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

Retinal oct image classification method based on deep learning

A technology of deep learning and classification method, applied in the field of deep learning, can solve the problem of low classification accuracy and achieve the effect of rapid classification

Active Publication Date: 2021-07-13
UNIV OF SCI & TECH OF CHINA
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing classification networks based on deep learning methods are relatively simple, and the classification accuracy is not high

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
  • Retinal oct image classification method based on deep learning
  • Retinal oct image classification method based on deep learning
  • Retinal oct image classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, 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.

[0022] Embodiments of the present invention provide a method for classifying retinal OCT images based on deep learning, such as figure 1 As shown, it mainly includes the following steps:

[0023] Step 1. Construct a convolutional neural network, which contains multiple Inception segments. Each Inception segment contains several Inception modules, and a residual attention model is inserted outside the Inception segment with a specific serial number....

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 retinal OCT image classification method based on deep learning, comprising: constructing a convolutional neural network, which includes a plurality of Inception segments, each Inception segment contains several Inception modules, and a specific sequence number is inserted outside the Inception segment A residual attention model is established, and the back end of the last Inception segment is also equipped with a global average pooling layer and a softmax layer in turn; the convolutional neural network is trained using a training set containing normal retinal OCT images and abnormal retinal OCT images ; use the trained convolutional neural network to classify the newly input retinal OCT image, and obtain the classification result. This method can automatically achieve accurate classification of retinal OCT images.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a retinal OCT image classification method based on deep learning. Background technique [0002] OCT (optical coherence tomography), that is, optical coherence tomography. As a non-contact, non-invasive ophthalmic imaging diagnostic technology, OCT is widely used in retinal imaging. The axial resolution of OCT can achieve the accuracy of microscopic resolution by observing the reflection, absorption and scattering of tissues. It can clearly display the posterior eye, mainly the morphological characteristics of the optic nerve head and macula, the changes in the thickness of the retina and nerve fiber layer, the structure of the retinal layer, and the anterior tissues such as the cornea, iris, and lens can also be observed. [0003] The current retinal OCT image classification methods are mainly divided into the following two categories: [0004] The first category:...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V2201/03G06N3/045G06F18/2414
Inventor 张勇东符子龙尚志华谢洪涛
Owner UNIV OF SCI & TECH OF CHINA