CN113470815A - AI technology-based cataract patient vision impairment degree evaluation system - Google Patents
AI technology-based cataract patient vision impairment degree evaluation systemDownload PDFInfo
- Publication number
- CN113470815A CN113470815ACN202110734838.3ACN202110734838ACN113470815ACN 113470815 ACN113470815 ACN 113470815ACN 202110734838 ACN202110734838 ACN 202110734838ACN 113470815 ACN113470815 ACN 113470815A
- Authority
- CN
- China
- Prior art keywords
- cataract
- module
- image
- patient
- fundus
- 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
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
- 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
- A61B3/117—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for examining the anterior chamber or the anterior chamber angle, e.g. gonioscopes
- A61B3/1173—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for examining the anterior chamber or the anterior chamber angle, e.g. gonioscopes for examining the eye lens
- A61B3/1176—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for examining the anterior chamber or the anterior chamber angle, e.g. gonioscopes for examining the eye lens for determining lens opacity, e.g. cataract
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Pathology (AREA)
- General Engineering & Computer Science (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Ophthalmology & Optometry (AREA)
- Heart & Thoracic Surgery (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Eye Examination Apparatus (AREA)
Abstract
Translated fromChinese
Description
Technical Field
The invention belongs to the technical field of medical image processing, and particularly relates to an AI technology-based cataract patient vision impairment degree evaluation system.
Background
Cataract is the first eye disease causing blindness, and China is the country with the most cataract patients and has over 7000 thousands of people. The cataract extraction operation at the present stage is the only effective treatment mode, and the timely diagnosis and the operation treatment can prevent the patient from blindness. However, cataract diagnosis at present depends on a limited specialized ophthalmologist. Data published by the International Council for Ophthalmology, ICO, 2012 showed that the total number of registered ophthalmologists in china was only 28338, only 1 ophthalmologist in every 6 ten thousand population, and had not reached the goal of 1 ophthalmologist in every 5 thousand population in asia by the year 2020 as proposed in the action of "vision 2020" initiated by the world health organization.
Ophthalmologists are relatively limited at present, cataract examination is time-consuming, and due to low sanitary expenditure, cataract blindness rate is high in middle and low income countries and regions, and extensive cataract blindness is difficult to prevent and avoid. Therefore, the artificial intelligence provides possibility for solving the contradiction between supply and demand of medical resources, can be popularized and used in primary hospitals and common people, is an important means for improving ophthalmic health care service in underdeveloped areas and bringing brightness to cataract patients.
However, the existing artificial intelligence system does not establish the relation between the severity of cataract and the degree of visual impairment, so that no specific diagnosis and treatment suggestions are given to patients with severe visual impairment and blindness, the diagnosis and treatment effect is easily reduced, and the illness state of the patients is delayed; the effectiveness of the blind prevention and blind treatment work is easily reduced, and the waste or insufficient administration of medical resources is caused.
Disclosure of Invention
Aiming at the existing problems, the invention provides the vision damage degree evaluation system for the cataract patient based on the AI technology, which can simply and quickly evaluate whether the patient has the cataract and the vision damage degree thereof, and provide related diagnosis and treatment suggestions, thereby improving the diagnosis and treatment efficiency.
The technical scheme of the invention is as follows: the cataract patient vision damage degree evaluation system based on the AI technology comprises an information acquisition module, a fundus image acquisition module, an image identification module, an image classification module, an illness state evaluation module and a diagnosis and treatment suggestion module;
the information acquisition module is used for acquiring basic information of an individual user;
the eye fundus image acquisition module is used for acquiring a mydriasis-free eye fundus image of a patient;
the image identification module is used for performing bottom image classification identification according to whether the patient has cataract in the mydriatic eye fundus image acquired by the eye fundus image acquisition module; grading and marking the fundus image marked as 'cataract' according to the vision damage degree of the cataract patient;
the image classification module is used for processing the mydriasis-free eye fundus image identification through the deep convolution neural network on the basis of the classification identification of whether cataract exists or not and the degree of cataract vision damage in the eye fundus image identified by the image identification module to obtain a deep learning model;
the disease condition evaluation module is used for acquiring a mydriasis-free eye fundus image of the patient through the eye fundus image acquisition module according to the deep learning model obtained by the image classification module, and evaluating and grading the vision damage degree of the cataract patient.
