CN112599244A - Intraocular lens refractive power calculation system based on machine learning - Google Patents
Intraocular lens refractive power calculation system based on machine learning Download PDFInfo
- Publication number
- CN112599244A CN112599244A CN202011480616.5A CN202011480616A CN112599244A CN 112599244 A CN112599244 A CN 112599244A CN 202011480616 A CN202011480616 A CN 202011480616A CN 112599244 A CN112599244 A CN 112599244A
- Authority
- CN
- China
- Prior art keywords
- intraocular lens
- refractive power
- module
- machine learning
- lens refractive
- 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
- G16H50/30—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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61F—FILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
- A61F2/00—Filters implantable into blood vessels; Prostheses, i.e. artificial substitutes or replacements for parts of the body; Appliances for connecting them with the body; Devices providing patency to, or preventing collapsing of, tubular structures of the body, e.g. stents
- A61F2/02—Prostheses implantable into the body
- A61F2/14—Eye parts, e.g. lenses, corneal implants; Implanting instruments specially adapted therefor; Artificial eyes
- A61F2/16—Intraocular lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Ophthalmology & Optometry (AREA)
- Epidemiology (AREA)
- Pathology (AREA)
- Computational Linguistics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Mathematical Analysis (AREA)
- Algebra (AREA)
- Mathematical Optimization (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Cardiology (AREA)
- Computational Mathematics (AREA)
- Transplantation (AREA)
- Heart & Thoracic Surgery (AREA)
- Vascular Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Prostheses (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention relates to a machine learning-based intraocular lens refractive power calculation system, which comprises: the device comprises a prediction model, an input module, a calculation module, an additional module and an output module. The calculation module is used for acquiring the refractive power of an Intraocular Lens (IOL) to be implanted by taking the target equivalent spherical power as an ideal value and taking preoperative information of a cataract patient as input based on a prediction model; the additional module is used for providing a plurality of different simulated intraocular lens refractive powers to the calculating module, and the calculating module generates the postoperative optometry equivalent spherical powers corresponding to the different simulated intraocular lens refractive powers. The method has the advantages that the artificial intelligence active learning data characteristics are fully utilized, the error calculation capability is automatically optimized, the refractive power of the artificial lens to be implanted in the cataract surgery is accurately calculated, the eyeball biological parameters of all dimensions are matched, and the eyeball prediction accuracy of the extreme eyeball biological parameters is higher.
Description
Technical Field
The invention relates to the field of artificial intelligence medical data analysis, in particular to an intraocular lens refractive power calculation system based on machine learning, which can calculate the refractive power of an implanted intraocular lens and the postoperative equivalent sphere power of a patient through input preoperative information of a cataract patient and information of an intraocular lens to be implanted.
Background
Cataract surgery is converted from vision recovery surgery to refractive surgery, the refractive power of the artificial lens suitable for cataract patients is accurately calculated, and accurate prediction of the postoperative refractive state is an extremely important step. In 2019, a multicenter large sample study showed that there was 17.9% of patients with prediction errors exceeding 0.5D. The influence on the refractive power of the intraocular lens is mainly derived from two aspects, namely an intraocular lens calculation formula and biological measurement of an eyeball. Currently, mechanisms and persons in the field can accurately detect eyeball parameters through various accurate measurement means, and intraocular lens calculation formulas are still the main sources of prediction errors.
Hagis, SRK/T, Hoffer Q, Barrett Universal II and the like are widely used intraocular lens calculation formulas at present, and are obtained by combining clinical data regression on the basis of a theoretical formula derived from a human eye geometric optical model. The range of the applicable ocular parameter values is relatively fixed, and the calculation accuracy is reduced for the intraocular lens power measurement of eyeballs with different biological parameter values, especially for extreme biological parameters such as ultra-long/short ocular axis, steep corneal curvature, deep/shallow anterior chamber and the like. From the using population, the cornea diameter of the national eyeball is relatively small, the central cornea thickness is thin, and if an intraocular lens formula established by using the ocular data of the national eyeball can be established, the calculation result can be favorably optimized, and the accuracy is further improved.
