Breast ultrasound video HER2 expression state recognition method based on space-time feature interaction

By preprocessing breast ultrasound videos and constructing a feature interaction method based on the UniFormerV2 network, the problem of ignoring temporal dynamic information in existing technologies is solved, and accurate three-classification prediction of HER2 expression status is achieved, especially the identification of the HER2-Low subtype.

CN122067164BActive Publication Date: 2026-06-19QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES) +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202610534066.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-22
Publication Date
2026-06-19
Estimated Expiration
2046-04-22

AI Technical Summary

Technical Problem

Existing technologies simplify breast ultrasound videos into static image processing, ignoring the temporal dynamic information in the video, making it difficult to accurately identify the HER2-Low subtype, and are limited to binary classification tasks, which cannot meet clinical needs.

Method used

A method based on the UniFormerV2 network is adopted to preprocess ultrasound videos through inter-frame registration, denoising, and contrast enhancement. By combining local and global feature interaction mechanisms, a multi-stage feature fusion module is constructed to achieve three-class classification prediction of HER2 expression status.

Benefits of technology

It achieves non-invasive and accurate prediction of HER2 expression status, breaks through the limitations of existing methods in spatiotemporal multi-scale feature modeling, significantly improves the identification ability of HER2-Low subtype, and solves the class imbalance problem.

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

Abstract

This invention belongs to the technical field of breast cancer molecular subtyping, and more specifically, relates to a method for identifying HER2 expression status in breast ultrasound videos based on spatiotemporal feature interaction. The method includes: using raw breast ultrasound videos as input data and performing multi-level data preprocessing operations; then performing data balancing on the training data to obtain a standardized training set; sequentially constructing a feature module, a multi-stage feature fusion module, and a classification module based on the UniFormerV2 network, and training the resulting model; and inputting the test set into the model to obtain the final prediction result of HER2 expression status. This invention solves the problems of existing HER2 detection methods being invasive and unable to dynamically monitor, and existing deep learning methods based on static images ignoring the spatiotemporal dynamic information in ultrasound videos, leading to insufficient accuracy in predicting HER2 expression status, especially the HER2-Low subtype.
Need to check novelty before this filing date? Find Prior Art