CN112862884A - Blood vessel extraction method based on graph cutting and fracture completion - Google Patents
Blood vessel extraction method based on graph cutting and fracture completion Download PDFInfo
- Publication number
- CN112862884A CN112862884A CN202110084518.8A CN202110084518A CN112862884A CN 112862884 A CN112862884 A CN 112862884A CN 202110084518 A CN202110084518 A CN 202110084518A CN 112862884 A CN112862884 A CN 112862884A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- points
- graph
- fitting
- vessel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 122
- 238000000605 extraction Methods 0.000 title claims abstract description 17
- 230000011218 segmentation Effects 0.000 claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 27
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000001502 supplementing effect Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000740 bleeding effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012916 structural analysis Methods 0.000 description 1
- 208000019553 vascular disease Diseases 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Abstract
The invention discloses a blood vessel extraction method based on graph cutting and fracture completion, which comprises the following steps: carrying out blood vessel enhancement on the image; performing blood vessel segmentation based on a graph segmentation method; extracting the center line of the blood vessel; the vessels were completed based on slope consistency analysis. The method provided by the invention is a full-automatic blood vessel extraction method, manual interaction and parameter setting are not needed, the defect that the existing segmentation method is easy to cause blood vessel structure fracture can be effectively overcome, a relatively complete blood vessel structure is extracted, the accuracy of blood vessel segmentation is improved, and further blood vessel structure and function analysis is facilitated.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a blood vessel extraction method based on graph cutting and fracture completion.
Background
Blood vessels are important structures in human bodies, and accurate structures of blood vessels separated from medical images play an important role in diagnosis and quantitative analysis of vascular diseases. The segmented blood vessel image can help a doctor to control surgical bleeding to the maximum extent in a surgical operation, and finally the surgical patient obtains the best recovery effect. Therefore, how to accurately extract the blood vessels has very important significance for operation planning.
At present, in a common blood vessel imaging technology, when a blood vessel is small, narrow or a diseased region is weak in imaging information, the traditional blood vessel segmentation method is easy to cause the breakage of the blood vessel structure when the blood vessel structure is extracted, and the trouble is caused to the subsequent structural analysis. Therefore, a new blood vessel segmentation technology is urgently needed to improve the accuracy of blood vessel segmentation.
Disclosure of Invention
The invention aims to provide a blood vessel extraction method based on graph cutting and fracture completion, which makes up the defects of the prior art and improves the accuracy of blood vessel segmentation.
To solve the above technical problem, an embodiment of the present invention provides the following solutions:
a blood vessel extraction method based on graph cutting and fracture completion comprises the following steps:
s1, conducting blood vessel enhancement towards the image;
s2, performing blood vessel segmentation based on the graph segmentation method;
s3, extracting the center line of the blood vessel;
and S4, completing the blood vessel based on the slope consistency analysis.
Preferably, the step S1 specifically includes:
and performing blood vessel enhancement on the obtained image by using a multiscale blood vessel enhancement method based on the characteristic value of the Hessian matrix, and enhancing the contrast of a tubular structure and a background in the image.
Preferably, the step S2 specifically includes:
combining all voxel points in the image with a source node S and a sink node T to form a graph model G (V, E), wherein V and E respectively represent the set of vertexes and edges;
wherein, the vertex includes two kinds: one is a normal vertex corresponding to all voxel points; the other is a terminal vertex; the edges include two types: one is the connection between common adjacent voxel points, which is n-link; the other is the connection between the voxel point and the terminal vertex, which is t-link; each edge corresponds to a non-negative weight W, a cut is a subset C of an edge set E in the graph, all edge breaks in the graph C can separate the remaining S graph and the remaining T graph, and the cost of the cut is the sum of all the edges in the graph C;
and designing a cost function, finding a segment which enables the cost function to be minimum, and realizing the segmentation of the blood vessel and the background at a voxel point.
