CN111047612B - Coronary artery CT angiography image segmentation method - Google Patents
Coronary artery CT angiography image segmentation method Download PDFInfo
- Publication number
- CN111047612B CN111047612B CN201911355636.7A CN201911355636A CN111047612B CN 111047612 B CN111047612 B CN 111047612B CN 201911355636 A CN201911355636 A CN 201911355636A CN 111047612 B CN111047612 B CN 111047612B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- noise
- image
- generated
- boundary
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 210000004351 coronary vessel Anatomy 0.000 title claims abstract description 20
- 238000010968 computed tomography angiography Methods 0.000 title claims abstract description 16
- 238000003709 image segmentation Methods 0.000 title claims abstract description 14
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 50
- 239000002872 contrast media Substances 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims description 15
- 230000000877 morphologic effect Effects 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 8
- 230000018109 developmental process Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 239000000203 mixture Substances 0.000 claims description 2
- 238000002583 angiography Methods 0.000 abstract description 9
- 201000010099 disease Diseases 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000002586 coronary angiography Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013152 interventional procedure Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 231100000216 vascular lesion Toxicity 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10116—X-ray image
- G06T2207/10121—Fluoroscopy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20152—Watershed segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a coronary artery CT angiography image segmentation method, belonging to the technical field of angiography, which comprises the following steps: the method comprises the following steps: after injecting contrast medium into the marked coronary artery position, carrying out ray identification by X-ray; step two: establishing a geometric model of the blood vessel; step three: acquiring a preliminary blood vessel image; step four: overlapping the blood vessel contours generated in the first step and the second step with image noise; step five: the blood vessel contour generated by combination is developed and refreshed, the two-dimensional image of the coronary artery is preliminarily calculated and extracted by different methods, the sharpened blood vessel contour is obtained by overlapping image noise, and the blood vessel contour under the three-dimensional image is obtained by the same method.
Description
Technical Field
The invention relates to the technical field of angiography, in particular to a coronary artery CT angiography image segmentation method.
Background
Angiography is an auxiliary examination technology, is generally used for diagnosis and treatment of various clinical diseases in the advanced period of modern technology, is helpful for doctors to find disease conditions in time, controls the progress of the disease conditions, and effectively improves the survival rate of patients. Angiography is an interventional procedure in which a contrast agent is injected into a blood vessel, and because X-rays cannot penetrate the contrast agent, angiography accurately reflects the location and extent of vascular lesions.
When the coronary artery is developed through an angiography technology, the generated image has an obvious fuzzy phenomenon, so that medical staff cannot conveniently check the specific condition of the coronary artery, the specific condition judgment of the position is easily influenced, and the condition of misdiagnosis is possibly caused in a serious condition.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above and/or other problems associated with the prior art coronary angiography.
Therefore, an object of the present invention is to provide a coronary CT angiography image segmentation method, which can perform optimized segmentation on an image generated by angiography, reduce blurring, improve the sharpness of the image, and facilitate diagnosis of a disease condition through the image.
In order to solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:
a coronary artery CT angiography image segmentation method comprises the following steps:
the method comprises the following steps: after injecting contrast agent into the marked coronary artery position, carrying out ray identification through X-ray, extracting a target and obtaining a blood vessel contour;
step two: establishing a vessel geometric model, distinguishing all unexpected modes which may affect vessels, extracting bright linear targets through morphological operation, and extracting vessel morphology through curvature differentiation and Laplace filtering;
step three: acquiring a preliminary blood vessel image, extracting a central line of the blood vessel, obtaining a boundary of the blood vessel by using a middle marker and a watershed algorithm, and then reconstructing a three-dimensional structure of the blood vessel;
step four: overlapping the blood vessel contours generated in the first step and the second step by using image noise, storing the generated overlapping noise, calculating a connecting line by combining the unidirectional noise by using the overlapping noise, and substituting the connecting line into the three-dimensional structure in the third step to obtain the blood vessel contour in a fuzzy state;
step five: and developing and refreshing the blood vessel contour generated by combination, and then extracting the boundary to obtain the segmented angiography image.
As a preferable embodiment of the coronary artery CT angiography image segmentation method according to the present invention, wherein: in the first step, different filters need to be designed for blood vessels in different directions and sizes before ray identification, the filters are linear filters, the image extraction method is an image convolution method, and the contour acquisition of the blood vessels needs to be matched with thresholding and connected composition analysis to obtain the contour.
