CN106446805A - Segmentation method and system for optic cup in eye ground photo - Google Patents
Segmentation method and system for optic cup in eye ground photo Download PDFInfo
- Publication number
- CN106446805A CN106446805A CN201610810816.XA CN201610810816A CN106446805A CN 106446805 A CN106446805 A CN 106446805A CN 201610810816 A CN201610810816 A CN 201610810816A CN 106446805 A CN106446805 A CN 106446805A
- Authority
- CN
- China
- Prior art keywords
- difference information
- point
- colour difference
- optic
- line
- 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
- 238000000034 method Methods 0.000 title claims abstract description 90
- 230000011218 segmentation Effects 0.000 title abstract description 30
- 238000005452 bending Methods 0.000 claims abstract description 140
- 210000003733 optic disk Anatomy 0.000 claims abstract description 73
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 47
- 230000002792 vascular Effects 0.000 claims description 124
- 230000004075 alteration Effects 0.000 claims description 40
- 239000008280 blood Substances 0.000 claims description 9
- 210000004369 blood Anatomy 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000004737 colorimetric analysis Methods 0.000 claims description 5
- 208000010412 Glaucoma Diseases 0.000 abstract description 18
- 238000003745 diagnosis Methods 0.000 abstract description 14
- 239000000654 additive Substances 0.000 description 9
- 230000000996 additive effect Effects 0.000 description 9
- 239000000284 extract Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000000205 computational method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000000926 separation method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 208000030533 eye disease Diseases 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 210000001328 optic nerve Anatomy 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 206010061323 Optic neuropathy Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000020911 optic nerve disease Diseases 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 230000004281 retinal morphology Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30041—Eye; Retina; Ophthalmic
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Eye Examination Apparatus (AREA)
Abstract
Embodiments of the invention provide a segmentation method and system for an optic cup in an eye ground photo. The method comprises the steps of obtaining an optic disk line in the eye ground photo and obtaining a plurality of color difference information points in an optic disk line region according to a preset rule; performing curve fitting on the color difference information points to obtain an initial optic cup line, and setting a search region according to the initial optic cup line; and obtaining a plurality of blood vessel bending points in the search region and performing curve fitting on the color difference information points and the blood vessel bending points to obtain an optic cup line. The system is used for executing the method. According to the segmentation method and system for the optic cup in the eye ground photo, provided by the embodiments of the invention, color difference information and blood vessel information in the eye ground photo are comprehensively utilized, the optic cup segmentation accuracy is improved, and the accuracy of a glaucoma diagnosis result is further improved.
Description
Technical field
The present embodiments relate to technical field of medical image processing and in particular to a kind of eyeground according in optic cup segmentation side
Method and system.
Background technology
Eyes are one of most important organs of human body, if suffering from eye disease, then the quality of life of patient will be subject to
Very big impact.Glaucoma is one kind of eye disease, and it is a kind of based on optic disk (also known as optic papilla) structural change
Want the progressivity optic neuropathy of feature, this structural change is mainly shown as optic disk disk along being gradually reduced, this explanation aixs cylinder and
Optic cell is degenerated.Because the function that optic nerve loses cannot be recovered again, early detection and timely treatment are to save
Rescue a key of glaucoma patient eyesight.
According to being the important inspection of one kind that oculist diagnoses glaucoma, eyeground is shone and is referred to eye-ground photography technology to eye on eyeground
The photo that bottom photograph obtains.Eye-ground photography technology is using special instrument such as digital camera, and ophthalmoscope connects, by eyeground
Image shows on computers, can print and get off to be saved in case history, does a contrast, it can be objective before and after can also treating again
The change of record eyeground Posterior pole retinal morphology, there is preferable objectivity, repeatability and comparability.Assessment eyeground is shone
Middle optic disk structure and optic cup structure are important links of diagnosis of glaucoma, and optic disk is that optic nerve enters ocular region position
Entrance, typically two-dimentional eyeground according in, optic disk is in a bright elliptical region, and optic cup is the recessed of optic disk central authorities
Fall into.The change of artificial observation optic disk structure and optic cup structure is a time-consuming process, and the degree of accuracy can be because of the water of observer
Put down and change, in the process, optic disk segmentation and optic cup segmentation are important steps.Wherein, optic disk segmentation has been achieved with
The result of a large amount of high accuracies, and the segmentation result of ophthalmologist, oculist is closely.Comparatively, the algorithm of optic cup segmentation
Also fewer.And the precision of optic cup segmentation, also also have larger distance compared with optic disk segmentation.
In prior art, mostly adopt on image after removing blood vessel for the C-means clustering method (C means clustering method)
Optic cup is extracted by fuzzy C-mean algorithm wavelet transformation, or center is calculated from super-pixel statistics using super-pixel sorting technique, and
Using histogram divion optic cup.Both approaches are all finally using ellipse, cup boundary to be fitted, and all do not fill
Divide and utilize vessel information, thus easily miss the local feature of optic cup, thus affecting the degree of accuracy of diagnosis of glaucoma result.
Therefore, how to propose a kind of method, can reasonably optic cup be split, improve the standard of diagnosis of glaucoma result
Exactness, becomes problem demanding prompt solution.
Content of the invention
For defect of the prior art, the embodiment of the present invention provide a kind of eyeground according in the dividing method of optic cup and be
System.
On the one hand, the embodiment of the present invention proposes a kind of dividing method of optic cup during eyeground is shone, including:
Obtain the optic disk line during eyeground is shone, obtain the multiple colour difference informations in described optic disk line region according to preset rules
Point;
The plurality of colour difference information point is carried out curve fitting, obtains initial optic cup line, and according to described initial optic cup line
Setting region of search;
Obtain the multiple vascular bending points in described region of search, by the plurality of colour difference information point and the plurality of blood
Pipe bending point carries out curve fitting and obtains optic cup line.
On the other hand, the segmenting system of optic cup during the embodiment of the present invention provides a kind of eyeground to shine, including:
Acquisition module, for obtaining the optic disk line during eyeground is shone, obtains in described optic disk line region according to preset rules
Multiple colour difference information points;
Processing module, for the plurality of colour difference information point carries out curve fitting, obtains initial optic cup line, and according to institute
State initial optic cup line setting region of search;
Fitting module, for obtaining the multiple vascular bending points in described region of search, by the plurality of colour difference information point
And the plurality of vascular bending point carries out curve fitting acquisition optic cup line.