Preferably, the step S3 specifically includes:
using an iterative refinement algorithm to perform vessel centerline extraction, comprising:
continuously traversing foreground voxel points containing blood vessels and finding simple points to be deleted until all the points are not the simple points;
wherein, the foreground voxels are defined as 26 connected, the background voxels are defined as 6 connected, and the voxel points with Euclidean distance equal to 1 are called 6 neighborhoodsAdjacent points, Euclidean distance equal to
Is called a 12-neighborhood neighbor point, and the Euclidean distance is equal to
The voxel points of (2) are called 26 neighborhood neighbor points;
points satisfying the following conditions at the same time are defined as simple points: at least one foreground point is arranged in 26 adjacent areas of the points, at least one background point is arranged in the 26 adjacent areas of the points, the foreground points of the 26 adjacent areas of the points must form a connected domain, and the background points of the 26 adjacent areas of the points must form a connected domain.
Preferably, the step S4 specifically includes:
numbering the points in the extracted blood vessel center line, and constructing a blood vessel center line tree according to the adjacent position relation of the points;
acquiring all endpoints according to the blood vessel center line tree, calculating the direction of the endpoints, selecting a fitting array according to each direction of the endpoints, and fitting a curve equation and an endpoint tangent of a three-dimensional curve;
judging the tangential direction;
performing optimized connection of the central line end points of the blood vessels;
and obtaining the radius of the blood vessel of each end point and the radius of the blood vessel to be supplemented according to the blood vessel segmentation result, and supplementing the blood vessel by combining the center line of the blood vessel.
Preferably, the selecting a fitting array according to each endpoint direction, and the fitting of the curve equation and the endpoint tangent of the three-dimensional curve specifically includes:
assuming that the number of points used for fitting in the fitting array is n, fitting is performed using a polynomial of order n-1, and in order to prevent overfitting, fitting is performed using a polynomial of order 3 for both n-4 and n-5;
counting the change rates of left and right points in each fitting array in three XYZ directions, selecting the direction with the maximum change rate as a fitting independent variable, and using the other two directions as fitting dependent variables;
if the X direction is chosen as the fitting argument, the curve equation is:
fy＝f1(x)；fz＝f2(x)
the tangent at the end point is:
preferably, the determining the tangential direction specifically includes:
suppose the endpoint is I0(x0,y0,z0) The point closest to the end point in the fitting points is I1Positive direction virtual point IpThe negative direction virtual point is InD is I0To I1Direction of (D)pIs I0To IpDirection of (D)nIs I0To InThe end point direction plus and minus Sign is:
wherein Angel is the angle between two directions.
Preferably, the performing optimized connection of the vessel centerline endpoint specifically includes:
finding out all the end point pairs which should be connected according to the end point direction;
the likelihood of a pair of endpoints being connected is measured by the following four conditions:
the Euclidean distance of the two endpoints; the included angle of the two end point directions; two endpoints cannot belong to the same connected domain; smoothness after connection of the two endpoints.
Preferably, the obtaining of the radius of the blood vessel at each end point and the radius of the blood vessel to be completed according to the result of the blood vessel segmentation, and completing the blood vessel by combining the center line of the blood vessel specifically includes:
through traversing all the segmented blood vessel foreground points, judging whether a background point exists in the 26 neighborhoods of the blood vessel foreground points; and extracting a vessel surface voxel set VS, wherein the vessel radius of the end point is as follows:
d＝min(dist(endpoint,I),I∈VS)
wherein endpoint is a blood vessel end point, dist is an Euclidean distance for calculating two points;
assuming that the vessel radius of two end points to be connected is d1 and d2, respectively, the radius of the vessel to be completed is (d1+ d2)/2, and then the vessel is completed according to the vessel center line.
The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:
the invention provides a full-automatic blood vessel extraction method, which does not need artificial interaction and parameter setting, can effectively make up the defect that the existing segmentation method is easy to cause the breakage of a blood vessel structure, extracts a relatively complete blood vessel structure, improves the accuracy of blood vessel segmentation, and is beneficial to further analysis of the blood vessel structure and function.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, 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 based on these drawings without creative efforts.
Fig. 1 is a flowchart of a blood vessel extraction method based on graph cut and fracture filling according to an embodiment of the present invention;
FIGS. 2 a-2 d illustrate four cases of determining whether endpoints are connected according to an embodiment of the present invention; FIG. 2a shows that the Euclidean distance between the end points cannot be too large, FIG. 2b shows that the included angle in the direction of the end points cannot be too small, FIG. 2c shows that the end points cannot belong to the same connected domain, and FIG. 2d shows that the end points are smooth enough after being connected;
fig. 3 is a schematic diagram of a vessel fracture completion in an embodiment of the invention.
Detailed Description
In order 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.
An embodiment of the present invention provides a blood vessel extraction method based on graph cutting and fracture completion, as shown in fig. 1, the method includes the following steps:
s1, conducting blood vessel enhancement towards the image;
s2, performing blood vessel segmentation based on the graph segmentation method;
s3, extracting the center line of the blood vessel;
and S4, completing the blood vessel based on the slope consistency analysis.
The method can effectively extract a relatively complete blood vessel structure, improves the accuracy of blood vessel segmentation, and is favorable for further analysis of the blood vessel structure and function.
Specifically, the detailed flow of the blood vessel extraction method based on graph cutting and fracture completion is as follows:
step S1, vessel enhancement is performed toward the image; the method specifically comprises the following steps:
and performing blood vessel enhancement on the obtained image by using a multiscale blood vessel enhancement method based on the characteristic value of the Hessian matrix, and enhancing the contrast of a tubular structure and a background in the image.
Step S2, performing blood vessel segmentation based on a graph segmentation method; the method specifically comprises the following steps:
combining all voxel points in the image with a source node S and a sink node T to form a graph model G (V, E), wherein V and E respectively represent the set of vertexes and edges;
wherein, the vertex includes two kinds: one is a normal vertex corresponding to all voxel points; the other is a terminal vertex; the edges include two types: one is the connection between common adjacent voxel points, which is n-link; the other is the connection between the voxel point and the terminal vertex, which is t-link; each edge corresponds to a non-negative weight W, a cut (cut) refers to a subset C of an edge set E in a graph, all edge breaks in the C can separate a residual S graph and a residual T graph, and the cost of the cut is the sum of all the W in the C;
and designing a cost function, finding a segment which enables the cost function to be minimum, and realizing the segmentation of the blood vessel and the background at a voxel point.
Step S3, extracting the center line of the blood vessel; the method specifically comprises the following steps:
using an iterative refinement algorithm to perform vessel centerline extraction, comprising:
continuously traversing foreground voxel points containing blood vessels and finding simple points to be deleted until all the points are not the simple points;
wherein, the foreground voxels are defined as 26 connected, the background voxels are defined as 6 connected, the voxel points with Euclidean distance equal to 1 are called 6 neighborhood adjacent points, and the Euclidean distance is equal to
Is called a 12-neighborhood neighbor point, and the Euclidean distance is equal to
The voxel points of (2) are called 26 neighborhood neighbor points;
points satisfying the following conditions at the same time are defined as simple points: at least one foreground point is arranged in 26 adjacent areas of the points, at least one background point is arranged in the 26 adjacent areas of the points, the foreground points of the 26 adjacent areas of the points must form a connected domain, and the background points of the 26 adjacent areas of the points must form a connected domain.
Step S4, completing the blood vessel based on the slope consistency analysis; the method specifically comprises the following steps:
numbering the points in the extracted blood vessel center line, and constructing a blood vessel center line tree according to the adjacent position relation of the points;
acquiring all endpoints according to the blood vessel center line tree, calculating the direction of the endpoints, selecting a fitting array according to each direction of the endpoints, and fitting a curve equation and an endpoint tangent of a three-dimensional curve;
assuming that the number of points used for fitting in the fitting array is n, fitting is performed using a polynomial of order n-1, and in order to prevent overfitting, fitting is performed using a polynomial of order 3 for both n-4 and n-5;
counting the change rates of left and right points in each fitting array in three XYZ directions, selecting the direction with the maximum change rate as a fitting independent variable, and using the other two directions as fitting dependent variables;
if the X direction is chosen as the fitting argument, the curve equation is:
fy＝f1(x)；fz＝f2(x) (1)
the tangent at the end point is:
judging the tangential direction, including:
suppose the endpoint is I0(x0,y0,z0) The point closest to the end point in the fitting points is I1Positive direction virtual point IpThe negative direction virtual point is InD is I0To I1Direction of (D)pIs I0To IpDirection of (D)nIs I0To InThe end point direction plus and minus Sign is:
wherein Angel is the angle between two directions.
