CT image data；
Infarct identification module, each target area for being included to the target area carry out infarct judgement, export target
The infarct judging result in region；
Measurement module, the infarct judging result based on the target area, measurement core Infarction volume.
Preferably, from multiframe head CT image data to be processed, target area is extracted, is specifically included:
By multiframe head CT image data to be processed, model is extracted in input, to each of head CT images data
Pixel carries out digital label classification, exports corresponding with each pixel in the head CT image data with digital label
Three-dimensional matrice, wherein the digital label and the target area correspond.
Preferably, each target area for being included to the target area carries out infarct judgement, exports the target area
The infarct judging result in domain, specifically includes:
Based on each pixel for being included in the target area, infarct judgement is carried out, the target area is exported
Infarct judging result.
Further, each target area for being included to the target area carries out infarct judgement, exports the target
The infarct judging result in region further comprises:
According to the infarct judging result of the target area, judge whether target area in the brain of left and right has infarct；
If target area has infarct in the brain of left and right, further infarct occurs for which specific side of judgement, described in correction
The infarct judging result of target area, the new infarct judging result as target area.
It is preferably based on the infarct judging result of the target area, measurement core Infarction volume specifically includes:
Infarct judging result based on the target area determines in each target area that infarct occurs and cerebral infarction occurs
Pixel number；
According to the pixel spacing of CT images, the thickness of CT images to be sent out in each target area that cerebral infarction occurs
The pixel number of raw cerebral infarction, determines the core Infarction volume that each target area of cerebral infarction occurs, each target
Measurement result of the summation of the core Infarction volume in region as core Infarction volume.
This specification embodiment use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that
From multiframe CT images data to be processed, extraction target area carries out infarct respectively and sentences this specification embodiment
It is disconnected, and then measurement core Infarction volume, can quick, accurate measurement core Infarction volume, exclude or reduce it is subjective because
The interference of element provides objective basis as computer-aid method for medical researches such as cerebral apoplexies.
Detailed description of the invention
In order to illustrate more clearly of this specification embodiment or technical solution in the prior art, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
The some embodiments recorded in this specification, for those of ordinary skill in the art, in not making the creative labor property
Under the premise of, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of measurement method for core Infarction volume based on head CT images that this specification embodiment provides
Frame diagram；
Fig. 2 a is that the core that this specification embodiment provides rolls into a ball showing for the target area of measurement core Infarction volume in layer
It is intended to；
Fig. 2 b is that the core that this specification embodiment provides is rolled into a ball in upper layer for the target area of measurement core Infarction volume
Schematic diagram；
Fig. 3 a be this specification embodiment provide be used for after recycle measurement core Infarction volume pons and bilateral cerebellar
Area schematic；
Fig. 3 b be this specification embodiment provide be used for after recycle measurement core Infarction volume mesencephalic region schematic diagram；
Fig. 3 c be this specification embodiment provide be used for after recycle measurement core Infarction volume bilateral thalamus and brain
Artery blood supply region schematic diagram；
Fig. 4 is a kind of measurement method for core Infarction volume based on head CT images that this specification embodiment provides
Flow chart；
Fig. 5 is that a kind of infarct that this specification embodiment provides judges schematic diagram；
Fig. 6 is a kind of measuring system for core Infarction volume based on head CT images that this specification embodiment provides
Schematic diagram.
Initialism explanation
C head of caudate nucleus
L lenticular nucleus
IC posterior limb of internal capsule
The island I band
M1 arteria cerebri media frontal cortex area
M2 arteria cerebri media Dao Ye lateral cortex area
Cortical area after M3 arteria cerebri media
Arteria cerebri media cortex above M4 M1
Arteria cerebri media cortex above M5 M2
Arteria cerebri media cortex above M6 M3
Explanation
It is from top to bottom pons, bilateral cerebellar in Fig. 3 a；
It is from top to bottom bilateral thalamus and arteria cerebri posterior blood supply area in Fig. 3 c；
Number 1 and 2 in Fig. 3 represents the weight in each region.
Specific embodiment
In order to make those skilled in the art more fully understand the technical solution in this specification, below in conjunction with this explanation
Attached drawing in book embodiment is clearly and completely described the technical solution in this specification embodiment, it is clear that described
Embodiment be merely a part but not all of the embodiments of the present application.Based on this specification embodiment, this field
Those of ordinary skill's every other embodiment obtained without creative efforts, all should belong to the application
The range of protection.
Fig. 1 is a kind of measurement method for core Infarction volume based on head CT images that this specification embodiment provides
Frame diagram, specific steps include:
Step S101: from multiframe head CT image data to be processed, target area is extracted.
CT images are to be arranged in a matrix to constitute by the pixel of different gray scales from black to white of certain amount.CT value is for anti-
Reflect the size of the density value of human body respective organization.Since the CT images of single frames are that have certain thickness level image, commonly
It is cross section, in order to show entire organ, needs multiple continuous level images.Therefore, when carrying out the measurement of core Infarction volume,
It needs that a series of multiframe images is combined to be observed, to be evaluated, head CT image data to be processed in the present embodiment
It is multiframe.
