CN117830308B - Intelligent contrast analysis method for angiography before and after interventional operation - Google Patents
Intelligent contrast analysis method for angiography before and after interventional operation Download PDFInfo
- Publication number
- CN117830308B CN117830308B CN202410244692.8A CN202410244692A CN117830308B CN 117830308 B CN117830308 B CN 117830308B CN 202410244692 A CN202410244692 A CN 202410244692A CN 117830308 B CN117830308 B CN 117830308B
- Authority
- CN
- China
- Prior art keywords
- edge
- pixel point
- edge pixel
- blood vessel
- curve
- 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
- 238000002583 angiography Methods 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 112
- 238000003708 edge detection Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 38
- 230000002792 vascular Effects 0.000 claims description 19
- 230000002980 postoperative effect Effects 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 230000003014 reinforcing effect Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013152 interventional procedure Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002526 effect on cardiovascular system Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000926 neurological effect Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- 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
- G06T2207/20081—Training; Learning
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention relates to the field of image data processing, in particular to an intelligent contrast analysis method for angiography before and after interventional operation, which comprises the following steps: acquiring an angiographic image and edge pixel points and a first edge curve and a second edge curve of the edge pixel points in the angiographic image after edge detection; obtaining the blood vessel feature confidence coefficient and the suspected blood vessel width of each edge pixel point according to the first edge curve and the second edge curve of each edge pixel point; obtaining the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of each edge pixel point; and obtaining an enhanced angiography image according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located. The invention enhances the different areas of the angiography image to different degrees, thereby improving the efficiency of intelligent contrast analysis.
Description
Technical Field
The invention relates to the field of image data processing, in particular to an intelligent contrast analysis method for angiography before and after interventional operation.
Background
With the continued advancement of technology, interventional procedures are becoming increasingly popular for the treatment of cardiovascular, neurological and other diseases. These procedures often use angiography to guide the physician through precise procedures, so intelligent contrast analysis of the angiographic images before and after the procedure becomes critical, and of course, enhancement of the images prior to analysis of the angiographic images is also important, which not only involves the physician to accurately locate and evaluate vascular structures, but also relates to the accuracy and safety of the procedure.
When the angiography image is directly enhanced through histogram equalization, the thickness degree, the distribution condition, the background interference and the like of blood vessels in different areas in the angiography image are different, so that the local contrast of partial areas is possibly distorted, the partial details of the blood vessels are difficult to embody, and the accuracy of angiography contrast analysis before and after an operation is reduced.
Disclosure of Invention
The invention provides an intelligent contrast analysis method for angiography before and after interventional operation, which aims to solve the existing problems.
The intelligent contrast analysis method for angiography before and after interventional operation adopts the following technical scheme:
An embodiment of the invention provides an intelligent contrast analysis method for angiography before and after interventional operation, which comprises the following steps:
acquiring angiography images before and after an operation and edge pixel points in the angiography images after edge detection;
Obtaining a first edge curve and a second edge curve of the edge pixel point according to the gray value of the edge pixel point; obtaining the blood vessel feature confidence coefficient of each edge pixel point according to the first edge curve and the second edge curve of each edge pixel point;
Constructing a window area of each edge pixel point; obtaining the suspected blood vessel width of each edge pixel point according to the distance between the pixel points on the first edge curve and the second edge curve of each edge pixel point; obtaining an adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of the edge pixel point in the window area of each edge pixel point;
Clustering all edge pixel points according to the blood vessel feature confidence coefficient of each edge pixel point to obtain a plurality of clustering clusters; obtaining the final confidence coefficient of the blood vessel feature of each edge pixel point according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located;
obtaining an enhanced angiography image according to the final confidence coefficient of the vascular characteristics of each edge pixel point; obtaining angiography contrast results before and after an operation according to the enhanced angiography image;
The method comprises the following specific steps of:
