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

Depth reconstruction method for optical coherence tomography based on deep learning

A technology of optical coherence tomography and imaging depth, which is applied in 2D image generation, image enhancement, image analysis, etc., can solve the problems of increasing complex steps, high cost, and increasing device complexity, and avoids parasitic depth signals and devices. The effect of simplifying the structure and reducing the parameter requirements

Active Publication Date: 2022-03-08
SOUTHWEAT UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This limits the choice of light sources available, or adds complex steps to smoothing the spectral signal
[0006] (3) Ordinary OCT uses a reference arm to suppress the spurious signal strength, and the reference arm will increase the complexity of the device and make the measurement results susceptible to vibration interference
The reference arm requires the same optical path as the sample arm, so if there is strong vibration in the environment, it will destroy the stability of the interference signal and affect the accuracy of depth reconstruction
In addition, for the soft X-ray band, it is difficult to manufacture or use optical splitting devices and beam combining devices, so the reference arm optical path is technically difficult to realize, or the cost is extremely 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
  • Depth reconstruction method for optical coherence tomography based on deep learning
  • Depth reconstruction method for optical coherence tomography based on deep learning
  • Depth reconstruction method for optical coherence tomography based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0018] Example: Deep learning realizes SD-OCT depth reconstruction of layered samples in the mid-infrared band

[0019] Illumination light source parameters: center wavelength 815nm, spectral half-maximum width 20nm. The sample is two glass plates with a thickness of about 130 microns, and the middle layer is an air layer whose thickness is to be measured. If Fourier transform is used as a depth reconstruction method, since the theoretical depth resolution of this light source is about 14.6 microns, if the thickness of the air layer is less than 14.6 microns (or so), depth reconstruction cannot be performed.

[0020] figure 1 Schematic diagram of the setup for measuring the thickness of the double-glazed air gap using an SD-OCT setup without a reference arm

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

A method for depth reconstruction of optical coherence tomography based on deep learning, comprising steps: 1) preparing training samples: including interference signal data and corresponding real depth data; 2) training neural network to learn the relationship between interference signal and real depth Mapping relationship; 3) Obtain the interference signal of the depth to be reconstructed and use the model to perform depth reconstruction. The present invention uses deep learning to realize the depth reconstruction of the interference signal obtained in the process of optical coherence tomography (instead of the Fourier transform method), and its depth reconstruction resolution can not be limited by the central wavelength or spectral width of the light source. There is no special requirement on the smoothness of the network, and the interference signal can be obtained by a simplified SD-OCT method that removes the reference arm.

Description

technical field [0001] The invention belongs to the field of computational optical imaging, in particular to a deep learning-based optical coherence tomography depth reconstruction method. Background technique [0002] Spectral-Domain Optical Coherence Tomography (SD-OCT for short) is an optical three-dimensional imaging technology that uses a broadband light source. The broadband optical signal is scattered back from the surface and inside of the sample and interferes. The intensity and phase information of the scattered light is encoded in the interference signal. The depth reconstruction process is to record each spectral component of the interference signal separately, and then reconstruct the depth-resolved interference envelope signal through Fourier transform. Through the Fourier transform of the interference spectrum, the one-dimensional depth of the sample can be obtained. Information, combined with lateral scanning, can realize three-dimensional imaging of the sam...

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): G06T11/00
CPCG06T11/003G06T11/005G06T2207/10101G06T2207/20081G06T2207/20084
Inventor 杨华胡剑波
Owner SOUTHWEAT UNIV OF SCI & TECH