Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent orthokeratology lens selection system and method based on big data and deep learning

An orthokeratology lens and deep learning technology, applied in neural learning methods, optics, optical components, etc., can solve problems affecting user experience, cross infection, corneal epithelial damage, etc.

Pending Publication Date: 2020-08-18
BEIJING TONGREN HOSPITAL AFFILIATED TO CAPITAL MEDICAL UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the accuracy of orthokeratology lens parameters obtained in this way largely depends on the fitting technology and experience of doctors or optometrists; at the same time, the user experience is affected by multiple try-ins, and it may be caused by multiple lenses. Taking off and wearing for the first time can cause corneal epithelial damage and even cross-infection, which should be paid more attention to during the epidemic

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent orthokeratology lens selection system and method based on big data and deep learning
  • Intelligent orthokeratology lens selection system and method based on big data and deep learning
  • Intelligent orthokeratology lens selection system and method based on big data and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The present invention provides an intelligent orthokeratology lens selection method based on big data and deep learning, such as figure 1 shown, including the following steps:

[0033] S1: Data collection:

[0034] Collecting lens model data and its corresponding historical corneal data, and constructing a training set, the lens model data including lens brand and corresponding lens parameters;

[0035] S2: Data processing:

[0036] performing dimensionality reduction on the training set by at least one dimensionality reduction algorithm, the dimensionality reduction algorithm including but not limited to PCA theory;

[0037] The training set after dimensionality reduction is trained by at least one learning algorithm to establish a model recognition data model. The algorithm includes but is not limited to known machine learning algorithms, such as neural network algorithms, Markov algorithms, etc., and neural Convolutional neural network algorithm in network algorit...

Embodiment 2

[0061] An intelligent orthokeratology lens selection method based on big data and deep learning is different from Embodiment 1 in that, as shown in Figure 5, the selection method also includes the following steps:

[0062] S4: Simulation prediction:

[0063] Part of the training set after dimension reduction is performed by at least one learning algorithm, a prediction model is established, the identified lens model data and actual cornea data are input into the prediction model, and the predicted corrected cornea data is output, wherein the historical cornea The data also includes corrected corneal data after the patient wears orthokeratology lenses, and the corrected corneal data includes corrected corneal e value, corrected corneal k value, corrected corneal Sag value, corrected corneal diameter, corrected corneal thickness, corrected hyperopia or myopia degree, To correct one or more of the astigmatism degrees, the algorithm includes but is not limited to known machine lea...

Embodiment 3

[0066] An intelligent orthokeratology lens selection system based on big data and deep learning, such as Image 6 As shown, including the following parts:

[0067] Data collection module 1, is used for collecting lens model data and its corresponding historical corneal data, and constructs training set, and described lens model data comprises lens brand and corresponding lens parameter;

[0068] The data processing module 2 is used to reduce the dimensionality of the training set by at least one dimensionality reduction algorithm, and train the dimensionality-reduced training set by at least one learning algorithm to establish a model identification data model;

[0069] The data identification module 3 is used to input the actual cornea data into the model identification data model, and after the verification is completely passed, output the determined lens model data; when part of the verification is passed, each parameter in the actual cornea data is randomly divided into at...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention belongs to the technical field of orthokeratology lenses, and particularly relates to an intelligent orthokeratology lens selection system and method based on big data and deep learning.The invention provides a novel intelligent orthokeratology lens selection system and method based on big data and deep learning. According to the intelligent orthokeratology lens selection system andmethod based on big data and deep learning, machine learning is carried out through lens model data and corresponding historical corneal data, and a model identification data model is constructed; the lens model of the shaping lens is identified through the model identification data model based on the actual cornea data, the determined lens model data is output after verification is completely passed, and identification verification is performed in a gradient and weighting mode after verification is partially passed, so that the purpose of rapidly, accurately and stably identifying the lens model data is achieved.

Description

technical field [0001] The invention belongs to the technical field of orthokeratology lenses, in particular to an intelligent orthokeratology lens selection system and method based on big data and deep learning. Background technique [0002] Orthokeratology lenses originated in the United States. They are rigid corneal contact lenses similar to contact lenses. Wearing them during sleep at night can flatten the central corneal curvature and steepen the peripheral areas. It can not only correct the refractive state of the central retina, At the same time, it can correct the hyperopic defocus of the peripheral retina, so as to effectively control the development of myopia in children. At present, the way of fitting orthokeratology lenses is that the doctor or optometrist manually conducts multiple try-in and fitting evaluations on the user to determine the best orthokeratology lens parameters, and then orders the orthokeratology lenses. system and processing. However, the ac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06N3/04G06N3/08G02C7/04G02C7/02
CPCG06N3/08G02C7/047G02C7/024G06N3/045G06F18/213G06F18/2135G06F18/214Y02P90/30
Inventor 王开杰宋红欣
Owner BEIJING TONGREN HOSPITAL AFFILIATED TO CAPITAL MEDICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com