CN102397070A - Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image - Google Patents
Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image Download PDFInfo
- Publication number
- CN102397070A CN102397070A CN2011100278475A CN201110027847A CN102397070A CN 102397070 A CN102397070 A CN 102397070A CN 2011100278475 A CN2011100278475 A CN 2011100278475A CN 201110027847 A CN201110027847 A CN 201110027847A CN 102397070 A CN102397070 A CN 102397070A
- Authority
- CN
- China
- Prior art keywords
- left ventricle
- center
- automatically
- area
- magnetic resonance
- 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
Images
Landscapes
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a method for fully-automatically segmenting and quantifying the left ventricle of a cardiac magnetic resonance image, comprising the following specific steps of: carrying out automatic denoising and edge enhancement processing on a 4D (four-dimensional) cardiac magnetic resonance image first; automatically and preprimarily determining the center of the left ventricle by utilizing Hough transform, and implementing a region growing technology by taking the center of the left ventricle as a starting seed point to provide a left ventricle full-voxel blood region, and taking the mass center of the left ventricle full-voxel blood region as a center of the left ventricle in the current layer; finding out the center of each layer by using a seed propagation technology; implementing a region growing technology based on an iterative falling threshold by taking the center of the left ventricle of each layer as a starting seed point to automatically provide a left ventricle blood region of each layer, and calculating the area of the left ventricle blood region of each layer; automatically segmenting the top of the left ventricle according to the time-space continuity of the area of the left ventricle and calculating the area of the top of the left ventricle; positioning the bottom of the left ventricle according to the area and shape time-space continuity of the left ventricle, and automatically segmenting the bottom of the left ventricle of the heart by adopting a region growing technology which is constricted by the left ventricle shape with time-space continuity, and calculating the area of the bottom of the left ventricle; and finally, realizing whole segmentation of the left ventricle image. The method disclosed by the invention is of a fully-automatic process without any manual intervene.
Description
Technical field
The invention belongs to the technical field of nuclear magnetic resonance; Concrete be meant a kind of automatic accurate location 4D cardiac magnetic resonance image left ventricle, discern left ventricle bottom and tip position automatically, thereby the method that quantizes whole cardiac magnetic resonance image left ventricle is automatically cut apart in realization.
Background technology
In recent years, heart disease has become the healthy No.1 killer of harm humans.To reduce the deaths from heart disease rate in order improving the quality of living, to have developed a large amount of technology at present and be used for the clinical heart disease of diagnosing perspectively and treat.Become the conventional effective means of current clinical diagnosis heart disease, formulation therapeutic scheme by the accurate assess cardiac disease of medical image technology.Nuclear magnetic resonance have not damaged, soft tissue contrast high, afford a wide field of vision, characteristics such as fault imaging arbitrarily, be widely used in clinical diagnose.Show that according to research the cardiac magnetic resonance imaging precision is high, favorable repeatability, application clinically is more and more wider, has become the golden standard of estimating cardiac function, the variation of evaluation cardiac muscle, detecting myocardial scar and congenital heart disease.Utilization cardiac magnetic resonance image not only can be observed the morphosis of heart, can also estimate the functional status of heart, can help the doctor that cardiac structure and function are made right judgement.
Because left ventricle is the systemic blood circulation pump housing; The left ventricular function index; For example the easypro volume that contracts of left ventricle (comprises EDD and end-systolic volume; Be the basic index of estimating the ventricle morphological function), the whenever rich output of left ventricle (pumps through aortic valve from left ventricle and to get into aortal blood volume; Be the important indicator of reflection heart contraction intensity and speed) and left ventricular ejection fraction (left ventricle stroke volume and end-diastolic volume ratio; Be one of important indicator of assess cardiac pumping function), be the important references of clinical diagnosis heart disease and curative effect, quantify left ventricular function index also just becomes the conventional means of clinical diagnosis and the employing of treatment heart disease.
