CN110969617B

CN110969617B - Method, device, equipment and storage medium for identifying video cup video disc image

Info

Publication number: CN110969617B
Application number: CN201911303604.2A
Authority: CN
Inventors: 余双; 马锴; 郑冶枫; 龚丽君; 边成; 初春燕; 刘含若; 王宁利
Original assignee: Tencent Healthcare Shenzhen Co Ltd
Current assignee: Tencent Healthcare Shenzhen Co Ltd
Priority date: 2019-12-17
Filing date: 2019-12-17
Publication date: 2024-03-15
Anticipated expiration: 2039-12-17
Also published as: CN110969617A

Abstract

The application discloses a method, a device, equipment and a storage medium for identifying video cup video disc images, wherein the method comprises the following steps: obtaining segmentation information of a video disc image of a video cup to be analyzed, and carrying out ellipse fitting on the edge information of the video cup area and the edge information of the video disc area to obtain fitting ellipses corresponding to the video cup area and fitting ellipses corresponding to the video disc area; and determining the quantitative value of the disk edge morphology of the video disk image of the video cup to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area. According to the embodiment of the application, the video cup video disc image is quantitatively identified in multiple dimensions, and whether the video cup video disc shape is abnormal or not is judged by utilizing the obtained disc edge shape quantized value, so that the judging accuracy is improved.

Description

Method, device, equipment and storage medium for identifying video cup video disc image

Technical Field

The present application relates generally to the field of artificial intelligence, and in particular, to a method, apparatus, device, and storage medium for identifying a video disc image.

Background

As an important organ of the human body, the health condition of eyes is closely related to the quality of life of a person. With the development of artificial intelligence technology and image processing technology, the technology is gradually used for processing and analyzing fundus images so as to reflect the change of eye states.

Conventionally, when analyzing an fundus image, a cup area and a disc area are generally divided by using a machine learning model or image processing, and the morphology of the divided cup area and disc area is empirically observed based on the division result to determine the morphology change of the cup and disc in fundus oculi.

The above-mentioned empirical observation is used to judge the form of the optic disc and the optic cup, so that the accuracy is low and the reliability is poor.

Disclosure of Invention

In view of the foregoing drawbacks or shortcomings in the prior art, it is desirable to provide a method, apparatus, device and storage medium for identifying a optic disc image of a cup, by determining a quantitative value of a rim morphology of a optic disc image of a cup to be analyzed, so as to improve accuracy of judging the optic disc morphology of the cup.

In a first aspect, an embodiment of the present application provides a method for identifying an image of a optic disc of a cup, where the method includes:

obtaining segmentation information of a video disc image of a video cup to be analyzed, wherein the segmentation information comprises edge information of a video cup area and edge information of the video disc area;

performing ellipse fitting on the edge information of the cup area and the edge information of the disk area to obtain a fitting ellipse corresponding to the cup area and a fitting ellipse corresponding to the disk area;

And determining a disk edge shape quantization value of the video disk image of the video cup to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area, wherein the disk edge shape quantization value is a parameter for judging whether the shape of the video disk in the video cup video disk image is normal or not.

In a second aspect, an embodiment of the present application provides a device for analyzing an image of a video disc, the device including:

the acquisition module is used for acquiring segmentation information of the video disc image of the video cup to be analyzed, wherein the segmentation information comprises edge information of a video cup area and edge information of a video disc area;

the fitting module is used for carrying out ellipse fitting on the edge information of the cup area and the edge information of the optic disc area to obtain fitting ellipses corresponding to the cup area and the optic disc area;

the first determining module is configured to determine a disk edge shape quantization value of the optic disk image of the optic cup to be analyzed based on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disk area, where the disk edge shape quantization value is a parameter for determining whether the shape of the optic disk in the optic cup optic disk image is normal.

In a third aspect, an embodiment of the present application provides an apparatus, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the method for identifying a video disc image according to the first aspect.

In a fourth aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program for implementing the method for identifying a video disc image according to the first aspect above.

According to the method, the device, the equipment and the storage medium for identifying the optic cup video disc image, after the segmentation result of the optic cup video disc image to be analyzed is obtained, after ellipse fitting processing is carried out on the edge information of the optic cup area and the optic disc area in the segmentation result, the multi-dimensional quantitative analysis of the optic cup video disc image is carried out, the disc edge shape quantization value of the optic cup video disc image to be analyzed is calculated, and further whether the optic cup video disc shape in the optic cup video disc image is abnormal or not is judged by utilizing the disc edge shape quantization value, so that a scientific basis is provided for the shape judgment and analysis of the optic cup video disc in the fundus image.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the following drawings, in which:

FIG. 1 is a schematic view of a video disc image to be analyzed according to an embodiment of the present application;

FIG. 2 is a schematic view showing a segmentation of a video disc image to be analyzed according to an embodiment of the present application;

FIG. 3 is a flow chart of a method for identifying a video disc image of a video cup according to the present application;

FIG. 4 is a schematic view of an ellipse fitting of a optic cup area and a optic disc area according to an embodiment of the present application;

FIG. 5 is a flowchart of a method for identifying an image of a video disc according to another embodiment of the present application;

FIG. 6 is a schematic view of a cup area and a disc area in a normal state according to an embodiment of the present application;

FIG. 7 is a schematic view of a cup area and a disc area in an abnormal state according to an embodiment of the present application;

FIG. 8 is a schematic view of a normal view cup region and a normal view disk region in a polar coordinate system according to an embodiment of the present application;

FIG. 9 is a schematic view of a cup region and a optic disc region in an abnormal state in a polar coordinate system according to an embodiment of the present application;

FIG. 10 is a schematic diagram showing the variation of the standard disk along the width;

FIG. 11 is a schematic view showing the variation of the width of the disc in the normal state according to the embodiment of the present application;

FIG. 12 is a schematic view showing the variation of the width of the disc in the normal state according to the embodiment of the present application;

FIG. 13 is a flowchart of a method for identifying an image of a video disc according to still another embodiment of the present application;

FIG. 14 is a schematic view of the longitudinal dimensions of a video cup area and a video disk area according to an embodiment of the present application;

FIG. 15 is a schematic view of the lateral dimensions of a cup area and a disc area according to an embodiment of the present application;

FIG. 16 is a schematic view of the major axis dimension of the optic cup area and optic disc area according to an embodiment of the present application;

FIG. 17 is a schematic view of the area of the optic cup area and optic disc area according to an embodiment of the present application;

fig. 18 is a schematic structural diagram of a video disc image analysis device according to an embodiment of the present application;

fig. 19 is a schematic structural diagram of a computer system of a terminal device according to an embodiment of the present application.

