CN109785296B - CTA image-based three-dimensional spherical index determination method - Google Patents
CTA image-based three-dimensional spherical index determination method Download PDFInfo
- Publication number
- CN109785296B CN109785296B CN201811591084.5A CN201811591084A CN109785296B CN 109785296 B CN109785296 B CN 109785296B CN 201811591084 A CN201811591084 A CN 201811591084A CN 109785296 B CN109785296 B CN 109785296B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- image
- left ventricle
- heart
- cta
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention belongs to the technical field of medical image processing, and discloses a three-dimensional spherical index determination method based on a CTA image; acquiring end diastole CTA data; image enhancement is carried out by adopting nonlinear gray level transformation, and then data are cut in a three-dimensional space, so that the cut image only comprises a left ventricle and a left ventricle cardiac muscle; performing a first correction of heart inclination angle from coronal view; performing a second correction of the heart inclination angle from the cross-sectional view; extracting a left ventricular heart cavity by using a three-dimensional region growing algorithm; automatically acquiring a long axis of the heart; and calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the acquired left ventricle long axis. The invention provides an automatic measurement method for evaluating the centrifugal reconstruction or the integral myocardial reconstruction caused by non-acute myocardial infarction due to overload, and provides accurate and robust quantification results of the ventricular shape change degree.
Description
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to a three-dimensional sphericity index determination method based on a CTA (CT angiography) image.
Background
Currently, the current state of the art commonly used in the industry is as follows: after myocardial infarction, partial myocardial ischemia necrosis, loss of contraction function, uncoordinated contraction movement of left ventricular wall, incapacitation of blood in the left ventricular cavity, increase of residual blood, aggravation of intra-ventricular pressure load, and increase of stress applied to the ventricular wall in the systolic and diastolic phases, so that the whole left ventricle (including an infarct zone and a non-infarct zone) is expanded and the structural morphology of the ventricle is changed, namely, the left ventricle is reconstructed. Left ventricular remodeling is a precursor to left ventricular dysfunction and is closely related to mortality. Ventricular global expansion is an important feature of left ventricular remodeling. Studies have found that extensive ventricular remodeling following revascularization (coronary bypass or revascularization) in the presence of viable myocardium can still prevent recovery of left ventricular function and can negatively impact its long-term prognosis. Therefore, how to simply, noninvasively, objectively and accurately judge whether or not the ventricular remodeling exists and the degree thereof, and quantify the ventricular remodeling, has important roles in the selection of clinical treatment schemes and the judgment of prognosis, and is closely concerned by clinicians. Currently, the imaging technique for non-invasive clinical evaluation of ventricular remodeling is mainly echocardiography. 2D ultrasound imaging is planar imaging and does not truly reflect the three-dimensional changes in the shape of the left ventricle. It analyzes the left ventricular volume by geometrically assuming the shape of the left ventricle, so that the left ventricular volume deviation obtained for the myocardial infarction patient is large and the result repeatability is poor. The real-time three-dimensional echocardiography technology overcomes the technical limitation during two-dimensional ultrasound measurement, can directly quantitatively measure the heart chamber volume of the right ventricle with irregular geometric forms without depending on any geometric assumption, but has smaller depth distance displayed in a real-time display mode, and in some phases of the cardiac cycle, partial structures are cut and leaked due to heart displacement to influence the observation result. Furthermore, breathing or body displacement of the subject during the overall imaging process can have an impact on the composition of the image, resulting in misalignment at the image reconstruction. The imaging method has the advantages that the quality of the image is not ideal, echo drop is easy to be caused to structures such as valve leaflets, oval fossa and the like and tiny lesions, and false images appear. The heart CTA technology has stable imaging and high spatial resolution, can perform three-dimensional reconstruction, and the examination focus is the change of the morphology of the heart and the blood vessels, so that a patient with clinical intervention or tower bridge postoperative efficacy evaluation can select heart CTA for examination. Analysis of current cardiac CTA images is mostly limited to lesions of the coronary arteries, but ignores potentially available and explorable information of cardiac CTA images. The intravenous injection of the contrast agent not only makes the coronary artery region easy to distinguish, but also makes other anatomical structures of the heart clearer and has stronger detail. However, to date, no method for assessing changes in cardiac morphology using cardiac CTA has emerged.
In summary, the problems of the prior art are: the analysis of current cardiac CTA images is mostly limited to lesions of the coronary arteries, and the morphological structure changes of the cardiac muscle and the ventricle are rarely evaluated by using the CTA images, which is the information potentially available and found by the cardiac CTA images. The main reason for this is the lack of automated/semi-automated methods for assessing cardiac morphology using cardiac CTA, which is currently being used clinically for cardiac ultrasound analysis. However, the quality of the heart ultrasonic image is low, the analysis result is unstable, and the observation of the illness state is not facilitated;
difficulty and meaning for solving the technical problems: the individual patients have different disease conditions, and the heart individuation has large difference. Analysis of cardiac images typically requires the clinical experience of a skilled practitioner. The heart morphological structure is evaluated by using images with higher resolution through a small amount of manual participation, so that the labor intensity is reduced, and meanwhile, the information of CTA images is further mined, so that the simultaneous evaluation of coronary artery and cardiac muscle by using one image is possible.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a three-dimensional spherical index determination method based on CTA images.
The invention is realized in such a way that a three-dimensional sphericity index measuring method based on CTA images comprises the following steps: acquiring end diastole CTA data; image enhancement is carried out by adopting nonlinear gray level transformation, and then data are cut in a three-dimensional space, so that the cut image only comprises a left ventricle and a left ventricle cardiac muscle; performing a first correction of heart inclination angle from coronal view; performing a second correction of the heart inclination angle from the cross-sectional view; extracting a left ventricular heart cavity by using a three-dimensional region growing algorithm; automatically acquiring a long axis of the heart; and calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the acquired left ventricle long axis.
Further, the three-dimensional sphericity index determination method based on the CTA image comprises the following steps:
(1) Acquiring end diastole CTA data;
(2) Image enhancement is carried out by adopting nonlinear gray level transformation;
(3) Clipping the data in a three-dimensional space, so that the clipped image only contains the left ventricle and the left ventricle cardiac muscle;
(4) Performing a first correction of heart inclination angle from coronal view;
(5) Performing a second correction of the heart inclination angle from the cross-sectional view;
(6) Extracting the inner cavity of the left ventricle by utilizing a three-dimensional region growing algorithm;
(7) Automatically acquiring a long axis of the heart according to the corrected image;
(8) And calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the obtained heart long axis.
Further, the correction of the heart inclination angle from a certain view angle in the steps (4) and (5) is performed as follows:
(a) Selected view angle ofiThe layer is used as an angle calculation layer;
(b) At the position ofInteractively selecting a rectangular area containing left ventricular myocardium on the binarized image, and dividing out the first regioniMyocardial region on the layer;
(c) Extracting myocardial center line, randomly sampling on the center linenA plurality of points, in this waynPerforming ellipse fitting on the sampling points, and using the fitted ellipse major axis inclination angleαAs a correction angle;
(d) To integrate data in three dimensionsαThe angle is angle corrected.
Further, the boundary of the object is continuously removed by using morphological corrosion operation until only the skeleton is left, wherein the skeleton is the myocardial center line; random sampling on a centerlinenA point of the light-emitting diode is located,the general equation of ellipse is known as +.>The method comprises the steps of carrying out a first treatment on the surface of the According to elliptic equation and least square method principle, solving the objective function +.>The minimum of (a) to determine the parameters A, B, C, D and E. Order theF(A,B,C,D,E)The partial derivative for each parameter is 0, resulting in the following system of equations:
solving this linear system of equations may solve A, B, C, D and E. Elliptical major axis tilt angleAs a correction angle.
Further, the specific steps of extracting the left ventricle inner cavity by the three-dimensional region growing algorithm in the step (6) are as follows:
(a) Interactively selecting a cube containing a left ventricle from the corrected data, and intercepting the cube region;
(b) Seed points are selected in the truncated cube region, three-dimensional region growing is carried out according to a growable voxel inclusion principle, and finally the left ventricle cavity is extracted.
