CN109549619A - Eyeground disk determines method, glaucoma disease diagnostic device and system along width - Google Patents
Eyeground disk determines method, glaucoma disease diagnostic device and system along width Download PDFInfo
- Publication number
- CN109549619A CN109549619A CN201811466223.1A CN201811466223A CN109549619A CN 109549619 A CN109549619 A CN 109549619A CN 201811466223 A CN201811466223 A CN 201811466223A CN 109549619 A CN109549619 A CN 109549619A
- Authority
- CN
- China
- Prior art keywords
- disk
- along width
- optic
- region
- width value
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/1005—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring distances inside the eye, e.g. thickness of the cornea
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
- A61B3/12—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for looking at the eye fundus, e.g. ophthalmoscopes
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Ophthalmology & Optometry (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Eye Examination Apparatus (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of eyeground disk and determines method, glaucoma disease diagnostic device and system along width, wherein the eyeground disk determines that method includes obtaining eye fundus image along width;Optic disk region and optic cup region are identified in the eye fundus image;Equalization point is determined according to the position of the central point of the position of the central point in the identification optic disk region and the optic cup region;Determine disk along width value based on the position of the equalization point.
Description
Technical field
The present invention relates to eye testing equipment fields, and in particular to a kind of eyeground disk determines method, green light eye illness along width
Sick diagnostic device and system.
Background technique
Glaucoma is a kind of irreversible blinding fundus oculi disease, and in screening or clinical diagnosis, doctor can pass through sight
Eye fundus image is examined to judge whether those who are investigated may be with glaucomas, to be made whether to need further to check or medical
It is recommended that.
In clinical diagnosis, oculist can be judged by the case where optic cup in observing eye base map and optic disk.Example
If optic cup is excessive, cause the ratio of optic cup optic disk excessive, then those who are investigated are likely to glaucoma, and cup disc ratio therein is general
For the perpendicular diameter of optic cup and optic disk ratio.
But oculist's naked eyes or by capture apparatus estimate cup disc ratio or disk along form mode subjectivity very
By force, lack objective data foundation, cause result not accurate enough, and consume a large amount of time and efforts.
Summary of the invention
In view of this, first aspect present invention, which provides a kind of eyeground disk, determines method along width, include the following steps:
Obtain eye fundus image;
Optic disk region and optic cup region are identified in the eye fundus image;
It is determined according to the position of the central point of the position of the central point in the identification optic disk region and the optic cup region flat
Point;
Determine disk along width value based on the position of the equalization point.
Optionally, the basis identifies optic disk region and optic cup region in the eye fundus image, comprising:
The effective coverage comprising optic disk is identified from the eye fundus image using the first machine learning model;
Optic disk region is identified from the effective coverage using the second machine learning model;
Optic cup region is identified from the effective coverage using third machine learning model.
Optionally, the position based on the equalization point determines disk along width, comprising:
The lateral straight line by the equalization point is determined in the horizontal direction;
Determine the lateral straight line and the first intersection point of the optic disk region contour and the lateral straight line and the view
Second intersection point of cup region contour;
First intersection point for calculating the same side in the eye fundus image is used as lateral disk at a distance from second intersection point
Along width value.
Optionally, the position based on the equalization point determines disk along width, comprising:
Longitudinal straight line by the equalization point is determined in vertical direction,
Determine longitudinal straight line and the third intersection point of the optic disk region contour and longitudinal straight line and the view
4th intersection point of cup region contour;
The third intersection point for calculating the same side in the eye fundus image is used as longitudinal disk at a distance from the 4th intersection point
Along width value.
Optionally, the position based on the equalization point determines disk along width, comprising:
The a plurality of straight line by the equalization point is determined on multiple direction initializations;
The 4th intersection point and a plurality of straight line and the institute of a plurality of straight line and the optic disk region contour are determined respectively
State the 5th intersection point of optic cup region contour;
Calculate separately the 4th intersection point on same straight line between the 5th intersection point at a distance from obtain multiple disk edges
Width value;
Minimum value of the multiple disk in width value is obtained as the disk of side where the multiple direction initialization along width.
Optionally, the disk along width value include upper square plate along width value, disk under along width value, left hand plate along width value
With right side disk along width value.
