Novel Feulgen staining method-based abnormal cervical cell automatic identification method

Abstract

The invention discloses a novel Feulgen staining method-based abnormal cervical cell automatic identification method. According to the automatic identification method disclosed by the invention, the features of the cervical cells are extracted, and the cervical cell classifier is trained, so that the identification of abnormal cervical cells is realized; the process of producing the cervical cellclassifier mainly comprises the following four steps of: 1, dyeing a cervical cell slide by using a Feulgen dyeing method, and automatically scanning the slide by using a microscope to generate a digital view; 2, segmenting cervical cell nuclei in the view map by using a Surf algorithm in combination with a RegionGrowing algorithm; 3, extracting DNA content information of the cell nucleus, cell nucleus morphological characteristics, cervical cell image texture characteristics and the like, and constructing a characteristic vector for representing the abnormal degree of each cervical cell; andstep 4, constructing and training a neural network classification model based on the feature vectors to obtain the cervical cell classifier; and finally, predicting a new cervical cell feature vectorby using the trained cervical cell classifier, thereby realizing the purpose of identifying abnormal cervical cells. Experiments show that the abnormal cervical cell automatic identification method based on the Feulgen staining method can complete the identification task of the abnormal cervical cell with high precision and efficiency, and the automatic identification method has high practical value when being applied to a real product.

Description

technical field [0001] The invention relates to an automatic identification method for abnormal cervical cells based on deep learning, which belongs to the application of machine learning neural network models in medical diagnosis. Background technique [0002] Many studies have shown that the nuclei of abnormal cervical cells usually undergo obvious changes. Large atypia, with different sizes and shapes; at the texture level, due to abnormal nuclear division, the chromatin is condensed into blocks and the texture is rough. In addition, this will also lead to an increase in the DNA content inside the nucleus. The above-mentioned abnormal characteristics of cervical cell nuclei provide a pathological basis for the computer to identify abnormal cervical cells based on cervical cell nuclei. [0003] At present, many studies are based on the characteristics of cervical cell nucleus and cytoplasm to identify abnormal cervical cells, which can be roughly divided into two methods....

AI Technical Summary

Problems solved by technology

However, in many studies on automatic identification of abnormal cervical cells, no researchers have used the characteristics of nuclear DNA content for automatic identification of abnormal cervical cells.

Images