Fluorescence labeling prediction method based on unlabeled transmission cell microscopic image

Abstract

The invention discloses a fluorescence labeling prediction method based on an unlabeled transmission cell microscopic image. The method comprises the following steps: constructing a deep learning cell fluorescence labeling prediction model; according to the constructed deep learning cell fluorescence labeling prediction model, training the constructed deep learning cell fluorescence labeling prediction model; inputting to-be-labeled data, and performing fluorescence labeling on the to-be-labeled data based on the trained deep learning cell fluorescence labeling prediction model; and establishing a calculation performance index, and performing similarity and peak signal-to-noise ratio evaluation on the marked data. According to the cell fluorescence labeling prediction method based on deep learning, the fluorescence labeling can be predicted from the unlabeled transmitted light image, and the positions and intensity of the cell nucleus and the cell membrane and the health condition of the cell can be accurately predicted. According to the method, a traditional fluorescence labeling process is avoided, and time and cost are saved.

Description

technical field [0001] The invention relates to a prediction method, in particular to a fluorescent label prediction method based on a non-labeled transmission cell microscopic image. Background technique [0002] In biology and medicine, microscopy provides researchers with details that cannot be seen with the naked eye. Among them, the transmitted light microscopic imaging technology is convenient to use, but it is difficult to judge the cell status according to the obtained images. In contrast, images obtained by fluorescence microscopy are easier to analyze. By fluorescently labeling cell samples, the researchers were able to observe the finer details of the cells. Fluorescence microscopy plays a crucial role in understanding the structure of cells, however, fluorescence microscopy also has many limitations. For example: 1) Sample preparation takes a lot of time and energy, the process of labeling fluorescence is complicated, and the reagents used are relatively expen...

AI Technical Summary

Problems solved by technology

[0003] In view of the above-mentioned defects in the prior art, the technical problem to be solved by the present invention is that the existence of the existing cell fluorescence labeling requires a lot of time and energy, the process of labeling fluorescence is complicated, the reagents are expensive, and the number of fluorescence is limited by spectral overlap. Needle toxicity and photobleaching can interfere with fluorescence imaging

Images