Detailed Description

The present application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the related disclosure and not limiting thereof. It should be further noted that, for convenience of description, only the portions related to the disclosure are shown in the drawings.

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Machine Learning (ML) involves multiple disciplines such as probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory, and the like. It is specially studied how a computer simulates or implements learning behavior of a human to acquire new knowledge or skills, and reorganizes existing knowledge structures to continuously improve own performance. Machine learning is the core of artificial intelligence, a fundamental approach to letting computers have intelligence, which is applied throughout various areas of artificial intelligence. Machine learning and deep learning typically include techniques such as artificial neural networks, confidence networks, reinforcement learning, transfer learning, induction learning, teaching learning, and the like.

It will be appreciated that, as shown in fig. 1, the fundus image of the left eye obtained by photographing or the like may include a optic disc area corresponding to the optic disc, a cup area corresponding to a cup located in the middle of the optic disc area, and a rim area between the optic disc area and the cup area. Further, in order to determine the edge positions of the cup area and the optic disc area, after the fundus image is acquired, the fundus image may be segmented by using a machine learning algorithm or an image processing technique, etc., the edge positions of the cup area and the optic disc area may be identified, and the identification result may be as shown in fig. 2, so that the rim area between the cup edge and the optic disc edge may be determined.

That is, based on the division result, the rim area is the area from the rim of the optic cup area to the rim of the optic disk area, and then the rim width can be expressed as the distance from the intersection point of the rim of the optic cup and the ray to the intersection point of the rim of the optic disk and the ray on the same ray when the ray is led out to each direction of the optic cup area and the optic disk area by taking the center of the optic cup as the center point; the optic disc radius is the distance from the center point to the intersection of the optic disc edge and each ray, and the optic cup radius is the distance from the center point to the intersection of the optic cup edge and each ray.

In order to realize multi-dimensional accurate description of the shapes of the optic cup and the optic disc, the embodiment of the application provides a basis for judging and analyzing the shape of the optic cup and the optic disc in the optic cup and optic disc image, and on the basis of the segmentation result shown in fig. 2, the quantitative value of the shape of the disc edge of the optic cup and optic disc is determined by utilizing the segmentation result, and the characteristics of the optic cup and the optic disc of the fundus image to be analyzed are described by the accurate quantitative value.

The method for identifying the video disc image in the embodiment of the application can be executed by a device, and the device can be a computer device with data processing capability, such as a computer with image identification and segmentation capability, or a portable medical terminal device.

For easy understanding and explanation, the method, apparatus, device and storage medium for identifying a video disc image according to the embodiments of the present application are described in detail below with reference to fig. 3 to 19.

Fig. 4 is a flowchart of a method for calculating parameters of a video disc, which is executed by an apparatus and includes:

s01, the device acquires segmentation information of the video disc image of the video cup to be analyzed, wherein the segmentation information comprises edge information of a video cup area and edge information of the video disc area.

S02, the equipment carries out ellipse fitting on the edge information of the cup area and the edge information of the optic disc area to obtain fitting ellipses corresponding to the cup area and the optic disc area;

s03, the device determines the disk edge shape quantization value of the video disk image of the video cup to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area, and judges whether the shape of the video cup video disk in the video cup video disk image is abnormal or not according to the disk edge shape quantization value.

Specifically, in the embodiment of the present application, when the calculation of the quantitative value of the disc edge morphology in the optic disc image of the optic cup is performed, the calculation is performed on the basis of the segmentation result shown in fig. 2, and the segmentation result includes the optic cup area and the optic disc area of the fundus image.

It can be understood that, based on the segmentation result, the segmentation information of the fundus image to be analyzed acquired in step 01 is obtained based on the segmentation of the fundus image to be analyzed by using a machine algorithm or the like, and the cup region and the optic disc region are identified. That is, the segmentation information indicates the identified cup region edge position and disc region edge position, such as a sequence of coordinates of the cup region edge and disc region edge in a Cartesian coordinate system.

In practice, when the optic disc segmentation of the optic cup is realized by using a machine algorithm or other processing methods, the morphology of the obtained optic disc area and the optic cup area edge is identified to have flaws due to different algorithm performance problems or fundus picture quality problems.

On the basis, after the segmentation information of the fundus image to be analyzed is obtained, coordinate values of the edges of the optic cup area and the optic disc area can be preprocessed, such as ellipse fitting, so that flaws in segmentation results are eliminated, and calculation accuracy is improved. As shown in fig. 3, a fitted ellipse corresponding to the optic cup area and the optic disc area may be obtained, and then a coordinate sequence value corresponding to the fitted ellipse may be obtained.

For example, when ellipse fitting is performed, an initial fitted ellipse may be given by using edge information of a cup area and a disc area in the segmentation result, further, a sum of distances between coordinate points of the fitted ellipse and coordinate points in the edge information is determined, and finally, by continuous try, a fitted ellipse corresponding to the minimum distance sum is determined as a target fitted ellipse.

After the fitted ellipses corresponding to the optic cup area and the optic disc area are obtained, in step 03, the obtained fitted ellipses, that is, the sequence values of the fitted ellipses of the identification area and the optic disc area, may be used to calculate and obtain one or more optic cup optic disc parameters of the optic cup optic disc image to be analyzed, that is, calculate and obtain a rim morphology quantization value representing the morphology features of the optic cup optic disc in the optic cup optic disc image, and further determine whether the morphology of the optic cup optic disc is abnormal by using the rim morphology quantization value.

