CN101791231A - Image processing method for automatically judging fetal hydrocephalus from ultrasonic images - Google Patents
Image processing method for automatically judging fetal hydrocephalus from ultrasonic images Download PDFInfo
- Publication number
- CN101791231A CN101791231A CN 201010102205 CN201010102205A CN101791231A CN 101791231 A CN101791231 A CN 101791231A CN 201010102205 CN201010102205 CN 201010102205 CN 201010102205 A CN201010102205 A CN 201010102205A CN 101791231 A CN101791231 A CN 101791231A
- Authority
- CN
- China
- Prior art keywords
- image
- pyramid
- fetal
- histogram
- brain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000001605 fetal effect Effects 0.000 title claims abstract description 41
- 208000003906 hydrocephalus Diseases 0.000 title claims abstract description 21
- 238000003672 processing method Methods 0.000 title claims abstract description 4
- 210000004556 brain Anatomy 0.000 claims abstract description 31
- 210000003625 skull Anatomy 0.000 claims abstract description 18
- 238000000034 method Methods 0.000 claims description 25
- 238000002604 ultrasonography Methods 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 4
- 230000015572 biosynthetic process Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 2
- 239000004744 fabric Substances 0.000 claims description 2
- 238000011002 quantification Methods 0.000 claims description 2
- 210000003140 lateral ventricle Anatomy 0.000 abstract 2
- 210000003754 fetus Anatomy 0.000 description 10
- 238000003745 diagnosis Methods 0.000 description 8
- 208000032170 Congenital Abnormalities Diseases 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 206010061619 Deformity Diseases 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 208000036830 Normal foetus Diseases 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013519 translation Methods 0.000 description 4
- 241000521257 Hydrops Species 0.000 description 3
- 206010030113 Oedema Diseases 0.000 description 3
- 230000007177 brain activity Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000003793 prenatal diagnosis Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 210000004289 cerebral ventricle Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 210000001519 tissue Anatomy 0.000 description 2
- 206010012289 Dementia Diseases 0.000 description 1
- 241000406668 Loxodonta cyclotis Species 0.000 description 1
- 208000005736 Nervous System Malformations Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000007698 birth defect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 210000001638 cerebellum Anatomy 0.000 description 1
- 210000001175 cerebrospinal fluid Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000035606 childbirth Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008175 fetal development Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Clinical applications
- A61B8/0808—Clinical applications for diagnosis of the brain
- A61B8/0816—Clinical applications for diagnosis of the brain using echo-encephalography
Landscapes
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention provides an image processing method for automatically judging fetal hydrocephalus from ultrasonic images, comprising the following steps: firstly extracting skull ellipse of a new fetal brain image on the second plane, lateral ventricle horizontal plane; establishing a space histogram pyramid in the interior zone of the ellipse in the image; respectively calculating the distances among the space histogram pyramids of the given fetal ultrasonic image, the normal fetal brain images in the same gestational week and the image of hydrocephalus in the brain on the lateral ventricle horizontal plane in the same gestational week; and setting a threshold and giving the possibility of fetal hydrocephalus from judgment according to the relationship between the distances among the space histogram pyramids and the threshold.
Description
Technical field
The present invention relates to image processing techniques, especially the hydrocephalic image detecting technique of fetal ultrasound image can be used for that fetal ultrasound cranium brain image is carried out the hydrocephalus deformity and detects automatically.
Background technology
The purpose of prenatal diagnosis is to find fetal anomaly early and take corresponding measure, reduces the birth defect incidence rate.Utilizing ultrasonic image equipment that fetus is carried out prenatal diagnosis is to find whether deformity and investigate the important technical of fetal development situation of fetus, wherein since the cranium brain as the nerve system of human body most important component, the odd-shaped generation of fetal brain or cause death or cause amentia, bring family and social white elephant, so the detection to deformity of brain is primary in the prenatal diagnosis.