In one embodiment of this specification, position is distinguished in 10 regions that the core Infarction volume for preceding circulation measures
Layer is rolled into a ball in core and core rolls into a ball upper layer, it is specific as shown in Figure 2.Therefore, the ASPECTS measurement core Infarction volume recycled before progress
When, it is thus necessary to determine that the position in each 10 regions of left and right brain.In particular it is required that determine in multiframe head CT images to be processed,
Whether each pixel belongs to the target area of left and right brain and belongs to which region in target area, goal in each frame
Region is the included region for being used to measure core Infarction volume, by right in multiframe head CT images to be analyzed
The judgement of the cerebral infarction of the target area can finally realize the measurement to the core Infarction volume of head CT images.In this theory
In bright book embodiment, target area can be head of caudate nucleus, lenticular nucleus, posterior limb of internal capsule, island band and the area M1-M6 of left and right brain, altogether
20 regions.When the pixel is not belonging to target area, then it is judged to belonging to background area.Utilize housebroken extraction mould
The extraction of target area may be implemented in type, inputs head CT images data, and output has the three-dimensional matrice of digital label, wherein
The target area of digital label and left and right brain corresponds.
In the another embodiment of this specification, in 8 regions of the core Infarction volume measurement recycled after being used for,
Pons and bilateral cerebellar are located at cerebellum layer, and midbrain is located at midbrain layer, and bilateral thalamus and arteria cerebri posterior blood supply area are located at strata cerebrale,
It is specific as shown in Figure 3.Therefore, when the core Infarction volume measurement recycled after progress, whether each pixel belongs to mesh in each frame
Mark region and belonging to which region in target area, goal region is in multiframe head CT images to be analyzed,
The included region for measuring core Infarction volume can be most by the judgement of the cerebral infarction to the target area
The measurement to the core Infarction volume of head CT images is realized eventually.In this specification embodiment, target area can be bilateral
Thalamus and cerebellum, bilateral cerebral artery blood supply area, midbrain and pons, totally 8 regions.When the pixel is not belonging to target area
When, then it is judged to belonging to background area.Using housebroken extraction model, the extraction of target area, input head may be implemented
Cranium CT images data, output have the three-dimensional matrice of digital label, wherein digital label and target area correspond.
Step S103: infarct judgement is carried out to target area, exports the infarct judging result of target area.
It after extracting target area by step S101, needs further to analyze and determine, infarct occurs for which region.
In CT images, the corresponding gray scale of a CT value.Judging infarct can be there are many mode, a kind of illustrative mode
Be what the symmetry based on human brain was realized: at nominal conditions, the CT value mean value of left and right brain symmetric position is substantially human brain tissue
It is identical, that is, gray value is substantially identical.But if infarct occurs for side brain tissue, gray value can decline, thus by with
The intensity contrast of opposite side corresponding region can carry out infarct judgement, to determine the region that infarct occurs, to realize target area
The infarct for each target for being included judges.
In addition to the above methods, another illustrative mode is first to extract characteristics of image, such as grayscale information, neighbor pixel
Grayscale information, gradient information, the gradient information of neighbor pixel etc., the then training pattern by way of supervised learning,
It can be used for judging that infarct judges.
Under normal circumstances, when cerebral infarction occurs, only infarct occurs for side, if infarct, brain tissue occur for two sides
It may be dead.Therefore, if the infarct judging result of target area is that infarct occurs for left and right brain, the stalk of certain side
Dead recognition result, it may be possible to caused by the noises such as image artifacts.For these reasons, if infarct judging result is that left and right brain is sent out
Raw infarct needs further to judge that infarct occurs for which specific side, to correct above-mentioned infarct judging result.Specific timing, can be with
Judged using based on grey scale change.In the target area, the combination of the ratio of gray scale or difference or ratio and difference
Numerical value it is smaller, confidence level is higher, thus compare target area in, the ratio or difference or ratio of gray scale and the knot of difference
The minimum value of the numerical value of conjunction, it is believed that the lesser side of numerical value, that is, the high side of confidence level is judged as infarct, the other side is judged as
The infarct judging result of aforementioned output is corrected by non-infarct according to the confidence level result.
Step S105: the infarct judging result based on target area, measurement core Infarction volume.
Based on the infarct judging result of target area in abovementioned steps S103, need further to judge the target area of infarct
In each pixel infarct state.Specifically, gray threshold is set, determines the pixel that cerebral infarction occurs in each target area
Number.Then according to the picture that cerebral infarction occurs in the pixel spacing of CT images, the thickness of CT images and each target area
The number of vegetarian refreshments calculates the volume that cerebral infarction occurs in each target area, the core Infarction volume in all target areas
Measurement result of the summation as core Infarction volume.
The method provided using this specification embodiment carries out the measurement of core Infarction volume to head CT images data,
Can quick, accurate measurement core Infarction volume, exclude or reduce subjective factor interference, as area of computer aided side
Method provides objective basis for medical researches such as cerebral apoplexies.
In order to further illustrate the measurement method of the core Infarction volume based on head CT images, Fig. 4 is that this specification is real
The flow chart for applying a kind of measurement method of core Infarction volume based on head CT images of example offer, recycles core infarct in the past
Measurement process is described in detail for cubing.
Step S401: head CT image data to be processed is obtained.
