Method, device and equipment for differentiating benign and malignant breast calcification

By processing breast calcification image data using generative adversarial networks and target segmentation models, synthetic samples are generated and calcification foci regions are segmented. Deep learning and radiomics features are extracted and fused, solving the problem of accuracy and reliability in differentiating between benign and malignant breast calcifications and improving the effectiveness of early breast cancer screening.

CN122510149APending Publication Date: 2026-08-04PEKING UNIVERSITY THIRD HOSPITAL (THE THIRD CLINICAL MEDICAL SCHOOL OF PEKING UNIVERSITY) +1
0 Cites 0 Cited by

Patent Information

Application Number
CN202610385082.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2026-01-07
Filing Date
2026-03-26
Publication Date
2026-08-04

AI Technical Summary

Technical Problem

In current technologies, the differentiation between benign and malignant breast calcifications relies heavily on the experience of radiologists, resulting in problems such as large differences in diagnostic results, low efficiency, and a high rate of missed diagnoses of microcalcifications. Furthermore, traditional methods lack quantitative interpretation, which affects the accuracy of early breast cancer screening.

Method used

Generative adversarial networks were used to augment medical image data, generating synthetic samples that conform to pathological characteristics. Calcification lesion regions were segmented using a target segmentation model. Deep learning features and radiomics features were extracted and fused to determine the benign or malignant differentiation of breast calcifications.

Benefits of technology

It significantly improves the accuracy and interpretability of early breast cancer screening, provides reliable support for clinical diagnosis, and enhances the accuracy and reliability of differentiating between benign and malignant calcifications.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

Embodiments of the present application provide a breast calcification benign and malignant differentiation method, device and equipment. The method comprises: performing data enhancement processing on medical image data through a generative adversarial network to obtain enhanced medical image data, wherein the medical image data comprises breast X-ray image data; performing calcification focus region segmentation on the enhanced medical image data through a target segmentation model to obtain a segmentation mask; extracting deep learning features and imageomic features in the segmentation mask, and performing feature fusion processing on the deep learning features and the imageomic features to obtain a fusion feature vector; and determining a breast calcification benign and malignant differentiation result corresponding to the medical image data based on the fusion feature vector. The method is used to improve the accuracy and reliability of breast calcification benign and malignant differentiation, and provides a more effective reference basis for the diagnosis and treatment of breast diseases.
Need to check novelty before this filing date? Find Prior Art