Fundus image processing method, model training method and equipment

A fundus image and processing method technology, applied in the field of image processing, can solve the problems of high demand for computing resources, tedious and complicated GAN model training process, etc., to improve the recognition accuracy, improve the scope of application, and reduce the effect of prediction deviation.

Pending Publication Date: 2021-06-15
BEIJING AIRDOC TECH CO LTD +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Using GAN for data enhancement can deal with the domain adaptation problem brought by unknown distribution data, but the significant disadvantage of this method is that the training process of the GAN model is cumbersome and complicated, and it has high demand for computing resources like the inference and prediction process
In addition, another limitation is that generative methods usually require a certain amount of unknown distribution data to intervene in the training process of the model

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
  • Fundus image processing method, model training method and equipment
  • Fundus image processing method, model training method and equipment
  • Fundus image processing method, model training method and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0046] In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as there is no conflict with each other.

[0047] An embodiment of the present invention provides a fundus image processing method, which can be executed by electronic devices such as computers or servers, such as figure 2 The method shown includes the following steps:

[0048]S1, extracting a single-channel fundus image from a multi-channel fundus ...

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 provides a fundus image processing method, a model training method and equipment, and the method comprises the steps: extracting a single-channel fundus image from a multi-channel fundus image; determining a maximum pixel value and a minimum pixel value in the single-channel eye fundus image; processing pixel values in the single-channel eye fundus image by using the maximum pixel value and the minimum pixel value; and synthesizing the processed single-channel fundus images into a multi-channel fundus image.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a fundus image processing method, model training method and equipment. Background technique [0002] In recent years, based on deep learning technology, intelligent image recognition has reached the recognition level of human experts on some specific medical issues, but the test performance of the learned model in unknown domains (data sources that are different from the model training data) is prone to drop significantly . The data in the unknown domain can come from collection devices different from the model training set or from different collection groups, etc. Common unknown domains in medical image scenarios are different groups of people, different collection devices, etc. This decrease in performance is due to the fact that the evaluation patterns learned by the training data are not fully applicable to unseen domain images, and how to improve the performance of the model...

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): G06K9/00G06K9/62G06N3/04
CPCG06V40/197G06V40/193G06N3/045G06F18/251
Inventor 熊健皓赵昕和超张大磊
Owner BEIJING AIRDOC TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap