CN111700582A - Common ocular surface disease diagnosis system based on intelligent terminal - Google Patents
Common ocular surface disease diagnosis system based on intelligent terminal Download PDFInfo
- Publication number
- CN111700582A CN111700582A CN202010578639.3A CN202010578639A CN111700582A CN 111700582 A CN111700582 A CN 111700582A CN 202010578639 A CN202010578639 A CN 202010578639A CN 111700582 A CN111700582 A CN 111700582A
- Authority
- CN
- China
- Prior art keywords
- eye
- module
- questionnaire
- classification
- intelligent terminal
- 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
Images
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
- A61B3/02—Subjective types, i.e. testing apparatus requiring the active assistance of the patient
-
- 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
Abstract
A common ocular surface disease diagnosis system based on an intelligent terminal comprises an information acquisition module, a diagnosis module and a diagnosis module, wherein the information acquisition module is arranged on the intelligent terminal and comprises an image acquisition unit, a questionnaire acquisition unit and a basic information acquisition unit; the data processing module is connected with the information acquisition module and comprises a questionnaire processing module and an intelligent picture classification module, wherein the questionnaire processing module is used for receiving the questionnaire information input by the questionnaire acquisition unit and giving out corresponding eye surface disease evaluation scores; the intelligent picture classification module classifies the input eye surface pictures by using an eye surface model stored in the intelligent picture classification module or in a cloud end, and obtains classification results of normal eye surfaces, viral keratitis, bacterial keratitis, fungal keratitis, pterygium, conjunctivitis and eye surface swelling; and the diagnosis and treatment suggestion module is connected with the data processing module, receives the evaluation score of the questionnaire processing module and/or the classification result of the intelligent picture classification module, and outputs a corresponding diagnosis and treatment suggestion according to the evaluation score and/or the classification result.
Description
Technical Field
The invention relates to medical equipment, in particular to a common ocular surface disease diagnosis system based on an intelligent terminal.
Background
The ocular surface anatomically refers to the entire mucosal epithelium of the ocular surface starting between the upper and lower eyelid margin lines, and clinically encompasses a variety of diseases of the cornea, conjunctiva, eyelids, lacrimal apparatus, and lacrimal passage. Common ocular surface diseases in clinic mainly include: infectious keratitis, dry eye, pterygium, conjunctivitis, ocular surface and eyelid swelling, blepharitis, meibomian gland dysfunction, and the like, regardless of the disease type, require early discovery and timely treatment, particularly infectious keratitis with severe complications.
Corneal opacity caused by infectious keratitis is one of the fourth most blind causes worldwide, and can be roughly classified into viral keratitis, bacterial keratitis and fungal keratitis in etiology. The most common of viral keratitis is Herpes Simplex Keratitis (HSK), the causative agent of which is a herpes simplex virus latent in the trigeminal nerve, usually at times when the patient is immunocompromised, and often relapses. It has to be taken into consideration that HSK ranks first in blindness due to ocular surface diseases, so early HSK screening diagnosis is particularly important. Bacterial keratitis is suppurative keratitis caused by bacterial infection, also called bacterial corneal ulcer, often caused by trauma or foreign bodies, has acute onset, rapid development and serious symptoms, and if the bacterial keratitis is not effectively treated, corneal ulcer perforation, even intraocular infection and finally eyeball atrophy can occur. Fungal keratitis is an infectious ocular surface disease which is caused by pathogenic fungi and has extremely high blinding rate, the onset of the disease is slow, the disease course is long, the disease course can last for 2 to 3 months, corneal ulcer often appears within a few days of the disease, the fungal keratitis is often caused by plant or crop trauma, and the number of patients is large in China.
International tear film and ocular surface association (TFOS) issued in 2017 a milestone expert consensus in the field of dry eye disease (tfosdess II), defining dry eye as a multifactorial ocular surface disease characterized by tear film imbalance and accompanying ocular symptoms, with tear film instability and hyperpermeability, ocular surface inflammation and damage, and neurosensory abnormalities playing a role in its pathogenesis. The disease is often diagnosed clinically by asking the patient for symptoms and other subjective indicators, with questionnaires being an important way to diagnose dry eye.
Pterygium is a degenerative disease that occurs in warm, dry areas, usually nasal, temporal or biceps, and is characterized by fibrovascular growth in the conjunctiva and invasion of the cornea. Outdoor work, age and males are the most relevant risk factors. At the early stage of pterygium, there are usually no symptoms, and dry eye, itching, lacrimation, etc. may occur. As the range of invasion into the cornea increases, corneal astigmatism will likely be affected, affecting vision, and thus requiring surgical treatment.
Conjunctivitis is a common conjunctival disease in clinical practice and can be classified into infectious and non-infectious according to the etiology. The common features of clinical manifestations are conjunctival congestion and increased secretions, and may have symptoms of foreign body sensation, burning sensation, heavy eyelids, photophobia, lacrimation, etc. When conjunctivitis is not treated in time, the conjunctivitis can be delayed and not healed, foreign body sensation and asthenopia discomfort can appear, and ptosis, blepharon adhesion and the like can appear in severe cases.
In the prior art, a large number of diagnoses are assisted by medical image methods, and no matter the patients go to community screening or go to a hospital for a doctor, ophthalmologists or trained medical assistants are required to perform professional examination and take pictures, so that a large number of operations are relied on, and the clinical cost is greatly increased. On the other hand, patients have difficulty in effectively distinguishing diseases through self-diagnosis, and cannot realize remote medical treatment and guarantee real-time performance.
Disclosure of Invention
The invention aims to solve the technical problem in the prior art, and provides a common eye surface disease diagnosis system based on a smart phone.
In order to achieve the above object, the present invention provides a common ocular surface disease diagnosis system based on an intelligent terminal, wherein the system comprises:
the system comprises an information acquisition module, a database and a database, wherein the information acquisition module is installed on an intelligent terminal and comprises an image acquisition unit, a questionnaire acquisition unit and a basic information acquisition unit;
the data processing module is installed on the intelligent terminal or the server and connected with the information acquisition module, the data processing module comprises a questionnaire processing module and an intelligent picture classification module, and the questionnaire processing module is used for receiving the questionnaire information input by the questionnaire acquisition unit and giving out corresponding eye surface disease evaluation scores; the intelligent picture classification module stores an eye surface model, classifies the input eye surface picture by using the eye surface model, and obtains classification results of normal eye surface, viral keratitis, bacterial keratitis, fungal keratitis, pterygium, conjunctivitis and eye surface swelling; and
and the diagnosis and treatment suggestion module is installed on the intelligent terminal or the server, is connected with the data processing module, receives the eye surface disease evaluation score of the questionnaire processing module and/or the classification result of the intelligent picture classification module, and outputs a corresponding diagnosis and treatment suggestion according to the eye surface disease evaluation score and/or the classification result.
In the above common ocular surface disease diagnosis system based on the intelligent terminal, the questionnaire acquisition unit adopts an OSDI dry eye questionnaire, and the questionnaire processing module calculates a final OSDI score according to the acquisition result of the OSDI dry eye questionnaire, and determines whether dry eye exists and a degree grade according to the final OSDI score.
The common ocular surface disease diagnosis system based on the intelligent terminal, wherein the formula for calculating the final OSDI score is as follows:
the sum of all the answer scores D is A + B + C;
the answer question number E is 12-H;
final OSDI score F ═ D × 25/E;
wherein A is the answer score of 1-5 questions, B is the answer score of 6-9 questions, C is the answer score of 10-12 questions, and H is the number of answer questions selected as 'not applicable'.
The above common ocular surface disease diagnosis system based on an intelligent terminal, wherein the determining whether dry eye exists and the degree grade according to the final OSDI score F includes:
f is less than or equal to 12, the product is normal and has no dry eye;
f < 13 < 22 is mild dry eye;
moderate dry eye with F < 23 < 32; and
f.gtoreq.33 is severe dry eye.
In the above common ocular surface disease diagnosis system based on the intelligent terminal, the ocular surface model is obtained by performing disease classification processing on an ocular surface picture database by using a deep convolutional neural network, generating the ocular surface model, and storing the ocular surface model in the picture intelligent classification module or the cloud.
In the above common ocular surface diagnosis system based on the intelligent terminal, the DenseNet classification network is used to classify the ocular surface image database for the diseases corresponding to the ocular surface image.