In recent years, the development and rise of artificial intelligence provide potential solutions for solving the problems. Machine learning is a large field of artificial intelligence, and is widely applied to research for assisting disease diagnosis and decision making. The CC-cruiser developed by Liuyi Zhi professor team screens congenital cataract patients with the same accuracy as that of a deep ophthalmologist. In the field of cataract, machine learning is mainly focused on image recognition based cataract diagnosis and grading, and prediction of posterior cataract. However, contrary to the booming image diagnosis and grading techniques, artificial intelligence has been sought in the application of cataract data mining. The artificial intelligence has the capability of mapping original data to a high-dimensional feature space in a nonlinear way, and can explore deeper and more complex laws among data, so that the artificial intelligence has a wide application prospect in calculating the refractive power of the artificial lens.
Currently, only two types of artificial lens formulas using artificial intelligence are available for clinical use. Hill-RBF is an artificial intelligence regression formula that requires the use of specific inspection instruments and intraocular lenses and can only be applied to ocular parameter values within a specified range beyond which the computational accuracy decreases. The Kane formula is constructed based on theoretical optics and clinical data regression, and the calculation accuracy is further optimized by combining artificial intelligence. The formula is also more demanding on the inspection instrument and does not further describe the artificial intelligence technique used. Although the artificial intelligence intraocular lens formula can autonomously optimize calculation results of different biological parameters through data learning, the formula is limited by domestic medical conditions, and currently, domestic mainstream ocular biological parameter inspection instruments such as ultrasonography and IOLMaster cannot meet the optimal requirements of the formula.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention aims to provide a machine learning-based intraocular lens refractive power calculation system.
In order to achieve the purpose, the invention provides the following technical scheme:
a machine learning based intraocular lens refractive power calculation system comprising:
the prediction model is generated by training by applying a machine learning algorithm by taking the cataract patient database as a training sample and the preoperative information of the training sample and the equivalent sphere power of postoperative medical optometry as training attributes;
the input module is used for inputting preoperative information of the cataract patient and target equivalent sphere power;
the calculation module is used for acquiring the refractive power of the artificial lens to be implanted by taking the target equivalent spherical power as an ideal value and taking the preoperative information of the cataract patient as input data based on the prediction model;
the additional module is used for providing a plurality of different simulated intraocular lens refractive powers to the calculating module, and the calculating module generates predicted equivalent spherical powers corresponding to the different simulated intraocular lens refractive powers;
and the output module is used for outputting the plurality of predicted equivalent spherical powers which are close to the target equivalent spherical power and are generated by the calculation module and the refractive powers of the corresponding artificial lenses.
The training sample is based on a cataract patient database, comprises cataract patient sample data and label information, and is divided into a training set and a testing set according to the proportion.
The sample data of the cataract patient is identity information, demographic information, ocular biological parameters and artificial lens information.
The cataract patient label information is equivalent spherical power of the same patient after cataract operation of the same eye.
The preoperative information of the cataract patient comprises demographic information of the cataract patient, ocular biological parameters and information of an artificial lens to be implanted.
The ocular biological parameters include, but are not limited to, ocular identity, ocular axis, corneal curvature, and anterior chamber depth
The ocular biological parameters can be increased by the parameters of total corneal astigmatism, lens thickness and the like with the updating of the inspection equipment.
The machine learning algorithm can fit label information through nonlinear change of sample data, the training set is used for adjusting weights of different parameters in the algorithm to achieve optimal fitting, and the testing set is used for carrying out accuracy inspection on the trained algorithm model.
The add-on module sequentially produces a plurality of different values of simulated intraocular lens refractive power.
The calculation module is used for predicting the postoperative optometry equivalent sphere power corresponding to the intraocular lens refractive power based on the input preoperative information of the cataract patient and in combination with the simulated intraocular lens refractive power input by the additional module.
The input module is provided with an optimization input module for inputting data of a main surgeon, and the calculation module optimizes the predicted parameters of the intraocular lens based on the input data of the main surgeon.