Second aspect of the present invention provides a kind of eyeground disk along width determining device, comprising:
Acquiring unit, for obtaining eye fundus image;
Region identification block, for identifying optic disk region and optic cup region in the eye fundus image;
Equalization point determination unit, for the position and the optic cup region according to the central point in the identification optic disk region
The position of central point determines equalization point;
Disk is along determination unit, for determining disk along width value based on the position of the equalization point.
Third aspect present invention provide a kind of electronic equipment characterized by comprising at least one processor and with institute
State the memory of at least one processor communication connection;Wherein, be stored with can be by least one described processor for the memory
The instruction of execution, described instruction are executed by least one described processor, so that at least one described processor executes above-mentioned eye
Chassis determines method along width.
Fourth aspect present invention provides a kind of glaucoma image judgment means, comprising:
Eyeground disk is along width determination unit, for determining that method determines disk along width value along width according to above-mentioned eyeground disk;
Judging unit, for determining whether the eye fundus image is glaucoma image along width value according to the disk.
Optionally, the disk along width value include upper square plate along width value, disk under along width value, nasal side disk along width value
With temporo side panel along width value;
The judging unit judges whether the eye fundus image is green along the size relation of width value according to four kinds of disks
Light eye image.
A kind of glaucoma disease diagnostic system of fifth aspect present invention, comprising:
Eye-ground photography equipment, for shooting user's eye fundus image;And above-mentioned glaucoma image judgment means.
The eyeground disk provided according to embodiments of the present invention determines method along width, and optic disk area is identified first from eye fundus image
Domain and optic cup region, then respectively determine both central point, further according to the two central points determine one it is average in
Heart point, to take into account the center in the two regions.Disk is determined along width based on the position of this mean center point, obtained number
Value can accurately embody the morphological character of optic disk and optic cup, and this programme is calculated based on image data and objective algorithm can be intuitive
The disk of measurement saves human resources, can effectively assist doctor or expert to judge glaucoma disease along data.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 determines the flow chart of method for the eyeground disk in the embodiment of the present invention along width;
Fig. 2 determines the flow chart of method for specific eyeground disk a kind of in the embodiment of the present invention along width;
Fig. 3 is the eye fundus image after the shearing in the embodiment of the present invention;
Fig. 4 is the effective coverage image comprising optic disk in the embodiment of the present invention;
Fig. 5 is one of embodiment of the present invention sample image;
Fig. 6 is another sample image in the embodiment of the present invention;
Fig. 7 is to determine eyeground disk along the schematic images of width process in the embodiment of the present invention;
Fig. 8 is structure chart of the eyeground disk in the embodiment of the present invention along width determining device;
Fig. 9 is the structure chart of the glaucoma image judgment means in the embodiment of the present invention;
Figure 10 is the structure chart of the glaucoma disease diagnostic system in the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is clearly and completely described below in conjunction with attached drawing, it is clear that described implementation
Example is a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" be based on the orientation or positional relationship shown in the drawings, merely to
Convenient for description the present invention and simplify description, rather than the device or element of indication or suggestion meaning must have a particular orientation,
It is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.In addition, term " first ", " second ",
" third " is used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance.
As long as in addition, the non-structure each other of technical characteristic involved in invention described below different embodiments
It can be combined with each other at conflict.
The present invention provides a kind of eyeground disks to determine method along width, and this method can be by computer, server or just
Take the execution of the electronic equipments such as formula terminal.As shown in Figure 1, this method comprises the following steps:
S1A obtains eye fundus image.Eye fundus image is usually color image, but also be can be used in embodiments of the present invention
Single pass gray level image possibly even uses lines image.
S2A identifies optic disk region and optic cup region in eye fundus image.Specific recognition methods includes a variety of, such as can be with
Based on machine vision principle, according to the two regions of the pixel value signature search of pixel;Intelligent algorithm can also be used,
These regions are identified using the machine learning model after training.
S3A determines equalization point according to the position of the central point of the position of the central point in optic disk region and optic cup region.Specifically
Ground determines optic disk central point and optic cup according to the edge (profile) at the edge (profile) in optic disk region and optic cup region respectively first
Central point.
Optic disk central point is to be and optic cup profile with optic disk profile surrounding distance position as equal as possible, optic cup central point
Surrounding distance position as equal as possible, the two central points will not be usually overlapped.
