CN110135528A - Age determines that method, eye health degree determine method and apparatus - Google Patents
Age determines that method, eye health degree determine method and apparatus Download PDFInfo
- Publication number
- CN110135528A CN110135528A CN201910509791.3A CN201910509791A CN110135528A CN 110135528 A CN110135528 A CN 110135528A CN 201910509791 A CN201910509791 A CN 201910509791A CN 110135528 A CN110135528 A CN 110135528A
- Authority
- CN
- China
- Prior art keywords
- age
- fundus image
- user
- eye fundus
- eye
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- A61B3/0016—Operational features thereof
- A61B3/0025—Operational features thereof characterised by electronic signal processing, e.g. eye models
-
- 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
-
- 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
- A61B3/14—Arrangements specially adapted for eye photography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06V40/193—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Data Mining & Analysis (AREA)
- Veterinary Medicine (AREA)
- General Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The present invention provides a kind of age and determines that method, eye health degree determine method and apparatus, wherein the method for determining the age based on eye fundus image, comprising: obtain at least eye fundus image of user；Classified using disaggregated model to the eye fundus image, obtains the classification results for being used to indicate the age；The age of user is determined according to the classification results.
Description
Technical field
The present invention relates to medical measurement fields, and in particular to a kind of age determines that method, eye health degree determine method
And device.
Background technique
Studies have shown that many human body diseases and age factor are closely related, the probability of human body illness with age can be big
Width improves.Such as macular degeneration, pathomechanism are mainly that the aging of macula lutea plot structure sexually revises, and are the natural knots degenerated at advanced age
Fruit.With age, retinal tissue degenerates, is thinning, macular function is caused to decline.
However, age and actual age that the organ of human body is embodied may have slightly gap, this phenomenon is in ophthalmology
It is more prominent.Such as human body is influenced by extraneous or oneself factor, the age that retina is embodied can be than its actual age more
Add young or aging, judged by the age of retina embodiment or predict the eye health situation of human body, than passing through reality
The border age is judged more accurate.
The disease being much positively correlated with the age is observed that in the picture of eyeground, such as artery sclerosis, diabetic keratopathy view
Film lesion, age related macular degeneration, Parkinson etc., therefore contained the age information for the person of being taken in eye fundus image.It is based on
Features above, mankind doctor can substantially judge the age that eye fundus image embodies be in young stage or stage at advanced age, but
Do not have to be unable to judge accurately the age of eye fundus image embodiment in the case where other information.
Summary of the invention
In view of this, the present invention provides a kind of method for determining the age based on eye fundus image, comprising:
Obtain at least eye fundus image of user；
Classified using disaggregated model to the eye fundus image, obtains the classification results for being used to indicate the age；
The age of user is determined according to the classification results.
Optionally, eyes each one are at least obtained in the step of obtaining at least eye fundus image of user to open one's eyes base map
Picture.
Optionally, in the step of classifying using disaggregated model to the eye fundus image, same disaggregated model is utilized
Classify respectively to an eye fundus image for eyes, obtains at least two classification results for being used to indicate the age；
The age of user is determined according to the classification results, comprising:
The age indicated by each classification results is determined respectively；
The age of user is determined according to the age indicated by each classification results.
Optionally, the classification results of the disaggregated model output are the information for being used to indicate age range；According to
Classification results determined in the step of age of user, determined age numerical value according to the age range；
Or the classification results of the disaggregated model output are age numerical value.
Optionally, the disaggregated model is directed to multiple tasks simultaneously and classifies to the eye fundus image, obtains for referring to
Show the classification results at age as a task in the multiple task, other tasks are and age incoherent task.
Optionally, in the step of obtaining at least eye fundus image of user, including eye fundus image is pre-processed,
With the characteristics of image in the protrusion eye fundus image with change of age.
The present invention also provides a kind of methods of determining user's eye health degree, comprising:
The age that eye fundus image embodies is determined using the above-mentioned method for determining the age based on eye fundus image；
Compare the actual age at age and target user that the eye fundus image embodies；
Target user's eye health degree is determined according to comparison result.
It is optionally, described that user's eye health degree is determined according to comparison result, comprising:
The historical data of a number of other users is determined according to the actual age of the target user, wherein each other users
Actual age and the target user actual age difference within the set range, the historical data includes other users
Eye fundus image embody age and its actual age difference；
Determine the probability distribution of the historical data of the multiple other users；
Obtain the age and the difference of its actual age that the eye fundus image of the target user embodies；
Determine the difference of target user section affiliated in the probability distribution.