Cutting apart left ventricle is the prerequisite of quantify left ventricular function index.In the clinical practice of standard, ventricle is cut apart all by experienced doctor's hand drawing.Yet the clinical image data volume is very big, manually cuts apart generally only to diastasis and end-systolic image, and when the myocardial structural of describing as complicacies such as girder flesh, papillary muscless, has subjective differences.This shows that it is very consuming time to cut apart ventricle by hand, inefficiency, labor intensity is big, and is repeatable poor.Therefore, automatical and efficiently accurately cut apart emphasis and the focus that the quantify left ventricle is a current research always.
Up to now, the left ventricle partitioning algorithm developed comparative maturity.These algorithms comprise traditional edge extracting, region growing, and some are based on the method for particular theory, like level set algorithm, genetic algorithm or the like.Yet; These algorithms are nearly all only effective when cutting apart the left ventricle of being surrounded fully by cardiac muscle; Roughly also there is the following problem: left ventricle can not accurately effectively be located automatically, can not discern the bottom and the top of left ventricle automatically, can not extract left ventricle bottom blood volume automatically.That is to say, before cutting apart quantify left ventricular function parameter, still need the manual positioning left ventricle, manually confirm the bottom of left ventricle and the position at top, manual closed bottom left ventricle etc. also need the bad image of some segmentation effects of manual correction simultaneously.In addition, though used some business softwares to replace traditional purely manually cut apart in clinical, owing to receive the limitation of algorithm, still need a large amount of manual functional parameter quantifications that to accomplish left ventricle that get involved.Therefore, still be badly in need of accuracy and repeatability that a kind of reliable and effective full-automatic method further improves heart function parameter clinically, increase work efficiency, alleviate working strength.
Summary of the invention
The objective of the invention is weak point to above-mentioned prior art; A kind of automatic location 4D cardiac magnetic resonance image left ventricle is provided, discerns bottom the left ventricle automatically and tip position, thereby realize automatically cutting apart the method that quantizes cardiac magnetic resonance image left ventricle.
Realization of the present invention is accomplished by following technical scheme:
A kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart is characterized in that the practical implementation step of this method is:
(1) 4D cardiac magnetic resonance image is carried out automatic denoising and edge enhancement process;
(2) tentatively confirm the left ventricle center, be that initial seed point is implemented all plain this regional barycenter of blood regions calculating of region growth technique proposition left ventricle with this center, and it is confirmed as current aspect left ventricle center; Implement seminal propagation technology estimated remaining aspect left ventricle center;
(3) be initial seed points with the left ventricle center of confirming in the step (2), adopt region growth technique to propose the left ventricle blood regions automatically and calculate respective area based on the iteration falling-threshold value to left ventricle middle part aspect;
(4) be initial seed points with the left ventricle center of confirming in the step (2); Left ventricle middle part aspect adopted based on the region growth technique of iteration falling-threshold value extract each tomographic image automatically in the blood regions that is gone up mutually sometimes and calculate respective area; Space and time continuous property according to extracting the region area variation is located the heart left ventricle top automatically, and proofreaies and correct the area at estimation left ventricle top;
(5) according to left ventricle area and shape space and time continuous property location left ventricle bottom, utilize the region growth technique that receives shape constraining to cut apart automatically bottom the heart left ventricle and and carry out from dynamic(al) correction to the zone that is partitioned into;
(6) calculate the left ventricular function index according to the area of left ventricle: comprise left ventricle volume, whenever rich output, the ejection fraction of contracting that relax, and describe full curve.
Preferably, in the said step (1) 4D cardiac magnetic resonance treatment of picture is adopted anisotropic diffusion method.
Preferably, in the said step (2) before proposing all plain blood regions of left ventricle, to left ventricle middle part aspect diastasis and end-systole subtraction image carrying out the Hough conversion.
Preferably; Seminal propagation technology in the said step (2) is to confirm to such an extent that the left ventricle center is the initial seed point of current aspect to close on aspect; Implement region growth technique and extract whole blood voxel left ventricle zone, and this regional barycenter is confirmed as the left ventricle center of current aspect.