As a preferable aspect of the method for segmenting a coronary CT angiography image according to the present invention, wherein: the performance of the algorithm in step two is derived from a combination of morphological and differential operations.
As a preferable embodiment of the coronary artery CT angiography image segmentation method according to the present invention, wherein: the method for acquiring the centerline of the blood vessel in the third step is annular template tracking, and the boundary of the blood vessel in the third step is a morphological boundary.
As a preferable embodiment of the coronary artery CT angiography image segmentation method according to the present invention, wherein: the specific method for overlapping the image noise in the fourth step is as follows:
the method comprises the following steps: according to the noise generated by overlapping, the mark caused by the same point is quasi-noise, and the noise generated by different points is auxiliary noise;
step two: marking dotted lines according to the similar positions of the auxiliary noise, and connecting the quasi-noise points by solid lines;
step three: selecting an optimal connection point of the auxiliary noise generation points according to the quasi-noise points connected by the solid lines, connecting the solid lines with the dotted lines generated by the optimal connection points, and blurring the intersection points to obtain a boundary area;
step four: the obtained boundary region is substituted into the three-dimensional structure according to the method to obtain the fuzzy blood vessel contour.
As a preferable aspect of the method for segmenting a coronary CT angiography image according to the present invention, wherein: and the step five of developing and refreshing specifically comprises the steps of carrying out boundary region sharpening on the fuzzy blood vessel contour, carrying out data position change on the contour generated by sharpening, generating multiple groups of sharpened data, and comparing the multiple groups of sharpened data to obtain average data, namely the blood vessel contour map before extraction.
Compared with the prior art: when coronary arteries are developed through an angiography technology, the generated images have obvious blurring phenomena, so that medical staff cannot conveniently check the specific conditions of the coronary arteries, the specific condition judgment of the positions is easily influenced, and misdiagnosis is possibly caused in severe cases.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail with reference to the accompanying drawings and detailed embodiments, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise. Wherein:
fig. 1 is a schematic flow structure diagram of a coronary artery CT angiography image segmentation method according to the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, embodiments accompanying figures are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described herein, and it will be apparent to those of ordinary skill in the art that the present invention may be practiced without departing from the spirit and scope of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Next, the present invention is described in detail with reference to the drawings, and in the detailed description of the embodiments of the present invention, the cross-sectional view illustrating the structure of the device is not enlarged partially in general scale for the convenience of illustration, and the drawings are only exemplary, which should not limit the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
To make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The invention provides a coronary artery CT angiography image segmentation method, please refer to FIG. 1, the method is as follows:
the method comprises the following steps: injecting contrast medium into the marked coronary artery position, performing X-ray identification, extracting the target, obtaining the blood vessel contour, and if the image is regarded as the image definition domain to the gray scale range
The boundary is perceptually where the function has a significant change, i.e. where the gradient is large, and therefore a simple edge detection can be defined as:
wherein the content of the first and second substances,
representing the image domain,/is the image on Λ, r is the point on the image, and p is a suitable threshold.
Step two: establishing a vessel geometric model, distinguishing all unexpected modes which may affect vessels, extracting bright linear targets through morphological operation, and extracting vessel morphology through curvature differentiation and Laplace filtering;
step three: acquiring a preliminary blood vessel image, extracting a central line of the blood vessel, obtaining a boundary of the blood vessel by using a middle marker and a watershed algorithm, and then reconstructing a three-dimensional structure of the blood vessel;
step four: and (3) overlapping the blood vessel contours generated in the first step and the second step with image noise, storing the generated overlapping noise, calculating a connection line by combining the overlapping noise with one-way noise, substituting the connection line into the three-dimensional structure in the third step to obtain the blood vessel contour in a fuzzy state, and applying Gaussian filtering to the image in order to reduce noise interference, wherein the step (b) comprises the following steps:
step five: the blood vessel contour generated by combination is developed and refreshed, and then boundary extraction is carried out, so that the segmented angiogram image can be obtained, wherein the development is a process for displaying the image in the industries of printing, photocopying, copying, blueprinting and the like. The development includes forward development and reverse development. The polarity of charges carried by developing toner in positive development is opposite to the charge polarity of an electrostatic latent image on the surface of a photosensitive drum, the charge polarities of the photosensitive drum and the toner in reverse development are the same, the developing operation is applied to the segmentation of a contrast image, the generated contrast image is refreshed, after a plurality of images are rapidly refreshed, similar boundaries of the images can be obtained, and in boundary extraction, namely edge extraction, edge extraction and exponential image processing, a process for the image contour is carried out. For the boundary, the place where the gray value change is more severe is defined as the edge. That is, an inflection point is a point at which a function changes irregularly. Where the second derivative is zero. Not the first derivative, because the first derivative is zero, the representation is an extreme point.