The invention has the beneficial effects that:
the method can fully utilize the characteristics of artificial intelligence active learning data, autonomously optimize the error calculation capacity, accurately calculate the refractive power of the artificial lens to be implanted in the cataract surgery, match the biological parameters of the eyeballs with various dimensions, and have higher eyeball prediction accuracy on the biological parameters of the extreme eyeballs.
The method can discriminate the regions and improve the accuracy by optimizing the population based on the regions, for example, training and optimizing the data of Chinese people, is more suitable for the eyeball of Chinese people and achieves higher accuracy. Meanwhile, the threshold of the inspection equipment is reduced, the method is suitable for various eyeball biological parameter inspection equipment such as IOLMMaster, A-super and the like, and is suitable for use and popularization in most domestic and foreign areas.
The invention provides online calculation and optimization for users by depending on an internet platform, provides accurate and personalized artificial lens calculation for patients and surgeons nationwide and worldwide, makes up the difference of diagnosis and treatment levels of different medical institutions among areas, is beneficial to improving the medical environment and is beneficial to the patients.
The invention can continuously optimize the prediction model along with the increase of clinical use, thereby further improving the accuracy.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In addition, the descriptions related to "first", "second", etc. in the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
A machine learning based intraocular lens refractive power calculation system comprising:
1. the prediction model is generated by taking a cataract patient database as a training sample and applying machine learning algorithm training;
the training sample is established on the basis of a database formed by cataract surgery patient sample data and label information, and the database is divided into a training set and a testing set according to a certain proportion (for example, 8: 2).
The sample data of the cataract surgery patient comprises identity information (such as a patient hospitalization number, a medical record number and the like), demographic information (such as age, gender and the like), ocular biological parameters (such as an eye type, an eye axis, corneal curvature, anterior chamber depth and the like), surgery information (such as an operating doctor, the eye type, a surgery mode and the like) and intraocular lens information (such as the eye type, the model, an A constant, a diopter number and the like). And the label information is corresponding to the sample data, and the label information refers to the equivalent spherical power of the same patient for the same-eye cataract postoperative medical optometry.
And in addition, the patient identity information is used for matching and linking the sample data and the label information to construct a total database. The total database is divided into training sets and test sets in a certain ratio (e.g., 8: 2).
Each piece of data in the overall database represents only one of the patient's eye information, including patient sample data (identity information, age, gender, identity, axis, corneal curvature, anterior chamber depth, procedure, iol model, a-constant, iol power) and patient label information (postoperative medical prescription equivalent sphere power).
The purpose of calculating the label information of the patient through the sample data of the patient is achieved by using a machine learning model, namely calculating the equivalent sphere power of the postoperative medical optometry. The method comprises the following two steps:
training: the machine learning model is trained using a training set.
Establishing a machine learning model by using a decision tree algorithm or a random forest algorithm → the model can calculate equivalent sphere power (predicted value) for each sample datum → calculate the error between the predicted value and corresponding label information → optimize the internal parameters of the model → finally generate the machine learning model with the minimum overall error under the training set.
And (3) testing: testing the finally generated machine learning model by using a test set
Each piece of sample data in the test set enters a model → the model calculates equivalent sphere power (predicted value) → calculates error between the predicted value and corresponding label information → the standard of test passing is as follows: the prediction accuracy of the model in different eye axis length subgroups, cornea curvature subgroups and anterior chamber depth subgroups is improved compared with the current common intraocular lens calculation formula.
Brief introduction to the Algorithm
The decision tree model is a tree structure model that is applied to classification and regression. The regression decision tree includes a root node, an internal node, and a leaf node. The root node represents the sample corpus, the internal nodes correspond to an attribute test, and the leaf nodes represent decision values. And starting from the root node, performing attribute test on the data to be tested and the internal nodes, entering the next internal node according to the attribute test result until reaching the leaf node, and outputting a corresponding decision value. And traversing all the input variables by the regression tree, and determining the optimal division characteristics and the optimal division points of the input samples by the least squares of the real values and the predicted values.
The process of using the regression decision tree is: and continuously performing attribute test on the sample to be predicted from the root node, selecting an output branch according to a test result, entering a next attribute test node until reaching a leaf node, and outputting a decision value corresponding to the leaf node.