In the above common ocular surface disease diagnosis system based on the intelligent terminal, the DenseNet network is trained by using the multivariate cross entropy as the cost function, the stochastic gradient descent method is used as the optimization algorithm, and the initial learning ratio of the algorithm is set as lr0＝1.0×10-3The momentum is 0.9, the learning ratio is reduced to 0.1 times of the original training every 20 global ergodic generations, the total number of the training generations is 100, and the number of batch processing samples is 8.
In the above common ocular surface disease diagnosis system based on the intelligent terminal, the size of the image of the ocular surface picture in the ocular surface picture database is 299 × 299, and the ocular surface picture is subjected to enhancement processing to reduce the overfitting phenomenon of the training result.
In the above common ocular surface disease diagnosis system based on the intelligent terminal, the CCE function is as follows:
wherein C represents the total number of classes, piAnd yiRespectively representing the prediction probability of the classification network and the manual labeling when the image belongs to the ith class.
The common eye surface disease diagnosis system based on the intelligent terminal comprises the intelligent mobile phone and the tablet computer.
The invention has the technical effects that:
the invention can be used for rapid diagnosis of common ocular surface diseases, and is cross fusion of artificial intelligence and ophthalmic medical clinical fields. The system can be carried on a common intelligent terminal, such as a mobile phone and a tablet personal computer of a user, and can also be manufactured into a portable intelligent terminal with a shooting function for independent use, the diagnosis range of the system covers various common eye surface diseases such as viral keratitis, bacterial keratitis, fungal keratitis, pterygium, conjunctivitis, eye surface swelling, normal eye surface and the like, more categories can be expanded according to clinical requirements, under the condition of not increasing the workload of doctors or the program cost, clinical instant diagnosis and treatment suggestions can be efficiently obtained at low cost, and remote self-diagnosis and pre-diagnosis of the user are facilitated; the cornea health condition of a patient can be simply, quickly and accurately evaluated, the diagnosis efficiency of the corneal diseases is improved, and the waiting time for clinical hospitalization is shortened. And can provide reference for a clinician; providing an opportunity for telemedicine.
The invention is described in detail below with reference to the drawings and specific examples, but the invention is not limited thereto.
Drawings
FIG. 1 is a schematic structural diagram of an embodiment of the present invention;
FIG. 2 is a schematic diagram of a diagnostic process according to an embodiment of the present invention;
FIG. 3 is an exemplary illustration of deep learning ophthalmic slit-lamp photo classification according to an embodiment of the present invention;
fig. 4 is an exemplary diagram of a classification of photos taken by a deep learning eye surface mobile phone according to an embodiment of the invention.
Wherein the reference numerals
1 information acquisition module
11 image acquisition unit
12 questionnaire acquisition unit
13 basic information acquisition unit
2 data processing module
21 questionnaire processing module
22 intelligent image classification module
3 diagnosis and treatment suggestion module
4 viral keratitis
5 fungal keratitis
6 bacterial keratitis
7 Normal eye surface
Pterygium 8
9 conjunctivitis
10 ocular surface swelling
Detailed Description
The invention will be described in detail with reference to the following drawings, which are provided for illustration purposes and the like:
referring to fig. 1, fig. 1 is a schematic structural diagram of an embodiment of the present invention. The common ocular surface disease diagnosis system based on the intelligent terminal adopts a user-server network architecture and comprises a client and a server, wherein the client is provided with common ocular surface disease diagnosis system APP software (application, APP) based on the intelligent terminal, and based on a deep learning technology, the server judges xerophthalmia and the severity thereof and the possible ocular surface disease types by extracting questionnaires or shot ocular surface pictures input by the intelligent terminal, feeds back corresponding diagnosis information and provides corresponding diagnosis suggestions and related cautions. This common ocular surface