The doctor obtaining the basic step of diagnosing after the fetus cranium brain image is:
(1) observes ultrasonoscopy, extract three typical tangent images.These three typical tangent images are respectively first plane-thalamus plane transverse faces, the horizontal cross section of second plane-tricorn, and the 3rd plane-through the cerebellum cross section, as shown in Figure 1;
(2) on different tangent plane pictures, carry out skull shape, a Zhou Daxiao measurement and acquisition related data;
(3) situation of different tangent plane picture skull shapes of observation and cranium brain inner tissue is carried out measurement of correlation, and is diagnosed in conjunction with doctor's clinical experience.
The technology of utilizing image processing techniques that antenatal fetal ultrasound image is analyzed auxiliary diagnosis automatically mainly is confined to the extraction of skull shape and all measurements aspect (Detection of incomplete ellipse in images with strong noise byiterative randomized Hough transform (IRHT) at present, Wei Lu, Jinglu Tan, and exist research that situation carries out auxiliary diagnosis seldom Pattern Recognition 41 (2008) 1268-1279), according to cranium brain interior tissue.
Fetal brain hydrops is a kind of of nervous system malformation, is meant that cerebrospinal fluid is gathered in the ventricular system too much, causes ventricular system expansion and pressure to raise.Because on the horizontal cross section of tricorn, the tricorn size is stable, from 15 weeks to childbirth, the tricorn mean size is about 7.6 ± 0.6mm, therefore the measurement of correlation to tricorn in the horizontal cross section of second plane-tricorn is the important evidence of diagnosis.When surpassing 4 times of standard deviations of average, can think that tricorn enlarges as the tricorn mean size; Cornu occipitale width diagnosable hydrocephalus during greater than 1.5cm is that the cornu occipitale width is the legend of 4.04cm on the horizontal cross section of tricorn as Fig. 2.
The main deficiency of this visual measuring method of doctor is:
(1) the medical image utilization rate is not high, and the image information that those human eyes can't be differentiated can not get abundant application;
(2) the various measurements in the diagnostic imaging process need the doctor to select the measuring position, and dependent diagnostic need rely on doctor's clinical experience, and therefore the individual is subjective.It is possible mistaken diagnosis taking place or fail to pinpoint a disease in diagnosis.
(3) diagnostic imaging work zone a guy's subjectivity, same medical image, different doctors may have different diagnostic results.
Utilize the technology of Flame Image Process that the fetal ultrasound image is analyzed, can avoid the subjectivity of doctor measuring and diagnosis on the one hand, can use for reference the similar diagnosis of existing case database on the other hand and carry out objective analysis and comparison, provide conclusion.
Summary of the invention
The present invention proposes a kind of based on the hydrocephalic method of the automatic differentiation of ultrasonoscopy, and it utilizes the technology of space rectangular histogram pyramid similarity comparison in the Flame Image Process to differentiate the hydrocephalus probability of fetus automatically.The benefit that adopts this method is the information that can make full use of image, especially the gradation of image of fetus normal brain activity image and dissimilar deformity of brain distribution character spatially, convenient relatively judgement objectively, spatial histogram pyramid practical in this method has translation invariant, yardstick is constant and the characteristic of invariable rotary to a certain extent, and possess simply, characteristics fast.
Technical conceive of the present invention is, new fetal brain image is at first extracted brain inside on the horizontal cross section of its second plane-tricorn, then relatively it and normal brain activity inside, hydrocephalus brain inside utilize the difference between the spatial histogram to be judged as the hydrocephalic probability of fetus at the cross section spatial histogram of tricorn level again.
What the present invention proposed is a kind of based on the hydrocephalic method of the automatic differentiation of ultrasonoscopy, it is characterized in that comprising following steps:
(1) the skull ellipse on the horizontal cross section of fetal ultrasound image tricorn is given in the semi-automatic method extraction, obtains elliptical center position and major and minor axis;
(2) be that the spatial histogram pyramid is set up at the center with the elliptical center, the pyramid number of plies is N;
(3) calculate institute's fetal ultrasound image of giving and reach with the distance between the horizontal crosscut viscerocranium of the pregnant all hydrocephalus tricorns brain internal image spatial histogram pyramid respectively with pregnant Zhou Zhengchang fetal brain image;
(4) setting threshold, the relation according to distance between the spatial histogram pyramid and threshold value provides the result.