Performing vessel centerline endpoint optimized connections, comprising:
finding out all the end point pairs which should be connected according to the end point direction;
the likelihood of a pair of endpoints being connected is measured by the following four conditions:
1. the Euclidean distance of the two endpoints; 2. the included angle of the two end point directions; 3. two endpoints cannot belong to the same connected domain; 4. smoothness after connection of the two endpoints.
Fig. 2 a-2 d show four cases of determining whether an endpoint is connected. Wherein, fig. 2a shows that the euclidean distance of the end points cannot be too large, fig. 2b shows that the included angle in the direction of the end points cannot be too small, fig. 2c shows that the end points cannot belong to the same connected domain, and fig. 2d shows that the end points are smooth enough after being connected.
Obtaining the radius of the blood vessel of each end point and the radius of the blood vessel to be supplemented according to the result of the blood vessel segmentation, and supplementing the blood vessel by combining the center line of the blood vessel, specifically comprising:
through traversing all the segmented blood vessel foreground points, judging whether a background point exists in the 26 neighborhoods of the blood vessel foreground points; and extracting a vessel surface voxel set VS, wherein the vessel radius of the end point is as follows:
d＝min(dist(endpoint,I),I∈VS) (4)
wherein endpoint is a blood vessel end point, dist is an Euclidean distance for calculating two points;
assuming that the vessel radius of two end points to be connected is d1 and d2, respectively, the radius of the vessel to be completed is (d1+ d2)/2, and then the vessel is completed according to the vessel center line.
Fig. 3 is a schematic diagram of a blood vessel fracture completion provided by an embodiment of the present invention, where a dark color part is a preliminary blood vessel segmentation result, a black dotted line is a blood vessel centerline, a black dot is a centerline endpoint, a white dotted line is a completed blood vessel centerline, a middle light color part is a completed blood vessel, and d1 and d2 are blood vessel radii.
In summary, the blood vessel extraction method based on graph cut and fracture completion provided by the embodiment of the invention can extract a more complete blood vessel structure through the steps of blood vessel enhancement, blood vessel segmentation based on a graph cut method, blood vessel centerline extraction, blood vessel completion based on slope consistency analysis and the like, and is favorable for further blood vessel structure and function analysis.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A blood vessel extraction method based on graph cutting and fracture completion is characterized by comprising the following steps:
s1, conducting blood vessel enhancement towards the image;
s2, performing blood vessel segmentation based on the graph segmentation method;
s3, extracting the center line of the blood vessel;
and S4, completing the blood vessel based on the slope consistency analysis.
2. The method for extracting blood vessels based on graph cut and fracture filling according to claim 1, wherein the step S1 specifically comprises:
and performing blood vessel enhancement on the obtained image by using a multiscale blood vessel enhancement method based on the characteristic value of the Hessian matrix, and enhancing the contrast of a tubular structure and a background in the image.
3. The method for extracting blood vessels based on graph cut and fracture filling according to claim 1, wherein the step S2 specifically comprises:
combining all voxel points in the image with a source node S and a sink node T to form a graph model G (V, E), wherein V and E respectively represent the set of vertexes and edges;
wherein, the vertex includes two kinds: one is a normal vertex corresponding to all voxel points; the other is a terminal vertex; the edges include two types: one is the connection between common adjacent voxel points, which is n-link; the other is the connection between the voxel point and the terminal vertex, which is t-link; each edge corresponds to a non-negative weight W, a cut is a subset C of an edge set E in the graph, all edge breaks in the graph C can separate the remaining S graph and the remaining T graph, and the cost of the cut is the sum of all the edges in the graph C;
and designing a cost function, finding a segment which enables the cost function to be minimum, and realizing the segmentation of the blood vessel and the background at a voxel point.