The quantitative value of the shape of the disc edge is a parameter for judging whether the shape of the optic disc of the optic cup in the optic disc image of the optic cup to be analyzed is normal or not. May include a rim average coefficient, a rim variation coefficient, and/or a rim reference coefficient, etc. The average disk edge coefficient represents the ratio of the disk edge area of the video disk image of the video cup to be analyzed in the video disk area, the variation coefficient of the disk edge represents the matching degree of the variation trend of the disk edge width of the video disk image of the video cup to be analyzed and the variation trend of the disk edge width of the video disk image of the standard video cup, and the reference coefficient of the disk edge represents the relation between the disk edge widths corresponding to all reference points of the video disk image of the video cup to be analyzed.

According to the method for identifying the video disc image of the video cup, after the segmentation result of the video disc image of the video cup to be analyzed is obtained, after ellipse fitting treatment is carried out on the edge information of the video cup area and the video disc area in the segmentation result, the multi-dimensional quantitative analysis of the video disc image of the video cup is carried out, the disc edge shape quantitative value of the video disc image of the video cup to be analyzed is calculated, and then whether the video disc shape of the video cup in the video disc image of the video cup is abnormal is judged by utilizing the disc edge shape quantitative value, so that scientific basis is provided for judging the video disc shape of the video cup, and judging accuracy is improved.

Further, in order to better understand the above-mentioned calculation process of the quantized values of the edge shapes, the calculation of the edge average coefficient, the edge variation coefficient, and the edge reference coefficient is described in detail with reference to fig. 5 to 19.

Fig. 5 is a schematic flow chart of a method for identifying an image of a video disc according to another embodiment of the present application, and as shown in the drawing, the method includes:

s21, the device acquires segmentation information of the video disc image of the video cup to be analyzed, wherein the segmentation information comprises edge information of the video cup area and edge information of the video disc area.

S22, carrying out ellipse fitting on the edge information of the cup area and the edge information of the optic disc area to obtain a fitting ellipse corresponding to the cup area and a fitting ellipse corresponding to the optic disc area.

S22, the device determines the width of the disk edge corresponding to each edge point of the video disk area of the video disk image to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area.

Specifically, in the embodiment of the present application, in a process of calculating a disk edge shape quantization value such as a disk edge average coefficient, a disk edge variation coefficient, a disk edge reference coefficient, and the like, after obtaining a segmentation result of a video disk image of a video cup to be analyzed, that is, edge information of a video cup area and a video disk area, ellipse fitting is further performed on the edge information, and then a disk edge width corresponding to each edge point of the video disk area can be calculated by using fitting ellipses corresponding to the video cup area and the video disk area.

Optionally, in an embodiment, the width of the rim corresponding to each edge point of the optic disc area is calculated by using the obtained fitted ellipses corresponding to the optic cup area and the optic disc area. As shown in fig. 4, the center of the fitted ellipse corresponding to the optic cup area may be taken as a center point, the distance between the center point and each edge point of the fitted ellipse of the optic disc area may be determined as a radius of the optic disc, and the distance between the center point and each edge point of the fitted ellipse of the optic cup area may be determined as a radius of the optic cup. And finally, calculating the difference value between the radius of the visual cup corresponding to each edge point of the visual disk area and the radius, wherein the difference value is used as the width of the disk edge corresponding to each edge point.

Optionally, in another embodiment, the result after ellipse fitting may be subjected to coordinate transformation, that is, coordinate sequence values corresponding to the fitted ellipse in the cartesian coordinate system are subjected to coordinate transformation, so as to obtain coordinate sequence values corresponding to the fitted ellipse in the polar coordinate system.

For example, as shown in fig. 6 and 7, the right-eye cup view disc image is shown in fig. 6, which shows the cup view disc image in a normal state, and fig. 7, which shows the cup view disc image in an abnormal state. The view cup disc segmentation result (or the result of the ellipse fitting processing as shown in the left-hand diagram of fig. 8 and 9) may be subjected to the polar coordinate transformation in the counterclockwise direction with the view cup center as the center and the nasal side as the starting point (or the temporal side as the starting point in the case of the left eye), and the resulting coordinate transformation diagram is shown in the middle polar coordinate diagram of fig. 8 and 9.

In fig. 8 and 9, the white area is an area obtained by coordinate expansion of the view cup area, the gray area is an area obtained by coordinate expansion of the disk edge area, that is, the coordinate values of the vertical axes (first directions) of the points at the lower edge of the view cup are represented by the view cup radius, the coordinate values of the points at the lower edge of the view disk are represented by the coordinate values in the vertical axis direction, the view disk radius, and the difference of the vertical axis coordinate values at the same horizontal axis point represents the disk edge width at that point.

Further, for ease of calculation, the alignment of the discs in fig. 8 and 9 is performed along the lower boundary (i.e., the lower edge of the optic disc area), resulting in the rightmost diagrams of fig. 8 and 9. For example, according to the gray edge coordinate values, the lower edges of the optic disc areas are then aligned uniformly to a value of polar coordinates, i.e., the coordinate values in the vertical axis direction are all subtracted by a certain height value.

At this time, the lower edge of the optic disc zone is taken as the horizontal axis, and the coordinate values of the vertical axis directions of the points of the upper edge of the disc edge zone between the lower edge of the optic disc and the lower edge of the optic cup directly represent the width of the disc edge at the position, namely, the coordinate values of the points of the lower edge of the optic cup zone in the first direction represent the width of the disc edge corresponding to the points of the edge of the optic disc zone, and the coordinate values of the vertical axis of the points of the upper edge of the optic cup zone represent the radius of the optic disc of the points of the edge of the optic disc.

It will be understood that the visualized results of the coordinate values representing the width of the rim are shown in fig. 11 and 12, that is, the curve corresponding to the coordinate values of the vertical axis in each sequence value of the upper edge of the rim represents the transformation curve of the width of the rim at each edge point of the optic disc in the polar coordinate system after the coordinate transformation is performed. As shown in fig. 11, the change curve of the disc edge, that is, the change curve of the disc rim width indicating each point of the disc zone edge in the normal state. As shown in fig. 12, the disc rim width change curve of each point of the disc rim in the abnormal state.