Obtaining a connected domain of each edge pixel point according to the gray level of the pixel point by using a region growing algorithm, marking the connected domain of each edge pixel point as a first edge curve of each edge pixel point, determining a first gray range corresponding to each edge pixel point according to the gray maximum value and the gray minimum value of the pixel point in the connected domain of each edge pixel point, and constructing by taking each edge pixel point as the center Local area of size, the/>Determining a second gray scale range corresponding to each edge pixel point according to the gray scale maximum value and the gray scale minimum value of the pixel points in the local area of each edge pixel point, marking out the pixel points with gray scale values in the second gray scale range in all the pixel points except the first edge curve in the local area, and performing curve fitting on the marked pixel points by using a least square method to obtain a second edge curve of each edge pixel point;
the blood vessel feature confidence coefficient of each edge pixel point is obtained according to the first edge curve and the second edge curve of each edge pixel point, and the specific formula is as follows:
；
Wherein, Represents the/>Vascular feature confidence of each edge pixel point,/>Represents the/>The number of pixel points on the first edge curve corresponding to the edge pixel points,/>Represents the/>The number of pixel points on the second edge curve corresponding to the edge pixel points,/>Representing an exponential function based on a natural constant,/>Representing absolute value functions,/>Represents the/>First edge curve corresponding to each edge pixel pointPixel dot and/>Slope of straight line formed by each pixel point,/>Represents the/>The/>, in the second edge curve corresponding to each edge pixel pointPixel dot and the firstSlope of straight line formed by each pixel point,/>Represents the/>First edge curve corresponding to each edge pixel pointThe/>, of the second edge curve and the pixel pointsDistance between individual pixels,/>Represent the firstFirst edge curve corresponding to each edge pixel pointFirst/>, in the pixel and second edge curvesA distance between the individual pixel points;
The construction of the window area of each edge pixel point comprises the following specific steps:
Each edge pixel point is taken as a center point to construct the pixel with the size of As a window area for each edge pixel, said/>The preset side length is set;
further, the obtaining the suspected blood vessel width of each edge pixel point according to the distance between the pixel points on the first edge curve and the second edge curve of each edge pixel point comprises the following specific steps:
Will be the first First edge curve of each edge pixel point/>First/>, in the point-to-second edge curveDistance of individual points/>And/>First edge curve of each edge pixel point/>The first point and the second edge curveDistance of individual points/>The ratio of (2) is recorded as (1) >Obtaining the suspected blood vessel width of each edge pixel point according to the first ratio of each edge pixel point and the minimum value of the pixel point numbers in the first edge curve and the second edge curve of each edge pixel point;
the method comprises the steps of obtaining the suspected blood vessel width of each edge pixel point according to the first ratio of each edge pixel point and the minimum value of the pixel point number in the first edge curve and the second edge curve of each edge pixel point, wherein the specific formulas are as follows:
；
Wherein, Represents the/>Suspected vessel width of each edge pixel,/>And/>Respectively represent the/>The number of the pixel points in the first edge curve and the second edge curve of each edge pixel point,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the point-to-second edge curveDistance of individual points,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the individual points and second edge curvesDistance of individual points,/>Representation/>And/>Minimum value of/>For/>A first ratio of edge pixels;
The method comprises the steps of obtaining an adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of the edge pixel point in a window area of each edge pixel point, wherein the adjustment coefficient comprises the following specific formulas:
；
Wherein, Represents the/>Adjustment coefficient of blood vessel feature confidence coefficient of each edge pixel point,/>Representing the current/>The number of edge pixel points except the center point in the window area of each edge pixel point,/>Represents the/>First/>, except for the center point, within the window area of each edge pixel pointSuspected vessel width of each edge pixel,/>Represents the/>The suspected blood vessel width of each edge pixel point;
the final confidence coefficient of the blood vessel feature of each edge pixel point is obtained according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located, and the method comprises the following specific steps:
Will be the first Vascular feature confidence, th/>, of individual edge pixelsAdjustment coefficient and/>, of blood vessel feature confidence coefficient of each edge pixel pointThe product of the number of edge pixel points in the cluster where the edge pixel points are located is recorded as a normalized value of the productVascular feature final confidence/>, of individual edge pixels。
Further, the obtaining the enhanced angiography image according to the final confidence coefficient of the vascular feature of each edge pixel point comprises the following specific steps:
According to the final confidence coefficient of the vascular characteristics of each edge pixel point, utilizing Clustering all edge pixel points again by using a clustering algorithm to obtain a plurality of new clusters, determining the boundary of each new cluster by using a convex hull algorithm, dividing an angiography image into a plurality of areas according to the boundaries of all new clusters, and reinforcing each area by using self-adaptive histogram equalization to obtain a plurality of reinforced areas; the image of all the enhancement regions is noted as an enhanced angiographic image.
