X-ray mammary gland image deep learning classification method

Abstract

The invention discloses an X-ray breast mass image automatic classification method. According to the invention, an automatic classification network for the X-ray breast mass image is designed from theperspective of image processing; according to the network, firstly, two computing paths are used for carrying out convolution and downsampling operation on an X-ray breast mass image by using convolution kernels of different sizes, convolution feature maps of different scale types are extracted, the feature maps input by the two computing paths are superposed and fused, and feature information obtained after double computing paths are fused is obtained. Feature extraction is carried out on the fusion features by using a full convolutional network, and finally the extracted features are sent to a Softmax classification layer to classify the features, and a breast mass image classification result is obtained. A model is trained by using a membership-based objective function suitable for X-ray breast mass image classification, and a new objective function enhances the generalization ability of the model by increasing the membership degree of a breast mass sample and a category to which the breast mass sample belongs and reducing the membership degree of the breast mass sample and a non-category to which the breast mass sample belongs, so that the classification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a deep learning classification method for X-ray breast images. Background technique [0002] According to GLOBOCAN statistics, there are approximately 12 million new cancer patients and approximately 8.2 million cancer deaths worldwide each year. Cancer poses a great burden to society, especially in developing countries, where cancer has a more serious impact on personal life and quality of life. Breast cancer is one of the most important malignant tumors threatening women's life and health. Mammography examination, because of its low cost, less harm to patients, simplicity and high resolution, meets medical requirements, has become the mainstream examination method for breast cancer. X-ray breast imaging provides rich and intuitive lesion information for breast cancer diagnosis, which is convenient for doctors to examine and analyze patients to determine patient sympt...

AI Technical Summary

Problems solved by technology

[0003] The texture of the mass in the breast image is highly similar to other human tissues such as muscles and glands; the edge of the breast mass is blurred and has a low degree of discrimination from the background; the color changes of the breast image are concentrated in a narrow area, which is extracted by convolution operation The feature similarity is high and it is difficult to distinguish. These factors increase the difficulty of breast mass image feature extraction

Using CNN to extract features from breast images, due to the small changes in the outline, texture, and shape of breast masses, if too many convolution operations are used on breast images, image features will be over-extracted and the quality of image features will be reduced

Images