CN111681276A - Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment - Google Patents
Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment Download PDFInfo
- Publication number
- CN111681276A CN111681276A CN202010532386.6A CN202010532386A CN111681276A CN 111681276 A CN111681276 A CN 111681276A CN 202010532386 A CN202010532386 A CN 202010532386A CN 111681276 A CN111681276 A CN 111681276A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- determining
- artery
- vein
- annular region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 351
- 210000001367 artery Anatomy 0.000 claims abstract description 119
- 210000003462 vein Anatomy 0.000 claims abstract description 118
- 230000011218 segmentation Effects 0.000 claims abstract description 75
- 238000012163 sequencing technique Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 7
- 230000001143 conditioned effect Effects 0.000 claims 1
- 238000012216 screening Methods 0.000 abstract description 8
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000013461 design Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 210000001210 retinal vessel Anatomy 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/30041—Eye; Retina; Ophthalmic
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Radiology & Medical Imaging (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The application provides a method and a device for determining a ratio of arteriovenous diameters in an eye fundus image, and electronic equipment, wherein the method comprises the following steps: acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image; determining the position of an optic disc according to the fundus image; determining an annular region from the blood vessel segmentation image by taking the optic disc position as a center; according to the blood vessel segmentation image in the annular region, determining arteries and veins meeting preset conditions; the diameter ratio of the artery to the vein is determined. The annular region is determined from the blood vessel segmentation image by taking the optic disc position as the center, then the artery and the vein which meet the preset condition are determined by utilizing the blood vessel segmentation image in the annular region, compared with the method for screening out the artery and the vein which meet the preset condition from the whole blood vessel segmentation image, the calculation complexity of the artery and vein screening process is reduced, manual participation is not needed, and then the artery and vein diameter ratio in the fundus image is automatically determined with lower complexity.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method and a device for determining a ratio of arteriovenous diameters in an eyeground image and electronic equipment.
Background
Accurate estimation of parameters of retinal blood vessels has been a major concern in fundus image analysis. The ratio of arteriovenous widths (AVR) can be used to measure the width variation of retinal vessels, but the relative variation is very small, and it is difficult for even an experienced ophthalmologist to find the variation at the time of clinical examination, i.e., it is complicated and laborious to manually or semi-automatically estimate the AVR value from the fundus image. Therefore, how to automatically determine the AVR with low complexity has great significance.
Disclosure of Invention
In view of the above, an object of the embodiments of the present application is to provide a method, an apparatus, and an electronic device for determining a ratio of arteriovenous diameters in a fundus image, which can automatically determine the ratio of arteriovenous diameters in the fundus image with low computational complexity.
In a first aspect, an embodiment of the present application provides a method for determining an arteriovenous diameter ratio in a fundus image, the method including: acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image; determining the position of an optic disc according to the fundus image; determining an annular region from the blood vessel segmentation image by taking the optic disc position as a center; according to the blood vessel segmentation image in the annular region, determining arteries and veins meeting preset conditions; the diameter ratio of the artery to the vein is determined.
In the implementation process, an annular area is determined from the blood vessel segmentation image by taking the optic disc position as the center, then the blood vessel segmentation image in the annular area is used for determining the artery and vein meeting the preset condition, and compared with the method for screening the artery and vein meeting the preset condition from the whole blood vessel segmentation image, the calculation complexity of the arteriovenous screening process is reduced.
Based on the first aspect, in a possible design, the determining, according to the segmented image of blood vessels in the annular region, an artery and a vein which satisfy a preset condition includes: determining blood vessels meeting the preset conditions according to the blood vessel segmentation images in the annular region; and determining the artery and the vein from the blood vessels of the preset condition.
In the implementation process, the artery and the vein which meet the preset conditions are directly identified from the blood vessel segmentation image in the annular region, so that the calculation complexity is high, and the error is easy to identify, so that the artery and the vein are determined from the blood vessels which meet the preset conditions after the blood vessels which meet the preset conditions are determined, the identification range is narrowed, the calculation complexity is reduced, and the accuracy is high.
In a possible design based on the first aspect, the determining the artery and the vein from the blood vessels of the preset condition includes: determining the pixel average value of the red components of all pixel points on the central line of each blood vessel in the blood vessels with the preset condition; and determining the artery and the vein according to the pixel average value of the red component corresponding to each blood vessel.
In the implementation process, the difference of the pixel average values of the red components of all the pixel points on the central line of the artery and the vein is obvious, the blood vessel with relatively deep color is the artery, and the blood vessel with relatively shallow color is the vein, so the artery and the vein can be accurately determined by using the pixel average values of the red components of all the pixel points on the central line of the blood vessel.
Based on the first aspect, in a possible design, the determining, according to the segmented image of blood vessels in the annular region, a blood vessel that meets the preset condition includes: determining a connected domain of each blood vessel in the annular region according to the blood vessel segmentation image in the annular region; determining the coordinates of a plurality of pixel points representing the shape, size and position of the connected domain of each blood vessel aiming at the connected domain of each blood vessel; determining communicated blood vessels which are simultaneously intersected with the inner circle and the outer circle of the annular area according to the coordinates of a plurality of pixel points of the communicated domain of each blood vessel; determining the ratio of the area of the convex hull of the connected region of the connected blood vessel to the area of the connected region of the connected blood vessel for each connected blood vessel; and determining a reference blood vessel with the ratio smaller than a preset ratio from the connected blood vessels.
