CN106777725B - Verification method and device for microcirculation image algorithm - Google Patents
Verification method and device for microcirculation image algorithm Download PDFInfo
- Publication number
- CN106777725B CN106777725B CN201611214146.1A CN201611214146A CN106777725B CN 106777725 B CN106777725 B CN 106777725B CN 201611214146 A CN201611214146 A CN 201611214146A CN 106777725 B CN106777725 B CN 106777725B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- simulated
- length
- map
- microcirculation
- 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
- 230000004089 microcirculation Effects 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000012795 verification Methods 0.000 title claims abstract description 45
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 285
- 238000004088 simulation Methods 0.000 claims abstract description 19
- 238000009877 rendering Methods 0.000 claims description 20
- 238000004458 analytical method Methods 0.000 abstract description 11
- 230000000007 visual effect Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000017531 blood circulation Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012634 optical imaging Methods 0.000 description 2
- 235000016735 Manihot esculenta subsp esculenta Nutrition 0.000 description 1
- 241000658379 Manihot esculenta subsp. esculenta Species 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 239000002207 metabolite Substances 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a verification method of a microcirculation image algorithm, which comprises the following steps: the method comprises the steps that a microcirculation simulation camera generates a simulated blood vessel map, and the width and the length of each blood vessel in the simulated blood vessel map are obtained through a pixel method; calculating the simulated vessel map through a microcirculation image algorithm to obtain the width and the length of each vessel in the simulated vessel map; and if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent, evaluating that the microcirculation image algorithm is effective. The verification method of the microcirculation algorithm solves the problems that the existing verification method cannot perform accurate analysis and the simulation mode is too limited, is convenient and quick, is beneficial to large-scale analysis, and is more visual and effective.
Description
Technical Field
The invention relates to the field of algorithm verification, in particular to a verification method and device for a microcirculation image algorithm.
Background
Microcirculation is the transport of O in the human blood circulation system2And nutrients to tissue cells and transport CO away2And the final and most important ones of the metabolites, microcirculatory perfusion impairment will cause severe metabolic disturbance, which in turn will cause failure of various tissues and organs and lead to death. And the microcirculation image algorithm performs algorithm analysis on a blood vessel distribution map generated by microcirculation optical imaging to obtain various physiological parameter values of the microcirculation state and perform data display. At present, the accuracy of the image processing algorithm on the analysis of the microcirculation blood vessel parameters is verified, the judgment is mainly carried out by adopting artificial naked eyes, and the result accuracy of the image processing algorithm is qualitatively judged by the experience of medical experts. This is achieved byThe verification judgment method is lack of scientific theoretical basis, cannot perform quantitative analysis and is difficult to realize batch statistical analysis verification.
Another common method of algorithmic verification is to record a video using physical simulation. The substance is a simulated blood vessel channel using a plastic tube with an inner diameter of 11mm, and water and cooked cassava powder are mixed to form a blood flow. Such a blood vessel simulation method is too fixed and troublesome, and the size of the diameter of the blood vessel that can be simulated is limited.
Disclosure of Invention
The embodiment of the invention aims to provide a verification method and a verification device for a microcirculation image algorithm, which can effectively solve the problems that the existing verification method cannot perform accurate analysis and the simulation mode is too limited.
In order to achieve the above object, an embodiment of the present invention provides a verification method for a micro-loop image algorithm, including the steps of:
the method comprises the steps that a microcirculation simulation camera generates a simulated blood vessel map, and the width and the length of each blood vessel in the simulated blood vessel map are obtained through a pixel method;
calculating the simulated vessel map through a microcirculation image algorithm to obtain the width and the length of each vessel in the simulated vessel map;
and if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent, evaluating that the microcirculation image algorithm is effective.
Compared with the prior art, the verification method of the microcirculation image algorithm generates the simulated blood vessel map by simulating the microcirculation camera, then obtains the length and the width of each blood vessel in the simulated blood vessel map by respectively using the pixel method and the microcirculation image algorithm, compares the widths and the lengths of the corresponding blood vessels under the two methods, if the lengths and the widths of the corresponding blood vessels are consistent, the microcirculation algorithm is effectively evaluated, the problems that the existing verification method cannot perform accurate analysis and the simulation mode is too limited are solved, and the verification method is convenient and quick, is beneficial to large-scale analysis, is more visual and is more effective.
