Multi-mode ultrasonic image classification method and breast cancer diagnosis device

Abstract

The invention provides a multi-mode ultrasonic image classification method and a breast cancer diagnosis device, and the method comprises the steps: S1, segmenting a region-of-interest image from an original gray-scale ultrasonic-elastic imaging image pair, and obtaining a pure elastic imaging image according to the segmented region-of-interest image; s2, extracting single-mode image features of the gray-scale ultrasonic image and the elastic imaging image by using a DenseNet network; s3, constructing a resistance loss function and an orthogonality constraint function, and extracting shared features between the gray-scale ultrasonic image and the elastic imaging image; and S4, constructing a multi-task learning framework, splicing the inter-modal shared features obtained in the S3 and thesingle-modal features obtained in the S2, inputting the inter-modal shared features and the single-modal features into a plurality of classifiers together, and performing benign and malignant classification respectively. According to the method, benign and malignant classification can be carried out on the gray-scale ultrasonic image, the elastic imaging image and the two modal images at the sametime, and the method has excellent performance of high accuracy and wide application range.

Description

technical field [0001] The invention relates to an image processing method, in particular to a multimodal ultrasonic image classification method and a breast cancer diagnosis device using the method. Background technique [0002] Cancer, because of its high morbidity and mortality, is considered to be the number one "killer" that threatens human health and safety. For example, breast cancer is currently the malignant tumor with the highest morbidity and mortality among women worldwide. In China, breast cancer also ranks first in the incidence of female malignant tumors in the country, and the fifth in mortality, and the incidence and mortality are increasing year by year. The situation of prevention and treatment of female breast cancer in China is very serious. Regular breast examination is the most effective way of "early detection and early treatment" of breast cancer. At present, in China, breast ultrasonography has become the preferred screening method for breast dis...

AI Technical Summary

Problems solved by technology

[0005] In summary, the existing CAD system for breast cancer diagnosis still stays in the more traditional deep learning network structure in terms of feature extraction, and the extracted features are different in benign and malignant There are certain deficiencies in the resolution

Moreover, the existing methods are only based on a certain ultrasonic modality, ignoring the complementary information between the two modalities, and degrading the classification accuracy.

Images