The blood vessels which are not intersected with the inner circle and the outer circle of the annular area at the same time, and the branched or intersected blood vessels can reduce the determination accuracy of the ratio of the arteriovenous diameters in the fundus image, so that in the implementation process, the influence of the blood vessels which are not intersected with the inner circle and the outer circle of the annular area at the same time on the determination accuracy of the ratio of the arteriovenous diameters is eliminated, meanwhile, the ratio of the arteriovenous diameters is determined by determining the reference blood vessels with the ratio smaller than the preset ratio from the communicated blood vessels, the influence of the intersected blood vessels or the branched blood vessels on the determination accuracy of the ratio of the arteriovenous diameters is eliminated, and the determination accuracy of the ratio of the arteriovenous diameters in the fundus image is further improved.
In a possible design based on the first aspect, after determining the reference vessel with the ratio smaller than the preset ratio, the method further includes: aiming at each reference blood vessel, determining a first included angle between a connecting line of a central point of a connected domain of the reference blood vessel and the position of the optic disc and a horizontal line; sorting the reference blood vessels according to the size of the first included angle to obtain a sorting result; and according to the sequencing result, determining a blood vessel pair with adjacent positions and a cosine value of an included angle between a connecting line of the central point of the connected domain of the blood vessel and the position of the optic disc larger than a first preset value.
The blood vessel pair with the position not adjacent or the cosine value of the included angle between the central point of the connected domain of the blood vessel and the connecting line of the optic disc position being less than or equal to a certain value can reduce the determination precision of the ratio of the arteriovenous diameters in the fundus image, so that the blood vessel pair with the position adjacent and the cosine value of the included angle between the central point of the connected domain of the blood vessel and the connecting line of the optic disc position being greater than a first preset value is determined from the reference blood vessel in the implementation process, the ratio of the arteriovenous diameters in the fundus image of the blood vessel is determined based on the blood vessel pair, and the determination precision of the ratio of the arteriovenous diameters in the fundus image is further improved.
Based on the first aspect, in a possible design, after the blood vessel pair whose positions are adjacent to each other and whose cosine value of an included angle between a central point of a connected domain of the blood vessel and a connecting line of the optic disc positions is greater than a first preset value is determined, the method further includes: for each blood vessel pair, determining a second included angle between a fitted line of a first blood vessel and a fitted line of a second blood vessel in the blood vessel pair; and determining the blood vessel pair with the cosine value of the second included angle larger than a second preset value from the blood vessel pair.
Since the trend consistency of the two blood vessels in the blood vessel pair is related to the determination accuracy of the arteriovenous diameter ratio in the fundus image, the more consistent the trend of the two blood vessels in the blood vessel pair is, the more favorable the determination accuracy of the arteriovenous diameter ratio is, otherwise, the accuracy is reduced, therefore, in the implementation process, the larger the cosine value of the second included angle of the two blood vessels in the blood vessel pair is, the more consistent the trend of the two blood vessels is represented, and conversely, the more inconsistent the trend is, and then the blood vessel pair (namely, the blood vessel pair with the trend close to the consistency) with the cosine value of the second included angle larger than the second preset value is determined from the blood vessel pair, and the arteriovenous diameter ratio in the fundus image is determined based on the blood vessel pair, so that the determination accuracy is further.
In a possible design based on the first aspect, the method further includes: when the artery and the vein which meet the preset conditions are not determined according to the blood vessel segmentation image in the annular region, under the condition that the distance between the inner circle and the outer circle is not changed, the radius of the inner circle and the radius of the outer circle are enlarged according to a preset step length so as to update the annular region, and the updated annular region is obtained; determining a first artery and a first vein which meet the preset condition according to the updated blood vessel segmentation image in the annular region; a ratio of diameters of the first artery and the first vein is determined.
In the implementation process, when the artery and the vein which meet the preset conditions are not determined according to the blood vessel segmentation image in the annular region, the annular region is continuously updated to re-determine the artery and the vein which meet the preset conditions, so that the artery and the vein which meet the preset conditions can be determined from the blood vessel segmentation image, and the determination precision of the ratio of the arteriovenous diameters can be further ensured.
In a possible design based on the first aspect, the determining a diameter ratio of the artery and the vein includes: when the number of the arteries is at least two, averaging the diameters of the at least two arteries to obtain a mean value of the arteries; determining a mean of the artery and a diameter ratio of the vein; or when the number of the veins is at least two, averaging the diameters of the veins to obtain a mean value of the veins; determining a diameter ratio of the mean of the artery and the vein.
In the implementation process, when the number of the arteries is at least two, the diameter mean value of the arteries and the diameter ratio of the veins are used as the final arteriovenous diameter ratio, and compared with the method for solving the arteriovenous diameter ratio by using the diameter of one of the two arteries, the determination precision is higher; similarly, when the number of the veins is at least two, the ratio of the diameter of the artery to the mean diameter of the veins is used as the final arteriovenous diameter ratio, and the determination precision is higher than that of solving the arteriovenous diameter ratio by using the diameter of one of the two veins.
In a second aspect, an embodiment of the present application provides an apparatus for determining an arteriovenous diameter ratio in a fundus image, the apparatus including: an image acquisition unit for acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image; a position determination unit for determining the optic disc position based on the fundus image; a region determining unit, configured to determine an annular region from the blood vessel segmentation image with the optic disc position as a center; the arteriovenous determining unit is used for determining arteries and veins meeting preset conditions according to the blood vessel segmentation image in the annular region; a diameter ratio determination unit for determining a diameter ratio of the artery and the vein.
Based on the second aspect, in one possible design, the arteriovenous determination unit includes: the first determining unit is used for determining the blood vessels meeting the preset conditions according to the blood vessel segmentation images in the annular region; a second determination unit configured to determine the artery and the vein from the blood vessels of the preset condition.