Edge extraction: the basic idea of edge detection is to firstly highlight local edges in an image by using an edge enhancement operator, then define the 'edge strength' of pixels, and extract an edge point set by setting a threshold value. The monitored boundary may widen or break at some point due to the presence of noise and ambiguity. Thus, boundary detection includes two basic contents: (1) And extracting an edge point set reflecting the gray level change by using an edge operator. (2) And removing certain boundary points or filling boundary discontinuous points in the edge point set, and connecting the edges into a complete line.
Edge definition: where the image gradation change rate is the greatest (where the image gradation change is the most drastic). The edges caused by discontinuities in the image intensity variation in the normal direction of the surface. Edge extraction is generally considered to be to reserve the region of the image where the gray level changes drastically, and mathematically, the most intuitive method is differentiation (differential for digital images), and from the viewpoint of signal processing, it can be said that a high-pass filter is used, that is, a high-frequency signal is reserved.
Referring to fig. 1 again, in the first step, different filters need to be designed for blood vessels with different directions and sizes before performing ray identification, the filters are linear filters, the image extraction method is an image convolution method, and the contour acquisition of the blood vessels needs to be obtained in cooperation with thresholding and connected component analysis.
The convolution kernel (operator) is a matrix used for image processing, also called a mask, and is a parameter for performing an operation with an original image. The convolution kernel is typically a square grid structure (e.g., a 3 x 3 matrix or pixel region) with a weight value for each square.
When convolution is used for calculation, the center of a convolution kernel needs to be placed on a pixel to be calculated, products of each element in the kernel and image pixel values covered by the element are calculated once and summed, an obtained structure is a new pixel value of the position, and edge detection and extraction of the image are carried out through the method.
Referring again to fig. 1, the performance of the algorithm in step two is derived from a combination of morphology and differential operations, specifically, morphology is an image analysis subject based on lattice theory and topology, and is a basic theory of mathematical morphology image processing. The basic operation comprises the following steps: corrosion and expansion, opening and closing operation, skeleton extraction, limit corrosion, hit-miss transformation, morphological gradient, top-hat transformation, particle analysis, watershed transformation and the like, and the differential operation, namely D control, refers to a control process and method taking differential as a control rule. The basic control law includes three kinds of proportion P, differential D and integral I.
PID control is the most common control mode in industrial production, namely proportional-integral-derivative control, and a PID controller performs certain proportional, integral and derivative operations on input to output control quantity to meet certain control requirements.
The basic transfer function of PID control is expressed as:
referring to fig. 1 again, the method for obtaining the blood vessel centerline in the third step is circular template tracking, and the blood vessel boundary in the third step is a morphological boundary.
Referring to fig. 1 again, the specific method of overlapping the image noise in the fourth step is as follows:
the method comprises the following steps: according to the noise generated by overlapping, the caused mark generated by the same point is quasi-noise, and the noise generated by different points is auxiliary noise;
step two: marking dotted lines according to the similar positions of the auxiliary noises, and then connecting the quasi-noise points by solid lines;
step three: selecting an optimal connection point of the auxiliary noise generation points according to the quasi-noise points connected by the solid lines, connecting the solid lines with the dotted lines generated by the optimal connection point, and blurring the intersection points to obtain a boundary area;
step four: the obtained boundary region is substituted into the three-dimensional structure according to the method to obtain the fuzzy blood vessel contour.
Referring to fig. 1 again, the developing and refreshing in the fifth step is to perform boundary area sharpening on the blurred blood vessel contour, perform data position modification on the contour generated by the sharpening, generate multiple sets of sharpened data, and compare the multiple sets of sharpened data to obtain average data, which is the blood vessel contour map before extraction.