Further, the method for obtaining the angiographic contrast results before and after the operation according to the enhanced angiographic image comprises the following specific steps:
And aligning the enhanced angiographic images before and after the operation by utilizing image registration to obtain abnormal areas in the angiographic images before and after the operation.
The technical scheme of the invention has the beneficial effects that: acquiring an angiography image and edge pixel points in the angiography image after edge detection; obtaining a first edge curve and a second edge curve of the edge pixel point according to the gray value of the edge pixel point; obtaining the suspected blood vessel width of each edge pixel point according to the blood vessel similarity of the window area where each edge pixel point is positioned; according to the suspected blood vessel width of each edge pixel point, the blood vessel feature confidence coefficient of each edge pixel point is obtained, and the blood vessel judging efficiency is improved; clustering all edge pixel points according to the blood vessel feature confidence coefficient of each edge pixel point to obtain a plurality of clustering clusters; obtaining the final confidence coefficient of the blood vessel feature of each edge pixel point according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located; according to the final confidence coefficient of the blood vessel characteristics of each edge pixel point, an enhanced angiography image is obtained, the contrast in different areas is improved, the problem of excessive enhancement is avoided, analysis of internal blood vessel distribution and detail information is facilitated, and accuracy of angiography contrast analysis before and after operation is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of an intelligent contrast analysis method for angiography before and after interventional operation according to the present invention;
FIG. 2 is an angiographic raw gray scale image;
fig. 3 is a Canny operator edge detection image of an angiographic image.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the intelligent contrast analysis method for angiography before and after interventional operation according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an intelligent contrast analysis method for angiography before and after interventional operation, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of an intelligent contrast analysis method for angiography before and after an interventional procedure according to an embodiment of the invention is shown, the method includes the following steps:
step S001: acquiring angiographic images before and after operation and edge pixel points in the angiographic images after edge detection.
Specifically, the angiographic images before and after the operation are obtained by using a digital subtraction angiography technology, as shown in fig. 2, in this embodiment, any angiographic image is taken as an example to perform subsequent analysis, and the angiographic image is preprocessed by a Canny operator edge detection algorithm, so as to obtain a preprocessed angiographic image, as shown in fig. 3, where the digital subtraction angiography technology and the Canny operator edge detection algorithm are both known technologies, and the specific method is not described herein.
So far, an original image and a preprocessed angiographic image are obtained.
Step S002: obtaining a first edge curve and a second edge curve of the edge pixel point according to the gray value of the edge pixel point; and obtaining the blood vessel feature confidence coefficient of each edge pixel point according to the first edge curve and the second edge curve of each edge pixel point.
It should be noted that, because the blood vessel has continuity and the edges on both sides of the blood vessel are parallel, all edge pixel points are obtained according to the preprocessed angiography image, and all edge pixel points are positioned in the original image, and the degree that each edge pixel point accords with the blood vessel characteristics in a certain local area is analyzed.
Specifically, the connected domain of each edge pixel point is obtained according to the gray level of the pixel point by using a region growing algorithm, the connected domain of each edge pixel point is marked as a first edge curve of each edge pixel point on an image, wherein the region growing algorithm is a known technology, a specific method is not described herein, then the first gray range corresponding to each edge pixel point is determined according to the gray maximum value and the gray minimum value of the pixel point in the connected domain of each edge pixel point, and the preset edge length in this embodiment isTaking this as an example, other values may be set in other embodiments, and this example is not limited, and is constructed/>, centered on each edge pixel pointAnd traversing all the pixel points except the pixel points forming the connected domain in the local area, screening and marking the pixel points in the second gray level range, performing curve fitting on the marked pixel points by using a least square method, and marking the curve obtained by fitting as a second edge curve of the edge pixel points, wherein the least square method is a known technology, and the specific method is not described herein.