Based on the second aspect, in a possible design, the second determining unit is specifically configured to determine, for each of the blood vessels that determine the preset condition, a pixel average value of red components of all pixel points on a centerline of the blood vessel; and determining the artery and the vein according to the pixel average value of the red component corresponding to each blood vessel.
Based on the second aspect, in a possible design, the first determining unit is specifically configured to determine a connected domain of each blood vessel in the annular region according to the blood vessel segmentation image in the annular region; determining the coordinates of a plurality of pixel points representing the shape, size and position of the connected domain of each blood vessel aiming at the connected domain of each blood vessel; determining communicated blood vessels which are simultaneously intersected with the inner circle and the outer circle of the annular area according to the coordinates of a plurality of pixel points of the communicated domain of each blood vessel; determining the ratio of the area of the convex hull of the connected region of the connected blood vessel to the area of the connected region of the connected blood vessel for each connected blood vessel; and determining a reference blood vessel with the ratio smaller than a preset ratio from the connected blood vessels.
Based on the second aspect, in one possible design, the apparatus further includes: the first screening unit is used for determining a first included angle between a connecting line of a central point of a connected domain of each reference blood vessel and the position of the optic disc and a horizontal line aiming at each reference blood vessel; sequencing the reference blood vessels according to the size of the first included angle to obtain a sequencing result; and according to the sequencing result, determining a blood vessel pair with adjacent positions and a cosine value of an included angle between a connecting line of the central point of the connected domain of the blood vessel and the position of the optic disc larger than a first preset value.
Based on the second aspect, in one possible design, the apparatus further includes: the second screening unit is used for determining a second included angle between a fitting line of the first blood vessel and a fitting line of the second blood vessel in each blood vessel pair; and determining the blood vessel pair with the cosine value of the second included angle larger than a second preset value from the blood vessel pair.
Based on the second aspect, in one possible design, the apparatus further includes: a re-determining unit, configured to, when an artery and a vein that meet the preset condition are not determined according to the blood vessel segmentation image in the annular region, enlarge the radii of the inner circle and the outer circle according to a preset step length under the condition that a distance between the inner circle and the outer circle is not changed, so as to update the annular region, and obtain an updated annular region; determining a first artery and a first vein which meet the preset condition according to the updated blood vessel segmentation image in the annular region; a ratio of diameters of the first artery and the first vein is determined.
Based on the second aspect, in a possible design, the diameter ratio determining unit is specifically configured to, when the number of the arteries is at least two, average the diameters of the at least two arteries to obtain a mean value of the arteries; and determining a mean of the artery and a diameter ratio of the vein; or when the number of the veins is at least two, averaging the diameters of the veins to obtain a mean value of the veins; determining a diameter ratio of the mean of the artery and the vein.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor and a memory connected to the processor, where a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device is caused to perform the method of the first aspect.
In a fourth aspect, an embodiment of the present application provides a storage medium, in which a computer program is stored, and when the computer program runs on a computer, the computer is caused to execute the method of the first aspect.
Additional features and advantages of the present application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the present application. The objectives and other advantages of the application may be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a schematic flow chart of a method for determining a ratio of arteriovenous diameters in a fundus image according to an embodiment of the present application.
Fig. 2 is a schematic view of a blood vessel segmentation image of a fundus image to be detected according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a segmented blood vessel image in an annular region according to an embodiment of the present application.
Fig. 4 is a schematic structural view of an arteriovenous diameter ratio determination device in a fundus image provided by an embodiment of the present application.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Icon: 400-means for determining the ratio of arteriovenous diameters of the fundus image; 410-an image acquisition unit; 420-a position determination unit; 430-region determination unit; 440-an arteriovenous determination unit; a 450-diameter ratio determining unit; 500-an electronic device; 501, a processor; 502-a memory; 503 — a communication interface.
Detailed Description
The technical solution in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present application, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, fig. 1 is a flowchart of a method for determining arteriovenous diameters of a fundus image according to an embodiment of the present application, and the flowchart shown in fig. 1 will be described in detail below, where the method includes the steps of: s11, S12, S13, S14 and S15.
S11: acquiring a blood vessel segmentation image of a fundus image to be detected.
S12: and determining the position of the optic disc according to the blood vessel segmentation image.
S13: and determining an annular area from the blood vessel segmentation image by taking the optic disc position as a center.
S14: and determining the artery and the vein which meet the preset conditions according to the blood vessel segmentation image in the annular region.
S15: the diameter ratio of the artery to the vein is determined.
The above-described method is described in detail below.
S11: acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image.
In practical implementation, S11 may be implemented by, after acquiring the fundus image to be detected, performing gaussian filtering on the fundus image by using a gaussian filter to reduce noise in the image to obtain a preprocessed fundus image, and then segmenting blood vessels in the preprocessed fundus image based on the deep neural network model to obtain a blood vessel segmentation image of the fundus image, as shown in fig. 2, wherein white parts in fig. 2 represent blood vessels, and black parts are backgrounds.
It is worth mentioning that, compared with the traditional image processing method, the blood vessel in the fundus image is segmented based on the deep neural network model, so that the blood vessel segmentation image has fewer artifacts and burrs, and is more accurate.
As an embodiment, the blood vessel in the fundus image to be detected may be segmented directly based on the deep neural network model to obtain a blood vessel segmentation image of the fundus image to be detected.
In one embodiment, the blood vessels in the preprocessed fundus image may be segmented based on the deep neural network model to obtain a blood vessel segmentation image of the fundus image to be detected.
As an embodiment, the fundus image to be detected and the blood vessel segmentation image of the fundus image may also be acquired directly from a third party.
After the fundus image to be detected is acquired, step S12 is executed.
S12: and determining the position of the optic disc according to the fundus image.