Further, seed points are selected in the truncated cube region, three-dimensional region growth is carried out according to a growable voxel inclusion principle, and a 26 neighborhood gray average value of voxels to be grown is calculatedμComparing the average value with the gray value of the voxel, if the difference is less than or equal to two times of standard deviationσThe voxel is a growable voxel; the mathematical expression of the inclusion principle of the growable voxels is as follows:
wherein->,/> ,NFor the number of neighborhood voxels, hereN=26,/>Is a neighborhood voxel; the available lumen volume from the extracted left ventricle is LVEDV.
Further, in the step (7), the long axis of the left ventricle is automatically acquired according to the corrected image, and the method comprises the following steps:
(a) Extracting the inner cavity contour layer by utilizing a candy operator for the binary image only comprising the inner cavity of the left ventricle;
(b) Perpendicular lines perpendicular to the valve plane are made layer by layer, and the longest perpendicular line after intersecting the apex of the heart among all perpendicular lines is the long axis of the left ventricle.
Further, the step (8) calculates a three-dimensional sphericity index according to the following calculation formula:。
another object of the present invention is to provide a cardiac image processing platform to which the CTA image-based three-dimensional sphericity index determination method is applied.
Another object of the present invention is to provide a cardiac CTA examination system applying the CTA image-based three-dimensional sphericity index determination method.
In summary, the invention has the advantages and positive effects that: according to the CTA image-based three-dimensional spherical index calculation method, the three-dimensional spherical index value is finally calculated through heart inclination angle correction and left ventricle cavity segmentation, and the precedent of evaluation of the heart morphological structure by using the CTA image is opened. The invention realizes a semi-automatic calculation process, has easy control of the process although an interaction process exists, has low manual participation degree and is easy for clinical use.
Drawings
Fig. 1 is a flowchart of a three-dimensional sphericity index measurement method based on a CTA image according to an embodiment of the present invention.
Fig. 2 is a flowchart of a three-dimensional sphericity index measurement method based on CTA images according to an embodiment of the present invention.
Fig. 3 is a schematic view of a heart CTA image obtained from a hospital and an enhanced image result according to an embodiment of the present invention.
Fig. 4 is a schematic view of three-dimensional clipping of an image according to an embodiment of the present invention.
Fig. 5 is a graph showing the segmentation of the left ventricular cavity according to an embodiment of the present invention.
Fig. 6 is a graph showing the three-dimensional sphericity index calculation results of different objects according to an embodiment of the present invention.
Description of the embodiments
The present invention will be described in further detail with reference to the following examples in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Analysis of current cardiac CTA images is mostly limited to lesions of the coronary arteries, whereas potentially available and explorable information of cardiac CTA images is ignored. The heart ultrasound is used as a medical image for analyzing heart morphology in clinical practice, and has the problems of low image quality, unstable analysis result and the like; no method for assessing changes in cardiac morphology using cardiac CTA has emerged. The method evaluates the morphological structure change of the heart by using the CTA image at the end diastole for the first time, and has the difficulty of reducing the human participation as much as possible, and semi-automatically realizing the calculation of the three-dimensional spherical index so as to obtain a stable and reliable quantitative index.
The principle of application of the invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the three-dimensional sphericity index determination method based on CTA image provided by the embodiment of the invention includes the following steps:
s101: acquiring end diastole CTA data; image enhancement is carried out by adopting nonlinear gray level transformation, and then data are cut in a three-dimensional space, so that the cut image only comprises a left ventricle and a left ventricle cardiac muscle;
s102: performing a first correction of heart inclination angle from coronal view; performing a second correction of the heart inclination angle from the cross-sectional view;
s103: extracting a left ventricular heart cavity by using a three-dimensional region growing algorithm; automatically acquiring a long axis of the heart; and calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the acquired left ventricle long axis.
The principle of application of the invention is further described below with reference to the accompanying drawings.