disease diagnostic system based on intelligent terminal includes: the system comprises an information acquisition module 1, an information acquisition module 1 and an information acquisition module, wherein the information acquisition module 1 is installed on an intelligent terminal, the intelligent terminal can be a smart phone and a tablet personal computer, and can also be other intelligent terminals with image photographing functions, the information acquisition module 1 comprises an image acquisition unit 11, a questionnaire acquisition unit 12 and a basic information acquisition unit 13, a subject fills in personal information, eye disease questionnaires such as xerophthalmia and the like through APP or shoots eye pictures by means of the intelligent terminal (such as a cell phone P30), and the information acquisition module 1 acquires the information; the data processing module 2 is installed on the intelligent terminal or the server and connected with the information acquisition module 1, the data processing module 2 comprises a questionnaire processing module 21 and a picture intelligent classification module 22, the questionnaire processing module 21 is used for receiving the questionnaire information input by the questionnaire acquisition unit 12 for analysis and giving out corresponding ocular surface disease evaluation scores to judge whether the eye has dry eye and the severity thereof or other ocular surface diseases which can be preliminarily diagnosed by the questionnaire; the intelligent picture classification module 22 stores an eye surface model, and the intelligent picture classification module 22 classifies the input eye surface picture by using the eye surface model stored in the intelligent picture classification module 22 or stored in a cloud, and obtains classification results of viral keratitis 4, fungal keratitis 5, bacterial keratitis 6, pterygium 8, conjunctivitis 9, eye surface swelling 10, normal eye surface 7 and the like; and a diagnosis and treatment suggestion module 3, which is installed on the intelligent terminal or the server and connected with the data processing module 2, receives the evaluation scores of the dry eye and the like of the questionnaire processing module 21 and/or the classification results of the intelligent image classification module 22, and outputs corresponding diagnosis and treatment suggestions according to the evaluation scores of the dry eye and the like and/or the classification results.
Referring to fig. 2, fig. 2 is a schematic diagram of a diagnostic process according to an embodiment of the present invention. The user fills in personal information of a person to be diagnosed on the APP, wherein the personal information comprises basic information such as name, gender, age and the like. After the personal information is filled in, the user can select to click a questionnaire self-check or eye disease button. If the questionnaire is clicked for self-checking, any questionnaire is selected on the corresponding interface to be filled in, as shown in the following table I. If click ophthalmopathy, then open intelligent terminal's camera automatically, if the macro camera shooting function in the shooting function, flash light, the camera function of the rear camera of cell-phone to shoot cornea photo through following step: after pressing ophthalmopathy button in the APP, use relevant instrument or finger to prop open the eyelid, aim at the intelligent terminal like the rearmounted camera of cell-phone and shoot the eye to place 2 ~ 3 centimetres away from the eye, shoot after automatic or manual focusing is clear to the eye surface picture (the effect of shooing is like figure 4).
In this embodiment, the questionnaire collecting unit 12 adopts an OSDI dry eye questionnaire (see table one below), and the questionnaire processing module 21 calculates a final OSDI score according to the collection result of the OSDI dry eye questionnaire, and determines whether dry eye exists and a degree grade according to the final OSDI score. Wherein the formula for calculating the final OSDI score is:
the sum of all the answer scores D is A + B + C;
the answer question number E is 12-H;
final OSDI score F ═ D × 25/E;
wherein A is the answer score of 1-5 questions, B is the answer score of 6-9 questions, C is the answer score of 10-12 questions, and H is the number of answer questions selected as 'not applicable'.
In this embodiment, determining whether dry eye and the degree grade according to the final OSDI score F includes:
f is less than or equal to 12, the product is normal and has no dry eye;
f < 13 < 22 is mild dry eye;
moderate dry eye with F < 23 < 32; and
f.gtoreq.33 is severe dry eye.