Since the optic disc is a highlight region that approximates a circle/ellipse in the fundus image, generally, only a highlight region of a circle/ellipse, i.e., the position of the optic disc, exists in the fundus image. The position of the optic disc can be represented by the position of a point in the center of the optic disc, or by the positions of a plurality of points representing the outline of the shape and size of the optic disc.
The specific implementation of determining the optic disc position in the fundus image by using the blob detector in opencv is well known in the art, and therefore, the detailed description is omitted here.
After the disk position in the fundus image and the blood vessel segmentation image of the fundus image are acquired, step S13 is executed.
S13: and determining an annular area from the blood vessel segmentation image by taking the optic disc position as a center.
Since the relative position of the optic disc in the fundus image is the same as the relative position of the optic disc in the blood vessel segmentation image, after acquiring the optic disc position in the fundus image and the blood vessel segmentation image of the fundus image, the position of the optic disc in the blood vessel segmentation image is determined from the blood vessel segmentation image according to the position of the optic disc in the fundus image and the pre-established coordinate system, if the position of the optic disc is characterized by the position of the point at the center of the optic disc, the position of the optic disc in the blood vessel segmentation image is taken as the center, and if the position of the optic disc is characterized by the positions of the plurality of points representing the contour of the shape and size of the optic disc, an annular region is determined from the blood vessel segmentation image with the center of the position of the optic disc in the blood vessel segmentation image as the center, as shown in fig. 3, wherein the distance between the inner circle of the annular region and the optic disc is a first distance, the distance between the outer circle of the annular area and the optic disc is a second distance, wherein the first distance and the second distance are both larger than 0, the second distance is larger than the first distance, the value of the first distance and the value of the second distance, and the difference between the first distance and the second distance is set according to actual requirements.
S14: and determining the artery and the vein which meet the preset conditions according to the blood vessel segmentation image in the annular region.
As an embodiment, S14 includes: steps a1 and a 2.
A1: and determining the blood vessels meeting the preset conditions according to the blood vessel segmentation images in the annular region.
As an embodiment, step a1 includes the steps of: a11, a12, a13, a14, and a 15.
A11: and determining the connected domain of each blood vessel in the annular region according to the blood vessel segmentation image in the annular region.
The specific implementation of determining the connected region is well known in the art and will not be described herein. In fig. 3, the white portion is a connected domain of each blood vessel, and the black portion is a background image.
A12: and determining the coordinates of a plurality of pixel points representing the shape, size and position of the connected domain of each blood vessel aiming at the connected domain of each blood vessel.
After the connected domain of each blood vessel is determined, for the connected domain of each blood vessel, according to the pre-established coordinate system, determining the coordinates of the pixel points representing the shape, size and position of the connected domain of the blood vessel in the pre-established coordinate system, and it can be understood that the coordinates of a plurality of pixel points in the connected domain of the blood vessel in the pre-established coordinate system are obtained.
A13: and determining the communicated blood vessels which are simultaneously intersected with the inner circle and the outer circle of the annular area according to the coordinates of a plurality of pixel points of the communicated domain of each blood vessel.
Determining the distance between each pixel point in a plurality of pixel points of the connected domain of each blood vessel and the optic disc according to the connected domain of each blood vessel, and if a pixel point exists in the plurality of pixel points of the connected domain of each blood vessel, wherein the distance between the pixel point and the optic disc is equal to the radius of the inner circle of the annular region, and the distance between the pixel point and the optic disc is equal to the radius of the outer circle of the annular region, determining that the blood vessel and the inner circle and the outer circle of the annular region are intersected at the same time; and otherwise, determining that the blood vessel is not simultaneously intersected with the inner circle and the outer circle of the annular area, and then determining a communicated blood vessel simultaneously intersected with the inner circle and the outer circle of the annular area.
A14: and determining the ratio of the area of the convex hull of the connected region of the connected blood vessel to the area of the connected region of the connected blood vessel for each connected blood vessel.
For each connected blood vessel, determining the convex hull of the connected domain of the connected blood vessel by using a convex hull algorithm according to the position of the connected blood vessel in the blood vessel segmentation image, wherein the convex hull is the minimum convex polygon including all pixel points in the connected domain of the blood vessel. The specific implementation of determining the convex hull by using the convex hull algorithm is well known in the art, and is not described herein again.
Determining the number of all pixel points included in the connected domain of each connected blood vessel as the area of the connected domain of the connected blood vessel; after the convex hull of the connected domain of the connected blood vessel is determined, the number of all the pixel points included in the connected convex hull is determined to be the area of the convex hull of the connected domain of the connected blood vessel, and then the ratio of the area of the convex hull of the connected domain of the connected blood vessel to the area of the connected domain of the connected blood vessel is determined.
A15: and determining a reference blood vessel with the ratio smaller than a preset ratio from the connected blood vessels.
And according to the ratio of each communicated blood vessel, determining a reference blood vessel with the ratio smaller than a preset ratio from the communicated blood vessels. The preset ratio is greater than 1, the preset ratio is set according to actual requirements, in the embodiment of the application, the preset ratio is 1.3, and in other embodiments, the preset ratio can also be 1.2, 1.4 and the like.
As an embodiment, after step a15, the method further comprises: a161, a162, and a 163.
A161: and determining a first included angle between a connecting line of a central point of a connected domain of each reference blood vessel and the position of the optic disc and a horizontal line.
