A Mask-RCNN-based cervical cell smear image segmentation method and system

Abstract

The invention relates to a Mask-RCNN-based cervical cell smear image segmentation method and system, and the method comprises a data set construction step of carrying out the preparation and labelingof a training data set, a verification data set and a test data set, and carrying out the normalization and preprocessing of the data set; b, constructing and training a model, constructing an image segmentation model based on Mask-RCNN, training the model by using the training data set, and verifying an image segmentation result of the model by using the verification data set; and a model verification step of testing the model by using the test data set, and evaluating a segmentation result by using a similarity coefficient. According to the method, the deep neural network model trained by utilizing a large amount of data can be used for modeling and abstracting information contained in the large amount of data, so that the cells and the cell nuclei in the cervical cytology smear image can be positioned, detected and subjected to the instance segmentation through a single model.

Description

technical field [0001] The present invention relates to the technical fields of computer vision and image processing, in particular to a method and system for image segmentation of cervical cell smears based on Mask-RCNN Background technique [0002] Worldwide, cervical cancer is the fourth most common cause of cancer death in women. Early detection of the disease and timely treatment can greatly improve the cure rate. Therefore, early diagnosis of cervical cancer is of great significance to women's health. The most commonly used diagnostic method in modern times is the Pap smear test. [0003] Pap smear (Pap Test) is a cervical cytology diagnostic method, commonly used to check for diseases such as cervical cancer. With the development of medical digitalization, modern hospitals have gradually abandoned the traditional method of directly observing and diagnosing Pap smears under a microscope, and replaced them by checking Pap smear images on a computer. The check steps ...

AI Technical Summary

Problems solved by technology

Therefore, it is difficult to segment overlapping cells based on pixel clustering methods; it is difficult to accurately segment a single naked nucleus based on the results of cell segmentation to locate nuclei; and there are few pictures of single cells or clusters of cells in clinical practice.

Among the existing solutions, there is no single model or process solution that can simultaneously solve the positioning, classification and segmentation of cells and nuclei in cervical cell images

In addition, the above-mentioned cell segmentation methods and models based on image processing rely more on the designer's extraction of cell features in cervical cytology smear images, and it is difficult to model and abstractly express the semantic information of cells and nuclei

Images