Since in CT images, Pixel Dimensions are different, corresponding number is different.As Pixel Dimensions can for 1.0mm*1.0mm,
0.5mm*0.5mm etc., corresponding number can be 256*256 or 512*512.Obviously, Pixel Dimensions are smaller, and number is got over
More, spatial resolution is higher.Since CT images are level images, in order to show entire organ, multiple continuous level shadows are needed
Picture, therefore head CT images to be processed are multiframe image.
Step S403: the target area of left and right brain is extracted.
For the target area for extracting left and right brain, need to click through to each pixel in multiframe head CT images to be processed
Line number word labeling judges which region that the pixel belongs in the target area of left and right brain.At one of this specification
In embodiment, with 0 represent background, 1 represent left side M1,2 represents left side M2,3 represents on the left of M3,4 represent on the left of head of caudate nucleus, 5
Represent left side island band, 6 represents left side posterior limb of internal capsule, 7 represents left side lenticular nucleus, 8 represents on the right side of M1,9 represent on the right side of M2,10 representatives
Right side M3,11 represent right caudate nucleus head, 12 represent right side island band, 13 represents right side posterior limb of internal capsule, 14 represent on the right side of lenticular nucleus,
15 represent left side M4,16 represents left side M5,17 represents left side M6,18 represents on the right side of M4,19 represent on the right side of M5,20 represent on the right side of
M6.Multiframe head CT image data to be processed can export one with digital label by neural network or other algorithms
Three-dimensional matrice, the value in matrix is 0-20, and wherein 1-20 represents target area.Such as the shadow that input data is 30*512*512
Picture represents 30 frame CT images data, and every frame CT images data are 512*512, then can export the two-dimensional matrix with digital label,
The label is the three-dimensional matrice of 30*512*512, and the three-dimensional matrice is corresponded with head CT image data respectively.
Step S405: infarct judgement is carried out to each target area that left and right brain target area includes.
The target area that abovementioned steps S403 is extracted needs further progress infarct to judge.Since CT value is measurement CT shadow
The index of relative density as in, unit are Heng Shi unit (Hounsfield unit, HU), and the CT value of tissue, which has, fixes
Range, as the CT value of water is 0, the CT value of blood is 60-100Hu, the CT value of grey matter is 30-35Hu, the CT value of white matter is 20-
25Hu, muscle CT value be 20-40Hu, bone CT value > 1000Hu.In CT images, the corresponding gray scale of a CT value.By
In the symmetry of human brain, at nominal conditions, the CT value mean value of left and right brain symmetric position is substantially identical, that is, gray value base
It originally is identical.But if side brain tissue infarct, gray value can decline, therefore by the intensity contrast with opposite side corresponding region,
Infarct judgement can be carried out, to determine the region that infarct occurs.
Based on the digital label of step S403 output, the same target region of left and right brain in image data is positioned, traverses mesh
The all pixels point in region is marked, while in order to exclude the interference such as noise, given threshold thre0 and thre1 select gray value to be situated between
In the pixel of thre0 and thre1, thre0 can be set to 30Hu, and thre1 is set as 50Hu.Meet each picture of above-mentioned condition
Average value is calculated after the gray value summation of vegetarian refreshments, as the average gray value of target area, by the gray value of side and opposite side ash
Angle value is compared, thus judge target area whether infarct.
In one embodiment of this specification, using the method for extracting image feature, infarct judgement is carried out.Specifically,
Extract image feature, as grayscale information, the grayscale information of neighbor pixel, gradient information, neighbor pixel gradient information, and
Handmarking is carried out, is trained in the way of the supervised learnings such as SVM, random forest.The model of application training, in image
Each pixel extract image feature, obtain the infarct judging result of each pixel.Specifically, it using this method, is exported
Infarct judging result is the mode of two classification, i.e., 0 indicates non-infarct, and 1 indicates infarct.
Fig. 5 is a kind of schematic diagram for infarct judgement that this specification embodiment provides.Specifically, can using differential technique,
Ratio method, ratio are judged that other infarct judgment methods based on grey scale change are accordingly to be regarded as and this methods of in conjunction with difference
Invent same method.Such as judge lenticular nucleus whether infarct, position image data in left side lenticular nucleus point (digital label 7)
With the point (digital label 14) of right side lenticular nucleus, all pixels point corresponding to digital label 7 and digital label 14 is traversed, point
It Shai Xuan not pixel of the gray value between 30Hu-50Hu in digital label 7 and digital label 14.Utilize the above-mentioned number filtered out
The pixel of label 7 and digital label 14 calculates the average value of the gray value of the pixel of digital label 7, as left side beans shape
The gray value of core, the average value for calculating the gray value of the pixel of digital label 14 will be left as the gray value of right side lenticular nucleus
The gray value of lenticular nucleus is compared on the right side of the sum of the grayscale values of side lenticular nucleus, thus judge lenticular nucleus whether infarct and any side beans shape
Core infarct.The calculation method of other average gray values, after the gray value of each pixel such as to be carried out to certain operation conversion, such as
Gray scale stretching calculates average gray value, is accordingly to be regarded as the same method with the present invention.