After the reference blood vessels are obtained, determining a first mean value of X-axis coordinates of all pixel points in a connected domain of the reference blood vessels and a second mean value of Y-axis coordinates of all pixel points in the connected domain of the reference blood vessels for each reference blood vessel, then determining that the X-axis coordinate of the central point of the connected domain of the reference blood vessels is the first mean value and the Y-axis coordinate of the central point of the connected domain of the reference blood vessels is the second mean value, and after the coordinates of the central point are determined, determining a first included angle between the connecting line of the coordinates of the central point and the optic disc position and a horizontal line according to the coordinates of the central point of the connected domain of the reference blood vessels and the optic disc position.
After the first angle corresponding to each reference vessel is determined, step a162 is performed.
A162: and sequencing the reference blood vessels according to the size of the first included angle to obtain a sequencing result.
After the first included angle corresponding to each reference blood vessel is obtained, sorting the reference blood vessels from small to large or from large to small according to the size of the first included angle to obtain a sorting result.
Example 1, if the first included angle corresponding to the reference blood vessel a is 30 degrees, the first included angle corresponding to the reference blood vessel B is 50 degrees, the first included angle corresponding to the reference blood vessel C is 40 degrees, and the first included angle corresponding to the reference blood vessel D is 45 degrees, the sorting result is as follows: reference vessel a, reference vessel C, reference vessel D, and reference vessel B.
After the sorting result is acquired, step a163 is executed.
A163: and according to the sequencing result, determining a blood vessel pair with adjacent positions and a cosine value of an included angle between a connecting line of the central point of the connected domain of the blood vessel and the position of the optic disc larger than a first preset value.
After the sequencing result is obtained, determining the blood vessel pairs with adjacent positions, determining a first cosine value of an included angle between a central point of a connected domain of two blood vessels in each blood vessel pair with adjacent positions and a connecting line of the optic disc positions, and then determining the blood vessel pair with the first cosine value larger than the first preset value from the blood vessel pairs with adjacent positions. The first preset value is set according to actual requirements. In the embodiment of the present application, the first preset value is 0.9, and in other embodiments, the preset value may also be 0.89, 0.91, and the like.
Example 2, assuming that the ordering result is shown in example 1, the blood vessel pairs adjacent to each other in position include: a first blood vessel pair formed by the reference blood vessel A and the reference blood vessel C, and a second blood vessel pair formed by the reference blood vessel C and the reference blood vessel D; a third vessel pair of reference vessel D and reference vessel B.
As an embodiment, after step a163, the method further comprises:
a171: for each blood vessel pair, a second angle is determined between the fitted line of the first blood vessel and the fitted line of the second blood vessel in the blood vessel pair.
After the blood vessel pairs with adjacent positions and the distance between the blood vessels being smaller than the preset distance are determined, aiming at each blood vessel pair, determining a fitting line of the first blood vessel according to the coordinates of all pixel points in a connected domain of the first blood vessel in the blood vessel pair; determining a fitting line of the second blood vessel according to the coordinates of all pixel points in the connected domain of the second blood vessel in the blood vessel pair; a second angle between the fitted line of the first blood vessel and the fitted line of the second blood vessel is then determined.
A172: and determining the blood vessel pair with the cosine value of the second included angle larger than a second preset value from the blood vessel pair.
The second preset value is set according to actual requirements, in the embodiment of the present application, the second preset value is 0.85, and in other embodiments, the second preset value may also be 0.84, 0.86, and the like.
After the blood vessel satisfying the preset condition is determined, step a2 is performed.
A2: and determining the artery and the vein from the blood vessels of the preset condition.
As an embodiment, a2 includes: determining the pixel average value of the red components of all pixel points on the central line of each blood vessel in the blood vessels with the preset condition; and determining the artery and the vein according to the pixel average value of the red component corresponding to each blood vessel.
It can be understood that the number of the blood vessels satisfying the preset condition is at least two, if the blood vessels satisfying the preset condition are the reference blood vessels determined according to steps a11-a15, two blood vessels are arbitrarily selected from the reference blood vessels, for each of the two blood vessels, a center line of the blood vessel is determined based on coordinates of all pixel points in a connected domain of the blood vessel, then an average value of pixel values of red components of all pixel points on the center line is determined, and if a difference between the average values of the pixel values of the red components of the two blood vessels is greater than 12, the blood vessel with the smaller average value of the two blood vessels is determined as an artery, and the blood vessel with the larger average value is determined as a vein;
if the difference between the average values of the red component pixel values of the two blood vessels is less than or equal to 12, comparing the A blood vessel (wherein, the A blood vessel is any one of the two blood vessels) in the two blood vessels with the B blood vessel (wherein, the B blood vessel is any one of the other blood vessels) in the rest blood vessels except the two blood vessels, and if the difference between the average value of the red component pixel values of the A blood vessel and the average value of the red component pixel values of the B blood vessel is determined to be more than 12, determining the blood vessel with the smaller average value in the A blood vessel and the B blood vessel as an artery and the larger average value as a vein; and determining the artery and the vein from the blood vessels with the preset condition by analogy. If the difference between the average values of the red component pixel values of the two blood vessels in the pair of blood vessels is greater than 12, determining that the blood vessel with the smaller average value in the pair of blood vessels is an artery and the blood vessel with the larger average value in the pair of blood vessels is a vein; otherwise, the pair of vessels is discarded.
In other embodiments, arteries and veins may be identified in other ways.
S15: the diameter ratio of the artery to the vein is determined.
If the artery and the vein are the blood vessels in the blood vessel pairs determined according to steps a11-a163 or a11-a172, S15 may be implemented in such a manner that, if the number of the blood vessel pairs including both arteries and veins is at least two pairs, for the artery and vein in each pair, the ratio of the artery to the vein in the pair is determined, the ratio of the artery to the vein in each pair is then determined, and finally the average of the ratios of the diameters of the at least two pairs is determined as the value of the ratio of the artery to the vein in the fundus image to be detected.