Calculating the first according to the characteristic expression of the two curves of the edge pixel points conforming to the blood vesselThe blood vessel feature confidence of each edge pixel point is calculated according to the following specific formula:
；
Wherein, Represents the/>Vascular feature confidence of each edge pixel point,/>Represents the/>The number of pixel points on the first edge curve corresponding to the edge pixel points,/>Represents the/>The number of pixel points on the second edge curve corresponding to the edge pixel points,/>Representing an exponential function based on a natural constant,/>Representing absolute value functions,/>Represents the/>First edge curve corresponding to each edge pixel pointPixel dot and/>Slope of straight line formed by each pixel point,/>Represents the/>The/>, in the second edge curve corresponding to each edge pixel pointIndividual pixel dot and/>Slope of straight line formed by each pixel point,/>Represents the/>First edge curve corresponding to each edge pixel pointThe/>, of the second edge curve and the pixel pointsDistance between individual pixels,/>Represents the/>First edge curve corresponding to each edge pixel pointFirst/>, in the pixel and second edge curvesDistance between individual pixels.
In the formula (i),Representation from the overall analysis, current/>The similarity of the first and second edge curves corresponding to the edge pixel points is relatively uniform because the two side edges of the blood vessel are relatively symmetrical. This embodiment is therefore directed to the method described by/>And analyzing the two side edges of the suspected blood vessel, namely the first edge curve and the second edge curve, which are determined by the edge pixel points, wherein the smaller the difference is, the higher the similarity of the first edge curve and the second edge curve on the whole is, and the more likely the first edge curve and the second edge curve are the true edges of the blood vessel. Of course this is only an initial determination and it is also necessary to combine analysis on the slave parts to determine the final confidence level.
In the formula (i),Indicating that the slope difference and the distance difference of the first and second edge curves are analyzed on a part-by-part basis. Because the edges of the two sides of the blood vessel are relatively parallel and the thickness of the blood vessel is relatively consistent in the blood vessel characteristics, the embodiment can be converted into a formula by comparing the slope difference between the corresponding points of the two curves and the extension distance difference of the two curves. The smaller the difference between the two is, the more likely the two side edges of the suspected blood vessel corresponding to the pixel point of the current edge are the true edges of the blood vessel. Meanwhile, the present embodiment combines the above-mentioned overall analysis to determine the probability that the current edge pixel point meets the vascular feature, namely, the first/>Vascular confidence of individual edge points.
Therefore, it isThe smaller the channel/>After treatment,/>The larger the corresponding vascular feature confidence is, the higher the confidence is.
According to the mode, the blood vessel feature confidence coefficient of each edge pixel point is obtained.
So far, the blood vessel feature confidence coefficient of each edge pixel point is obtained.
Step S003: constructing a window area of each edge pixel point; obtaining the suspected blood vessel width of each edge pixel point according to the distance between the pixel points on the first edge curve and the second edge curve of each edge pixel point; and obtaining an adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of the edge pixel point in the window area of each edge pixel point.
It should be noted that, through the above procedure, the confidence of the blood vessel feature of each edge pixel point is calculated in this embodiment, but a continuous and similar interference edge portion to the blood vessel feature may also occur due to the possible background interference. In this case, the present embodiment can use regional blood vessel similarity, which means that the distribution of blood vessels in the human body is that each capillary vessel extends from a continuous main blood vessel, so that, in general, coarse blood vessels are distributed more around coarse blood vessels, and fine blood vessels are distributed around fine blood vessels naturally.
Specifically, each edge pixel point is taken as a center point to construct a pixel structure with the size ofThe window area of the pixel point of each edge is taken as the window area of each edge, and the preset side length/>, of the embodimentTaking this as an example for illustration, other values may be set in other embodiments, which are not limited in this embodiment, and according to the suspected blood vessel width of the edge pixel points except the center point in the window area where each edge pixel point is located, the adjustment coefficient of the blood vessel feature confidence coefficient of the edge pixel point is calculated, where the calculation formula is as follows:
；
Wherein, Represents the/>The suspected vessel width of each edge pixel point is determined based on the local area of the edge pixel point,/>And/>Respectively represent the/>The number of the pixel points in the first edge curve and the second edge curve of each edge pixel point,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the point-to-second edge curveDistance of individual points,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the individual points and second edge curvesDistance of individual points,/>The minimum value of the two is taken, and the whole expression of the formula takes the average curve distance of the local area where the pixel point of the current certain edge is positioned as the width of the corresponding suspected blood vessel.