Alternatively, in another embodiment, for the calculation of the rim width, the calculation of the rim width may be directly performed without performing ellipse fitting; or directly converting coordinates without ellipse fitting, and then determining the width of the disk edge based on the information under the polar coordinates; alternatively, the calculation of the rim width may be performed directly after ellipse fitting.

For example, when ellipse fitting and coordinate transformation are not performed, in calculating the rim width, coordinate values of edges of the optic cup area and the optic disc area may be traversed first, rays are led out in all directions of the optic cup area and the optic disc area with the center of the optic cup as a center point, on the same ray, the radius of the optic disc is a distance from the center point to an intersection point of the optic disc edge and each ray, the radius of each point of the optic cup edge is determined with the distance from the center point to the intersection point of the optic cup edge and each ray, and the radius of each point of the optic disc edge is determined, and then the rim width of each point of the optic disc edge is determined by a difference value between the radius of the optic disc edge and the optic cup edge.

S24, the apparatus determines the disc edge average coefficient, the disc edge variation coefficient, and/or the reference coefficient based on the disc edge width.

Specifically, in the embodiment of the present application, when the rim width is obtained, the rim average coefficient, the rim variation coefficient, and/or the rim reference coefficient may be calculated.

For the rim average coefficient, it may be an average value of the ratio of the rim width corresponding to all or part of the rim points of the optic disc area (or the rim points of the optic cup area) to the radius of the optic disc at the corresponding position. The rim-average coefficient may represent the duty cycle of the rim-area in the total area of the disc. For abnormal optic cup video disk morphology images, the average disk edge coefficient becomes lower as the disk edge area becomes narrower; for normal cup optic disc images, the rim factor is high.

After the width of the disc edge is determined by the method, the specific calculation process of the average coefficient of the disc edge is as follows:

first, the device calculates the ratio of the rim width to the radius of the disc corresponding to each edge point of the disc zone, and then calculates the average value of the ratios corresponding to all or part of the edge points of the disc zone as the rim average coefficient.

Specifically, when coordinate transformation is performed, the average coefficient of the disc edge is calculated, and as shown in fig. 11 and 12, the coordinate value of the disc along the longitudinal axis corresponding to the edge point, that is, the disc edge width of each edge point of the optic disc, and the coordinate value of the longitudinal axis corresponding to each edge point of the corresponding optic cup area, that is, the radius of the optic disc may be taken for each point or every N points along the horizontal axis direction of the image. And then comparing the two to obtain the ratio corresponding to each point, and finally averaging the ratios corresponding to all the points to obtain the average coefficient of the disk edge.

Optionally, when the coordinate transformation is not performed, the rim width of each point on the rim of the optic disc can be calculated through the radius of the optic cup and the radius of the optic disc, or the rim width corresponding to every N points is determined, then the ratio of the obtained rim width to the radius of the optic disc at the corresponding position is determined, and finally the average value of all the ratios is calculated to determine the average coefficient of the rim.

For another example, for a disc rim variation coefficient, it is the trend or magnitude of the disc rim width at each edge point of the optic disc zone.

In practice, the trend of the disc width of the standard optic disc image as shown in fig. 10 may be taken as a reference standard, and the disc edge change coefficient may represent the matching degree of the trend of the disc width of the optic disc image of the optic cup to be analyzed and the trend of the disc width of the standard optic disc image. For example, the correlation between the curve corresponding to the width of the video disc image of the video cup to be analyzed and the variation curve of the width of the video disc image of the standard video cup can be calculated.

It can be understood that the disc edge variation coefficient may represent whether the disc edge variation width variation trend of the fundus image currently to be analyzed conforms to a normal disc edge width variation rule.

The specific calculation process can be as follows:

After the coordinate conversion, the coordinate value of the vertical axis on the upper boundary position of the disk edge is the width of the disk edge corresponding to each edge point of the video disk area. When calculating the disc edge variation coefficient, firstly, calculating the correlation of the two curves, such as calculating the correlation coefficient or calculating the mean square error of the two curves, by using the sequence value under the polar coordinate system and the sequence value corresponding to the standard disc edge curve, as the disc edge variation coefficient.

In one embodiment, the correlation coefficient may be calculated using the formula shown below to represent the disc edge variation coefficient:

in the above formula, a _i The rim width of the optic disc edge i point representing the standard cup optic disc image, i.e., the coordinate value of the vertical axis as shown in fig. 10, b _i Disc edge variation data representing the width of the disc edge i point of the video disc image of the video cup to be analyzed, i.e. the ordinate value of the disc edge i point as shown in fig. 11 or 12, r _ab I.e. representing the disc edge variation coefficient.

It will be appreciated that clinically standard disc change along width complies with the ISNT rule, i.e. as shown in fig. 10, under polar transformation starting at the nasal or temporal side, the normal disc change along width follows: ascending (upper side S), then descending (temporal side T or nasal side N), then ascending (lower side I), and finally descending (nasal side N or temporal side T). Fig. 11 and fig. 12 respectively show the disc edge width change diagrams of the normal disc and the abnormal disc, and the correlation coefficients between the two disc edge change diagrams and the standard disc edge change curve shown in fig. 10 respectively show whether the disc edge change accords with the normal disc edge change rule, namely, the disc edge change trend coefficient.

Then for r calculated as above _ab The larger the value, the more consistent the change of the disc edge is with the normal change rule of the disc edge, and the smaller the value, the abnormal change of the disc edge is indicated. The disc edge variation coefficient of the optic disc map of the fundus image in the normal state as shown in fig. 11 is 0.71, and the disc edge variation coefficient of the fundus image in the abnormal state as shown in fig. 12 is-0.58, reflecting whether or not both disc edge variations are normal.

For another example, for the rim reference coefficient, a relationship between rim widths corresponding to respective reference points of the optic disc image of the optic cup to be analyzed may be represented.