As an improvement of the above scheme, the generating of the simulated blood vessel map by the simulated microcirculation camera specifically includes the steps of:
initializing n driving points of the simulated vessel map; wherein each driving point is a driving point of a blood vessel central line of a single blood vessel; wherein n is less than 1000;
acquiring a fitting equation of each blood vessel according to a preset type of each blood vessel, and extending from a driving point corresponding to each blood vessel to two sides based on the fitting equation of each blood vessel to obtain a central line of each blood vessel;
expanding the central line of each blood vessel to two sides to generate a canalized blood vessel according to the preset width of each blood vessel, thereby obtaining a simulated blood vessel map of the simulated microcirculation camera; the width of each canalized blood vessel is equal to the width of each corresponding preset blood vessel. Through the process of driving points, central lines and canalization blood vessels, a single blood vessel can be drawn quickly, so that an integral blood vessel distribution simulation diagram is presented.
As an improvement of the scheme, the method further comprises the following steps before obtaining the simulated blood vessel map of the simulated microcirculation camera:
rendering each of the pipelined blood vessels according to preset parameters; the rendering mode comprises rendering of a blood vessel central line, rendering of a blood vessel outline, rendering of a blood vessel number and rendering of a blood vessel key pixel point. Through multiple rendering modes, the imaging of the microcirculation camera can be further simulated, and the method is more intuitive, the picture is more vivid, and the method is closer to the actual situation.
As a modification of the above, the types of the blood vessel include a parabolic type, a vertical type, a horizontal type, and an oblique type.
As an improvement of the above scheme, the obtaining of the centerline of each blood vessel by extending the corresponding driving point of each blood vessel to both sides based on the fitting equation of each blood vessel specifically includes:
generating a first extension part by extending a driving point to the positive direction of an x coordinate axis along a fitting equation, and stopping extending to the positive direction of the x coordinate axis when the first extension part is equal to the length of the preset blood vessel or the first extension part intersects with the boundary of the simulated blood vessel map;
when the first extension part is intersected with the boundary of the simulated blood vessel graph and the length of the first extension part is smaller than the length of a preset blood vessel, extending the driving point to the negative direction of the x coordinate axis along the fitting equation to generate a second extension part; wherein the centerline is comprised of the first and second extensions;
when the sum of the lengths of the first extension part and the second extension part is equal to the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis, and generating a central line of the blood vessel;
and when the second extension part intersects with the boundary of the simulated blood vessel map and the sum of the lengths of the first extension part and the second extension part is less than the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis so as to generate the central line of the blood vessel. The central line of the blood vessel is generated through the above process, the process is simple and quick, and different types of blood vessels can be obtained.
As an improvement of the above scheme, the length of each blood vessel in the simulated blood vessel map obtained by the pixel method specifically includes:
initializing cursors of pixel points on the center line of the blood vessel, and enabling the cursors of the pixel points to point to a first pixel point on the center line;
traversing the cursors of the pixels from the first pixel to the last pixel, and accumulating the side length orObtaining an accumulated value of the side length of the multiple; if the current pixel point is horizontally adjacent to the previous pixel point, accumulating the side length of the current pixel point, and if the current pixel point is vertically adjacent to the previous pixel point, accumulating the side length of the current pixel pointThe length of the side of the times;
and converting the accumulated value into the actual physical size of the central line based on the proportion of the side length and the actual physical size of the pixel point of the simulated blood vessel graph, wherein the actual physical size of the central line is the length of the corresponding blood vessel. The actual physical size is calculated by a pixel method, the real width and length of the simulated blood vessel map can be reflected, the width and length of the blood vessel obtained by the microcirculation algorithm can be compared conveniently, and the microcirculation algorithm can be used as a reliable standard to evaluate whether the microcirculation algorithm is effective or not.
As an improvement of the above scheme, the generation of the simulated blood vessel map by the simulated microcirculation camera specifically comprises the following steps:
calling an opencv image processing open source library to initialize an IpilImage picture variable, and randomly initializing n coordinate points on the IpilImage picture variable; wherein n is less than 1000;
respectively initializing a VesslPicture drawing type variable for each coordinate point, and setting each parameter of each VesslPicture drawing type variable;
drawing the Iplimage picture variable based on each VesslPicture drawing class variable and coordinate point, thereby generating the simulated vessel map. The opencv image processing open source library can realize a plurality of general algorithms in the aspects of image processing and computer vision, can improve the execution speed and the processing speed, and can quickly obtain a distribution simulation diagram of blood vessels.