In the photograph of eyeground provided in an embodiment of the present invention, the dividing method of optic cup and system, fully utilize the color during eyeground is shone
Difference information and vessel information obtain colour difference information point and vascular bending point, simulate more accurate optic cup line, and doctor is true
Determine the process modelling of optic cup line during eyeground is shone, not only make use of colour difference information point and the position of vascular bending point, also utilize
Each colour difference information point and the corresponding reliability of vascular bending point, and reasonably determine each colour difference information point with
And the weight of vascular bending point, even if carrying out curve fitting in conjunction with weight so that having minority colour difference information point or vascular bending point
Inaccurate, it still is able to obtain accurate optic cup line.Improve the accuracy of optic cup line fitting result, reduce and artificially carry out
The amount of labour of optic cup segmentation, further increases the accuracy of diagnosis of glaucoma result.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description are these
Some bright embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also root
Obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the dividing method of optic cup in eyeground photograph in the embodiment of the present invention;
Fig. 2 is the idiographic flow schematic diagram of the dividing method of optic cup in eyeground photograph in the embodiment of the present invention;
Fig. 3 is the schematic flow sheet of the dividing method of optic cup in another eyeground photograph in the embodiment of the present invention;
Fig. 4 is the dividing method compares figure of optic cup in eyeground photograph in the embodiment of the present invention;
Fig. 5 is the structural representation of the segmenting system of optic cup in eyeground photograph in the embodiment of the present invention;
Fig. 6 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention;
Fig. 7 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention;
Fig. 8 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention.
Specific embodiment
Purpose, technical scheme and advantage for making the embodiment of the present invention are clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described it is clear that described embodiment is
The a part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment being obtained under the premise of not making creative work, broadly falls into the scope of protection of the invention.
Fig. 1 is the schematic flow sheet of the dividing method of optic cup in eyeground photograph in the embodiment of the present invention, as shown in figure 1, this reality
Apply the dividing method that example discloses optic cup during a kind of eyeground is shone, including:
S10, the optic disk line obtaining during eyeground is shone, obtain the multiple aberration letters in described optic disk line region according to preset rules
Breath point;
Specifically, in the segmenting system of optic cup in shining eyeground according to incoming eyeground first, because eyeground can be right according to medium vessels
Obtain colour difference information point to interfere, the blood vessel during eyeground is shone by the embodiment of the present invention first is erased, then to eyeground according to image
Red value carries out optic disk segmentation using CV (Chan-Vese active contour model, CV active contour model) algorithm,
Obtain the optic disk line during eyeground is shone.Because color distortion is larger inside and outside near optic cup line, can be according to preset rules
Multiple colour difference information points are got, colour difference information point refers to the larger separation of color distortion in optic disk line in optic disk line region.
Wherein red value refers to the R value in rgb value in photochrome.It is understood that carry out optic disk segmentation when can also be to eyeground
According in blue valve or green value carry out optic disk segmentation, the effectiveness comparison that red value carries out optic disk segmentation is good, the embodiment of the present invention
Red value during preferred pair eyeground is shone carries out optic disk segmentation, further, it is also possible to obtain the optic disk during eyeground is shone using additive method
Line, is not limited to the method enumerated in the embodiment of the present invention.
S11, the plurality of colour difference information point is carried out curve fitting, obtain initial optic cup line, and initially regarded according to described
Cup line setting region of search;
Specifically, after getting the multiple colour difference information points in optic disk line, using computer software by the plurality of aberration
Information point fits to the curve of a closure, as initial optic cup line.First the closed curve matching under rectangular coordinate system is asked
Topic changes into the normal profile fitting problems under polar coordinate system, particularly the colour difference information getting point is carried out coordinate and turns
Change, that is, rectangular co-ordinate is converted into polar coordinates, under polar coordinate system, these colour difference information points carry out curve fitting and obtain a song
Line, then polar coordinates will be carried out be converted into rectangular co-ordinate, obtain the closed curve under rectangular coordinate system, that is, initial optic cup line,
And region of search is set near initial optic cup line, so that search vascular bending point.Wherein specifically multiple colour difference information points are intended
One closed curve of synthesis can adopt regularization curve matching, and the discrete coordinates data matching of multiple colour difference information points is obtained
Function data, specifically can adopt regularization least square approximating method, so that the curve that matching obtains is more smooth rationally.
It should be noted that multiple colour difference information points can also be carried out curve fitting using additive method, it is not limited to the present invention and implements
The approximating method that example is enumerated, for example:Using computer software Curve Fitting Toolbox etc..
S12, the multiple vascular bending points obtaining in described region of search, by the plurality of colour difference information point and described many
Individual vascular bending point carries out curve fitting and obtains optic cup line.
Specifically, can occur more significantly to bend due to when blood vessel passes through optic cup line, arrange near initial optic cup line
Region of search in can get multiple vascular bending points, more multiple vascular bending points and multiple colour difference information point are fitted to
Article one, the curve of closure, as optic cup line, wherein vascular bending point refer to the larger separation of vascular bending.Specific curve is intended
Conjunction method is identical with the above-mentioned method that multiple colour difference information points are fitted to initial optic cup line, and here is omitted.In the field of search
Obtain in domain vascular bending point method can be first eyeground according in extract all blood vessels, then extract and bend relatively on every blood vessel
Significantly separation is vascular bending point, finally obtains the vascular bending point in region of search;Can also extracting directly exist
Blood vessel in region of search, then it is extracted in the vascular bending point on the blood vessel in region of search, when certainly obtaining vascular bending point
The blood vessel erased should be recovered first, or again in the identical eyeground of another blood vessel of not erasing is shone, obtain blood vessel
Bending point, then two data summarization opened one's eyes in the photograph of bottom are opened one's eyes in the photograph of bottom to same.The concrete method obtaining vascular bending point can
To be, first extract the vessel centerline of the blood vessel searching, take a point every 5 pixels on heart line in the blood vessel, calculate
The vascular bending angle of each point position, will put as blood accordingly when angle of bend is less than a predetermined angle threshold value
Pipe bending point, can also be additive method to determine vascular bending point, the embodiment of the present invention is not especially limited certainly.Need
Bright, the calculating of vascular bending angle can be counted using related formula or using the correlation function in computer software
Calculate, specific computational methods are not specifically limited herein, additionally, predetermined angle threshold value can also be carried out according to actually used situation
Setting, the embodiment of the present invention is not especially limited.
In the photograph of eyeground provided in an embodiment of the present invention, the dividing method of optic cup, the optic cup line simulating, had both merged aberration
Information point, combines vascular bending point again, than the ellipse fitting method only applying colour difference information and only the inserting of application vascular bending point
Value method embodies obvious advantage so that the optic cup line obtaining is more reasonable, further increases diagnosis of glaucoma result
The degree of accuracy.