In one embodiment of this specification, using differential technique carry out infarct judgement, it is believed that left and right brain two sides it is identical
In target area, when the difference of side gray value and opposite side gray value is less than preset threshold diff, it is believed that in head CT images
Infarct occurs for corresponding region, and the relatively low side of gray value is infarct side.In general, it is believed that threshold value diff is -2.Such as in Fig. 5
Embodiment in, the difference of the left side area M2 gray value and the area right side M2 gray value is -2.7, is less than threshold value -2, therefore, it is considered that on a left side
Infarct occurs for the side area M2.Using same method, left side M3 and right side M4 infarct are judged.
In one embodiment of this specification, using ratio method carry out infarct judgement, it is believed that left and right brain two sides it is identical
In target area, when the ratio of side gray value and opposite side gray value is less than preset threshold ratio, it is believed that in head CT images
Infarct occurs for corresponding region, and the relatively low side of gray value is infarct side.In general, it is believed that threshold value ratio is 0.96.Such as exist
In the embodiment of Fig. 5, the ratio of left side lenticular nucleus and right side lenticular nucleus is 0.99, is greater than 0.96, it is believed that lenticular nucleus does not have infarct,
It is consistent with the judging result of differential technique.The ratio of the gray value of the gray value and area right side M2 in the left side area M2 is 0.92, is less than
0.96, it is believed that infarct occurs for the left side area M2.Using same method, judge that infarct occurs for the left side area M3.
In one embodiment of this specification, using ratio in conjunction with differential technique, infarct judgement is carried out.Think infarct according to
According to being ratio less than 0.96, and difference is less than -2.In the 5 embodiment of figure 5, using this method to the target in head CT images
Region carries out infarct judgement, left side M2, M3 and right side M4 infarct.Infarct judgment basis may be ratio less than 0.96, or
Difference is less than -2.In the 5 embodiment of figure 5, infarct judgement, the left side area M2, M3 infarct are carried out using this method.
The tissue CT value of general new hair infarct is not less than 20Hu, it is assumed that the non-infarct of other side brain tissue, average gray value
In 40Hu or so, two sides ratio r atio will not be less than 0.5, and the absolute value of difference diff is not more than 20.The one of this specification
In a embodiment, c=(ratio-0.5)/0.7+ (diff+20)/50 can also be used, to the target areas of head CT images into
Row infarct judgement, if the value is less than or equal to 1, then it is assumed that infarct occurs for the target area of the side brain tissue, is greater than 1, then non-infarct.
In the 5 embodiment of figure 5, the difference in the area right side M4 is -1.6, and ratio 0.95 is calculated: (0.95- using the above method
0.5)/0.7+ (- 1.6+20)/50=1.02 > 1, therefore, it is considered that infarct does not occur for the area M4.Judged using this method, left side
The area M2, M3 infarct.
Using the method for the extraction target area that this specification embodiment provides, since each target area has centainly
Thickness, and the thickness of CT images is smaller, therefore each target area included by the target area extracted is present at least at one
In frame CT images.The target area to each frame is needed to sentence when carrying out infarct judgement using infarct judgment method above-mentioned
It is disconnected.For the same target area being present at least two frame CT images, it is likely to appear in a frame or multiframe CT images
Middle infarct, and infarct does not occur in other frames or multiframe CT images, as long as that is, some target area is sent out in a frame
Raw infarct, then it is assumed that infarct occurs for the target area.Specifically, the target area of extraction, such as lenticular nucleus are located at the tenth frame
In CT images and the 11st frame CT images, using aforementioned infarct judging result, left side lenticular nucleus infarct in the CT images of the tenth frame,
And the left side non-infarct of lenticular nucleus in the 11st frame CT images, then it is assumed that left side lenticular nucleus infarct.
After multiframe head CT image data to be processed completes infarct judgement, the infarct judgement knot of 20 target areas is exported
Fruit, for the subsequent measurement for carrying out core Infarction volume.Aforementioned infarct judging result is an array, which includes three
Element, first element of array are the number of Boolean type, and 0 represents non-infarct, and 1 represents infarct；Second element is floating-point
Number, numerical value are the side average gray value divided by opposite side average gray value；Third element is floating number, and numerical value is the average ash in the side
Angle value subtracts opposite side average gray value.If the 1st output is [0,1,0], wherein 0 indicates that the left side area M1 does not have infarct, left side M1
The average gray value in area is 1 divided by the average gray value in the right side area M1, and the average gray value in the left side area M1 subtracts the right side area M1
Average gray value is 0.
Step S407: denoising is carried out to the infarct pixel in the target area of left and right brain.
Abovementioned steps S405, which is realized, classifies to each pixel in target area, the pixel in these regions
In it is possible that isolated infarct pixel, these isolated infarct pixels may be due to the quality of image, equipment etc. because
Caused by element, belong to interference noise, it is therefore desirable to these noise removes, to avoid interference to subsequent measurement core Infarction volume
Influence.
The infarct judging result of the isolated pixel of above-mentioned removal, then need to be corrected.As step S405 infarct is sentenced
Disconnected result output is [1,1], using the denoising method of regional connectivity, it is found that the pixel is isolated pixel, therefore, it is considered that
Infarct does not occur for the pixel, so the infarct judging result in above-mentioned steps S405 is corrected to [1,0].
Step S409: the further judgement to the infarct judging result of the target area of left and right brain.