Further, the image identification module divides the fundus image into two stages according to the lenticular opacity: the degree of visual impairment of patients with cataract is marked in five grades, namely 1 grade, 2 grade, 3 grade, 4 grade and 5 grade.
Furthermore, the grade 1 represents no/mild visual impairment with the vision being more than or equal to 0.5, thegrade 2 represents no/mild visual impairment with the vision being more than or equal to 0.3, thegrade 3 represents moderate visual impairment with the vision being more than or equal to 0.1, thegrade 4 represents severe visual impairment with the vision being more than or equal to 0.05, and thegrade 5 represents blind with the vision being less than 0.05.
Furthermore, the diagnosis and treatment suggestion module gives necessary diagnosis and treatment suggestions according to different degrees of visual impairment of the cataract patient obtained by the disease condition evaluation module, and different diagnosis and treatment suggestions can be given in a targeted manner by giving the diagnosis and treatment suggestions with different degrees of visual impairment, so that the diagnosis accuracy is improved.
Further, the diagnosis and treatment suggestion module judges whether cataract surgery is needed or not at the time of diagnosis, and the judgment criteria are as follows: assessment of visual impairment abovegrade 3 requires cataract surgery.
Further, the deep convolutional neural network is a densenert 121, and the specific steps of performing interpretation training by using the densenert 121 are as follows:
first, the experimental algorithm sets up:
SGD is adopted as an optimization algorithm, the initial learning rate (lr) corresponding to the algorithm is set to be 0.001, the momentum is 0.9, the weight attenuation degree is 5 multiplied by 10-5The iteration time epoch is 80, and the batch size batchsize is 64; a learning rate attenuation strategy is adopted in the training process: each iteration 20 times, the learning rate decays to one tenth of the original, expressed as:
lr ═ Lr (0.1 ═ epoch//20)), i.e., the formula is as follows
Lr＝lr×(0.1(k//20))
Wherein, the operator of integer division is obtained, namely the integer part (not including remainder) of the quotient is obtained, and k is the iteration number;
the Loss function used for the experiment was a Cross Entropy Loss function (Cross entry Loss):
wherein p isiAnd yiRespectively representing the prediction probability of the classification model predicted image as the ith class and the real label of the image, wherein n is the total number of the classified classes;
second, experimental environment:
in the experiment, a network model of the experiment is built by using a Pythrch deep learning framework, and the network model is trained on NVIDIA TITAN RTX GPUs with 24G video memory;
thirdly, data preprocessing:
the image size of the data set is uniformly scaled to 224 x 224 to meet the input requirement of the network model, meanwhile, in order to enhance the generalization capability of the model, the image is randomly rotated by 90 degrees and turned over in the horizontal or vertical direction, and the random probability is 0.5;
fourth, data set partitioning:
the original data set is randomly divided into a training set, a verification set and a test set, and the proportion of each part is 70%, 15% and 15% respectively.
Furthermore, in the above experimental process, after each round of training, the model is verified by using the verification set, and after the training times are completed, the final model after the training is completed is tested by using the test set, so as to evaluate the performance of the classification model.
Furthermore, when the eye fundus image acquisition module acquires the mydriasis-free eye fundus image of the patient, the digital photographing examination of the small pupil eye fundus is carried out through the mydriasis-free eye fundus digital photographing equipment, and the method for screening the moderate and severe cataract which obviously affects the vision is feasible, can replace a slit lamp microscopy examination method to screen the cataract, needs an operator, has the advantages of simple and quick process, and can realize the combined screening of various eye diseases causing blindness.
Further, the non-mydriatic fundus digital photographing apparatus includes, but is not limited to, a desktop fundus camera, a portable fundus camera, or a mobile terminal-equipped fundus camera.
The vision damage degree evaluation system for cataract patients based on AI technology is also suitable for after cataract.
The invention has the beneficial effects that:
the invention provides a cataract patient vision damage degree evaluation system based on AI technology, which classifies and marks a mydriasis-free eye fundus image according to whether a patient has cataract, classifies and finishes classification of corrected vision damage degree of the eye fundus image marked with cataract, and gives diagnosis and treatment suggestions pertinently for vision damage patients with different degrees caused by cataract; the system utilizes the deep learning artificial intelligence system to evaluate the disease condition, constructs a diagnosis and treatment suggestion module, gives the right of obtaining eye images to the eye health examination of community hospitals or intelligent terminal users, but not all levels of ophthalmic medical units, is wider and more popular to some extent, also relieves the problems of time and labor waste and high price in examination of general patients, and realizes a promising community medical treatment and portable emerging medical solution.