Preferably; Adopting in the said step (4) earlier from the left ventricle middle part aspect to carry out the breeding of left ventricle center along the left ventricle top-direction, is that initial seed points is carried out and come to extract automatically each tomographic image in the blood regions that is gone up mutually sometimes based on the region growth technique of iteration falling-threshold value method with this center.
The continuous falling-threshold value of said threshold value can be obtained by following formula:
th＝u
b/r
In the above-mentioned formula, μ
bBe the average of blood regions, r is a variable, and initial value is 1.0, increases progressively with step-length 0.05.
Preferably, working as certain one deck in the said step (4) has part phase place growth district area generation transition, adopts following formula estimated area according to time continuity:
Wherein, s represents the s layer, and the time phase of transition takes place in the p representative, and the q representative is from the nearest time phase that area transition does not take place of p, and ms represents the number of plies of left ventricle intermediate surface.Preferably, transition all takes place in all phase place growth district areas of certain one deck in the said step (4), and the ventricle top is regarded as circular cone or elliptic cone, adopts following formula estimated area according to spatial continuity:
Wherein, s represents the s layer, and the time phase of transition takes place in the p representative.
Preferably; Adopting in the said step (5) earlier from the left ventricle middle part aspect to carry out the breeding of left ventricle center along the left ventricle bottom direction, is that initial seed points is carried out and come to extract automatically each tomographic image in the blood regions that is gone up mutually sometimes based on the region growth technique of iteration falling-threshold value method with this center.
Advantage of the present invention is that the inventive method accurately automatic location of the whole left ventricle part of Rapid Realization cardiac magnetic resonance image is cut apart.With current existing method relatively, the present invention adopts the full automatic quantization method of cutting apart automatically, can accomplish cutting apart and the calculating of the functional parameter of left ventricle left ventricle automatically; Without any need for manual intervention, functional parameter all comprises, the left ventricle volume that contracts that relaxes; Ejection fraction, whenever rich output, full curve; Because former method all is to need the people to cut apart base of heart and top by hand for going, and has very strong subjectivity, the result that different people obtains has very big diversity.
Description of drawings
Fig. 1 is a curve chart, shows the change in volume of extracting the zone;
Fig. 2 is left ventricle middle part original image and a split image (left side is original image, and the right side is a split image) thereof among the embodiment;
Fig. 3 is the area and the variation (left side be spatial continuity, the right side be time continuity) of shape on space-time of left ventricle among the embodiment;
Fig. 4 is Zhang San's dimension curve figure, shows left ventricle area space and time continuous property;
Fig. 5 is a left ventricle top original image and a split image (left side is original image, and the right side is a split image) thereof among the embodiment;
Fig. 6 is left ventricle bottom original image and a split image (left side is original image, and the right side is a split image) thereof among the embodiment;
Fig. 7 is the full curve (phase when transverse axis is left ventricle, the longitudinal axis are left ventricular volumes) of left ventricle among the embodiment.
The specific embodiment
Through embodiment characteristic of the present invention and other correlated characteristic are done further explain below in conjunction with accompanying drawing:
The inventive method accurately automatically quantizes 4D cardiac magnetic resonance image (CMRI) left ventricular function index efficiently, without any need for manual intervention.Following instance step-by-step instructions the inventive method is located left ventricle automatically, confirms left ventricle top and bottom position automatically, cuts apart the specific operation process of quantify left ventricle automatically.
The magnetic resonance imaging data of present embodiment collection is the cardiac magnetic resonance imaging data.Data from GE Signa 1.5T magnetic resonance imaging system, the imaging sequence of being selected for use is the SSFP sequence.Concrete imaging parameters: TR 3.3-4.5ms, TE 1.1-2.0ms, flip angle 55-60; Matrix size 192 * 192 256 * 256, image size 256 * 256 receives bandwidth 125kHz; The visual field (FOV) 290-400 * 240-360; Bed thickness and interlamellar spacing are respectively 6-8mm and 2-4mm (10mm altogether), and the left ventricle of each data has the 6-10 layer, phase during the 20-28 heart.