The infarct judging result of 20 target areas of abovementioned steps S407 output, it is understood that there may be bilateral has target area
There is the case where infarct.Due under normal circumstances, it should which only infarct, therefore, feelings of bilateral infarct if it exists occur for side
Condition needs further to judge that infarct occurs for which specific side.The probability of infarct can occur according to the lesser side of gray-value variation
It is higher, judged.In the target area of left and right brain, the number of the combination of the ratio or difference or ratio and difference of gray scale
It is worth smaller, confidence level is higher, therefore compares in the target area of left and right brain, the ratio or difference or ratio and difference of gray scale
Combination numerical value minimum value, it is believed that the lesser side of numerical value, that is, the high side of confidence level is infarct, the other side does not obstruct
Extremely, the infarct judging result that abovementioned steps S407 is exported is corrected.
According to method described in step S407, infarct is carried out to embodiment shown in fig. 5 using ratio method or differential technique and is sentenced
Disconnected, the infarct judging result of the output of target area 1-20 is as follows: 1:[0, and 0.99, -0.5], 2:[1,0.92, -2.7], 3:[1,
0.93, -2.4], 4:[0,1,0], 5:[0,1.01,0.2] and, 6:[0,1.03,0.9], 7:[0,0.99, -0.5], 8:[0,1.02,
0.5], 9:[0,1.09,2.7], 10:[0,1.08,2.4] and, 11:[0,1,0], 12:[0,0.99, -0.2], 13:[0,0.97, -
0.9], 14:[0,1.01,0.5], 15:[0,1.05,1.6] and, 16:[0,1,0], 17:[0,1,0] and, 18:[1,0.95, -1.6],
19:[0,1,0], 20:[0,1,0].
In one embodiment of the invention, using the confidence level method based on ratio to the infarct judging result of above-mentioned output
Further judged, the minimum ratio of left side target area is 0.92, and the minimum ratio of right side target area is 0.95.Due to
The small side confidence level of ratio is high, and infarct, therefore left side infarct occurs.Further, by the infarct judging result of above-mentioned output
It is corrected, by 18:[1,0.95, -1.6] it is corrected to 18:[0,0.95, -1.6], other infarct judging results are constant, will correct
The infarct judging result of the target area of left and right brain afterwards is as new infarct judging result, for subsequent core Infarction volume
Measurement.
In one embodiment of the invention, using the confidence level method based on difference to the infarct judging result of above-mentioned output
Further judged, the minimal difference of left side target area is -2.7, and the minimal difference of right side target area is -1.6.Due to
The small side confidence level of ratio is high, generation infarct, and -2.7 < -1.6, therefore left side infarct.Further, by the stalk of above-mentioned output
Dead judging result is corrected, by 18:[1,0.95, -1.6] it is corrected to 18:[0,0.95, -1.6], other infarct judging results
Constant, using the infarct judging result after correction as new infarct judging result, for subsequent core Infarction volume measurement.
In one embodiment of the invention, the confidence level method combined using ratio and difference, to the infarct of above-mentioned output
Judging result is further judged.This method utilizes function c=(ratio-0.5)/0.7+ (diff+20)/50, to aforementioned defeated
Infarct judging result out carries out the calculating of c value.Since c value is lower, the probability that infarct occurs is higher, i.e., confidence level is higher, compares
Infarct occurs for the minimum c value of two sides, the low side of minimum c value.According to use ratio method or differential technique to embodiment shown in fig. 5
The infarct judging result of output calculates the c value of target area, and the c value of target area 1-20 is successively are as follows: 1.09,0.95,0.97,
1.11、1.13、1.17、1.09、1.15、1.30、1.28、1.11、1.10、1.05、1.14、1.22、1.11、1.11、1.01、
1.11,1.11, according to above-mentioned c value result as it can be seen that the minimum c value in left side is 0.95, the minimum c value on right side is 1.01, due to
0.95 < 1.01, therefore infarct occurs for left side.Further, the infarct judging result of above-mentioned output is corrected, by 18:[1,
0.95, -1.6] it is corrected to 18:[0,0.95, -1.6], other infarct judging results are constant, by the infarct judging result after correction
Measurement as new infarct judging result, for subsequent core Infarction volume.
It, can if the infarct judging result of step S407 output occurs infarct for side, then do not need further to be judged
It is directly used in the measurement of subsequent core Infarction volume.
Step S411: the infarct judging result of the target area based on aforementioned left and right brain, measurement core Infarction volume.
The infarct judging result of the target area of left and right brain based on abovementioned steps S409 output, according to preset gray scale threshold
Value determines the number that the pixel of cerebral infarction occurs in target area, according to the pixel spacing of CT images, the thickness of CT images
And the number of the pixel of cerebral infarction occurs in each target area, the volume that cerebral infarction occurs in each target area is calculated,
Measurement result of the summation of core Infarction volume in all target areas as core Infarction volume.
In one embodiment of this specification, judge that infarct, infarct judging result are left side lenticular nucleus using differential technique
Infarct occurs.Assuming that the average gray value of left side lenticular nucleus is h1, it is ash with h2-2 that the average gray value of right side lenticular nucleus, which is h2,
Threshold value is spent, the pixel number for determining that the gray value of pixel in the lenticular nucleus of left side is lower than gray threshold is N.Assuming that head CT shadow
The size of picture is 512*512, pel spacing 0.5*0.5mm, the thickness of head CT images is 5mm, then each pixel
Volume is 0.5*0.5*5=0.125mm3, then the core Infarction volume of lenticular nucleus is N*0.125mm3.Aforementioned infarct judging result
In the Infarction volume of each target area be all made of the method and calculated, the core Infarction volume in all target areas
Summation is the measurement result of core Infarction volume.