Wherein,Represents the/>Adjustment coefficient of blood vessel feature confidence coefficient of each edge pixel point,/>Representing the current/>The number of edge pixel points except the center point in the window area of each edge pixel point,/>Represents the/>First/>, except for the center point, within the window area of each edge pixel pointSuspected vessel width of each edge pixel,/>Represents the/>The suspected vessel width of each edge pixel.
In the formula (i),Representing the current/>The ratio of the difference of the width of the suspected blood vessels corresponding to each edge point in the 24 neighborhood of each edge point to the total suspected blood vessel difference is that when the difference of the width of the suspected blood vessels is smaller, the two suspected blood vessels are more consistent with the similarity of the regional blood vessels, so the method passes through the ratio of/>And a larger adjustment coefficient is given to the test piece, so that the confidence level obtained by the test piece is larger.
The integral formula is compared one by one, and the average value is obtained to obtain the final firstAnd adjusting the coefficient of the blood vessel confidence of each edge point.
According to the mode, the adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point is obtained.
So far, the adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point is obtained.
Step S004: clustering all edge pixel points according to the blood vessel feature confidence coefficient of each edge pixel point to obtain a plurality of clustering clusters; and obtaining the final confidence coefficient of the blood vessel feature of each edge pixel point according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located.
By the above-mentioned process, the present embodiment determines the adjustment coefficient of the blood vessel feature confidence of each edge pixel point through the regional blood vessel similarity. The embodiment can be replaced by another angle for analysis, because the edge pixel points corresponding to the blood vessel are continuous, the corresponding confidence degrees are similar, and certain background points or interference points are not continuous, so that the embodiment can obtain a plurality of clustering clusters with different degrees through k-means clustering so as to eliminate the interference of the continuous background points or interference points.
Specifically, according to the blood vessel feature confidence of the edge pixel point, the method utilizesThe algorithm clusters all edge pixel points, and the preset cluster number/>, in the embodimentIn the description of this example, other values may be set in other embodiments, and the example is not limited thereto, where/>The clustering algorithm is a well-known technique, and the specific method is not described here, and the following needs to be described: taking the blood vessel feature confidence coefficient of each edge pixel point as a gray value of the edge pixel point, carrying out clustering operation, counting the number of the edge pixel points contained in each cluster, taking the number of the edge pixel points as a parameter of the cluster where each edge pixel point is located, and calculating the final blood vessel feature confidence coefficient of each edge pixel point according to the blood vessel feature confidence coefficient of each edge pixel point, an adjustment coefficient of the blood vessel feature confidence coefficient and the parameter of the cluster where each edge pixel point is located, wherein the calculation formula is as follows:
；
Wherein, Represents the/>Final confidence of vascular features of each edge pixel point,/>Represents the/>Vascular feature confidence of each edge pixel point,/>Represents the/>Adjustment coefficient of blood vessel feature confidence coefficient of each edge pixel point,/>Represent the firstThe number of edge pixel points in the cluster where the edge pixel points are located,/>The normalization process is represented.
According to the mode, the final confidence of the blood vessel characteristics of each edge pixel point is obtained.
Step S005: obtaining an enhanced angiography image according to the final confidence coefficient of the vascular characteristics of each edge pixel point; and obtaining angiography contrast results before and after the operation according to the enhanced angiography images.
Specifically, according to the final confidence of the vascular characteristics of each edge pixel point, the method utilizesClustering each edge pixel point by a clustering algorithm to obtain a plurality of new clusters, wherein the DBSCAN algorithm is a known technology, a specific method is not described herein, the boundary of each new cluster is determined by a convex hull algorithm, an image is divided into a plurality of areas according to the boundaries of all the new clusters, the convex hull algorithm is a known technology, a specific method is not described herein, and each area is respectively enhanced by using self-adaptive histogram equalization to obtain a plurality of enhanced areas; the image formed by all the enhancement regions is recorded as an enhanced angiographic image, wherein the histogram equalization algorithm is a well-known technique, and the specific method is not described herein.
The enhanced pre-operative and post-operative angiographic images are aligned using image registration, which is a well-known technique, and specific methods are not described herein, to obtain the abnormal regions in the pre-operative and post-operative angiographic images.
