Unlock instant, AI-driven research and patent intelligence for your innovation.

A digital PCR droplet detection method based on lbp-adaboost algorithm

A detection method and technology for droplets, applied in computing, image data processing, computer components and other directions, can solve the problems of uneven brightness, large changes in the brightness value of yin and yang droplets, affecting the actual number of droplets, etc., and achieve a shortened time. Effect

Active Publication Date: 2021-06-01
领航医学科技(深圳)有限公司
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In an optical imaging system with a large field of view, the loss of light energy will produce uneven brightness, which will lead to deviations in the shooting effect of droplets at the edge of the image; a high-definition genetic detection picture contains more than 20,000 droplet points, and the image processing It takes more than 90 seconds for the technology to detect all the droplet points; in the droplet chip, droplets are misdetected due to factors such as uneven droplet size, droplet fusion, random distribution of droplet points, and large changes in brightness values ​​of yin and yang droplets. or missed detection, affecting the true number of droplets

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
  • A digital PCR droplet detection method based on lbp-adaboost algorithm
  • A digital PCR droplet detection method based on lbp-adaboost algorithm
  • A digital PCR droplet detection method based on lbp-adaboost algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0094] The present invention is further illustrated below by means of examples, but the present invention is not limited to the scope of the examples.

[0095] The key point that the present invention implements is as follows:

[0096] (1) The droplet image is divided into 3840 sub-block images, and the LBP extracts the droplet features of the sub-block images (other feature extraction algorithms are not as fast as the LBP time), and the cascade classifier is used to detect droplets in parallel, which improves the droplet detection time.

[0097] (2) The co-occurrence matrix calculates the contrast of sub-images in different directions, and uses the contrast standard deviation to segment the droplet area and non-droplet area of ​​the gene detection image, reducing the mis-segmentation of the droplet boundary caused by the inhomogeneity of the optical path, and accurately positioning the droplet boundary area, to quickly exclude non-droplet points and irregular droplet areas. ...

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 provides a digital PCR droplet detection method based on the LBP-Adaboost algorithm, including S1: Adaboost trains the positive and negative samples of the droplet based on the LBP feature, and generates a cascade classifier; area” to generate a binarized image; S3: The droplet image is divided into (overlapped) sub-images, and each sub-image is loaded with a cascade classifier to calculate the position and gray value of the detected droplet; S4: According to “ Calculate the radius and volume of the droplet in the position of the droplet in the effective area; S5: Calculate the total volume and target gene concentration of all droplets. The invention utilizes the droplet pictures taken by the industrial high-definition camera, and based on machine learning and image processing technology, can quickly and accurately locate the droplet point and improve the accuracy rate of calculating the concentration of the target gene.

Description

technical field [0001] The invention relates to the fields of machine learning technology and image processing technology, and aims at identifying and locating droplets generated in gene detection images, and accurately calculating the concentration of target genes. Background technique [0002] The PCR technology used in genetic testing is to dilute and disperse DNA or RNA samples into tens of thousands or even millions of independent reaction units, each reaction unit contains (or does not contain) 1 or more target molecules (DNA or RNA template), carry out molecular template PCR amplification for the target sequences of all micro-reaction units, after the amplification is completed, analyze the negative or positive fluorescent signals of each reaction unit and perform statistical analysis (Poisson distribution), and finally detect the nuclear concentration of glycosides. [0003] The droplet digital PCR system uses the droplet obtained by separating the oil and water pha...

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 Patents(China)
IPC IPC(8): G06T7/11G06T7/62G06K9/62G16B25/20
Inventor 高鹏夏江
Owner 领航医学科技(深圳)有限公司