Agarose gel electrophoresis image automatic analysis method and system based on image recognition

By combining deep learning and rolling ball algorithms in image recognition, the problems of band localization and quantification in agarose gel electrophoresis image analysis were solved, achieving high-precision automated analysis and providing reliable biological experimental data.

CN122156613APending Publication Date: 2026-06-05SUZHOU ZHONGYAN BIO-INFORMATION CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610224139.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-02-25
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing agarose gel electrophoresis image analysis methods suffer from insufficient band localization accuracy and errors in quantitative analysis, making it difficult to achieve sub-pixel-level precise localization and automatic compensation for diffuse signal loss.

Method used

A deep learning-based image recognition method is adopted. The deep learning model is trained to perform image annotation and rotation cropping, and the rolling ball algorithm is combined to remove the background. The grayscale projection integral is used to perform swimlane segmentation and strip integral calculation to calculate the strip purity and molecular weight.

Benefits of technology

It achieves high-precision strip localization and quantitative analysis, eliminates the differences in analysis results caused by human intervention, improves detection sensitivity and the objectivity of quantitative analysis, and provides comprehensive and objective biological experimental data support.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an automatic analysis method and system for an agarose gel electrophoresis image based on image recognition, and the method comprises the steps: obtaining an agarose gel electrophoresis gray image, marking the gray image, and training a deep learning model through a marked image data set; inputting a to-be-analyzed agar gel electrophoresis grayscale image into the deep learning model, outputting image information by the deep learning model, and performing rotary cutting on the to-be-analyzed image according to the image information; carrying out background removal, carrying out gray scale projection integration in the vertical direction based on the image after background removal so as to segment a lane in the image, and carrying out gray scale projection integration in the horizontal direction based on the image after lane segmentation; calculating integral values of all sample molecular weight bands detected in a single lane in the image after lane segmentation, and obtaining the purity of the bands according to the integral values; through the method and the corresponding system, the image analysis accuracy of the samples with serious degradation and trailing can be obviously improved.
Need to check novelty before this filing date? Find Prior Art