Correspondingly, the present invention also provides a kind of equipment for determining the age based on eye fundus image, comprising: at least one processing
Device；And the memory being connect at least one described processor communication；Wherein, be stored with can be one for the memory
The instruction that processor executes, described instruction are executed by least one described processor, so that at least one described processor executes
The above-mentioned method that the age is determined based on eye fundus image.
Correspondingly, the present invention also provides a kind of equipment of determining user's eye health degree, comprising: at least one processing
Device；And the memory being connect at least one described processor communication；Wherein, be stored with can be one for the memory
The instruction that processor executes, described instruction are executed by least one described processor, so that at least one described processor executes
The method of above-mentioned determining user's eye health degree.
What is provided according to embodiments of the present invention determines the method and device at age based on eye fundus image, using disaggregated model this
Kind machine learning algorithm is classified for the age that eye fundus image is embodied, since disaggregated model is in terms of abstract characteristics identification
It, can be in the base for surmounting human work's memory and abstract ability with the more powerful summary and extractability for surmounting human brain
The information that the mankind can not summarize is captured on plinth, is showed compared with the mankind more stable.
Exact age letter only can be obtained with eye fundus image in the case where not needing other information auxiliary in this programme
Breath, this result is not always equal with the actual age of human body in actual use, and usually has certain difference, the information
It can be used for the health status for assisting determining human body in the medical field.
The method and device of the determination user's eye health degree provided according to the present invention, is primarily based on the eyeground figure of user
As determining its age, then the age is compared with the actual age of this user, whether user is measured with comparison result
Whether excess eye-using leads to retinal abnormalities for some reason, this process does not need professional and diagnoses, it is only necessary to
User provides eye fundus image and age information is that can reach the purpose of determining user's eye health degree, has stronger convenience
Property.
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 is the flow chart of the method that the age is determined based on eye fundus image in the embodiment of the present invention；
Fig. 2 is the flow chart of the method for determination user's eye health degree in the embodiment of the present invention；
Fig. 3 is the retina age information probability distribution graph of multiple users 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.
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 embodiment of the invention provides a kind of method for determining the age based on eye fundus image, this method can by computer and
The electronic equipments such as server execute.Disaggregated model has been used to handle eye fundus image in technical solution provided by the invention, mould of classifying
Type specifically can be the neural network model of various structures and type.Before using disaggregated model, a large amount of sample should be used
Notebook data is trained it, so that it has certain classification capacity.
Specifically, eye fundus image and the actual age for the person of being taken are acquired first, and eyeground figure is marked according to actual age
Picture.
In one embodiment, the range of age is set as 0-100 years old, and is arranged every 3-5 years old as a section, obtain year
Age grouping as (0,1,2), (3,4,5) ..., (98,99,100), wherein each respectively correspond different identification informations.
After acquiring the actual age of an eye fundus image and the person of being taken, group belonging to its actual age is determined, the group is corresponding
Label of the identification information as this eye fundus image obtains a sample data；In another embodiment, by the value of actual age
As the label of eye fundus image, sample data is eye fundus image and the actual age for the person of being taken.
Initial disaggregated model is trained using above-mentioned sample data, obtains that there is inferential capability for age height
Linear regression model.
In a preferred embodiment, disaggregated model is made to be performed simultaneously multiple tasks, the age, reasoning was as one of them
Task.Specifically, the disease (such as macular disease, glaucoma, sugar net etc.) that disaggregated model is used to embody eye fundus image into
Row classification, while the age for being embodied to eye fundus image classifies.It as a result, include eye fundus image in a sample data
And its corresponding label about the age and the label about disease.
It is public due to having between different task when giving model multiple tasks due in disaggregated model building process
Feature, performance can better than execute individual task when performance, therefore can building classification of diseases and prediction model it is same
When, it will determine that the age is trained and exports simultaneously as a subtask, disaggregated model can be improved and classify for the age
Performance.