In one embodiment of this specification, judge that infarct, infarct judging result are left side lenticular nucleus using ratio method
Infarct occurs.Assuming that the average gray value of left side lenticular nucleus is h1, the average gray value of right side lenticular nucleus is h2, and h1/h2=
S determines that the gray value of pixel in the lenticular nucleus of left side is lower than the pixel of gray threshold then with (h2* (s+1)/2) for gray threshold
Point number is N.Assuming that the size of head CT images is 512*512, pel spacing 0.5*0.5mm, the layer of head CT images
Thickness is 5mm, then the volume of each pixel is 0.5*0.5*5=0.125mm3, then the core Infarction volume of lenticular nucleus is N*
0.125mm3.The Infarction volume of each target area in aforementioned infarct judging result is all made of the method and is calculated, and owns
The summation of core Infarction volume in target area is the measurement result of core Infarction volume.
In one embodiment of this specification, infarct is judged using c=(ratio-0.5)/0.7+ (diff+20)/50,
Infarct judging result is that infarct occurs for left side lenticular nucleus, then the average gray value h1 of left side lenticular nucleus is less than the flat of right side lenticular nucleus
Equal gray value h2, the checkout result according to (ratio-0.5)/0.7+ (diff+20)/50 pairs of left side lenticular nucleus is C, is with h1*C
Gray threshold, the pixel number for determining that the gray value of pixel in the lenticular nucleus of left side is lower than gray threshold is N.Assuming that head CT
The size of image is 512*512, and pel spacing 0.5*0.5mm, the thickness of head CT images is 5mm, then each pixel
Volume be 0.5*0.5*5=0.125mm3, then the core Infarction volume of lenticular nucleus is N*0.125mm3.Aforementioned infarct judgement knot
The Infarction volume of each target area in fruit is all made of the method and is calculated, the core Infarction volume in all target areas
Summation be core Infarction volume measurement result.
In one embodiment of this specification, using the method for extracting image feature, after carrying out infarct judgement, direct root
According to infarct judging result, the number that the pixel of infarct occurs in each target area is calculated.Then according to the pixel of CT images
The number that the pixel of cerebral infarction occurs in point spacing, the thickness of CT images and each target area, calculates each target area
The middle volume that cerebral infarction occurs, measurement knot of the summation of the core Infarction volume in all target areas as core Infarction volume
Fruit.
In one embodiment of this specification, the measurement result of the core Infarction volume of output can be a core stalk
The numerical value of dead volume, the numerical value are that the infarct twice of the target area based on left and right brain judges the result obtained.It is also possible to two
The numerical value of a core Infarction volume respectively indicates the core Infarction volume of left and right brain.If measurement result is expressed as two core stalks
When dead volume, in specific application, the infarct side that can be determined according to cardinal symptom directly exports the core infarct body of corresponding side
Long-pending measurement result, the judgement of infarct twice of the target area without carrying out left and right brain.If known Symptoms are that left side is inclined
Paralysis, it is known that be that infarct has occurred in right brain, can directly export the measurement result of the core Infarction volume of right brain in measurement.
Using the measurement method infarct measurement result ratio obtained for the core Infarction volume that this specification embodiment provides
Relatively comprehensively, the infarct pixel of target area included in all frames is contained.
The measurement method of the core Infarction volume based on head CT images recycled before being previously used for, it can also be used to after follow
Ring.In the specific implementation process, the measurement method of the core Infarction volume based on head CT images recycled after being used for, and is preceding followed
Ring may have some differences, target area pons, bilateral cerebellar, midbrain, bilateral ganglion cerebral and the bilateral cerebral such as recycled afterwards
Artery blood supply area, therefore digital label are as follows: with 0 represent background, 1 represent pons, 2 represent left side cerebellum, 3 represents on the right side of it is small
Brain, 4 represent midbrain, 5 represent left side thalamus, 6 represents right side thalamus, 7 represents on the left of arteria cerebri posterior blood supply area, 8 represent on the right side of
Artery blood supply area.When for Objective extraction, extracted feature is also had any different.Due to the target area of rear circulation, it is not
All areas exist in the brain of left and right, as midbrain, pons be not required to carry out the judgement of bilateral infarct, therefore carry out infarct judgement
When, can also there be certain difference.
Whether the measurement for preceding circulation core Infarction volume or the measurement of rear circulation core Infarction volume, Suo Youji
In the thinking of this specification, or it is based on improved method proposed by the present invention, all belonged to the scope of protection of the present invention.Above content
A kind of measurement method of core Infarction volume based on head CT images is described in detail, corresponding, the application also provides
A kind of measuring system of the core Infarction volume based on head CT images, as shown in fig. 6, specifically including:
Region extraction module extracts target area, wherein the mesh from multiframe head CT image data to be processed
Marking region is the region that measurement core Infarction volume is used in the head CT image data；
Infarct identification module, each target area for being included to the target area carry out infarct judgement, export target
The infarct judging result in region；
Measurement module, the infarct judging result based on the target area, measurement core Infarction volume.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims
It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment
It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable
Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can
With or may be advantageous.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for device,
For electronic equipment, nonvolatile computer storage media embodiment, since it is substantially similar to the method embodiment, so description
It is fairly simple, the relevent part can refer to the partial explaination of embodiments of method.