On the basis of above-described embodiment, the described multiple aberration letters being obtained according to preset rules in described optic disk line region
Breath point, including:
Obtain the center in the corresponding region of described optic disk line, make one for end points every predetermined angle with described center and penetrate
Line, obtains the ray of respective numbers;
Each ray takes a pixel every presetted pixel, calculates along pixel each described in described directions of rays
Value of chromatism inside and outside corresponding, takes the corresponding pixel of maximum aberration value on described ray as the institute on described ray
State colour difference information point, wherein said pixel is in described optic disk line region.
Specifically, obtain the center of optic disk line corresponding region, and make one with described center for each predetermined angle of end points
Ray, thus obtains a plurality of ray, and the center of wherein optic disk line corresponding region refers to the geometric center of optic disk line.Each
On bar ray, take a pixel every presetted pixel, and pixel in optic disk line that is to say, that being in optic disk in ray
A pixel is taken every presetted pixel on line segment in line region.Calculate all pixels point along along the direction of its place ray
The value of chromatism of outer both sides, that is, calculate all pixels point along its place ray the aberration inside and outside ray end points outward direction
Value, maximum aberration on every ray is worth corresponding pixel as colour difference information point.Wherein predetermined angle and presetted pixel can
To pre-set as needed, the embodiment of the present invention is not specifically limited.
For example:After getting the geometric center of optic disk line, with described center as end points, make a ray every 10 degree, this
Sample just obtains 36 rays.The part being in optic disk line in every ray takes a pixel every 5 pixels, calculates every
Individual pixel along the interior outside value of chromatism of its place directions of rays, specific computational methods can be:Calculate each pixel institute
On ray from the average brightness of adjacent 5 pixels of pixel to ray end points direction and from pixel along ray outward
To adjacent 5 pixels average brightness difference, the as corresponding value of chromatism of pixel, when last pixel is corresponding
Along the outside of its place directions of rays there is no 5 pixels when, such as only 3 pixels, can select to abandon this pixel, also may be used
Only to calculate the average brightness of this 3 pixels.The corresponding pixel of maximum aberration value on every ray is taken to be colour difference information
Point, thus obtains 36 colour difference information points.It should be noted that in the embodiment of the present invention, predetermined angle is 10 degree, just
Optic disk line averagely can be divided into 36 parts, predetermined angle can also be other number of degrees, such as 5 degree, 36 degree etc., can be according to reality
Need to arrange, certainly also occur that optic disk line can not averagely be split by the predetermined angle of setting, such as 11 degree, such situation is fair
Permitted, the ray so obtaining is 33, certainly preferably be configured to be divided exactly by 360 by predetermined angle, be achieved in that
Colour difference information point more all even accurately.Additionally, the computational methods of value of chromatism can also be calculated using additive method, it is not limited to
The computational methods enumerated in the embodiment of the present invention.
Optic cup dividing method in the photograph of eyeground provided in an embodiment of the present invention, by drawing a plurality of ray in optic disk line,
And calculate pixel on the ray value of chromatism along inside and outside directions of rays, take the corresponding pixel of maximum aberration value as color
Difference information point, to simulate initial optic cup line.Make use of the larger feature of optic cup line neighbouring interior outside color distortion so that obtaining
The initial optic cup line got is more reasonable, and progress can simulate more accurate optic cup line, thus improve glaucoma examining
The accuracy of disconnected result.
On the basis of above-described embodiment, described region of search is arranged according to described initial optic cup line include:
Calculate the institute on the corresponding described maximum aberration value of described colour difference information point and described colour difference information point place ray
There is the ratio of the aberration mean value of described pixel, using described ratio as corresponding first reliability of described colour difference information point;
It is respectively provided with inside curve and the outside curve of described initial optic cup line, described inner side according to described first reliability
Region between curve and described outside curve is described region of search.
Specifically, after getting colour difference information point, calculate the aberration of all pixels point on the ray of colour difference information point place
The mean value of value, using the ratio of corresponding for colour difference information point maximum aberration value and described mean value as described colour difference information point pair
The first reliability answered, that is, colour difference information point one first reliability of correspondence, thus obtains multiple first reliabilitys.
The a plurality of radius of inside curve, with the center of optic disk line as initial point, is set along above-mentioned each ray according to the first reliability, that is,
Article one, the radius of the corresponding inside curve of ray, the wherein radius of inside curve is linear with the first reliability, and
The maximum radius of inside curve can not be less than initial optic cup line maximum radius half, the radius of all inside curve non-described
The curve that the end points at center simulates is inside curve.Outside curve adopts identical method to obtain, and outside curve
Maximum radius not can exceed that disk along the 4/5 of width, disk along the part referring between optic disk line and initial optic cup line, inside curve and
Region between the curve of outside is region of search.The linear relationship such as formula of the wherein radius of inside curve and the first reliability
(1) shown in, the linear relationship formula such as formula (2) of the radius of outside curve and the first reliability shown it is to be understood that interior
The radius of the radius of lateral curvature line and outside curve can also be obtained by additive method, is not limited to row in the embodiment of the present invention
The method lifted.It should be noted that inside curve and outside curve can also be obtained by additive method, such as:Initially to regard
Cup line be border, according to the first reliability on above-mentioned ray respectively to inside initial optic cup line setting inside search width, to
Setting outside search width outside initial optic cup line, the side end points matching of inner side search width obtains inside curve, and outside is searched
The side end points matching of Suo Kuandu obtains outside curve.
RInner side=RCup(1/2+1/2 (the first reliability-min)/(max-min)) (1)
ROutside=RCup+ 1.4 (4/5-3/5 (the first reliability-min)/(max-min)) RDisk edge(2)
In formula:Min refers to minimum first reliability in the first reliability of all colour difference information points;Max refers to own
Maximum first reliability in first reliability of colour difference information point;RDisk edgeRefer to the radius of optic disk line and the half of initial optic cup line
The difference in footpath.It should be noted that the linear relationship formula that the embodiment of the present invention is enumerated is the preferred formula through experimental verification, tool
Can also be not especially limited using other linear formula, the embodiment of the present invention when body uses.
The method introducing region of search acquisition below by specific example, for example:Existed by the method for above-described embodiment
36 rays and 36 colour difference information points are acquired it is assumed that to be calculated one of colour difference information point A corresponding in optic disk line
The aberration mean value of all pixels point on ray is 6, and the corresponding maximum aberration value of colour difference information point A is 8, then colour difference information
First reliability of point A is 4/3 it is assumed that the radius of the optic disk line obtaining is RDisk, the radius of initial optic cup line is RCup, it is calculated
Minimum first reliability be 7/6, maximum first reliability be 5/3, then colour difference information point A pair can be obtained according to formula (1)
The radius R of the initial optic disk line inside curve answeredInner side, the radius R of outside curve is obtained according to formula (1)Outside.With optic disk line center
For initial point respectively with RInner sideAnd ROutsideMake the corresponding interior lateral curvature of aberration information point A for radius on the ray that colour difference information point A is located
The radius of line and the radius of outside curve, acquire two terminal A accordingly1And A2.Same method gets other aberration letter
The end points of the radius of the end points of radius of the breath corresponding inside curve of point and outside curve, respectively by the half of this 36 inside curve
The end points of the end points in footpath and outside sweep is fitted, and obtains inside curve and outside curve, and region of search is interior lateral curvature
Part between line and outside curve.
