CN-122024231-A - Method, system and electronic equipment for identifying electrophoresis strip of microorganism PCR product

CN122024231ACN 122024231 ACN122024231 ACN 122024231ACN-122024231-A

Abstract

The invention provides a method, a system and electronic equipment for identifying a microbial PCR product electrophoresis strip, which comprise the steps of obtaining a sample electrophoresis gel diagram after a microbial PCR test is carried out on a sample extract in a pig body, dividing the sample electrophoresis gel diagram based on a pre-constructed dividing model to obtain a PCR gel image, carrying out electrophoresis strip identification on the PCR gel image based on a pre-constructed identification model to obtain a mark and a sample electrophoresis strip, and splicing and analyzing the sample electrophoresis strip and a corresponding mark to obtain length information of the sample electrophoresis strip. The invention can automatically identify and analyze the electrophoresis strip of the microorganism PCR product, thereby rapidly positioning the cause of the diseased pig and timely and accurately taking the medicine, and reducing the silencing cost in the pig breeding process.

Inventors

QIN YINGLIN
YANG BIN
LI YANPENG
NIU MIN
HU YIYONG
HUANG DANCHENG
Zhang gun

Assignees

牧原食品股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260128

Claims (10)

1. A method for identifying an electrophoresis strip of a microbial PCR product, comprising: obtaining a sample electrophoresis gel diagram after a microorganism PCR test is carried out on a sample extract in a pig body; Dividing the sample electrophoresis gel image based on a pre-constructed dividing model to obtain a PCR gel image; And carrying out electrophoresis strip identification on the PCR gel image based on a pre-constructed identification model to obtain a mark and a sample electrophoresis strip, and splicing and analyzing the sample electrophoresis strip and the corresponding mark to obtain the length information of the sample electrophoresis strip.
2. The method of claim 1, wherein segmenting the sample electrophoresis gel image based on a pre-constructed segmentation model yields a PCR gel image, comprising: normalizing the sample electrophoresis gel map to obtain a normalized sample electrophoresis gel map; Inputting the normalized sample electrophoresis gel diagram into a pre-constructed segmentation model to obtain an initial PCR gel image; and correcting the initial PCR gel image based on a transmission transformation algorithm to obtain a PCR gel image.
3. The method of claim 2, wherein inputting the normalized sample electrophoresis gel map into a pre-constructed segmentation model, results in an initial PCR gel image, comprising: inputting the normalized sample electrophoresis gel diagram into a pre-constructed segmentation model for feature extraction and feature fusion to obtain electrophoresis gel region features; And generating an electrophoresis gel region mask based on the electrophoresis gel region characteristics, and cutting the sample electrophoresis gel image based on the electrophoresis gel region mask to obtain an initial PCR gel image.
4. A method according to claim 3, wherein generating an electrophoretic gel region mask based on the electrophoretic gel region characteristics comprises: predicting the normalized sample electrophoresis gel map to obtain a plurality of electrophoresis gel prediction areas, and aligning the electrophoresis gel prediction areas with the electrophoresis gel area characteristics to obtain at least one candidate electrophoresis gel area; and determining a predicted probability value of the candidate electrophoretic gel region based on a Mask branch, and generating an electrophoretic gel region Mask based on the predicted probability value.
5. The method of claim 1, wherein performing electrophoresis strip recognition on the PCR gel image based on a pre-constructed recognition model to obtain a marker and a sample electrophoresis strip, comprising: normalizing the PCR gel image to obtain a normalized PCR gel image; Inputting the normalized PCR gel image into a pre-constructed recognition model for feature extraction to obtain a PCR feature map; Generating an electrophoresis band candidate region based on the PCR feature map, and carrying out feature fusion on the electrophoresis band candidate region to obtain electrophoresis band candidate features; and determining the boundary box position of the sample electrophoresis strip in the PCR gel image based on the electrophoresis strip candidate characteristics.
6. The method of claim 5, further comprising, after performing electrophoretic stripe recognition on the PCR gel image based on a pre-constructed recognition model: And obtaining the glue making size, and processing the identified sample electrophoresis strip based on the glue making size to obtain the physical coordinates of the sample electrophoresis strip.
7. A microbial PCR product electrophoresis strip identification system, comprising: The sample map acquisition module is used for acquiring a sample electrophoresis gel map after the microorganism PCR test is carried out on the sample extract in the pig body; The image segmentation module is used for segmenting the sample electrophoresis gel image based on a pre-constructed segmentation model to obtain a PCR gel image; And the strip identification module is used for carrying out electrophoresis strip identification on the PCR gel image based on a pre-constructed identification model to obtain a mark and a sample electrophoresis strip, and splicing and analyzing the sample electrophoresis strip and the corresponding mark to obtain the length information of the sample electrophoresis strip.
8. The system of claim 7, wherein the image segmentation module is specifically configured to: normalizing the sample electrophoresis gel map to obtain a normalized sample electrophoresis gel map; Inputting the normalized sample electrophoresis gel diagram into a pre-constructed segmentation model to obtain an initial PCR gel image; and correcting the initial PCR gel image based on a transmission transformation algorithm to obtain a PCR gel image.
9. An electronic device comprising a processor and a memory, the memory storing computer executable instructions executable by the processor, the processor executing the computer executable instructions to implement the steps of the method of any one of claims 1 to 6.
10. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor performs the steps of the method of any of the preceding claims 1 to 6.