4. The method for extracting blood vessels based on graph cut and fracture filling according to claim 1, wherein the step S3 specifically comprises:
using an iterative refinement algorithm to perform vessel centerline extraction, comprising:
continuously traversing foreground voxel points containing blood vessels and finding simple points to be deleted until all the points are not the simple points;
wherein, the foreground voxels are defined as 26 connected, the background voxels are defined as 6 connected, and the Euclidean distanceThe voxel points with distance equal to 1 are called neighborhood neighbors 6, the Euclidean distance is equal to
Is called a 12-neighborhood neighbor point, and the Euclidean distance is equal to
The voxel points of (2) are called 26 neighborhood neighbor points;
points satisfying the following conditions at the same time are defined as simple points: at least one foreground point is arranged in 26 adjacent areas of the points, at least one background point is arranged in the 26 adjacent areas of the points, the foreground points of the 26 adjacent areas of the points must form a connected domain, and the background points of the 26 adjacent areas of the points must form a connected domain.
5. The method for extracting blood vessels based on graph cut and fracture filling according to claim 1, wherein the step S4 specifically comprises:
numbering the points in the extracted blood vessel center line, and constructing a blood vessel center line tree according to the adjacent position relation of the points;
acquiring all endpoints according to the blood vessel center line tree, calculating the direction of the endpoints, selecting a fitting array according to each direction of the endpoints, and fitting a curve equation and an endpoint tangent of a three-dimensional curve;
judging the tangential direction;
performing optimized connection of the central line end points of the blood vessels;
and obtaining the radius of the blood vessel of each end point and the radius of the blood vessel to be supplemented according to the blood vessel segmentation result, and supplementing the blood vessel by combining the center line of the blood vessel.
6. The method for extracting blood vessels based on graph cut and fracture completion according to claim 5, wherein the selecting a fitting array according to each endpoint direction, and fitting a curve equation and an endpoint tangent of a three-dimensional curve specifically comprises:
assuming that the number of points used for fitting in the fitting array is n, fitting is performed using a polynomial of order n-1, and in order to prevent overfitting, fitting is performed using a polynomial of order 3 for both n-4 and n-5;
counting the change rates of left and right points in each fitting array in three XYZ directions, selecting the direction with the maximum change rate as a fitting independent variable, and using the other two directions as fitting dependent variables;
if the X direction is chosen as the fitting argument, the curve equation is:
fy＝f1(x)；fz＝f2(x)
the tangent at the end point is:
7. the method for extracting blood vessels based on graph cut and fracture filling according to claim 5, wherein the determining the tangential direction specifically comprises:
suppose the endpoint is I0(x0,y0,z0) The point closest to the end point in the fitting points is I1Positive direction virtual point IpThe negative direction virtual point is InD is I0To I1Direction of (D)pIs I0To IpDirection of (D)nIs I0To InThe end point direction plus and minus Sign is:
wherein Angel is the angle between two directions.
8. The method for extracting blood vessels based on graph cut and fracture completion according to claim 5, wherein the performing optimized connection of the end points of the centerline of the blood vessel specifically comprises:
finding out all the end point pairs which should be connected according to the end point direction;
the likelihood of a pair of endpoints being connected is measured by the following four conditions:
the Euclidean distance of the two endpoints; the included angle of the two end point directions; two endpoints cannot belong to the same connected domain; smoothness after connection of the two endpoints.