As an improvement of the above solution, the generating the simulated blood vessel map specifically includes, based on each VesslPicture drawing-like variable and coordinate point, drawing the ipimage picture variable:
writing pixel points of each blood vessel into the IpilImage picture variable by taking each coordinate point as a datum point based on each parameter of each VesslPicture drawing variable;
and refreshing the IplImage picture variable to a Qtable to generate the simulated vessel map.
The embodiment of the invention also correspondingly provides a verification device of the microcirculation image algorithm, which comprises the following steps:
the simulated blood vessel map module is used for simulating a microcirculation camera to generate a simulated blood vessel map, and the width and the length of each blood vessel in the simulated blood vessel map are obtained through a pixel method;
the algorithm operation module is used for obtaining the width and the length of each blood vessel in the simulated blood vessel map after the simulated blood vessel map is operated through a microcirculation image algorithm;
and the algorithm verification module is used for evaluating the effectiveness of the microcirculation image algorithm if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent.
Compared with the prior art, the verification device of the microcirculation image algorithm obtains the simulated blood vessel map through the simulated blood vessel map module, and obtains the width and the length of each blood vessel in the simulated blood vessel map based on a pixel method; then obtaining the width and length of each blood vessel in the simulated blood vessel map under a microcirculation image algorithm through an algorithm operation module; the algorithm verification module compares the width and the length of each blood vessel obtained in the simulated blood vessel image module and the algorithm operation module, if the width and the length of the corresponding blood vessel are equal, the microcirculation image algorithm is effectively evaluated, the problems that the existing verification method cannot perform accurate analysis and the simulation mode is too limited are solved, the method is convenient and quick, mass analysis is facilitated, and the method is more visual and effective.
Drawings
Fig. 1 is a schematic flow chart of a verification method of a micro-loop image algorithm according to a preferred embodiment of the present invention.
FIG. 2 is a schematic flow chart of a preferred embodiment of generating a simulated touch screen in the verification method of the micro-loop image algorithm provided by the invention.
FIG. 3 is a schematic flow chart of a preferred embodiment of generating the center line of the blood vessel in the verification method of the microcirculation image algorithm provided by the present invention.
Fig. 4 is a schematic flow chart of a preferred embodiment of calculating the length of a blood vessel by a pixel method in the verification method of the microcirculation image algorithm provided by the present invention.
FIG. 5 is a schematic flow chart of another preferred embodiment of generating a simulated touch screen in the verification method of the micro-loop image algorithm provided by the invention.
Fig. 6 is a schematic structural diagram of a verification apparatus for a micro-loop image algorithm according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a schematic flow chart of a verification method of a micro-loop image algorithm provided in embodiment 1 of the present invention is shown. The verification method of the micro-loop image algorithm shown in FIG. 1 comprises the following steps:
s1, generating a simulated blood vessel map by the aid of the simulated microcirculation camera, and obtaining the width and length of each blood vessel in the simulated blood vessel map by the aid of a pixel method;
s2, obtaining the width and length of each blood vessel in the simulated blood vessel map after the simulated blood vessel map is operated through a microcirculation image algorithm;
s3, if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained through the pixel method and the microcirculation image algorithm are consistent, the microcirculation image algorithm is evaluated to be effective.
In specific implementation, a simulated blood vessel graph is generated by simulating a microcirculation camera, the simulated blood vessel graph comprises a plurality of blood vessels, and can preferably show a central line, a profile and a serial number of the blood vessels, and the simulated blood vessel graph can be subjected to operations of switching a background graph, adjusting transparency, adjusting image brightness, adjusting pixel points, relaxing and the like, so that the simulated blood vessel graph can be closer to the imaging of the microcirculation camera; calculating the width and the length of each blood vessel in the simulated blood vessel map by a pixel method, and on the other hand, calculating the simulated blood vessel map by a microcirculation image algorithm to obtain the width and the length of each blood vessel in the simulated blood vessel map; and if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent, evaluating the microcirculation image algorithm. In practical operation, a plurality of simulated blood vessel maps can be obtained, the width and the length of each blood vessel of each simulated blood vessel map under the pixel method and the microcirculation image algorithm are obtained respectively, and the effectiveness of the plurality of simulated blood vessel maps is evaluated in batch. In the embodiment, the simulated blood vessel image is obtained by simulating the microcirculation camera, and the microcirculation image algorithm verification is carried out based on the simulated blood vessel image, so that the problems of unscientific and inaccurate microcirculation algorithm verification through naked eye verification are solved, the trouble that a real object of the simulated blood vessel needs to be built to verify the algorithm and the condition that parameters are fixed are avoided, convenience and rapidness are realized, batch analysis can be carried out, and the effectiveness is high.
