A method and system for classifying cytofluorescence images based on artificial intelligence
A fluorescent image and classification method technology, applied in the field of cytology, can solve the problems of unstable staining effect, many cell subtypes, and poor results
Active Publication Date: 2020-10-23
THE NAT CENT FOR NANOSCI & TECH NCNST OF CHINA
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, due to many interfering factors such as many cell subtypes in complex samples such as tissue or whole blood, complex impurity composition, and unstable staining effect, threshold-based image classification methods often do not work well, and still require a lot of labor by experienced operators , constantly revise the software classification parameters, and do manual review on the results
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.
[0038] Figure 1 to Figure 3 A method for classifying cell fluorescence images is shown, comprising the following steps:
[0039] S1. Input positive cell fluorescence images, negative cell fluorescence images and non-cellular impurity fluorescence images as samples into the artificial intelligence model for training to obtain a cell fluorescence image classification model;
[0040] S2. Input the sample of the cell fluorescence image to be tested into the cell fluorescence image classification model to classify the cell fluorescence image.
[0041] Preferably, in step S1, the artificial intelligence model includes convolution calculation, pooling calculation and full conn...
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
Login to View More Abstract
The present invention provides a method and system for classifying cell fluorescence images based on artificial intelligence. The method includes the following steps: S1. Input positive cell fluorescence images and negative cell fluorescence images as samples into an artificial intelligence model for training to obtain cell fluorescence Image classification model; S2. Input the cell fluorescence image sample to be tested into the cell fluorescence image classification model to obtain correct classification of the cell fluorescence image. Through the artificial intelligence algorithm, the fluorescence image samples are trained and learned, and a large number of samples are used as the input of the network. After the network learns the labels of the samples, the network can accurately classify the samples correctly, and effectively avoid the threshold-based classification method. It significantly improves the classification efficiency and accuracy of cell fluorescence images, and reduces the consumption of time and human resources.
Description
technical field [0001] The present invention relates to the technical field of cytology, and more specifically, to an artificial intelligence-based cell fluorescence image classification method and system. Background technique [0002] Immunofluorescence is a technique established on the basis of immunology, biochemistry and microscopy. Antigen-antibody reactions can be used to localize antigenic substances in tissues or cells by combining antibody molecules with some fluorescent tracers. Since the expression and distribution of antigenic substances in tissues or cells are related to genetic background, disease, cell differentiation, etc., the use of one or more immunofluorescence to characterize tissues or cells can clarify the target in cells at the protein level. Protein expression status, thus providing experimental basis for drug research, disease diagnosis, and cell subgroup classification. [0003] Due to the possible non-specific staining and other problems in the ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/66
CPCG06V30/194G06F18/241
Inventor 胡志远郑晖李永吴佳涛潘玉霖
Owner THE NAT CENT FOR NANOSCI & TECH NCNST OF CHINA