In a preferred embodiment, when preparing sample data, also eye fundus image is pre-processed.Specifically,
Such as it to operations such as locally or globally degree of the comparing enhancings of eye fundus image, is more applicable in so that picture itself can show
The gray scale difference etc. in another characteristic, such as the profile of blood vessel, macula lutea profile and its range is known in the age.This processing mode
Disaggregated model can be made more clearly to extract age-related characteristics of image, to improve the performance of disaggregated model.
It can classify to the eye fundus image at unknown age after obtaining disaggregated model.As shown in Figure 1, the present invention is implemented
The method for determining the age based on eye fundus image that example provides includes the following steps:
S1A obtains at least eye fundus image of user.Such as when obtaining an eye fundus image, it can be in eyes and appoint
The image of one eye eyeball；Such as when obtaining multiple eye fundus images, multiple images of available same eyes, or obtain respectively
Take multiple eye fundus images of eyes.
S2A classifies to eye fundus image using disaggregated model, obtains the classification results for being used to indicate the age, classification knot
The content of fruit depends on used label when train classification models.The classification results of disaggregated model output at this time, which can be, to be used for
Indicate the information or age numerical value of age range.Disaggregated model exports a classification results for each eye fundus image, respectively
A classification results may be identical or different.
S3A determines the age of user according to classification results.Such as there was only an eye fundus image and its classification results, if
Classification results are the information for being used to indicate age range, then can determine that the corresponding age is grouped according to the information, take in grouping
Median or average value as finally determining age of user；It, can be by the numerical value if classification results are age numerical value
It is rounded as finally determining age of user, or to the numerical value as finally determining age of user.
Such as have multiple eye fundus images and its classification results, then age of user is determined according to each classification results respectively, so
Take the average value of all age of user as finally determining age of user afterwards.
As a preferred embodiment, each eye fundus image of eyes of user is obtained respectively in step S1A；In step
In rapid S2A, using disaggregated model, an eye fundus image each to eyes is classified respectively, obtains two classification results；In step
In S3A, the age of user is determined in conjunction with two classification results, such as determines the age indicated by two classification results respectively, so
Take the average value of two age values as final result afterwards.The state of this preferred schemes synthesis user eyes makes final
Calculated age value is more objective and accurate.
The method that age is determined based on eye fundus image provided according to embodiments of the present invention, using this machine of disaggregated model
Learning algorithm is classified for the age that eye fundus image is embodied, and is surpassed since disaggregated model has in terms of abstract characteristics identification
The more more powerful summary and extractability of human brain can catch on the basis of surmounting human work's memory and abstract ability
The information that the mankind can not summarize is grasped, is showed compared with the mankind more stable.This programme is in the feelings for not needing other information auxiliary
Under condition, exact age information only can be obtained with eye fundus image, in actual use this result not always with the reality of human body
The border age is equal, and usually has certain difference, which can be used for the health for assisting determining human body in the medical field
State.
It should be noted that this programme, which not only limits, is applied to ophthalmology, the differentiation of many other section's purpose diseases is also required to tie
Age information is closed, therefore can preferably realize the building of medical algorithm by this task.
In a preferred embodiment, before step S2A, eye fundus image is pre-processed, to protrude eyeground figure
With characteristics of image of change of age, such as the feature of blood vessel image, the feature of macular region etc. as in.Pretreatment is so that classification
Model more accurately extracts the feature in eye fundus image with change of age, to improve the accuracy of classification results.
In a preferred embodiment, the disaggregated model used is performed simultaneously multiple classification tasks, such as first task
It is to classify to disease type belonging to eye fundus image, the second task is to divide at the age embodied to eye fundus image
Class.It include for indicating disease type in the classification results of disaggregated model output when inputting an eye fundus image to disaggregated model
Information and be used to indicate the information at age.Due to having common feature between different task, this makes the table of disaggregated model
Performance when now can be better than execution individual task, it is possible thereby to improve the accuracy of classification results.
The embodiment of the invention also provides a kind of equipment for determining the age based on eye fundus image, comprising: at least one processing
Device；And the memory being connect at least one described processor communication；Wherein, be stored with can be one for the memory
The instruction that processor executes, described instruction are executed by least one described processor, so that at least one described processor executes
The above-mentioned method that the age is determined based on eye fundus image.
The embodiment of the invention also provides a kind of methods of determining user's eye health degree, and this method can be by computer
It is executed with electronic equipments such as servers.As shown in Fig. 2, this method comprises the following steps:
S1B determines the age that the eye fundus image of target user embodies, specifically method shown in usable Fig. 1.
