Phase chromatography method and device based on deep learning and random patterns

A deep learning and phase layer technology, applied in the field of deep learning, to achieve ultra-fast tomographic speed, system accuracy, and strong universality

Active Publication Date: 2019-10-25
TSINGHUA UNIV
View PDF13 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a phase tomography method and device based on deep learning and random patterns to solve the technical problem that effective three-dimensional refractive index reconstruction can only be carried out by changing the angle of incident light several times

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
  • Phase chromatography method and device based on deep learning and random patterns
  • Phase chromatography method and device based on deep learning and random patterns
  • Phase chromatography method and device based on deep learning and random patterns

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0031] The phase tomography method and device based on deep learning and random patterns according to the embodiments of the present invention will be described below with reference to the accompanying drawings. First, the phase tomography method based on deep learning and random patterns according to the embodiments of the present invention will be described with reference to the accompanying drawings.

[0032] figure 1 It is a flowchart of a phase tomography method based on deep learning and random patterns provided by an embod...

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 phase chromatography method and a phase chromatography device based on deep learning and random patterns. The method comprises the following steps: establishing a multi-layerneural network; generating a random pattern by using the digital micromirror array, and modulating the sample by using the random pattern to obtain a preset number of holograms; setting training parameters of the multi-layer neural network according to the actual parameters of the sample and the hologram, and training the multi-layer neural network; calculating the actual three-dimensional refractive index of the sample according to the training parameters; and performing three-dimensional tomography reconstruction on the sample according to the actual three-dimensional refractive index to obtain a three-dimensional tomography image. According to the method, an inclined illumination light beam is not required to be designed and generated. The high-precision phase chromatography reconstruction of a sample can be realized only by using a digital micro-mirror array to project random patterns and using a small amount of random patterns.The functions of high-speed acquisition and precise chromatography are realized by designing a calculation scheme and utilizing a deep learning neural network to be matched with an intensity random modulation plane wave illumination acquisition system.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a phase tomography method and device based on deep learning and random patterns. Background technique [0002] Observing living cells and their subcellular structures is crucial for research in the field of cell biology. For this reason, scholars have invented many three-dimensional imaging methods to achieve this purpose. Fluorescence microscopy is currently the most widely used imaging method, which can achieve submicron imaging by specifically labeling cells with fluorescent proteins or dyes. Based on fluorescence microscopy, various imaging methods have been invented, such as confocal microscopy, two-photon fluorescence microscopy, light sheet microscopy, and light field microscopy, etc. However, fluorescence microscopy can only image labeled cells or structures, so other Applications are limited in some cases. [0003] At the same time, phase tomography, as ...

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): G06N3/04G03H1/12
CPCG03H1/12G06N3/045
Inventor 戴琼海乔畅乔晖
Owner TSINGHUA 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

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