As shown in fig. 2, the three-dimensional sphericity index measurement method based on CTA image provided by the embodiment of the invention specifically includes the following steps:
step one, inputting heart CTA images:
the heart CTA image was obtained from a hospital, and as shown in FIG. 3 (a), the heart CT image was 512X 512, the number of layers was 423 or so, and the pixel resolution was 0.51X 0.51mm 2 ;
And secondly, enhancing the image by adopting nonlinear gray level transformation, so that the contrast between the left ventricular myocardium and the inner cavity is increased, and the images are easier to distinguish. The enhanced image is shown in fig. 3 (b);
cutting the data in a three-dimensional space, so that the cut image only comprises a left ventricle and left ventricle cardiac muscle, and the cutting mode is shown in fig. 4;
step four, performing first correction on the heart inclination angle from the coronary surface view angle;
the first step: selected coronal planeiThe layer is used as an angle calculation layer;
and a second step of: segmentation of the first by thresholdiThe myocardial region on the layer is manually corrected for the region which is not the left ventricular myocardium but is judged to be the left ventricular myocardium by threshold segmentation;
and a third step of: morphological erosion operations are used to continuously remove the boundary of the object until only its skeleton remains, which is the myocardial centerline. Random sampling on a centerlinenEvery point is [ ]) The general equation of ellipse is known as +.>Solving an objective function according to an elliptic equation and a least square method principleThe minimum of (a) to determine the parameters A, B, C, D and E. Order theF (A,B,C,D,E)The partial derivative for each parameter is 0, resulting in the following system of equations:
solving this linear system of equations may solve A, B, C, D and E. Elliptical major axis tilt angleAs a correction angle;
fourth step: layer-by-layer contrast CTA imageαCorrecting the angle;
fifthly, performing second correction on the heart inclination angle from the view angle of the section;
the first step: selected section plane firstkLayer as angle calculation layer
And a second step of: segmentation of the first by thresholdkThe myocardial region on the layer is manually corrected for the region which is not the left ventricular myocardium but is judged to be the left ventricular myocardium by threshold segmentation;
and a third step of: make the following stepsMyocardial center lines were acquired using morphological procedures. Random sampling on a centerlinenEvery point is [ ]). Fitting an elliptic equation according to the sampling points and the least square method, and obtaining the major axis inclination angle according to the obtained elliptic equationβ,As a second heart correction angle;
fourth step: layer-by-layer contrast CTA imageβThe angle is corrected.
Step six, extracting the left ventricle cavity from the angle corrected CTA image by using a three-dimensional region growing algorithm;
the first step: interactively selecting a cube only comprising a left ventricle from the corrected data, and intercepting the cube region;
and a second step of: seed points are selected in the truncated cube region, and three-dimensional region growth is carried out according to the inclusion principle of the growable voxels, namely 26 neighborhood gray average values of the voxels to be grown are calculatedμComparing the average value with the gray value of the voxel, if the difference is less than or equal to two times of standard deviationσThe voxel is a growable voxel. The mathematical expression of the inclusion principle of the growable voxels is as follows:
wherein->,/>,NFor the number of neighborhood voxels, hereN=26,/>Is a neighborhood voxel. The extracted left ventricular cavity is shown in fig. 4. According to the extracted left ventricle, the volume of the available inner cavity is LVEDV;
step seven, automatically acquiring a long axis of the heart according to the corrected image;
the first step: extracting the inner cavity contour layer by utilizing a candy operator for the binary image only comprising the inner cavity of the left ventricle;
and a second step of: making vertical lines perpendicular to the valve plane layer by layer, wherein the longest vertical line after intersecting with the apex in all the vertical lines is a long axis D of the left ventricle;
and step eight, calculating a three-dimensional sphericity index according to the left ventricular cavity volume LVEDV obtained in the step six and the heart long axis D obtained in the step seven. The calculation formula is as follows:。
the application effect of the present invention will be described in detail with reference to simulation.