As shown in fig. 2, in embodiment 1, the step of generating the simulated blood vessel map by the simulated microcirculation camera in step S1 specifically includes the steps of:
s11, initializing n driving points of the simulated blood vessel map; wherein each driving point is a driving point of a blood vessel central line of a single blood vessel; wherein n is less than 1000;
s12, obtaining a fitting equation of each blood vessel according to the type of each preset blood vessel, and extending from the corresponding driving point of each blood vessel to two sides based on the fitting equation of each blood vessel to obtain the central line of each blood vessel;
s13, expanding the central line of each blood vessel to two sides according to the preset width of each blood vessel to generate a canalized blood vessel; wherein the width of each of the canalized blood vessels is equal to the width of each of the corresponding preset blood vessels;
s14, rendering each of the pipelined blood vessels according to preset parameters; the rendering mode comprises rendering of a blood vessel central line, rendering of a blood vessel outline, rendering of a blood vessel number and rendering of a blood vessel key pixel point, so that a simulated blood vessel graph of the simulated microcirculation camera is obtained.
Step S11-S14 is a process of obtaining a simulated blood vessel map in embodiment 1, and includes initializing n driving points as driving points of a blood vessel centerline of a single blood vessel, and obtaining a fitting equation corresponding to each blood vessel, where the fitting equation corresponds to a type of the blood vessel, and includes a parabolic type, a vertical type, a horizontal type, and an oblique type. Based on a fitting equation corresponding to each blood vessel, extending from the center point of the blood vessel to two sides to obtain the central line of each blood vessel; expanding the central line of each blood vessel to two sides to generate a canalized blood vessel according to the preset width of each blood vessel; and finally, rendering each channelized blood vessel according to preset parameters so as to obtain a simulated blood vessel map of the simulated microcirculation camera. The process can be summarized as a process of driving points, central lines and canalization blood vessels, can quickly draw a simulated blood vessel graph and simulate an optical imaging picture of a microcirculation camera, is simple, effective, convenient and quick, and can be used for generating and managing the simulated blood vessel graph in batches.
As shown in fig. 3, in embodiment 1, the step S11 of obtaining the centerline of each blood vessel by extending the corresponding driving point of each blood vessel to two sides based on the fitting equation of each blood vessel specifically includes the steps of:
s111, extending a driving point to the positive direction of an x coordinate axis along a fitting equation to generate a first extending part, and stopping extending to the positive direction of the x coordinate axis when the first extending part is equal to the length of the preset blood vessel or the first extending part is intersected with the boundary of the simulated blood vessel map;
s112, when the first extension part is intersected with the boundary of the simulated blood vessel map and the length of the first extension part is smaller than that of a preset blood vessel, extending the driving point to the negative direction of the x coordinate axis along the fitting equation to generate a second extension part; wherein the centerline is comprised of the first and second extensions;
s113, when the sum of the lengths of the first extension part and the second extension part is equal to the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis, and generating a central line of the blood vessel;
and S114, when the second extension part intersects with the boundary of the simulated blood vessel map and the sum of the lengths of the first extension part and the second extension part is less than the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis, thereby generating a central line of the blood vessel.
Step S111-S114 is the process of drawing the central line of a single blood vessel, and the driving point extends to the positive direction of the x coordinate axis along the fitting equation until the extending length is equal to the length of the preset central line; and if the length extending to the position intersecting with the boundary of the blood vessel simulation diagram is still less than the length of the preset central line, stopping extending to the positive direction of the x-axis, and starting extending from the driving point to the negative direction of the x-axis until the sum of the lengths of the extension line extending to the positive direction of the x-axis and the extension line extending to the negative direction of the x-axis of the driving point is equal to the length of the preset central line, so that the central line of the blood vessel is generated. And when the second extension part is intersected with the boundary of the simulated blood vessel graph and the sum of the lengths of the first extension part and the second extension part is smaller than the length of a preset blood vessel, the extension in the negative direction of the x coordinate axis is stopped, so that the central line of the blood vessel is generated.