In practice, the analysis is typically performed with the rim width corresponding to four reference points on the fundus image, including three basic reference points and one fiducial reference point. As shown in fig. 2, the rim width (I) of the first reference point at the lowermost, the rim width (S) of the second reference point at the uppermost, the rim width (N) of the third reference point near the nasal side, i.e., the reference point, and the rim width (T) of the fourth reference point near the temporal side.

It will be appreciated that in normal conditions, the rim width of each reference point complies with the ISNT rule, i.e., I > S > N > T. I.e. the rim width of the base reference point on the nose side is smaller than the rim width of the other three reference points. Therefore, the rim width of the reference point on the nose side can be set as one reference, and the rim widths of the reference points in the other three directions can be compared with the rim width of the reference point to acquire the rim reference coefficient.

The specific process is as follows:

after the coordinate conversion is performed, the sequence value of the rim width of each edge point of the optic disc zone, that is, the coordinate value in the longitudinal axis direction is obtained, so that the rim width corresponding to each reference point of the optic disc zone can be determined, and then the rim reference coefficient is determined according to the rim width of each reference point.

Based on the above embodiment, four reference points are defined on the fundus image, as shown in fig. 11 and 12, including three basic reference points and one base reference point:

first, the rim widths corresponding to the first reference point, the second reference point, the third reference point, and the fourth reference point of the video disc rim may be determined. And further calculating the variation degree of the edge width corresponding to the first reference point, the second reference point and the fourth reference point and the edge width corresponding to the third reference point, and finally determining the sum of the variation degrees corresponding to the first reference point, the second reference point and the fourth reference point as the edge reference coefficient.

Optionally, in this embodiment of the present application, the degree of variation r of each reference point _s ，r _i And r _t The disk edge reference coefficient r _n The expression can be expressed by the following formula:

r _N ＝r _s +r _I +0.5r _t

wherein S, N, I, T represent the rim widths of the upper, nasal, lower and temporal sides, respectively, i.e., the rim widths corresponding to the first, second, third and fourth reference points.

It can be understood that since the variation of the disc width of each reference point is in accordance with the ISNT rule under normal conditions, the disc of the fundus image in normal state, r _s ，r _i And r _t The parameters are all positive numbers, so r _n And is also a positive number. When the fundus image in an abnormal state, namely the width of the disc edge does not accord with the ISNT rule, r _s ，r _i And r _t The parameter may become negative, indicating that the width of the disc along the relevant side is smaller (upper, lower) than the nasal side.

On the other hand, when the coordinate transformation step is not performed, that is, when the cup radius is determined by using the edge information of the cup area in the division information and the disc radius is determined by using the edge information of the disc area, and then the rim width of each point is determined by using the cup radius and the disc radius, the rim change coefficient and the rim standard coefficient may be calculated by using the above formula after obtaining the rim width of each point on the edge of the disc by using the coordinate sequence values obtained by division or after performing ellipse fitting on the division information.

Optionally, in another embodiment of the present application, before obtaining the segmentation information of the optic disc image of the optic cup to be analyzed, the method may further include obtaining a fundus image to be analyzed, and performing segmentation processing on the fundus image to obtain the segmentation information.

According to the method for identifying the video disc image of the video disc to be analyzed, after the segmentation result of the video disc to be analyzed is obtained, ellipse fitting is carried out on the result, and then coordinate conversion is carried out on the basis of the obtained fitting ellipse, so that the disc edge width, the disc radius and the video disc radius of the video disc image of the video disc to be analyzed are intuitively displayed in a polar coordinate system, and therefore coordinate values on a vertical axis in the polar coordinate system can be directly utilized as input quantities when the quantitative value of the disc edge shape is calculated, the average disc edge coefficient, the disc edge changing coefficient and the disc edge reference coefficient can be quickly obtained, the disc edge width changing characteristic of the video disc image of the video disc to be analyzed can be intuitively displayed in a visual mode, the video disc image identification efficiency of the video disc to be analyzed is improved, and an accurate reference basis is provided for judging the shape of the video disc.

On the other hand, in the embodiment of the present application, after the segmentation information of the fundus image is acquired, cup-Disc Ratio (Cup Disc Ratio, CDR) of the optic Disc image to be analyzed may also be calculated by using the edge information of the optic Cup region and the edge information of the optic Disc region in the segmentation information.

It will be appreciated that the size of this cup to disc ratio is a very important feature describing the morphology of the optic disc in the optic disc image of the optic cup to be analyzed, and that the value of the cup to disc ratio is mostly no more than 0.4 for the fundus image in the normal state. Clinically, if the cup to disc ratio is greater than 0.6 or 0.7, there is a high probability of a cup to disc morphology being considered abnormal to determine the subsequent need for functional checks such as visual field and eye pressure.

Fig. 13 is a schematic flow chart of a cup/tray ratio calculation method according to an embodiment of the present application, and as shown in the fig. 13, the method includes:

s11, the device acquires segmentation information of the video disc image of the video cup to be analyzed.

S12, the equipment respectively carries out ellipse fitting on the edge information of the cup area and the edge information of the optic disc area to obtain fitting ellipses corresponding to the cup area and the optic disc area;

s13, the device determines the square root, the longitudinal ratio, the transverse ratio and the long axis ratio of the area ratio of the optic cup area to the optic disc based on the fitting ellipse corresponding to the optic cup area and the fitting ellipse corresponding to the optic disc area.

S14, the device calculates the average value of the square root of the area ratio, the longitudinal ratio, the transverse ratio and the long axis ratio, wherein the average value is the cup-disc ratio of the video disc image of the cup to be analyzed.

It will be appreciated that in practice, based on the segmentation result, the method of measuring the cup/disc ratio is focused on the measurement of the vertical longitudinal cup/disc ratio, i.e. the diameters of the viewing cup area and the optic disc area in the vertical direction, respectively, with the ratio of the two being the final cup/disc ratio. However, in actual clinic, especially under the influence of high myopia, the optic disc may be inclined, and the vertical cup ratio may not reflect the actual optic disc area and the form size of the optic cup area, so that the calculation of the vertical cup ratio is directly performed, and there is a relatively large error or deviation.