S2B compares the actual age at age and target user that eye fundus image embodies.It for ease of description, can be by eyeground
The age that image embodies is known as the retina age.Actual age can be provided by user, or according to date of birth and current date
It is calculated, the actual age obtained herein is preferably integer value.
S3B determines target user's eye health degree according to comparison result.Comparison result is, for example, to be greater than at the retina age
Actual age, retina age are less than actual age, the retina age is equal to actual age, these three situations can correspond to several
Health degree.
Such as think the retina age be greater than actual age the case where be to user it is unfavorable, this may be user's eye mistake
Caused by degree, it is poor that health degree can be determined it as when obtaining this comparison result, while can mention to user feedback
Show information, user is prompted to pay attention to eye health etc..
Comparison result can also include the difference at retina age and actual age, such as when the retina age is greater than reality
When the age, the more big then corresponding health degree of difference is poorer；When being less than actual age at the retina age, the difference the big, corresponds to
Health degree it is better.
The method of the determination user's eye health degree provided according to embodiments of the present invention, is primarily based on the eyeground figure of user
As determining its age, then the age is compared with the actual age of this user, whether user is measured with comparison result
Whether excess eye-using leads to retinal abnormalities for some reason, this process does not need professional and diagnoses, it is only necessary to
User provides eye fundus image and age information is that can reach the purpose of determining user's eye health degree, has stronger convenience
Property.
In a preferred embodiment, also the data of the above-mentioned age difference of target user and other users are compared
It is right.Specifically, step S3B may include following steps:
S3B1 determines that the historical data of a number of other users, historical data include it according to the actual age of target user
The difference at age and its actual age that the eye fundus image of its user embodies, such as the historical data of user 1 are the reality of user 1
The actual age and its retina age that the historical data of difference ... the user n at age and its retina age is user n
Difference.
In one embodiment, the actual age of the actual age of other user, that is, user 1 ... user n and target user
Difference within the set range, such as difference 5 years old within.This is to obtain and belong to the other of same age bracket with target user
The data of user.
S3B2 determines the probability distribution of the historical data of a number of other users.Other users are determined using statistical algorithms
That is the probability distribution (such as Gaussian Profile) of the historical data of user 1 ... user n.Probability distribution embodies the number of each difference
Accounting, Fig. 3 show the Gaussian Profile of an age gap, and abscissa is age gap Δ X=actual age-retina age,
95.44%, which represents in user 1 ... in user in ± 5 years old, has in user n with target user's actual age difference
95.44% user's Δ X has 13.59% user's Δ X within (- 2, -1) within (- 2 ,+2).
S3B3 obtains age and the difference of its actual age that the eye fundus image of target user embodies, namely calculates target
The Δ X of user.
S3B4 determines the difference of target user section affiliated in probability distribution.By taking Fig. 3 as an example, for one newly into
The Δ X entered finds probability interval of the numerical value in this Gaussian Profile, such as the Δ X of target user is+2, then drops out
Except 95.44% distribution, it is determined that the user of Δ X ratio (1- (1-0.9544)/2) * 100%=97.7% of the target user
It is more excellent.
Being compared by the data with other people can be used family and recognizes my general level of the health in group, make user
Data that are more intuitive and can refer to are obtained, to improve the practicability of this programme.
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 method for determining the age based on eye fundus image characterized by comprising
Obtain at least eye fundus image of user；
Classified using disaggregated model to the eye fundus image, obtains the classification results for being used to indicate the age；
The age of user is determined according to the classification results.
2. the method according to claim 1, wherein in the step of obtaining at least eye fundus image of user
At least obtain each eye fundus image of eyes.
3. according to the method described in claim 2, it is characterized in that, being classified using disaggregated model to the eye fundus image
The step of in, classified respectively to eye fundus image for eyes using same disaggregated model, obtain at least two and be used to indicate
The classification results at age；
The age of user is determined according to the classification results, comprising:
The age indicated by each classification results is determined respectively；
The age of user is determined according to the age indicated by each classification results.
4. method according to any one of claim 1-3, which is characterized in that the classification results of the disaggregated model output
It is the information for being used to indicate age range；In the age for determining user according to the classification results the step of, according to the year
Age section determines age numerical value；
Or the classification results of the disaggregated model output are age numerical value.