Random forests are integrated machine learning models based on decision trees. And generating different sub training sets in the test set by a bootstrap sampling method, randomly selecting different feature sets, and generating a plurality of different regression decision trees, wherein the average value of the decision values of all the regression decision trees is the predicted value of the random forest.
The embodiment of the invention provides a training method for an intraocular lens refractive power calculation model, wherein the prediction model is a machine learning model, such as an artificial neural network, a support vector machine and the like, and the model is feasible.
2. The input module is used for inputting cataract patient information parameters and target equivalent sphere power; the input module can be designed based on the internet, and can also realize batch import of data by utilizing an internet platform, wherein the preoperative information of the cataract patient comprises demographic information (such as age, sex and the like), ocular biological parameters (such as eye type, eye axis, corneal curvature, anterior chamber depth and the like) and artificial lens information (such as model and A constant), wherein the user can also input target equivalent spherical power, such as "-1D", according to clinical requirements, and if the user does not input the target equivalent spherical power, the target equivalent spherical power is defaulted to 0D ".
3. And the calculating module is used for predicting the corresponding postoperative equivalent spherical power by taking the target equivalent spherical power as an ideal value, taking the preoperative information of the cataract patient as input data and combining the simulated intraocular lens refractive power input by the additional module based on the prediction model.
The preoperative information of the cataract patient comprises demographic information of the cataract patient, ocular biological parameters and information of an artificial lens to be implanted.
The information of the intraocular lens to be implanted is not limited to a specific type of intraocular lens, and according to the use requirement, a user can select various types of intraocular lenses at one time so as to achieve the purpose of simultaneously calculating and outputting the refractive power corresponding to the selected intraocular lens.
4. The additional module is used for providing a plurality of different simulated intraocular lens refractive powers to the calculating module, and the calculating module generates predicted equivalent spherical powers corresponding to the different simulated intraocular lens refractive powers; the add-on modules in turn produce a simulated intraocular lens refractive power of-10 to +30D (extensible range if necessary) and 0.5D steps (step size reducible if necessary).
5. And the output module is used for outputting the plurality of predicted optometry equivalent spherical powers which are close to the target equivalent spherical power and are generated by the calculation module and the corresponding refractive powers of the artificial lens.
By generating a plurality of calculation results close to the target equivalent spherical power, the doctor can select different intraocular lens refractive powers according to the eye state of the patient and the requirements of the patient so as to achieve the purpose of more accurate matching.
Aiming at the requirements of different regions and different main doctors, the system also provides the function of individually optimizing the main knife parameters. The input module is additionally provided with a data batch import module for importing the historical data of the doctor. Based on the historical data imported in batches, the calculation module can optimize the parameters (such as A constant) of a specific main knife or a specific artificial lens in a specific area, and provide more accurate and personalized calculation services.
The specific operation is as follows:
patient data including pre-operative ocular biological examination results, implanted intraocular lens type and intraocular lens refractive power, target post-operative equivalent spherical power, and actual post-operative equivalent spherical power is collected.
Calculating prediction error = true-target;
the data is entered into a model, parameters (such as A constants) are reversely optimized by using the formed artificial lens calculation model, the overall prediction error is minimized, and the optimized parameters (such as A constants) of the artificial lens are obtained.
In addition, the method has the characteristic of actively learning the data characteristics. Therefore, the amount and diversity of the training database is very important to the accuracy of the system prediction. To further expand the data volume, the system will collect the input data and perform a continuous follow-up. When the reliable follow-up data volume reaches a certain level, the optimization calculation model is returned, and the accuracy is further improved.
Meanwhile, the system can rely on an internet platform to acquire cataract patient data of different regions, races and biological parameters of different eyeballs, namely, the diversity of a training database is increased, so that a prediction model of the system is more accurate.
In order to avoid low-quality data from entering system optimization, noise is caused to system training, and the reliability of a training sample is improved, the system has a data discrimination function. The system training optimization phase may be entered only if the external data meets the data quality requirements. And if the overall accuracy of the system is reduced after the newly-included data set is trained, the system rejects the part of the training data set so as to avoid negative optimization of the system.