As an embodiment, if the number of the blood vessel pairs including both arteries and veins is at least two pairs, a first mean value of the diameters of the arteries and a second mean value of the diameters of the veins in the at least two pairs of blood vessels are determined, and then a ratio of the first mean value and the second mean value is determined as a value of the diameter ratio of the arteries and veins in the fundus image to be detected.
If the number of the blood vessel pairs including both arteries and veins is one pair, then the diameter ratio of the arteries and veins in the pair is determined to be the value of the diameter ratio of the arteries and veins in the fundus image to be detected.
As an embodiment, S15 includes the steps of: b1, B2, B3 and B4.
B1: when the number of the arteries is at least two, the diameters of the at least two arteries are averaged to obtain a mean value of the arteries.
Assuming that the artery comprises an A artery and a B artery, and the vein is a C vein; then, the diameters of the a artery and the B artery are averaged to obtain the mean value of the artery.
B2: determining a mean of the artery and a diameter ratio of the vein; or
B3: and when the number of the veins is at least two, averaging the diameters of the at least two veins to obtain a mean value of the veins.
Assuming that the artery comprises an A artery, and the veins are a B vein and a C vein; then, the diameters of the B and C veins are averaged to obtain the mean value of the veins.
B4: determining a diameter ratio of the mean of the artery and the vein.
As an embodiment, the method further comprises: c1, C2, and C3.
C1: and when the artery and the vein which meet the preset conditions are not determined according to the blood vessel segmentation image in the annular region, under the condition that the distance between the inner circle and the outer circle is not changed, the radius of the inner circle and the radius of the outer circle are enlarged according to a preset step length so as to update the annular region, and the updated annular region is obtained.
The preset step length is set according to actual requirements, wherein the shorter the preset step length is, the more the first artery and the first vein which meet the preset conditions can be determined.
It is worth mentioning that when the number of the pixel points in the outer circle reaches a threshold value, the update of the annular region is stopped, and it can be understood that the number of the pixel points in the outer circle needs to be less than or equal to the threshold value. The threshold is set according to actual requirements, in the implementation of the present application, the threshold is 300, and in other embodiments, the threshold may also be 310, 290, and the like.
C2: and determining a first artery and a first vein which meet the preset condition according to the updated blood vessel segmentation image in the annular region.
The specific implementation of C2 is the same as step S14, and therefore, is not described herein again.
C3: a ratio of diameters of the first artery and the first vein is determined.
The specific implementation of C3 is the same as S15, and therefore, the detailed description thereof is omitted here.
Referring to fig. 4, fig. 4 is a block diagram illustrating a device 400 for determining a ratio of arteriovenous diameters in a fundus image according to an embodiment of the present application. The block diagram of fig. 4 will be explained, and the apparatus shown comprises:
an image acquisition unit 410 for acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image.
A position determination unit 420 for determining a disc position from the fundus image.
A region determining unit 430, configured to determine an annular region from the blood vessel segmentation image by taking the optic disc position as a center.
And an arteriovenous determining unit 440, configured to determine an artery and a vein that meet a preset condition according to the blood vessel segmentation image in the annular region.
A diameter ratio determination unit 450 for determining a diameter ratio of the artery and the vein.
As an embodiment, the arteriovenous determination unit 440 includes: the first determining unit is used for determining the blood vessels meeting the preset conditions according to the blood vessel segmentation images in the annular region; a second determination unit configured to determine the artery and the vein from the blood vessels of the preset condition.
As an embodiment, the second determining unit is specifically configured to determine, for each blood vessel in the blood vessels for which the preset condition is determined, a pixel average value of red components of all pixel points on a centerline of the blood vessel; and determining the artery and the vein according to the pixel average value of the red component corresponding to each blood vessel.
As an embodiment, the first determining unit is specifically configured to determine a connected domain of each blood vessel in the annular region according to the blood vessel segmentation image in the annular region; determining the coordinates of a plurality of pixel points representing the shape, size and position of the connected domain of each blood vessel aiming at the connected domain of each blood vessel; determining communicated blood vessels which are simultaneously intersected with the inner circle and the outer circle of the annular area according to the coordinates of a plurality of pixel points of the communicated domain of each blood vessel; determining the ratio of the area of the convex hull of the connected region of the connected blood vessel to the area of the connected region of the connected blood vessel for each connected blood vessel; and determining a reference blood vessel with the ratio smaller than a preset ratio from the connected blood vessels.
As an embodiment, the apparatus further comprises: the first screening unit is used for determining a first included angle between a connecting line of a central point of a connected domain of each reference blood vessel and the position of the optic disc and a horizontal line aiming at each reference blood vessel; sequencing the reference blood vessels according to the size of the first included angle to obtain a sequencing result; and according to the sequencing result, determining a blood vessel pair with adjacent positions and a cosine value of an included angle between a connecting line of the central point of the connected domain of the blood vessel and the position of the optic disc larger than a first preset value.
As an embodiment, the apparatus further comprises: the second screening unit is used for determining a second included angle between a fitting line of the first blood vessel and a fitting line of the second blood vessel in each blood vessel pair; and determining the blood vessel pair with the cosine value of the second included angle larger than a second preset value from the blood vessel pair.
As an embodiment, the apparatus further comprises: a re-determining unit, configured to, when an artery and a vein that meet the preset condition are not determined according to the blood vessel segmentation image in the annular region, enlarge the radii of the inner circle and the outer circle according to a preset step length under the condition that a distance between the inner circle and the outer circle is not changed, so as to update the annular region, and obtain an updated annular region; determining a first artery and a first vein which meet the preset condition according to the updated blood vessel segmentation image in the annular region; a ratio of diameters of the first artery and the first vein is determined.
As an embodiment, the diameter ratio determining unit 450 is specifically configured to, when the number of the arteries is at least two, average the diameters of the at least two arteries to obtain a mean value of the arteries; and determining a mean of the artery and a diameter ratio of the vein; or when the number of the veins is at least two, averaging the diameters of the veins to obtain a mean value of the veins; determining a diameter ratio of the mean of the artery and the vein.
Please refer to the contents described in the embodiments shown in fig. 1 to 3, and details thereof are not repeated herein.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device 400 according to an embodiment of the present disclosure, where the electronic device 400 may be a Personal Computer (PC), a tablet PC, a Personal Digital Assistant (PDA), or the like.
The electronic device 500 may include: memory 502, processing 501, communication interface 503, and a communication bus for enabling connection communication of these components.
The Memory 502 is used for storing various data such as a computer program instruction corresponding to the method and the device for determining the ratio of arteriovenous diameters in an eye fundus image provided by the embodiment of the present application, wherein the Memory 502 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an electrically Erasable Programmable Read-Only Memory (EEPROM), and the like.
The processor 401 is configured to, when reading and executing the computer program instructions stored in the memory, execute the steps of the method for determining a ratio of arteriovenous diameters in a fundus image provided in the embodiment of the present application to acquire a fundus image to be detected and a blood vessel segmentation image of the fundus image; determining the position of an optic disc according to the fundus image; determining an annular region from the blood vessel segmentation image by taking the optic disc position as a center; according to the blood vessel segmentation image in the annular region, determining arteries and veins meeting preset conditions; the diameter ratio of the artery to the vein is determined.
The processor 501 may be an integrated circuit chip having signal processing capability. The Processor 501 may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The communication interface 503 may use any transceiver or the like for receiving or transmitting data.
In addition, a storage medium is provided in an embodiment of the present application, and a computer program is stored in the storage medium, and when the computer program runs on a computer, the computer is caused to execute the method provided in any embodiment of the present application.
To sum up, the method, the device and the electronic device for determining the ratio of arteriovenous diameters in the fundus image provided by the embodiments of the present application determine an annular region from a blood vessel segmentation image by using the optic disc position as a center, and then determine the artery and vein satisfying the preset condition by using the blood vessel segmentation image in the annular region.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based devices that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
Claims (10)
1. A method of determining an arteriovenous diameter ratio in a fundus image, the method comprising:
acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image;
determining the position of an optic disc according to the fundus image;
determining an annular region from the blood vessel segmentation image by taking the optic disc position as a center;
according to the blood vessel segmentation image in the annular region, determining arteries and veins meeting preset conditions;
the diameter ratio of the artery to the vein is determined.
2. The method according to claim 1, wherein the determining arteries and veins satisfying a preset condition according to the segmented image of the blood vessels in the annular region comprises:
determining blood vessels meeting the preset conditions according to the blood vessel segmentation images in the annular region;
and determining the artery and the vein from the blood vessels of the preset condition.
3. The method of claim 2, wherein said determining said artery and said vein from said pre-conditioned blood vessels comprises:
determining the pixel average value of the red components of all pixel points on the central line of each blood vessel in the blood vessels with the preset condition;
and determining the artery and the vein according to the pixel average value of the red component corresponding to each blood vessel.
4. The method according to claim 2, wherein the determining the blood vessel satisfying the preset condition according to the blood vessel segmentation image in the annular region comprises:
determining a connected domain of each blood vessel in the annular region according to the blood vessel segmentation image in the annular region;
determining the coordinates of a plurality of pixel points representing the shape, size and position of the connected domain of each blood vessel aiming at the connected domain of each blood vessel;
determining communicated blood vessels which are simultaneously intersected with the inner circle and the outer circle of the annular area according to the coordinates of a plurality of pixel points of the communicated domain of each blood vessel;
determining the ratio of the area of the convex hull of the connected region of the connected blood vessel to the area of the connected region of the connected blood vessel for each connected blood vessel;
and determining a reference blood vessel with the ratio smaller than a preset ratio from the connected blood vessels.
5. The method of claim 4, wherein after determining the reference vessel with the ratio less than the preset ratio, the method further comprises:
aiming at each reference blood vessel, determining a first included angle between a connecting line of a central point of a connected domain of the reference blood vessel and the position of the optic disc and a horizontal line;
sorting the reference blood vessels according to the size of the first included angle to obtain a sorting result;
and according to the sequencing result, determining a blood vessel pair with adjacent positions and a cosine value of an included angle between a connecting line of the central point of the connected domain of the blood vessel and the position of the optic disc larger than a first preset value.
6. The method of claim 5, wherein after determining the blood vessel pair with adjacent positions and the cosine value of the included angle between the connecting line of the central point of the connected domain of the blood vessel and the optic disc position is larger than a first preset value, the method further comprises:
for each blood vessel pair, determining a second included angle between a fitted line of a first blood vessel and a fitted line of a second blood vessel in the blood vessel pair;
and determining the blood vessel pair with the cosine value of the second included angle larger than a second preset value from the blood vessel pair.
7. The method of claim 1, further comprising:
when the artery and the vein which meet the preset conditions are not determined according to the blood vessel segmentation image in the annular region, under the condition that the distance between the inner circle and the outer circle is not changed, the radius of the inner circle and the radius of the outer circle are enlarged according to a preset step length so as to update the annular region, and the updated annular region is obtained;
determining a first artery and a first vein which meet the preset condition according to the updated blood vessel segmentation image in the annular region;
a ratio of diameters of the first artery and the first vein is determined.