As shown in fig. 4, in embodiment 1, the step of obtaining the length of each blood vessel in the simulated blood vessel map by the pixel method in step S1 specifically includes the steps of:
s15, initializing cursors of pixel points on the center line of the blood vessel, and enabling the cursors of the pixel points to point to a first pixel point on the center line;
s16, traversing the cursors of the pixels from the first pixel to the last pixel, and accumulating the side length orObtaining an accumulated value of the side length of the multiple; if the current pixel point is horizontally adjacent to the previous pixel point, accumulating the side length of the current pixel point, and if the current pixel point is vertically adjacent to the previous pixel point, accumulating the side length of the current pixel pointThe length of the side of the times;
and S17, converting the accumulated value into the actual physical size of the central line based on the ratio of the side length of the pixel point of the simulated blood vessel graph to the actual physical size of the central line, wherein the actual physical size of the central line is the length of the corresponding blood vessel.
Step S15-S17 is a process of calculating the length of each blood vessel in the simulated blood vessel map by pixel method, first initializing the cursor of the pixel point on the centerline of the blood vessel, making the cursor of the pixel point to the first pixel point on the centerline, then traversing the cursor from the first pixel point to the last pixel point, and accumulating the side length or length of each pixel pointThe length of the side of the fold. As can be understood, when the next pixel point is horizontally adjacent to the previous pixel point, the next pixel point and the previous pixel point share the same edge, and the edge length of the next pixel point is accumulated; if the next pixel point is vertically adjacent to the previous pixel point and the next pixel point and the previous pixel point share a vertex, accumulating the intersection line of the next pixel point, namelyThe length of the side of the fold. The actual physical size of the central line can be obtained by multiplying the accumulated value by the ratio of the actual physical size to the side length of the pixel point, and the actual physical size of the central line is the length of the corresponding blood vessel.
As shown in fig. 5, preferably, in embodiment 1, the step of generating the simulated blood vessel map by the simulated microcirculation camera in the step S1 may further specifically include the steps of:
s11', calling an opencv image processing open source library to initialize an IpilImage picture variable, and randomly initializing n coordinate points on the IpilImage picture variable; wherein n is less than 1000;
s12', respectively initializing a VesslPicture drawing type variable for each coordinate point, and setting each parameter of each VesslPicture drawing type variable;
s13', based on each VesslPicture drawing-like variable and coordinate point, drawing the ipimage picture variable, thereby generating the simulated blood vessel map.
S11 'to S13' are program processing procedures for simulating a microcirculation camera to generate a simulated blood vessel map, an opencv image processing open source library is called to initiate an IpilImage picture variable, and n coordinate points are initiated on the IpilImage picture variable; secondly, initializing n VesslPicture drawing variables based on n coordinate points respectively, and setting each parameter of each VesslPicture drawing variable; wherein each VesslPicture drawing class variable corresponds to each blood vessel; and finally, drawing the IpilImage picture variable based on each VesslPicture drawing class variable and coordinate point so as to generate the simulated vessel map.
Preferably, the generating of the simulated blood vessel map based on each VesslPicture drawing-like variable and coordinate point may specifically be writing a pixel point of each blood vessel into the ipilimage picture variable with each coordinate point as a reference point based on each parameter based on each VesslPicture drawing-like variable; and then refreshing the IplImage picture variable to a Qtable to generate the simulated vessel map.
The opencv image processing open source library can realize a plurality of general algorithms in the aspects of image processing and computer vision, can improve the execution speed and the processing speed, and can quickly obtain a distribution simulation diagram of blood vessels.
As shown in fig. 6, an embodiment of the present invention further provides a verification apparatus 100 for a micro-loop image algorithm, including:
the simulated blood vessel map module 101 is used for simulating a microcirculation camera to generate a simulated blood vessel map, and obtaining the width and length of each blood vessel in the simulated blood vessel map by a pixel method;
an algorithm operation module 102, configured to obtain a width and a length of each blood vessel in the simulated blood vessel map after the simulated blood vessel map is operated through a microcirculation image algorithm;
the algorithm verification module 103 is configured to evaluate that the microcirculation image algorithm is valid if the width and the length of the corresponding blood vessel in the simulated blood vessel map obtained by the pixel method and the microcirculation image algorithm are consistent.
The working process of the verification apparatus for a micro-loop image algorithm provided in this embodiment may refer to the specific description of the verification method for a micro-loop image algorithm provided in the above embodiment, and is not described herein again.
To sum up, the embodiment of the invention discloses a verification method and a device of a microcirculation image algorithm, a simulation blood vessel map is generated by a simulation microcirculation camera, the length and the width of each blood vessel in the simulation blood vessel map are obtained by respectively using a pixel method and a microcirculation image algorithm, the width and the length of the corresponding blood vessel under the two methods are compared, if the two methods are consistent, the microcirculation algorithm is effectively evaluated, and the problems that the existing verification method cannot perform accurate analysis and the simulation mode is too limited are solved.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (6)
1. A verification method of a microcirculation image algorithm is characterized by comprising the following steps:
the method comprises the steps that a microcirculation simulation camera generates a simulated blood vessel map, and the width and the length of each blood vessel in the simulated blood vessel map are obtained through a pixel method; wherein,
the method for generating the simulated blood vessel map by the simulated microcirculation camera specifically comprises the following steps:
initializing n driving points of the simulated vessel map; wherein each driving point is a driving point of a blood vessel central line of a single blood vessel; wherein n < 1000;
acquiring a fitting equation of each blood vessel according to a preset type of each blood vessel, and extending from a driving point corresponding to each blood vessel to two sides based on the fitting equation of each blood vessel to obtain a central line of each blood vessel;
expanding the central line of each blood vessel to two sides to generate a canalized blood vessel according to the preset width of each blood vessel, thereby obtaining a simulated blood vessel map of the simulated microcirculation camera; the width of each pipelined blood vessel is equal to the width of each corresponding preset blood vessel;
the step of extending the corresponding driving point of each blood vessel to two sides based on the fitting equation of each blood vessel to obtain the center line of each blood vessel specifically comprises:
generating a first extension part by extending a driving point to the positive direction of an x coordinate axis along a fitting equation, and stopping extending to the positive direction of the x coordinate axis when the first extension part is equal to the length of the preset blood vessel or the first extension part intersects with the boundary of the simulated blood vessel map;
when the first extension part is intersected with the boundary of the simulated blood vessel graph and the length of the first extension part is smaller than the length of a preset blood vessel, extending the driving point to the negative direction of the x coordinate axis along the fitting equation to generate a second extension part; wherein the centerline is comprised of the first and second extensions;
when the sum of the lengths of the first extension part and the second extension part is equal to the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis, and generating a central line of the blood vessel;
when the second extension part intersects with the boundary of the simulated blood vessel map and the sum of the lengths of the first extension part and the second extension part is smaller than the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis so as to generate a central line of the blood vessel;
the length of each blood vessel in the simulated blood vessel map obtained by the pixel method specifically comprises the following steps:
initializing cursors of pixel points on the center line of the blood vessel, and enabling the cursors of the pixel points to point to a first pixel point on the center line;
traversing the cursors of the pixel points from the first pixel point to the last pixel pointA pixel point, the side length of each pixel point is accumulated orObtaining an accumulated value of the side length of the multiple; if the current pixel point is horizontally adjacent to the previous pixel point, accumulating the side length of the current pixel point, and if the current pixel point is vertically adjacent to the previous pixel point, accumulating the side length of the current pixel pointThe length of the side of the times;
converting the accumulated value into the actual physical size of the central line based on the proportion of the side length and the actual physical size of the pixel point of the simulated blood vessel map, wherein the actual physical size of the central line is the length of the corresponding blood vessel;
calculating the simulated vessel map through a microcirculation image algorithm to obtain the width and the length of each vessel in the simulated vessel map;
and if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent, evaluating that the microcirculation image algorithm is effective.
2. The verification method of the microcirculation image algorithm according to claim 1, wherein before obtaining the simulated blood vessel map of the simulated microcirculation camera, the method further comprises the following steps:
rendering each of the pipelined blood vessels according to preset parameters; the rendering mode comprises rendering of a blood vessel central line, rendering of a blood vessel outline, rendering of a blood vessel number and rendering of a blood vessel key pixel point.
3. A verification method of a micro-loop image algorithm as claimed in claim 1, wherein the type of the blood vessel includes a parabolic type, a vertical type, a horizontal type, and a diagonal type.