Table one eye disease index questionnaire (OSDI scale)
Please answer the following question (circle the number in the table that best fits the question)
In the embodiment, the eye surface model is obtained by performing disease classification processing on an eye surface image database by using a deep convolutional neural network, generating the eye surface model, and storing the eye surface model in the image intelligent classification module 22. Based on the eye surface picture taken by a slit-lamp microscope (see fig. 3) and the eye surface picture taken by a macro lens of a mobile phone (see fig. 4), the two types of cornea pictures are labeled as follows: normal, viral keratitis, bacterial keratitis, fungal keratitis, pterygium, ocular surface swelling, conjunctivitis and others (more categories can be expanded according to clinical needs). And carrying out disease classification processing on the pictures by utilizing a deep convolutional neural network to complete the eye surface model construction of intelligent picture classification. In this embodiment, a DenseNet classification network is used to classify the eye table image database into the eye table image corresponding diseases (refer to Keras software library, https:// github for specific implementation).com/keras-team/keras-applications), classification of the eye surface image corresponding to the disease is performed. In order to train the DenseNet, multivariate cross entropy is adopted as a cost function, a Stochastic Gradient Descent (SGD) method is used as an optimization algorithm, and an initial learning ratio (lr) of the algorithm is set as lr0＝1.0×10-3The momentum is 0.9, the learning ratio is reduced to 0.1 times every 20 global traversals (epochs), the total epoch number is 100, and the batch size is 8. In the training of the classification model, the image size of the eye surface picture is set to 299 and 299, and necessary enhancement processing (such as turning, translation, rotation and the like) is carried out on the eye surface picture so as to reduce the overfitting phenomenon of a training result. The CCE function is:
wherein C represents the total number of classes, piAnd yiRespectively representing the prediction probability of the classification network and the manual labeling when the image belongs to the ith class.
The eye surface pictures (see fig. 4) taken by the smart phone are classified by using the constructed eye surface model with intelligently classified pictures, and the classification results of eye surface diseases such as normal eye surface 7, viral keratitis 4, fungal keratitis 5, bacterial keratitis 6, pterygium 8, conjunctivitis 9, eye surface swelling 10 and the like are obtained.
Finally, the diagnosis and treatment suggestion module 3 outputs disease names (including no dry eye, light dry eye, moderate dry eye, severe dry eye, severity of other eye surface diseases preliminarily diagnosed by the questionnaire, viral keratitis 4, fungal keratitis 5, bacterial keratitis 6, pterygium 8, conjunctivitis 9, eye surface swelling 10, normal eye surface 7 or the like) and corresponding related disease descriptions, diagnosis and treatment suggestions, immediate diagnosis, follow-up visit observation frequency, daily diet suggestions, nursing suggestions and the like according to the classification results of the questionnaire processing module 21 or the picture intelligent classification module 22, and the disease names can be directly displayed on a display screen of the intelligent terminal, and also can be stored, downloaded, printed, sent to a mailbox, uploaded to a cloud and the like.
The invention is based on the deep learning image recognition technology, can be carried on an intelligent terminal, is used for intelligent screening diagnosis of common ocular surface diseases, realizes intelligent diagnosis of different ocular surface diseases by means of a deep convolution neural network technology, covers various common ocular surface diseases such as viral keratitis 4, fungal keratitis 5, bacterial keratitis 6, pterygium 8, conjunctivitis 9, ocular surface swelling 10, dry eye and the like, and is cross fusion of artificial intelligence and the clinical field of ophthalmic medical treatment. The system can be mounted on a mobile intelligent terminal (for example, the system can be mounted on a mobile phone of a user, and can also be mounted on a mobile device with a shooting function such as a tablet personal computer), so that remote self-diagnosis and pre-diagnosis can be carried out anytime and anywhere; and can provide reference for clinicians and can expand more categories according to clinical needs, such as keratoconus, corneal dystrophy, blepharitis, corneal degeneration and the like.
The present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof, and it should be understood that various changes and modifications can be effected therein by one skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A common eye surface disease diagnosis system based on an intelligent terminal is characterized by comprising:
the system comprises an information acquisition module, a database and a database, wherein the information acquisition module is installed on an intelligent terminal and comprises an image acquisition unit, a questionnaire acquisition unit and a basic information acquisition unit;
the data processing module is installed on the intelligent terminal or the server and connected with the information acquisition module, the data processing module comprises a questionnaire processing module and an intelligent picture classification module, and the questionnaire processing module is used for receiving the questionnaire information input by the questionnaire acquisition unit and giving out corresponding eye surface disease evaluation scores; the intelligent picture classification module stores an eye surface model, classifies the input eye surface picture by using the eye surface model, and obtains classification results of other eye surface diseases such as normal eye surface, viral keratitis, bacterial keratitis, fungal keratitis, pterygium, conjunctivitis, eye surface swelling and the like; and
and the diagnosis and treatment suggestion module is installed on the intelligent terminal or the server, is connected with the data processing module, receives the eye surface disease evaluation score of the questionnaire processing module and/or the classification result of the intelligent picture classification module, and outputs a corresponding diagnosis and treatment suggestion according to the eye surface disease evaluation score and/or the classification result.