The present invention has been completed.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (2)
1. An intelligent contrast analysis method for angiography before and after interventional operation is characterized by comprising the following steps:
acquiring angiography images before and after an operation and edge pixel points in the angiography images after edge detection;
Obtaining a first edge curve and a second edge curve of the edge pixel point according to the gray value of the edge pixel point; obtaining the blood vessel feature confidence coefficient of each edge pixel point according to the first edge curve and the second edge curve of each edge pixel point;
Constructing a window area of each edge pixel point; obtaining the suspected blood vessel width of each edge pixel point according to the distance between the pixel points on the first edge curve and the second edge curve of each edge pixel point; obtaining an adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of the edge pixel point in the window area of each edge pixel point;
Clustering all edge pixel points according to the blood vessel feature confidence coefficient of each edge pixel point to obtain a plurality of clustering clusters; obtaining the final confidence coefficient of the blood vessel feature of each edge pixel point according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located;
obtaining an enhanced angiography image according to the final confidence coefficient of the vascular characteristics of each edge pixel point; obtaining angiography contrast results before and after an operation according to the enhanced angiography image;
The method comprises the following specific steps of:
Obtaining a connected domain of each edge pixel point according to the gray level of the pixel point by using a region growing algorithm, marking the connected domain of each edge pixel point as a first edge curve of each edge pixel point, determining a first gray range corresponding to each edge pixel point according to the gray maximum value and the gray minimum value of the pixel point in the connected domain of each edge pixel point, and constructing by taking each edge pixel point as the center Local area of size, the/>Determining a second gray scale range corresponding to each edge pixel point according to the gray scale maximum value and the gray scale minimum value of the pixel points in the local area of each edge pixel point, marking out the pixel points with gray scale values in the second gray scale range in all the pixel points except the first edge curve in the local area, and performing curve fitting on the marked pixel points by using a least square method to obtain a second edge curve of each edge pixel point;
the blood vessel feature confidence coefficient of each edge pixel point is obtained according to the first edge curve and the second edge curve of each edge pixel point, and the specific formula is as follows:
；
Wherein, Represents the/>Vascular feature confidence of each edge pixel point,/>Represents the/>The number of pixel points on the first edge curve corresponding to the edge pixel points,/>Represents the/>The number of pixel points on the second edge curve corresponding to the edge pixel points,/>Representing an exponential function based on a natural constant,/>Representing absolute value functions,/>Represents the/>First edge curve corresponding to each edge pixel pointPixel dot and/>Slope of straight line formed by each pixel point,/>Represents the/>The/>, in the second edge curve corresponding to each edge pixel pointPixel dot and the firstSlope of straight line formed by each pixel point,/>Represents the/>First edge curve corresponding to each edge pixel pointThe/>, of the second edge curve and the pixel pointsDistance between individual pixels,/>Represent the firstFirst edge curve corresponding to each edge pixel pointFirst/>, in the pixel and second edge curvesA distance between the individual pixel points;
The construction of the window area of each edge pixel point comprises the following specific steps:
Each edge pixel point is taken as a center point to construct the pixel with the size of As a window area for each edge pixel, said/>The preset side length is set;
The method for obtaining the suspected blood vessel width of each edge pixel point according to the distance between the pixel points on the first edge curve and the second edge curve of each edge pixel point comprises the following specific steps:
Will be the first First edge curve of each edge pixel point/>First/>, in the point-to-second edge curveDistance of individual pointsAnd/>First edge curve of each edge pixel point/>The first point and the second edge curveDistance of individual points/>The ratio of (2) is recorded as (1) >Obtaining the suspected blood vessel width of each edge pixel point according to the first ratio of each edge pixel point and the minimum value of the pixel point numbers in the first edge curve and the second edge curve of each edge pixel point;
