Female reproductive tract cytopathology intelligent classification method, diagnostic apparatus and storage medium

Abstract

The invention discloses a female reproductive tract cell pathological intelligent classification method, which is implemented on the basis of a convolutional neural network, and which specifically comprises the following steps: constructing a female reproductive tract cell intelligent classification convolution neural network model; obtaining training samples, which are images of multiple kinds offemale reproductive tract cells; labeling the target cells in the images of all female reproductive tract cells; pre-processing the tagged image of female reproductive tract cells; inputting the pre-processed images of female reproductive tract cells into the intelligent classification and convolutional neural network model, inputting the images of female reproductive tract cells to be detected into the intelligent classification and the convolutional neural network model of female reproductive tract cells after training, and obtaining the classification and judgment results. The invention can realize the yin and yang judgment of various cells of female reproductive tract and the classification of specific pathological changes of positive female reproductive tract cells, realize automaticidentification and classification, and achieve the purpose of intelligent diagnosis.

Description

technical field [0001] The invention relates to the technical field of cell image processing, in particular to an intelligent classification method for female reproductive tract cell pathology, a diagnostic instrument and a storage medium. Background technique [0002] Pathology is known as the "foundation of medicine" and the "gold standard" of medical diagnosis; the fundamental task of pathologists is to make a final diagnosis of the disease, discover and explore new diseases, and provide clinicians with a basis for treatment and prevention . [0003] However, diagnosis by pathologists alone has the following deficiencies: (1) Although pathological diagnosis is the "gold standard" of medical diagnosis, the gold content of pathological diagnosis is different due to the different qualifications, levels and cognitive abilities of pathologists. Manual diagnosis is highly subjective, lacks quality control, and the accuracy rate of pathological diagnosis varies greatly; (2) The...

AI Technical Summary

Problems solved by technology

[0003] However, diagnosis by pathologists alone has the following deficiencies: (1) Although pathological diagnosis is the "gold standard" of medical diagnosis, the gold content of pathological diagnosis is different due to the different qualifications, levels and cognitive abilities of pathologists. Manual diagnosis is highly subjective, lacks quality control, and the accuracy rate of pathological diagnosis varies greatly; (2) The ratio of waiting cases to diagnosing pathologists is seriously out of balance, and pathologists usually need to work overloaded day and night, which affects the physical and mental health of pathologists; (3) The time for screening, diagnosis and diagnosis is too long, and the diagnosis report cannot be issued accurately and in time

Images