Cell nucleus region extraction method and imaging method for multi-cell nucleus color image

Abstract

The invention discloses a cell nucleus region extraction method for a multi-cell nucleus color image. The method comprises the following steps: acquiring a training data set and obtaining a single-cell nucleus cutting image; processing the single cell nucleus clipping image to obtain preliminary rough pixel-level cell nucleus segmentation information; constructing a cell nucleus region extraction model for the multi-cell nucleus color image; carrying out feature extraction on the image data in the training data set, and predicting bounding box position information of a cell nucleus in an image by adopting an extraction model; supervising and optimizing the position information of the cell nucleus by adopting rough pixel-level segmentation information; repeating the above steps, updating the training data set by using the obtained result, and obtaining a final cell nucleus region extraction model; and performing cell nucleus region extraction on the actual multi-cell nucleus color image by adopting the cell nucleus region extraction model. The invention also discloses an imaging method comprising the cell nucleus region extraction method for the multi-cell nucleus color image. The method is high in precision, good in reliability and good in effect.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for extracting cell nucleus regions and an imaging method for multi-nucleus color images. Background technique [0002] With the development of economy and technology and the improvement of people's living standards, people pay more and more attention to health. [0003] In the field of medical imaging, the extraction of cell nuclei from multi-nucleus color images has always been a research focus in the field of medical imaging. Accurately segmenting and extracting cell nucleus regions in multi-nucleus color images can lay a solid foundation for subsequent research and diagnosis. [0004] At present, for the research on the extraction of nuclei in multi-nuclei color images, traditional methods generally use artificially designed features to find nuclear areas, so as to segment and extract nuclear areas; however, the existing technology is often not suitable f...

AI Technical Summary

Problems solved by technology

[0004] At present, for the research on the extraction of nucleus regions in multi-nuclei color images, the traditional methods generally use artificially designed features to find nuclear regions, so as to segment and extract nuclear regions; however, the existing technologies are often not suitable for complex images, and it is difficult to extract stable The feature representation directly leads to the lack of accuracy and robustness of the results, which further affects the follow-up work

Images