Cervical cancer focus analysis method based on cell image recognition

Abstract

The invention puts forward a cervical cancer focus analysis method based on cell image recognition. The cervical cancer focus analysis method of the invention has the beneficial effects that: pixel grade features with abundant feature expression and super pixel grade features with certain semantic features are combined to obtain level grade features, then the level grade features are used for training a random forest to perform segmentation of cells, thereby well describing a microstructure with intricate and complex parts, and improving a recognition performance; in addition, automatic analysis is performed on an image from a cell level grade, a cervical cancer focus can be captured accurately, thus targeted treatment can be performed, and a high automation degree is achieved.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for analyzing cervical cancer lesions based on cell image recognition. Background technique [0002] The 300 million women in China need regular cervical cancer screening, and the coverage rate of 20% of the population has not yet been reached, which is still far from the goal of 80% of the population coverage required for cervical cancer prevention and control. [0003] At present, China lacks cytopathologists. Automated and cloud diagnosis can solve the problem of lack of pathologists in China, and provide accurate and objective diagnostic reports for cervical cancer examination. In recent years, machine learning methods based on supervised learning have been increasingly used in the analysis of cervical cancer lesions, and have achieved good recognition results. This method is mainly divided into two steps: feature extraction and pattern recognition. The quality of f...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, when identifying cervical cancer lesions based on supervised learning methods, only single pixel information is considered in the feature extraction stage, or when context information is considered, a square window with a fixed size and shape is simply used, which cannot fully describe the local complex and diverse The changed microstructure greatly reduces the recognition rate

Images