Unlock instant, AI-driven research and patent intelligence for your innovation.

Retinopathy image type recognition method, device and storage medium

A retinopathy and image type technology, applied in the field of communication, can solve the problems of low recognition accuracy, low processing efficiency, fixed algorithm, etc., and achieve the effect of improving recognition efficiency, improving accuracy and reducing human factors

Active Publication Date: 2022-05-06
腾讯医疗健康(深圳)有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the existing technology, the inventors of the present invention found that the processing efficiency is low due to the need for manual definition, and because the manually defined features have limitations and the algorithm is relatively fixed, the recognition Accuracy is also low and unstable

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
  • Retinopathy image type recognition method, device and storage medium
  • Retinopathy image type recognition method, device and storage medium
  • Retinopathy image type recognition method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] This embodiment will be described from the perspective of a retinopathy image type recognition device. The retinopathy image type recognition device may be integrated in a network device, and the network device may be a terminal or a server, wherein the terminal may include a tablet computer , laptop or personal computer (PC, Personal Computer), etc.

[0059] A method for recognizing image types of retinopathy, comprising: collecting an international staging sample set and a domestic staging sample set, training a preset international staging model according to the international staging sample set, and using the trained international staging model to perform a domestic staging sample set Calculate and train the preset domestic staging model based on the calculated output vector of each convolutional layer in the international staging model and the domestic staging sample set, and identify the type of retinal lesion on the fundus image to be recognized based on the traine...

Embodiment 2

[0160] According to the methods described in the previous embodiments, examples will be given below for further detailed description.

[0161] In this embodiment, it will be described by taking the apparatus for identifying the type of retinopathy image specifically integrated in a network device as an example.

[0162] Such as Figure 2a As shown, a retinopathy image type recognition method, the specific process can be as follows:

[0163] 201. Network equipment collects international installment sample sets and domestic installment sample sets.

[0164] Among them, there are many ways to collect, for example, multiple international staging samples of diabetic retinopathy can be obtained from the Internet, designated databases and / or medical records, and an international staging sample set can be obtained; and, from the Internet, designated databases and / or Or obtain multiple domestic staging samples of diabetic retinopathy from medical records to obtain a domestic staging ...

Embodiment 3

[0253] In order to better implement the above method, an embodiment of the present invention also provides a retinopathy image type recognition device, the retinopathy image type recognition device may be integrated in a network device, and the network device may be a terminal or a server.

[0254] For example, if Figure 3a As shown, the retinopathy image type recognition device may include an acquisition unit 301, an international training unit 302, a transfer learning unit 303, a domestic training unit 304 and a recognition unit 305, as follows:

[0255] (1) acquisition unit 301;

[0256] The collection unit 301 is configured to collect international installment sample sets and domestic installment sample sets.

[0257] Among them, there are many ways to collect. For example, the collection unit 301 can be used to obtain multiple international staging samples from the Internet, designated databases and / or medical records, obtain international staging sample sets, and obtai...

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 embodiment of the present invention discloses a retinopathy image type recognition method, device and storage medium; the embodiment of the present invention can collect the international staging sample set and the domestic staging sample set, and then, according to the international staging sample set, preset the international staging model Carry out training, and use the trained international staging model to calculate the domestic staging sample set, and obtain the output vector of each convolutional layer in the international staging model, and then, according to the domestic staging sample set and output vector, the preset domestic staging model Carry out training, and identify the type of retinopathy based on the trained domestic staged model of the fundus image to be recognized; this solution can improve the processing efficiency while improving the accuracy of the recognition, and make the accuracy have a certain stability.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a method, device and storage medium for identifying the type of retinopathy images. Background technique [0002] Diabetic retinopathy (DR), one of the most common microvascular complications of diabetes and a leading cause of low vision and blindness in adults, seriously affects the quality of life of millions of people worldwide. There is no effective cure for diabetic retinopathy so far. Early detection and early treatment are crucial to delay its progression. Therefore, it is necessary to classify retinopathy according to its severity and accurately identify its lesion type for later diagnosis and treatment. [0003] For the degree of retinopathy, there are many classification methods. Among them, the international classification method (international staging) can be divided into 5 categories, namely normal, mild non-proliferative (Mild NPDR), moderate non-prol...

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 Patents(China)
IPC IPC(8): G06T7/00G06V10/764G06V10/774G06K9/62G16H50/20
CPCG06T7/0012G16H50/20G06T2207/20081G06T2207/20084G06T2207/30041G06F18/24147G06F18/214
Inventor 张毅孙星郭晓威周旋常佳
Owner 腾讯医疗健康(深圳)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com