8. The method of claim 1, wherein said determining a ratio of diameters of said artery and said vein comprises:
when the number of the arteries is at least two, averaging the diameters of the at least two arteries to obtain a mean value of the arteries;
determining a mean of the artery and a diameter ratio of the vein; or
When the number of the veins is at least two, averaging the diameters of the veins to obtain a mean value of the veins;
determining a diameter ratio of the mean of the artery and the vein.
9. An apparatus for determining a ratio of arteriovenous diameters in a fundus image, the apparatus comprising:
an image acquisition unit for acquiring a fundus image to be detected and a blood vessel segmentation image of the fundus image;
a position determination unit for determining the optic disc position based on the fundus image;
a region determining unit, configured to determine an annular region from the blood vessel segmentation image with the optic disc position as a center;
the arteriovenous determining unit is used for determining arteries and veins meeting preset conditions according to the blood vessel segmentation image in the annular region;
a diameter ratio determination unit for determining a diameter ratio of the artery and the vein.
10. An electronic device, comprising a processor and a memory coupled to the processor, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method of any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010532386.6A CN111681276A (en) | 2020-06-11 | 2020-06-11 | Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010532386.6A CN111681276A (en) | 2020-06-11 | 2020-06-11 | Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111681276A true CN111681276A (en) | 2020-09-18 |
Family
ID=72454698
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010532386.6A Pending CN111681276A (en) | 2020-06-11 | 2020-06-11 | Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111681276A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932535A (en) * | 2020-09-24 | 2020-11-13 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing image |
| CN113344842A (en) * | 2021-03-24 | 2021-09-03 | 同济大学 | Blood vessel labeling method of ultrasonic image |
| CN114387209A (en) * | 2021-12-03 | 2022-04-22 | 依未科技(北京)有限公司 | Method, apparatus, medium, and device for fundus structural feature determination |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073918A (en) * | 2018-01-26 | 2018-05-25 | 浙江大学 | The vascular arteriovenous crossing compression feature extracting method of eye ground |
| CN111000563A (en) * | 2019-11-22 | 2020-04-14 | 北京理工大学 | Automatic measuring method and device for retinal artery and vein diameter ratio |
-
2020
- 2020-06-11 CN CN202010532386.6A patent/CN111681276A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108073918A (en) * | 2018-01-26 | 2018-05-25 | 浙江大学 | The vascular arteriovenous crossing compression feature extracting method of eye ground |
| CN111000563A (en) * | 2019-11-22 | 2020-04-14 | 北京理工大学 | Automatic measuring method and device for retinal artery and vein diameter ratio |
Non-Patent Citations (4)
| Title |
|---|
| CHISAKO MURAMATSU等: "Automated selection of major arteries and veins for measurement of arteriolar-to-venular diameter ratio on retinal fundus images" * |
| 蒋小森: "基于音视频特征的新闻视频分割技术研究与应用" * |
| 薛岚燕;曹新容;林嘉雯;郑绍华;余轮;: "动静脉血管自动分类方法及其管径测量" * |
| 郭莹等: "一种自动测量眼底图像中动静脉宽度比的方法" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111932535A (en) * | 2020-09-24 | 2020-11-13 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for processing image |
| CN113344842A (en) * | 2021-03-24 | 2021-09-03 | 同济大学 | Blood vessel labeling method of ultrasonic image |
| CN114387209A (en) * | 2021-12-03 | 2022-04-22 | 依未科技(北京)有限公司 | Method, apparatus, medium, and device for fundus structural feature determination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111681276A (en) | Method and device for determining ratio of arteriovenous diameter in fundus image and electronic equipment | |
| Tolias et al. | A fuzzy vessel tracking algorithm for retinal images based on fuzzy clustering | |
| Giachetti et al. | Accurate and reliable segmentation of the optic disc in digital fundus images | |
| JP7333465B2 (en) | Method and apparatus for discriminating artery and vein of retinal vessels | |
| CN107564048B (en) | Feature registration method based on bifurcation point | |
| US9974442B2 (en) | Method of, and apparatus for, processing volumetric image data | |
| US11783488B2 (en) | Method and device of extracting label in medical image | |
| CN111932535A (en) | Method, apparatus, device and storage medium for processing image | |
| Giachetti et al. | Multiresolution localization and segmentation of the optical disc in fundus images using inpainted background and vessel information | |
| Turior et al. | Quantification and classification of retinal vessel tortuosity | |
| CN114937024A (en) | Image evaluation method and device and computer equipment | |
| CN114549395A (en) | Method, apparatus, medium, and device for image feature determination based on view computation | |
| CN113450329B (en) | Microcirculation image blood vessel branch erythrocyte flow rate calculation method and system | |
| CN111797900A (en) | Arteriovenous classification method and device of OCT-A image | |
| CN109493383B (en) | Method for measuring intima-media thickness in ultrasonic image, server and storage medium | |
| CN115908405A (en) | Method and device for determining characteristics of eyeground and electronic equipment | |
| Shabbir et al. | A comparison and evaluation of computerized methods for blood vessel enhancement and segmentation in retinal images | |
| CN114387209A (en) | Method, apparatus, medium, and device for fundus structural feature determination | |
| CN113344893A (en) | High-precision fundus arteriovenous identification method, device, medium and equipment | |
| CN114373216A (en) | Eye movement tracking method, device, equipment and storage medium for anterior segment OCTA | |
| CN114387210A (en) | Method, apparatus, medium, and device for fundus feature acquisition | |
| CN114170258A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| Nazari et al. | Segmentation of retinal blood vessels by top-hat multi-scale detection for optic disc removal | |
| Tascini et al. | Retina vascular network recognition | |
| Roy et al. | A novel computer aided quantification method of focal arteriolar narrowing using colour retinal image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200918 |