Drawings
FIG. 1 is a schematic overall flow diagram of the present invention;
FIG. 2 is a schematic view of an information collection module of the present invention;
FIG. 3 is a schematic diagram of the Lens opacity Classification System III (LOCS) of the present invention;
FIG. 4 is a schematic view of each level of fundus images of the present invention;
the system comprises an information acquisition module, a 2-fundus image acquisition module, a 3-image identification module, a 4-image classification module, a 5-illness state evaluation module and a 6-diagnosis and treatment suggestion module.
Detailed Description
Examples
As shown in fig. 1, the present embodiment provides an AI technology-based cataract patient vision impairment degree evaluation system, which includes an information acquisition module 1, a fundusimage acquisition module 2, animage identification module 3, animage classification module 4, an illnessstate evaluation module 5, and a diagnosis andtreatment suggestion module 6;
as shown in fig. 2, the information collecting module 1 is used for collecting basic information of an individual user, and includes: name, sex, age, cataract surgery history, etc. Name, sex, age, etc. for personal data improvement. The information collection of the cataract surgery history comprises the answer of the question of whether cataract surgery exists or not or whether cataract surgery and other eye surgery exist or not, if the answer of the two questions is no, the question is 'lens eye', and if the answer of any question of the two questions is 'yes', the question is 'non-crystalline eye'. The opacification of the posterior capsule formed by the proliferation of residual cortex and lens epithelial cells after cataract extraction is called as posterior cataract (posterior cataract). Both cataracts, and secondary cataracts, affect the passage of light through the ocular refractive medium, causing a decrease in fundus imaging quality, resulting in a decrease in visual function. The eyegroundimage acquisition module 2 is used for acquiring the patient mydriasis-free eyeground image, and is used for photographing and checking the eyeground under the small pupil by the mydriasis-free eyeground photographing device, and the mydriasis-free eyeground digital photographing device can be a desktop eyeground photographing instrument, a portable eyeground photographing instrument or an eyeground photographing instrument matched with a mobile terminal and the like.
As shown in fig. 3 and 4, theimage identification module 4 is used for performing classification identification of 'whether cataract exists' on the mydriatic fundus image acquired by the fundusimage acquisition module 2 according to whether cataract exists in the patient; grading and marking the fundus image marked as 'cataract' according to the vision damage degree of the cataract patient; wherein, the visual impairment degree of the cataract patient is divided into five grades of marks according to the phacoelomorphism, which are respectively 1 grade, 2 grade, 3 grade, 4 grade and 5 grade, wherein the 1 grade represents the no/mild visual impairment of the visual impairment of more than or equal to 0.5, the 2 grade represents the no/mild visual impairment of more than 0.5, the 3 grade represents the moderate visual impairment of more than 0.3, the 4 grade represents the severe visual impairment of more than 0.05, and the 5 grade represents the blind of less than 0.05;
theimage classification module 4 is used for identifying and processing the mydriasis-free eye fundus image through a deep convolution neural network on the basis of grading identification of cataract and degree of cataract vision damage in the eye fundus image identified by theimage identification module 3 to obtain a deep learning model;
the deep convolutional neural network is densenert 121, and the specific steps of performing interpretation training by using the densenert 121 are as follows:
first, the experimental algorithm sets up:
adopting SGD as an optimization algorithm, and obtaining an initial learning rate (learning) corresponding to the algorithmg rate, lr) is set to 0.001, momentum is 0.9, weight decay is 5 × 10-5The iteration time epoch is 80, and the batch size batchsize is 64; a learning rate attenuation strategy is adopted in the training process: each iteration 20 times, the learning rate decays to one tenth of the original, expressed as:
lr ═ Lr (0.1 ═ epoch//20)), i.e., the formula is as follows
Lr＝lr×(0.1(k//20))
Wherein, the operator of integer division is obtained, namely the integer part (not including remainder) of the quotient is obtained, and k is the iteration number;
the Loss function used for the experiment was a Cross Entropy Loss function (Cross entry Loss):
wherein p isiAnd yiRespectively representing the prediction probability of the classification model predicted image as the ith class and the real label of the image, wherein n is the total number of the classified classes;