In the embodiment of the application, in order to improve the calculation accuracy of the cup-disc ratio, compensate errors caused by the inclination of the video disc caused by special conditions such as myopia and the like, acquire a plurality of different measurement sizes at a plurality of measurement angles, thereby acquiring a plurality of cup-disc ratios, and finally fuse the acquired cup-disc ratios to obtain the target cup-disc ratio.

Specifically, as shown in fig. 13, when calculating the cup/disc ratio of the optic disc image of the optic cup to be analyzed, first, ellipse fitting of the optic cup area and the optic disc area may be performed by using the edge information of the optic cup area and the edge information of the optic disc area in the acquired segmentation information, and as shown in fig. 5, fitting ellipses corresponding to the optic cup area and the optic disc area may be obtained.

After the corresponding fitting ellipses are obtained, different sizes of the visual cup area and the visual disk area can be calculated to obtain a plurality of cup-disk ratios corresponding to the different sizes, and then the cup-disk ratios are fused to obtain the final cup-disk ratio.

For example, as shown in fig. 14 to 17, the longitudinal dimension, the lateral dimension, the major axis dimension, and the area of the optic cup area and the optic disc area are calculated, respectively. The ratio of the longitudinal dimension of the optic cup area to the optic disc area, the ratio of the transverse dimension, the ratio of the long axis dimension, and the square root of the area ratio are then calculated. Finally, all ratios can be averaged, i.e. the cup-to-disc ratio as the cup-to-disc image to be analyzed.

As shown in fig. 14, the longitudinal dimension is the overall dimension of the optic cup area and the optic disc area in the vertical direction; as shown in fig. 15, the lateral dimension is the overall dimension of the optic cup area and the optic disc area in the horizontal direction; as shown in fig. 16, the major axis dimension is the dimension of the major axis of the ellipse corresponding to the optic cup area and the optic disc area; as shown in fig. 17, the area is the area of an ellipse corresponding to the optic cup area and the optic disc area.

It can be understood that in this embodiment, when calculating the longitudinal dimension, the transverse dimension, the long axis dimension, and the area, two or more terms may be selectively calculated to improve the accuracy of calculation, that is, it may be determined, according to the actual situation, to use two or more terms of the square root of the longitudinal ratio, the transverse ratio, the long axis ratio, and the area ratio of the optic disc area and the optic cup area to represent the cup-disc ratio of the optic disc image of the optic cup to be analyzed.

It is further understood that in the embodiment of the present application, the obtained edge coordinate values may be directly utilized, that is, S12 may not be executed. The longitudinal dimension, the transverse dimension, the long axis dimension and the area value can be determined by traversing the edge coordinate values by taking the center of the visual cup as a center point.

According to the embodiment of the application, the average value of the square root, the longitudinal ratio, the transverse ratio and the long axis ratio of the area ratio is calculated, and the average value is used as the cup-disc ratio of the video disc image of the cup to be analyzed, so that the accuracy difference caused by a single calculation scale is made up in multiple aspects.

In addition, in the embodiment of the present application, before obtaining the segmentation information of the optic disc image of the optic cup to be analyzed, the method may further include obtaining the optic disc image of the optic cup to be analyzed, and performing segmentation processing on the fundus image to obtain the segmentation information of the optic disc image of the optic cup to be analyzed.

In another aspect, as shown in fig. 18, the present application provides a device for analyzing an image of a video disc, the device 200 comprising:

an obtaining module 210, configured to obtain segmentation information of a video disc image of a video cup to be analyzed, where the segmentation information includes edge information of a video cup area and edge information of a video disc area;

and the fitting module 220 is configured to perform ellipse fitting on the edge information of the optic cup area and the edge information of the optic disc area to obtain a fitting ellipse corresponding to the optic cup area and a fitting ellipse corresponding to the optic disc area.

The first determining module 230 is configured to determine a disk edge morphology quantization value of the optic disk image of the optic cup to be analyzed based on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disk area, and determine whether the morphology of the optic cup in the optic disk image of the optic cup is abnormal according to the disk edge morphology quantization value.

Optionally, the optic disc image analysis device of the embodiment of the application, the disc edge morphology quantization value includes a disc edge average coefficient, a disc edge variation coefficient and/or a disc edge reference coefficient.

The first determination module 230 includes:

a first determining unit 231, configured to determine a rim width corresponding to each edge point of the optic disc area of the optic disc image of the optic cup to be analyzed based on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disc area;

a second determining unit 232 that determines the rim-average coefficient, the rim-variation coefficient, and/or the rim-reference coefficient based on the rim width, wherein,

the average disk edge coefficient represents the ratio of the disk edge area of the video disk image of the video cup to be analyzed in the video disk area;

the disc edge change coefficient represents the matching degree of the change trend of the disc edge width of the video disc image of the video cup to be analyzed and the change trend of the disc edge width of the video disc image of the standard video cup;

the rim reference coefficient represents the relationship between the rim widths corresponding to each reference point of the optic disc image of the optic cup to be analyzed.

Optionally, in the video disc image analysis device of the embodiment of the present application, the first determining unit 231 is specifically configured to:

and taking the center of the fitting ellipse corresponding to the cup area as a center point, wherein the distance from the center point to each edge point of the fitting ellipse of the disk area is the radius of the disk, the distance from the center point to each edge point of the fitting ellipse of the cup area is the radius of the cup, and the difference between the radius of the cup corresponding to each edge point and the radius is the width of the disk edge.

taking the fitted ellipse center corresponding to the optic cup area as a starting point, and carrying out coordinate transformation on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disk area to obtain the edge information of the optic cup area and the edge information of the optic disk area in a polar coordinate system;

and aligning the lower edge of the video disc zone in the polar coordinate system, wherein coordinate values in the first direction of each point of the lower edge of the video cup zone in the polar coordinate system represent the width of the disc edge.