Device that this specification embodiment provides, electronic equipment, nonvolatile computer storage media with method are corresponding
, therefore, device, electronic equipment, nonvolatile computer storage media also have the Advantageous effect similar with corresponding method
Fruit, since the advantageous effects of method being described in detail above, which is not described herein again corresponding intrument,
The advantageous effects of electronic equipment, nonvolatile computer storage media.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when specification one or more embodiment.
It should be understood by those skilled in the art that, this specification embodiment can provide as method, system or computer program
Product.Therefore, this specification embodiment can be used complete hardware embodiment, complete software embodiment or combine software and hardware
The form of the embodiment of aspect.Moreover, it wherein includes that computer is available that this specification embodiment, which can be used in one or more,
It is real in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form for the computer program product applied.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
In the dress for realizing the function of specifying in one or more flows of the flowchart and/or one or more blocks of the block diagram
It sets.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects,
Component, data structure etc..Specification can also be practiced in a distributed computing environment, in these distributed computing environments,
By executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module can
To be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely this specification embodiments, are not intended to limit this application.For those skilled in the art
For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal
Replacement, improvement etc., should be included within the scope of the claims of this application.
Claims (10)
1. a kind of measurement method of the core Infarction volume based on head CT images characterized by comprising
From multiframe head CT image data to be processed, target area is extracted, wherein the target area is the head CT
The region of measurement core Infarction volume is used in image data；
The each target area for being included to the target area carries out infarct judgement respectively, exports the infarct of the target area
Judging result；
Infarct judging result based on the target area, measurement core Infarction volume.
2. the method as described in claim 1, which is characterized in that it is described from multiframe head CT image data to be processed, it mentions
Target area is taken, is specifically included:
By head CT image data to be processed, input is extracted in model, to each of head CT images data pixel
Digital label classification is carried out, the three-dimensional with digital label corresponding with each pixel in the head CT image data is exported
Matrix, wherein the digital label and the target area correspond.
3. the method as described in claim 1, which is characterized in that each target area for being included to the target area
Infarct judgement is carried out, the infarct judging result of the target area is exported, specifically includes:
Based on each pixel for being included in the target area, infarct judgement is carried out, the infarct of the target area is exported
Judging result.
4. method as claimed in claim 1 or 3, which is characterized in that each target for being included to the target area
Region carries out infarct judgement, exports the infarct judging result of the target area, further comprises:
According to the infarct judging result of the target area, judge whether target area in the brain of left and right has infarct；
If target area has infarct in the brain of left and right, further infarct occurs for which specific side of judgement, corrects the target
The infarct judging result in region, the new infarct judging result as target area.
5. the method as described in claim 1, which is characterized in that the infarct judging result based on the target area is surveyed
Core Infarction volume is measured, is specifically included:
Infarct judging result based on the target area determines the picture that cerebral infarction occurs in each target area that infarct occurs
Vegetarian refreshments number；
Brain occurs according in the pixel spacing of CT images, the thickness of CT images and each target area that cerebral infarction occurs
The pixel number of infarct determines the core Infarction volume that each target area of cerebral infarction occurs, each target area
Core Infarction volume measurement result of the summation as core Infarction volume.
6. a kind of measuring system of the core Infarction volume based on head CT images characterized by comprising
Region extraction module extracts target area, wherein the target area from multiframe head CT image data to be processed
Domain is the region that measurement core Infarction volume is used in the head CT image data；
Infarct identification module, each target area for being included to the target area carry out infarct judgement, export target area
Infarct judging result；
Measurement module, the infarct judging result based on the target area, measurement core Infarction volume.
7. system as claimed in claim 6, which is characterized in that it is described from multiframe head CT image data to be processed, it mentions
Target area is taken, is specifically included:
By multiframe head CT image data to be processed, input is extracted in model, to each of head CT images data picture
Vegetarian refreshments carries out digital label classification, exports and with each pixel in the head CT image data corresponding has digital label
Three-dimensional matrice, wherein the digital label and the target area correspond.
8. system as claimed in claim 6, which is characterized in that each target area for being included to the target area
Infarct judgement is carried out, the infarct judging result of the target area is exported, specifically includes:
Based on each pixel for being included in the target area, infarct judgement is carried out, the infarct of the target area is exported
Judging result.
9. the system as described in claim 6 or 8, which is characterized in that each target for being included to the target area
Region carries out infarct judgement, exports the infarct judging result of the target area, further comprises:
According to the infarct judging result of the target area, judge whether target area in the brain of left and right has infarct；
If target area has infarct in the brain of left and right, further infarct occurs for which specific side of judgement, corrects the target
The infarct judging result in region, the new infarct judging result as target area.
