Method for analyzing virus capture of nanoprobe in dark field microscope based on deep learning

A dark-field microscope and nano-probe technology, applied in the field of nano-probe capture virus, can solve problems such as not very convincing, low-dimensional data collapse, transmission loss, etc., to enhance efficiency and scientificity, and remove background interference , the effect of strengthening the actual value

Active Publication Date: 2021-04-02
YANGZHOU UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

(2) The nanoparticles that are not bound to the target molecules are difficult to be completely removed during the elution process, resulting in excessive nanoparticles in the final field of view, making the method of quantification by scattering spectroscopy not very convincing
(3) Due to the different scattering angles of the light source due to the anisotropy of the nanoparticles, the imaging results of differen

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
  • Method for analyzing virus capture of nanoprobe in dark field microscope based on deep learning
  • Method for analyzing virus capture of nanoprobe in dark field microscope based on deep learning
  • Method for analyzing virus capture of nanoprobe in dark field microscope based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In this embodiment, the present invention is based on the dark-field microscope imaging analysis of Opencv and ResNet50, and the flow process is as follows figure 1, including the following two models:

[0041] Model 1: Gold nanoparticles extraction and denoising model based on Opencv, the processing flow is as follows figure 1 As shown, it specifically includes the following steps:

[0042] a. Use a pipette to draw the silver particles modified with virus antibody on the glass slide, and incubate at room temperature for 15 minutes. Then add the original virus and gold particles modified with antibodies, and block and incubate at room temperature for 15 minutes each time.

[0043] b. Fix the glass slide on the stage of STL-P1600CMOS3 dark field microscope, observe with 50 times objective lens.

[0044] c. Use the STL-IMCS dark field field of view acquisition software to collect dark field imaging pictures in the field of view, take pictures without processing, and sa...

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 analyzing virus capture of a nanoprobe in a dark field microscope based on deep learning. The method comprises the following steps: (1) extracting a gold nanoprobebased on Opencv and designing a denoising model; (2) ResNet50 is a model design for judging the sandwich structure of the nanoprobe; and (3) performing real-time analysis and judgment on the dark field microscope imaging original image by using the trained ResNet50-based sandwich structure resolution model and the Opencv-based gold nanoparticle extraction denoising model. According to the method,background interference is effectively removed based on a gold nanoprobe extraction model of OpenCV, and a sandwich structure judgment model based on ResNet50 correctly recognizes a'silver nanoprobe-virus-gold nanoprobe 'sandwich structure formed by combining gold and silver double nanoprobes and viruses, so that the counting efficiency and accuracy of the nanoprobes in a dark field after capturing the viruses are guaranteed; therefore, the method has a real application value in target molecule and microorganism detection with the nanoparticles as signal probes and a dark-field microscope asa platform.

Description

technical field [0001] The invention relates to the technical fields of biological image analysis and computer vision, and in particular to a method for capturing viruses by nano-probes in dark-field microscopes based on deep learning analysis. Background technique [0002] There are endless articles on the construction of biological detection methods for microorganisms and various molecular targets using different nanoparticles as dual-signal probes and dark-field microscopy as a platform. However, in the final counting process, most of them choose pictures with less impurities and clearer particles in the field of view; or use image analysis software to over-process to achieve the purpose of deliberately removing impurities and beautifying the results; or use high-end instruments to measure scattering spectra . These methods are time-consuming and time-consuming. Combined with our previous research and analysis, there are three reasons why the final imaging result is not...

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
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08G06T5/30G06T7/90G16H50/80
CPCG06T7/90G06T5/30G06N3/08G16H50/80G06T2207/20081G06T2207/20084G06V20/69G06N3/045G06F18/214
Inventor 周昕陈铭煜袁嘉晟
Owner YANGZHOU 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