The dividing method of optic cup in the photograph of eyeground provided in an embodiment of the present invention, by calculating the first of each colour difference information point
Reliability, and inside curve and outside curve is obtained according to the first reliability, obtain rational region of search, enable to
More accurately search for and get vascular bending point, obtain optic cup line further combined with colour difference information point, improve optic cup and divide
The degree of accuracy cut, and then improve the degree of accuracy of diagnosis of glaucoma result.
On the basis of above-described embodiment, by the plurality of colour difference information point and the plurality of vascular bending point march
Line matching obtains optic cup line and includes:
Calculate corresponding multiple second reliabilitys of the plurality of vascular bending point;
According to corresponding multiple first weights of described first reliability calculating the plurality of colour difference information point, according to described
Corresponding multiple second weights of two reliability calculating the plurality of vascular bending point;
According to the plurality of first weight and the plurality of second weight by the plurality of colour difference information point and described many
Individual vascular bending point carries out curve fitting and obtains optic cup line.
Specifically, calculate the second reliability of the vascular bending point in region of search first, a vascular bending point corresponds to
One the second reliability, according to corresponding multiple first weights of the first reliability calculating multiple colour difference information point, can according to second
Calculate corresponding multiple second weights of multiple vascular bending points by degree, i.e. colour difference information point one first weight of correspondence, one
Individual vascular bending point corresponds to second weight.Concrete calculating the first weight and the second weight can be adopted with the following method:
First, total weight distribution:First information point will be made, from the point of view of all of vascular bending from the point of view of all of colour difference information
Make the second information point, total weight 1 is distributed to first information point and the second information point.Specifically total weight 1 is distributed to the first letter
The method of breath point and the second information point may be referred to following steps:
R1, calculate the mean value of corresponding all first reliabilitys of above-mentioned all colour difference information point, put down as aberration ratio
Average;
If R2 aberration average of relatives value is more than or equal to 3, the weight making first information point is 2/3, the power of the second information point
It is 1/3 again;
If R3 aberration average of relatives value is less than or equal to 2, the weight making first information point is 1/3, the power of the second information point
It is 2/3 again;
If R4 aberration average of relatives value is 1/2 between the weight between 2 and 3, making first information point, the second information point
Weight be 1/2.
Secondly, the first weight and the distribution of the second weight:Corresponding for first information point weight is distributed to each aberration letter
Breath point, i.e. each corresponding first weight of colour difference information point, the wherein first weight and the first reliability are linear, specifically
Linear relationship such as formula (3) shown in, corresponding for the second information point weight is distributed to each vascular bending point, the second weight
Linear with the second reliability, shown in specific linear relationship such as formula (4).It is understood that the embodiment of the present invention
In the numerical value enumerated such as:2nd, 3,1/3 etc. is the preferred value through experimental verification, during practical application, can be according to service condition
It is configured, the embodiment of the present invention is not specifically limited.
Weight * (the first reliability/the first reliability sum) (3) of the first weight=first information point
Weight * (the second reliability/the second reliability sum) (4) of the second weight=the second information point
In formula:The weight of first information point refers to distribute to the weight of all colour difference information points when total weight is distributed, the
The weight of two information points refers to distribute to the weight of all vascular bending points when total weight is distributed, for example:If calculating gained color
Difference average of relatives value is more than or equal to 3, then the weight of first information point is 2/3, and the weight of the second information point is 1/3;First is reliable
Degree refers to corresponding first reliability of the first weight corresponding colour difference information point, and the first reliability sum refers to all colour difference informations
The corresponding all first reliability sums of point, corresponding second reliability and the second reliability sum are similar implications, only
It is that colour difference information point is changed to vascular bending point, here is omitted.It should be noted that the embodiment of the present invention enumerate linear
Relation formula (3) and formula (4) are the preferred formulas through experimental verification, can also be linearly public using others when specifically used
Formula, the embodiment of the present invention is not especially limited.
The method carrying out curve fitting with specific reference to the first weight and the second weight can be, by each first weight and
Each second weight is multiplied by default value, and such as 100, and acquired results are rounded, as corresponding colour difference information point and phase
The number of times that the vascular bending point answered occurs, the number of times occurring in conjunction with each colour difference information point and each vascular bending point occur
Number of times, all of colour difference information point and all of vascular bending point is carried out curve fitting, obtains optic cup line.For example:Assume there is 3
Individual colour difference information point a, b, c, corresponding transverse and longitudinal coordinate matrix and ordinate matrix are x=[x1, x2, x3] respectively, y=[y1,
Y2, y3] it is assumed that corresponding first weight of a, b, c is 0.01,0.02,0.03 respectively, after the first weight is multiplied by 100 respectively
To 1,2,3 then it represents that a, b, c occur respectively 1 time, twice, three times.The coordinate value of colour difference information point is combined when carrying out curve fitting
The number of times occurring with each aberration information point calculating gained, during curve matching the coordinate representation of colour difference information point be x=[x1, x2,
X2, x3, x3, x3], y=[y1, y2, y2, y3, y3, y3], vascular bending point is with same method.It should be noted that, according to
One weight and the second weight carry out curve fitting to aberration information point and vascular bending point and are not limited to row in the embodiment of the present invention
The method lifted, can also adopt additive method, for example, utilize the weight fitting function of correlation in computer software or weight to intend
Close tool box to carry out curve fitting.
In the photograph of eyeground provided in an embodiment of the present invention, the dividing method of optic cup, calculates each colour difference information point and blood vessel
The corresponding weighted value of bending point, to carry out curve to the colour difference information point obtaining and vascular bending point in conjunction with corresponding weighted value
Matching, in the case of there is minority inaccurate colour difference information point or vascular bending point, still can obtain and accurately regard
Cup line, improves the anti-noise ability of curve matching, so that the optic cup line that matching obtains is more accurate, improves green light further
The accuracy of eye diagnostic result.
On the basis of above-described embodiment, the described calculating corresponding multiple second reliability bags of the plurality of vascular bending point
Include:Obtain the corresponding vascular bending curvature of described each vascular bending point and blood vessel diameter, described vascular bending curvature and corresponding
The product of described blood vessel diameter is the second reliability of corresponding described vascular bending point.