Optic disk region and optic cup region are all irregular shapes, determine that the algorithm of the central point of irregular closed area has
A variety of, the present invention can be used any existing algorithm and find the two central points.
A central point is determined according to the two-dimensional coordinate (position in the picture) of optic disk central point and optic cup central point, it is right
Optic disk center point coordinate and optic cup center point coordinate are summed and are averaged, and new center point coordinate is obtained, this new central point can quilt
It is considered revised optic disk central point.Following formula calculating can be used for example:
Wherein xdiscFor the abscissa in the picture of optic disk central point, ydiscFor in the picture vertical of optic disk central point
Coordinate, xcupFor the abscissa in the picture of optic cup central point, ycupFor the ordinate in the picture of optic cup central point,
xcenterFor the abscissa of equalization point in the picture, ycenterFor the ordinate of equalization point in the picture.
S4A determines disk along width value based on the position of equalization point.From equalization point, to any one of image side
Position generates straight line, or from any one position of image border, generates straight line to central point, can make this
Straight line and the edge in optic cup region generate an intersection point, and generate an intersection point with the edge in optic disk region.The two are handed over
Distance between point is distance of the optic disk edge on this direction to optic cup edge, is referred to as disk in the present invention along width
Value.
In one embodiment of the invention, multiple directions to be selected can be set separately for each side in image in advance,
It is multiple in the angle radian interval such as to the small sector of a certain one smaller angle radian side-draw of image centered on equalization point
Direction can be used as direction to be selected.When calculating, can be determined on these directions to be selected for the side by a plurality of straight of equalization point
Line;Then the intersection point of these straight lines and optic disk region contour and the intersection point of these straight lines and optic cup region contour are determined respectively;
And the distance for calculating separately two intersection points on same straight line obtains multiple disks along width value;Finally take these disks along width value
In minimum value as this side disk along width value.
The orientation and person body orientation of the eye fundus image obtained under normal conditions are consistent, i.e., above and below image i.e.
Above and below human body, image two sides are nasal side and temporo side of human body respectively (left-and right-eye images are contrary).If obtained
The image angle taken is more special, can adjust image angle after step S1, keep it consistent with person body orientation.
In practical application, the disk of any direction can be determined along width, these disk edges to any direction based on the equalization point
Width can be used as the objective basis that doctor judges glaucoma.
The eyeground disk provided according to embodiments of the present invention determines method along width, and optic disk area is identified first from eye fundus image
Domain and optic cup region, then respectively determine both central point, further according to the two central points determine one it is average in
Heart point, to take into account the center in the two regions.Disk is determined along width based on the position of this mean center point, obtained number
Value can accurately embody the morphological character of optic disk and optic cup, and this programme is calculated based on image data and objective algorithm can be intuitive
The disk of measurement saves human resources, can effectively assist doctor or expert to judge glaucoma disease along data.
An embodiment provides a kind of specific eyeground disks to determine method along width, as shown in Fig. 2, including
Following steps:
S1B obtains the fundus photograph of eye-ground photography equipment shooting, usually there is the image of black background, may in background
It further include some text informations;
S2B is cut out fundus photograph to obtain eye fundus image, which accommodates circular eyeground region just.
As shown in figure 3, four sides of image are intersected with eyeground edges of regions respectively after shearing.It is this that cut out operation be for subsequent use
Machine learning model is identified to image and the optimization processing made, in other embodiments can also be without the behaviour that cuts out
Make, or puncture more contents, at least reservation optic disk region.
S3B identifies the effective coverage comprising optic disk using the first machine learning model from eye fundus image.Effective coverage
It inside may include optic disk and small part eyeground background content, its shape can be the regular shape of setting, such as one rectangular
Region or border circular areas, this step can get rid of most of eyeground background content, obtain one as shown in Figure 4 based on optic disk
Effective coverage.
Before being identified using machine learning model, training data should be used to be trained it.About first
The training process of machine learning model, the embodiment of the present invention provide a kind of preferred model training scheme.First lead in the training stage
It crosses and the effective coverage for including optic disk is marked out in eye fundus image by hand to obtain training data, such as dotted line shown in fig. 5
Frame is marked content, and the form that this callout box enters machine learning model is (x, y, height, width), wherein x, and y is mark
The coordinate of frame upper left angle point in the picture is infused, height, width are respectively the height and width of callout box.Utilize a large amount of eye
Input model is trained together for base map picture and callout box, and model can predict the effective coverage including optic disk by study
Position exports result in the form of identical with callout box.
