A method for angle classification of as-oct images based on convolutional recurrent neural network

A technology of cyclic neural network and convolutional neural network, applied in the field of image processing, can solve the problem that it is difficult to distinguish between narrow-angle and fully-closed-angle areas

Active Publication Date: 2022-05-31
CIXI INST OF BIOMEDICAL ENG NINGBO INST OF MATERIALS TECH & ENG CHINESE ACAD OF SCI +2
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is because it may be difficult to distinguish between narrow-angle and fully-closed-angle regions based on only one static AS-OCT image

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
  • A method for angle classification of as-oct images based on convolutional recurrent neural network
  • A method for angle classification of as-oct images based on convolutional recurrent neural network
  • A method for angle classification of as-oct images based on convolutional recurrent neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In the framework proposed in this chapter, a global AS-OCT alignment method is adopted to address alignment errors. first set

[0049]

[0050] The diamond search algorithm employed in the present invention uses two search modes. The first mode is large iterations

[0052] The present invention proposes an effective ACA positioning method based on a deep learning algorithm. The root of the iris is the ACA area

[0058] The recurrent network LSTM has shown its superiority in video anomaly detection and recognition. Recently, research scholars

[0059]

[0060]

[0061]

[0062]

[0063]

[0066]

[0067]

[0068]

[0069] Finally, the network inputs the output information after feature fusion to the fully connected layer to classify glaucoma. reason

[0070]

[0071] where C and k represent the classifier and the classification label, respectively. n represents the number of images in the sequence. C

[0076]

[0077]

[0078]

[0082]

[0084] The choice of ACA region...

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 method for classifying room angles of AS-OCT images based on a convolutional cyclic neural network, using a global scanning alignment method to perform alignment operations on AS-OCT slices, and solving the problems of involuntary eye movement and improper placement of the optical axis of the eyes Image misalignment caused by possibility; use deep learning segmentation algorithm to segment iris, so as to determine the area of ​​ACA from the root of iris; based on convolutional cyclic neural network to simultaneously model two-dimensional image and image sequence information, improve the network's narrow angle and adhesion classification performance. The invention can accurately classify open, narrow and cohesive glaucoma, reaching the advanced level in the world.

Description

A Convolutional Recurrent Neural Network-based AS-OCT Image Angle Classification Method technical field The present invention relates to a kind of classification method of AS-OCT image based on deep learning, belong to the field of image processing, not Open-angle and angle-closure glaucoma can only be determined from a single AS‑OCT image, and dynamic state features, and then achieve accurate open, narrow and adhesion ACA classification. Background technique [0002] Glaucoma, cataract and diabetic retinopathy are collectively known as the "three major killers" of blindness. According to statistics, globally In China, glaucoma is the second leading cause of blindness in eye diseases, second only to cataracts. Not only that, glaucoma is also the world's The first irreversible eye disease, among which, 70% of glaucoma patients will eventually lose their sight and become blind. glaucoma is impossible Reversible is because glaucoma disease causes a series of damage t...

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): G06T7/11G06T7/00G06N3/08G06N3/04G06K9/62G06V10/774
CPCG06T7/11G06T7/0012G06N3/084G06T2207/30041G06N3/045G06F18/241G06F18/214
Inventor 郝华颖赵一天蒋珊珊李飞张秀兰刘江
Owner CIXI INST OF BIOMEDICAL ENG NINGBO INST OF MATERIALS TECH & ENG CHINESE ACAD OF SCI
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