Cell nucleus segmentation and counting method and system for immunohistochemical cell images

Abstract

The present invention provides a method for segmenting and counting cell nuclei in immunohistochemical cell images, comprising: obtaining a pathological cell image through a preset input data source; determining a display image on an image display panel according to the pathological cell image and the input data source ; Determine the cell nucleus segmentation area by graphical drawing on the display image; perform color correction and noise reduction on the cell nucleus segmentation area to determine the initial cell image; process the initial cell image to obtain a negative area mask and a positive area mask According to the outline of the nucleus, the negative area mask and the positive area mask, the nuclei detected in the initial cell image are classified to determine the classified nuclei; the classified nuclei are counted, and according to the classified nuclei , determine the diagnostic index, and optimize the display results according to the diagnostic index.

Description

technical field [0001] The present invention relates to the technical field of cell nucleus segmentation and counting methods and systems for immunohistochemical cell images, in particular to a cell nucleus segmentation and counting method and system for immunohistochemical cell images. Background technique [0002] At present, pathological diagnosis is the most reliable method of tumor examination and is called the "gold standard". Cancerous nuclei are significantly different from normal nuclei in size and shape, and can be visualized by specific staining. Currently, pathological diagnosis is mostly done through observation under a microscope, which requires very high expertise, takes a lot of time, and produces subjective differences. Computer-aided diagnosis can provide high-speed, repeatable medical image analysis, and the results are more objective and accurate. Nucleus detection and segmentation is a critical first step in medical image analysis. However, due to the ...

AI Technical Summary

Problems solved by technology

Nucleus detection and segmentation is the key first step in medical image analysis. However, due to the existence of uneven staining, irregular cell shape, adhesion between nuclei, and impurity noise, accurate cell nucleus segmentation and counting still face many challenges. It is a big challenge. The existing cell image segmentation technology mainly adopts deep learning algorithm, which requires a large amount of training data. However, it is extremely difficult to obtain labeled samples of immunohistochemical cell images, and the training data is insufficient, resulting in insufficient accuracy.

At the same time, the deep learning algorithm has a large amount of calculation and requires high computer resources.

However, the segmentation method based on non-deep learning algorithm needs to regulate a large number of parameters, and the selection of parameters is more difficult.

Images