5. method according to any of claims 1-4, which is characterized in that the disaggregated model is directed to multiple simultaneously
Business classifies to the eye fundus image, and the classification results for obtaining being used to indicate the age are appointed as one in the multiple task
Business, other tasks are and age incoherent task.
6. method according to any one of claims 1-5, which is characterized in that open one's eyes base map in obtain user at least one
In the step of picture, including eye fundus image is pre-processed, with the characteristics of image in the protrusion eye fundus image with change of age.
7. a kind of method of determining user's eye health degree characterized by comprising
The age that eye fundus image embodies is determined using the method for any of claims 1-6；
Compare the actual age at age and target user that the eye fundus image embodies；
Target user's eye health degree is determined according to comparison result.
8. the method according to the description of claim 7 is characterized in that described determine user's eye health journey according to comparison result
Degree, comprising:
The historical data of a number of other users is determined according to the actual age of the target user, wherein the reality of each other users
Within the set range, the historical data includes the eye of other users to the difference of the actual age of border age and the target user
The difference at age and its actual age that base map picture embodies；
Determine the probability distribution of the historical data of the multiple other users；
Obtain the age and the difference of its actual age that the eye fundus image of the target user embodies；
Determine the difference of target user section affiliated in the probability distribution.
9. a kind of equipment for determining the age based on eye fundus image characterized by comprising at least one processor；And with institute
State the memory of at least one processor communication connection；Wherein, the memory, which is stored with, to be executed by one processor
Instruction, described instruction executed by least one described processor, so that at least one described processor executes such as claim
The method that the age is determined based on eye fundus image described in any one of 1-6.
10. a kind of equipment of determining user's eye health degree characterized by comprising at least one processor；And with institute
State the memory of at least one processor communication connection；Wherein, the memory, which is stored with, to be executed by one processor
Instruction, described instruction executed by least one described processor, so that at least one described processor executes such as claim 8
Or the method for determination user eye health degree described in 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509791.3A CN110135528A (en) | 2019-06-13 | 2019-06-13 | Age determines that method, eye health degree determine method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910509791.3A CN110135528A (en) | 2019-06-13 | 2019-06-13 | Age determines that method, eye health degree determine method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110135528A true CN110135528A (en) | 2019-08-16 |
Family
ID=67581403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910509791.3A Pending CN110135528A (en) | 2019-06-13 | 2019-06-13 | Age determines that method, eye health degree determine method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110135528A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111028232A (en) * | 2019-12-31 | 2020-04-17 | 上海鹰瞳医疗科技有限公司 | Diabetes classification method and equipment based on fundus images |
| CN111047590A (en) * | 2019-12-31 | 2020-04-21 | 上海鹰瞳医疗科技有限公司 | Hypertension classification method and device based on fundus images |
| CN111080643A (en) * | 2019-12-31 | 2020-04-28 | 上海鹰瞳医疗科技有限公司 | Method and device for classifying diabetes and related diseases based on fundus images |
| CN111862020A (en) * | 2020-07-13 | 2020-10-30 | 南方科技大学 | Method, device, server and storage medium for predicting physiological age of anterior segment |
| CN115171204A (en) * | 2022-09-06 | 2022-10-11 | 北京鹰瞳科技发展股份有限公司 | Method for training prediction model for predicting retinal age and related product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106650653A (en) * | 2016-12-14 | 2017-05-10 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Method for building deep learning based face recognition and age synthesis joint model |
| CN106682389A (en) * | 2016-11-18 | 2017-05-17 | 武汉大学 | Health management system for monitoring ocular lesions resulting from high blood pressure |
| DE102017109856A1 (en) * | 2017-04-19 | 2018-10-25 | Instrumentacion Y Oftalmologia Insoft S.L. | Method for determining the age of the lens |