An myocardial infarction model is established in a miniature pig body by an embolism method, and the reconstruction of the left ventricle of the miniature pig is evaluated according to the method of the invention. The evaluation results are shown in fig. 6. The three-dimensional sphericity index of the subject with a large degree of left ventricular remodeling (fig. 6 (a)) is larger, whereas the three-dimensional sphericity index of the subject with a small degree of left ventricular remodeling (fig. 6 (b)) is smaller.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. The three-dimensional sphericity index determination method based on the CTA image is characterized by comprising the following steps of: acquiring end diastole CTA data; image enhancement is carried out by adopting nonlinear gray level transformation, and then data are cut in a three-dimensional space, so that the cut image only comprises a left ventricle and a left ventricle cardiac muscle; performing a first correction of heart inclination angle from coronal view; performing a second correction of the heart inclination angle from the cross-sectional view; extracting a left ventricular heart cavity by using a three-dimensional region growing algorithm; automatically acquiring a long axis of the heart; calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the acquired left ventricle long axis;
the three-dimensional sphericity index determination method based on CTA image comprises the following steps:
(1) Acquiring end diastole CTA data;
(2) Image enhancement is carried out by adopting nonlinear gray level transformation;
(3) Clipping the data in a three-dimensional space, so that the clipped image only contains the left ventricle and the left ventricle cardiac muscle;
(4) Performing a first correction of heart inclination angle from coronal view;
(5) Performing a second correction of the heart inclination angle from the cross-sectional view;
(6) Extracting the inner cavity of the left ventricle by utilizing a three-dimensional region growing algorithm;
(7) Automatically acquiring a long axis of the heart according to the corrected image;
(8) Calculating a three-dimensional sphericity index according to the segmented left ventricle cavity and the obtained heart long axis;
the heart inclination angle correction from a certain view angle in the step (4) and the step (5) is performed according to the following steps:
(a) Selected view angle ofiThe layer is used as an angle calculation layer;
(b) Interactively selecting a rectangular region containing left ventricular myocardium on the binarized image, and dividing out the first regioniMyocardial region on the layer;
(c) Extracting myocardial center line, randomly sampling on the center linenA plurality of points, in this waynPerforming ellipse fitting on the sampling points, and using the fitted ellipse major axis inclination angleαAs a correction angle;
(d) To integrate data in three dimensionsαAngle correction is carried out on the angle;
continuously removing the boundary of the object by using morphological corrosion operation until only a framework is left, wherein the framework is a myocardial center line; random sampling on a centerlinenA point of the light-emitting diode is located,the general equation of ellipse is known as +.>The method comprises the steps of carrying out a first treatment on the surface of the Solving according to elliptic equation and least square method principleObjective functionTo determine the parameters A, B, C, D and E; order theF(A,B,C,D,E)The partial derivative for each parameter is 0, resulting in the following system of equations:
2. The CTA image-based three-dimensional sphericity index determination method of claim 1, wherein the specific step of extracting the left ventricular cavity by the three-dimensional region growing algorithm in the step (6) is as follows:
(a) Interactively selecting a cube containing a left ventricle from the corrected data, and intercepting the cube region;
(b) Seed points are selected in the truncated cube region, three-dimensional region growing is carried out according to a growable voxel inclusion principle, and finally the left ventricle cavity is extracted.
3. The CTA image-based three-dimensional sphericity index determination method of claim 2 wherein seed points are selected in truncated cube regions, three-dimensional region growing is performed according to a growable voxel inclusion principle, and a 26 neighborhood gray average of voxels to be grown is calculatedμComparing the average value with the gray value of the voxel, if the difference is less than or equal to two times of standard deviationσThe voxel is a growable voxel; the mathematical expression of the inclusion principle of the growable voxels is as follows:
4. The CTA image-based three-dimensional sphericity index determination method of claim 1 wherein the step (7) of automatically acquiring the long axis of the left ventricle from the corrected image is performed by:
(a) Extracting the inner cavity contour layer by utilizing a candy operator for the binary image only comprising the inner cavity of the left ventricle;
(b) Perpendicular lines perpendicular to the valve plane are made layer by layer, and the longest perpendicular line after intersecting the apex of the heart among all perpendicular lines is the long axis of the left ventricle.
6. a heart image processing platform applying the CTA image-based three-dimensional sphericity index measurement method of any one of claims 1 to 5.