(1) iteration falling-threshold value method is extracted blood
At first begin execution area growth technology and extract the whole blood voxel, calculate whole blood sample mean value of areas and standard deviation (μ from seed points
bAnd σ
b).Then with μ
bFor extracting a series of growth districts, a series of region growth technique based on continuous falling-threshold value (th) of initial threshold implementation break through away from cardiac muscle suddenly up to this zone.Falling-threshold value can be by μ continuously
bObtain with a variable, specifically adopt following formula:
th＝u
b/r
①
In the above-mentioned formula, r is a variable, and initial value is 1.0, increases progressively with step-length 0.05.Accompanying drawing 1 (a) has been described to extract regional area from the angle of region area and has been changed until sudden change along with the threshold value of continuous reduction is continuous.Transverse axis is represented variable r, and the longitudinal axis is represented area (representing with the voxel number).According to threshold value and the σ before the volume sudden change
bCan find one just when being used to cut apart left ventricle.Fig. 2 has shown that left ventricle middle part original image reaches the split image that obtains based on continuous falling-threshold value method among the embodiment.
(2) cardiac magnetic resonance image left ventricle center breeding
The part at the heart middle part is that starting point is carried out region growth technique to current aspect with adjacent layer left ventricle center, the barycenter of growth district is confirmed as the center of current aspect left ventricle; Top and bottom at heart are the center of current aspect left ventricle with the center that is close to the aspect left ventricle separately.
(3) the left ventricle top is cut apart and the area estimation
The left ventricle area is a continually varying in time and space.Fig. 3 has explained the area and the seriality of shape on space-time of left ventricle.Fig. 4 is with the clear space and time continuous property of left ventricle area numerical tabular among the embodiment.As shown in Figure 4, the number of phases when y axle is represented, the number of data layers that the representative of x axle collects, the z axle is represented the growth district area.Phase when this embodiment one has 12 layers 20,12 batten curves are represented 12 layers among the figure, the growth district area variation of phase at any time that on behalf of each layer, each bar extract.Area change space and time continuous property according to extracting the zone is cut apart the heart top automatically, and estimates the area of these positions according to the situation of top generation transition.Two kinds of situation are arranged:
(a) certain one deck has part phase place growth district area generation transition, adopts following formula estimated area according to time continuity:
②
Wherein, s represents the s layer, and the time phase of transition takes place in the p representative, and the q representative is from the nearest time phase that area transition does not take place of p, and ms represents the number of plies of left ventricle intermediate surface.
(b) transition all takes place in all phase place growth district areas of certain one deck, and the ventricle top is regarded as circular cone or ellipse is sewed, and adopts following formula estimated area according to spatial continuity:
③
Here, s represents the s layer, and the time phase of transition takes place in the p representative.
Fig. 5 has shown left ventricle top original image among the embodiment and the split image that obtains according to space and time continuous property.
(4) location, left ventricle bottom and estimation
Change the bottom position that the time space seriality is confirmed left ventricle according to the area change of extracting the zone and center of gravity.And utilize the region growth technique that receives shape constraining to cut apart automatically bottom the heart left ventricle and and proofread and correct the zone that is partitioned into.Fig. 6 has shown left ventricle bottom original image among the embodiment and the split image that obtains according to space and time continuous property.
(5) the full curve of left ventricle
Accomplish automatically cut apart left ventricle after, can quantize the left ventricular function parameter according to the area that is partitioned into the zone, comprise left ventricle volume, whenever rich output, the ejection fraction of contracting that relax, and describe full curve.Fig. 7 has described the full curve of embodiment left ventricle, phase when transverse axis is, and the longitudinal axis is a left ventricular mass.
Above-described only is preferred implementation of the present invention; Should be pointed out that for the person of ordinary skill of the art, under the prerequisite that does not break away from the invention design; Can also make some similar distortion and improvement, these also should be regarded as within protection scope of the present invention.
