Abnormal cell detection method, device and computer readable storage medium

Abstract

The invention relates to an artificial intelligence technology. The invention discloses an abnormal cell detection method. The method comprises the following steps: acquiring an original cell set anda label set comprising a positive sample set and a negative sample set, performing Gaussian blur, graying and Sobel operator operation on the original cell set to obtain a preliminary data set; carrying out binarization, closing operation and cell taking operation on the preliminary data set to obtain a cell set; performing contrast enhancement processing on the cell set by utilizing gamma correction to obtain a training set, inputting the training set and the label set into a pre-constructed abnormal cell detection model for training, receiving a to-be-detected cell set input by a user, inputting the to-be-detected cell set into the trained abnormal cell detection model to detect whether the to-be-detected cell set contains abnormal cells or not, and outputting a detection result. The invention further provides an abnormal cell detection device and a computer readable storage medium. According to the method, an accurate abnormal cell detection function can be realized.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, device and computer-readable storage medium for receiving a cell picture or video input by a user and detecting whether there are abnormal cells in the cell picture or video. Background technique [0002] Abnormal cells, such as cancer cells, myelofibrosis cells, lupus erythematosus cells, etc., are often the fuse of major human diseases. According to surveys, there are 500,000 new cases and 274,000 deaths worldwide every year, of which 85% of the new cases was due to the low recognition rate of abnormal cells identified in the early stage. In particular, cervical cancer is currently the only cancer that can be detected and cured early, so early identification is critical for the treatment of the disease. Cell fluid examination is currently the most commonly used method for identifying abnormal cells. However, due to the lack of pathologists and...

AI Technical Summary

Problems solved by technology

Cell fluid examination is currently the most commonly used method for identifying abnormal cells. However, due to the lack of pathologists and cell testing equipment in China, the identification rate for abnormalities is very low. In addition, there are various artificial identification equipment systems, but most auxiliary identification systems Generally based on traditional methods, which rely on precise segmentation of cytoplasm or nucleus and traditional image processing algorithms for feature extraction and selection, so the pre-processing of recognition is cumbersome, and the recognition rate is not high

Images