2. The system as claimed in claim 1, wherein the questionnaire collecting unit adopts an OSDI dry eye questionnaire, and the questionnaire processing module calculates a final OSDI score according to the collection result of the OSDI dry eye questionnaire, and determines whether dry eye occurs and a degree grade according to the final OSDI score.
3. The system of claim 2, wherein the final OSDI score is calculated by the formula:
the sum of all the answer scores D is A + B + C;
the answer question number E is 12-H;
final OSDI score F ═ D × 25/E;
wherein A is the answer score of 1-5 questions, B is the answer score of 6-9 questions, C is the answer score of 10-12 questions, and H is the number of answer questions selected as 'not applicable'.
4. The system as claimed in claim 3, wherein the determining whether dry eye occurs and the degree grade according to the final OSDI score F comprises:
f is less than or equal to 12, the product is normal and has no dry eye;
f < 13 < 22 is mild dry eye;
moderate dry eye with F < 23 < 32; and
f.gtoreq.33 is severe dry eye.
5. The system for diagnosing common eye surface diseases based on the intelligent terminal as claimed in claim 1, 2, 3 or 4, wherein the eye surface model is obtained by performing disease classification processing on an eye surface picture database by using a deep convolutional neural network, and generating the eye surface model to be stored in the picture intelligent classification module or a cloud terminal.
6. The system as claimed in claim 5, wherein the DenseNet classification network is used to classify the eye table image into corresponding diseases.
7. The system as claimed in claim 6, wherein the Densenet network is trained by using multivariate cross entropy as a cost function, a stochastic gradient descent method is used as an optimization algorithm, and an initial learning ratio of the algorithm is set as lr0＝1.0×10-3The momentum is 0.9, the learning ratio is reduced to 0.1 times of the original training every 20 global ergodic generations, the total number of the training generations is 100, and the number of batch processing samples is 8.
8. The system according to claim 7, wherein the size of the image of the eye table picture in the eye table picture database is 299 x 299, and the eye table picture is subjected to enhancement processing to reduce the overfitting phenomenon of the training result.
9. The intelligent terminal-based diagnosis system for common ocular surface diseases according to claim 8, wherein the CCE function is as follows:
wherein C represents the total number of classes, piAnd yiRespectively representing the prediction probability of the classification network and the manual labeling when the image belongs to the ith class.
10. The system for diagnosing the common ocular surface diseases based on the intelligent terminal as claimed in any one of claims 1 to 9, wherein the intelligent terminal comprises a smart phone and a tablet computer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010578639.3A CN111700582A (en) | 2020-06-23 | 2020-06-23 | Common ocular surface disease diagnosis system based on intelligent terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010578639.3A CN111700582A (en) | 2020-06-23 | 2020-06-23 | Common ocular surface disease diagnosis system based on intelligent terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111700582A true CN111700582A (en) | 2020-09-25 |
Family
ID=72541526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010578639.3A Pending CN111700582A (en) | 2020-06-23 | 2020-06-23 | Common ocular surface disease diagnosis system based on intelligent terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111700582A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114005541A (en) * | 2021-11-24 | 2022-02-01 | 珠海全一科技有限公司 | Dynamic dry eye early warning method and system based on artificial intelligence |
| WO2022092134A1 (en) * | 2020-10-28 | 2022-05-05 | ライオン株式会社 | Examination method, machine learning execution method, examination device, and machine learning execution method |
| JP7094468B1 (en) | 2020-12-25 | 2022-07-01 | ライオン株式会社 | Inspection methods |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104398234A (en) * | 2014-12-19 | 2015-03-11 | 厦门大学 | Comprehensive ocular surface analyzer based on expert system |
| CN107644676A (en) * | 2017-11-08 | 2018-01-30 | 天津牧瞳星科技有限公司 | A kind of easily xerophthalmia diagnosis and therapy system |
| CN109636796A (en) * | 2018-12-19 | 2019-04-16 | 中山大学中山眼科中心 | A kind of artificial intelligence eye picture analyzing method, server and system |