Description

Method, system and electronic equipment for identifying electrophoresis strip of microorganism PCR product Technical Field The invention relates to the technical field of microorganism genetic information analysis, in particular to a method, a system and electronic equipment for identifying electrophoresis strips of a microorganism PCR product. Background In the growth process of pigs, analysis of the genetic information of microorganisms in the pigs is an important link, and the genetic information of microorganisms in the pigs not only reflects the health condition of the pigs, but also can be used for confirming whether certain diseases exist in the growth process of the pigs, and timely, qualitative and quantitative medication can be performed so as to ensure that the pigs grow healthily at the fastest growth speed. At present, most laboratories only take PCR (polymerase chain reaction) product strips of genetic information of microorganisms as a simple reference, save data for a short period, and cannot systematically sort and analyze the genetic information of the microorganisms, so that the group dependence relationship among the microorganisms cannot be understood, and the control time is delayed in the prevention and control of epidemic diseases of pigs, thereby increasing the silencing cost. Disclosure of Invention In view of the above, the invention aims to provide a method, a system and an electronic device for identifying the electrophoresis strip of the microbial PCR product, which can automatically identify the electrophoresis strip of the microbial PCR product and analyze the electrophoresis strip, so that the cause of the diseased pig can be rapidly positioned, timely and accurately used, and the silencing cost in the pig breeding process is reduced. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: The invention provides a method for identifying a microbial PCR product electrophoresis strip, which comprises the steps of obtaining a sample electrophoresis gel diagram after a microbial PCR test is carried out on a sample extract in a pig body, dividing the sample electrophoresis gel diagram based on a pre-constructed dividing model to obtain a PCR gel image, carrying out electrophoresis strip identification on the PCR gel image based on a pre-constructed identification model to obtain a mark and a sample electrophoresis strip, and splicing and analyzing the sample electrophoresis strip and a corresponding mark to obtain length information of the sample electrophoresis strip. Optionally, the sample electrophoresis gel map is segmented based on a pre-built segmentation model to obtain a PCR gel image, and the method comprises the steps of normalizing the sample electrophoresis gel map to obtain a normalized sample electrophoresis gel map, inputting the normalized sample electrophoresis gel map into the pre-built segmentation model to obtain an initial PCR gel image, and correcting the initial PCR gel image based on a transmission transformation algorithm to obtain the PCR gel image. Optionally, inputting the normalized sample electrophoresis gel image into a pre-constructed segmentation model to obtain an initial PCR gel image, wherein the method comprises inputting the normalized sample electrophoresis gel image into the pre-constructed segmentation model to perform feature extraction and feature fusion to obtain electrophoresis gel region features, generating an electrophoresis gel region mask based on the electrophoresis gel region features, and cutting the sample electrophoresis gel image based on the electrophoresis gel region mask to obtain the initial PCR gel image. Optionally, generating an electrophoresis gel region Mask based on electrophoresis gel region features comprises predicting a normalized sample electrophoresis gel map to obtain multiple electrophoresis gel prediction regions, aligning the electrophoresis gel prediction regions with the electrophoresis gel region features to obtain at least one candidate electrophoresis gel region, determining a prediction probability value of the candidate electrophoresis gel region based on Mask branches, and generating the electrophoresis gel region Mask based on the prediction probability value. The method comprises the steps of carrying out normalization processing on a PCR gel image to obtain a normalized PCR gel image, inputting the normalized PCR gel image into a pre-built recognition model to carry out feature extraction to obtain a PCR feature map, generating an electrophoresis band candidate region based on the PCR feature map, carrying out feature fusion on the electrophoresis band candidate region to obtain electrophoresis band candidate features, and determining the boundary frame position of a sample electrophoresis band in the PCR gel image based on the electrophoresis band candidate features. Optionally, after the electrophoresis strip identification is performed on the PCR g