OCT image detection method and system based on retinal hierarchical data

A technology of image detection and layered data, applied in the field of image processing, can solve the problems of missing details, complex fundus images, increasing the workload of ophthalmologists, etc., and achieve the effect of network parameters

Pending Publication Date: 2021-07-16
HANGZHOU DIANZI UNIV
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the patient's fundus image is relatively complex, and it is difficult for the doctor to observe, and it is easy to miss some key details, which will affect the diagnosis of the patient.
At the same time, ophthalmologists need to invest a lot of energy, increasing the workload of ophthalmologists

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
  • OCT image detection method and system based on retinal hierarchical data
  • OCT image detection method and system based on retinal hierarchical data
  • OCT image detection method and system based on retinal hierarchical data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Aiming at the problems present in the diagnosis of fundus diseases, the present invention proposes a highly accurate, low-artificial cost, an OCT-based nominal disease detection technology. Solved the traditional diagnosis method is not easy to observe, the labor cost is large, and the accuracy is not high.

[0024] The overtill is composed of nodes and hyperbinds, and the hyperbide represents a relationship, and the overtravel matrix can represent the relationship between the respective nodes. In this supermap structure, each patient is a node, and the above characteristics are set to the hyperbide, and the patient with this feature is 1 in the matrix of 1, otherwise 0. In the above characteristics, the two-class properties are directly used to represent the hyperbind, and the remaining features are established using the KNN algorithm. After using the OCT image with the OCT tag with the fundus disease, you can enter this supergram into the dynamic supergraph volume web to ...

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 an OCT image detection method and system based on retinal hierarchical data. The method comprises the following steps: segmenting an OCT image by using a convolutional neural network, namely an OCT image feature extraction network, extracting feature parameters, constructing a hypergraph by using the parameters, and finally, diagnosing fundus diseases of a patient by using a dynamic hypergraph convolutional network. According to the method, image data and physiological data features are combined together by using the hypergraph, so the relationship between multi-modal data can be explored; and the deep relationship between the feature and the label of the data of a certain mode can be explored. A hypergraph matrix is constructed by using a dynamic method, and automatic optimization of network parameters can be realized.

Description

Technical field [0001] The present invention belongs to the field of image processing, and more particularly to the fundus image detecting method and system of the retinal layering data of the optical coherence breakage to the imaging OCT. Background technique [0002] Optical Coherence Tomography (Oct) is an imaging technology that has developed rapidly in the past decade. It uses the basic principles of weak phase drying optical interferometers, and detects different depth levels of biological tissues to incident weakness. Reflection or several scattering signals, by scanning, biological tissue 2D or three-dimensional structural images can be obtained. It can be used in vivo view, axial tomography, and measurement of the backbone structure (including retinal, retinal neurofiber, macular and visible tray), which is particularly useful as assistance detection and managing eye diseases (including but not limited to yellow split holes, grouse Diagnostic equipment of sample edema, d...

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): G06T7/00G06K9/46G06K9/62G06N3/04G06N3/08A61B3/00A61B3/10A61B3/12
CPCG06T7/0012G06N3/08A61B3/0025A61B3/102A61B3/12G06T2207/10101G06T2207/20081G06T2207/20084G06T2207/30041G06V10/44G06N3/045G06F18/23G06F18/24147G06F18/241
Inventor 颜成钢高宇涵朱晨瑞孙垚棋张继勇张勇东
Owner HANGZHOU DIANZI UNIV
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