Described semi-automatic extraction may further comprise the steps for the method for fetal ultrasound image skull ellipse: 3 points are chosen in man-machine interaction more equably on fetal ultrasound image skull; Utilize 3 fitted ellipse selecting; Obtain oval center and major and minor axis length after the match.As shown in Figure 3.
The described number of plies that with the elliptical center is the center is set up is the spatial histogram pyramid of N, and its spatial histogram pyramid form is (N=2) as shown in Figure 4, and wherein the 0th layer of rectangular histogram (Fig. 4 (a)) is made of the rectangular histogram of image in oval; The 4=2 that the 1st layer (Fig. 4 (b)) divided with ellipse long and short shaft by the 0th layer image
2The subimage rectangular histogram of piece almost fan constitutes; The 2nd layer (Fig. 4 (c)) by the 1st layer image continue with the ellipse long and short shaft be the basis add with the transverse angle be that the subimage block rectangular histogram that 45 °, 135 ° straight line is divided constitutes, the subimage block number of the almost fan of division is 8, promptly 2
3The rest may be inferred for the division of other each layers and the rectangular histogram of formation, under the default situation, and N=3.
The spatial histogram pyramid of described normal fetus brain image refers to the spatial histogram pyramid that obtains by the cluster mode from the spatial histogram pyramid data base of the horizontal cross-sectional view picture of normal fetus tricorn.
The spatial histogram pyramid of described hydrocephalus image refers to the spatial histogram pyramid that obtains by the cluster mode from the spatial histogram pyramid data base of the horizontal cross-sectional view picture of fetal brain hydrops tricorn.
Described spatial histogram pyramid distance refer to define in the following manner apart from K
Δ(X, Y):
Wherein, ω
lBe weight, ω
l=2
L-N, (l, X Y) are the χ of the corresponding l layer of spatial histogram of two width of cloth tangent plane picture X and Y to D
2Distance is defined as follows:
Here H
X lAnd H
Y lThe rectangular histogram of representing the corresponding i number of sub images of l layer among X and the Y respectively; K is quantized gray level, and K is total quantification number; D is the piece number of the corresponding subimage of l sheaf space rectangular histogram pyramid, d=2
L+1
Described threshold setting is as described below: set dual threshold; threshold value 1 is a high threshold; high threshold is different threshold value; threshold value 2 is low threshold value; low threshold value is a similar threshold value; be high threshold represent the fetal ultrasound tricorn cross-sectional view picture of giving and the normal or pyramidal diversity of hydrocephalus tricorn cross-sectional view image space rectangular histogram, low threshold value is represented institute's fetal ultrasound tricorn cross section image slices of giving and normally or the pyramidal similarity of hydrocephalus tangent plane tricorn cross-sectional view image space rectangular histogram.When giving fetal ultrasound tricorn cross-sectional view picture with normal fetal ultrasound tricorn cross-sectional view image space rectangular histogram pyramid distance greater than threshold value 1 during simultaneously less than threshold value 2, think that the ultrasonoscopy tangent plane of giving represents that hydrocephalic probability is bigger; When giving fetal ultrasound image and normal fetus brain image rectangular histogram distance less than threshold value 2, the distance between institute's fetal ultrasound image of giving and the hydrocephalus image space rectangular histogram pyramid is greater than threshold value 1, can think be normal picture to image; If institute's fetal ultrasound image of giving and normal fetus brain image rectangular histogram be apart from greater than threshold value 1, the distance between the fetal ultrasound image of giving and the hydrocephalus image space rectangular histogram pyramid less than threshold value 1, can think to be other kind abnormal images to image.
