Cell classification method and device, computer equipment and storage medium

Abstract

The invention relates to a cell classification method and device, computer equipment and a storage medium. The method comprises the following steps: inputting the to-be-analyzed image into a pre-trained target detection model, obtaining position information and initial classification information of each target cell in the to-be-analyzed image; segmenting a to-be-analyzed image according to the position information; and obtaining a plurality of target cell images, inputting the target cell images into a classification model containing an expanded convolutional network to obtain secondary classification information of the target cells corresponding to the target cell images, and when the initial classification information is the same as the secondary classification information, marking the secondary classification information as a classification result of the target cells. On one hand, accurate positioning and primary classification of target cells are realized through a target detectionmodel. On the other hand, the single target cell image is classified and analyzed through the classification model. An accurate classification result is obtained, through mutual verification of two times of classification, rapid positioning and accurate classification of the target cell are improved, and the working efficiency of a doctor is improved.

Description

technical field [0001] The present application relates to the technical field of medical image processing, in particular to a cell classification method, device, computer equipment and storage medium. Background technique [0002] With the development of medical technology, the identification of various cells in pathological slice images plays an important role in medical treatment. In recent years, many medical research teams at home and abroad have begun to study the identification of various types of cells in pleural effusion. There are many causes of pleural effusion, which can be summarized into two categories: one is the disease caused by inflammation, such as: infectious inflammation caused by infection of the pleura by viruses, fungi, bacteria, etc., which leads to pleural effusion, or due to pulmonary Pleural effusions caused by non-infectious diseases such as embolism and connective tissue diseases are called non-malignant diseased cells in the pleural cavity. The...

AI Technical Summary

Problems solved by technology

[0003] However, under normal circumstances, there are a large number of diseased cells in each pathological slice image, with various cell types, complex cell structures, and diverse cell shapes. Every time, the doctor needs to extract the type and location of the diseased cells from the pathological slice image. Marking out one by one, on the one hand, will undoubtedly increase the repetition of doctors' daily work, on the other hand, the identification and classification of diseased cells depends on the professional skills of doctors, which leads to low efficiency in the analysis and processing of pathological slice images

Images