Computer-aided detection and diagnosis system for breast micro-calcification

By acquiring and analyzing breast X-ray images from different projection angles, and utilizing cross-view pairing and feature fusion techniques, the problems of high false positive and high false negative rates in single-view systems have been solved, achieving more efficient detection and diagnosis of breast microcalcifications.

CN122368575APending Publication Date: 2026-07-10THE FIRST HOSPITAL OF HEBEI MEDICAL UNIV
0 Cites 0 Cited by

Patent Information

Application Number
CN202610355298.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-23
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing single-view computer-aided detection systems have difficulty effectively distinguishing real microcalcifications from image noise or artifacts in mammograms, resulting in high false positive or false negative rates and making it difficult to balance sensitivity and specificity.

Method used

Digital mammograms of the same breast tissue from at least two different projection angles are acquired. Cross-view pairing and correlation are used to extract cross-view consistency features and fuse enhanced feature vectors for malignant or benign classification.

Benefits of technology

By using cross-view matching and feature fusion, the false positive rate is significantly reduced, the specificity and accuracy of the detection results are improved, and the detection efficiency and diagnostic confidence of early breast cancer are enhanced.

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

Abstract

The invention provides a computer-aided detection and diagnosis system for breast micro-calcification. The computer-aided detection and diagnosis system comprises an acquisition unit, a processing unit and a control unit, wherein the acquisition unit is used for acquiring at least two breast X-ray images of the same breast tissue at different projection angles as a target view group; the region detection unit is used for performing suspected micro-calcification candidate region detection on each single view to obtain a candidate region set corresponding to each single view; performing cross-view pairing association on candidate areas from different views based on a geometric projection relationship among the different views in the target view group to establish candidate area pairs representing image representation of the same potential micro-calcification at different projection angles; the extraction module is used for extracting the cross-view consistency feature of each candidate region pair, and the calculation unit is used for fusing the cross-view consistency feature corresponding to each candidate region pair and the internal image feature of each candidate region pair in each single view to form an enhanced feature vector of the potential micro-calcification; and obtaining a benign or malignant classification result of the corresponding potential micro-calcification.
Need to check novelty before this filing date? Find Prior Art