The present invention compared with prior art has following characteristics: the present invention is based upon the fetal ultrasound image is analyzed automatically and handled on the basis, and is less to doctor's subjective dependency; Spatial histogram pyramid according to the present invention structure has translation invariant, yardstick is constant and the characteristic of invariable rotary to a certain extent; The method that the present invention gave has the characteristics of simple and fast.
Description of drawings
Three typical tangent sketch maps of Fig. 1 fetal brain deformity diagnosis
The fetal brain hydrops image that the horizontal cross section of Fig. 2 tricorn shows
Fig. 3 selects the sketch map of 3 fitted ellipse on skull
Fig. 4 three sheaf space rectangular histogram pyramid sketch maps
Fig. 5 is based on the hydrocephalic basic flow sheet of automatic differentiation of ultrasonoscopy
The specific embodiment
The present invention is described in further detail by embodiment below in conjunction with accompanying drawing.
Accompanying drawing 5 is based on the hydrocephalic basic flow sheet of automatic differentiation of ultrasonoscopy.Pyramid number of plies N is preassigned, and the pyramidal number of plies of Xuan Zeing is 3 here.The image that reads in the accompanying drawing 5 obtains the result through after following 5 cell processing.
The 100 pairs of images that read in unit are manually chosen 3 points, obtain the skull ellipse, and obtain elliptical center position and major and minor axis.The oval process that obtains of skull is the process of fitted ellipse curve, and 3 distributions of requirement on elliptic curve manually choosing are relatively even, selected 3 X
1, X
2, X
3Coordinate be coordinate on the image.
Ellipse fitting adopt a kind of directly, be exclusively used in the Least Square Fit Method of elliptic curve, it is to improve (the list of references: Fitzgibbon A that general conic section approximating method obtains, Pilu M, Fisher RB.Direct least square fitting ofellipses.IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999,21 (5): 476～480).General conic section match can be represented with the second order polynomial of an implicit expression:
F(a，x)＝ax＝ax
2+bxy+cy
2+dx+ey+f＝0
Wherein, a=[a b c d e f], x=[x
2Xt y
2X y 1]
T, when satisfying discriminant b
2The conic section of non-ellipse o'clock can be got rid of in-4ac＜0.
Oval direct least square fitting algorithm key step is as follows:
(1) by input pixel point set X
1, X
2, X
3Horizontal vertical coordinate structure design matrix D, D=[x
1x
2X
n]
T
(2) structure sparse matrix S=D
TD;
(3) make constraint matrix
(4) find the solution generalized eigenvalue equation Sa=λ Ca;
(5) obtain unique positive generalized eigenvalue λ
iAnd corresponding generalized eigenvector u
i, finally separate into
(6) elliptic curve of trying to achieve is carried out formal argument, can obtain oval major and minor axis length and elliptical center coordinate.
The fetus tricorn cross-sectional view that 110 pairs of unit are given looks like to set up space pyramid subimage.The process of setting up as shown in Figure 4.At first that ellipse is inner image is as the 0th layer of (Fig. 4 (a)) image; Then the 4=2 that the 0th layer image is divided with ellipse long and short shaft
2The subimage of piece almost fan is as the 1st layer on pyramid (Fig. 4 (b)) subimage, the label of subimage from trunnion axis forward angle less than acute angle, by transverse as the subimage that fan-shaped radius constituted, according to counterclockwise increasing; The 2nd layer (Fig. 4 (c)) by the 1st layer image continue with the ellipse long and short shaft be the basis add with the transverse angle be that the subimage block that 45 °, 135 ° straight line is divided constitutes, the subimage block number of the almost fan of division is 8, promptly 2
3, the index order of subimage is identical with the label principle of the 1st straton image; The rest may be inferred for division of other each layers and label.
Distance between the unit 130 computer memory rectangular histogram pyramids.During Practical Calculation, calculate respectively that the institute's horizontal cross-sectional view of fetal ultrasound tricorn image space rectangular histogram pyramid of giving reaches with distance between the pyramid rectangular histogram of the horizontal cross-sectional view of identical pregnant all brain normal development fetus tricorns image space and the horizontal cross-sectional view of identical pregnant all hydrocephalus fetus tricorns image space pyramid rectangular histogram between distance.The calculated distance formula defines as (1) formula.Weights omega
l=2
L-NMean that weight increases along with the number of plies increases, the difference between expression normal brain activity and the lopsided brain to be embodied in the subimage of segmentation.χ between the rectangular histogram
2Distance between two rectangular histograms of distance expression, be used for here its judge the identification institute horizontal cross-sectional view of fetal ultrasound tricorn of giving as shown spatial histogram pyramid and data base normally with hydrocephalic where the class image is more approaching.Spatial histogram pyramid according to such method construct has following characteristic:
(1) the tangent plane picture rotation has rotational invariance less than 90 °.This is because space pyramid subimage is constructed with the skull ellipse, the benchmark of dividing for the ground floor subimage with the ellipse long and short shaft, therefore, when tangent plane picture rotates less than 90 °, the order of space pyramid ground floor subimage is constant, thereby the rectangular histogram of subimage keeps.Know that from the construction process of space pyramid subimage spatial histogram pyramid at this moment has rotational invariance;
(2) translation invariance.This is that even therefore image generation translation, space pyramid subimage keeps, thereby the spatial histogram pyramid keeps owing to be central configuration with the skull ellipse during space pyramid subimage structure;
(3) flexible invariance.Because tangent plane picture is amplified or dwindle, do not change the shape of skull ellipse, thereby the spatial histogram pyramid keeps.
140 pairs of unit are according to the pyramidal distance of spatial histogram, setting threshold, according to threshold value, determine the hydrocephalus probability of the fetus of giving.Because the gamma characteristic difference of different ultrasonic device images, this threshold value may be different at different ultrasonic devices.In one embodiment of the present of invention, at a class ultrasonic device, threshold value 1 is 0.9, and threshold value 2 is 0.55.
Claims (5)
1. one kind from the ultrasonoscopy image processing method for automatically judging fetal hydrocephalus, it is characterized in that comprising following steps:
(1) the skull ellipse on the horizontal cross section of fetal ultrasound image tricorn is given in the semi-automatic method extraction, obtains elliptical center position and major and minor axis;
(2) be that the spatial histogram pyramid is set up at the center with the elliptical center, the pyramid number of plies is N, and the number of plies can be specified in advance, defaults to 3;
(3) calculate institute's fetal ultrasound image of giving and reach with the distance between the horizontal crosscut viscerocranium of the pregnant all hydrocephalus tricorns brain internal image spatial histogram pyramid respectively with pregnant Zhou Zhengchang fetal brain image;
(4) setting threshold, the relation according to distance between the spatial histogram pyramid and threshold value provides the result.
2. the oval extracting method of the skull on the horizontal cross section of the fetal brain image-side ventricles of the brain according to claim 1 is a semi-automatic method, it is characterized in that: after the image that reads in manually chooses, utilize oval Least Square Fit Method match to obtain at 3.
3. the pyramidal method of formation spatial histogram according to claim 1, it is characterized in that: this rectangular histogram pyramid is that the center is set up with the center of the skull ellipse on the horizontal cross section of the fetal brain image-side ventricles of the brain, and wherein the 0th layer of rectangular histogram is made of the rectangular histogram of image in oval; The 1st layer of 4=2 that divides with ellipse long and short shaft by the 0th layer image
2The subimage rectangular histogram of piece almost fan constitutes; The 2nd layer by the 1st layer image continue with the ellipse long and short shaft be the basis add with the transverse angle be that the subimage block rectangular histogram that 45 °, 135 ° straight line is divided constitutes, the subimage block number of the almost fan of division is 8, promptly 2
3The rest may be inferred for the division of other each layers and the rectangular histogram of formation.