second, experimental environment:
in the experiment, a network model of the experiment is built by using a Pythrch deep learning framework, and the network model is trained on NVIDIA TITAN RTX GPUs with 24G video memory;
thirdly, data preprocessing:
the image size of the data set is uniformly scaled to 224 x 224 to meet the input requirement of the network model, meanwhile, in order to enhance the generalization capability of the model, the image is randomly rotated by 90 degrees and turned over in the horizontal or vertical direction, and the random probability is 0.5;
fourth, data set partitioning:
randomly dividing an original data set into a training set, a verification set and a test set, wherein the proportion of each part is 70%, 15% and 15%, respectively, after each training round, verifying the model by using the verification set, and after the training times are all completed, testing the final model after the training is completed by using the test set so as to evaluate the performance of the classification model;
the diseasecondition evaluation module 5 is used for acquiring a mydriasis-free eye fundus image of the patient through the eye fundusimage acquisition module 2 according to the deep learning model obtained by theimage classification module 4, and evaluating and grading the vision damage degree of the cataract patient;
the diseasecondition evaluation module 5 judges the collected mydriasis-free eye fundus images by using the established deep learning artificial intelligence system to obtain the classification of whether cataract exists and the vision damage degree grading;
the diagnosis andtreatment suggestion module 6 gives necessary diagnosis and treatment suggestions according to different degrees of the vision damage of the cataract patient obtained by the diseasecondition evaluation module 5, and suggests observation when the vision damage is grade 1 or no cataract exists; when the visual impairment isgrade 2, it is recommended that cataract surgery be considered according to the individual's living needs; the degree of visual impairment isgrade 3 or above, and patients are advised to seek medical advice in time to perform cataract surgery.
Claims (9)
1. The system for evaluating the eyesight damage degree of the cataract patient based on the AI technology is characterized by comprising an information acquisition module (1), an eyeground image acquisition module (2), an image identification module (3), an image classification module (4), an illness state evaluation module (5) and a diagnosis and treatment suggestion module (6);
the information acquisition module (1) is used for acquiring basic information of an individual user;
the eye fundus image acquisition module (2) is used for acquiring a mydriasis-free eye fundus image of a patient;
the image identification module (3) identifies whether the patient suffers from cataract or not according to the mydriatic eye fundus image acquired by the eye fundus image acquisition module (2); grading and marking the fundus image marked as 'cataract' according to the corrected visual impairment degree of the cataract patient;
the image classification module (4) is used for identifying and processing the mydriasis-free eye fundus image through a deep convolution neural network on the basis of grading identification of whether cataract exists or not and the vision damage degree of a cataract patient in the eye fundus image identified by the image identification module (3) to obtain a deep learning model;
the disease condition evaluation module (5) is used for acquiring a mydriasis-free eye fundus image of the patient through the eye fundus image acquisition module (2) according to the deep learning model obtained by the image classification module (4), and evaluating and grading the vision damage degree of the cataract patient.
2. The AI technology based cataract patient visual impairment evaluation system according to claim 1, wherein the image identification module (3) divides the fundus image into two stages according to the opacity of the crystalline lens or the opacity of the posterior capsule of the crystalline lens: cataract and no cataract respectively; the degree of visual impairment for patients with cataract is marked in five grades, i.e. 1 grade, 2 grade, 3 grade, 4 grade and 5 grade.
3. The AI-technology based vision impairment assessment system according to claim 2, wherein level 1 represents no/mild vision impairment of 0.5 or more, level 2 represents no/mild vision impairment of 0.5 or more and 0.3 or more, level 3 represents moderate vision impairment of 0.3 or more and 0.1 or more, level 4 represents severe vision impairment of 0.1 or more and 0.05 or less, and level 5 represents blindness of 0.05 or less.
4. The AI-technology-based vision impairment evaluation system of claim 3, wherein the diagnosis and treatment advice module (6) provides necessary diagnosis and treatment advice according to the cataract patients' vision impairment obtained by the disease evaluation module (5).