the method comprises the steps of obtaining the suspected blood vessel width of each edge pixel point according to the first ratio of each edge pixel point and the minimum value of the pixel point number in the first edge curve and the second edge curve of each edge pixel point, wherein the specific formulas are as follows:
；
Wherein, Represents the/>Suspected vessel width of each edge pixel,/>And/>Respectively represent the/>The number of the pixel points in the first edge curve and the second edge curve of each edge pixel point,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the point-to-second edge curveDistance of individual points,/>Represents the/>First edge curve of each edge pixel point/>First/>, in the individual points and second edge curvesThe distance between the points of interest,Representation/>And/>Minimum value of/>For/>A first ratio of edge pixels;
The method comprises the steps of obtaining an adjustment coefficient of the blood vessel feature confidence coefficient of each edge pixel point according to the suspected blood vessel width of the edge pixel point in a window area of each edge pixel point, wherein the adjustment coefficient comprises the following specific formulas:
；
Wherein, Represents the/>Adjustment coefficient of blood vessel feature confidence coefficient of each edge pixel point,/>Representing the current/>The number of edge pixel points except the center point in the window area of each edge pixel point,/>Represents the/>First/>, except for the center point, within the window area of each edge pixel pointSuspected vessel width of each edge pixel,/>Represents the/>The suspected blood vessel width of each edge pixel point;
the final confidence coefficient of the blood vessel feature of each edge pixel point is obtained according to the blood vessel feature confidence coefficient of each edge pixel point, the adjustment coefficient of the blood vessel feature confidence coefficient and the number of the edge pixel points of the cluster where each edge pixel point is located, and the method comprises the following specific steps:
Will be the first Vascular feature confidence, th/>, of individual edge pixelsAdjustment coefficient and/>, of blood vessel feature confidence coefficient of each edge pixel pointThe product of the number of edge pixel points in the cluster where the edge pixel points are located is recorded as a normalized value of the productVascular feature final confidence/>, of individual edge pixels；
The method for obtaining the enhanced angiography image according to the final confidence coefficient of the vascular characteristics of each edge pixel point comprises the following specific steps: according to the final confidence coefficient of the vascular characteristics of each edge pixel point, utilizingClustering all edge pixel points again by using a clustering algorithm to obtain a plurality of new clusters, determining the boundary of each new cluster by using a convex hull algorithm, dividing an angiography image into a plurality of areas according to the boundaries of all new clusters, and reinforcing each area by using self-adaptive histogram equalization to obtain a plurality of reinforced areas; the image of all the enhancement regions is noted as an enhanced angiographic image.
2. The intelligent contrast analysis method for preoperative and postoperative angiography according to claim 1, wherein the step of obtaining the preoperative and postoperative angiography contrast results from the enhanced angiography images comprises the following specific steps:
And aligning the enhanced angiographic images before and after the operation by utilizing image registration to obtain abnormal areas in the angiographic images before and after the operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410244692.8A CN117830308B (en) | 2024-03-05 | 2024-03-05 | Intelligent contrast analysis method for angiography before and after interventional operation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410244692.8A CN117830308B (en) | 2024-03-05 | 2024-03-05 | Intelligent contrast analysis method for angiography before and after interventional operation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117830308A CN117830308A (en) | 2024-04-05 |
| CN117830308B true CN117830308B (en) | 2024-05-10 |
Family
ID=90504340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410244692.8A Active CN117830308B (en) | 2024-03-05 | 2024-03-05 | Intelligent contrast analysis method for angiography before and after interventional operation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117830308B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118052745B (en) * | 2024-04-16 | 2024-06-18 | 摸鱼科技(大连)有限公司 | Gynecological cervical image enhancement processing method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120031A (en) * | 2019-04-02 | 2019-08-13 | 四川锦江电子科技有限公司 | A kind of method and apparatus obtaining vascular flow deposit score |