Specifically, obtain corresponding vascular bending point in region of search first, and obtain the corresponding coordinate of vascular bending point
Value, calculates the corresponding vascular bending curvature of described vascular bending point, and the concrete method calculating vascular bending curvature can utilize blood
The correlation formula that pipe bending curvature calculates is calculated it is also possible to be utilized the phase of the vascular bending curvature estimation in computer software
Close function to calculate, certainly can also adopt additive method, the specific computational methods embodiment of the present invention is not especially limited.Again
Obtain the blood vessel diameter at vascular bending point, the method for concrete acquisition blood vessel diameter can be, with vascular bending point as the center of circle, half
Footpath gradually expands picture circle, stops when intersecting with vessel borders, and now corresponding circular diameter is that at vascular bending point, blood vessel is straight
Footpath.The product of the vascular bending obtaining curvature and corresponding blood vessel diameter is second reliable as corresponding vascular bending point
Degree.It is understandable that the acquisition methods of vascular bending curvature and blood vessel diameter are not limited to the side enumerated in the embodiment of the present invention
Method.
In the photograph of eyeground provided in an embodiment of the present invention, the dividing method of optic cup, combines colour difference information point and vascular bending
Point, and calculate colour difference information point and the corresponding weighted value of vascular bending point, the colour difference information point that will obtain in conjunction with weighted value
Carry out curve fitting with vascular bending point, obtain optic cup line, it is to avoid minority colour difference information point or the inaccurate shadow of vascular bending point
Ring the accuracy that optic cup line obtains, improve the accuracy of optic cup segmentation, thus improve the accuracy of diagnosis of glaucoma result,
Reduce the amount of labour that artificial observation carries out optic cup segmentation, avoid simultaneously due to observer level difference optic cup segmentation accurate
Degree is different, the accuracy of impact diagnosis of glaucoma result.
The concrete dividing method of eyeground shine in optic cup is described below, so that being better understood from technical scheme,
Fig. 2 is the idiographic flow schematic diagram of the dividing method of optic cup in eyeground photograph in the embodiment of the present invention, and Fig. 3 is in the embodiment of the present invention
The schematic flow sheet of the dividing method of optic cup in the photograph of another eyeground, as shown in Figure 2 and Figure 3, in the embodiment of the present invention, eyeground regards in shining
The comprising the following steps that of dividing method of cup:
S20, the blood vessel erased in the photograph of eyeground.Because when determining colour difference information point, the blood vessel during eyeground is shone can cause to do
Disturb, therefore, the blood vessel in shining eyeground first is erased, obtain no blood vessel eyeground and shine.
S21, extraction optic disk line.The method that the embodiment of the present invention extracts optic disk line is that the red value during eyeground is shone utilizes CV
Algorithm determines the optic disk line in eyeground, can also adopt additive method when specifically used.
S22, acquisition colour difference information point, the initial optic cup line obtaining.The concrete method obtaining colour difference information point can be as above-mentioned
The method introduced in embodiment, draws a plurality of ray with the center of optic disk line for initial point, takes multiple on each ray respectively
Pixel, and calculate pixel on each ray corresponding along its place directions of rays by optic disk line center outward direction
Value of chromatism, takes on each ray the corresponding pixel of maximum aberration value as described ray corresponding colour difference information point, and counts
Calculate each corresponding first reliability of colour difference information point, the method calculating the first reliability is with the method one in above-described embodiment
Cause, here is omitted.
S23, determine region of search.The inside curve of initial optic disk line and outer lateral curvature are respectively provided with according to the first reliability
Line, the part between inside curve and outside curve is region of search, the method to set up of inside curve and outside curve and upper
The method stated in embodiment is consistent, and here is omitted.
S24, all vascular bending points extracting during eyeground is shone.Obtain the blood vessel during eyeground is shone, and extract the blood on blood vessel
Pipe bending point.
S25, the vascular bending point extracting in region of search.In extraction step S24 extract and in step S23 determine
Region of search in vascular bending point, and calculate each corresponding second reliability of vascular bending point, specifically extract blood vessel
Method that is bending point and calculating the second reliability is consistent with above-mentioned fact Example, and here is omitted.
S26, curve matching obtain optic cup line.According to the first reliability and the second reliability calculate respectively colour difference information point and
First weight of vascular bending point and the second weight, the first weight and the second weight are multiplied by default value as corresponding aberration
The number of times that information point and vascular bending point occur, according to calculating the number of times of gained by colour difference information point and vascular bending point march
Line matching, first carries out Coordinate Conversion, rectangular coordinate system is converted to polar coordinate system, and matching obtains the optic cup line under polar coordinate system,
Again polar coordinate system is converted to rectangular coordinate system, obtains the optic cup line under rectangular coordinate system, concrete fit procedure and above-mentioned enforcement
Example is consistent, and here is omitted.
Fig. 4 be in the embodiment of the present invention eyeground according in optic cup dividing method compares figure, as shown in Figure 4 it can be seen that this
In the eyeground photograph that inventive embodiments provide, the dividing method of optic cup and the contrast of general method have a significant effect, and the present invention is real
Apply the optic cup segmentation result of a gained and ophthalmologist, oculist carries out the result of staff optic cup segmentation and has the uniformity of height.
In the photograph of eyeground provided in an embodiment of the present invention, the dividing method of optic cup, fully utilizes the colour difference information during eyeground is shone
Obtain colour difference information point and vascular bending point with vessel information, simulate more accurate optic cup line, doctor is determined eyeground
According to the process modelling of middle optic cup line, not only make use of colour difference information point and the position of vascular bending point, also use each
Colour difference information point and the reliability degree of vascular bending point, and reasonably determine each colour difference information point and blood vessel is curved
The weight of bent point, even if carry out curve fitting so that having minority colour difference information point or vascular bending point inaccurate in conjunction with weight, still
It is obtained in that accurate optic cup line.Improve the accuracy of optic cup line fitting result, reduce and artificially carry out optic cup segmentation
The amount of labour, further increase the accuracy of diagnosis of glaucoma result.
Fig. 5 is the structural representation of the segmenting system of optic cup in eyeground photograph in the embodiment of the present invention, as shown in figure 5, this
The segmenting system for optic cup in the photograph of eyeground that bright embodiment provides includes:Acquisition module 50, processing module 51 and fitting module 52,
Wherein:
Acquisition module 50 is used for obtaining the optic disk line during eyeground is shone, and is obtained in described optic disk line region according to preset rules
Multiple colour difference information points;Processing module 51 is used for the plurality of colour difference information point carries out curve fitting, and obtains initial optic cup line,
And region of search is arranged according to described initial optic cup line;Multiple blood vessels that fitting module 52 is used for obtaining in described region of search are curved
Qu Dian, the plurality of colour difference information point and the plurality of vascular bending point is carried out curve fitting and obtains optic cup line.