The examples should not be construed as limiting the present invention, but any modifications made based on the spirit of the present invention should be within the scope of protection of the present invention.
Claims (10)
1. A machine learning based intraocular lens refractive power calculation system characterized by: it includes:
the prediction model is generated by training by applying a machine learning algorithm by taking the cataract patient database as a training sample and the preoperative information of the training sample and the equivalent sphere power of postoperative medical optometry as training attributes;
the input module is used for inputting preoperative information of the cataract patient and target equivalent sphere power;
the calculation module is used for acquiring the refractive power of the artificial lens to be implanted by taking the target equivalent spherical power as an ideal value and taking the preoperative information of the cataract patient as input data based on the prediction model;
the additional module is used for providing a plurality of different simulated intraocular lens refractive powers to the calculating module, and the calculating module generates predicted equivalent spherical powers corresponding to the different simulated intraocular lens refractive powers;
and the output module is used for outputting the plurality of predicted equivalent spherical powers which are close to the target equivalent spherical power and are generated by the calculation module and the refractive powers of the corresponding artificial lenses.
2. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the training sample is based on a cataract patient database, comprises cataract patient sample data and label information, and is divided into a training set and a testing set according to the proportion.
3. The machine learning based intraocular lens refractive power calculation system of claim 2, wherein: the sample data of the cataract patient is identity information, demographic information, ocular biological parameters and artificial lens information.
4. The system of claim 3 in which the machine learning based intraocular lens refractive power calculation system comprises: the cataract patient label information is equivalent spherical power of the same patient after cataract operation of the same eye.
5. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the preoperative information of the cataract patient comprises demographic information of the cataract patient, ocular biological parameters and information of an artificial lens to be implanted.
6. A machine learning based intraocular lens refractive power calculation system according to claim 3 or 4 or 5 wherein: the ocular biological parameters include the eye identity, eye axis, corneal curvature, and anterior chamber depth.
7. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the machine learning algorithm can fit label information through nonlinear change of sample data, the training set is used for adjusting weights of different parameters in the algorithm to achieve optimal fitting, and the testing set is used for carrying out accuracy inspection on the trained algorithm model.
8. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the add-on module sequentially produces a plurality of different values of simulated intraocular lens refractive power.
9. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the calculation module is used for predicting the postoperative optometry equivalent sphere power corresponding to the intraocular lens refractive power based on the input preoperative information of the cataract patient and in combination with the simulated intraocular lens refractive power input by the additional module.
10. The system for calculating intraocular lens refractive power based on machine learning of claim 1, wherein: the input module is provided with an optimization input module for inputting data of a main surgeon, and the calculation module optimizes the predicted parameters of the intraocular lens based on the input data of the main surgeon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011480616.5A CN112599244A (en) | 2020-12-16 | 2020-12-16 | Intraocular lens refractive power calculation system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011480616.5A CN112599244A (en) | 2020-12-16 | 2020-12-16 | Intraocular lens refractive power calculation system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112599244A true CN112599244A (en) | 2021-04-02 |
Family
ID=75196529
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011480616.5A Pending CN112599244A (en) | 2020-12-16 | 2020-12-16 | Intraocular lens refractive power calculation system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112599244A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202499A (en) * | 2021-06-22 | 2022-03-18 | 深圳盛达同泽科技有限公司 | Refractive information measuring method, device and computer readable storage medium |