While the invention has been described above with reference to an embodiment, various modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the invention. In particular, the various features of the disclosed embodiments of this invention can be used in any combination as long as there is no structural conflict, and the combination is not exhaustively described in this specification merely for the sake of brevity and resource savings. Therefore, it is intended that the invention not be limited to the particular embodiments disclosed, but that the invention will include all embodiments falling within the scope of the appended claims.
Claims (3)
1. A coronary artery CT angiography image segmentation method is characterized in that: the method comprises the following steps:
the method comprises the following steps: injecting a contrast agent into a marked coronary artery position, performing ray identification through X-ray, extracting a target, and obtaining a blood vessel contour, wherein different filters need to be designed for blood vessels in different directions and sizes before performing ray identification, the filters are linear filters, the image extraction method is an image convolution method, and the blood vessel contour acquisition also needs to be obtained by being matched with thresholding and communicating composition analysis;
step two: establishing a vessel geometric model, distinguishing all unexpected modes which may affect vessels, extracting bright linear targets through morphological operation, and extracting vessel morphology through curvature differentiation and Laplace filtering;
step three: obtaining the boundary of the blood vessel by using a watershed algorithm, and then reconstructing a three-dimensional structure of the blood vessel;
step four: overlapping the blood vessel contours generated in the first step and the second step with image noise, storing the generated overlapping noise, calculating a connection line by combining the overlapping noise with one-way noise, and substituting the connection line into the three-dimensional structure in the third step to obtain the blood vessel contour in a fuzzy state;
the specific method for overlapping the image noise is as follows:
s1: according to the noise generated by overlapping, the caused mark generated by the same point is quasi-noise, and the noise generated by different points is auxiliary noise;
s2: marking dotted lines according to the similar positions of the auxiliary noise, and connecting the quasi-noise points by solid lines;
s3: selecting an optimal connection point of the auxiliary noise generation points according to the quasi-noise points connected by the solid lines, connecting the solid lines with the dotted lines generated by the optimal connection point, and blurring the intersection points to obtain a boundary area;
s4: and substituting the obtained boundary area into the three-dimensional structure according to the method to obtain a fuzzy blood vessel contour step five: and performing development refreshing on the blood vessel contour generated by combination, then performing boundary extraction to obtain a segmented angiogram image, wherein the development refreshing specifically comprises the steps of performing boundary region sharpening on a fuzzy blood vessel contour, then performing data position change on the contour generated by sharpening to generate a plurality of groups of sharpened data, and comparing the plurality of groups of sharpened data to obtain average data, namely the blood vessel contour map before extraction.
2. The coronary CT angiography image segmentation method according to claim 1, wherein: the performance of the algorithm in step two is derived from a combination of morphological and differential operations.
3. The coronary CT angiography image segmentation method according to claim 1, wherein: the method for acquiring the centerline of the blood vessel in the third step is annular template tracking, and the boundary of the blood vessel in the third step is a morphological boundary.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355636.7A CN111047612B (en) | 2019-12-25 | 2019-12-25 | Coronary artery CT angiography image segmentation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911355636.7A CN111047612B (en) | 2019-12-25 | 2019-12-25 | Coronary artery CT angiography image segmentation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111047612A CN111047612A (en) | 2020-04-21 |
| CN111047612B true CN111047612B (en) | 2023-02-24 |
Family
ID=70239450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911355636.7A Active CN111047612B (en) | 2019-12-25 | 2019-12-25 | Coronary artery CT angiography image segmentation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047612B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6842638B1 (en) * | 2001-11-13 | 2005-01-11 | Koninklijke Philips Electronics N.V. | Angiography method and apparatus |