Specifically, the blood vessel during eyeground is shone by acquisition module 50 is erased, and obtains the optic disk line during eyeground is shone, further according to pre-
If the multiple colour difference information points in Rule optic disk line region, and colour difference information point is sent to processing module 51;Process mould
Colour difference information point is carried out curve fitting by block 51, obtains initial optic cup line, and determines region of search;Fitting module 52 obtains at place
The vascular bending point in region of search that reason module 51 determines, and acquired vascular bending point and acquisition module 50 are obtained
Colour difference information point carry out curve fitting and obtain optic cup line.The concrete method obtaining optic disk line and curve matching and above-mentioned of obtaining
Embodiment is consistent, and here is omitted.
In the photograph of eyeground provided in an embodiment of the present invention, the segmenting system of optic cup, has merged the colour difference information during eyeground is shone and blood
Pipe bend information, by doctor determine eyeground according in optic cup line process modelling, improve eyeground according in optic cup segmentation accurate
Property, further increase the accuracy of diagnosis of glaucoma result, reduce the amount of labour artificially carrying out optic cup segmentation simultaneously, it is to avoid
The optic cup segmentation result that artificial segmentation is caused due to level difference is different.
Fig. 6 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention, as shown in fig. 6,
On the basis of above-described embodiment, described acquisition module 50 also includes ray acquisition submodule 501 and Colorimetry submodule
502, wherein:
Ray acquisition submodule 501 is used for obtaining the center in the corresponding region of described optic disk line, with described center as end points
Make a ray every predetermined angle, obtain the ray of respective numbers;Colorimetry submodule 502 is used in each ray
Take a pixel every presetted pixel, calculate along pixel each described in described directions of rays corresponding inside and outside aberration
Value, takes the corresponding pixel of maximum aberration value on described ray as the described colour difference information point on described ray, wherein institute
State pixel in described optic disk line region.
Specifically, ray acquisition submodule 501 gets the center of optic disk line, and draws every predetermined angle from described center
Go out a ray, obtain the ray of respective numbers, the method for concrete acquisition ray is consistent with above-described embodiment, no longer superfluous herein
State.Colorimetry submodule 502 takes a pixel every presetted pixel on the ray that ray acquisition submodule 501 obtains,
And described pixel is in optic disk line, calculate each pixel along its place directions of rays by ray end points outward direction
Inside and outside value of chromatism, take on each ray the corresponding pixel of maximum aberration value as colour difference information point.Wherein default
The calculating of angle, presetted pixel and value of chromatism is all consistent with above-described embodiment, and here is omitted.
Optic cup segmenting system in the photograph of eyeground provided in an embodiment of the present invention, determines colour difference information point by rational, makes
The initial optic cup line that must get is more reasonable, is further able to simulate more accurate optic cup line, thus improving green grass or young crops
The accuracy of light eye diagnostic result.
Fig. 7 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention, as shown in fig. 7,
On the basis of above-described embodiment, described processing module 51 also includes the first reliability calculating submodule 511 and region of search is true
Stator modules 512, wherein:
First reliability calculating submodule 511 is used for calculating the corresponding described maximum aberration value of described colour difference information point and institute
State the ratio of the aberration mean value of all described pixel on the ray of colour difference information point place, using described ratio as described color
Difference corresponding first reliability of information point;Region of search determination sub-module 512, for being respectively provided with according to described first reliability
The inside curve of described initial optic cup line and outside curve, the region between described inside curve and described outside curve is described
Region of search.
Specifically, after Colorimetry submodule 502 gets colour difference information point, the first reliability calculating submodule 511 is counted
Calculate the mean value of the value of chromatism of all pixels point on the ray of colour difference information point place, by corresponding for colour difference information point maximum aberration
Value is with the ratio of described mean value as corresponding first reliability of described colour difference information point.Region of search determination sub-module 512
Determine inside curve and the outside curve of initial optic cup line further according to the first reliability respectively, between inside curve and outside curve
Region be described region of search.Concrete determination inside curve is consistent with above-described embodiment with the method for outside curve, herein not
Repeat again.
The segmenting system of optic cup, the rational field of search determining vascular bending point in the photograph of eyeground provided in an embodiment of the present invention
Domain, obtains optic cup line further combined with vascular bending point and colour difference information point, improves the degree of accuracy of optic cup segmentation, and then improve
The degree of accuracy of diagnosis of glaucoma result.
Fig. 8 is the structural representation of the segmenting system of optic cup in another eyeground photograph in the embodiment of the present invention, as shown in fig. 7,
On the basis of above-described embodiment, described fitting module 52 also includes the second reliability calculating submodule 521, weight calculation submodule
Block 522 and curve matching submodule 523, wherein:
Second reliability calculating submodule 521 is used for calculating corresponding multiple second reliability of the plurality of vascular bending point
Degree;Weight calculation submodule 522 is used for according to described first reliability calculating the plurality of colour difference information point corresponding multiple the
One weight, according to corresponding multiple second weights of described second reliability calculating the plurality of vascular bending point;Curve matching
Module 523 is used for the plurality of colour difference information point and described according to the plurality of first weight and the plurality of second weight
Multiple vascular bending points carry out curve fitting and obtain optic cup line.
Specifically, the second reliability calculating submodule 521 gets the vascular bending point in region of search and calculates search
Corresponding second reliability of vascular bending point in region, a vascular bending point corresponds to second reliability.Weight calculation
Submodule 522 according to corresponding multiple first weights of the first reliability calculating multiple colour difference information point, according to the second reliability meter
Calculate corresponding multiple second weights of multiple vascular bending points, that is, a colour difference information point corresponds to first weight, a blood vessel
Bending point corresponds to second weight.The computational methods of the wherein first weight and the second weight are consistent with above-described embodiment herein
Repeat no more.Curve matching submodule 523 is according to the first weight and the second weight by all of colour difference information point and all of blood
Pipe bending point carries out curve fitting, and obtains optic cup line, and specific approximating method is consistent with above-described embodiment, and here is omitted.
In the photograph of eyeground provided in an embodiment of the present invention, the segmenting system of optic cup, calculates each colour difference information point and blood vessel
The corresponding weighted value of bending point so that in the case of there is minority inaccurate colour difference information point or vascular bending point, still
Accurate optic cup line can be obtained, improve the anti-noise ability of curve matching, so that the optic cup line that matching obtains is more
Accurately, improve the accuracy of diagnosis of glaucoma result further.
On the basis of above-described embodiment, the second reliability calculating submodule 521 specifically for:Obtain described each blood vessel curved
Song puts corresponding vascular bending curvature and blood vessel diameter, and the product of described vascular bending curvature and corresponding described blood vessel diameter is
Second reliability of corresponding described vascular bending point.