The embodiment of the present invention can be using existing depth detection model as the first machine learning model, such as SSD, YOLO
Or Faster-RCNN etc., it can also be with designed, designed depth network model.
S4B pre-processes effective coverage to enhance pixel point feature.Local fat figure specifically can be used to account
Method (CLAHE) does image enhancement to effective coverage.This step can make the feature in image more prominent, right after pretreatment
It is easier to find the profile of optic disk and the profile of optic cup when image is identified, to improve identification accuracy and recognition efficiency.
S5B identifies optic disk region using the second machine learning model from effective coverage, utilizes third machine learning mould
Type identifies optic cup region from effective coverage.This step obtains being more preferably accurate region segmentation result, profile and human body
Optic disk it is consistent with optic cup profile, usually irregular shape.By identifying available optic disk region 71 as shown in Figure 7
With optic cup region 72.
About the training process of the first machine learning model and the second machine learning model, the embodiment of the present invention provides one kind
Preferred model training scheme.Specifically, optic disk is accurately marked out by hand in training, is then based on the profile manually marked
It generates filling as shown in Figure 6 and covers figure, wherein white is optic disk region, black is background.Finally the optic disk region of interception and right
Input model is trained the figure of covering answered together, and model identifies optic disk region by study, it is split.The mark of optic cup
Note and the process of segmentation follow same step.
The embodiment of the present invention can use existing depth detection model as second and third machine learning model, such as
It can be using the existing models such as U-Net, Mask R-CNN, DeepLabV3 or the depth segmentation model of designed, designed.
S6B is determined average according to the position of the position of identification optic disk regional center point 711 and optic cup regional center point 712
Point 73.Fig. 7 illustrates the schematic diagram of determining equalization point, this is intended merely to clearly demonstrate and the citing made, and real process is
Hind computation step, it is not necessary to show these contents in the picture.
S7B determines the lateral straight line 74 for passing through equalization point 73 in the horizontal direction, determines in vertical direction and passes through equalization point 73
Longitudinal straight line 75.Wherein lateral straight line 74 and the upper and lower sides aligned parallel of image are horizontal linear, longitudinal straight line 75 and image be left,
Right hand edge parallel vertical is in lateral straight line 74.
S8B determines the intersection point of straight line and profile.Specifically, it is determined that lateral straight line 74 and the first of 71 profile of optic disk region
Intersection point 741, and the second intersection point 742 of lateral straight line 74 and 72 profile of optic cup region;Determine longitudinal direction straight line 75 and optic disk region
The third intersection point 751 of 71 profiles, and the 4th intersection point 752 of longitudinal straight line 75 and 72 profile of optic cup region.Left side and the right side in figure
There are first intersection point 741 and second intersection point 742 in side respectively, in figure above and below have a third intersection point 751 respectively
With the 4th intersection point 752.
S9B calculates disk along width value according to intersection position.Specifically, first intersection point of the same side in eye fundus image is calculated
With the lateral disk of conduct at a distance from the second intersection point along width value;Calculate the third intersection point and the 4th intersection point of the same side in eye fundus image
Distance is as longitudinal disk along width value.
It is possible thereby to which calculating left side the distance between the first intersection point 741 and the second intersection point 742 obtains left hand plate along width value
T, right side the distance between the first intersection point 741 and the second intersection point 742 are calculated and obtains right side disk along width value N;Calculate top third
The distance between intersection point 751 and the 4th intersection point 752 obtain square plate and hand over along width value S, calculating lower section third intersection point 751 and the 4th
The distance between point 752 obtains disk under along width value I.
The eyeground disk provided according to embodiments of the present invention determines method along width, and optic disk area is identified first from eye fundus image
Domain and optic cup region, then respectively determine both central point, further according to the two central points determine one it is average in
Heart point, to take into account the center in the two regions.Position based on this mean center point obtains the disk in tetra- orientation ISNT
Along width numerical value, these numerical value can accurately embody the morphological character of optic disk and optic cup, and this programme is based on image data and objective
Algorithm, which calculates, to be saved human resources with the disk of Objective measurement along data, can effectively assist doctor or expert to glaucoma
Disease judges.
Correspondingly, one embodiment of the present of invention additionally provides a kind of eyeground disk along width determining device, as shown in figure 8,
Include:
Acquiring unit 81, for obtaining eye fundus image;
Region identification block 82, for identifying optic disk region and optic cup region in the eye fundus image;
Equalization point determination unit 83, for the position and the optic cup region according to the central point for identifying optic disk region
The position of central point determine equalization point;
Disk is along determination unit 84, for determining disk along width value based on the position of the equalization point.
One embodiment of the present of invention additionally provides a kind of electronic equipment, comprising: at least one processor and with it is described
The memory of at least one processor communication connection;Wherein, the memory, which is stored with, to be held by least one described processor
Capable instruction, described instruction are executed by least one described processor, so that at least one described processor executes above-mentioned implementation
Eyeground disk in example determines method along width.
One embodiment of the present of invention additionally provides a kind of glaucoma image judgment means, includes: as shown in Figure 9
Eyeground disk is along width determination unit 91, for determining that method determines along width according to the eyeground disk in above-described embodiment
Disk is along width value;
Judging unit 92, for determining whether eye fundus image is glaucoma image along width value according to disk.This device can be with
According to the rule of setting automatically determine input eye fundus image whether be glaucoma patient image.Setting rule therein is for example
It can be the disk that will be calculated to be compared along width value with given threshold, be determined according to comparison result;It is also possible to
The disk in each orientation being calculated is compared to each other along width value, is determined according to their size relation;It can also adopt
Manually intelligent algorithm identifies disk along width value using the machine learning model after training, is identified or classified
As a result.
The glaucoma image judgment means provided according to embodiments of the present invention are calculated by eyeground disk along width determination unit
Disk along width value can by the disk in objective quantification eye fundus image in the form of, using judging unit can according to the disk of quantization along form from
It is dynamic determine eye fundus image whether be glaucoma patient image.This programme is based on image data and objective algorithm determines glaucoma figure
Picture saves human resources, can effectively assist doctor or expert to judge glaucoma disease.
As a preferred embodiment, square plate can be calculated and determined along width value, disk under along width value, nose
Side panel is along width value and temporo side panel along width value.Judging unit judges the eye along the size relation of width value according to these four disks
Base map seems no for glaucoma image.For example, it can be set to judgment basis is disk along width I > S > N > T, this condition will not met
Eye fundus image be determined as glaucoma image.
One embodiment of the present of invention additionally provides a kind of glaucoma disease diagnostic system, includes: as shown in Figure 10
Eye-ground photography equipment 90, for shooting user's eye fundus image;And
Eyeground disk is along width determination unit 91, for determining that method determines along width according to the eyeground disk in above-described embodiment
Disk is along width value;
Judging unit 92, for determining whether eye fundus image is glaucoma image along width value according to disk.
The glaucoma disease diagnostic system provided according to embodiments of the present invention acquires user eyeground using eye-ground photography equipment
Image, and eye fundus image is obtained along width determination unit by eyeground disk and calculates disk along width value, with objective quantification eyeground figure
Disk as in is along form;It can determine automatically whether eye fundus image is that glaucoma is suffered from along form according to the disk of quantization using judging unit
The image of person.This programme is based on image data and objective algorithm determines glaucoma image, saves human resources, can effectively assist
Doctor or expert judge glaucoma disease.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Obviously, the above embodiments are merely examples for clarifying the description, and does not limit the embodiments.It is right
For those of ordinary skill in the art, can also make on the basis of the above description it is other it is various forms of variation or
It changes.There is no necessity and possibility to exhaust all the enbodiments.And it is extended from this it is obvious variation or
It changes still within the protection scope of the invention.
Claims (10)
1. a kind of eyeground disk determines method along width, which comprises the steps of:
Obtain eye fundus image;
Optic disk region and optic cup region are identified in the eye fundus image;
Equalization point is determined according to the position of the central point of the position of the central point in the identification optic disk region and the optic cup region;
Determine disk along width value based on the position of the equalization point.
2. the method according to claim 1, wherein the basis identifies optic disk region in the eye fundus image
With optic cup region, comprising:
The effective coverage comprising optic disk is identified from the eye fundus image using the first machine learning model;
Optic disk region is identified from the effective coverage using the second machine learning model;
Optic cup region is identified from the effective coverage using third machine learning model.