7. A heart CTA examination system applying the CTA image-based three-dimensional sphericity index measurement method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811591084.5A CN109785296B (en) | 2018-12-25 | 2018-12-25 | CTA image-based three-dimensional spherical index determination method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811591084.5A CN109785296B (en) | 2018-12-25 | 2018-12-25 | CTA image-based three-dimensional spherical index determination method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109785296A CN109785296A (en) | 2019-05-21 |
CN109785296B true CN109785296B (en) | 2023-07-04 |
Family
ID=66497665
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811591084.5A Active CN109785296B (en) | 2018-12-25 | 2018-12-25 | CTA image-based three-dimensional spherical index determination method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109785296B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111652954B (en) * | 2020-07-01 | 2023-09-05 | 杭州脉流科技有限公司 | Left ventricle volume automatic calculation method, device, computer equipment and storage medium based on left ventricle segmentation picture |
CN113495099B (en) * | 2021-09-08 | 2021-12-07 | 之江实验室 | Image processing method for correcting sample inclination of ultrasonic scanning microscope |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
CN107123095A (en) * | 2017-04-01 | 2017-09-01 | 上海联影医疗科技有限公司 | A kind of PET image reconstruction method, imaging system |
CN107330888A (en) * | 2017-07-11 | 2017-11-07 | 中国人民解放军第三军医大学 | Each chamber dividing method of dynamic heart based on CTA images |
CN107491471A (en) * | 2017-06-19 | 2017-12-19 | 天津科技大学 | Extensive chronometer data day area covering generation method based on Spark |
CN108765430A (en) * | 2018-05-24 | 2018-11-06 | 西安思源学院 | A kind of heart left chamber region segmentation method based on cardiac CT image and machine learning |
CN108805913A (en) * | 2018-05-14 | 2018-11-13 | 首都医科大学附属北京安贞医院 | A kind of fusion method of coronary artery CT images and cardiac ultrasonic strain imaging |
Family Cites Families (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005119025A2 (en) * | 2004-06-01 | 2005-12-15 | Spectrum Dynamics Llc | Radioactive-emission-measurement optimization to specific body structures |
US7321676B2 (en) * | 2003-07-30 | 2008-01-22 | Koninklijke Philips Electronics N.V. | Automatic determination of the long axis of the left ventricle in 3D cardiac imaging |
US7702141B2 (en) * | 2005-06-29 | 2010-04-20 | General Electric Company | Method for quantifying an object in a larger structure using a reconstructed image |
CN101383006A (en) * | 2007-09-05 | 2009-03-11 | 清华大学深圳研究生院 | Image pre-processing method of oval correction and circle normalization |
WO2009108135A1 (en) * | 2008-02-29 | 2009-09-03 | Agency For Science, Technology And Research | A method and system for anatomy structure segmentation and modeling in an image |
FR2942669B1 (en) * | 2009-02-27 | 2011-04-01 | Commissariat Energie Atomique | METHODS OF IMAGE SEGMENTATION AND DETECTION OF PARTICULAR STRUCTURES. |
US8311301B2 (en) * | 2010-12-10 | 2012-11-13 | Carestream Health, Inc. | Segmenting an organ in a medical digital image |
US20140121549A1 (en) * | 2012-10-31 | 2014-05-01 | Katholieke Universiteit Leuven, KU LEUVEN R&D | Method and apparatus for determining the myocardial inotropic state |
EP2912988A4 (en) * | 2012-12-19 | 2016-07-13 | Olympus Corp | Medical image processing device and medical image processing method |
CN104835112B (en) * | 2015-05-07 | 2018-06-08 | 厦门大学 | A kind of liver multiphase phase CT image interfusion methods |
CN105372165B (en) * | 2015-12-22 | 2018-07-17 | 东南大学 | A kind of droplet diameter distribution measurement method based on hydrophobic material |
CN107742297B (en) * | 2017-09-13 | 2021-07-06 | 西北工业大学 | Local three-dimensional maximum inter-class variance segmentation method for three-dimensional CT image |
CN107705303A (en) * | 2017-10-16 | 2018-02-16 | 长沙乐成医疗科技有限公司 | The dividing method of blood vessel on a kind of medical image |
-
2018