4. The verification method of the microcirculation image algorithm according to claim 1, wherein the step of simulating the microcirculation camera to generate the simulated blood vessel map specifically comprises the following steps:
calling an opencv image processing open source library to initialize an IpilImage picture variable, and randomly initializing n coordinate points on the IpilImage picture variable; wherein n < 1000;
respectively initializing a VesslPicture drawing type variable for each coordinate point, and setting each parameter of each VesslPicture drawing type variable;
drawing the Iplimage picture variable based on each VesslPicture drawing class variable and coordinate point, thereby generating the simulated vessel map.
5. The verification method of the microcirculation image algorithm according to claim 4, wherein the generating the simulated vessel map by drawing the IplImage picture variables based on each VesslPicture drawing-like variable and coordinate point specifically comprises:
writing pixel points of each blood vessel into the IpilImage picture variable by taking each coordinate point as a datum point based on each parameter of each VesslPicture drawing variable;
and refreshing the IplImage picture variable to a Qtable to generate the simulated vessel map.
6. An apparatus for validating a microcirculation image algorithm, comprising:
the simulated blood vessel map module is used for simulating a microcirculation camera to generate a simulated blood vessel map, and the width and the length of each blood vessel in the simulated blood vessel map are obtained through a pixel method; wherein,
the simulation microcirculation camera generating the simulation blood vessel map specifically comprises the following steps: initializing n driving points of the simulated vessel map; wherein each driving point is a driving point of a blood vessel central line of a single blood vessel; wherein n < 1000; acquiring a fitting equation of each blood vessel according to a preset type of each blood vessel, and extending from a driving point corresponding to each blood vessel to two sides based on the fitting equation of each blood vessel to obtain a central line of each blood vessel; expanding the central line of each blood vessel to two sides to generate a canalized blood vessel according to the preset width of each blood vessel, thereby obtaining a simulated blood vessel map of the simulated microcirculation camera; the width of each pipelined blood vessel is equal to the width of each corresponding preset blood vessel;
the step of extending the corresponding driving point of each blood vessel to two sides based on the fitting equation of each blood vessel to obtain the center line of each blood vessel specifically comprises: generating a first extension part by extending a driving point to the positive direction of an x coordinate axis along a fitting equation, and stopping extending to the positive direction of the x coordinate axis when the first extension part is equal to the length of the preset blood vessel or the first extension part intersects with the boundary of the simulated blood vessel map; when the first extension part is intersected with the boundary of the simulated blood vessel graph and the length of the first extension part is smaller than the length of a preset blood vessel, extending the driving point to the negative direction of the x coordinate axis along the fitting equation to generate a second extension part; wherein the centerline is comprised of the first and second extensions; when the sum of the lengths of the first extension part and the second extension part is equal to the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis, and generating a central line of the blood vessel; when the second extension part intersects with the boundary of the simulated blood vessel map and the sum of the lengths of the first extension part and the second extension part is smaller than the length of a preset blood vessel, stopping extending towards the negative direction of the x coordinate axis so as to generate a central line of the blood vessel;
the length of each blood vessel in the simulated blood vessel map obtained by the pixel method specifically comprises the following steps: initializing cursors of pixel points on the center line of the blood vessel, and enabling the cursors of the pixel points to point to a first pixel point on the center line; traversing the cursors of the pixels from the first pixel to the last pixel, and accumulating the side length orObtaining an accumulated value of the side length of the multiple; if the current pixel point is horizontally adjacent to the previous pixel pointIf the current pixel point is vertically adjacent to the previous pixel point, accumulating the side length of the current pixel pointThe length of the side of the times; converting the accumulated value into the actual physical size of the central line based on the proportion of the side length and the actual physical size of the pixel point of the simulated blood vessel map, wherein the actual physical size of the central line is the length of the corresponding blood vessel;
the algorithm operation module is used for obtaining the width and the length of each blood vessel in the simulated blood vessel map after the simulated blood vessel map is operated through a microcirculation image algorithm;