3. the method according to claim 1, wherein the position based on the equalization point determines disk along wide
Degree, comprising:
The lateral straight line by the equalization point is determined in the horizontal direction;
Determine the lateral straight line and the first intersection point of the optic disk region contour and the lateral straight line and the optic cup area
Second intersection point of domain profile;
First intersection point for calculating the same side in the eye fundus image is wide as lateral disk edge at a distance from second intersection point
Angle value;
And/or
Longitudinal straight line by the equalization point is determined in vertical direction;
Determine longitudinal straight line and the third intersection point of the optic disk region contour and longitudinal straight line and the optic cup area
4th intersection point of domain profile;
The third intersection point for calculating the same side in the eye fundus image is wide as longitudinal disk edge at a distance from the 4th intersection point
Angle value.
4. the method according to claim 1, wherein the position based on the equalization point determines disk along wide
Degree, comprising:
The a plurality of straight line by the equalization point is determined on multiple direction initializations;
The 4th intersection point and a plurality of straight line and the view of a plurality of straight line and the optic disk region contour are determined respectively
5th intersection point of cup region contour;
Calculate separately the 4th intersection point on same straight line between the 5th intersection point at a distance from obtain multiple disks along width
Value;
Minimum value of the multiple disk in width value is obtained as the disk of side where the multiple direction initialization along width.
5. the method according to claim 1, wherein the disk along width value include upper square plate along width value, under
Square plate is along width value, left hand plate along width value and right side disk along width value.
6. a kind of eyeground disk is along width determining device characterized by comprising
Acquiring unit, for obtaining eye fundus image;
Region identification block, for identifying optic disk region and optic cup region in the eye fundus image;
Equalization point determination unit, for according to the position of the central point for identifying optic disk region and the center in the optic cup region
The position of point determines equalization point;
Disk is along determination unit, for determining disk along width value based on the position of the equalization point.
7. a kind of electronic equipment characterized by comprising at least one processor and at least one described processor communication
The memory of connection;Wherein, the memory is stored with the instruction that can be executed by least one described processor, described instruction quilt
At least one described processor executes, so that at least one described processor perform claim requires eye described in any one of 1-6
Chassis determines method along width.
8. a kind of glaucoma image judgment means characterized by comprising
Eyeground disk determines disk along width value along width determination unit, for method according to any one of claims 1-5;
Judging unit, for determining whether the eye fundus image is glaucoma image along width value according to the disk.
9. device according to claim 8, which is characterized in that the disk along width value include upper square plate along width value, under
Square plate is along width value, nasal side disk along width value and temporo side panel along width value;
The judging unit judges whether the eye fundus image is glaucoma along the size relation of width value according to four kinds of disks
Image.
10. a kind of glaucoma disease diagnostic system characterized by comprising
Eye-ground photography equipment, for shooting user's eye fundus image;And
Glaucoma image judgment means described in claim 8 or 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466223.1A CN109549619B (en) | 2018-12-03 | 2018-12-03 | Fundus disc edge width determination method, glaucoma disease diagnosis device and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811466223.1A CN109549619B (en) | 2018-12-03 | 2018-12-03 | Fundus disc edge width determination method, glaucoma disease diagnosis device and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109549619A true CN109549619A (en) | 2019-04-02 |
CN109549619B CN109549619B (en) | 2021-11-16 |
Family
ID=65868706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811466223.1A Active CN109549619B (en) | 2018-12-03 | 2018-12-03 | Fundus disc edge width determination method, glaucoma disease diagnosis device and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109549619B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969617A (en) * | 2019-12-17 | 2020-04-07 | 腾讯医疗健康(深圳)有限公司 | Method, device and equipment for identifying image of optic cup and optic disk and storage medium |