4. the distance between the spatial histogram pyramid according to claim 1 is characterized in that: described spatial histogram pyramid distance be meant definition in the following manner apart from K
Δ(X, Y):
Wherein, ω
lBe weight, ω
l=2
L-N, N is the preassigned pyramid number of plies, (l, X Y) are the χ of the corresponding l layer of spatial histogram of two width of cloth tangent plane picture X and Y to D
2Distance is defined as follows:
Here H
X lAnd H
Y lThe rectangular histogram of representing the corresponding i number of sub images of l layer among X and the Y respectively; K is quantized gray level, and K is total quantification number; D is the piece number of the corresponding subimage of l sheaf space rectangular histogram pyramid, d=2
L+1
5. preset threshold according to claim 1 is characterized in that: the threshold value that sets is a dual threshold, and high threshold is different threshold value, and low threshold value is a similar threshold value.High threshold represent the fetal ultrasound tricorn cross-sectional view picture of giving and the normal or pyramidal diversity of hydrocephalus tricorn cross-sectional view image space rectangular histogram, low threshold value is represented institute's fetal ultrasound tricorn cross section image slices of giving and normally or the pyramidal similarity of hydrocephalus tangent plane tricorn cross-sectional view image space rectangular histogram.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010102205 CN101791231A (en) | 2010-01-28 | 2010-01-28 | Image processing method for automatically judging fetal hydrocephalus from ultrasonic images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010102205 CN101791231A (en) | 2010-01-28 | 2010-01-28 | Image processing method for automatically judging fetal hydrocephalus from ultrasonic images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101791231A true CN101791231A (en) | 2010-08-04 |
Family
ID=42584308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010102205 Pending CN101791231A (en) | 2010-01-28 | 2010-01-28 | Image processing method for automatically judging fetal hydrocephalus from ultrasonic images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101791231A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103477357A (en) * | 2011-04-15 | 2013-12-25 | 麦蒂彼兹有限公司 | System for providing clinical information in real time, method for providing clinical information in real time, and storage medium on which a program performing same is recorded |
| WO2015096352A1 (en) * | 2013-12-23 | 2015-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Contrast-enhanced ultrasound imaging method and method for regional detection and development of imaged picture |
| CN105359186A (en) * | 2013-06-04 | 2016-02-24 | 赫尔实验室有限公司 | A system for detecting an object of interest in a scene |
| CN110322550A (en) * | 2015-02-16 | 2019-10-11 | 深圳迈瑞生物医疗电子股份有限公司 | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data |
| CN110464380A (en) * | 2019-09-12 | 2019-11-19 | 李肯立 | A kind of method that the ultrasound cross-section image of the late pregnancy period fetus of centering carries out quality control |
| CN112155603A (en) * | 2020-09-24 | 2021-01-01 | 广州爱孕记信息科技有限公司 | Weighted value determination method and device for fetal structural features |
| CN114521914A (en) * | 2020-11-23 | 2022-05-24 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic parameter measuring method and ultrasonic parameter measuring system |
-
2010
- 2010-01-28 CN CN 201010102205 patent/CN101791231A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103477357A (en) * | 2011-04-15 | 2013-12-25 | 麦蒂彼兹有限公司 | System for providing clinical information in real time, method for providing clinical information in real time, and storage medium on which a program performing same is recorded |
| CN105359186A (en) * | 2013-06-04 | 2016-02-24 | 赫尔实验室有限公司 | A system for detecting an object of interest in a scene |
| CN105359186B (en) * | 2013-06-04 | 2019-06-25 | 赫尔实验室有限公司 | For detecting system, method and the storage medium of the interested object in scene |