Optionally, in the video disc image analysis device of the embodiment of the present application, the second determining unit 232 is specifically configured to:

determining the ratio of the width of the disc edge corresponding to each edge point of the video disc zone to the radius of the video disc;

and determining the average value of the ratios corresponding to all or part of edge points, wherein the average value is used as the average coefficient of the disk edge, and coordinate values in the first direction of each point of the upper edge of the view cup area represent the radius of the video disk in the polar coordinate system.

and determining the disk edge width of each edge point of the video disk area of the video cup video disk image to be analyzed, and taking the correlation coefficient between the disk edge widths of each edge point corresponding to the video disk area of the standard video cup video disk image as the disk edge change coefficient.

determining the widths of the disk edges corresponding to a first reference point, a second reference point, a third reference point and a fourth reference point of the disk edge;

calculating the variation degree of the edge width corresponding to the first reference point, the second reference point and the fourth reference point and the edge width corresponding to the third reference point;

and determining the sum of the variation degrees corresponding to the first reference point, the second reference point and the fourth reference point as the disk edge reference coefficient.

Optionally, the device for analyzing a video disc image according to the embodiment of the present application further includes a second determining module 240, configured to:

based on the fitting ellipse corresponding to the optic cup area and the fitting ellipse corresponding to the optic disk area, respectively determining square root, longitudinal ratio, transverse ratio and long axis ratio of the area ratio of the optic cup area to the optic disk area;

the square root of the area ratio, the average of the longitudinal ratio, the transverse ratio and the long axis ratio was calculated, and the average was taken as the cup/tray ratio.

In another aspect, an apparatus provided by an embodiment of the present application includes a memory, a processor, and a computer program stored on the memory and executable on the processor, which when executed by the processor implements a method for identifying a video disc image as described above.

Referring now to fig. 19, fig. 19 is a schematic structural diagram of a computer system of a terminal device according to an embodiment of the present application.

As shown in fig. 19, the computer system 300 includes a Central Processing Unit (CPU) 301 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage section 303 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the system 300 are also stored. The CPU 301, ROM 302, and RAM 303 are connected to each other through a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

The following components are connected to the I/O interface 305: an input section 306 including a keyboard, a mouse, and the like; an output portion 307 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 308 including a hard disk or the like; and a communication section 309 including a network interface card such as a LAN card, a modem, or the like. The communication section 309 performs communication processing via a network such as the internet. The drive 310 is also connected to the I/O interface 305 as needed. A removable medium 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed on the drive 310 as needed, so that a computer program read therefrom is installed into the storage section 308 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 303, and/or installed from the removable medium 311. The above-described functions defined in the system of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 301.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, 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 systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units or modules described in the embodiments of the present application may be implemented by software, or may be implemented by hardware. The described units or modules may also be provided in a processor, for example, as: a processor, comprising: the device comprises an acquisition module, a fitting module and a determination module. The names of these units or modules do not limit the units or modules, for example, the determining module may be further described as "determining a quantitative value of a disk edge morphology of the optic disk image of the optic cup to be analyzed based on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disk area", and determining whether the morphology of the optic cup in the optic cup disk image is abnormal or not according to the quantitative value of the disk edge morphology ".

As another aspect, the present application also provides a computer-readable storage medium that may be included in the electronic device described in the above embodiments; or may be present alone without being incorporated into the electronic device. The computer-readable storage medium stores one or more programs that, when executed by one or more processors, perform the method of identifying a video disc image described herein:

obtaining segmentation information of a video disc image of a video cup to be analyzed, wherein the segmentation information comprises edge information of a video cup area and edge information of a video disc area;

performing ellipse fitting on the edge information of the cup area and the edge information of the disk area to obtain fitting ellipses corresponding to the cup area and the disk area;

and determining a disk edge shape quantization value of the video disk image to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area, and judging whether the shape of the video disk in the video cup video disk image is abnormal or not according to the disk edge shape quantization value.

In summary, after the segmentation result of the optic disc image of the optic cup to be analyzed is obtained, the method, the device, the equipment and the storage medium for identifying the optic disc image of the optic cup are used for carrying out ellipse fitting processing on the edge information of the optic cup area and the optic disc area in the segmentation result, then carrying out multidimensional quantitative analysis on the optic disc image of the optic cup to be analyzed, calculating the shape quantization value of the edge of the optic disc image of the optic cup to be analyzed, and further judging whether the shape of the optic disc in the optic disc image of the optic cup is normal or not by utilizing the shape quantization value of the edge, thereby providing scientific basis for judging whether the shape of the optic disc of the optic cup is abnormal or not and improving the judging accuracy.

The foregoing description is only of the preferred embodiments of the present application and is presented as a description of the principles of the technology being utilized. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this application is not limited to the specific combinations of features described above, but it is intended to cover other embodiments in which any combination of features described above or equivalents thereof is possible without departing from the spirit of the disclosure. Such as the above-described features and technical features having similar functions (but not limited to) disclosed in the present application are replaced with each other.

Claims

1. A method for identifying a cup optic disc image, the method comprising:

determining a disk edge shape quantization value of the video disk image to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area, and judging whether the shape of the video disk in the video cup video disk image is abnormal or not according to the disk edge shape quantization value;

The disk edge shape quantization value includes a disk edge average coefficient, a disk edge variation coefficient, and/or a disk edge reference coefficient, and determining the disk edge shape quantization value of the to-be-analyzed cup optic disk image based on the fitted ellipse corresponding to the cup region and the fitted ellipse corresponding to the optic disk region includes:

determining the width of a disk edge corresponding to each edge point of the video disk area of the video disk image to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area; determining the rim-average coefficient, the rim-variation coefficient, and/or the rim-reference coefficient based on the rim width;

wherein the disc edge average coefficient represents the duty ratio of the disc edge area of the video disc image of the video cup to be analyzed in the video disc area; the disc edge change coefficient represents the matching degree of the change trend of the disc edge width of the to-be-analyzed cup video disc image and the change trend of the disc edge width of the standard cup video disc image; and the disc edge reference coefficient represents the relation between the disc edge widths corresponding to all the reference points of the video disc image of the cup to be analyzed.