| CN113723418A (en) * | 2021-09-03 | 2021-11-30 | 乐普（北京）医疗器械股份有限公司 | Method and device for optimally processing contrast images |
| WO2022105647A1 (en) * | 2020-11-23 | 2022-05-27 | 西安科锐盛创新科技有限公司 | Method for establishing enhanced three-dimensional model of intracranial angiography |
| CN116138877A (en) * | 2022-11-29 | 2023-05-23 | 中国科学院自动化研究所 | Target positioning method, target positioning device, electronic equipment and storage medium |
| WO2023237034A1 (en) * | 2022-06-10 | 2023-12-14 | 中国医学科学院北京协和医院 | Image reconstruction and analysis method, system, and device based on saline radiography electrical impedance lung perfusion and cardiac imaging |
| CN117237243A (en) * | 2023-11-16 | 2023-12-15 | 大连壹致科技有限公司 | Local self-adaptive enhancement method for angiocardiography image |
| CN117392128A (en) * | 2023-12-11 | 2024-01-12 | 华中科技大学同济医学院附属协和医院 | Artificial intelligent measuring method for aortic diameter |
| CN117557460A (en) * | 2024-01-12 | 2024-02-13 | 济南科汛智能科技有限公司 | Angiography image enhancement method |
-
2024
- 2024-03-05 CN CN202410244692.8A patent/CN117830308B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110120031A (en) * | 2019-04-02 | 2019-08-13 | 四川锦江电子科技有限公司 | A kind of method and apparatus obtaining vascular flow deposit score |
| WO2022105647A1 (en) * | 2020-11-23 | 2022-05-27 | 西安科锐盛创新科技有限公司 | Method for establishing enhanced three-dimensional model of intracranial angiography |
| CN113723418A (en) * | 2021-09-03 | 2021-11-30 | 乐普（北京）医疗器械股份有限公司 | Method and device for optimally processing contrast images |
| WO2023237034A1 (en) * | 2022-06-10 | 2023-12-14 | 中国医学科学院北京协和医院 | Image reconstruction and analysis method, system, and device based on saline radiography electrical impedance lung perfusion and cardiac imaging |
| CN116138877A (en) * | 2022-11-29 | 2023-05-23 | 中国科学院自动化研究所 | Target positioning method, target positioning device, electronic equipment and storage medium |
| CN117237243A (en) * | 2023-11-16 | 2023-12-15 | 大连壹致科技有限公司 | Local self-adaptive enhancement method for angiocardiography image |
| CN117392128A (en) * | 2023-12-11 | 2024-01-12 | 华中科技大学同济医学院附属协和医院 | Artificial intelligent measuring method for aortic diameter |
| CN117557460A (en) * | 2024-01-12 | 2024-02-13 | 济南科汛智能科技有限公司 | Angiography image enhancement method |
Non-Patent Citations (1)
| Title |
|---|
| 基于Faster-RCNN的正常数字减影血管造影脑血管检测与时相分期研究;石珂珂;杨恒;肖炜平;胡宙;刘英涛;余锦华;雷宇;;中国临床神经科学;20200720(04);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117830308A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115330800B (en) | Automatic segmentation method of radiotherapy target area based on image processing | |
| CN115359052B (en) | Medical image enhancement method based on clustering algorithm | |
| CN116109663B (en) | Stomach CT image segmentation method based on multi-threshold segmentation | |
| CN115797356B (en) | Nuclear magnetic resonance tumor region extraction method | |
| CN117830308B (en) | Intelligent contrast analysis method for angiography before and after interventional operation | |
| CN116152505A (en) | Bone target identification and segmentation method based on X-ray data | |
| CN116883293B (en) | Image enhancement processing method for nerve anesthesia puncture | |
| CN116630358B (en) | Threshold segmentation method for brain tumor CT image | |
| CN114359288B (en) | Medical image cerebral aneurysm detection and positioning method based on artificial intelligence | |
| CN116912255A (en) | Follicular region segmentation method for ovarian tissue analysis | |
| CN117437492A (en) | White lung feature recognition and segmentation method in lung X-ray image | |
| CN112651507A (en) | Method for constructing microvascular invasion prediction model of hepatocellular carcinoma and probability prediction method | |
| CN117593192B (en) | Gynecological cervical image enhancement analysis method | |
| CN118172380B (en) | Orthopedics leg bone intelligent recognition segmentation method based on local threshold | |
| CN118297812A (en) | Liver cancer pathological image enhancement method based on artificial intelligence | |
| CN116258864B (en) | Village planning construction big data management system | |
| CN118038064B (en) | Image segmentation method for hepatic duct and biliary tract calculus | |
| CN118397023B (en) | Trigeminal region segmentation method based on MRI | |
| CN116167949B (en) | Clinical auxiliary decision-making system based on medical image big data | |
| CN117974692B (en) | Ophthalmic medical image processing method based on region growing | |
| CN118247277B (en) | Self-adaptive enhancement method for lung CT image | |
| CN118052745B (en) | Gynecological cervical image enhancement processing method | |
| CN118135335B (en) | Brain injury CT image optimization classification method based on machine learning | |
| CN117575977B (en) | Follicular region enhancement method for ovarian tissue analysis | |
| CN118379313B (en) | Method for dividing medical images of intracranial arteriosclerosis plaques of patients suffering from atrial fibrillation |
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 |