| WO2015096352A1 (en) * | 2013-12-23 | 2015-07-02 | 深圳迈瑞生物医疗电子股份有限公司 | Contrast-enhanced ultrasound imaging method and method for regional detection and development of imaged picture |
| CN110322550A (en) * | 2015-02-16 | 2019-10-11 | 深圳迈瑞生物医疗电子股份有限公司 | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data |
| CN110338844A (en) * | 2015-02-16 | 2019-10-18 | 深圳迈瑞生物医疗电子股份有限公司 | The display processing method and 3-D supersonic imaging method and system of three-dimensional imaging data |
| US11229419B2 (en) | 2015-02-16 | 2022-01-25 | Shenzhen Mindray Bio-Medical Electronics Co., Ltd. | Method for processing 3D image data and 3D ultrasonic imaging method and system |
| CN110338844B (en) * | 2015-02-16 | 2022-04-19 | 深圳迈瑞生物医疗电子股份有限公司 | Three-dimensional imaging data display processing method and three-dimensional ultrasonic imaging method and system |
| CN110464380A (en) * | 2019-09-12 | 2019-11-19 | 李肯立 | A kind of method that the ultrasound cross-section image of the late pregnancy period fetus of centering carries out quality control |
| CN112155603A (en) * | 2020-09-24 | 2021-01-01 | 广州爱孕记信息科技有限公司 | Weighted value determination method and device for fetal structural features |
| CN114521914A (en) * | 2020-11-23 | 2022-05-24 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic parameter measuring method and ultrasonic parameter measuring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101791231A (en) | Image processing method for automatically judging fetal hydrocephalus from ultrasonic images | |
| EP3543880B1 (en) | Stroke diagnosis and prognosis system | |
| US9047394B2 (en) | 3D ultrasound system for intuitive displaying to check abnormality of object and method for operating 3D ultrasound system | |
| JP3928978B1 (en) | Medical image processing apparatus, medical image processing method, and program | |
| EP2744417A1 (en) | A method and system of characterization of carotid plaque | |
| CN105433988A (en) | Target image recognition method and device and ultrasonic equipment thereof | |
| JP2010512218A (en) | Medical imaging system | |
| CN104414636A (en) | Magnetic resonance image based cerebral micro-bleeding computer auxiliary detection system | |
| WO2012105907A1 (en) | Method and apparatus for processing of stroke ct scans | |
| Yaqub et al. | Automatic detection of local fetal brain structures in ultrasound images | |
| Xing et al. | Automatic detection of A‐line in lung ultrasound images using deep learning and image processing | |
| CN103169506A (en) | Ultrasonic diagnosis device and method capable of recognizing liver cancer automatically | |
| KR102503646B1 (en) | Method and Apparatus for Predicting Cerebral Infarction Based on Cerebral Infarction Volume Calculation | |
| US9483705B2 (en) | Image processing device, image processing method, and image processing program | |
| CN114399493B (en) | Automatic detection and display method for ultrasonic craniocerebral abnormal region | |
| KR102447400B1 (en) | Method and Apparatus for Predicting Cerebral Infarction Based on Lesion Area Extraction Using a Deep Learning Model | |
| KR102363221B1 (en) | Diagnosis Method and System of Idiopathic Normal Pressure Hydrocephalus Using Brain Image | |
| Liao et al. | Tracing the deformed midline on brain CT | |
| CN115760851B (en) | Ultrasonic image data processing equipment, system and computer readable storage medium based on machine learning | |
| KR102447401B1 (en) | Method and Apparatus for Predicting Cerebral Infarction Based on Cerebral Infarction Severity | |
| KR102349360B1 (en) | Diagnosis Method and System of Idiopathic Normal Pressure Hydrocephalus Using Imaging Diagnostic Equipment | |
| Susomboon et al. | A co-occurrence texture semi-invariance to direction, distance, and patient size | |
| Wang et al. | Learning to diagnose cirrhosis via combined liver capsule and parenchyma ultrasound image features | |
| CN114418984A (en) | Human tissue symmetry detection and analysis method based on ultrasound | |
| Wang et al. | Multi-scale heat kernel based volumetric morphology signature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Open date: 20100804 |