5. The AI technology based vision impairment evaluation system of claim 4, wherein the diagnosis and treatment recommendation module (6) determines whether cataract surgery is needed at the time of diagnosis based on the following criteria: assessment of visual impairment above grade 3 requires cataract surgery.
6. The AI technology based vision impairment assessment system of claim 5, wherein the deep convolutional neural network is densenet121 and the interpretation training using densenet121 comprises the following steps:
first, the experimental algorithm sets up:
SGD is adopted as an optimization algorithm, the initial learning rate (lr) corresponding to the algorithm is set to be 0.001, the momentum mean is 0.9, the weight attenuation degree is 5 multiplied by 10-5The iteration time epoch is 80, and the batch size is 64; a learning rate attenuation strategy is adopted in the training process: each iteration 20 times, the learning rate decays to one tenth of the original, expressed as:
lr ═ Lr (0.1 ═ epoch//20)), i.e., the formula is as follows
Lr＝lr×(0.1(k//20))
Wherein, the operator of integer division is obtained, namely the integer part (not including remainder) of the quotient is obtained, and k is the iteration number;
the Loss function used for the experiment was a Cross Entropy Loss function (Cross entry Loss):
wherein p isiAnd yiRespectively representing the prediction probability of the classification model predicted image as the ith class and the real label of the image, wherein n is the total number of the classified classes;
second, experimental environment:
in the experiment, a network model of the experiment is built by using a Pythrch deep learning framework, and the network model is trained on NVIDIA TITAN RTX GPUs with 24G video memory;
thirdly, data preprocessing:
the image size of the data set is uniformly scaled to 224 x 224 to meet the input requirement of the network model, meanwhile, in order to enhance the generalization capability of the model, the image is randomly rotated by 90 degrees and turned over in the horizontal or vertical direction, and the random probability is 0.5;
fourth, data set partitioning:
the original data set is randomly divided into a training set, a verification set and a test set, and the proportion of each part is 70%, 15% and 15% respectively.
7. The AI-technology based vision impairment evaluation system of claim 6, wherein during the testing procedure, after each training cycle, the model is verified by the verification set, and after the training cycle is completed, the final trained model is tested by the test set to evaluate the performance of the classification model.
8. The AI-technology-based vision impairment evaluation system for cataract patients according to claim 1, wherein the fundus image acquisition module (2) is used for performing digital photographic examination of the fundus with small pupil by using a digital photographic device of the fundus without mydriasis when acquiring the fundus image without mydriasis of the patient.
9. The AI-technology-based vision impairment evaluation system for cataract patients according to claim 8, wherein the non-mydriatic fundus digital camera is a fundus camera such as a desktop fundus camera, a portable fundus camera, or a mobile-terminal-equipped fundus camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110734838.3ACN113470815A (en) | 2021-06-30 | 2021-06-30 | AI technology-based cataract patient vision impairment degree evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110734838.3ACN113470815A (en) | 2021-06-30 | 2021-06-30 | AI technology-based cataract patient vision impairment degree evaluation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113470815Atrue CN113470815A (en) | 2021-10-01 |
Family
ID=77874361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110734838.3APendingCN113470815A (en) | 2021-06-30 | 2021-06-30 | AI technology-based cataract patient vision impairment degree evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113470815A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116092665A (en)* | 2022-12-14 | 2023-05-09 | 中南大学湘雅医院 | An artificial intelligence-based eye screening diagnosis and treatment system |
| CN120072278A (en)* | 2025-04-28 | 2025-05-30 | 江西展群科技有限公司 | Data processing method and system based on cataract detection |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030058405A1 (en)* | 2001-07-23 | 2003-03-27 | Cornsweet Tom N. | Instruments and methods for examining and quantifying cataracts |
| CN109102885A (en)* | 2018-08-20 | 2018-12-28 | 北京邮电大学 | The cataract automatic grading method combined based on convolutional neural networks with random forest |
