Deep fusion model applied to mammary gland X-ray image anomaly recognition and classification method thereof

Abstract

The invention discloses a deep fusion model applied to mammary gland X-ray image anomaly recognition and a classification method of the deep fusion model, and relates to the technical field of image processing methods.The method comprises the steps that a mammary gland X-ray image is preprocessed to remove noise and improve image quality; collecting regions of interest (ROI) of abnormal tissue image categories (i.e. Benign and malignant), and extracting the ROI from random positions of normal tissue image categories; randomly extracting a smaller ROI sub-block image from the ROI image; constructing a depth fusion model, and training the depth fusion model by adopting the ROI sub-block images; finishing classification of each ROI image by using majority voting; according to the method, thedepth information of all the five pre-trained VGG16 blocks is fused, so that the information between different channels of each module is highly correlated, a 1 * 1 convolution layer integrates cross-channel information and further realizes dimensionality reduction, and model parameters can be effectively reduced, so that the performance of the model is improved.

Description

technical field [0001] The invention relates to the technical field of image processing methods, in particular to a deep fusion model applied to abnormal recognition of mammogram images and a classification method thereof. Background technique [0002] Breast cancer is one of the most common types of cancer in women. Early detection and treatment can effectively increase the cure rate and reduce mortality, and early diagnosis and treatment can increase the cure rate of breast cancer from 40% to 90%. Detecting breast cancer using mammogram images is an efficient and low-cost technique, and radiologists can analyze these images to make a diagnosis. However, the detection of a large number of mammograms generated every day has brought a huge workload to radiologists, and misdiagnosis may occur. Therefore, developing a computer-aided diagnosis (CAD) system can effectively reduce the pressure on radiologists and improve diagnostic accuracy. CAD can help radiologists differenti...

AI Technical Summary

Problems solved by technology

[0007] (3) Based on pre-trained deep learning models, such as VGG16 and other models, it does not fully cover the "granularity" of depth information at different levels of deep learning models and mine cross-channel information between different channels of each module

Images