10. system as claimed in claim 6, which is characterized in that the infarct judging result to the target area, measurement
Core Infarction volume, specifically includes:
Infarct judging result based on the target area determines the picture that cerebral infarction occurs in each target area that infarct occurs
The number of vegetarian refreshments；
Brain occurs according in the pixel spacing of CT images, the thickness of CT images and each target area that cerebral infarction occurs
The pixel number of infarct determines the core Infarction volume that each target area of cerebral infarction occurs, each target area
Core Infarction volume measurement result of the summation as core Infarction volume.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811531722.4A CN109671067B (en) | 2018-12-14 | 2018-12-14 | Method and system for measuring core infarction volume based on skull CT image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811531722.4A CN109671067B (en) | 2018-12-14 | 2018-12-14 | Method and system for measuring core infarction volume based on skull CT image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109671067A true CN109671067A (en) | 2019-04-23 |
| CN109671067B CN109671067B (en) | 2021-02-19 |
Family
ID=66143916
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811531722.4A Active CN109671067B (en) | 2018-12-14 | 2018-12-14 | Method and system for measuring core infarction volume based on skull CT image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109671067B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956626A (en) * | 2019-12-09 | 2020-04-03 | 北京推想科技有限公司 | Image-based prognosis evaluation method and device |
| CN114638843A (en) * | 2022-03-18 | 2022-06-17 | 北京安德医智科技有限公司 | Method and device for identifying high-density characteristic image of middle cerebral artery |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1270005A (en) * | 2000-03-21 | 2000-10-18 | 上海医科大学 | Method for automatically measuring area and volume of cerebral infarction |
| CN101756712A (en) * | 2008-11-19 | 2010-06-30 | 李祥 | Research of volume measuring method for CT (Computer Tomography) image intracranial hematoma |
| CN106780492A (en) * | 2017-01-23 | 2017-05-31 | 天津大学 | A kind of extraction method of key frame of CT pelvises image |
-
2018
- 2018-12-14 CN CN201811531722.4A patent/CN109671067B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1270005A (en) * | 2000-03-21 | 2000-10-18 | 上海医科大学 | Method for automatically measuring area and volume of cerebral infarction |
| CN101756712A (en) * | 2008-11-19 | 2010-06-30 | 李祥 | Research of volume measuring method for CT (Computer Tomography) image intracranial hematoma |
| CN106780492A (en) * | 2017-01-23 | 2017-05-31 | 天津大学 | A kind of extraction method of key frame of CT pelvises image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956626A (en) * | 2019-12-09 | 2020-04-03 | 北京推想科技有限公司 | Image-based prognosis evaluation method and device |
| CN110956626B (en) * | 2019-12-09 | 2020-12-18 | 推想医疗科技股份有限公司 | Image-based prognosis evaluation method and device |
| CN114638843A (en) * | 2022-03-18 | 2022-06-17 | 北京安德医智科技有限公司 | Method and device for identifying high-density characteristic image of middle cerebral artery |
| CN114638843B (en) * | 2022-03-18 | 2022-09-06 | 北京安德医智科技有限公司 | Method and device for identifying high-density characteristic image of middle cerebral artery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109671067B (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685123B (en) | Scoring method and system based on skull CT image | |
| CN109886986A (en) | A kind of skin lens image dividing method based on multiple-limb convolutional neural networks | |
| Kim et al. | Fully automatic segmentation of coronary arteries based on deep neural network in intravascular ultrasound images | |
| CN109671066A (en) | A kind of method and system of the cerebral infarction judgement based on head CT images | |
| Hu et al. | Automatic segmentation of intracerebral hemorrhage in CT images using encoder–decoder convolutional neural network | |
| CN109671069A (en) | A kind of measurement method and system of the core Infarction volume based on head CT images | |
| Otsuki et al. | Cine-mr image segmentation for assessment of small bowel motility function using 3d u-net | |
| CN109712122B (en) | Scoring method and system based on skull CT image | |
| CN109671067A (en) | A kind of measurement method and system of the core Infarction volume based on head CT images | |
| Dong et al. | Identifying carotid plaque composition in MRI with convolutional neural networks | |
| Sharma et al. | Brain tumor classification using the modified ResNet50 model based on transfer learning | |
| Chen et al. | Mu-Net: Multi-Path Upsampling Convolution Network for Medical Image Segmentation. | |
| Hu et al. | Axis-guided vessel segmentation using a self-constructing cascade-AdaBoost-SVM classifier | |
| CN112185550A (en) | Typing method, device and equipment | |
| Zhang et al. | Study on TCM tongue image segmentation model based on convolutional neural network fused with superpixel | |
| CN109685843A (en) | A kind of measurement method and system of the core Infarction volume based on head CT images | |
| Öztürk | Convolutional neural networks for medical image processing applications | |
| CN109741339A (en) | A kind of partition method and system | |
| Khani | Medical image segmentation using machine learning | |
| CN109741299A (en) | A kind of error-detecting method and system of the target area based on head CT images | |
| Banerjee et al. | Segmentation of intracranial aneurysm remnant in MRA using dual-attention atrous net | |
| Liu et al. | LSKANet: Long strip kernel attention network for robotic surgical scene segmentation | |
| He et al. | HMOE-Net: hybrid multi-scale object equalization network for intracerebral hemorrhage segmentation in CT Images | |
| CN110517243A (en) | A kind of localization method and system based on DSA image | |
| CN112801996A (en) | Grading method, grading device and grading equipment |
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 |