Immunochromatography concentration detection method and system based on machine learning

Abstract

The invention relates to an immunochromatography concentration detection method and system based on machine learning. The method comprises the following steps of: acquiring an immunochromatography test strip image of human chorionic gonadotropin HCG and three indexes of myocardial infarction; preprocessing the immunochromatographic test strip image, and determining the preprocessed immunochromatographic test strip image; constructing a UNet semantic segmentation network according to the preprocessed immunochromatography test strip image; inputting a to-be-detected sample into the UNet semanticsegmentation network, and outputting a target detection area in a foreground and background segmentation mode; and dividing the pixel point intensity in the target detection area into RGB three-channel vector intensity, inputting the RGB three-channel vector intensity into a classification network, and outputting the concentration category of the to-be-detected sample according to the concentration range of the to-be-detected sample. According to the method, the sample difference can be eliminated, the problem that the detection precision is reduced along with the increase of detection categories is avoided, the sample category detection precision is improved, and the missed detection rate of weak positive samples is reduced.

Description

technical field [0001] The invention relates to the field of immunochromatography concentration detection, in particular to a machine learning-based immunochromatography concentration detection method and system. Background technique [0002] Immunochromatography is a rapid detection method using nanoparticles as markers, which is mainly used in medical testing, food safety testing, agriculture and animal husbandry and other fields. As a commonly used rapid detection method, immunochromatographic detection effectively combines the advantages of chromatography and immunoassay. At the same time, immunochromatographic method has the advantages of simple operation, rapid detection, good repeatability, high specificity and sensitivity, and sampling The advantages of small amount, no complicated instruments or only simple instruments are needed in the test strip detection process, and the operators do not need professional training, so the immunochromatographic detection is very s...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a machine learning-based immunochromatographic concentration detection method and system to solve the problem that the traditional sample concentration detection method has large differences for different concentration samples and multi-target detection, and the detection accuracy varies with the detection category. The problem of increasing the drop and the high miss rate of weak positive samples

Images