| CN111160271A (en) * | 2019-12-30 | 2020-05-15 | 哈尔滨商业大学 | Indoor chicken farm sick chicken detecting system based on deep learning |
-
2020
- 2020-06-23 CN CN202010578639.3A patent/CN111700582A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104398234A (en) * | 2014-12-19 | 2015-03-11 | 厦门大学 | Comprehensive ocular surface analyzer based on expert system |
| CN107644676A (en) * | 2017-11-08 | 2018-01-30 | 天津牧瞳星科技有限公司 | A kind of easily xerophthalmia diagnosis and therapy system |
| CN109636796A (en) * | 2018-12-19 | 2019-04-16 | 中山大学中山眼科中心 | A kind of artificial intelligence eye picture analyzing method, server and system |
| CN111160271A (en) * | 2019-12-30 | 2020-05-15 | 哈尔滨商业大学 | Indoor chicken farm sick chicken detecting system based on deep learning |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022092134A1 (en) * | 2020-10-28 | 2022-05-05 | ライオン株式会社 | Examination method, machine learning execution method, examination device, and machine learning execution method |
| JP7094468B1 (en) | 2020-12-25 | 2022-07-01 | ライオン株式会社 | Inspection methods |
| JP2022104840A (en) * | 2020-12-25 | 2022-07-11 | ライオン株式会社 | Inspection method |
| CN114005541A (en) * | 2021-11-24 | 2022-02-01 | 珠海全一科技有限公司 | Dynamic dry eye early warning method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111700582A (en) | Common ocular surface disease diagnosis system based on intelligent terminal | |
| CN109528155B (en) | Intelligent screening system suitable for high myopia complicated with open angle glaucoma and establishment method thereof | |
| CN112545452B (en) | High myopia fundus lesion image recognition device | |
| CN111986211A (en) | Deep learning-based ophthalmic ultrasonic automatic screening method and system | |
| US20210391056A1 (en) | Health big data service method and system based on remote fundus screening | |
| CN109464120A (en) | A kind of screening for diabetic retinopathy method, apparatus and storage medium | |
| CN112101424B (en) | Method, device and equipment for generating retinopathy identification model | |
| CN109998477A (en) | A kind of high myopia cataract operation prognosis intelligence anticipation system | |
| CN110013216B (en) | Artificial intelligence cataract analysis system | |
| Ram et al. | The relationship between Fully Connected Layers and number of classes for the analysis of retinal images | |
| CN111199794B (en) | Intelligent surgical decision making system suitable for high myopia cataract and establishing method thereof | |
| CN116433644B (en) | Eye image dynamic diagnosis method based on recognition model | |
| Subramanian et al. | Classification of retinal oct images using deep learning | |
| Hassan et al. | Exploiting the transferability of deep learning systems across multi-modal retinal scans for extracting retinopathy lesions | |
| CN113962995B (en) | Cataract model training method and cataract identification method | |
| Das et al. | Impact of implementing teleophthalmology referral guidelines using the eyeSmart EMR app in 63,703 patients from India | |
| Camara et al. | A comprehensive review of methods and equipment for aiding automatic glaucoma tracking | |
| Zhang et al. | DeepUWF-plus: automatic fundus identification and diagnosis system based on ultrawide-field fundus imaging | |
| CN113408593A (en) | Diabetic retinopathy image classification method based on improved ResNeSt convolutional neural network model | |
| Triyadi et al. | Deep learning in image classification using vgg-19 and residual networks for cataract detection | |
| Ali et al. | Cataract disease detection used deep convolution neural network | |
| CN113470815A (en) | AI technology-based cataract patient vision impairment degree evaluation system | |
| CN112220445A (en) | Mobile terminal-based cataract and after cataract analysis system and device | |
| CN214484464U (en) | Mobile terminal-based cataract and after cataract analysis system and device | |
| Choudhry et al. | DarkNet-19 Based Intelligent Diagnostic System for Ocular Diseases |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230317 Address after: Room 513, Building D, No. 100, Luodong North Street, Yongzhong Street, Longwan District, Wenzhou City, Zhejiang Province, 325000 Applicant after: Eye Medicine (Wenzhou) Biotechnology Co.,Ltd. Address before: 325027 No. 270 College West Road, Zhejiang, Wenzhou Applicant before: THE EYE HOSPITAL OF WENZHOU MEDICAL University |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200925 |