WO2020125318A1 (en) * | 2018-12-19 | 2020-06-25 | 上海鹰瞳医疗科技有限公司 | Glaucoma image recognition method and device and diagnosis system |
CN112541883A (en) * | 2020-10-16 | 2021-03-23 | 天津大学 | Real-time detection device and method for fundus optic disk and fovea based on deep learning |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106651888A (en) * | 2016-09-28 | 2017-05-10 | 天津工业大学 | Color fundus image optic cup segmentation method based on multi-feature fusion |
US9706917B1 (en) * | 2016-03-24 | 2017-07-18 | Don C. Bagwell, Sr. | Eye examination template |
CN108717696A (en) * | 2018-05-16 | 2018-10-30 | 上海鹰瞳医疗科技有限公司 | Macula lutea image detection method and equipment |
-
2018
- 2018-12-03 CN CN201811466223.1A patent/CN109549619B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9706917B1 (en) * | 2016-03-24 | 2017-07-18 | Don C. Bagwell, Sr. | Eye examination template |
CN106651888A (en) * | 2016-09-28 | 2017-05-10 | 天津工业大学 | Color fundus image optic cup segmentation method based on multi-feature fusion |
CN108717696A (en) * | 2018-05-16 | 2018-10-30 | 上海鹰瞳医疗科技有限公司 | Macula lutea image detection method and equipment |
Non-Patent Citations (1)
Title |
---|
PRANJAL DAS等: "Detection of Glaucoma Using Neuroretinal Rim Information", 《2016 INTERNATIONAL CONFERENCE ON ACCESSIBILITY TO DIGITAL WORLD》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020125318A1 (en) * | 2018-12-19 | 2020-06-25 | 上海鹰瞳医疗科技有限公司 | Glaucoma image recognition method and device and diagnosis system |
CN110969617A (en) * | 2019-12-17 | 2020-04-07 | 腾讯医疗健康(深圳)有限公司 | Method, device and equipment for identifying image of optic cup and optic disk and storage medium |
CN110969617B (en) * | 2019-12-17 | 2024-03-15 | 腾讯医疗健康(深圳)有限公司 | Method, device, equipment and storage medium for identifying video cup video disc image |
CN112541883A (en) * | 2020-10-16 | 2021-03-23 | 天津大学 | Real-time detection device and method for fundus optic disk and fovea based on deep learning |
Also Published As
Publication number | Publication date |
---|---|
CN109549619B (en) | 2021-11-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109684981A (en) | Glaucoma image-recognizing method, equipment and screening system | |
CN105513077B (en) | A kind of system for diabetic retinopathy screening | |
CN109697716A (en) | Glaucoma image-recognizing method, equipment and screening system | |
Gegundez-Arias et al. | Locating the fovea center position in digital fundus images using thresholding and feature extraction techniques | |
EP2888718B1 (en) | Methods and systems for automatic location of optic structures in an image of an eye, and for automatic retina cup-to-disc ratio computation | |
CN109549619A (en) | Eyeground disk determines method, glaucoma disease diagnostic device and system along width | |
CN109859168A (en) | A kind of X-ray rabat picture quality determines method and device | |
CN109035187A (en) | A kind of mask method and device of medical image | |
CN109662686A (en) | A kind of fundus flavimaculatus localization method, device, system and storage medium | |
CN109697719A (en) | A kind of image quality measure method, apparatus and computer readable storage medium | |
CN106157279A (en) | Eye fundus image lesion detection method based on morphological segment | |
WO2021190656A1 (en) | Method and apparatus for localizing center of macula in fundus image, server, and storage medium | |
CN108186051A (en) | A kind of image processing method and processing system of the automatic measurement fetus Double Tops electrical path length from ultrasonoscopy | |
CN108378869A (en) | A kind of image processing method and processing system of the automatic measurement fetal head girth degree from ultrasonoscopy | |
CN109859836A (en) | Medical image recognition methods and equipment | |
JP2022546344A (en) | Image processing for stroke feature acquisition | |
CN109658385A (en) | Eye fundus image judgment method and equipment | |
CN111522437A (en) | Method and system for obtaining product prototype based on eye movement data | |
US20130222767A1 (en) | Methods and systems for detecting peripapillary atrophy | |
CN106446805A (en) | Segmentation method and system for optic cup in eye ground photo | |
Onkaew et al. | Automatic extraction of retinal vessels based on gradient orientation analysis | |
CN110136140A (en) | Eye fundus image blood vessel image dividing method and equipment | |
CN110969617B (en) | Method, device, equipment and storage medium for identifying video cup video disc image | |
CN106372593A (en) | Optic disc area position method based on blood vessel convergence | |
US11295448B1 (en) | Concurrent display of hemodynamic parameters and damaged brain tissue |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |