Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Antinuclear antibody karyotype interpretation method and device based on deep learning

An anti-nuclear antibody and deep learning technology, applied in neural learning methods, biological neural network models, instruments, etc., can solve the problem of not being able to identify mixed karyotypes, and achieve the effect of improving inspection efficiency

Active Publication Date: 2021-01-15
南京金域医学检验所有限公司
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing problems: In order to realize the automatic recognition of anti-nuclear antibody fluorescence pictures, some manufacturers have introduced automatic recognition instruments, such as Helios from AESUKU, EUROPattern from Oumeng, etc.
However, these automated instruments can only identify some common karyotypes, and do not have the ability to identify mixed karyotypes and rare karyotypes

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
  • Antinuclear antibody karyotype interpretation method and device based on deep learning
  • Antinuclear antibody karyotype interpretation method and device based on deep learning
  • Antinuclear antibody karyotype interpretation method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be further illustrated below in conjunction with the accompanying drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0054] Such as figure 1 As shown, the embodiment of the present invention provides a deep learning-based antinuclear antibody karyotype reading method, including:

[0055] Obtain the fluorescent pictures of anti-nuclear antibodies, and classify the fluorescent pictures of anti-nuclear antibodies based on the image classification model. The categories of fluorescent pictures of anti-nuclear antibodies include negative, positive and fuzzy. If the categories of fluorescent pictures of anti-nuclear antibodies are negative, then Negative results are output directly. If the category of the f...

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 antinuclear antibody karyotype interpretation method and device based on deep learning. The method comprises the following steps: acquiring a fluorescent picture of an antinuclear antibody, classifying the fluorescent picture of the antinuclear antibody based on a picture classification model, and identifying cells in the fluorescent picture of the antinuclear antibody of which the category is positive based on a cell identification model so as to acquire a karyotype category of the cells in the fluorescent picture of the antinuclear antibody, wherein the karyotype category comprises a conventional karyotype and a rare karyotype, and if the karyotype category of the cell is the rare karyotype, outputting an early warning result; and generating a fluorescence karyotype interpretation result based on the karyotype discrimination model by taking the type of the conventional karyotype contained in the fluorescence picture of the antinuclear antibody as an input.According to the invention, nuclear type interpretation can be automatically carried out, and a special situation early warning system is provided, so that a doctor can use the software to carry out nuclear type interpretation at ease and interpret early warning pictures manually, and the inspection efficiency is greatly improved.

Description

technical field [0001] The invention relates to the technical field of antinuclear antibody karyotype interpretation, in particular to a deep learning-based antinuclear antibody karyotype interpretation method and equipment. Background technique [0002] Antinuclear antibody (Antinuclear Antibody, ANA) refers to the general term for a class of autoantibodies that use eukaryotic cell nucleus components, such as RNA, DNA, and extractable nuclear antigens, as target antigens. , SLE) and other important indicators of autoimmune diseases (Autoimmune Disease, AID), and also play an important role in the diagnosis, treatment and prognosis of AID. Currently, there are many methods for detecting ANA, such as indirect immunofluorescence (Indirect Immuno-Fluorescence Assay, IIF), immunoblotting (Immunoblotting Assay), enzyme-linked immunosorbent assay (Enzyme-Linked ImmunoSorbent Assay, ELISA), etc. Among them, IIF based on Hep-2 cells has high sensitivity and semi-quantitative charac...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/698G06N3/045G06F18/24
Inventor 任茂源夏玲芝袁杭毛源文华廷
Owner 南京金域医学检验所有限公司
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
Eureka Blog
Learn More
PatSnap group products