Sample data processing method for cervix uteri image

Abstract

The invention discloses a sample data processing method for a cervix uteri image. The method comprises the following steps: classifying and establishing; preprocessing the data; performing segmentation; data enhancement: classifying the target image data, determining differences among the target image data, and performing enhancement processing for the differences; equalization processing: aimingat the total quantity difference among various target image data, supplementing a few types of samples by adopting data fitting to realize total quantity balance among the various target image data; constructing a data set: for each type of target image data after equalization processing, randomly dividing the target image data into a training data set, a verification data set and a test data setin proportion; and model construction: on the basis of the training data set and / or the verification data set and / or the test data set, mapping the training data set and / or the verification data set and / or the test data set to a contrast data set to obtain a classification corresponding to the sample data. According to the method, the problem of data imbalance in cervical image data classificationis solved, the precision and efficiency of image classification are improved, and the effect and quality of auxiliary diagnosis are improved.

Description

technical field [0001] The invention belongs to a computer-aided application method in the medical field, and in particular relates to a sample data processing method of a cervical image. Background technique [0002] Since the cause of cervical lesions is clear, it can be prevented clinically. Therefore, the high fatality rate of cervical cancer can be alleviated to a great extent. However, because my country is still a developing country with a high population density, it is still difficult to fully promote HPV vaccines. Therefore, screening for early cervical lesions is still the main measure and method for the prevention and treatment of cervical related diseases. At present, the main methods for screening cervical lesions in major hospitals include Pap smear method (Pap test), liquid-based cytology test (TCT), HPV-DNA detection, electronic colposcopy observation method and histopathological detection. However, the mainstream screening methods for precancerous lesions...

AI Technical Summary

Problems solved by technology

The present invention first uses the electronic colposcope to collect color images of cervical regions from different patients, and obtains available patient image data through data cleaning; then performs a series of image filtering, image segmentation (ROI extraction), image enhancement, etc. on the collected images Preprocessing operation; in view of the problem of data imbalance and small amount of data in the lesions to be classified, the SMOTE algorithm and data enhancement are used to perform balanced processing; the processed image data is sent to the deep learning model for learning and training, and finally Get normal, inflammation, cervical intraepithelial neoplasia grade I (CIN I), cervical intraepithelial neoplasia grade II (CIN II), cervical intraepithelial neoplasia grade III (CIN III), cancerous six classification results

Images