and the algorithm verification module is used for evaluating the effectiveness of the microcirculation image algorithm if the width and the length of the corresponding blood vessel in the simulated blood vessel image obtained by the pixel method and the microcirculation image algorithm are consistent.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611214146.1A CN106777725B (en) | 2016-12-23 | 2016-12-23 | Verification method and device for microcirculation image algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611214146.1A CN106777725B (en) | 2016-12-23 | 2016-12-23 | Verification method and device for microcirculation image algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106777725A CN106777725A (en) | 2017-05-31 |
CN106777725B true CN106777725B (en) | 2020-04-03 |
Family
ID=58920681
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611214146.1A Active CN106777725B (en) | 2016-12-23 | 2016-12-23 | Verification method and device for microcirculation image algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106777725B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112309542B (en) * | 2020-07-27 | 2021-06-15 | 李星阳 | Heart bypass mode selection system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1915185A (en) * | 2005-08-18 | 2007-02-21 | 西门子公司 | Image evaluation method for two-dimensional projection images and items corresponding thereto |
CN103445764A (en) * | 2013-09-04 | 2013-12-18 | 广州医软智能科技有限公司 | Device and method for monitoring microcirculation imaging |
CN104224135A (en) * | 2014-10-20 | 2014-12-24 | 广州医软智能科技有限公司 | Multilevel microcirculation condition monitoring device and method |
CN105184819A (en) * | 2015-09-14 | 2015-12-23 | 浙江大学 | Objective image quality evaluation method for optimizing medical image reconstruction parameter |
-
2016
- 2016-12-23 CN CN201611214146.1A patent/CN106777725B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1915185A (en) * | 2005-08-18 | 2007-02-21 | 西门子公司 | Image evaluation method for two-dimensional projection images and items corresponding thereto |
CN103445764A (en) * | 2013-09-04 | 2013-12-18 | 广州医软智能科技有限公司 | Device and method for monitoring microcirculation imaging |
CN104224135A (en) * | 2014-10-20 | 2014-12-24 | 广州医软智能科技有限公司 | Multilevel microcirculation condition monitoring device and method |
CN105184819A (en) * | 2015-09-14 | 2015-12-23 | 浙江大学 | Objective image quality evaluation method for optimizing medical image reconstruction parameter |
Non-Patent Citations (2)
Title |
---|
微循环监测技术的研究进展;古妮娜;《医学综述》;20150305;第21卷(第5期);第873页至875页 * |
胰腺癌微循环CT灌注成像分析;陈小龙等;《陕西医学杂志》;20151105;第44卷(第11期);第1478页至1480页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106777725A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10855909B2 (en) | Method and apparatus for obtaining binocular panoramic image, and storage medium | |
CN104715731B (en) | Screen brightness adjustment method and device and liquid crystal display device | |
WO2014106445A1 (en) | Method and apparatus for detecting backlight | |
CN104461573B (en) | A kind of control process method of view level | |
WO2022199364A1 (en) | Image processing method and apparatus, and storage medium and device | |
CN107239216A (en) | Drawing modification method and apparatus based on touch-screen | |
CN112184873B (en) | Fractal graph creation method, fractal graph creation device, electronic equipment and storage medium | |
US20220375258A1 (en) | Image processing method and apparatus, device and storage medium | |
US10991068B2 (en) | Projection image construction method and device | |
US11205290B2 (en) | Method and device for inserting an image into a determined region of a target eye image | |
US20230326174A1 (en) | Image processing method and apparatus, computer device and computer program product | |
CN114527980A (en) | Display rendering method and device, electronic equipment and readable storage medium | |
CN106777725B (en) | Verification method and device for microcirculation image algorithm | |
WO2019127319A1 (en) | Distortion measurement method and system for head-mounted display device | |
CN107330849A (en) | A kind of method of Panorama Mosaic, device, equipment and storage medium | |
CN110930492A (en) | Model rendering method and device, computer readable medium and electronic equipment | |
CN109558842A (en) | A kind of method, apparatus, equipment and medium adjusting image display direction | |
CN112580213A (en) | Method and apparatus for generating display image of electric field lines, and storage medium | |
US10580178B2 (en) | Techniques for automatic and dynamic opacity settings for scatterplots | |
Ashida et al. | Helmholtz illusion makes you look fit only when you are already fit, but not for everyone | |
WO2022007787A1 (en) | Image processing method and apparatus, device and medium | |
US20240177409A1 (en) | Image processing method and apparatus, electronic device, and readable storage medium | |
CN114782345A (en) | Oral cavity detection method and device based on artificial intelligence, electronic equipment and medium | |
CN114820968A (en) | Three-dimensional visualization method and device, robot, electronic device and storage medium | |
CN108629786A (en) | Method for detecting image edge and device |
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 |