| CN109376932A (en) * | 2018-10-30 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Age prediction technique, device, server and storage medium based on prediction model |
| CN109844868A (en) * | 2016-08-18 | 2019-06-04 | 谷歌有限责任公司 | Eye fundus image is handled using machine learning model |
-
2019
- 2019-06-13 CN CN201910509791.3A patent/CN110135528A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109844868A (en) * | 2016-08-18 | 2019-06-04 | 谷歌有限责任公司 | Eye fundus image is handled using machine learning model |
| CN106682389A (en) * | 2016-11-18 | 2017-05-17 | 武汉大学 | Health management system for monitoring ocular lesions resulting from high blood pressure |
| CN106650653A (en) * | 2016-12-14 | 2017-05-10 | 广东顺德中山大学卡内基梅隆大学国际联合研究院 | Method for building deep learning based face recognition and age synthesis joint model |
| DE102017109856A1 (en) * | 2017-04-19 | 2018-10-25 | Instrumentacion Y Oftalmologia Insoft S.L. | Method for determining the age of the lens |
| CN109376932A (en) * | 2018-10-30 | 2019-02-22 | 平安医疗健康管理股份有限公司 | Age prediction technique, device, server and storage medium based on prediction model |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111028232A (en) * | 2019-12-31 | 2020-04-17 | 上海鹰瞳医疗科技有限公司 | Diabetes classification method and equipment based on fundus images |
| CN111047590A (en) * | 2019-12-31 | 2020-04-21 | 上海鹰瞳医疗科技有限公司 | Hypertension classification method and device based on fundus images |
| CN111080643A (en) * | 2019-12-31 | 2020-04-28 | 上海鹰瞳医疗科技有限公司 | Method and device for classifying diabetes and related diseases based on fundus images |
| CN111862020A (en) * | 2020-07-13 | 2020-10-30 | 南方科技大学 | Method, device, server and storage medium for predicting physiological age of anterior segment |
| CN111862020B (en) * | 2020-07-13 | 2024-04-05 | 南方科技大学 | Method and device for predicting physiological age of anterior ocular segment, server and storage medium |
| CN115171204A (en) * | 2022-09-06 | 2022-10-11 | 北京鹰瞳科技发展股份有限公司 | Method for training prediction model for predicting retinal age and related product |
| CN115171204B (en) * | 2022-09-06 | 2023-02-21 | 北京鹰瞳科技发展股份有限公司 | Method for training prediction model for predicting retinal age and related product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110135528A (en) | Age determines that method, eye health degree determine method and apparatus | |
| Jiwani et al. | Novel healthcare framework for cardiac arrest with the application of AI using ANN | |
| Vega et al. | Retinal vessel extraction using lattice neural networks with dendritic processing | |
| Guo et al. | A computer-aided healthcare system for cataract classification and grading based on fundus image analysis | |
| Prentašić et al. | Detection of exudates in fundus photographs using convolutional neural networks | |
| Forestier et al. | Classification of surgical processes using dynamic time warping | |
| CN110897639A (en) | Electroencephalogram sleep staging method based on deep convolutional neural network | |
| CN107330449A (en) | A kind of BDR sign detection method and device | |
| JP2011520503A (en) | Automatic concave nipple ratio measurement system | |
| WO2018012601A1 (en) | Image analysis system, culture management system, image analysis method, culture management method, cell group structure method, and program | |
| CN110163839A (en) | The recognition methods of leopard line shape eye fundus image, model training method and equipment | |
| El Hossi et al. | Applied CNN for automatic diabetic retinopathy assessment using fundus images | |
| Yerokhin et al. | Usage of phase space diagram to finding significant features of rhinomanometric signals | |
| Shaik et al. | Glaucoma identification based on segmentation and fusion techniques | |
| Choudhary et al. | ANN glaucoma detection using cup-to-disk ratio and neuroretinal rim | |
| CN110490138A (en) | A kind of data processing method and device, storage medium, electronic equipment | |
| Zhu et al. | A computer vision-based approach to grade simulated cataract surgeries | |
| KR20220123518A (en) | Method and device for generating improved surgical report using machine learning | |
| Schweitzer et al. | Definition, modeling, and detection of saccades in the face of post-saccadic oscillations | |
| Tucker et al. | The pseudotemporal bootstrap for predicting glaucoma from cross-sectional visual field data | |
| Cornforth et al. | Automated classification reveals morphological factors associated with dementia | |
| CN115205954A (en) | Eye disease identification method, device and equipment | |
| Jusoh et al. | An overview of retinal blood vessels segmentation | |
| Barman et al. | Image quality assessment | |
| Raghavan et al. | Bio-inspired and deep learning approach for cerebral aneurysms prediction in healthcare environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190816 |
|
| RJ01 | Rejection of invention patent application after publication |