| CN104867147A (en) * | 2015-05-21 | 2015-08-26 | 北京工业大学 | SYNTAX automatic scoring method based on coronary angiogram image segmentation |
| CN107392994A (en) * | 2017-06-30 | 2017-11-24 | 深圳大学 | Three-dimensional rebuilding method, device, equipment and the storage medium of coronary artery blood vessel |
| CN107527341A (en) * | 2017-08-30 | 2017-12-29 | 上海联影医疗科技有限公司 | The processing method and system of angiographic image |
| CN110448319A (en) * | 2018-05-08 | 2019-11-15 | 博动医学影像科技（上海）有限公司 | Based on radiography image and blood flow velocity calculation method coronarius |
| CN110490040A (en) * | 2019-05-30 | 2019-11-22 | 浙江理工大学 | A method of local vascular stenosis in identification DSA coronary artery images |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102202576B (en) * | 2008-10-10 | 2015-04-08 | 皇家飞利浦电子股份有限公司 | Angiographic image acquisition system and method with automatic shutter adaptation for yielding a reduced field of view covering a segmented target structure or lesion for decreasing x-radiation dose in minimally invasive x-ray-guided interventions |
-
2019
- 2019-12-25 CN CN201911355636.7A patent/CN111047612B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6842638B1 (en) * | 2001-11-13 | 2005-01-11 | Koninklijke Philips Electronics N.V. | Angiography method and apparatus |
| CN104867147A (en) * | 2015-05-21 | 2015-08-26 | 北京工业大学 | SYNTAX automatic scoring method based on coronary angiogram image segmentation |
| CN107392994A (en) * | 2017-06-30 | 2017-11-24 | 深圳大学 | Three-dimensional rebuilding method, device, equipment and the storage medium of coronary artery blood vessel |
| CN107527341A (en) * | 2017-08-30 | 2017-12-29 | 上海联影医疗科技有限公司 | The processing method and system of angiographic image |
| CN110448319A (en) * | 2018-05-08 | 2019-11-15 | 博动医学影像科技（上海）有限公司 | Based on radiography image and blood flow velocity calculation method coronarius |
| CN110490040A (en) * | 2019-05-30 | 2019-11-22 | 浙江理工大学 | A method of local vascular stenosis in identification DSA coronary artery images |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进活动窄带模型的冠状动脉CT血管造影图像分割;张梦璐等;《中国医学物理学杂志》(第02期);全文 * |
| 形状约束下活动轮廓模型冠脉血管图像多尺度分割;郭笑妍等;《中国图象图形学报》(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111047612A (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107644420B (en) | Blood vessel image segmentation method based on centerline extraction and nuclear magnetic resonance imaging system | |
| Shen et al. | An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy | |
| Sun et al. | Local morphology fitting active contour for automatic vascular segmentation | |
| Bouraoui et al. | 3D segmentation of coronary arteries based on advanced mathematical morphology techniques | |
| Rad et al. | Morphological region-based initial contour algorithm for level set methods in image segmentation | |
| Wan et al. | Automated coronary artery tree segmentation in X-ray angiography using improved Hessian based enhancement and statistical region merging | |
| WO2001078005A2 (en) | System and method for three-dimensional image rendering and analysis | |
| Lassen et al. | Lung and lung lobe segmentation methods at Fraunhofer MEVIS | |
| García et al. | Evaluation of texture for classification of abdominal aortic aneurysm after endovascular repair | |
| CN109886973B (en) | Blood vessel extraction method and device and computer readable storage medium | |
| CN101140659B (en) | Method for dividing vas data in digital vas angiography image | |
| CN105167798A (en) | Method for extracting blood vessel information from coronary artery CTA (computed tomographic angiography) image | |
| Metz et al. | Semi-automatic coronary artery centerline extraction in computed tomography angiography data | |
| Dizdaroğlu et al. | Structure-based level set method for automatic retinal vasculature segmentation | |
| Lim et al. | Segmentation of the liver using the deformable contour method on CT images | |
| Hameeteman et al. | Carotid wall volume quantification from magnetic resonance images using deformable model fitting and learning-based correction of systematic errors | |
| Zhuang et al. | Local fuzzy fractal dimension and its application in medical image processing | |
| Kumar et al. | Edge detection of angiogram images using the classical image processing techniques | |
| CN111047612B (en) | Coronary artery CT angiography image segmentation method | |
| Nanayakkara et al. | Automatic breast boundary segmentation of mammograms | |
| Ogiela et al. | Automatic segmentation of the carotid artery bifurcation region with a region-growing approach | |
| Subašić et al. | Model-based quantitative AAA image analysis using a priori knowledge | |
| Franchi et al. | A shape-based segmentation algorithm for X-ray digital subtraction angiography images | |
| CN113706563B (en) | X-ray chest radiography lung field segmentation method for automatically initializing Snake model | |
| CN113724264B (en) | Image segmentation method, system and readable storage medium |
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 |