Specifically, the second reliability calculating submodule 521 obtains corresponding vascular bending point in region of search, and obtains blood
The corresponding coordinate value of pipe bending point, calculates the blood vessel at the corresponding vascular bending curvature of vascular bending point and vascular bending point
Diameter, the product of vascular bending curvature and corresponding described blood vessel diameter is the second reliability of corresponding described vascular bending point
Degree.The concrete method calculating the blood vessel diameter at the corresponding vascular bending curvature of vascular bending point and vascular bending point is with above-mentioned
Embodiment is consistent, and here is omitted.
In the photograph of eyeground provided in an embodiment of the present invention, the segmenting system of optic cup, fully utilizes the colour difference information during eyeground is shone
Obtain colour difference information point and vascular bending point with vessel information, simulate more accurate optic cup line, doctor is determined eyeground
According to the process modelling of middle optic cup line, not only make use of colour difference information point and the position of vascular bending point, also use each
Colour difference information point and vascular bending point corresponding reliability degree, and reasonably determine each colour difference information point and blood
The weight of pipe bending point, even if carry out curve fitting in conjunction with weight so that having minority colour difference information point or vascular bending point to be forbidden
Really, it still is able to obtain accurate optic cup line.Improve the accuracy of optic cup line fitting result, reduce and artificially carry out optic cup
The amount of labour of segmentation, further increases the accuracy of diagnosis of glaucoma result.
Finally it should be noted that:Above example only in order to technical scheme to be described, is not intended to limit;Although
With reference to the foregoing embodiments the present invention is described in detail, it will be understood by those within the art that:It still may be used
To modify to the technical scheme described in foregoing embodiments, or equivalent is carried out to wherein some technical characteristics;
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
1. during a kind of eyeground is shone, the dividing method of optic cup is it is characterised in that include:
Obtain the optic disk line during eyeground is shone, obtain the multiple colour difference information points in described optic disk line region according to preset rules;
The plurality of colour difference information point is carried out curve fitting, obtains initial optic cup line, and arranged according to described initial optic cup line
Region of search;
Obtain the multiple vascular bending points in described region of search, will be curved to the plurality of colour difference information point and the plurality of blood vessel
Bent point carries out curve fitting and obtains optic cup line.
2. method according to claim 1 is it is characterised in that described obtain in described optic disk line region according to preset rules
Multiple colour difference information points, including:
Obtain the center in the corresponding region of described optic disk line, a ray is made for end points every predetermined angle with described center, obtains
Obtain the ray of respective numbers;
Each ray takes a pixel every presetted pixel, calculates and correspond to along pixel each described in described directions of rays
Inside and outside value of chromatism, take the corresponding pixel of maximum aberration value on described ray as the described color on described ray
Difference information point, wherein said pixel is in described optic disk line region.
3. method according to claim 2 is it is characterised in that described arrange region of search bag according to described initial optic cup line
Include:
Calculate all institutes on the corresponding described maximum aberration value of described colour difference information point and described colour difference information point place ray
State the ratio of the aberration mean value of pixel, using described ratio as corresponding first reliability of described colour difference information point;
It is respectively provided with inside curve and the outside curve of described initial optic cup line, described inside curve according to described first reliability
The region and curve of described outside between is described region of search.
4. method according to claim 3 is it is characterised in that by the plurality of colour difference information point and the plurality of blood vessel
Bending point carry out curve fitting acquisition optic cup line include:
Calculate corresponding multiple second reliabilitys of the plurality of vascular bending point;
According to corresponding multiple first weights of described first reliability calculating the plurality of colour difference information point, can according to described second
Calculate corresponding multiple second weights of the plurality of vascular bending point by degree;
According to the plurality of first weight and the plurality of second weight by the plurality of colour difference information point and the plurality of blood
Pipe bending point carries out curve fitting and obtains optic cup line.
5. method according to claim 4 is it is characterised in that described calculating the plurality of vascular bending point is corresponding multiple
Second reliability includes:Obtain the corresponding vascular bending curvature of described each vascular bending point and blood vessel diameter, described vascular bending
The product of curvature and corresponding described blood vessel diameter is the second reliability of corresponding described vascular bending point.
6. during a kind of eyeground is shone, the segmenting system of optic cup is it is characterised in that include:
Acquisition module, for obtaining the optic disk line during eyeground is shone, obtains multiple in described optic disk line region according to preset rules
Colour difference information point;
Processing module, for the plurality of colour difference information point carries out curve fitting, obtains initial optic cup line, and according to described first
Beginning optic cup line arranges region of search;
Fitting module, for obtaining the multiple vascular bending points in described region of search, by the plurality of colour difference information point and
The plurality of vascular bending point carries out curve fitting and obtains optic cup line.
7. system according to claim 6 is it is characterised in that described acquisition module also includes ray acquisition submodule and color
Difference calculating sub module, wherein:
Ray acquisition submodule, for obtaining the center in the corresponding region of described optic disk line, with described center for end points every pre-
If angle makees a ray, obtain the ray of respective numbers;
Colorimetry submodule, for taking a pixel every presetted pixel on each ray, calculates along described ray
Value of chromatism inside and outside each pixel described in direction is corresponding, takes the corresponding pixel of maximum aberration value on described ray to make
For the described colour difference information point on described ray, wherein said pixel is in described optic disk line region.
8. system according to claim 7 is it is characterised in that described processing module also includes the first reliability calculating submodule
Block and region of search determination sub-module, wherein:
First reliability calculating submodule, for calculating the corresponding described maximum aberration value of described colour difference information point and described aberration
The ratio of the aberration mean value of all described pixel on the ray of information point place, using described ratio as described colour difference information
Corresponding first reliability of point;
Region of search determination sub-module, for being respectively provided with the inside curve of described initial optic cup line according to described first reliability
With outside curve, the region between described inside curve and described outside curve is described region of search.
9. system according to claim 8 is it is characterised in that described fitting module also includes the second reliability calculating submodule
Block, weight calculation submodule and curve matching submodule, wherein:
Second reliability calculating submodule, for calculating corresponding multiple second reliabilitys of the plurality of vascular bending point;
Weight calculation submodule, for according to described first reliability calculating the plurality of colour difference information point corresponding multiple first
Weight, according to corresponding multiple second weights of described second reliability calculating the plurality of vascular bending point;
Curve matching submodule, for believing the plurality of aberration according to the plurality of first weight and the plurality of second weight
Breath point and the plurality of vascular bending point carry out curve fitting and obtain optic cup line.