Claims (8)
1. automatically cut apart the method that quantizes cardiac magnetic resonance image left ventricle for one kind, it is characterized in that the practical implementation step of this method is:
(1) 4D cardiac magnetic resonance image is carried out automatic denoising and edge enhancement process;
(2) tentatively confirm the left ventricle center, be that initial seed point is implemented all plain this regional barycenter of blood regions calculating of region growth technique proposition left ventricle with this center, and it is confirmed as current aspect left ventricle center; Implement seminal propagation technology estimated remaining aspect left ventricle center;
(3) be initial seed points with the left ventricle center of confirming in the step (2), adopt region growth technique to propose the left ventricle blood regions automatically and calculate respective area based on the iteration falling-threshold value to left ventricle middle part aspect;
(4) be initial seed points with the left ventricle center of confirming in the step (2); Left ventricle middle part aspect adopted based on the region growth technique of iteration falling-threshold value extract each tomographic image automatically in the blood regions that is gone up mutually sometimes and calculate respective area; Space and time continuous property according to extracting the region area variation is located the heart left ventricle top automatically, and proofreaies and correct the area at estimation left ventricle top;
(5) according to left ventricle area and shape space and time continuous property location left ventricle bottom, utilize the region growth technique that receives shape constraining to cut apart automatically bottom the heart left ventricle and and carry out from dynamic(al) correction to the zone that is partitioned into;
(6) calculate the left ventricular function index according to the area of left ventricle: comprise left ventricle volume, whenever rich output, the ejection fraction of contracting that relax, and describe full curve.
2. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 1 is characterized in that, in the said step (1) 4D cardiac magnetic resonance treatment of picture is adopted anisotropic diffusion method.
3. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 2; It is characterized in that; In the said step (2) before proposing all plain blood regions of left ventricle, to left ventricle middle part aspect diastasis and end-systole subtraction image carrying out the Hough conversion.
4. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 2; It is characterized in that; Seminal propagation technology in the said step (2) is to confirm to such an extent that the left ventricle center is the initial seed point of current aspect to close on aspect; Implement region growth technique and extract whole blood voxel left ventricle zone, and this regional barycenter is confirmed as the left ventricle center of current aspect.
5. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 4; It is characterized in that; Adopting in the said step (4) earlier from the left ventricle middle part aspect to carry out the breeding of left ventricle center along the left ventricle top-direction, is that initial seed points is carried out and come to extract automatically each tomographic image in the blood regions that is gone up mutually sometimes based on the region growth technique of iteration falling-threshold value method with this center.
The continuous falling-threshold value of said threshold value can be obtained by following formula:
th＝u
b/r
In the above-mentioned formula, μ
bBe the average of blood regions, r is a variable, and initial value is 1.0, increases progressively with step-length 0.05.
6. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 5; It is characterized in that; Working as certain one deck in the said step (4) has part phase place growth district area generation transition, adopts following formula estimated area according to time continuity:
Wherein, s represents the s layer, and the time phase of transition takes place in the p representative, and the q representative is from the nearest time phase that area transition does not take place of p, and ms represents the number of plies of left ventricle intermediate surface.
7. a kind of method that quantizes cardiac magnetic resonance image left ventricle of automatically cutting apart according to claim 5; It is characterized in that; Transition all takes place in all phase place growth district areas of certain one deck in the said step (4); The ventricle top is regarded as circular cone or elliptic cone, adopts following formula estimated area according to spatial continuity:
Wherein, s represents the s layer, and the time phase of transition takes place in the p representative.
8. according to claim 6 or 7 described a kind of methods that quantize cardiac magnetic resonance image left ventricle of automatically cutting apart; It is characterized in that; Adopting in the said step (5) earlier from the left ventricle middle part aspect to carry out the breeding of left ventricle center along the left ventricle bottom direction, is that initial seed points is carried out and come to extract automatically each tomographic image in the blood regions that is gone up mutually sometimes based on the region growth technique of iteration falling-threshold value method with this center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110027847 CN102397070B (en) | 2011-01-26 | 2011-01-26 | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110027847 CN102397070B (en) | 2011-01-26 | 2011-01-26 | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102397070A true CN102397070A (en) | 2012-04-04 |
| CN102397070B CN102397070B (en) | 2013-06-19 |
Family
ID=45879982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110027847 Expired - Fee Related CN102397070B (en) | 2011-01-26 | 2011-01-26 | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102397070B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400398A (en) * | 2013-07-31 | 2013-11-20 | 东北大学 | Automatic heart locating method based on chest locating film |
| CN103810688A (en) * | 2012-11-06 | 2014-05-21 | 上海联影医疗科技有限公司 | Automatic left ventricle block dividing method |
| CN103854287A (en) * | 2014-03-11 | 2014-06-11 | 深圳市旭东数字医学影像技术有限公司 | Meniscus segmentation method and device based on magnetic resonance image |
| CN103908279A (en) * | 2013-01-07 | 2014-07-09 | 上海联影医疗科技有限公司 | Method for identifying heart status time phase |
| CN104200465A (en) * | 2014-08-20 | 2014-12-10 | 沈阳东软医疗系统有限公司 | Segmentation method and device for heart three-dimensional image |
| CN104220008A (en) * | 2012-03-09 | 2014-12-17 | 学校法人金泽医科大学 | Manufacturing method for heart correction net |
| CN105741310A (en) * | 2016-03-21 | 2016-07-06 | 东北大学 | Heart's left ventricle image segmentation system and method |
| CN106709930A (en) * | 2016-12-29 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for cutting volume of interest of three-dimensional medical image |
| US9949643B2 (en) | 2014-10-18 | 2018-04-24 | International Business Machines Corporation | Automatic visualization of regional functional parameters of left ventricle from cardiac imaging |
| CN109741395A (en) * | 2018-12-14 | 2019-05-10 | 北京市商汤科技开发有限公司 | Biventricular quantization method, device, electronic equipment and storage medium |
| CN110322414A (en) * | 2019-07-05 | 2019-10-11 | 北京探境科技有限公司 | A kind of image data based on AI processor quantifies antidote and system online |
| CN110731777A (en) * | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | Left ventricle measuring method and device based on image recognition and computer equipment |
| CN110766693A (en) * | 2018-09-06 | 2020-02-07 | 北京连心医疗科技有限公司 | Method for jointly predicting radiotherapy structure position based on multi-model neural network |
| CN112308845A (en) * | 2020-11-03 | 2021-02-02 | 赛诺威盛科技（北京）有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112881467A (en) * | 2021-03-15 | 2021-06-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size composite material damage imaging and quantitative identification method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006102125A (en) * | 2004-10-05 | 2006-04-20 | Toshiba Corp | Method for identifying region of interest with time in medical image processing apparatus and medical image processing apparatus |
| CN101596111A (en) * | 2008-05-23 | 2009-12-09 | 西门子公司 | In the nuclear magnetic resonance of heart film to the automatic location of left ventricle |
| US20100215238A1 (en) * | 2009-02-23 | 2010-08-26 | Yingli Lu | Method for Automatic Segmentation of Images |
| CN101849240A (en) * | 2007-05-21 | 2010-09-29 | 康奈尔大学 | Method for segmenting objects in images |
-
2011
- 2011-01-26 CN CN 201110027847 patent/CN102397070B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006102125A (en) * | 2004-10-05 | 2006-04-20 | Toshiba Corp | Method for identifying region of interest with time in medical image processing apparatus and medical image processing apparatus |
| CN101849240A (en) * | 2007-05-21 | 2010-09-29 | 康奈尔大学 | Method for segmenting objects in images |
| CN101596111A (en) * | 2008-05-23 | 2009-12-09 | 西门子公司 | In the nuclear magnetic resonance of heart film to the automatic location of left ventricle |
| US20100215238A1 (en) * | 2009-02-23 | 2010-08-26 | Yingli Lu | Method for Automatic Segmentation of Images |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104220008A (en) * | 2012-03-09 | 2014-12-17 | 学校法人金泽医科大学 | Manufacturing method for heart correction net |
| CN103810688A (en) * | 2012-11-06 | 2014-05-21 | 上海联影医疗科技有限公司 | Automatic left ventricle block dividing method |
| CN103810688B (en) * | 2012-11-06 | 2017-08-11 | 上海联影医疗科技有限公司 | A kind of automatic Partitioning method of left ventricle |
| CN103908279A (en) * | 2013-01-07 | 2014-07-09 | 上海联影医疗科技有限公司 | Method for identifying heart status time phase |
| CN103908279B (en) * | 2013-01-07 | 2017-07-28 | 上海联影医疗科技有限公司 | A kind of recognition methods of heart state time phase |
| CN103400398B (en) * | 2013-07-31 | 2015-11-04 | 东北大学 | A kind of heart automatic positioning method based on chest spacer |
| CN103400398A (en) * | 2013-07-31 | 2013-11-20 | 东北大学 | Automatic heart locating method based on chest locating film |
| CN103854287B (en) * | 2014-03-11 | 2017-06-06 | 深圳市旭东数字医学影像技术有限公司 | The method and its device of the meniscus segmentation based on MRI |
| CN103854287A (en) * | 2014-03-11 | 2014-06-11 | 深圳市旭东数字医学影像技术有限公司 | Meniscus segmentation method and device based on magnetic resonance image |
| CN104200465A (en) * | 2014-08-20 | 2014-12-10 | 沈阳东软医疗系统有限公司 | Segmentation method and device for heart three-dimensional image |
| CN104200465B (en) * | 2014-08-20 | 2017-08-25 | 沈阳东软医疗系统有限公司 | The dividing method and device of cardiac three-dimensional image |
| US9795351B2 (en) | 2014-08-20 | 2017-10-24 | Shenyang Neusoft Medical Systems Co., Ltd. | Three-dimensional cardiac image segmentation method and apparatus |
| US9949643B2 (en) | 2014-10-18 | 2018-04-24 | International Business Machines Corporation | Automatic visualization of regional functional parameters of left ventricle from cardiac imaging |
| US9962087B2 (en) | 2014-10-18 | 2018-05-08 | International Business Machines Corporation | Automatic visualization of regional functional parameters of left ventricle from cardiac imaging |
| CN105741310A (en) * | 2016-03-21 | 2016-07-06 | 东北大学 | Heart's left ventricle image segmentation system and method |
| CN105741310B (en) * | 2016-03-21 | 2018-05-04 | 东北大学 | A kind of cardiac left-ventricle image segmenting system and method |
| CN106709930A (en) * | 2016-12-29 | 2017-05-24 | 上海联影医疗科技有限公司 | Method and device for cutting volume of interest of three-dimensional medical image |
| CN106709930B (en) * | 2016-12-29 | 2020-03-31 | 上海联影医疗科技有限公司 | Method and device for segmenting interested volume of three-dimensional medical image |
| US10417767B2 (en) | 2016-12-29 | 2019-09-17 | Shenzhen United Imaging Healthcare Co., Ltd. | Systems and methods for image segmentation |
| CN110766693A (en) * | 2018-09-06 | 2020-02-07 | 北京连心医疗科技有限公司 | Method for jointly predicting radiotherapy structure position based on multi-model neural network |
| CN109741395A (en) * | 2018-12-14 | 2019-05-10 | 北京市商汤科技开发有限公司 | Biventricular quantization method, device, electronic equipment and storage medium |
| CN109741395B (en) * | 2018-12-14 | 2021-07-23 | 北京市商汤科技开发有限公司 | Dual-chamber quantification method and device, electronic equipment and storage medium |
| CN110322414A (en) * | 2019-07-05 | 2019-10-11 | 北京探境科技有限公司 | A kind of image data based on AI processor quantifies antidote and system online |
| CN110322414B (en) * | 2019-07-05 | 2021-08-10 | 北京探境科技有限公司 | Image data online quantitative correction method and system based on AI processor |
| CN110731777A (en) * | 2019-09-16 | 2020-01-31 | 平安科技（深圳）有限公司 | Left ventricle measuring method and device based on image recognition and computer equipment |
| CN112308845A (en) * | 2020-11-03 | 2021-02-02 | 赛诺威盛科技（北京）有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112308845B (en) * | 2020-11-03 | 2021-07-02 | 赛诺威盛科技(北京)股份有限公司 | Left ventricle segmentation method and device and electronic equipment |
| CN112881467A (en) * | 2021-03-15 | 2021-06-01 | 中国空气动力研究与发展中心超高速空气动力研究所 | Large-size composite material damage imaging and quantitative identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102397070B (en) | 2013-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102397070B (en) | Method for fully-automatically segmenting and quantifying left ventricle of cardiac magnetic resonance image | |
| CN110136157B (en) | Three-dimensional carotid artery ultrasound image vessel wall segmentation method based on deep learning | |
| CN104992430B (en) | Full automatic three-dimensional liver segmentation method based on convolutional neural networks | |
| CN111798462B (en) | Automatic delineation method of nasopharyngeal carcinoma radiotherapy target area based on CT image | |
| CN109584254A (en) | A kind of heart left ventricle's dividing method based on the full convolutional neural networks of deep layer | |
| US9875581B2 (en) | Automated 3D reconstruction of the cardiac chambers from MRI or ultrasound | |
| CN102068281B (en) | Processing method for space-occupying lesion ultrasonic images | |
| CN102048550B (en) | Method for automatically generating liver 3D (three-dimensional) image and accurately positioning liver vascular domination region | |
| CN109584244B (en) | Hippocampus segmentation method based on sequence learning | |
| CN111105424A (en) | Lymph node automatic delineation method and device | |
| CN110047082A (en) | Pancreatic Neuroendocrine Tumors automatic division method and system based on deep learning | |
| CN107578413B (en) | Method, apparatus, equipment and the readable storage medium storing program for executing of retinal images layering | |
| CN109272510A (en) | The dividing method of tubular structure in a kind of 3 d medical images | |
| CN110874860B (en) | Target extraction method of symmetrical supervision model based on mixed loss function | |
| CN112270667B (en) | TI-RADS-based integrated deep learning multi-tag identification method | |
| Constantinides et al. | Semi-automated cardiac segmentation on cine magnetic resonance images using GVF-Snake deformable models | |
| Wang et al. | Slic-Seg: slice-by-slice segmentation propagation of the placenta in fetal MRI using one-plane scribbles and online learning | |
| CN109325955B (en) | Retina layering method based on OCT image | |
| CN110738637A (en) | Automatic classification method and system for breast cancer pathological sections | |
| CN110060234B (en) | Method and device for calculating kidney GFR value based on SPECT (single photon emission computed tomography) tomographic image | |
| CN106991660B (en) | The three dimensional ultrasonic image data methods of sampling decomposed based on modified Octree | |
| CN104077754B (en) | Based on symmetric retinal vessel filtering reinforcement method | |
| Cristobal-Huerta et al. | Automated quantification of epicardial adipose tissue in cardiac magnetic resonance imaging | |
| CN104517315A (en) | Method and system for reconstructing bilateral ureters based on interactive region growing method | |
| Li et al. | APCP-NET: Aggregated parallel Cross-Scale pyramid network for CMR segmentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| ASS | Succession or assignment of patent right |
Owner name: JIAXING YIFU SOFTWARE CO., LTD. Free format text: FORMER OWNER: WUXI ZHOUSHI MEDICAL SOFTWARE DEVELOPMENT CO., LTD. Effective date: 20130417 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 214213 WUXI, JIANGSU PROVINCE TO: 314000 JIAXING, ZHEJIANG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20130417 Address after: Jiaxing City, Zhejiang province 314000 South Road No. 1369 Building No. 8 Room 309 Branch Center Applicant after: Wuxi Zhoushi Medical Software Development Co.,Ltd. Applicant after: East China Normal University Address before: 925 room 8, R & D building, Wen Zhuang Road, Yixing Economic Development Zone, Jiangsu 214213, China Applicant before: Wuxi Zhoushi Medical Software Development Co.,Ltd. Applicant before: East China Normal University |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20130619 Termination date: 20140126 |