- 2018-12-25 CN CN201811591084.5A patent/CN109785296B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102438529A (en) * | 2008-12-22 | 2012-05-02 | 美的派特恩公司 | Method and system of automated detection of lesions in medical images |
CN107123095A (en) * | 2017-04-01 | 2017-09-01 | 上海联影医疗科技有限公司 | A kind of PET image reconstruction method, imaging system |
CN107491471A (en) * | 2017-06-19 | 2017-12-19 | 天津科技大学 | Extensive chronometer data day area covering generation method based on Spark |
CN107330888A (en) * | 2017-07-11 | 2017-11-07 | 中国人民解放军第三军医大学 | Each chamber dividing method of dynamic heart based on CTA images |
CN108805913A (en) * | 2018-05-14 | 2018-11-13 | 首都医科大学附属北京安贞医院 | A kind of fusion method of coronary artery CT images and cardiac ultrasonic strain imaging |
CN108765430A (en) * | 2018-05-24 | 2018-11-06 | 西安思源学院 | A kind of heart left chamber region segmentation method based on cardiac CT image and machine learning |
Non-Patent Citations (2)
Title |
---|
Lu Liu, Xiangyun Bai.Theoretical calculation and numerical simulation of Spherical lung cancer cells' refractive index.Proceedings of 2011 6th International Forum on Strategic Technology.2011,1053 - 1057. * |
扩张型心肌病患者左室扭转与几何重构的关系;邓燕,郭盛兰,王茜,苏红月,谭臻;广东医学;第35卷(第19期);3054-3056 * |
Also Published As
Publication number | Publication date |
---|---|
CN109785296A (en) | 2019-05-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106023202B (en) | CFR fraction computational methods based on cardiac CT image | |
CN107230206B (en) | Multi-mode data-based 3D pulmonary nodule segmentation method for hyper-voxel sequence lung image | |
US11557072B2 (en) | Clustering algorithm-based multi-parameter cumulative calculation method for lower limb vascular calcification indexes | |
WO2022105623A1 (en) | Intracranial vascular focus recognition method based on transfer learning | |
CN102722882B (en) | Elastic registration method of CAG image sequence | |
CN103985123B (en) | Abdominal aortic aneurysm external boundary dividing method based on CTA images | |
GB2490477A (en) | Processing ultrasound images to determine diameter of vascular tissue lumen and method of segmenting an image of a tubular structure comprising a hollow core | |
CN110648338B (en) | Image segmentation method, readable storage medium, and image processing apparatus | |
CN112562058B (en) | Method for quickly establishing intracranial vascular simulation three-dimensional model based on transfer learning | |
JP2006314790A (en) | Method and apparatus for reconstructing two-dimensional sectional image | |
US11830193B2 (en) | Recognition method of intracranial vascular lesions based on transfer learning | |
CN109785296B (en) | CTA image-based three-dimensional spherical index determination method | |
JP6039876B2 (en) | System and method for measuring left ventricular torsion | |
KR101611488B1 (en) | Method of classifying an artifact and a diseased area in a medical image | |
CN115019014B (en) | Four-dimensional vascular reconstruction method and mechanical calculation method | |
CN113935976A (en) | Method and system for automatically segmenting blood vessels in internal organs by enhancing CT (computed tomography) image | |
CN113470060B (en) | Coronary artery multi-angle curved surface reconstruction visualization method based on CT image | |
Kiraly et al. | 3D human airway segmentation for virtual bronchoscopy | |
CN114170151A (en) | Intracranial vascular lesion identification method based on transfer learning | |
CN112022345B (en) | Three-dimensional visual preoperative planning method, system and terminal for abdominal wall defect reconstruction | |
Larralde et al. | Evaluation of a 3D segmentation software for the coronary characterization in multi-slice computed tomography | |
Chacko et al. | Sequential functional analysis of left ventricle from 2D-echocardiography images | |
CN112669439B (en) | Method for establishing intracranial angiography enhanced three-dimensional model based on transfer learning | |
Kühl | Left ventricular function | |
CN117934651B (en) | Coronary artery CTA projection transformation method for lesion coronary artery detection |
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 |