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

Mobile phone terminal diabetic retinopathy screening APP based on deep learning

A retinopathy and deep learning technology, applied in the field of AI technology products, can solve problems such as low data security and poor real-time performance, and achieve the effects of reducing the sense of delay, low product cost and high efficiency

Pending Publication Date: 2020-06-26
苏州爱可尔智能科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The main disadvantage of this method is poor real-time performance and low data security

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
  • Mobile phone terminal diabetic retinopathy screening APP based on deep learning
  • Mobile phone terminal diabetic retinopathy screening APP based on deep learning
  • Mobile phone terminal diabetic retinopathy screening APP based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] A mobile diabetic retinopathy screening APP based on deep learning. The main content includes 1. The deep learning model is compressed and pruned and then migrated to the mobile terminal, which achieves real-time (less than 2-second response) operation on the mobile terminal. speed. 2 The use of image processing technology for fundus photos on mobile phones. 3. The sugar screening APP of the present invention provides a very easy-to-use interface design. 4 The mobile terminal generates a screening report.

[0044] The technical process of the technical solution of the present invention is as follows:

[0045] 1. Training of deep learning model: the principle of model training is as follows: figure 1 As shown, the data input includes the original fundus photo and the input target vector. The fundus photo is calculated through the deep convolu...

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 discloses a mobile phone terminal diabetic retinopathy screening APP based on deep learning. The technical process is as follows: 1) training a deep learning model; 2) pruning and compressing the trained deep learning model; 3) deploying the compressed model to a mobile phone end, embedding the compressed model into mobile phone end APPs of Android and IOS, and migrating an image processing algorithm to the mobile phone end. The mobile phone terminal diabetic retinopathy screening APP based on deep learning provided by the invention has the advantages that real-time fundus photoanalysis is focused on, and real-time intelligent processing and execution of local services can be better supported.

Description

technical field [0001] The invention relates to an AI technology product combined with deep learning and edge computing, which is applied to the screening of diabetic retinopathy in fundus photos. Specifically, it relates to a mobile terminal diabetic retinopathy screening APP based on deep learning. Background technique [0002] The present invention provides a mobile terminal diabetic retinopathy screening APP based on deep learning, which is used to complete the screening of diabetic retinopathy for fundus photos, which can be completed in real time on the mobile terminal, image processing, deep learning model All the work of reasoning and screening result feedback. [0003] Classified from the perspective of data service methods, this invention belongs to the data service method of edge computing. Edge computing is a data service method relative to cloud computing. Cloud Computing Since the deep learning (artificial intelligence) model is deployed in the cloud, the da...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G16H50/80G16H15/00G06N3/04G06N3/08A61B3/12A61B3/14A61B3/00
CPCG16H50/80G16H15/00G06N3/082A61B3/12A61B3/14A61B3/0025G06N3/045
Inventor 方倩
Owner 苏州爱可尔智能科技有限公司
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