10. system according to claim 9 it is characterised in that the second reliability calculating submodule specifically for:Obtain institute
State the corresponding vascular bending curvature of each vascular bending point and blood vessel diameter, described vascular bending curvature and corresponding described blood vessel are straight
The product in footpath is the second reliability of corresponding described vascular bending point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610810816.XA CN106446805B (en) | 2016-09-08 | 2016-09-08 | A kind of eyeground shine in optic cup dividing method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610810816.XA CN106446805B (en) | 2016-09-08 | 2016-09-08 | A kind of eyeground shine in optic cup dividing method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106446805A true CN106446805A (en) | 2017-02-22 |
CN106446805B CN106446805B (en) | 2019-09-13 |
Family
ID=58164537
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610810816.XA Active CN106446805B (en) | 2016-09-08 | 2016-09-08 | A kind of eyeground shine in optic cup dividing method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106446805B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109166095A (en) * | 2018-07-11 | 2019-01-08 | 广东技术师范学院 | A kind of ophthalmoscopic image cup disk dividing method based on generation confrontation mechanism |
CN110037651A (en) * | 2018-01-15 | 2019-07-23 | 江威 | The method of quality control and device of eye fundus image |
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 |
CN111863241A (en) * | 2020-07-10 | 2020-10-30 | 北京化工大学 | Eye fundus image classification system based on integrated deep learning |
CN114387210A (en) * | 2021-12-03 | 2022-04-22 | 依未科技(北京)有限公司 | Method, apparatus, medium, and device for fundus feature acquisition |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102112044A (en) * | 2008-05-14 | 2011-06-29 | 科学、技术与研究机构 | Automatic cup-to-disc ratio measurement system |
CN102316789A (en) * | 2008-12-15 | 2012-01-11 | 新加坡保健服务集团有限公司 | Confirm the method and system of the position of cup boundary |
JP5007420B2 (en) * | 2006-09-21 | 2012-08-22 | タック株式会社 | Image analysis system and image analysis program |
-
2016
- 2016-09-08 CN CN201610810816.XA patent/CN106446805B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5007420B2 (en) * | 2006-09-21 | 2012-08-22 | タック株式会社 | Image analysis system and image analysis program |
CN102112044A (en) * | 2008-05-14 | 2011-06-29 | 科学、技术与研究机构 | Automatic cup-to-disc ratio measurement system |
CN102316789A (en) * | 2008-12-15 | 2012-01-11 | 新加坡保健服务集团有限公司 | Confirm the method and system of the position of cup boundary |
Non-Patent Citations (3)
Title |
---|
JOSHI GD ET AL: "《Optic Disk and Cup Segmentation from Monocular Colour Retinal Images for Glaucoma Assessment》", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
LU SHIJIAN: "《Accurate and Efficient Optic Disc Detection and Segmentation by a Circular Transformation》", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
吴晗辉: "《基于眼底图像的青光眼形态特征自动分析的研究》", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110037651A (en) * | 2018-01-15 | 2019-07-23 | 江威 | The method of quality control and device of eye fundus image |
CN109166095A (en) * | 2018-07-11 | 2019-01-08 | 广东技术师范学院 | A kind of ophthalmoscopic image cup disk dividing method based on generation confrontation mechanism |
CN109166095B (en) * | 2018-07-11 | 2021-06-25 | 广东技术师范学院 | Fundus image cup and disc segmentation method based on generation countermeasure mechanism |
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 |
CN111863241A (en) * | 2020-07-10 | 2020-10-30 | 北京化工大学 | Eye fundus image classification system based on integrated deep learning |
CN111863241B (en) * | 2020-07-10 | 2023-06-30 | 北京化工大学 | Fundus imaging classification system based on integrated deep learning |
CN114387210A (en) * | 2021-12-03 | 2022-04-22 | 依未科技(北京)有限公司 | Method, apparatus, medium, and device for fundus feature acquisition |
Also Published As
Publication number | Publication date |
---|---|
CN106446805B (en) | 2019-09-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109493954B (en) | SD-OCT image retinopathy detection system based on category distinguishing and positioning | |
Wong et al. | Level-set based automatic cup-to-disc ratio determination using retinal fundus images in ARGALI | |
CN106446805A (en) | Segmentation method and system for optic cup in eye ground photo | |
CN109166124A (en) | A kind of retinal vascular morphologies quantization method based on connected region | |
CN110276356A (en) | Eye fundus image aneurysms recognition methods based on R-CNN | |
CN108095683A (en) | The method and apparatus of processing eye fundus image based on deep learning | |
CN107506770A (en) | Diabetic retinopathy eye-ground photography standard picture generation method | |
CN106408564A (en) | Depth-learning-based eye-fundus image processing method, device and system | |
CN107563996B (en) | A kind of novel discus nervi optici dividing method and system | |
CN108510493A (en) | Boundary alignment method, storage medium and the terminal of target object in medical image | |
WO2021190656A1 (en) | Method and apparatus for localizing center of macula in fundus image, server, and storage medium | |
CN106650794A (en) | Method and system for eliminating highlight of image affected by highlight reflection on object surface | |
CN114694236B (en) | Eyeball motion segmentation positioning method based on cyclic residual convolution neural network | |
CN106846293A (en) | Image processing method and device | |
Zhang et al. | Convex hull based neuro-retinal optic cup ellipse optimization in glaucoma diagnosis | |
CN110110782A (en) | Retinal fundus images optic disk localization method based on deep learning | |
CN110288574A (en) | A kind of adjuvant Ultrasonographic Diagnosis hepatoncus system and method | |
CN110575132A (en) | Method for calculating degree of strabismus based on eccentric photography | |
Choudhary et al. | ANN glaucoma detection using cup-to-disk ratio and neuroretinal rim | |
CN114445666A (en) | Deep learning-based method and system for classifying left eye, right eye and visual field positions of fundus images | |
CN116309235A (en) | Fundus image processing method and system for diabetes prediction | |
CN113920077A (en) | Method for training fundus image segmentation model and arteriovenous segmentation method | |
Garcia-Marin et al. | Patch-based CNN for corneal segmentation of AS-OCT images: Effect of the number of classes and image quality upon performance | |
CN115359002A (en) | Automatic carotid artery ultrasonic image plaque detection system and method | |
CN111292285A (en) | Automatic screening method for diabetes mellitus based on naive Bayes and support vector machine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20231211 Address after: 215000 Bamboo Garden Road, Suzhou high tech Zone, Jiangsu Province, No. 209 Patentee after: Suzhou Zichuan Information Technology Co.,Ltd. Address before: 100029, No. 15 East Third Ring Road, Chaoyang District, Beijing Patentee before: BEIJING University OF CHEMICAL TECHNOLOGY |
|
TR01 | Transfer of patent right |