Method and system for automatically recognizing rare cells

A rare cell and automatic identification technology, applied in the field of biomedical inspection, can solve the problems of too large smear area, weak expression of CTC-specific antibodies, and difficulty in manually finding CTCs, so as to improve the effect of staining and identification

Inactive Publication Date: 2016-12-07
SHENZHEN HUADA GENE INST
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even if various positive and negative screening enrichment methods are used to greatly reduce blood cells and then carry out fluorescent staining and identification, due to the spontaneous quenching of fluorescence, the expression of CTCs for specific antib

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 and system for automatically recognizing rare cells
  • Method and system for automatically recognizing rare cells

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0041] A schematic flowchart of a method for automatically identifying rare cells provided in this embodiment is shown in figure 1 As shown, it includes: injecting the cell enrichment solution containing rare cells into the prepared smear device, staining the cells according to the standard immunostaining process, and taking pictures of multi-fluorescence channels through a fluorescence microscope to obtain the image acquisition step S10 of the fluorescence image. The fluorescence image is processed into a clean image whose background gray value is strictly zero while retaining the true fluorescence value in the cell outline by using an image processing algorithm, and then the image processing step S20 of extracting the cell outline is performed on the clean image, and each extracted The profile statistics corresponds to the average fluorescence intensity value of each channel of the multi-fluorescent channels and the statistical identification step S30 of determining rare cell...

Embodiment 2

[0060] The difference between this embodiment and Embodiment 1 is that, considering that the images obtained when the fluorescence scanning microscope performs multi-channel fluorescence scanning are usually very large, such as larger than 5G, the memory allocated to Matlab calculations is very limited, and it is difficult to process such a large image. The matrix is ​​obviously very slow. Therefore, compared with Embodiment 1, in this embodiment, when performing the aforementioned image processing step S20, the fluorescence image is first divided into several small pictures, such as ensuring that each small picture is not greater than 30M, and Matlab searches for the loop according to the file name. Read in the small images and process them, that is, perform sub-steps such as background processing, binarization, and restore the initial value for each small image, and then splicing the output results of all the processed small images to obtain the corresponding original fluoresc...

Embodiment 3

[0062] The difference between this embodiment and embodiment 1 or embodiment 2 is that after the clean image is obtained, a pseudo-color can be added to the clean image for manual observation. How to add the pseudo-color specifically can refer to the existing related technology implementation, which will not be described in detail here.

[0063]In summary, the method or system for automatically identifying rare cells provided by the present invention involves immunostaining of rare cells such as circulating tumor cells, image recognition, identification and counting, and by designing grooves in PDMS smears, it avoids rare cells The loss during the staining operation can also facilitate the setting of the scanning area to prevent cells from being missed due to unscanned cells; the background of the cell fluorescence image after background processing in the image recognition part is very clean, the background fluorescence value is strictly zero, and the cell outline The original...

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 present invention relates to a method and a system for automatically recognizing rare cells. The method comprises: injecting a cell enrichment liquid carrying rare cells into a prepared coating-slice device, staining the cells according to a standard immunostaining process, and carrying out multi-fluorescence channel shooting through a fluorescence microscope to obtain a fluorescence image; treating the fluorescence image into a clean image strictly having a background gray value of zero and retaining the true fluorescence value in the cell contour, and carrying out cell contour extraction on the clean image; and carrying out statistics on the average fluorescence intensity value of various extracted contour channels corresponding to the multi-fluorescence channel, and determining the rare cells according to the statistics results. According to the present invention, the obtained fluorescence image is treated to strictly achieve the background gray value of zero while the true fluorescence value in the cell contour is retained, such that the influence of the background noise on the cell contour extraction is minimized; and for the fluorescence image obtained through the multi-fluorescence channel, the cells are confirmed and recognized from more parameters so as to improve the staining recognizing of the rare cells.

Description

technical field [0001] The invention relates to the technical field of biomedical testing, in particular to a method and system for automatically identifying rare cells. Background technique [0002] As one of the most commonly used tools for identifying specific cells, immunofluorescence staining has a convenient operation process and direct effect, and has a wide range of applications in cell identification, medical diagnosis, and antibody expression detection. Laser capture microdissection (LCM) counting based on smear staining and recognition, compared with flow cytometry single-cell separation, has less damage to cells and is more conducive to molecular biology research of tumors. When the number of cells on the smear is small, it is easy to find the target cells with the naked eye under the fluorescence microscope. However, when the number of cells is large (more than 10 5 ), and when the number of target cells is relatively rare, it becomes extremely difficult to ma...

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): C12N5/00C12Q1/06C12M1/00
Inventor 吴平李贵波王楠李鹏鑫王琳琳肖利云刘梦钟娜
Owner SHENZHEN HUADA GENE INST
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