| CN117238514A (en) * | 2023-05-12 | 2023-12-15 | 中山大学中山眼科中心 | Intraocular lens refractive power prediction method, system, equipment and medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110101504A (en) * | 2018-08-02 | 2019-08-09 | 复旦大学附属眼耳鼻喉科医院 | It can adjust safety goggles suitable for high myopia cataract post-operative refractive degree |
| CN110211686A (en) * | 2019-06-11 | 2019-09-06 | 复旦大学附属眼耳鼻喉科医院 | A kind of high myopia cataract intraocular lens precisely select system |
| CN111653364A (en) * | 2020-07-09 | 2020-09-11 | 王世明 | Intraocular lens refractive power calculation method and device |
| CN111796418A (en) * | 2020-07-30 | 2020-10-20 | 杭州明视康眼科医院有限公司 | Diopter calculation method of astigmatic intraocular lens (Toric IOL) |
-
2020
- 2020-12-16 CN CN202011480616.5A patent/CN112599244A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110101504A (en) * | 2018-08-02 | 2019-08-09 | 复旦大学附属眼耳鼻喉科医院 | It can adjust safety goggles suitable for high myopia cataract post-operative refractive degree |
| CN110211686A (en) * | 2019-06-11 | 2019-09-06 | 复旦大学附属眼耳鼻喉科医院 | A kind of high myopia cataract intraocular lens precisely select system |
| CN111653364A (en) * | 2020-07-09 | 2020-09-11 | 王世明 | Intraocular lens refractive power calculation method and device |
| CN111796418A (en) * | 2020-07-30 | 2020-10-20 | 杭州明视康眼科医院有限公司 | Diopter calculation method of astigmatic intraocular lens (Toric IOL) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114202499A (en) * | 2021-06-22 | 2022-03-18 | 深圳盛达同泽科技有限公司 | Refractive information measuring method, device and computer readable storage medium |
| CN117238514A (en) * | 2023-05-12 | 2023-12-15 | 中山大学中山眼科中心 | Intraocular lens refractive power prediction method, system, equipment and medium |
| CN117238514B (en) * | 2023-05-12 | 2024-05-07 | 中山大学中山眼科中心 | Intraocular lens refractive power prediction method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7841720B2 (en) | Methods of obtaining ophthalmic lenses providing the eye with reduced aberrations | |
| EP1943984B1 (en) | Method for designing ophthalmic lenses providing the eye with reduced aberrations | |
| Canovas et al. | Customized eye models for determining optimized intraocular lenses power | |
| JP6672529B2 (en) | Apparatus and computer program for determining predicted subjective refraction data or predicted correction value | |
| US8998415B2 (en) | Methods of obtaining ophthalmic lenses providing the eye with reduced aberrations | |
| AU2001263942A1 (en) | Methods of obtaining ophthalmic lenses providing the eye with reduced aberrations | |
| CN112599244A (en) | Intraocular lens refractive power calculation system based on machine learning | |
| CN112185564B (en) | Ophthalmic disease prediction method based on structured electronic medical record and storage device | |
| Burwinkel et al. | Physics-aware learning and domain-specific loss design in ophthalmology | |
| Kommineni et al. | Comparison of total keratometry with corneal power measured by optical low-coherence reflectometry and placido-dual Scheimpflug system | |
| CN114300136A (en) | Artificial intelligence assisted and optimized high myopia intraocular lens power calculator | |
| CN112700863A (en) | Method for accurately evaluating diopter based on Scheimpflug anterior segment morphology and application | |
| Castillo-Cabrera et al. | Proposal for a tool for the calculation of toric intraocular lens using multivariate regression | |
| US20240081640A1 (en) | Prediction of iol power | |
| US20230148857A1 (en) | Methods of Automated Determination of Parameters for Vision Correction | |
| ÇİFTCİ | ARTIFICIAL INTELLIGENCE FOR CATARACT | |
| US20230148859A1 (en) | Prediction of iol power | |
| US20230009821A1 (en) | Evaluation and control system for cornea and intraocular refractive surgery | |
| RU2791204C1 (en) | Method for determining the optical power of an intraocular lens using an artificial neural network | |
| CN115101196A (en) | Special intraocular lens degree calculation software for high myopia based on machine learning | |
| Li | Artificial Intelligence-Based Clinical Decision-Making System for Cataract Surgery | |
| Shin et al. | Code-Free Machine Learning Approach for EVO-ICL Vault Prediction: A Retrospective Two-Center Study | |
| Wang et al. | Artificial Intelligence in Refractive Surgery | |
| Keshavarz et al. | AI-Driven Keratoconus Detection: Integrating Medical Insights for Enhanced Diagnosis | |
| CN117976205A (en) | Method and software for calculating intraocular lens power of malformed eye of Marfan syndrome |
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 |