2. The method of claim 1, wherein determining a rim width corresponding to each edge point of the optic disc zone of the optic disc image to be analyzed based on the fitted ellipse corresponding to the optic cup zone and the fitted ellipse corresponding to the optic disc zone comprises:

Taking the fitted ellipse center corresponding to the visual cup area as a starting point, and carrying out coordinate transformation on the fitted ellipse corresponding to the visual cup area and the fitted ellipse corresponding to the video disc area to obtain the edge information of the visual cup area and the edge information of the video disc area in a polar coordinate system;

and aligning the lower edge of the video disc zone in the polar coordinate system, wherein in the polar coordinate system, coordinate values of each point of the lower edge of the video cup zone in the first direction represent the width of the disc edge corresponding to each edge point of the video disc zone.

3. The method of claim 1, wherein determining a rim width corresponding to each edge point of the optic disc zone of the optic disc image to be analyzed based on the fitted ellipse corresponding to the optic cup zone and the fitted ellipse corresponding to the optic disc zone comprises:

the center of the fitting ellipse corresponding to the view cup area is taken as a center point, the distance from the center point to each edge point of the fitting ellipse of the view disk area is determined as the radius of the view disk, and the distance from the center point to each edge point of the fitting ellipse of the view cup area is determined as the radius of the view cup;

and calculating the difference value between the radius of the optic cup corresponding to each edge point of the optic disc area and the radius, wherein the difference value is used as the width of the disc edge corresponding to each edge point.

4. A method of identifying a video disc as claimed in any one of claims 1 to 3 wherein said determining said disc rim average coefficient based on said disc rim width comprises:

determining the ratio of the width of the disc edge corresponding to each edge point of the video disc area to the radius of the video disc;

and determining an average value of the ratios corresponding to all or part of edge points, wherein the average value is used as the disc edge average coefficient, and coordinate values in a first direction of each point of the upper edge of the view cup area in the polar coordinate system represent the radius of the video disc.

5. A method of identifying a video disc as claimed in any one of claims 1 to 3 wherein said determining said disc rim variation factor based on said disc rim width comprises:

and determining the disk edge width of each edge point of the video disk area of the video disk image of the video cup to be analyzed, and taking the correlation coefficient between the disk edge widths of each edge point corresponding to the video disk area of the video disk image of the standard video cup as the disk edge changing coefficient.

6. A method of identifying a video disc as claimed in any one of claims 1 to 3 wherein said determining said disc rim reference factor based on said disc rim width comprises:

Determining the widths of the disc edges corresponding to a first reference point, a second reference point, a third reference point and a fourth reference point of the video disc edge;

calculating the variation degree of the disc edge width corresponding to the first reference point, the second reference point and the fourth reference point and the disc edge width corresponding to the third reference point;

and determining the sum value of the variation degrees corresponding to the first reference point, the second reference point and the fourth reference point as the disk edge reference coefficient.

7. The method for identifying a video disc image according to claim 1, wherein after performing ellipse fitting on the edge information of the video cup area and the edge information of the video disc area to obtain a fitting ellipse corresponding to the video cup area and a fitting ellipse corresponding to the video disc area, the method further comprises:

and calculating the square root of the area ratio, the longitudinal ratio, the transverse ratio and the average value of the long axis ratio, and taking the average value as the cup-disk ratio.

8. A cup optic disc image recognition device, the device comprising:

the fitting module is used for carrying out ellipse fitting on the edge information of the visual cup area and the edge information of the visual disk area to obtain fitting ellipses corresponding to the visual cup area and the fitting ellipses corresponding to the visual disk area;

the first determining module is used for determining a disk edge shape quantization value of the video disk image of the video cup to be analyzed based on the fitting ellipse corresponding to the video cup area and the fitting ellipse corresponding to the video disk area, and judging whether the shape of the video cup video disk in the video cup video disk image is abnormal or not through the disk edge shape quantization value;

the edge morphology quantization value includes an edge average coefficient, an edge variation coefficient, and/or an edge reference coefficient, and the first determining module includes:

a first determining unit, configured to determine a rim width corresponding to each edge point of the optic disc area of the optic disc image of the optic cup to be analyzed based on the fitted ellipse corresponding to the optic cup area and the fitted ellipse corresponding to the optic disc area;

A second determination unit configured to determine the rim-average coefficient, the rim-variation coefficient, and/or the rim-reference coefficient based on the rim width, wherein,

the disc edge average coefficient represents the ratio of the disc edge area of the video disc image of the video cup to be analyzed in the video disc area;

the disc edge change coefficient represents the matching degree of the change trend of the disc edge width of the to-be-analyzed cup video disc image and the change trend of the disc edge width of the standard cup video disc image;

and the disc edge reference coefficient represents the relation between the disc edge widths corresponding to all the reference points of the video disc image of the cup to be analyzed.

9. The device for recognizing an image of a video disc according to claim 8, wherein said first determining unit is specifically configured to:

10. The device for recognizing an image of a video disc according to claim 8, wherein said first determining unit is specifically configured to:

11. The device for identifying a video disc image according to any one of claims 8 to 10, characterized in that said second determining unit is specifically configured to:

12. The identifying disc image identifying device according to any of the claims 8-10, characterized in that the second determining unit is specifically adapted to:

13. The device for identifying a video disc image according to any one of claims 8 to 10, characterized in that said second determining unit is specifically configured to:

14. The optic disc image recognition device of claim 8, further comprising a second determining module configured to determine a square root, a longitudinal ratio, a transverse ratio, and a major axis ratio of an area ratio of the optic cup region to the optic disc region, respectively, based on the fitted ellipse for the optic cup region and the fitted ellipse for the optic disc region;

15. A terminal device comprising a memory, a processor and a computer program stored on the memory and executable on the processor for implementing the method of identifying a video disc image according to any one of claims 1-7 when said program is executed.

16. A computer-readable storage medium having stored thereon a computer program for implementing the cup optic disc image recognition method according to any one of claims 1-7.