| CN111199794A (en)* | 2018-11-19 | 2020-05-26 | 复旦大学附属眼耳鼻喉科医院 | A surgical intelligent decision-making system suitable for high myopia cataract and its establishment method |
| CN112053780A (en)* | 2020-08-24 | 2020-12-08 | 宁波市眼科医院 | Artificial intelligence cataract screening referral system based on eye ground picture |
| CN112220445A (en)* | 2020-09-29 | 2021-01-15 | 温州医科大学附属眼视光医院 | Mobile terminal-based cataract and after cataract analysis system and device |
| US20210035689A1 (en)* | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
- 2021
- 2021-06-30CNCN202110734838.3Apatent/CN113470815A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030058405A1 (en)* | 2001-07-23 | 2003-03-27 | Cornsweet Tom N. | Instruments and methods for examining and quantifying cataracts |
| US20210035689A1 (en)* | 2018-04-17 | 2021-02-04 | Bgi Shenzhen | Modeling method and apparatus for diagnosing ophthalmic disease based on artificial intelligence, and storage medium |
| CN109102885A (en)* | 2018-08-20 | 2018-12-28 | 北京邮电大学 | The cataract automatic grading method combined based on convolutional neural networks with random forest |
| CN111199794A (en)* | 2018-11-19 | 2020-05-26 | 复旦大学附属眼耳鼻喉科医院 | A surgical intelligent decision-making system suitable for high myopia cataract and its establishment method |
| CN112053780A (en)* | 2020-08-24 | 2020-12-08 | 宁波市眼科医院 | Artificial intelligence cataract screening referral system based on eye ground picture |
| CN112220445A (en)* | 2020-09-29 | 2021-01-15 | 温州医科大学附属眼视光医院 | Mobile terminal-based cataract and after cataract analysis system and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116092665A (en)* | 2022-12-14 | 2023-05-09 | 中南大学湘雅医院 | An artificial intelligence-based eye screening diagnosis and treatment system |
| CN116092665B (en)* | 2022-12-14 | 2023-11-03 | 中南大学湘雅医院 | Ophthalmic screening diagnosis and treatment system based on artificial intelligence |
| CN120072278A (en)* | 2025-04-28 | 2025-05-30 | 江西展群科技有限公司 | Data processing method and system based on cataract detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Keenan et al. | DeepLensNet: deep learning automated diagnosis and quantitative classification of cataract type and severity | |
| Subramanian et al. | Classification of retinal oct images using deep learning | |
| CN110013216B (en) | Artificial intelligence cataract analysis system | |
| CN111700582A (en) | A diagnostic system for common ocular surface diseases based on smart terminals | |
| Pratap et al. | Efficient network selection for computer-aided cataract diagnosis under noisy environment | |
| Ram et al. | The relationship between Fully Connected Layers and number of classes for the analysis of retinal images | |
| CN110211686A (en) | A kind of high myopia cataract intraocular lens precisely select system | |
| 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 | |
| Triyadi et al. | Deep learning in image classification using vgg-19 and residual networks for cataract detection | |
| CN113854957A (en) | Artificial intelligence diopter accurate measurement method based on eye image | |
| CN214484464U (en) | Cataract and Cataract Analysis System and Device Based on Mobile Terminal | |
| Shojol et al. | Enhanced convolutional neural networks for early detection and classification of ophthalmic diseases | |
| Upadhyaya et al. | Diagnostic performance of the offline Medios artificial intelligence for glaucoma detection in a rural tele-ophthalmology setting | |
| CN111259743B (en) | Training method and system for myopia image deep learning recognition model | |
| Uddin et al. | A novel deep ensemble learning approach to predict eye diseases from oct images | |
| Nagaraj et al. | A comparative analysis of retinal disease image classification for OCT using deep learning techniques | |
| Alipour et al. | PERSIAN Eye Cohort Study (PECS): Design, methodology | |
| CN215534276U (en) | AI-based visual impairment assessment system for cataract patients | |
| CN116798602A (en) | An intelligent cataract diagnosis and grading system based on the international gold standard LOCS III grading system | |
| Burle et al. | Advances in glaucoma detection through machine learning technology | |
| Suwandi et al. | A Systematic Literature Review: Diabetic Retinopathy Detection Using Deep Learning | |
| Suryavanshi et al. | Unlocking Insights: Diseases Recognition in the Human Eye Using CNN and Random Forest | |
| TWI871882B (en) | Medical image processing system, method, and computer readable medium thereof | |
| Kuriakose | Clinical Insights and Examination Techniques in Ophthalmology |
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:20230424 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 | Application publication date:20211001 |