9. The method for extracting blood vessels based on graph cut and fracture filling according to claim 5, wherein the obtaining of the radius of the blood vessel at each end point and the radius of the blood vessel to be filled according to the result of the blood vessel segmentation, and filling the blood vessel by combining the blood vessel center line specifically comprises:
through traversing all the segmented blood vessel foreground points, judging whether a background point exists in the 26 neighborhoods of the blood vessel foreground points;
and extracting a vessel surface voxel set VS, wherein the vessel radius of the end point is as follows:
d＝min(dist(endpoint,I),I∈VS)
wherein endpoint is a blood vessel end point, dist is an Euclidean distance for calculating two points;
assuming that the vessel radius of two end points to be connected is d1 and d2, respectively, the radius of the vessel to be completed is (d1+ d2)/2, and then the vessel is completed according to the vessel center line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110084518.8A CN112862884A (en) | 2021-01-21 | 2021-01-21 | Blood vessel extraction method based on graph cutting and fracture completion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110084518.8A CN112862884A (en) | 2021-01-21 | 2021-01-21 | Blood vessel extraction method based on graph cutting and fracture completion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862884A true CN112862884A (en) | 2021-05-28 |
Family
ID=76007721
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110084518.8A Pending CN112862884A (en) | 2021-01-21 | 2021-01-21 | Blood vessel extraction method based on graph cutting and fracture completion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862884A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822897A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Blood vessel segmentation method, terminal and computer-readable storage medium |
| CN116758050A (en) * | 2023-07-12 | 2023-09-15 | 强联智创（北京）科技有限公司 | Method and product for blind completion of central line of intracranial Wills ring blood vessel |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741251A (en) * | 2016-03-17 | 2016-07-06 | 中南大学 | Blood vessel segmentation method for liver CTA sequence image |
-
2021
- 2021-01-21 CN CN202110084518.8A patent/CN112862884A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105741251A (en) * | 2016-03-17 | 2016-07-06 | 中南大学 | Blood vessel segmentation method for liver CTA sequence image |
Non-Patent Citations (1)
| Title |
|---|
| XIAOYU GUO等: "A novel method to model hepatic vascular network using vessel segmentation, thinning, and completion", 《MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING》, vol. 58, pages 2 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113822897A (en) * | 2021-11-22 | 2021-12-21 | 武汉楚精灵医疗科技有限公司 | Blood vessel segmentation method, terminal and computer-readable storage medium |
| CN116758050A (en) * | 2023-07-12 | 2023-09-15 | 强联智创（北京）科技有限公司 | Method and product for blind completion of central line of intracranial Wills ring blood vessel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020001217A1 (en) | Segmentation method for dissected aorta in ct image based on convolutional neural network | |
| CN112716446B (en) | Method and system for measuring pathological change characteristics of hypertensive retinopathy | |
| WO2022100495A1 (en) | Method for automatically segmenting ground-glass pulmonary nodule and computer device | |
| WO2022063198A1 (en) | Lung image processing method, apparatus and device | |
| WO2019000455A1 (en) | Method and system for segmenting image | |
| CN109272512B (en) | Method for automatically segmenting left ventricle inner and outer membranes | |
| CN112862884A (en) | Blood vessel extraction method based on graph cutting and fracture completion | |
| CN110796670B (en) | Dissection method and device for dissecting interbed artery | |
| Ye et al. | Automatic graph cut segmentation of lesions in CT using mean shift superpixels | |
| CN111242958B (en) | Carotid artery cascade learning segmentation method based on structural feature optimization | |
| US7394933B2 (en) | Region competition via local watershed operators | |
| CN114757960B (en) | Tooth segmentation and reconstruction method based on CBCT image and storage medium | |
| KR20220108158A (en) | Method for Severity Determination of Skin Diseases Based on Percentage of Body Surface Area Covered with Lesions | |
| WO2022048171A1 (en) | Method and apparatus for measuring blood vessel diameter in fundus image | |
| JP2005278690A (en) | Method for detecting nodular shadow from three-dimensional chest ct image using computer, apparatus therefor and computer program | |
| CN114155193B (en) | Blood vessel segmentation method and device based on feature enhancement | |
| Shi et al. | Hamilton–Jacobi skeleton on cortical surfaces | |
| CN111080556A (en) | Method, system, equipment and medium for strengthening trachea wall of CT image | |
| CN113935961A (en) | Robust breast molybdenum target MLO (Multi-level object) visual angle image pectoral muscle segmentation method | |
| CN113139929A (en) | Gastrointestinal tract endoscope image preprocessing method comprising information screening and fusion repairing | |
| CN113012127A (en) | Cardiothoracic ratio measuring method based on chest medical image | |
| Shao et al. | A segmentation method of airway from chest ct image based on vgg-unet neural network | |
| CN116664592A (en) | Image-based arteriovenous blood vessel separation method and device, electronic equipment and medium | |
| CN110942433A (en) | Skull CBCT image-based repair guide plate generation method | |
| CN115908418A (en) | Method, system, equipment and medium for determining central line of aorta CT image |
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 |